diff options
474 files changed, 15170 insertions, 10172 deletions
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt index 45932ec21ce..b41f3e58aef 100644 --- a/Documentation/cputopology.txt +++ b/Documentation/cputopology.txt @@ -18,11 +18,11 @@ For an architecture to support this feature, it must define some of these macros in include/asm-XXX/topology.h: #define topology_physical_package_id(cpu) #define topology_core_id(cpu) -#define topology_thread_siblings(cpu) -#define topology_core_siblings(cpu) +#define topology_thread_cpumask(cpu) +#define topology_core_cpumask(cpu) The type of **_id is int. -The type of siblings is cpumask_t. +The type of siblings is (const) struct cpumask *. To be consistent on all architectures, include/linux/topology.h provides default definitions for any of the above macros that are diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt index d73fbd2b2b4..026ec7d5738 100644 --- a/Documentation/kernel-doc-nano-HOWTO.txt +++ b/Documentation/kernel-doc-nano-HOWTO.txt @@ -43,7 +43,8 @@ Only comments so marked will be considered by the kernel-doc scripts, and any comment so marked must be in kernel-doc format. Do not use "/**" to be begin a comment block unless the comment block contains kernel-doc formatted comments. The closing comment marker for -kernel-doc comments can be either "*/" or "**/". +kernel-doc comments can be either "*/" or "**/", but "*/" is +preferred in the Linux kernel tree. Kernel-doc comments should be placed just before the function or data structure being described. @@ -63,7 +64,7 @@ Example kernel-doc function comment: * comment lines. * * The longer description can have multiple paragraphs. - **/ + */ The first line, with the short description, must be on a single line. @@ -85,7 +86,7 @@ Example kernel-doc data structure comment. * perhaps with more lines and words. * * Longer description of this structure. - **/ + */ The kernel-doc function comments describe each parameter to the function, in order, with the @name lines. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index d8362cf9909..b182626739e 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -937,6 +937,8 @@ and is between 256 and 4096 characters. It is defined in the file intel_iommu= [DMAR] Intel IOMMU driver (DMAR) option + on + Enable intel iommu driver. off Disable intel iommu driver. igfx_off [Default Off] diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 7b4596ac412..12299697b7c 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -158,7 +158,7 @@ Offset Proto Name Meaning 0202/4 2.00+ header Magic signature "HdrS" 0206/2 2.00+ version Boot protocol version supported 0208/4 2.00+ realmode_swtch Boot loader hook (see below) -020C/2 2.00+ start_sys The load-low segment (0x1000) (obsolete) +020C/2 2.00+ start_sys_seg The load-low segment (0x1000) (obsolete) 020E/2 2.00+ kernel_version Pointer to kernel version string 0210/1 2.00+ type_of_loader Boot loader identifier 0211/1 2.00+ loadflags Boot protocol option flags @@ -170,10 +170,11 @@ Offset Proto Name Meaning 0224/2 2.01+ heap_end_ptr Free memory after setup end 0226/2 N/A pad1 Unused 0228/4 2.02+ cmd_line_ptr 32-bit pointer to the kernel command line -022C/4 2.03+ initrd_addr_max Highest legal initrd address +022C/4 2.03+ ramdisk_max Highest legal initrd address 0230/4 2.05+ kernel_alignment Physical addr alignment required for kernel 0234/1 2.05+ relocatable_kernel Whether kernel is relocatable or not -0235/3 N/A pad2 Unused +0235/1 N/A pad2 Unused +0236/2 N/A pad3 Unused 0238/4 2.06+ cmdline_size Maximum size of the kernel command line 023C/4 2.07+ hardware_subarch Hardware subarchitecture 0240/8 2.07+ hardware_subarch_data Subarchitecture-specific data @@ -299,14 +300,14 @@ Protocol: 2.00+ e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version 10.17. -Field name: readmode_swtch +Field name: realmode_swtch Type: modify (optional) Offset/size: 0x208/4 Protocol: 2.00+ Boot loader hook (see ADVANCED BOOT LOADER HOOKS below.) -Field name: start_sys +Field name: start_sys_seg Type: read Offset/size: 0x20c/2 Protocol: 2.00+ @@ -468,7 +469,7 @@ Protocol: 2.02+ zero, the kernel will assume that your boot loader does not support the 2.02+ protocol. -Field name: initrd_addr_max +Field name: ramdisk_max Type: read Offset/size: 0x22c/4 Protocol: 2.03+ diff --git a/MAINTAINERS b/MAINTAINERS index 0ea3a6d9871..db65b4e6d13 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1202,6 +1202,8 @@ S: Supported CONTROL GROUPS (CGROUPS) P: Paul Menage M: menage@google.com +P: Li Zefan +M: lizf@cn.fujitsu.com L: containers@lists.linux-foundation.org S: Maintained @@ -3537,6 +3539,12 @@ S: Maintained PXA MMCI DRIVER S: Orphan +PXA RTC DRIVER +P: Robert Jarzmik +M: robert.jarzmik@free.fr +L: rtc-linux@googlegroups.com +S: Maintained + QLOGIC QLA2XXX FC-SCSI DRIVER P: Andrew Vasquez M: linux-driver@qlogic.com @@ -4285,8 +4293,8 @@ P: Rajiv Andrade M: srajiv@linux.vnet.ibm.com W: http://tpmdd.sourceforge.net P: Marcel Selhorst -M: tpm@selhorst.net -W: http://www.prosec.rub.de/tpm/ +M: m.selhorst@sirrix.com +W: http://www.sirrix.com L: tpmdd-devel@lists.sourceforge.net (moderated for non-subscribers) S: Maintained @@ -532,8 +532,9 @@ KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN}) endif # Force gcc to behave correct even for buggy distributions -# Arch Makefiles may override this setting +ifndef CONFIG_CC_STACKPROTECTOR KBUILD_CFLAGS += $(call cc-option, -fno-stack-protector) +endif ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 703731accda..7bc7489223f 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -55,7 +55,7 @@ int irq_select_affinity(unsigned int irq) cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0); last_cpu = cpu; - irq_desc[irq].affinity = cpumask_of_cpu(cpu); + cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu)); irq_desc[irq].chip->set_affinity(irq, cpumask_of(cpu)); return 0; } diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 363db186cb9..45eacb5a2ec 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -104,6 +104,11 @@ static struct irq_desc bad_irq_desc = { .lock = __SPIN_LOCK_UNLOCKED(bad_irq_desc.lock), }; +#ifdef CONFIG_CPUMASK_OFFSTACK +/* We are not allocating bad_irq_desc.affinity or .pending_mask */ +#error "ARM architecture does not support CONFIG_CPUMASK_OFFSTACK." +#endif + /* * do_IRQ handles all hardware IRQ's. Decoded IRQs should not * come via this function. Instead, they should provide their @@ -161,7 +166,7 @@ void __init init_IRQ(void) irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE; #ifdef CONFIG_SMP - bad_irq_desc.affinity = CPU_MASK_ALL; + cpumask_setall(bad_irq_desc.affinity); bad_irq_desc.cpu = smp_processor_id(); #endif init_arch_irq(); @@ -191,15 +196,16 @@ void migrate_irqs(void) struct irq_desc *desc = irq_desc + i; if (desc->cpu == cpu) { - unsigned int newcpu = any_online_cpu(desc->affinity); - - if (newcpu == NR_CPUS) { + unsigned int newcpu = cpumask_any_and(desc->affinity, + cpu_online_mask); + if (newcpu >= nr_cpu_ids) { if (printk_ratelimit()) printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n", i, cpu); - cpus_setall(desc->affinity); - newcpu = any_online_cpu(desc->affinity); + cpumask_setall(desc->affinity); + newcpu = cpumask_any_and(desc->affinity, + cpu_online_mask); } route_irq(desc, i, newcpu); diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 440dc62cdc3..598ca61e7bc 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -13,8 +13,8 @@ #include <asm/cacheflush.h> #include <asm/mach-types.h> -const extern unsigned char relocate_new_kernel[]; -const extern unsigned int relocate_new_kernel_size; +extern const unsigned char relocate_new_kernel[]; +extern const unsigned int relocate_new_kernel_size; extern void setup_mm_for_reboot(char mode); diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 00216071eaf..85598f7da40 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -65,6 +65,7 @@ SECTIONS #endif . = ALIGN(4096); __per_cpu_start = .; + *(.data.percpu.page_aligned) *(.data.percpu) *(.data.percpu.shared_aligned) __per_cpu_end = .; diff --git a/arch/arm/mach-pxa/dma.c b/arch/arm/mach-pxa/dma.c index b1514fb20d3..7de17fc5d54 100644 --- a/arch/arm/mach-pxa/dma.c +++ b/arch/arm/mach-pxa/dma.c @@ -121,20 +121,22 @@ int __init pxa_init_dma(int num_ch) if (dma_channels == NULL) return -ENOMEM; - ret = request_irq(IRQ_DMA, dma_irq_handler, IRQF_DISABLED, "DMA", NULL); - if (ret) { - printk (KERN_CRIT "Wow! Can't register IRQ for DMA\n"); - kfree(dma_channels); - return ret; - } - /* dma channel priorities on pxa2xx processors: * ch 0 - 3, 16 - 19 <--> (0) DMA_PRIO_HIGH * ch 4 - 7, 20 - 23 <--> (1) DMA_PRIO_MEDIUM * ch 8 - 15, 24 - 31 <--> (2) DMA_PRIO_LOW */ - for (i = 0; i < num_ch; i++) + for (i = 0; i < num_ch; i++) { + DCSR(i) = 0; dma_channels[i].prio = min((i & 0xf) >> 2, DMA_PRIO_LOW); + } + + ret = request_irq(IRQ_DMA, dma_irq_handler, IRQF_DISABLED, "DMA", NULL); + if (ret) { + printk (KERN_CRIT "Wow! Can't register IRQ for DMA\n"); + kfree(dma_channels); + return ret; + } num_dma_channels = num_ch; return 0; diff --git a/arch/arm/mach-pxa/include/mach/regs-ac97.h b/arch/arm/mach-pxa/include/mach/regs-ac97.h index e41b9d202b8..b8d14bd9ae5 100644 --- a/arch/arm/mach-pxa/include/mach/regs-ac97.h +++ b/arch/arm/mach-pxa/include/mach/regs-ac97.h @@ -1,6 +1,8 @@ #ifndef __ASM_ARCH_REGS_AC97_H #define __ASM_ARCH_REGS_AC97_H +#include <mach/hardware.h> + /* * AC97 Controller registers */ diff --git a/arch/arm/mach-pxa/include/mach/regs-ssp.h b/arch/arm/mach-pxa/include/mach/regs-ssp.h index 3c04cde2cf1..cf31986f6f0 100644 --- a/arch/arm/mach-pxa/include/mach/regs-ssp.h +++ b/arch/arm/mach-pxa/include/mach/regs-ssp.h @@ -41,6 +41,9 @@ #elif defined(CONFIG_PXA27x) || defined(CONFIG_PXA3xx) #define SSCR0_SCR (0x000fff00) /* Serial Clock Rate (mask) */ #define SSCR0_SerClkDiv(x) (((x) - 1) << 8) /* Divisor [1..4096] */ +#endif + +#if defined(CONFIG_PXA27x) || defined(CONFIG_PXA3xx) #define SSCR0_EDSS (1 << 20) /* Extended data size select */ #define SSCR0_NCS (1 << 21) /* Network clock select */ #define SSCR0_RIM (1 << 22) /* Receive FIFO overrrun interrupt mask */ diff --git a/arch/arm/mach-pxa/pxa300.c b/arch/arm/mach-pxa/pxa300.c index f735e58e666..83fb609b6eb 100644 --- a/arch/arm/mach-pxa/pxa300.c +++ b/arch/arm/mach-pxa/pxa300.c @@ -88,13 +88,13 @@ static struct pxa3xx_mfp_addr_map pxa310_mfp_addr_map[] __initdata = { static DEFINE_PXA3_CKEN(common_nand, NAND, 156000000, 0); static struct clk_lookup common_clkregs[] = { - INIT_CLKREG(&clk_common_nand, "pxa3xx-nand", "NANDCLK"), + INIT_CLKREG(&clk_common_nand, "pxa3xx-nand", NULL), }; static DEFINE_PXA3_CKEN(pxa310_mmc3, MMC3, 19500000, 0); static struct clk_lookup pxa310_clkregs[] = { - INIT_CLKREG(&clk_pxa310_mmc3, "pxa2xx-mci.2", "MMCCLK"), + INIT_CLKREG(&clk_pxa310_mmc3, "pxa2xx-mci.2", NULL), }; static int __init pxa300_init(void) diff --git a/arch/arm/mach-pxa/pxa320.c b/arch/arm/mach-pxa/pxa320.c index effe408c186..36f066196fa 100644 --- a/arch/arm/mach-pxa/pxa320.c +++ b/arch/arm/mach-pxa/pxa320.c @@ -83,7 +83,7 @@ static struct pxa3xx_mfp_addr_map pxa320_mfp_addr_map[] __initdata = { static DEFINE_PXA3_CKEN(pxa320_nand, NAND, 104000000, 0); static struct clk_lookup pxa320_clkregs[] = { - INIT_CLKREG(&clk_pxa320_nand, "pxa3xx-nand", "NANDCLK"), + INIT_CLKREG(&clk_pxa320_nand, "pxa3xx-nand", NULL), }; static int __init pxa320_init(void) diff --git a/arch/arm/oprofile/op_model_mpcore.c b/arch/arm/oprofile/op_model_mpcore.c index 6d6bd589924..853d42bb868 100644 --- a/arch/arm/oprofile/op_model_mpcore.c +++ b/arch/arm/oprofile/op_model_mpcore.c @@ -263,7 +263,7 @@ static void em_route_irq(int irq, unsigned int cpu) const struct cpumask *mask = cpumask_of(cpu); spin_lock_irq(&desc->lock); - desc->affinity = *mask; + cpumask_copy(desc->affinity, mask); desc->chip->set_affinity(irq, mask); spin_unlock_irq(&desc->lock); } diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c index 75724eee649..23e9aa08071 100644 --- a/arch/blackfin/kernel/irqchip.c +++ b/arch/blackfin/kernel/irqchip.c @@ -70,6 +70,11 @@ static struct irq_desc bad_irq_desc = { #endif }; +#ifdef CONFIG_CPUMASK_OFFSTACK +/* We are not allocating a variable-sized bad_irq_desc.affinity */ +#error "Blackfin architecture does not support CONFIG_CPUMASK_OFFSTACK." +#endif + int show_interrupts(struct seq_file *p, void *v) { int i = *(loff_t *) v, j; diff --git a/arch/frv/mm/dma-alloc.c b/arch/frv/mm/dma-alloc.c index dc6522c464d..44840e73e90 100644 --- a/arch/frv/mm/dma-alloc.c +++ b/arch/frv/mm/dma-alloc.c @@ -36,10 +36,10 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/pci.h> +#include <linux/hardirq.h> #include <asm/pgalloc.h> #include <asm/io.h> -#include <asm/hardirq.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> #include <asm/mmu.h> diff --git a/arch/ia64/include/asm/percpu.h b/arch/ia64/include/asm/percpu.h index 77f30b664b4..30cf46534dd 100644 --- a/arch/ia64/include/asm/percpu.h +++ b/arch/ia64/include/asm/percpu.h @@ -27,12 +27,12 @@ extern void *per_cpu_init(void); #else /* ! SMP */ -#define PER_CPU_ATTRIBUTES __attribute__((__section__(".data.percpu"))) - #define per_cpu_init() (__phys_per_cpu_start) #endif /* SMP */ +#define PER_CPU_BASE_SECTION ".data.percpu" + /* * Be extremely careful when taking the address of this variable! Due to virtual * remapping, it is different from the canonical address returned by __get_cpu_var(var)! diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 32f3af1641c..3193f4417e1 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -84,7 +84,7 @@ void build_cpu_to_node_map(void); .child = NULL, \ .groups = NULL, \ .min_interval = 8, \ - .max_interval = 8*(min(num_online_cpus(), 32)), \ + .max_interval = 8*(min(num_online_cpus(), 32U)), \ .busy_factor = 64, \ .imbalance_pct = 125, \ .cache_nice_tries = 2, \ diff --git a/arch/ia64/include/asm/uv/uv.h b/arch/ia64/include/asm/uv/uv.h new file mode 100644 index 00000000000..61b5bdfd980 --- /dev/null +++ b/arch/ia64/include/asm/uv/uv.h @@ -0,0 +1,13 @@ +#ifndef _ASM_IA64_UV_UV_H +#define _ASM_IA64_UV_UV_H + +#include <asm/system.h> +#include <asm/sn/simulator.h> + +static inline int is_uv_system(void) +{ + /* temporary support for running on hardware simulator */ + return IS_MEDUSA() || ia64_platform_is("uv"); +} + +#endif /* _ASM_IA64_UV_UV_H */ diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index 5cfd3d91001..006ad366a45 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -880,7 +880,7 @@ iosapic_unregister_intr (unsigned int gsi) if (iosapic_intr_info[irq].count == 0) { #ifdef CONFIG_SMP /* Clear affinity */ - cpus_setall(idesc->affinity); + cpumask_setall(idesc->affinity); #endif /* Clear the interrupt information */ iosapic_intr_info[irq].dest = 0; diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index a58f64ca9f0..226233a6fa1 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -103,7 +103,7 @@ static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 }; void set_irq_affinity_info (unsigned int irq, int hwid, int redir) { if (irq < NR_IRQS) { - cpumask_copy(&irq_desc[irq].affinity, + cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu_logical_id(hwid))); irq_redir[irq] = (char) (redir & 0xff); } @@ -148,7 +148,7 @@ static void migrate_irqs(void) if (desc->status == IRQ_PER_CPU) continue; - if (cpumask_any_and(&irq_desc[irq].affinity, cpu_online_mask) + if (cpumask_any_and(irq_desc[irq].affinity, cpu_online_mask) >= nr_cpu_ids) { /* * Save it for phase 2 processing diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 28d3d483db9..927ad027820 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -493,11 +493,13 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs) saved_tpr = ia64_getreg(_IA64_REG_CR_TPR); ia64_srlz_d(); while (vector != IA64_SPURIOUS_INT_VECTOR) { + struct irq_desc *desc = irq_to_desc(vector); + if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) { smp_local_flush_tlb(); - kstat_this_cpu.irqs[vector]++; + kstat_incr_irqs_this_cpu(vector, desc); } else if (unlikely(IS_RESCHEDULE(vector))) - kstat_this_cpu.irqs[vector]++; + kstat_incr_irqs_this_cpu(vector, desc); else { int irq = local_vector_to_irq(vector); @@ -551,11 +553,13 @@ void ia64_process_pending_intr(void) * Perform normal interrupt style processing */ while (vector != IA64_SPURIOUS_INT_VECTOR) { + struct irq_desc *desc = irq_to_desc(vector); + if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) { smp_local_flush_tlb(); - kstat_this_cpu.irqs[vector]++; + kstat_incr_irqs_this_cpu(vector, desc); } else if (unlikely(IS_RESCHEDULE(vector))) - kstat_this_cpu.irqs[vector]++; + kstat_incr_irqs_this_cpu(vector, desc); else { struct pt_regs *old_regs = set_irq_regs(NULL); int irq = local_vector_to_irq(vector); diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c index 89033933903..dcb6b7c51ea 100644 --- a/arch/ia64/kernel/msi_ia64.c +++ b/arch/ia64/kernel/msi_ia64.c @@ -75,7 +75,7 @@ static void ia64_set_msi_irq_affinity(unsigned int irq, msg.data = data; write_msi_msg(irq, &msg); - irq_desc[irq].affinity = cpumask_of_cpu(cpu); + cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu)); } #endif /* CONFIG_SMP */ @@ -187,7 +187,7 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask) msg.address_lo |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu)); dmar_msi_write(irq, &msg); - irq_desc[irq].affinity = *mask; + cpumask_copy(irq_desc[irq].affinity, mask); } #endif /* CONFIG_SMP */ diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index 10a7d47e851..f45e4e508ec 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -219,6 +219,7 @@ SECTIONS .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET) { __per_cpu_start = .; + *(.data.percpu.page_aligned) *(.data.percpu) *(.data.percpu.shared_aligned) __per_cpu_end = .; diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c index ca553b0429c..81e428943d7 100644 --- a/arch/ia64/sn/kernel/msi_sn.c +++ b/arch/ia64/sn/kernel/msi_sn.c @@ -205,7 +205,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq, msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff); write_msi_msg(irq, &msg); - irq_desc[irq].affinity = *cpu_mask; + cpumask_copy(irq_desc[irq].affinity, cpu_mask); } #endif /* CONFIG_SMP */ diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index abc62aa744a..3214ade02d1 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -66,7 +66,7 @@ extern void smtc_forward_irq(unsigned int irq); */ #define IRQ_AFFINITY_HOOK(irq) \ do { \ - if (!cpu_isset(smp_processor_id(), irq_desc[irq].affinity)) { \ + if (!cpumask_test_cpu(smp_processor_id(), irq_desc[irq].affinity)) {\ smtc_forward_irq(irq); \ irq_exit(); \ return; \ diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 1a1f320c30d..0884947ebe2 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -51,6 +51,7 @@ static inline int __raw_spin_is_contended(raw_spinlock_t *lock) return (((counters >> 14) - counters) & 0x1fff) > 1; } +#define __raw_spin_is_contended __raw_spin_is_contended static inline void __raw_spin_lock(raw_spinlock_t *lock) { diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index 494a49a317e..87deb8f6c45 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -187,7 +187,7 @@ static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask); } - irq_desc[irq].affinity = *cpumask; + cpumask_copy(irq_desc[irq].affinity, cpumask); spin_unlock_irqrestore(&gic_lock, flags); } diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index b6cca01ff82..5f5af7d4c89 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -686,7 +686,7 @@ void smtc_forward_irq(unsigned int irq) * and efficiency, we just pick the easiest one to find. */ - target = first_cpu(irq_desc[irq].affinity); + target = cpumask_first(irq_desc[irq].affinity); /* * We depend on the platform code to have correctly processed @@ -921,11 +921,13 @@ void ipi_decode(struct smtc_ipi *pipi) struct clock_event_device *cd; void *arg_copy = pipi->arg; int type_copy = pipi->type; + int irq = MIPS_CPU_IRQ_BASE + 1; + smtc_ipi_nq(&freeIPIq, pipi); switch (type_copy) { case SMTC_CLOCK_TICK: irq_enter(); - kstat_this_cpu.irqs[MIPS_CPU_IRQ_BASE + 1]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); cd = &per_cpu(mips_clockevent_device, cpu); cd->event_handler(cd); irq_exit(); diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c index aabd7274507..5ba31888fef 100644 --- a/arch/mips/mti-malta/malta-smtc.c +++ b/arch/mips/mti-malta/malta-smtc.c @@ -116,7 +116,7 @@ struct plat_smp_ops msmtc_smp_ops = { void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) { - cpumask_t tmask = *affinity; + cpumask_t tmask; int cpu = 0; void smtc_set_irq_affinity(unsigned int irq, cpumask_t aff); @@ -139,11 +139,12 @@ void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) * be made to forward to an offline "CPU". */ + cpumask_copy(&tmask, affinity); for_each_cpu(cpu, affinity) { if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu)) cpu_clear(cpu, tmask); } - irq_desc[irq].affinity = tmask; + cpumask_copy(irq_desc[irq].affinity, &tmask); if (cpus_empty(tmask)) /* diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c index f8b18af141a..0ecd5fe9486 100644 --- a/arch/mips/sgi-ip22/ip22-int.c +++ b/arch/mips/sgi-ip22/ip22-int.c @@ -155,7 +155,7 @@ static void indy_buserror_irq(void) int irq = SGI_BUSERR_IRQ; irq_enter(); - kstat_this_cpu.irqs[irq]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); ip22_be_interrupt(irq); irq_exit(); } diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c index 3dcb27ec0c5..c8f7d2328b2 100644 --- a/arch/mips/sgi-ip22/ip22-time.c +++ b/arch/mips/sgi-ip22/ip22-time.c @@ -122,7 +122,7 @@ void indy_8254timer_irq(void) char c; irq_enter(); - kstat_this_cpu.irqs[irq]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); printk(KERN_ALERT "Oops, got 8254 interrupt.\n"); ArcRead(0, &c, 1, &cnt); ArcEnterInteractiveMode(); diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c index dddfda8e829..314691648c9 100644 --- a/arch/mips/sibyte/bcm1480/smp.c +++ b/arch/mips/sibyte/bcm1480/smp.c @@ -178,9 +178,10 @@ struct plat_smp_ops bcm1480_smp_ops = { void bcm1480_mailbox_interrupt(void) { int cpu = smp_processor_id(); + int irq = K_BCM1480_INT_MBOX_0_0; unsigned int action; - kstat_this_cpu.irqs[K_BCM1480_INT_MBOX_0_0]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); /* Load the mailbox register to figure out what we're supposed to do */ action = (__raw_readq(mailbox_0_regs[cpu]) >> 48) & 0xffff; diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c index 5950a288a7d..cad14003b84 100644 --- a/arch/mips/sibyte/sb1250/smp.c +++ b/arch/mips/sibyte/sb1250/smp.c @@ -166,9 +166,10 @@ struct plat_smp_ops sb_smp_ops = { void sb1250_mailbox_interrupt(void) { int cpu = smp_processor_id(); + int irq = K_INT_MBOX_0; unsigned int action; - kstat_this_cpu.irqs[K_INT_MBOX_0]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); /* Load the mailbox register to figure out what we're supposed to do */ action = (____raw_readq(mailbox_regs[cpu]) >> 48) & 0xffff; diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c index 10811e981d2..2e370d88a87 100644 --- a/arch/mn10300/kernel/mn10300-watchdog.c +++ b/arch/mn10300/kernel/mn10300-watchdog.c @@ -130,6 +130,7 @@ void watchdog_interrupt(struct pt_regs *regs, enum exception_code excep) * the stack NMI-atomically, it's safe to use smp_processor_id(). */ int sum, cpu = smp_processor_id(); + int irq = NMIIRQ; u8 wdt, tmp; wdt = WDCTR & ~WDCTR_WDCNE; @@ -138,7 +139,7 @@ void watchdog_interrupt(struct pt_regs *regs, enum exception_code excep) NMICR = NMICR_WDIF; nmi_count(cpu)++; - kstat_this_cpu.irqs[NMIIRQ]++; + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); sum = irq_stat[cpu].__irq_count; if (last_irq_sums[cpu] == sum) { diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index ac2c822928c..49482806863 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -120,7 +120,7 @@ int cpu_check_affinity(unsigned int irq, cpumask_t *dest) if (CHECK_IRQ_PER_CPU(irq)) { /* Bad linux design decision. The mask has already * been set; we must reset it */ - irq_desc[irq].affinity = CPU_MASK_ALL; + cpumask_setall(irq_desc[irq].affinity); return -EINVAL; } @@ -136,7 +136,7 @@ static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest) if (cpu_check_affinity(irq, dest)) return; - irq_desc[irq].affinity = *dest; + cpumask_copy(irq_desc[irq].affinity, dest); } #endif @@ -295,7 +295,7 @@ int txn_alloc_irq(unsigned int bits_wide) unsigned long txn_affinity_addr(unsigned int irq, int cpu) { #ifdef CONFIG_SMP - irq_desc[irq].affinity = cpumask_of_cpu(cpu); + cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu)); #endif return per_cpu(cpu_data, cpu).txn_addr; @@ -352,7 +352,7 @@ void do_cpu_irq_mask(struct pt_regs *regs) irq = eirr_to_irq(eirr_val); #ifdef CONFIG_SMP - dest = irq_desc[irq].affinity; + cpumask_copy(&dest, irq_desc[irq].affinity); if (CHECK_IRQ_PER_CPU(irq_desc[irq].status) && !cpu_isset(smp_processor_id(), dest)) { int cpu = first_cpu(dest); diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts index 909a89cab9a..3ebf7ec0484 100644 --- a/arch/powerpc/boot/dts/mpc8313erdb.dts +++ b/arch/powerpc/boot/dts/mpc8313erdb.dts @@ -191,7 +191,8 @@ interrupts = <37 0x8 36 0x8 35 0x8>; interrupt-parent = <&ipic>; tbi-handle = < &tbi0 >; - phy-handle = < &phy1 >; + /* Vitesse 7385 isn't on the MDIO bus */ + fixed-link = <1 1 1000 0 0>; fsl,magic-packet; mdio@24520 { @@ -199,12 +200,6 @@ #size-cells = <0>; compatible = "fsl,gianfar-mdio"; reg = <0x24520 0x20>; - phy1: ethernet-phy@1 { - interrupt-parent = <&ipic>; - interrupts = <19 0x8>; - reg = <0x1>; - device_type = "ethernet-phy"; - }; phy4: ethernet-phy@4 { interrupt-parent = <&ipic>; interrupts = <20 0x8>; @@ -219,6 +214,8 @@ }; enet1: ethernet@25000 { + #address-cells = <1>; + #size-cells = <1>; cell-index = <1>; device_type = "network"; model = "eTSEC"; diff --git a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig index 9e47ae957e2..409d017621a 100644 --- a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig @@ -651,7 +651,7 @@ CONFIG_CICADA_PHY=y # CONFIG_NATIONAL_PHY is not set # CONFIG_STE10XP is not set # CONFIG_LSI_ET1011C_PHY is not set -# CONFIG_FIXED_PHY is not set +CONFIG_FIXED_PHY=y # CONFIG_MDIO_BITBANG is not set CONFIG_NET_ETHERNET=y CONFIG_MII=y diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 5355244c99f..60c60ccf5e3 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -195,8 +195,9 @@ __ftrace_make_nop(struct module *mod, return -EINVAL; } - offset = (unsigned)((unsigned short)jmp[0]) << 16 | - (unsigned)((unsigned short)jmp[1]); + /* The bottom half is signed extended */ + offset = ((unsigned)((unsigned short)jmp[0]) << 16) + + (int)((short)jmp[1]); DEBUGP(" %x ", offset); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 23b8b5e36f9..ad1e5ac721d 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -231,7 +231,7 @@ void fixup_irqs(cpumask_t map) if (irq_desc[irq].status & IRQ_PER_CPU) continue; - cpus_and(mask, irq_desc[irq].affinity, map); + cpumask_and(&mask, irq_desc[irq].affinity, &map); if (any_online_cpu(mask) == NR_CPUS) { printk("Breaking affinity for irq %i\n", irq); mask = map; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 19b12d2cbb4..0f418127231 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -561,8 +561,21 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus, (unsigned long long)(offset + size - 1)); if (mmap_state == pci_mmap_mem) { - if ((offset + size) > hose->isa_mem_size) - return -ENXIO; + /* Hack alert ! + * + * Because X is lame and can fail starting if it gets an error trying + * to mmap legacy_mem (instead of just moving on without legacy memory + * access) we fake it here by giving it anonymous memory, effectively + * behaving just like /dev/zero + */ + if ((offset + size) > hose->isa_mem_size) { + printk(KERN_DEBUG + "Process %s (pid:%d) mapped non-existing PCI legacy memory for 0%04x:%02x\n", + current->comm, current->pid, pci_domain_nr(bus), bus->number); + if (vma->vm_flags & VM_SHARED) + return shmem_zero_setup(vma); + return 0; + } offset += hose->isa_mem_phys; } else { unsigned long io_offset = (unsigned long)hose->io_base_virt - _IO_BASE; diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 161b9b9691f..295ccc5e86b 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -184,6 +184,7 @@ SECTIONS . = ALIGN(PAGE_SIZE); .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { __per_cpu_start = .; + *(.data.percpu.page_aligned) *(.data.percpu) *(.data.percpu.shared_aligned) __per_cpu_end = .; diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 4aae0c38764..13b7d54f185 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -172,6 +172,8 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) } break; case 0x378: /* orx */ + if (instr & 1) + break; rs = (instr >> 21) & 0x1f; rb = (instr >> 11) & 0x1f; if (rs == rb) { /* mr */ diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c index 1971e4ee3d6..ea6e41e39d9 100644 --- a/arch/powerpc/mm/fsl_booke_mmu.c +++ b/arch/powerpc/mm/fsl_booke_mmu.c @@ -73,7 +73,7 @@ extern unsigned int tlbcam_index; /* * Return PA for this VA if it is mapped by a CAM, or 0 */ -unsigned long v_mapped_by_tlbcam(unsigned long va) +phys_addr_t v_mapped_by_tlbcam(unsigned long va) { int b; for (b = 0; b < tlbcam_index; ++b) @@ -85,7 +85,7 @@ unsigned long v_mapped_by_tlbcam(unsigned long va) /* * Return VA for a given PA or 0 if not mapped */ -unsigned long p_mapped_by_tlbcam(unsigned long pa) +unsigned long p_mapped_by_tlbcam(phys_addr_t pa) { int b; for (b = 0; b < tlbcam_index; ++b) diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S index 67850ec9feb..14af8cedab7 100644 --- a/arch/powerpc/mm/hash_low_32.S +++ b/arch/powerpc/mm/hash_low_32.S @@ -320,7 +320,7 @@ _GLOBAL(create_hpte) and r8,r8,r0 /* writable if _RW & _DIRTY */ rlwimi r5,r5,32-1,30,30 /* _PAGE_USER -> PP msb */ rlwimi r5,r5,32-2,31,31 /* _PAGE_USER -> PP lsb */ - ori r8,r8,0xe14 /* clear out reserved bits and M */ + ori r8,r8,0xe04 /* clear out reserved bits */ andc r8,r5,r8 /* PP = user? (rw&dirty? 2: 3): 0 */ BEGIN_FTR_SECTION rlwinm r8,r8,0,~_PAGE_COHERENT /* clear M (coherence not required) */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 22972cd83cc..58bcaeba728 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -61,8 +61,8 @@ void setbat(int index, unsigned long virt, phys_addr_t phys, #ifdef HAVE_TLBCAM extern unsigned int tlbcam_index; -extern unsigned long v_mapped_by_tlbcam(unsigned long va); -extern unsigned long p_mapped_by_tlbcam(unsigned long pa); +extern phys_addr_t v_mapped_by_tlbcam(unsigned long va); +extern unsigned long p_mapped_by_tlbcam(phys_addr_t pa); #else /* !HAVE_TLBCAM */ #define v_mapped_by_tlbcam(x) (0UL) #define p_mapped_by_tlbcam(x) (0UL) diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c index 9305ddaac51..b129d007e7f 100644 --- a/arch/powerpc/oprofile/cell/spu_profiler.c +++ b/arch/powerpc/oprofile/cell/spu_profiler.c @@ -16,6 +16,7 @@ #include <linux/smp.h> #include <linux/slab.h> #include <asm/cell-pmu.h> +#include <asm/time.h> #include "pr_util.h" #define SCALE_SHIFT 14 diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c index 9876d7e072f..ddf0bdc0fc8 100644 --- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c +++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c @@ -186,7 +186,7 @@ out_unmap_regs: iounmap(priv->regs); out_free_bootmem: free_bootmem((unsigned long)priv, - sizeof(sizeof(struct pq2ads_pci_pic))); + sizeof(struct pq2ads_pci_pic)); of_node_put(np); out_unmap_irq: irq_dispose_mapping(irq); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index a623ad256e9..9b21ee68ea5 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -14,6 +14,7 @@ #include <asm/firmware.h> #include <asm/machdep.h> #include <asm/pSeries_reconfig.h> +#include <asm/sparsemem.h> static int pseries_remove_lmb(unsigned long base, unsigned int lmb_size) { diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 84e058f1e1c..80b513449f4 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -153,9 +153,10 @@ static int get_irq_server(unsigned int virq, unsigned int strict_check) { int server; /* For the moment only implement delivery to all cpus or one cpu */ - cpumask_t cpumask = irq_desc[virq].affinity; + cpumask_t cpumask; cpumask_t tmp = CPU_MASK_NONE; + cpumask_copy(&cpumask, irq_desc[virq].affinity); if (!distribute_irqs) return default_server; @@ -869,7 +870,7 @@ void xics_migrate_irqs_away(void) virq, cpu); /* Reset affinity to all cpus */ - irq_desc[virq].affinity = CPU_MASK_ALL; + cpumask_setall(irq_desc[virq].affinity); desc->chip->set_affinity(virq, cpu_all_mask); unlock: spin_unlock_irqrestore(&desc->lock, flags); diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c index b16ca3ed65d..78f1f7cca0a 100644 --- a/arch/powerpc/sysdev/cpm2_pic.c +++ b/arch/powerpc/sysdev/cpm2_pic.c @@ -165,7 +165,7 @@ static int cpm2_set_irq_type(unsigned int virq, unsigned int flow_type) edibit = (14 - (src - CPM2_IRQ_EXT1)); else if (src >= CPM2_IRQ_PORTC15 && src <= CPM2_IRQ_PORTC0) - edibit = (31 - (src - CPM2_IRQ_PORTC15)); + edibit = (31 - (CPM2_IRQ_PORTC0 - src)); else return (flow_type & IRQ_TYPE_LEVEL_LOW) ? 0 : -EINVAL; diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c index 88a983ece5c..9a89cd3e80a 100644 --- a/arch/powerpc/sysdev/ipic.c +++ b/arch/powerpc/sysdev/ipic.c @@ -890,7 +890,7 @@ unsigned int ipic_get_irq(void) return irq_linear_revmap(primary_ipic->irqhost, irq); } -#ifdef CONFIG_PM +#ifdef CONFIG_SUSPEND static struct { u32 sicfr; u32 siprr[2]; diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index a35297dbac2..532e205303a 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -566,9 +566,10 @@ static void __init mpic_scan_ht_pics(struct mpic *mpic) #ifdef CONFIG_SMP static int irq_choose_cpu(unsigned int virt_irq) { - cpumask_t mask = irq_desc[virt_irq].affinity; + cpumask_t mask; int cpuid; + cpumask_copy(&mask, irq_desc[virt_irq].affinity); if (cpus_equal(mask, CPU_MASK_ALL)) { static int irq_rover; static DEFINE_SPINLOCK(irq_rover_lock); diff --git a/arch/s390/defconfig b/arch/s390/defconfig index a0e748da990..31e809c7779 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.28-rc6 -# Thu Nov 27 11:00:49 2008 +# Linux kernel version: 2.6.29-rc4 +# Wed Feb 11 10:07:16 2009 # CONFIG_SCHED_MC=y CONFIG_MMU=y @@ -14,12 +14,14 @@ CONFIG_RWSEM_XCHGADD_ALGORITHM=y # CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_TIME_VSYSCALL=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_GENERIC_BUG=y CONFIG_NO_IOMEM=y CONFIG_NO_DMA=y CONFIG_GENERIC_LOCKBREAK=y CONFIG_PGSTE=y +CONFIG_VIRT_CPU_ACCOUNTING=y CONFIG_S390=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" @@ -39,20 +41,29 @@ CONFIG_POSIX_MQUEUE=y # CONFIG_TASKSTATS is not set CONFIG_AUDIT=y # CONFIG_AUDITSYSCALL is not set + +# +# RCU Subsystem +# +CONFIG_CLASSIC_RCU=y +# CONFIG_TREE_RCU is not set +# CONFIG_PREEMPT_RCU is not set +# CONFIG_TREE_RCU_TRACE is not set +# CONFIG_PREEMPT_RCU_TRACE is not set CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=17 +CONFIG_GROUP_SCHED=y +CONFIG_FAIR_GROUP_SCHED=y +# CONFIG_RT_GROUP_SCHED is not set +CONFIG_USER_SCHED=y +# CONFIG_CGROUP_SCHED is not set CONFIG_CGROUPS=y # CONFIG_CGROUP_DEBUG is not set CONFIG_CGROUP_NS=y # CONFIG_CGROUP_FREEZER is not set # CONFIG_CGROUP_DEVICE is not set # CONFIG_CPUSETS is not set -CONFIG_GROUP_SCHED=y -CONFIG_FAIR_GROUP_SCHED=y -# CONFIG_RT_GROUP_SCHED is not set -CONFIG_USER_SCHED=y -# CONFIG_CGROUP_SCHED is not set # CONFIG_CGROUP_CPUACCT is not set # CONFIG_RESOURCE_COUNTERS is not set CONFIG_SYSFS_DEPRECATED=y @@ -63,6 +74,7 @@ CONFIG_UTS_NS=y CONFIG_IPC_NS=y # CONFIG_USER_NS is not set # CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set @@ -91,17 +103,17 @@ CONFIG_SLAB=y # CONFIG_SLUB is not set # CONFIG_SLOB is not set # CONFIG_PROFILING is not set -# CONFIG_MARKERS is not set CONFIG_HAVE_OPROFILE=y CONFIG_KPROBES=y +CONFIG_HAVE_SYSCALL_WRAPPERS=y CONFIG_KRETPROBES=y CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y CONFIG_HAVE_ARCH_TRACEHOOK=y +CONFIG_USE_GENERIC_SMP_HELPERS=y # CONFIG_HAVE_GENERIC_DMA_COHERENT is not set CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y -# CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 CONFIG_MODULES=y # CONFIG_MODULE_FORCE_LOAD is not set @@ -109,7 +121,7 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_MODULE_FORCE_UNLOAD is not set CONFIG_MODVERSIONS=y # CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y +CONFIG_INIT_ALL_POSSIBLE=y CONFIG_STOP_MACHINE=y CONFIG_BLOCK=y # CONFIG_BLK_DEV_IO_TRACE is not set @@ -130,7 +142,6 @@ CONFIG_DEFAULT_DEADLINE=y # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="deadline" CONFIG_PREEMPT_NOTIFIERS=y -CONFIG_CLASSIC_RCU=y # CONFIG_FREEZER is not set # @@ -161,6 +172,7 @@ CONFIG_S390_EXEC_PROTECT=y CONFIG_MARCH_Z900=y # CONFIG_MARCH_Z990 is not set # CONFIG_MARCH_Z9_109 is not set +# CONFIG_MARCH_Z10 is not set CONFIG_PACK_STACK=y # CONFIG_SMALL_STACK is not set CONFIG_CHECK_STACK=y @@ -174,7 +186,6 @@ CONFIG_ARCH_POPULATES_NODE_MAP=y # CONFIG_PREEMPT_NONE is not set # CONFIG_PREEMPT_VOLUNTARY is not set CONFIG_PREEMPT=y -# CONFIG_PREEMPT_RCU is not set CONFIG_ARCH_SPARSEMEM_ENABLE=y CONFIG_ARCH_SPARSEMEM_DEFAULT=y CONFIG_ARCH_SELECT_MEMORY_MODEL=y @@ -195,7 +206,6 @@ CONFIG_MEMORY_HOTREMOVE=y CONFIG_PAGEFLAGS_EXTENDED=y CONFIG_SPLIT_PTLOCK_CPUS=4 CONFIG_MIGRATION=y -CONFIG_RESOURCES_64BIT=y CONFIG_PHYS_ADDR_T_64BIT=y CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y @@ -207,7 +217,6 @@ CONFIG_UNEVICTABLE_LRU=y # CONFIG_MACHCHK_WARNING=y CONFIG_QDIO=y -# CONFIG_QDIO_DEBUG is not set CONFIG_CHSC_SCH=m # @@ -227,15 +236,13 @@ CONFIG_PFAULT=y # CONFIG_SHARED_KERNEL is not set # CONFIG_CMM is not set # CONFIG_PAGE_STATES is not set -CONFIG_VIRT_TIMER=y -CONFIG_VIRT_CPU_ACCOUNTING=y # CONFIG_APPLDATA_BASE is not set CONFIG_HZ_100=y # CONFIG_HZ_250 is not set # CONFIG_HZ_300 is not set # CONFIG_HZ_1000 is not set CONFIG_HZ=100 -# CONFIG_SCHED_HRTICK is not set +CONFIG_SCHED_HRTICK=y CONFIG_S390_HYPFS_FS=y CONFIG_KEXEC=y # CONFIG_ZFCPDUMP is not set @@ -245,6 +252,7 @@ CONFIG_NET=y # # Networking options # +CONFIG_COMPAT_NET_DEV_OPS=y CONFIG_PACKET=y # CONFIG_PACKET_MMAP is not set CONFIG_UNIX=y @@ -383,6 +391,7 @@ CONFIG_NET_SCH_TBF=m CONFIG_NET_SCH_GRED=m CONFIG_NET_SCH_DSMARK=m # CONFIG_NET_SCH_NETEM is not set +# CONFIG_NET_SCH_DRR is not set # CONFIG_NET_SCH_INGRESS is not set # @@ -400,6 +409,7 @@ CONFIG_CLS_U32_MARK=y CONFIG_NET_CLS_RSVP=m CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_FLOW=m +# CONFIG_NET_CLS_CGROUP is not set # CONFIG_NET_EMATCH is not set CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=y @@ -411,6 +421,7 @@ CONFIG_NET_ACT_NAT=m # CONFIG_NET_ACT_SKBEDIT is not set # CONFIG_NET_CLS_IND is not set CONFIG_NET_SCH_FIFO=y +# CONFIG_DCB is not set # # Network testing @@ -428,6 +439,7 @@ CONFIG_CAN_VCAN=m # CONFIG_CAN_DEBUG_DEVICES is not set # CONFIG_AF_RXRPC is not set # CONFIG_PHONET is not set +# CONFIG_WIMAX is not set # CONFIG_RFKILL is not set # CONFIG_NET_9P is not set # CONFIG_PCMCIA is not set @@ -475,11 +487,15 @@ CONFIG_DASD_DIAG=y CONFIG_DASD_EER=y CONFIG_VIRTIO_BLK=m CONFIG_MISC_DEVICES=y -# CONFIG_EEPROM_93CX6 is not set # CONFIG_ENCLOSURE_SERVICES is not set # CONFIG_C2PORT is not set # +# EEPROM support +# +# CONFIG_EEPROM_93CX6 is not set + +# # SCSI device support # # CONFIG_RAID_ATTRS is not set @@ -520,6 +536,7 @@ CONFIG_SCSI_FC_ATTRS=y # CONFIG_SCSI_SRP_ATTRS is not set CONFIG_SCSI_LOWLEVEL=y # CONFIG_ISCSI_TCP is not set +# CONFIG_LIBFC is not set # CONFIG_SCSI_DEBUG is not set CONFIG_ZFCP=y CONFIG_SCSI_DH=m @@ -566,6 +583,10 @@ CONFIG_NET_ETHERNET=y CONFIG_NETDEV_1000=y CONFIG_NETDEV_10000=y # CONFIG_TR is not set + +# +# Enable WiMAX (Networking options) to see the WiMAX drivers +# # CONFIG_WAN is not set # @@ -593,9 +614,11 @@ CONFIG_VIRTIO_NET=m # CONFIG_DEVKMEM=y CONFIG_UNIX98_PTYS=y +# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 CONFIG_HVC_DRIVER=y +CONFIG_HVC_IUCV=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=m CONFIG_HW_RANDOM_VIRTIO=m @@ -645,7 +668,6 @@ CONFIG_S390_VMUR=m # CONFIG_NEW_LEDS is not set CONFIG_ACCESSIBILITY=y # CONFIG_STAGING is not set -CONFIG_STAGING_EXCLUDE_BUILD=y # # File systems @@ -668,6 +690,7 @@ CONFIG_FILE_LOCKING=y # CONFIG_XFS_FS is not set # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set +# CONFIG_BTRFS_FS is not set CONFIG_DNOTIFY=y CONFIG_INOTIFY=y CONFIG_INOTIFY_USER=y @@ -703,10 +726,7 @@ CONFIG_TMPFS_POSIX_ACL=y # CONFIG_HUGETLBFS is not set # CONFIG_HUGETLB_PAGE is not set CONFIG_CONFIGFS_FS=m - -# -# Miscellaneous filesystems -# +CONFIG_MISC_FILESYSTEMS=y # CONFIG_ADFS_FS is not set # CONFIG_AFFS_FS is not set # CONFIG_HFS_FS is not set @@ -715,6 +735,7 @@ CONFIG_CONFIGFS_FS=m # CONFIG_BFS_FS is not set # CONFIG_EFS_FS is not set # CONFIG_CRAMFS is not set +# CONFIG_SQUASHFS is not set # CONFIG_VXFS_FS is not set # CONFIG_MINIX_FS is not set # CONFIG_OMFS_FS is not set @@ -808,6 +829,7 @@ CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_LIST is not set # CONFIG_DEBUG_SG is not set +# CONFIG_DEBUG_NOTIFIERS is not set # CONFIG_FRAME_POINTER is not set # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_RCU_CPU_STALL_DETECTOR is not set @@ -818,15 +840,19 @@ CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_FAULT_INJECTION is not set # CONFIG_LATENCYTOP is not set CONFIG_SYSCTL_SYSCALL_CHECK=y +CONFIG_HAVE_FUNCTION_TRACER=y # # Tracers # +# CONFIG_FUNCTION_TRACER is not set # CONFIG_IRQSOFF_TRACER is not set # CONFIG_PREEMPT_TRACER is not set # CONFIG_SCHED_TRACER is not set # CONFIG_CONTEXT_SWITCH_TRACER is not set # CONFIG_BOOT_TRACER is not set +# CONFIG_TRACE_BRANCH_PROFILING is not set +# CONFIG_STACK_TRACER is not set # CONFIG_DYNAMIC_PRINTK_DEBUG is not set CONFIG_SAMPLES=y # CONFIG_SAMPLE_KOBJECT is not set @@ -847,11 +873,17 @@ CONFIG_CRYPTO=y # CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_ALGAPI=y -CONFIG_CRYPTO_AEAD=y +CONFIG_CRYPTO_ALGAPI2=y +CONFIG_CRYPTO_AEAD=m +CONFIG_CRYPTO_AEAD2=y CONFIG_CRYPTO_BLKCIPHER=y -CONFIG_CRYPTO_HASH=y -CONFIG_CRYPTO_RNG=y +CONFIG_CRYPTO_BLKCIPHER2=y +CONFIG_CRYPTO_HASH=m +CONFIG_CRYPTO_HASH2=y +CONFIG_CRYPTO_RNG=m +CONFIG_CRYPTO_RNG2=y CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_MANAGER2=y CONFIG_CRYPTO_GF128MUL=m # CONFIG_CRYPTO_NULL is not set # CONFIG_CRYPTO_CRYPTD is not set @@ -885,7 +917,7 @@ CONFIG_CRYPTO_HMAC=m # # Digest # -# CONFIG_CRYPTO_CRC32C is not set +CONFIG_CRYPTO_CRC32C=m # CONFIG_CRYPTO_MD4 is not set CONFIG_CRYPTO_MD5=m # CONFIG_CRYPTO_MICHAEL_MIC is not set @@ -942,6 +974,7 @@ CONFIG_S390_PRNG=m # Library routines # CONFIG_BITREVERSE=m +CONFIG_GENERIC_FIND_LAST_BIT=y # CONFIG_CRC_CCITT is not set # CONFIG_CRC16 is not set CONFIG_CRC_T10DIF=y diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index ffdef5fe858..f3720defdd1 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -384,8 +384,8 @@ struct _lowcore __u32 panic_magic; /* 0xe00 */ /* Per cpu primary space access list */ - __u8 pad_0xe04[0xe3c-0xe04]; /* 0xe04 */ - __u32 vdso_per_cpu_data; /* 0xe3c */ + __u8 pad_0xe04[0xe38-0xe04]; /* 0xe04 */ + __u64 vdso_per_cpu_data; /* 0xe38 */ __u32 paste[16]; /* 0xe40 */ __u8 pad13[0x11b8-0xe80]; /* 0xe80 */ diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index e7c5bfb7c75..026a37a94fc 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -95,6 +95,7 @@ asmlinkage void do_softirq(void) local_irq_restore(flags); } +#ifdef CONFIG_PROC_FS void init_irq_proc(void) { struct proc_dir_entry *root_irq_dir; @@ -102,3 +103,4 @@ void init_irq_proc(void) root_irq_dir = proc_mkdir("irq", NULL); create_prof_cpu_mask(root_irq_dir); } +#endif diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 8ffee714f93..a46c3a21e26 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -891,10 +891,35 @@ prom_tba: .xword 0 tlb_type: .word 0 /* Must NOT end up in BSS */ .section ".fixup",#alloc,#execinstr - .globl __ret_efault, __retl_efault -__ret_efault: + .globl __ret_efault, __retl_efault, __ret_one, __retl_one +ENTRY(__ret_efault) ret restore %g0, -EFAULT, %o0 -__retl_efault: +ENDPROC(__ret_efault) + +ENTRY(__retl_efault) retl mov -EFAULT, %o0 +ENDPROC(__retl_efault) + +ENTRY(__retl_one) + retl + mov 1, %o0 +ENDPROC(__retl_one) + +ENTRY(__ret_one_asi) + wr %g0, ASI_AIUS, %asi + ret + restore %g0, 1, %o0 +ENDPROC(__ret_one_asi) + +ENTRY(__retl_one_asi) + wr %g0, ASI_AIUS, %asi + retl + mov 1, %o0 +ENDPROC(__retl_one_asi) + +ENTRY(__retl_o1) + retl + mov %o1, %o0 +ENDPROC(__retl_o1) diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index e289376198e..3d2c6baae96 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -252,9 +252,10 @@ struct irq_handler_data { #ifdef CONFIG_SMP static int irq_choose_cpu(unsigned int virt_irq) { - cpumask_t mask = irq_desc[virt_irq].affinity; + cpumask_t mask; int cpuid; + cpumask_copy(&mask, irq_desc[virt_irq].affinity); if (cpus_equal(mask, CPU_MASK_ALL)) { static int irq_rover; static DEFINE_SPINLOCK(irq_rover_lock); @@ -796,7 +797,7 @@ void fixup_irqs(void) !(irq_desc[irq].status & IRQ_PER_CPU)) { if (irq_desc[irq].chip->set_affinity) irq_desc[irq].chip->set_affinity(irq, - &irq_desc[irq].affinity); + irq_desc[irq].affinity); } spin_unlock_irqrestore(&irq_desc[irq].lock, flags); } diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 09f088ed4a6..f3577223c86 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -70,6 +70,7 @@ static void die_nmi(const char *str, struct pt_regs *regs, int do_panic) printk(" on CPU%d, ip %08lx, registers:\n", smp_processor_id(), regs->tpc); show_regs(regs); + dump_stack(); bust_spinlocks(0); diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 92e0dda141a..1ae8cdd7e70 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -133,11 +133,16 @@ int __init pcr_arch_init(void) case cheetah: case cheetah_plus: - case spitfire: pcr_ops = &direct_pcr_ops; pcr_enable = PCR_SUN4U_ENABLE; break; + case spitfire: + /* UltraSPARC-I/II and derivatives lack a profile + * counter overflow interrupt so we can't make use of + * their hardware currently. + */ + /* fallthrough */ default: err = -ENODEV; goto out_unregister; diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 2db3c2229b9..db310aa0018 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -729,7 +729,7 @@ void timer_interrupt(int irq, struct pt_regs *regs) irq_enter(); - kstat_this_cpu.irqs[0]++; + kstat_incr_irqs_this_cpu(0, irq_to_desc(0)); if (unlikely(!evt->event_handler)) { printk(KERN_WARNING diff --git a/arch/sparc/lib/GENbzero.S b/arch/sparc/lib/GENbzero.S index 6a4f956a2f7..8e7a843ddd8 100644 --- a/arch/sparc/lib/GENbzero.S +++ b/arch/sparc/lib/GENbzero.S @@ -6,13 +6,9 @@ #define EX_ST(x,y) \ 98: x,y; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov %o1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_o1; \ .text; \ .align 4; diff --git a/arch/sparc/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S index 2b9df99e87f..b7d0bd6b140 100644 --- a/arch/sparc/lib/GENcopy_from_user.S +++ b/arch/sparc/lib/GENcopy_from_user.S @@ -5,13 +5,9 @@ #define EX_LD(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one; \ .text; \ .align 4; @@ -27,7 +23,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S index bb3f7084daf..780550e1afc 100644 --- a/arch/sparc/lib/GENcopy_to_user.S +++ b/arch/sparc/lib/GENcopy_to_user.S @@ -5,13 +5,9 @@ #define EX_ST(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one; \ .text; \ .align 4; @@ -31,7 +27,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S index c77ef5f2210..119ccb9a54f 100644 --- a/arch/sparc/lib/NG2copy_from_user.S +++ b/arch/sparc/lib/NG2copy_from_user.S @@ -5,14 +5,9 @@ #define EX_LD(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: wr %g0, ASI_AIUS, %asi;\ - retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one_asi;\ .text; \ .align 4; @@ -33,7 +28,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S index 4bd4093acbb..7fe1ccefd9d 100644 --- a/arch/sparc/lib/NG2copy_to_user.S +++ b/arch/sparc/lib/NG2copy_to_user.S @@ -5,14 +5,9 @@ #define EX_ST(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: wr %g0, ASI_AIUS, %asi;\ - retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one_asi;\ .text; \ .align 4; @@ -42,7 +37,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NGbzero.S b/arch/sparc/lib/NGbzero.S index 814d5f7a45e..beab29bf419 100644 --- a/arch/sparc/lib/NGbzero.S +++ b/arch/sparc/lib/NGbzero.S @@ -6,13 +6,9 @@ #define EX_ST(x,y) \ 98: x,y; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov %o1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_o1; \ .text; \ .align 4; diff --git a/arch/sparc/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S index e7f433f71b4..5d1e4d1ac21 100644 --- a/arch/sparc/lib/NGcopy_from_user.S +++ b/arch/sparc/lib/NGcopy_from_user.S @@ -5,14 +5,9 @@ #define EX_LD(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: wr %g0, ASI_AIUS, %asi;\ - ret; \ - restore %g0, 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __ret_one_asi;\ .text; \ .align 4; @@ -30,7 +25,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S index 6ea01c5532a..ff630dcb273 100644 --- a/arch/sparc/lib/NGcopy_to_user.S +++ b/arch/sparc/lib/NGcopy_to_user.S @@ -5,14 +5,9 @@ #define EX_ST(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: wr %g0, ASI_AIUS, %asi;\ - ret; \ - restore %g0, 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __ret_one_asi;\ .text; \ .align 4; @@ -33,7 +28,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop #endif diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S index 3192b0bf4fa..a6ae2ea04bf 100644 --- a/arch/sparc/lib/U1copy_from_user.S +++ b/arch/sparc/lib/U1copy_from_user.S @@ -5,13 +5,9 @@ #define EX_LD(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one; \ .text; \ .align 4; @@ -27,7 +23,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop; \ #include "U1memcpy.S" diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S index d1210ffb0b8..f4b970eeb48 100644 --- a/arch/sparc/lib/U1copy_to_user.S +++ b/arch/sparc/lib/U1copy_to_user.S @@ -5,13 +5,9 @@ #define EX_ST(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one; \ .text; \ .align 4; @@ -27,7 +23,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop; \ #include "U1memcpy.S" diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S index f5bfc8d9d21..b1acd1331c3 100644 --- a/arch/sparc/lib/U3copy_from_user.S +++ b/arch/sparc/lib/U3copy_from_user.S @@ -5,13 +5,9 @@ #define EX_LD(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one; \ .text; \ .align 4; diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S index 2334f111bb0..ef1e493afdf 100644 --- a/arch/sparc/lib/U3copy_to_user.S +++ b/arch/sparc/lib/U3copy_to_user.S @@ -5,13 +5,9 @@ #define EX_ST(x) \ 98: x; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one; \ .text; \ .align 4; @@ -27,7 +23,7 @@ #define PREAMBLE \ rd %asi, %g1; \ cmp %g1, ASI_AIUS; \ - bne,pn %icc, memcpy_user_stub; \ + bne,pn %icc, ___copy_in_user; \ nop; \ #include "U3memcpy.S" diff --git a/arch/sparc/lib/bzero.S b/arch/sparc/lib/bzero.S index c7bbae8c590..b6557297440 100644 --- a/arch/sparc/lib/bzero.S +++ b/arch/sparc/lib/bzero.S @@ -88,13 +88,9 @@ __bzero_done: #define EX_ST(x,y) \ 98: x,y; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov %o1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_o1; \ .text; \ .align 4; diff --git a/arch/sparc/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S index 650af3f21f7..302c0e60dc2 100644 --- a/arch/sparc/lib/copy_in_user.S +++ b/arch/sparc/lib/copy_in_user.S @@ -3,19 +3,16 @@ * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) */ +#include <linux/linkage.h> #include <asm/asi.h> #define XCC xcc #define EX(x,y) \ 98: x,y; \ - .section .fixup; \ - .align 4; \ -99: retl; \ - mov 1, %o0; \ .section __ex_table,"a";\ .align 4; \ - .word 98b, 99b; \ + .word 98b, __retl_one; \ .text; \ .align 4; @@ -31,18 +28,7 @@ * to copy register windows around during thread cloning. */ - .globl ___copy_in_user - .type ___copy_in_user,#function -___copy_in_user: /* %o0=dst, %o1=src, %o2=len */ - /* Writing to %asi is _expensive_ so we hardcode it. - * Reading %asi to check for KERNEL_DS is comparatively - * cheap. - */ - rd %asi, %g1 - cmp %g1, ASI_AIUS - bne,pn %icc, memcpy_user_stub - nop - +ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */ cmp %o2, 0 be,pn %XCC, 85f or %o0, %o1, %o3 @@ -53,22 +39,24 @@ ___copy_in_user: /* %o0=dst, %o1=src, %o2=len */ /* 16 < len <= 64 */ andcc %o3, 0x7, %g0 bne,pn %XCC, 90f - sub %o0, %o1, %o3 + nop andn %o2, 0x7, %o4 and %o2, 0x7, %o2 1: subcc %o4, 0x8, %o4 EX(ldxa [%o1] %asi, %o5) - EX(stxa %o5, [%o1 + %o3] ASI_AIUS) + EX(stxa %o5, [%o0] %asi) + add %o1, 0x8, %o1 bgu,pt %XCC, 1b - add %o1, 0x8, %o1 + add %o0, 0x8, %o0 andcc %o2, 0x4, %g0 be,pt %XCC, 1f nop sub %o2, 0x4, %o2 EX(lduwa [%o1] %asi, %o5) - EX(stwa %o5, [%o1 + %o3] ASI_AIUS) + EX(stwa %o5, [%o0] %asi) add %o1, 0x4, %o1 + add %o0, 0x4, %o0 1: cmp %o2, 0 be,pt %XCC, 85f nop @@ -78,14 +66,15 @@ ___copy_in_user: /* %o0=dst, %o1=src, %o2=len */ 80: /* 0 < len <= 16 */ andcc %o3, 0x3, %g0 bne,pn %XCC, 90f - sub %o0, %o1, %o3 + nop 82: subcc %o2, 4, %o2 EX(lduwa [%o1] %asi, %g1) - EX(stwa %g1, [%o1 + %o3] ASI_AIUS) + EX(stwa %g1, [%o0] %asi) + add %o1, 4, %o1 bgu,pt %XCC, 82b - add %o1, 4, %o1 + add %o0, 4, %o0 85: retl clr %o0 @@ -94,26 +83,10 @@ ___copy_in_user: /* %o0=dst, %o1=src, %o2=len */ 90: subcc %o2, 1, %o2 EX(lduba [%o1] %asi, %g1) - EX(stba %g1, [%o1 + %o3] ASI_AIUS) + EX(stba %g1, [%o0] %asi) + add %o1, 1, %o1 bgu,pt %XCC, 90b - add %o1, 1, %o1 + add %o0, 1, %o0 retl clr %o0 - - .size ___copy_in_user, .-___copy_in_user - - /* Act like copy_{to,in}_user(), ie. return zero instead - * of original destination pointer. This is invoked when - * copy_{to,in}_user() finds that %asi is kernel space. - */ - .globl memcpy_user_stub - .type memcpy_user_stub,#function -memcpy_user_stub: - save %sp, -192, %sp - mov %i0, %o0 - mov %i1, %o1 - call memcpy - mov %i2, %o2 - ret - restore %g0, %g0, %o0 - .size memcpy_user_stub, .-memcpy_user_stub +ENDPROC(___copy_in_user) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 73f7fe8fd4d..1042d69b267 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -5,7 +5,7 @@ mainmenu "Linux Kernel Configuration for x86" config 64BIT bool "64-bit kernel" if ARCH = "x86" default ARCH = "x86_64" - help + ---help--- Say yes to build a 64-bit kernel - formerly known as x86_64 Say no to build a 32-bit kernel - formerly known as i386 @@ -34,8 +34,8 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST - select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) - select HAVE_ARCH_KGDB if !X86_VOYAGER + select HAVE_KVM + select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -133,18 +133,16 @@ config ARCH_HAS_CACHE_LINE_SIZE def_bool y config HAVE_SETUP_PER_CPU_AREA - def_bool X86_64_SMP || (X86_SMP && !X86_VOYAGER) + def_bool y config HAVE_CPUMASK_OF_CPU_MAP def_bool X86_64_SMP config ARCH_HIBERNATION_POSSIBLE def_bool y - depends on !SMP || !X86_VOYAGER config ARCH_SUSPEND_POSSIBLE def_bool y - depends on !X86_VOYAGER config ZONE_DMA32 bool @@ -174,11 +172,6 @@ config GENERIC_PENDING_IRQ depends on GENERIC_HARDIRQS && SMP default y -config X86_SMP - bool - depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64) - default y - config USE_GENERIC_SMP_HELPERS def_bool y depends on SMP @@ -194,19 +187,17 @@ config X86_64_SMP config X86_HT bool depends on SMP - depends on (X86_32 && !X86_VOYAGER) || X86_64 - default y - -config X86_BIOS_REBOOT - bool - depends on !X86_VOYAGER default y config X86_TRAMPOLINE bool - depends on X86_SMP || (X86_VOYAGER && SMP) || (64BIT && ACPI_SLEEP) + depends on SMP || (64BIT && ACPI_SLEEP) default y +config X86_32_LAZY_GS + def_bool y + depends on X86_32 && !CC_STACKPROTECTOR + config KTIME_SCALAR def_bool X86_32 source "init/Kconfig" @@ -244,14 +235,10 @@ config SMP If you don't know what to do here, say N. -config X86_HAS_BOOT_CPU_ID - def_bool y - depends on X86_VOYAGER - config SPARSE_IRQ bool "Support sparse irq numbering" depends on PCI_MSI || HT_IRQ - help + ---help--- This enables support for sparse irqs. This is useful for distro kernels that want to define a high CONFIG_NR_CPUS value but still want to have low kernel memory footprint on smaller machines. @@ -265,137 +252,154 @@ config NUMA_MIGRATE_IRQ_DESC bool "Move irq desc when changing irq smp_affinity" depends on SPARSE_IRQ && NUMA default n - help + ---help--- This enables moving irq_desc to cpu/node that irq will use handled. If you don't know what to do here, say N. -config X86_FIND_SMP_CONFIG - def_bool y - depends on X86_MPPARSE || X86_VOYAGER - config X86_MPPARSE bool "Enable MPS table" if ACPI default y depends on X86_LOCAL_APIC - help + ---help--- For old smp systems that do not have proper acpi support. Newer systems (esp with 64bit cpus) with acpi support, MADT and DSDT will override it -choice - prompt "Subarchitecture Type" - default X86_PC +config X86_BIGSMP + bool "Support for big SMP systems with more than 8 CPUs" + depends on X86_32 && SMP + ---help--- + This option is needed for the systems that have more than 8 CPUs -config X86_PC - bool "PC-compatible" - help - Choose this option if your computer is a standard PC or compatible. +config X86_EXTENDED_PLATFORM + bool "Support for extended (non-PC) x86 platforms" + default y + ---help--- + If you disable this option then the kernel will only support + standard PC platforms. (which covers the vast majority of + systems out there.) + + If you enable this option then you'll be able to select a number + of non-PC x86 platforms. + + If you have one of these systems, or if you want to build a + generic distribution kernel, say Y here - otherwise say N. + +# This is an alphabetically sorted list of 64 bit extended platforms +# Please maintain the alphabetic order if and when there are additions + +config X86_VSMP + bool "ScaleMP vSMP" + select PARAVIRT + depends on X86_64 && PCI + depends on X86_EXTENDED_PLATFORM + ---help--- + Support for ScaleMP vSMP systems. Say 'Y' here if this kernel is + supposed to run on these EM64T-based machines. Only choose this option + if you have one of these machines. + +config X86_UV + bool "SGI Ultraviolet" + depends on X86_64 + depends on X86_EXTENDED_PLATFORM + ---help--- + This option is needed in order to support SGI Ultraviolet systems. + If you don't have one of these, you should say N here. + +# Following is an alphabetically sorted list of 32 bit extended platforms +# Please maintain the alphabetic order if and when there are additions config X86_ELAN bool "AMD Elan" depends on X86_32 - help + depends on X86_EXTENDED_PLATFORM + ---help--- Select this for an AMD Elan processor. Do not use this option for K6/Athlon/Opteron processors! If unsure, choose "PC-compatible" instead. -config X86_VOYAGER - bool "Voyager (NCR)" - depends on X86_32 && (SMP || BROKEN) && !PCI - help - Voyager is an MCA-based 32-way capable SMP architecture proprietary - to NCR Corp. Machine classes 345x/35xx/4100/51xx are Voyager-based. - - *** WARNING *** - - If you do not specifically know you have a Voyager based machine, - say N here, otherwise the kernel you build will not be bootable. - -config X86_GENERICARCH - bool "Generic architecture" +config X86_RDC321X + bool "RDC R-321x SoC" depends on X86_32 - help - This option compiles in the NUMAQ, Summit, bigsmp, ES7000, default + depends on X86_EXTENDED_PLATFORM + select M486 + select X86_REBOOTFIXUPS + ---help--- + This option is needed for RDC R-321x system-on-chip, also known + as R-8610-(G). + If you don't have one of these chips, you should say N here. + +config X86_32_NON_STANDARD + bool "Support non-standard 32-bit SMP architectures" + depends on X86_32 && SMP + depends on X86_EXTENDED_PLATFORM + ---help--- + This option compiles in the NUMAQ, Summit, bigsmp, ES7000, default subarchitectures. It is intended for a generic binary kernel. if you select them all, kernel will probe it one by one. and will fallback to default. -if X86_GENERICARCH +# Alphabetically sorted list of Non standard 32 bit platforms config X86_NUMAQ bool "NUMAQ (IBM/Sequent)" - depends on SMP && X86_32 && PCI && X86_MPPARSE + depends on X86_32_NON_STANDARD select NUMA - help + select X86_MPPARSE + ---help--- This option is used for getting Linux to run on a NUMAQ (IBM/Sequent) NUMA multiquad box. This changes the way that processors are bootstrapped, and uses Clustered Logical APIC addressing mode instead of Flat Logical. You will need a new lynxer.elf file to flash your firmware with - send email to <Martin.Bligh@us.ibm.com>. +config X86_VISWS + bool "SGI 320/540 (Visual Workstation)" + depends on X86_32 && PCI && X86_MPPARSE && PCI_GODIRECT + depends on X86_32_NON_STANDARD + ---help--- + The SGI Visual Workstation series is an IA32-based workstation + based on SGI systems chips with some legacy PC hardware attached. + + Say Y here to create a kernel to run on the SGI 320 or 540. + + A kernel compiled for the Visual Workstation will run on general + PCs as well. See <file:Documentation/sgi-visws.txt> for details. + config X86_SUMMIT bool "Summit/EXA (IBM x440)" - depends on X86_32 && SMP - help + depends on X86_32_NON_STANDARD + ---help--- This option is needed for IBM systems that use the Summit/EXA chipset. In particular, it is needed for the x440. config X86_ES7000 - bool "Support for Unisys ES7000 IA32 series" - depends on X86_32 && SMP - help + bool "Unisys ES7000 IA32 series" + depends on X86_32_NON_STANDARD && X86_BIGSMP + ---help--- Support for Unisys ES7000 systems. Say 'Y' here if this kernel is supposed to run on an IA32-based Unisys ES7000 system. -config X86_BIGSMP - bool "Support for big SMP systems with more than 8 CPUs" - depends on X86_32 && SMP - help - This option is needed for the systems that have more than 8 CPUs - and if the system is not of any sub-arch type above. - -endif - -config X86_VSMP - bool "Support for ScaleMP vSMP" - select PARAVIRT - depends on X86_64 && PCI - help - Support for ScaleMP vSMP systems. Say 'Y' here if this kernel is - supposed to run on these EM64T-based machines. Only choose this option - if you have one of these machines. - -endchoice - -config X86_VISWS - bool "SGI 320/540 (Visual Workstation)" - depends on X86_32 && PCI && !X86_VOYAGER && X86_MPPARSE && PCI_GODIRECT - help - The SGI Visual Workstation series is an IA32-based workstation - based on SGI systems chips with some legacy PC hardware attached. - - Say Y here to create a kernel to run on the SGI 320 or 540. +config X86_VOYAGER + bool "Voyager (NCR)" + depends on SMP && !PCI && BROKEN + depends on X86_32_NON_STANDARD + ---help--- + Voyager is an MCA-based 32-way capable SMP architecture proprietary + to NCR Corp. Machine classes 345x/35xx/4100/51xx are Voyager-based. - A kernel compiled for the Visual Workstation will run on general - PCs as well. See <file:Documentation/sgi-visws.txt> for details. + *** WARNING *** -config X86_RDC321X - bool "RDC R-321x SoC" - depends on X86_32 - select M486 - select X86_REBOOTFIXUPS - help - This option is needed for RDC R-321x system-on-chip, also known - as R-8610-(G). - If you don't have one of these chips, you should say N here. + If you do not specifically know you have a Voyager based machine, + say N here, otherwise the kernel you build will not be bootable. config SCHED_OMIT_FRAME_POINTER def_bool y prompt "Single-depth WCHAN output" depends on X86 - help + ---help--- Calculate simpler /proc/<PID>/wchan values. If this option is disabled then wchan values will recurse back to the caller function. This provides more accurate wchan values, @@ -405,7 +409,7 @@ config SCHED_OMIT_FRAME_POINTER menuconfig PARAVIRT_GUEST bool "Paravirtualized guest support" - help + ---help--- Say Y here to get to see options related to running Linux under various hypervisors. This option alone does not add any kernel code. @@ -419,8 +423,7 @@ config VMI bool "VMI Guest support" select PARAVIRT depends on X86_32 - depends on !X86_VOYAGER - help + ---help--- VMI provides a paravirtualized interface to the VMware ESX server (it could be used by other hypervisors in theory too, but is not at the moment), by linking the kernel to a GPL-ed ROM module @@ -430,8 +433,7 @@ config KVM_CLOCK bool "KVM paravirtualized clock" select PARAVIRT select PARAVIRT_CLOCK - depends on !X86_VOYAGER - help + ---help--- Turning on this option will allow you to run a paravirtualized clock when running over the KVM hypervisor. Instead of relying on a PIT (or probably other) emulation by the underlying device model, the host @@ -441,17 +443,15 @@ config KVM_CLOCK config KVM_GUEST bool "KVM Guest support" select PARAVIRT - depends on !X86_VOYAGER - help - This option enables various optimizations for running under the KVM - hypervisor. + ---help--- + This option enables various optimizations for running under the KVM + hypervisor. source "arch/x86/lguest/Kconfig" config PARAVIRT bool "Enable paravirtualization code" - depends on !X86_VOYAGER - help + ---help--- This changes the kernel so it can modify itself when it is run under a hypervisor, potentially improving performance significantly over full virtualization. However, when run without a hypervisor @@ -464,51 +464,51 @@ config PARAVIRT_CLOCK endif config PARAVIRT_DEBUG - bool "paravirt-ops debugging" - depends on PARAVIRT && DEBUG_KERNEL - help - Enable to debug paravirt_ops internals. Specifically, BUG if - a paravirt_op is missing when it is called. + bool "paravirt-ops debugging" + depends on PARAVIRT && DEBUG_KERNEL + ---help--- + Enable to debug paravirt_ops internals. Specifically, BUG if + a paravirt_op is missing when it is called. config MEMTEST bool "Memtest" - help + ---help--- This option adds a kernel parameter 'memtest', which allows memtest to be set. - memtest=0, mean disabled; -- default - memtest=1, mean do 1 test pattern; - ... - memtest=4, mean do 4 test patterns. + memtest=0, mean disabled; -- default + memtest=1, mean do 1 test pattern; + ... + memtest=4, mean do 4 test patterns. If you are unsure how to answer this question, answer N. config X86_SUMMIT_NUMA def_bool y - depends on X86_32 && NUMA && X86_GENERICARCH + depends on X86_32 && NUMA && X86_32_NON_STANDARD config X86_CYCLONE_TIMER def_bool y - depends on X86_GENERICARCH + depends on X86_32_NON_STANDARD source "arch/x86/Kconfig.cpu" config HPET_TIMER def_bool X86_64 prompt "HPET Timer Support" if X86_32 - help - Use the IA-PC HPET (High Precision Event Timer) to manage - time in preference to the PIT and RTC, if a HPET is - present. - HPET is the next generation timer replacing legacy 8254s. - The HPET provides a stable time base on SMP - systems, unlike the TSC, but it is more expensive to access, - as it is off-chip. You can find the HPET spec at - <http://www.intel.com/hardwaredesign/hpetspec_1.pdf>. + ---help--- + Use the IA-PC HPET (High Precision Event Timer) to manage + time in preference to the PIT and RTC, if a HPET is + present. + HPET is the next generation timer replacing legacy 8254s. + The HPET provides a stable time base on SMP + systems, unlike the TSC, but it is more expensive to access, + as it is off-chip. You can find the HPET spec at + <http://www.intel.com/hardwaredesign/hpetspec_1.pdf>. - You can safely choose Y here. However, HPET will only be - activated if the platform and the BIOS support this feature. - Otherwise the 8254 will be used for timing services. + You can safely choose Y here. However, HPET will only be + activated if the platform and the BIOS support this feature. + Otherwise the 8254 will be used for timing services. - Choose N to continue using the legacy 8254 timer. + Choose N to continue using the legacy 8254 timer. config HPET_EMULATE_RTC def_bool y @@ -519,7 +519,7 @@ config HPET_EMULATE_RTC config DMI default y bool "Enable DMI scanning" if EMBEDDED - help + ---help--- Enabled scanning of DMI to identify machine quirks. Say Y here unless you have verified that your setup is not affected by entries in the DMI blacklist. Required by PNP @@ -531,7 +531,7 @@ config GART_IOMMU select SWIOTLB select AGP depends on X86_64 && PCI - help + ---help--- Support for full DMA access of devices with 32bit memory access only on systems with more than 3GB. This is usually needed for USB, sound, many IDE/SATA chipsets and some other devices. @@ -546,7 +546,7 @@ config CALGARY_IOMMU bool "IBM Calgary IOMMU support" select SWIOTLB depends on X86_64 && PCI && EXPERIMENTAL - help + ---help--- Support for hardware IOMMUs in IBM's xSeries x366 and x460 systems. Needed to run systems with more than 3GB of memory properly with 32-bit PCI devices that do not support DAC @@ -564,7 +564,7 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT def_bool y prompt "Should Calgary be enabled by default?" depends on CALGARY_IOMMU - help + ---help--- Should Calgary be enabled by default? if you choose 'y', Calgary will be used (if it exists). If you choose 'n', Calgary will not be used even if it exists. If you choose 'n' and would like to use @@ -576,7 +576,7 @@ config AMD_IOMMU select SWIOTLB select PCI_MSI depends on X86_64 && PCI && ACPI - help + ---help--- With this option you can enable support for AMD IOMMU hardware in your system. An IOMMU is a hardware component which provides remapping of DMA memory accesses from devices. With an AMD IOMMU you @@ -591,7 +591,7 @@ config AMD_IOMMU_STATS bool "Export AMD IOMMU statistics to debugfs" depends on AMD_IOMMU select DEBUG_FS - help + ---help--- This option enables code in the AMD IOMMU driver to collect various statistics about whats happening in the driver and exports that information to userspace via debugfs. @@ -600,7 +600,7 @@ config AMD_IOMMU_STATS # need this always selected by IOMMU for the VIA workaround config SWIOTLB def_bool y if X86_64 - help + ---help--- Support for software bounce buffers used on x86-64 systems which don't have a hardware IOMMU (e.g. the current generation of Intel's x86-64 CPUs). Using this PCI devices which can only @@ -618,7 +618,7 @@ config MAXSMP depends on X86_64 && SMP && DEBUG_KERNEL && EXPERIMENTAL select CPUMASK_OFFSTACK default n - help + ---help--- Configure maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. @@ -629,7 +629,7 @@ config NR_CPUS default "4096" if MAXSMP default "32" if SMP && (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000) default "8" if SMP - help + ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. The maximum supported value is 512 and the minimum value which makes sense is 2. @@ -640,7 +640,7 @@ config NR_CPUS config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" depends on X86_HT - help + ---help--- SMT scheduler support improves the CPU scheduler's decision making when dealing with Intel Pentium 4 chips with HyperThreading at a cost of slightly increased overhead in some places. If unsure say @@ -650,7 +650,7 @@ config SCHED_MC def_bool y prompt "Multi-core scheduler support" depends on X86_HT - help + ---help--- Multi-core scheduler support improves the CPU scheduler's decision making when dealing with multi-core CPU chips at a cost of slightly increased overhead in some places. If unsure say N here. @@ -659,8 +659,8 @@ source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" - depends on X86_32 && !SMP && !(X86_VOYAGER || X86_GENERICARCH) - help + depends on X86_32 && !SMP && !X86_32_NON_STANDARD + ---help--- A local APIC (Advanced Programmable Interrupt Controller) is an integrated interrupt controller in the CPU. If you have a single-CPU system which has a processor with a local APIC, you can say Y here to @@ -673,7 +673,7 @@ config X86_UP_APIC config X86_UP_IOAPIC bool "IO-APIC support on uniprocessors" depends on X86_UP_APIC - help + ---help--- An IO-APIC (I/O Advanced Programmable Interrupt Controller) is an SMP-capable replacement for PC-style interrupt controllers. Most SMP systems and many recent uniprocessor systems have one. @@ -684,11 +684,11 @@ config X86_UP_IOAPIC config X86_LOCAL_APIC def_bool y - depends on X86_64 || (X86_32 && (X86_UP_APIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH)) + depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC config X86_IO_APIC def_bool y - depends on X86_64 || (X86_32 && (X86_UP_IOAPIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH)) + depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC config X86_VISWS_APIC def_bool y @@ -698,7 +698,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS bool "Reroute for broken boot IRQs" default n depends on X86_IO_APIC - help + ---help--- This option enables a workaround that fixes a source of spurious interrupts. This is recommended when threaded interrupt handling is used on systems where the generation of @@ -720,7 +720,6 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS config X86_MCE bool "Machine Check Exception" - depends on !X86_VOYAGER ---help--- Machine Check Exception support allows the processor to notify the kernel if it detects a problem (e.g. overheating, component failure). @@ -739,7 +738,7 @@ config X86_MCE_INTEL def_bool y prompt "Intel MCE features" depends on X86_64 && X86_MCE && X86_LOCAL_APIC - help + ---help--- Additional support for intel specific MCE features such as the thermal monitor. @@ -747,14 +746,14 @@ config X86_MCE_AMD def_bool y prompt "AMD MCE features" depends on X86_64 && X86_MCE && X86_LOCAL_APIC - help + ---help--- Additional support for AMD specific MCE features such as the DRAM Error Threshold. config X86_MCE_NONFATAL tristate "Check for non-fatal errors on AMD Athlon/Duron / Intel Pentium 4" depends on X86_32 && X86_MCE - help + ---help--- Enabling this feature starts a timer that triggers every 5 seconds which will look at the machine check registers to see if anything happened. Non-fatal problems automatically get corrected (but still logged). @@ -767,7 +766,7 @@ config X86_MCE_NONFATAL config X86_MCE_P4THERMAL bool "check for P4 thermal throttling interrupt." depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP) - help + ---help--- Enabling this feature will cause a message to be printed when the P4 enters thermal throttling. @@ -775,11 +774,11 @@ config VM86 bool "Enable VM86 support" if EMBEDDED default y depends on X86_32 - help - This option is required by programs like DOSEMU to run 16-bit legacy + ---help--- + This option is required by programs like DOSEMU to run 16-bit legacy code on X86 processors. It also may be needed by software like - XFree86 to initialize some video cards via BIOS. Disabling this - option saves about 6k. + XFree86 to initialize some video cards via BIOS. Disabling this + option saves about 6k. config TOSHIBA tristate "Toshiba Laptop support" @@ -853,33 +852,33 @@ config MICROCODE module will be called microcode. config MICROCODE_INTEL - bool "Intel microcode patch loading support" - depends on MICROCODE - default MICROCODE - select FW_LOADER - --help--- - This options enables microcode patch loading support for Intel - processors. - - For latest news and information on obtaining all the required - Intel ingredients for this driver, check: - <http://www.urbanmyth.org/microcode/>. + bool "Intel microcode patch loading support" + depends on MICROCODE + default MICROCODE + select FW_LOADER + ---help--- + This options enables microcode patch loading support for Intel + processors. + + For latest news and information on obtaining all the required + Intel ingredients for this driver, check: + <http://www.urbanmyth.org/microcode/>. config MICROCODE_AMD - bool "AMD microcode patch loading support" - depends on MICROCODE - select FW_LOADER - --help--- - If you select this option, microcode patch loading support for AMD - processors will be enabled. + bool "AMD microcode patch loading support" + depends on MICROCODE + select FW_LOADER + ---help--- + If you select this option, microcode patch loading support for AMD + processors will be enabled. - config MICROCODE_OLD_INTERFACE +config MICROCODE_OLD_INTERFACE def_bool y depends on MICROCODE config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" - help + ---help--- This device gives privileged processes access to the x86 Model-Specific Registers (MSRs). It is a character device with major 202 and minors 0 to 31 for /dev/cpu/0/msr to /dev/cpu/31/msr. @@ -888,7 +887,7 @@ config X86_MSR config X86_CPUID tristate "/dev/cpu/*/cpuid - CPU information support" - help + ---help--- This device gives processes access to the x86 CPUID instruction to be executed on a specific processor. It is a character device with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to @@ -940,7 +939,7 @@ config NOHIGHMEM config HIGHMEM4G bool "4GB" depends on !X86_NUMAQ - help + ---help--- Select this if you have a 32-bit processor and between 1 and 4 gigabytes of physical RAM. @@ -948,7 +947,7 @@ config HIGHMEM64G bool "64GB" depends on !M386 && !M486 select X86_PAE - help + ---help--- Select this if you have a 32-bit processor and more than 4 gigabytes of physical RAM. @@ -959,7 +958,7 @@ choice prompt "Memory split" if EMBEDDED default VMSPLIT_3G depends on X86_32 - help + ---help--- Select the desired split between kernel and user memory. If the address range available to the kernel is less than the @@ -1005,20 +1004,20 @@ config HIGHMEM config X86_PAE bool "PAE (Physical Address Extension) Support" depends on X86_32 && !HIGHMEM4G - help + ---help--- PAE is required for NX support, and furthermore enables larger swapspace support for non-overcommit purposes. It has the cost of more pagetable lookup overhead, and also consumes more pagetable space per process. config ARCH_PHYS_ADDR_T_64BIT - def_bool X86_64 || X86_PAE + def_bool X86_64 || X86_PAE config DIRECT_GBPAGES bool "Enable 1GB pages for kernel pagetables" if EMBEDDED default y depends on X86_64 - help + ---help--- Allow the kernel linear mapping to use 1GB pages on CPUs that support it. This can improve the kernel's performance a tiny bit by reducing TLB pressure. If in doubt, say "Y". @@ -1028,9 +1027,8 @@ config NUMA bool "Numa Memory Allocation and Scheduler Support" depends on SMP depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL) - default n if X86_PC default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP) - help + ---help--- Enable NUMA (Non Uniform Memory Access) support. The kernel will try to allocate memory used by a CPU on the @@ -1053,19 +1051,19 @@ config K8_NUMA def_bool y prompt "Old style AMD Opteron NUMA detection" depends on X86_64 && NUMA && PCI - help - Enable K8 NUMA node topology detection. You should say Y here if - you have a multi processor AMD K8 system. This uses an old - method to read the NUMA configuration directly from the builtin - Northbridge of Opteron. It is recommended to use X86_64_ACPI_NUMA - instead, which also takes priority if both are compiled in. + ---help--- + Enable K8 NUMA node topology detection. You should say Y here if + you have a multi processor AMD K8 system. This uses an old + method to read the NUMA configuration directly from the builtin + Northbridge of Opteron. It is recommended to use X86_64_ACPI_NUMA + instead, which also takes priority if both are compiled in. config X86_64_ACPI_NUMA def_bool y prompt "ACPI NUMA detection" depends on X86_64 && NUMA && ACPI && PCI select ACPI_NUMA - help + ---help--- Enable ACPI SRAT based node topology detection. # Some NUMA nodes have memory ranges that span @@ -1080,7 +1078,7 @@ config NODES_SPAN_OTHER_NODES config NUMA_EMU bool "NUMA emulation" depends on X86_64 && NUMA - help + ---help--- Enable NUMA emulation. A flat machine will be split into virtual nodes when booted with "numa=fake=N", where N is the number of nodes. This is only useful for debugging. @@ -1093,7 +1091,7 @@ config NODES_SHIFT default "4" if X86_NUMAQ default "3" depends on NEED_MULTIPLE_NODES - help + ---help--- Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accomodate various tables. @@ -1131,7 +1129,7 @@ config ARCH_SPARSEMEM_DEFAULT config ARCH_SPARSEMEM_ENABLE def_bool y - depends on X86_64 || NUMA || (EXPERIMENTAL && X86_PC) || X86_GENERICARCH + depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD select SPARSEMEM_STATIC if X86_32 select SPARSEMEM_VMEMMAP_ENABLE if X86_64 @@ -1148,61 +1146,61 @@ source "mm/Kconfig" config HIGHPTE bool "Allocate 3rd-level pagetables from highmem" depends on X86_32 && (HIGHMEM4G || HIGHMEM64G) - help + ---help--- The VM uses one page table entry for each page of physical memory. For systems with a lot of RAM, this can be wasteful of precious low memory. Setting this option will put user-space page table entries in high memory. config X86_CHECK_BIOS_CORRUPTION - bool "Check for low memory corruption" - help - Periodically check for memory corruption in low memory, which - is suspected to be caused by BIOS. Even when enabled in the - configuration, it is disabled at runtime. Enable it by - setting "memory_corruption_check=1" on the kernel command - line. By default it scans the low 64k of memory every 60 - seconds; see the memory_corruption_check_size and - memory_corruption_check_period parameters in - Documentation/kernel-parameters.txt to adjust this. - - When enabled with the default parameters, this option has - almost no overhead, as it reserves a relatively small amount - of memory and scans it infrequently. It both detects corruption - and prevents it from affecting the running system. - - It is, however, intended as a diagnostic tool; if repeatable - BIOS-originated corruption always affects the same memory, - you can use memmap= to prevent the kernel from using that - memory. + bool "Check for low memory corruption" + ---help--- + Periodically check for memory corruption in low memory, which + is suspected to be caused by BIOS. Even when enabled in the + configuration, it is disabled at runtime. Enable it by + setting "memory_corruption_check=1" on the kernel command + line. By default it scans the low 64k of memory every 60 + seconds; see the memory_corruption_check_size and + memory_corruption_check_period parameters in + Documentation/kernel-parameters.txt to adjust this. + + When enabled with the default parameters, this option has + almost no overhead, as it reserves a relatively small amount + of memory and scans it infrequently. It both detects corruption + and prevents it from affecting the running system. + + It is, however, intended as a diagnostic tool; if repeatable + BIOS-originated corruption always affects the same memory, + you can use memmap= to prevent the kernel from using that + memory. config X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK - bool "Set the default setting of memory_corruption_check" + bool "Set the default setting of memory_corruption_check" depends on X86_CHECK_BIOS_CORRUPTION default y - help - Set whether the default state of memory_corruption_check is - on or off. + ---help--- + Set whether the default state of memory_corruption_check is + on or off. config X86_RESERVE_LOW_64K - bool "Reserve low 64K of RAM on AMI/Phoenix BIOSen" + bool "Reserve low 64K of RAM on AMI/Phoenix BIOSen" default y - help - Reserve the first 64K of physical RAM on BIOSes that are known - to potentially corrupt that memory range. A numbers of BIOSes are - known to utilize this area during suspend/resume, so it must not - be used by the kernel. + ---help--- + Reserve the first 64K of physical RAM on BIOSes that are known + to potentially corrupt that memory range. A numbers of BIOSes are + known to utilize this area during suspend/resume, so it must not + be used by the kernel. - Set this to N if you are absolutely sure that you trust the BIOS - to get all its memory reservations and usages right. + Set this to N if you are absolutely sure that you trust the BIOS + to get all its memory reservations and usages right. - If you have doubts about the BIOS (e.g. suspend/resume does not - work or there's kernel crashes after certain hardware hotplug - events) and it's not AMI or Phoenix, then you might want to enable - X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check typical - corruption patterns. + If you have doubts about the BIOS (e.g. suspend/resume does not + work or there's kernel crashes after certain hardware hotplug + events) and it's not AMI or Phoenix, then you might want to enable + X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check typical + corruption patterns. - Say Y if unsure. + Say Y if unsure. config MATH_EMULATION bool @@ -1268,7 +1266,7 @@ config MTRR_SANITIZER def_bool y prompt "MTRR cleanup support" depends on MTRR - help + ---help--- Convert MTRR layout from continuous to discrete, so X drivers can add writeback entries. @@ -1283,7 +1281,7 @@ config MTRR_SANITIZER_ENABLE_DEFAULT range 0 1 default "0" depends on MTRR_SANITIZER - help + ---help--- Enable mtrr cleanup default value config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT @@ -1291,7 +1289,7 @@ config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT range 0 7 default "1" depends on MTRR_SANITIZER - help + ---help--- mtrr cleanup spare entries default, it can be changed via mtrr_spare_reg_nr=N on the kernel command line. @@ -1299,7 +1297,7 @@ config X86_PAT bool prompt "x86 PAT support" depends on MTRR - help + ---help--- Use PAT attributes to setup page level cache control. PATs are the modern equivalents of MTRRs and are much more @@ -1314,20 +1312,20 @@ config EFI bool "EFI runtime service support" depends on ACPI ---help--- - This enables the kernel to use EFI runtime services that are - available (such as the EFI variable services). + This enables the kernel to use EFI runtime services that are + available (such as the EFI variable services). - This option is only useful on systems that have EFI firmware. - In addition, you should use the latest ELILO loader available - at <http://elilo.sourceforge.net> in order to take advantage - of EFI runtime services. However, even with this option, the - resultant kernel should continue to boot on existing non-EFI - platforms. + This option is only useful on systems that have EFI firmware. + In addition, you should use the latest ELILO loader available + at <http://elilo.sourceforge.net> in order to take advantage + of EFI runtime services. However, even with this option, the + resultant kernel should continue to boot on existing non-EFI + platforms. config SECCOMP def_bool y prompt "Enable seccomp to safely compute untrusted bytecode" - help + ---help--- This kernel feature is useful for number crunching applications that may need to compute untrusted bytecode during their execution. By using pipes or other transports made available to @@ -1340,13 +1338,16 @@ config SECCOMP If unsure, say Y. Only embedded should say N here. +config CC_STACKPROTECTOR_ALL + bool + config CC_STACKPROTECTOR bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)" - depends on X86_64 && EXPERIMENTAL && BROKEN - help - This option turns on the -fstack-protector GCC feature. This - feature puts, at the beginning of critical functions, a canary - value on the stack just before the return address, and validates + select CC_STACKPROTECTOR_ALL + ---help--- + This option turns on the -fstack-protector GCC feature. This + feature puts, at the beginning of functions, a canary value on + the stack just before the return address, and validates the value just before actually returning. Stack based buffer overflows (that need to overwrite this return address) now also overwrite the canary, which gets detected and the attack is then @@ -1354,22 +1355,14 @@ config CC_STACKPROTECTOR This feature requires gcc version 4.2 or above, or a distribution gcc with the feature backported. Older versions are automatically - detected and for those versions, this configuration option is ignored. - -config CC_STACKPROTECTOR_ALL - bool "Use stack-protector for all functions" - depends on CC_STACKPROTECTOR - help - Normally, GCC only inserts the canary value protection for - functions that use large-ish on-stack buffers. By enabling - this option, GCC will be asked to do this for ALL functions. + detected and for those versions, this configuration option is + ignored. (and a warning is printed during bootup) source kernel/Kconfig.hz config KEXEC bool "kexec system call" - depends on X86_BIOS_REBOOT - help + ---help--- kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot but it is independent of the system firmware. And like a reboot @@ -1386,7 +1379,7 @@ config KEXEC config CRASH_DUMP bool "kernel crash dumps" depends on X86_64 || (X86_32 && HIGHMEM) - help + ---help--- Generate crash dump after being started by kexec. This should be normally only set in special crash dump kernels which are loaded in the main kernel with kexec-tools into @@ -1401,7 +1394,7 @@ config KEXEC_JUMP bool "kexec jump (EXPERIMENTAL)" depends on EXPERIMENTAL depends on KEXEC && HIBERNATION && X86_32 - help + ---help--- Jump between original kernel and kexeced kernel and invoke code in physical address mode via KEXEC @@ -1410,7 +1403,7 @@ config PHYSICAL_START default "0x1000000" if X86_NUMAQ default "0x200000" if X86_64 default "0x100000" - help + ---help--- This gives the physical address where the kernel is loaded. If kernel is a not relocatable (CONFIG_RELOCATABLE=n) then @@ -1451,7 +1444,7 @@ config PHYSICAL_START config RELOCATABLE bool "Build a relocatable kernel (EXPERIMENTAL)" depends on EXPERIMENTAL - help + ---help--- This builds a kernel image that retains relocation information so it can be loaded someplace besides the default 1MB. The relocations tend to make the kernel binary about 10% larger, @@ -1471,7 +1464,7 @@ config PHYSICAL_ALIGN default "0x100000" if X86_32 default "0x200000" if X86_64 range 0x2000 0x400000 - help + ---help--- This value puts the alignment restrictions on physical address where kernel is loaded and run from. Kernel is compiled for an address which meets above alignment restriction. @@ -1492,7 +1485,7 @@ config PHYSICAL_ALIGN config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" - depends on SMP && HOTPLUG && !X86_VOYAGER + depends on SMP && HOTPLUG ---help--- Say Y here to allow turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. @@ -1504,7 +1497,7 @@ config COMPAT_VDSO def_bool y prompt "Compat VDSO support" depends on X86_32 || IA32_EMULATION - help + ---help--- Map the 32-bit VDSO to the predictable old-style address too. ---help--- Say N here if you are running a sufficiently recent glibc @@ -1516,7 +1509,7 @@ config COMPAT_VDSO config CMDLINE_BOOL bool "Built-in kernel command line" default n - help + ---help--- Allow for specifying boot arguments to the kernel at build time. On some systems (e.g. embedded ones), it is necessary or convenient to provide some or all of the @@ -1534,7 +1527,7 @@ config CMDLINE string "Built-in kernel command string" depends on CMDLINE_BOOL default "" - help + ---help--- Enter arguments here that should be compiled into the kernel image and used at boot time. If the boot loader provides a command line at boot time, it is appended to this string to @@ -1551,7 +1544,7 @@ config CMDLINE_OVERRIDE bool "Built-in command line overrides boot loader arguments" default n depends on CMDLINE_BOOL - help + ---help--- Set this option to 'Y' to have the kernel ignore the boot loader command line, and use ONLY the built-in command line. @@ -1573,7 +1566,6 @@ config HAVE_ARCH_EARLY_PFN_TO_NID depends on NUMA menu "Power management and ACPI options" - depends on !X86_VOYAGER config ARCH_HIBERNATION_HEADER def_bool y @@ -1651,7 +1643,7 @@ if APM config APM_IGNORE_USER_SUSPEND bool "Ignore USER SUSPEND" - help + ---help--- This option will ignore USER SUSPEND requests. On machines with a compliant APM BIOS, you want to say N. However, on the NEC Versa M series notebooks, it is necessary to say Y because of a BIOS bug. @@ -1675,7 +1667,7 @@ config APM_DO_ENABLE config APM_CPU_IDLE bool "Make CPU Idle calls when idle" - help + ---help--- Enable calls to APM CPU Idle/CPU Busy inside the kernel's idle loop. On some machines, this can activate improved power savings, such as a slowed CPU clock rate, when the machine is idle. These idle calls @@ -1686,7 +1678,7 @@ config APM_CPU_IDLE config APM_DISPLAY_BLANK bool "Enable console blanking using APM" - help + ---help--- Enable console blanking using the APM. Some laptops can use this to turn off the LCD backlight when the screen blanker of the Linux virtual console blanks the screen. Note that this is only used by @@ -1699,7 +1691,7 @@ config APM_DISPLAY_BLANK config APM_ALLOW_INTS bool "Allow interrupts during APM BIOS calls" - help + ---help--- Normally we disable external interrupts while we are making calls to the APM BIOS as a measure to lessen the effects of a badly behaving BIOS implementation. The BIOS should reenable interrupts if it @@ -1724,7 +1716,7 @@ config PCI bool "PCI support" default y select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC) - help + ---help--- Find out whether you have a PCI motherboard. PCI is the name of a bus system, i.e. the way the CPU talks to the other stuff inside your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or @@ -1795,40 +1787,51 @@ config PCI_MMCONFIG config DMAR bool "Support for DMA Remapping Devices (EXPERIMENTAL)" depends on X86_64 && PCI_MSI && ACPI && EXPERIMENTAL - help + ---help--- DMA remapping (DMAR) devices support enables independent address translations for Direct Memory Access (DMA) from devices. These DMA remapping devices are reported via ACPI tables and include PCI device scope covered by these DMA remapping devices. +config DMAR_DEFAULT_ON + def_bool n + prompt "Enable DMA Remapping Devices by default" + depends on DMAR + help + Selecting this option will enable a DMAR device at boot time if + one is found. If this option is not selected, DMAR support can + be enabled by passing intel_iommu=on to the kernel. It is + recommended you say N here while the DMAR code remains + experimental. + config DMAR_GFX_WA def_bool y prompt "Support for Graphics workaround" depends on DMAR - help - Current Graphics drivers tend to use physical address - for DMA and avoid using DMA APIs. Setting this config - option permits the IOMMU driver to set a unity map for - all the OS-visible memory. Hence the driver can continue - to use physical addresses for DMA. + ---help--- + Current Graphics drivers tend to use physical address + for DMA and avoid using DMA APIs. Setting this config + option permits the IOMMU driver to set a unity map for + all the OS-visible memory. Hence the driver can continue + to use physical addresses for DMA. config DMAR_FLOPPY_WA def_bool y depends on DMAR - help - Floppy disk drivers are know to bypass DMA API calls - thereby failing to work when IOMMU is enabled. This - workaround will setup a 1:1 mapping for the first - 16M to make floppy (an ISA device) work. + ---help--- + Floppy disk drivers are know to bypass DMA API calls + thereby failing to work when IOMMU is enabled. This + workaround will setup a 1:1 mapping for the first + 16M to make floppy (an ISA device) work. config INTR_REMAP bool "Support for Interrupt Remapping (EXPERIMENTAL)" depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL - help - Supports Interrupt remapping for IO-APIC and MSI devices. - To use x2apic mode in the CPU's which support x2APIC enhancements or - to support platforms with CPU's having > 8 bit APIC ID, say Y. + ---help--- + Supports Interrupt remapping for IO-APIC and MSI devices. + To use x2apic mode in the CPU's which support x2APIC enhancements or + to support platforms with CPU's having > 8 bit APIC ID, say Y. source "drivers/pci/pcie/Kconfig" @@ -1842,8 +1845,7 @@ if X86_32 config ISA bool "ISA support" - depends on !X86_VOYAGER - help + ---help--- Find out whether you have ISA slots on your motherboard. ISA is the name of a bus system, i.e. the way the CPU talks to the other stuff inside your box. Other bus systems are PCI, EISA, MicroChannel @@ -1869,9 +1871,8 @@ config EISA source "drivers/eisa/Kconfig" config MCA - bool "MCA support" if !X86_VOYAGER - default y if X86_VOYAGER - help + bool "MCA support" + ---help--- MicroChannel Architecture is found in some IBM PS/2 machines and laptops. It is a bus system similar to PCI or ISA. See <file:Documentation/mca.txt> (and especially the web page given @@ -1881,8 +1882,7 @@ source "drivers/mca/Kconfig" config SCx200 tristate "NatSemi SCx200 support" - depends on !X86_VOYAGER - help + ---help--- This provides basic support for National Semiconductor's (now AMD's) Geode processors. The driver probes for the PCI-IDs of several on-chip devices, so its a good dependency @@ -1894,7 +1894,7 @@ config SCx200HR_TIMER tristate "NatSemi SCx200 27MHz High-Resolution Timer Support" depends on SCx200 && GENERIC_TIME default y - help + ---help--- This driver provides a clocksource built upon the on-chip 27MHz high-resolution timer. Its also a workaround for NSC Geode SC-1100's buggy TSC, which loses time when the @@ -1905,7 +1905,7 @@ config GEODE_MFGPT_TIMER def_bool y prompt "Geode Multi-Function General Purpose Timer (MFGPT) events" depends on MGEODE_LX && GENERIC_TIME && GENERIC_CLOCKEVENTS - help + ---help--- This driver provides a clock event source based on the MFGPT timer(s) in the CS5535 and CS5536 companion chip for the geode. MFGPTs have a better resolution and max interval than the @@ -1914,7 +1914,7 @@ config GEODE_MFGPT_TIMER config OLPC bool "One Laptop Per Child support" default n - help + ---help--- Add support for detecting the unique features of the OLPC XO hardware. @@ -1939,16 +1939,16 @@ config IA32_EMULATION bool "IA32 Emulation" depends on X86_64 select COMPAT_BINFMT_ELF - help + ---help--- Include code to run 32-bit programs under a 64-bit kernel. You should likely turn this on, unless you're 100% sure that you don't have any 32-bit programs left. config IA32_AOUT - tristate "IA32 a.out support" - depends on IA32_EMULATION - help - Support old a.out binaries in the 32bit emulation. + tristate "IA32 a.out support" + depends on IA32_EMULATION + ---help--- + Support old a.out binaries in the 32bit emulation. config COMPAT def_bool y diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 8078955845a..a95eaf0e582 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -50,7 +50,7 @@ config M386 config M486 bool "486" depends on X86_32 - help + ---help--- Select this for a 486 series processor, either Intel or one of the compatible processors from AMD, Cyrix, IBM, or Intel. Includes DX, DX2, and DX4 variants; also SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or @@ -59,7 +59,7 @@ config M486 config M586 bool "586/K5/5x86/6x86/6x86MX" depends on X86_32 - help + ---help--- Select this for an 586 or 686 series processor such as the AMD K5, the Cyrix 5x86, 6x86 and 6x86MX. This choice does not assume the RDTSC (Read Time Stamp Counter) instruction. @@ -67,21 +67,21 @@ config M586 config M586TSC bool "Pentium-Classic" depends on X86_32 - help + ---help--- Select this for a Pentium Classic processor with the RDTSC (Read Time Stamp Counter) instruction for benchmarking. config M586MMX bool "Pentium-MMX" depends on X86_32 - help + ---help--- Select this for a Pentium with the MMX graphics/multimedia extended instructions. config M686 bool "Pentium-Pro" depends on X86_32 - help + ---help--- Select this for Intel Pentium Pro chips. This enables the use of Pentium Pro extended instructions, and disables the init-time guard against the f00f bug found in earlier Pentiums. @@ -89,7 +89,7 @@ config M686 config MPENTIUMII bool "Pentium-II/Celeron(pre-Coppermine)" depends on X86_32 - help + ---help--- Select this for Intel chips based on the Pentium-II and pre-Coppermine Celeron core. This option enables an unaligned copy optimization, compiles the kernel with optimization flags @@ -99,7 +99,7 @@ config MPENTIUMII config MPENTIUMIII bool "Pentium-III/Celeron(Coppermine)/Pentium-III Xeon" depends on X86_32 - help + ---help--- Select this for Intel chips based on the Pentium-III and Celeron-Coppermine core. This option enables use of some extended prefetch instructions in addition to the Pentium II @@ -108,14 +108,14 @@ config MPENTIUMIII config MPENTIUMM bool "Pentium M" depends on X86_32 - help + ---help--- Select this for Intel Pentium M (not Pentium-4 M) notebook chips. config MPENTIUM4 bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon" depends on X86_32 - help + ---help--- Select this for Intel Pentium 4 chips. This includes the Pentium 4, Pentium D, P4-based Celeron and Xeon, and Pentium-4 M (not Pentium M) chips. This option enables compile @@ -151,7 +151,7 @@ config MPENTIUM4 config MK6 bool "K6/K6-II/K6-III" depends on X86_32 - help + ---help--- Select this for an AMD K6-family processor. Enables use of some extended instructions, and passes appropriate optimization flags to GCC. @@ -159,22 +159,22 @@ config MK6 config MK7 bool "Athlon/Duron/K7" depends on X86_32 - help + ---help--- Select this for an AMD Athlon K7-family processor. Enables use of some extended instructions, and passes appropriate optimization flags to GCC. config MK8 bool "Opteron/Athlon64/Hammer/K8" - help - Select this for an AMD Opteron or Athlon64 Hammer-family processor. Enables - use of some extended instructions, and passes appropriate optimization - flags to GCC. + ---help--- + Select this for an AMD Opteron or Athlon64 Hammer-family processor. + Enables use of some extended instructions, and passes appropriate + optimization flags to GCC. config MCRUSOE bool "Crusoe" depends on X86_32 - help + ---help--- Select this for a Transmeta Crusoe processor. Treats the processor like a 586 with TSC, and sets some GCC optimization flags (like a Pentium Pro with no alignment requirements). @@ -182,13 +182,13 @@ config MCRUSOE config MEFFICEON bool "Efficeon" depends on X86_32 - help + ---help--- Select this for a Transmeta Efficeon processor. config MWINCHIPC6 bool "Winchip-C6" depends on X86_32 - help + ---help--- Select this for an IDT Winchip C6 chip. Linux and GCC treat this chip as a 586TSC with some extended instructions and alignment requirements. @@ -196,7 +196,7 @@ config MWINCHIPC6 config MWINCHIP3D bool "Winchip-2/Winchip-2A/Winchip-3" depends on X86_32 - help + ---help--- Select this for an IDT Winchip-2, 2A or 3. Linux and GCC treat this chip as a 586TSC with some extended instructions and alignment requirements. Also enable out of order memory @@ -206,19 +206,19 @@ config MWINCHIP3D config MGEODEGX1 bool "GeodeGX1" depends on X86_32 - help + ---help--- Select this for a Geode GX1 (Cyrix MediaGX) chip. config MGEODE_LX bool "Geode GX/LX" depends on X86_32 - help + ---help--- Select this for AMD Geode GX and LX processors. config MCYRIXIII bool "CyrixIII/VIA-C3" depends on X86_32 - help + ---help--- Select this for a Cyrix III or C3 chip. Presently Linux and GCC treat this chip as a generic 586. Whilst the CPU is 686 class, it lacks the cmov extension which gcc assumes is present when @@ -230,7 +230,7 @@ config MCYRIXIII config MVIAC3_2 bool "VIA C3-2 (Nehemiah)" depends on X86_32 - help + ---help--- Select this for a VIA C3 "Nehemiah". Selecting this enables usage of SSE and tells gcc to treat the CPU as a 686. Note, this kernel will not boot on older (pre model 9) C3s. @@ -238,14 +238,14 @@ config MVIAC3_2 config MVIAC7 bool "VIA C7" depends on X86_32 - help + ---help--- Select this for a VIA C7. Selecting this uses the correct cache shift and tells gcc to treat the CPU as a 686. config MPSC bool "Intel P4 / older Netburst based Xeon" depends on X86_64 - help + ---help--- Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey Xeon CPUs with Intel 64bit which is compatible with x86-64. Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the @@ -255,15 +255,17 @@ config MPSC config MCORE2 bool "Core 2/newer Xeon" - help - Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and 53xx) - CPUs. You can distinguish newer from older Xeons by the CPU family - in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo) + ---help--- + + Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and + 53xx) CPUs. You can distinguish newer from older Xeons by the CPU + family in /proc/cpuinfo. Newer ones have 6 and older ones 15 + (not a typo) config GENERIC_CPU bool "Generic-x86-64" depends on X86_64 - help + ---help--- Generic x86-64 CPU. Run equally well on all x86-64 CPUs. @@ -272,7 +274,7 @@ endchoice config X86_GENERIC bool "Generic x86 support" depends on X86_32 - help + ---help--- Instead of just including optimizations for the selected x86 variant (e.g. PII, Crusoe or Athlon), include some more generic optimizations as well. This will make the kernel @@ -292,25 +294,23 @@ config X86_CPU # Define implied options from the CPU selection here config X86_L1_CACHE_BYTES int - default "128" if GENERIC_CPU || MPSC - default "64" if MK8 || MCORE2 - depends on X86_64 + default "128" if MPSC + default "64" if GENERIC_CPU || MK8 || MCORE2 || X86_32 config X86_INTERNODE_CACHE_BYTES int default "4096" if X86_VSMP default X86_L1_CACHE_BYTES if !X86_VSMP - depends on X86_64 config X86_CMPXCHG def_bool X86_64 || (X86_32 && !M386) config X86_L1_CACHE_SHIFT int - default "7" if MPENTIUM4 || X86_GENERIC || GENERIC_CPU || MPSC + default "7" if MPENTIUM4 || MPSC default "4" if X86_ELAN || M486 || M386 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX - default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7 + default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7 || X86_GENERIC || GENERIC_CPU config X86_XADD def_bool y @@ -319,15 +319,15 @@ config X86_XADD config X86_PPRO_FENCE bool "PentiumPro memory ordering errata workaround" depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1 - help - Old PentiumPro multiprocessor systems had errata that could cause memory - operations to violate the x86 ordering standard in rare cases. Enabling this - option will attempt to work around some (but not all) occurances of - this problem, at the cost of much heavier spinlock and memory barrier - operations. + ---help--- + Old PentiumPro multiprocessor systems had errata that could cause + memory operations to violate the x86 ordering standard in rare cases. + Enabling this option will attempt to work around some (but not all) + occurances of this problem, at the cost of much heavier spinlock and + memory barrier operations. - If unsure, say n here. Even distro kernels should think twice before enabling - this: there are few systems, and an unlikely bug. + If unsure, say n here. Even distro kernels should think twice before + enabling this: there are few systems, and an unlikely bug. config X86_F00F_BUG def_bool y @@ -412,14 +412,14 @@ config X86_DEBUGCTLMSR menuconfig PROCESSOR_SELECT bool "Supported processor vendors" if EMBEDDED - help + ---help--- This lets you choose what x86 vendor support code your kernel will include. config CPU_SUP_INTEL default y bool "Support Intel processors" if PROCESSOR_SELECT - help + ---help--- This enables detection, tunings and quirks for Intel processors You need this enabled if you want your kernel to run on an @@ -433,7 +433,7 @@ config CPU_SUP_CYRIX_32 default y bool "Support Cyrix processors" if PROCESSOR_SELECT depends on !64BIT - help + ---help--- This enables detection, tunings and quirks for Cyrix processors You need this enabled if you want your kernel to run on a @@ -446,7 +446,7 @@ config CPU_SUP_CYRIX_32 config CPU_SUP_AMD default y bool "Support AMD processors" if PROCESSOR_SELECT - help + ---help--- This enables detection, tunings and quirks for AMD processors You need this enabled if you want your kernel to run on an @@ -460,7 +460,7 @@ config CPU_SUP_CENTAUR_32 default y bool "Support Centaur processors" if PROCESSOR_SELECT depends on !64BIT - help + ---help--- This enables detection, tunings and quirks for Centaur processors You need this enabled if you want your kernel to run on a @@ -474,7 +474,7 @@ config CPU_SUP_CENTAUR_64 default y bool "Support Centaur processors" if PROCESSOR_SELECT depends on 64BIT - help + ---help--- This enables detection, tunings and quirks for Centaur processors You need this enabled if you want your kernel to run on a @@ -488,7 +488,7 @@ config CPU_SUP_TRANSMETA_32 default y bool "Support Transmeta processors" if PROCESSOR_SELECT depends on !64BIT - help + ---help--- This enables detection, tunings and quirks for Transmeta processors You need this enabled if you want your kernel to run on a @@ -502,7 +502,7 @@ config CPU_SUP_UMC_32 default y bool "Support UMC processors" if PROCESSOR_SELECT depends on !64BIT - help + ---help--- This enables detection, tunings and quirks for UMC processors You need this enabled if you want your kernel to run on a @@ -521,7 +521,7 @@ config X86_PTRACE_BTS bool "Branch Trace Store" default y depends on X86_DEBUGCTLMSR - help + ---help--- This adds a ptrace interface to the hardware's branch trace store. Debuggers may use it to collect an execution trace of the debugged diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 10d6cc3fd05..ba4781b9389 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -7,7 +7,7 @@ source "lib/Kconfig.debug" config STRICT_DEVMEM bool "Filter access to /dev/mem" - help + ---help--- If this option is disabled, you allow userspace (root) access to all of memory, including kernel and userspace memory. Accidental access to this is obviously disastrous, but specific access can @@ -25,7 +25,7 @@ config STRICT_DEVMEM config X86_VERBOSE_BOOTUP bool "Enable verbose x86 bootup info messages" default y - help + ---help--- Enables the informational output from the decompression stage (e.g. bzImage) of the boot. If you disable this you will still see errors. Disable this if you want silent bootup. @@ -33,7 +33,7 @@ config X86_VERBOSE_BOOTUP config EARLY_PRINTK bool "Early printk" if EMBEDDED default y - help + ---help--- Write kernel log output directly into the VGA buffer or to a serial port. @@ -47,7 +47,7 @@ config EARLY_PRINTK_DBGP bool "Early printk via EHCI debug port" default n depends on EARLY_PRINTK && PCI - help + ---help--- Write kernel log output directly into the EHCI debug port. This is useful for kernel debugging when your machine crashes very @@ -59,14 +59,14 @@ config EARLY_PRINTK_DBGP config DEBUG_STACKOVERFLOW bool "Check for stack overflows" depends on DEBUG_KERNEL - help + ---help--- This option will cause messages to be printed if free stack space drops below a certain limit. config DEBUG_STACK_USAGE bool "Stack utilization instrumentation" depends on DEBUG_KERNEL - help + ---help--- Enables the display of the minimum amount of free stack which each task has ever had available in the sysrq-T and sysrq-P debug output. @@ -75,7 +75,7 @@ config DEBUG_STACK_USAGE config DEBUG_PAGEALLOC bool "Debug page memory allocations" depends on DEBUG_KERNEL - help + ---help--- Unmap pages from the kernel linear mapping after free_pages(). This results in a large slowdown, but helps to find certain types of memory corruptions. @@ -83,9 +83,9 @@ config DEBUG_PAGEALLOC config DEBUG_PER_CPU_MAPS bool "Debug access to per_cpu maps" depends on DEBUG_KERNEL - depends on X86_SMP + depends on SMP default n - help + ---help--- Say Y to verify that the per_cpu map being accessed has been setup. Adds a fair amount of code to kernel memory and decreases performance. @@ -96,7 +96,7 @@ config X86_PTDUMP bool "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL select DEBUG_FS - help + ---help--- Say Y here if you want to show the kernel pagetable layout in a debugfs file. This information is only useful for kernel developers who are working in architecture specific areas of the kernel. @@ -108,7 +108,7 @@ config DEBUG_RODATA bool "Write protect kernel read-only data structures" default y depends on DEBUG_KERNEL - help + ---help--- Mark the kernel read-only data as write-protected in the pagetables, in order to catch accidental (and incorrect) writes to such const data. This is recommended so that we can catch kernel bugs sooner. @@ -117,7 +117,8 @@ config DEBUG_RODATA config DEBUG_RODATA_TEST bool "Testcase for the DEBUG_RODATA feature" depends on DEBUG_RODATA - help + default y + ---help--- This option enables a testcase for the DEBUG_RODATA feature as well as for the change_page_attr() infrastructure. If in doubt, say "N" @@ -125,7 +126,7 @@ config DEBUG_RODATA_TEST config DEBUG_NX_TEST tristate "Testcase for the NX non-executable stack feature" depends on DEBUG_KERNEL && m - help + ---help--- This option enables a testcase for the CPU NX capability and the software setup of this feature. If in doubt, say "N" @@ -133,7 +134,7 @@ config DEBUG_NX_TEST config 4KSTACKS bool "Use 4Kb for kernel stacks instead of 8Kb" depends on X86_32 - help + ---help--- If you say Y here the kernel will use a 4Kb stacksize for the kernel stack attached to each process/thread. This facilitates running more threads on a system and also reduces the pressure @@ -144,7 +145,7 @@ config DOUBLEFAULT default y bool "Enable doublefault exception handler" if EMBEDDED depends on X86_32 - help + ---help--- This option allows trapping of rare doublefault exceptions that would otherwise cause a system to silently reboot. Disabling this option saves about 4k and might cause you much additional grey @@ -154,7 +155,7 @@ config IOMMU_DEBUG bool "Enable IOMMU debugging" depends on GART_IOMMU && DEBUG_KERNEL depends on X86_64 - help + ---help--- Force the IOMMU to on even when you have less than 4GB of memory and add debugging code. On overflow always panic. And allow to enable IOMMU leak tracing. Can be disabled at boot @@ -170,7 +171,7 @@ config IOMMU_LEAK bool "IOMMU leak tracing" depends on DEBUG_KERNEL depends on IOMMU_DEBUG - help + ---help--- Add a simple leak tracer to the IOMMU code. This is useful when you are debugging a buggy device driver that leaks IOMMU mappings. @@ -223,25 +224,25 @@ choice config IO_DELAY_0X80 bool "port 0x80 based port-IO delay [recommended]" - help + ---help--- This is the traditional Linux IO delay used for in/out_p. It is the most tested hence safest selection here. config IO_DELAY_0XED bool "port 0xed based port-IO delay" - help + ---help--- Use port 0xed as the IO delay. This frees up port 0x80 which is often used as a hardware-debug port. config IO_DELAY_UDELAY bool "udelay based port-IO delay" - help + ---help--- Use udelay(2) as the IO delay method. This provides the delay while not having any side-effect on the IO port space. config IO_DELAY_NONE bool "no port-IO delay" - help + ---help--- No port-IO delay. Will break on old boxes that require port-IO delay for certain operations. Should work on most new machines. @@ -275,18 +276,18 @@ config DEBUG_BOOT_PARAMS bool "Debug boot parameters" depends on DEBUG_KERNEL depends on DEBUG_FS - help + ---help--- This option will cause struct boot_params to be exported via debugfs. config CPA_DEBUG bool "CPA self-test code" depends on DEBUG_KERNEL - help + ---help--- Do change_page_attr() self-tests every 30 seconds. config OPTIMIZE_INLINING bool "Allow gcc to uninline functions marked 'inline'" - help + ---help--- This option determines if the kernel forces gcc to inline the functions developers have marked 'inline'. Doing so takes away freedom from gcc to do what it thinks is best, which is desirable for the gcc 3.x series of @@ -299,4 +300,3 @@ config OPTIMIZE_INLINING If unsure, say N. endmenu - diff --git a/arch/x86/Makefile b/arch/x86/Makefile index d1a47adb5ae..1836191839e 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -70,14 +70,17 @@ else # this works around some issues with generating unwind tables in older gccs # newer gccs do it by default KBUILD_CFLAGS += -maccumulate-outgoing-args +endif - stackp := $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh - stackp-$(CONFIG_CC_STACKPROTECTOR) := $(shell $(stackp) \ - "$(CC)" -fstack-protector ) - stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(stackp) \ - "$(CC)" -fstack-protector-all ) - - KBUILD_CFLAGS += $(stackp-y) +ifdef CONFIG_CC_STACKPROTECTOR + cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh + ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC)),y) + stackp-y := -fstack-protector + stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += -fstack-protector-all + KBUILD_CFLAGS += $(stackp-y) + else + $(warning stack protector enabled but no compiler support) + endif endif # Stackpointer is addressed different for 32 bit and 64 bit x86 @@ -102,29 +105,6 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # prevent gcc from generating any FP code by mistake KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) -### -# Sub architecture support -# fcore-y is linked before mcore-y files. - -# Default subarch .c files -mcore-y := arch/x86/mach-default/ - -# Voyager subarch support -mflags-$(CONFIG_X86_VOYAGER) := -Iarch/x86/include/asm/mach-voyager -mcore-$(CONFIG_X86_VOYAGER) := arch/x86/mach-voyager/ - -# generic subarchitecture -mflags-$(CONFIG_X86_GENERICARCH):= -Iarch/x86/include/asm/mach-generic -fcore-$(CONFIG_X86_GENERICARCH) += arch/x86/mach-generic/ -mcore-$(CONFIG_X86_GENERICARCH) := arch/x86/mach-default/ - -# default subarch .h files -mflags-y += -Iarch/x86/include/asm/mach-default - -# 64 bit does not support subarch support - clear sub arch variables -fcore-$(CONFIG_X86_64) := -mcore-$(CONFIG_X86_64) := - KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) @@ -150,9 +130,6 @@ core-$(CONFIG_LGUEST_GUEST) += arch/x86/lguest/ core-y += arch/x86/kernel/ core-y += arch/x86/mm/ -# Remaining sub architecture files -core-y += $(mcore-y) - core-y += arch/x86/crypto/ core-y += arch/x86/vdso/ core-$(CONFIG_IA32_EMULATION) += arch/x86/ia32/ diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index edba00d98ac..739bce993b5 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -188,7 +188,6 @@ CONFIG_GENERIC_CLOCKEVENTS_BUILD=y CONFIG_SMP=y CONFIG_X86_FIND_SMP_CONFIG=y CONFIG_X86_MPPARSE=y -CONFIG_X86_PC=y # CONFIG_X86_ELAN is not set # CONFIG_X86_VOYAGER is not set # CONFIG_X86_GENERICARCH is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 322dd2748fc..02b514e8f4c 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -187,7 +187,6 @@ CONFIG_GENERIC_CLOCKEVENTS_BUILD=y CONFIG_SMP=y CONFIG_X86_FIND_SMP_CONFIG=y CONFIG_X86_MPPARSE=y -CONFIG_X86_PC=y # CONFIG_X86_ELAN is not set # CONFIG_X86_VOYAGER is not set # CONFIG_X86_GENERICARCH is not set diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 9dabd00e980..dd77ac0cac4 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -46,78 +46,83 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where); int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { - int err; + int err = 0; if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) return -EFAULT; - /* If you change siginfo_t structure, please make sure that - this code is fixed accordingly. - It should never copy any pad contained in the structure - to avoid security leaks, but must copy the generic - 3 ints plus the relevant union member. */ - err = __put_user(from->si_signo, &to->si_signo); - err |= __put_user(from->si_errno, &to->si_errno); - err |= __put_user((short)from->si_code, &to->si_code); - - if (from->si_code < 0) { - err |= __put_user(from->si_pid, &to->si_pid); - err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user(ptr_to_compat(from->si_ptr), &to->si_ptr); - } else { - /* - * First 32bits of unions are always present: - * si_pid === si_band === si_tid === si_addr(LS half) - */ - err |= __put_user(from->_sifields._pad[0], - &to->_sifields._pad[0]); - switch (from->si_code >> 16) { - case __SI_FAULT >> 16: - break; - case __SI_CHLD >> 16: - err |= __put_user(from->si_utime, &to->si_utime); - err |= __put_user(from->si_stime, &to->si_stime); - err |= __put_user(from->si_status, &to->si_status); - /* FALL THROUGH */ - default: - case __SI_KILL >> 16: - err |= __put_user(from->si_uid, &to->si_uid); - break; - case __SI_POLL >> 16: - err |= __put_user(from->si_fd, &to->si_fd); - break; - case __SI_TIMER >> 16: - err |= __put_user(from->si_overrun, &to->si_overrun); - err |= __put_user(ptr_to_compat(from->si_ptr), - &to->si_ptr); - break; - /* This is not generated by the kernel as of now. */ - case __SI_RT >> 16: - case __SI_MESGQ >> 16: - err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user(from->si_int, &to->si_int); - break; + put_user_try { + /* If you change siginfo_t structure, please make sure that + this code is fixed accordingly. + It should never copy any pad contained in the structure + to avoid security leaks, but must copy the generic + 3 ints plus the relevant union member. */ + put_user_ex(from->si_signo, &to->si_signo); + put_user_ex(from->si_errno, &to->si_errno); + put_user_ex((short)from->si_code, &to->si_code); + + if (from->si_code < 0) { + put_user_ex(from->si_pid, &to->si_pid); + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); + } else { + /* + * First 32bits of unions are always present: + * si_pid === si_band === si_tid === si_addr(LS half) + */ + put_user_ex(from->_sifields._pad[0], + &to->_sifields._pad[0]); + switch (from->si_code >> 16) { + case __SI_FAULT >> 16: + break; + case __SI_CHLD >> 16: + put_user_ex(from->si_utime, &to->si_utime); + put_user_ex(from->si_stime, &to->si_stime); + put_user_ex(from->si_status, &to->si_status); + /* FALL THROUGH */ + default: + case __SI_KILL >> 16: + put_user_ex(from->si_uid, &to->si_uid); + break; + case __SI_POLL >> 16: + put_user_ex(from->si_fd, &to->si_fd); + break; + case __SI_TIMER >> 16: + put_user_ex(from->si_overrun, &to->si_overrun); + put_user_ex(ptr_to_compat(from->si_ptr), + &to->si_ptr); + break; + /* This is not generated by the kernel as of now. */ + case __SI_RT >> 16: + case __SI_MESGQ >> 16: + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(from->si_int, &to->si_int); + break; + } } - } + } put_user_catch(err); + return err; } int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - int err; + int err = 0; u32 ptr32; if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) return -EFAULT; - err = __get_user(to->si_signo, &from->si_signo); - err |= __get_user(to->si_errno, &from->si_errno); - err |= __get_user(to->si_code, &from->si_code); + get_user_try { + get_user_ex(to->si_signo, &from->si_signo); + get_user_ex(to->si_errno, &from->si_errno); + get_user_ex(to->si_code, &from->si_code); - err |= __get_user(to->si_pid, &from->si_pid); - err |= __get_user(to->si_uid, &from->si_uid); - err |= __get_user(ptr32, &from->si_ptr); - to->si_ptr = compat_ptr(ptr32); + get_user_ex(to->si_pid, &from->si_pid); + get_user_ex(to->si_uid, &from->si_uid); + get_user_ex(ptr32, &from->si_ptr); + to->si_ptr = compat_ptr(ptr32); + } get_user_catch(err); return err; } @@ -142,17 +147,23 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr, struct pt_regs *regs) { stack_t uss, uoss; - int ret; + int ret, err = 0; mm_segment_t seg; if (uss_ptr) { u32 ptr; memset(&uss, 0, sizeof(stack_t)); - if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)) || - __get_user(ptr, &uss_ptr->ss_sp) || - __get_user(uss.ss_flags, &uss_ptr->ss_flags) || - __get_user(uss.ss_size, &uss_ptr->ss_size)) + if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t))) + return -EFAULT; + + get_user_try { + get_user_ex(ptr, &uss_ptr->ss_sp); + get_user_ex(uss.ss_flags, &uss_ptr->ss_flags); + get_user_ex(uss.ss_size, &uss_ptr->ss_size); + } get_user_catch(err); + + if (err) return -EFAULT; uss.ss_sp = compat_ptr(ptr); } @@ -161,10 +172,16 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr, ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp); set_fs(seg); if (ret >= 0 && uoss_ptr) { - if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)) || - __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) || - __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) || - __put_user(uoss.ss_size, &uoss_ptr->ss_size)) + if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t))) + return -EFAULT; + + put_user_try { + put_user_ex(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp); + put_user_ex(uoss.ss_flags, &uoss_ptr->ss_flags); + put_user_ex(uoss.ss_size, &uoss_ptr->ss_size); + } put_user_catch(err); + + if (err) ret = -EFAULT; } return ret; @@ -174,18 +191,18 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr, * Do a signal return; undo the signal stack. */ #define COPY(x) { \ - err |= __get_user(regs->x, &sc->x); \ + get_user_ex(regs->x, &sc->x); \ } #define COPY_SEG_CPL3(seg) { \ unsigned short tmp; \ - err |= __get_user(tmp, &sc->seg); \ + get_user_ex(tmp, &sc->seg); \ regs->seg = tmp | 3; \ } #define RELOAD_SEG(seg) { \ unsigned int cur, pre; \ - err |= __get_user(pre, &sc->seg); \ + get_user_ex(pre, &sc->seg); \ savesegment(seg, cur); \ pre |= 3; \ if (pre != cur) \ @@ -209,39 +226,42 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, sc, sc->err, sc->ip, sc->cs, sc->flags); #endif - /* - * Reload fs and gs if they have changed in the signal - * handler. This does not handle long fs/gs base changes in - * the handler, but does not clobber them at least in the - * normal case. - */ - err |= __get_user(gs, &sc->gs); - gs |= 3; - savesegment(gs, oldgs); - if (gs != oldgs) - load_gs_index(gs); - - RELOAD_SEG(fs); - RELOAD_SEG(ds); - RELOAD_SEG(es); - - COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); - COPY(dx); COPY(cx); COPY(ip); - /* Don't touch extended registers */ - - COPY_SEG_CPL3(cs); - COPY_SEG_CPL3(ss); - - err |= __get_user(tmpflags, &sc->flags); - regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); - /* disable syscall checks */ - regs->orig_ax = -1; - - err |= __get_user(tmp, &sc->fpstate); - buf = compat_ptr(tmp); - err |= restore_i387_xstate_ia32(buf); - - err |= __get_user(*pax, &sc->ax); + get_user_try { + /* + * Reload fs and gs if they have changed in the signal + * handler. This does not handle long fs/gs base changes in + * the handler, but does not clobber them at least in the + * normal case. + */ + get_user_ex(gs, &sc->gs); + gs |= 3; + savesegment(gs, oldgs); + if (gs != oldgs) + load_gs_index(gs); + + RELOAD_SEG(fs); + RELOAD_SEG(ds); + RELOAD_SEG(es); + + COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); + COPY(dx); COPY(cx); COPY(ip); + /* Don't touch extended registers */ + + COPY_SEG_CPL3(cs); + COPY_SEG_CPL3(ss); + + get_user_ex(tmpflags, &sc->flags); + regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); + /* disable syscall checks */ + regs->orig_ax = -1; + + get_user_ex(tmp, &sc->fpstate); + buf = compat_ptr(tmp); + err |= restore_i387_xstate_ia32(buf); + + get_user_ex(*pax, &sc->ax); + } get_user_catch(err); + return err; } @@ -319,36 +339,38 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, { int tmp, err = 0; - savesegment(gs, tmp); - err |= __put_user(tmp, (unsigned int __user *)&sc->gs); - savesegment(fs, tmp); - err |= __put_user(tmp, (unsigned int __user *)&sc->fs); - savesegment(ds, tmp); - err |= __put_user(tmp, (unsigned int __user *)&sc->ds); - savesegment(es, tmp); - err |= __put_user(tmp, (unsigned int __user *)&sc->es); - - err |= __put_user(regs->di, &sc->di); - err |= __put_user(regs->si, &sc->si); - err |= __put_user(regs->bp, &sc->bp); - err |= __put_user(regs->sp, &sc->sp); - err |= __put_user(regs->bx, &sc->bx); - err |= __put_user(regs->dx, &sc->dx); - err |= __put_user(regs->cx, &sc->cx); - err |= __put_user(regs->ax, &sc->ax); - err |= __put_user(current->thread.trap_no, &sc->trapno); - err |= __put_user(current->thread.error_code, &sc->err); - err |= __put_user(regs->ip, &sc->ip); - err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs); - err |= __put_user(regs->flags, &sc->flags); - err |= __put_user(regs->sp, &sc->sp_at_signal); - err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss); - - err |= __put_user(ptr_to_compat(fpstate), &sc->fpstate); - - /* non-iBCS2 extensions.. */ - err |= __put_user(mask, &sc->oldmask); - err |= __put_user(current->thread.cr2, &sc->cr2); + put_user_try { + savesegment(gs, tmp); + put_user_ex(tmp, (unsigned int __user *)&sc->gs); + savesegment(fs, tmp); + put_user_ex(tmp, (unsigned int __user *)&sc->fs); + savesegment(ds, tmp); + put_user_ex(tmp, (unsigned int __user *)&sc->ds); + savesegment(es, tmp); + put_user_ex(tmp, (unsigned int __user *)&sc->es); + + put_user_ex(regs->di, &sc->di); + put_user_ex(regs->si, &sc->si); + put_user_ex(regs->bp, &sc->bp); + put_user_ex(regs->sp, &sc->sp); + put_user_ex(regs->bx, &sc->bx); + put_user_ex(regs->dx, &sc->dx); + put_user_ex(regs->cx, &sc->cx); + put_user_ex(regs->ax, &sc->ax); + put_user_ex(current->thread.trap_no, &sc->trapno); + put_user_ex(current->thread.error_code, &sc->err); + put_user_ex(regs->ip, &sc->ip); + put_user_ex(regs->cs, (unsigned int __user *)&sc->cs); + put_user_ex(regs->flags, &sc->flags); + put_user_ex(regs->sp, &sc->sp_at_signal); + put_user_ex(regs->ss, (unsigned int __user *)&sc->ss); + + put_user_ex(ptr_to_compat(fpstate), &sc->fpstate); + + /* non-iBCS2 extensions.. */ + put_user_ex(mask, &sc->oldmask); + put_user_ex(current->thread.cr2, &sc->cr2); + } put_user_catch(err); return err; } @@ -437,13 +459,17 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka, else restorer = &frame->retcode; } - err |= __put_user(ptr_to_compat(restorer), &frame->pretcode); - /* - * These are actually not used anymore, but left because some - * gdb versions depend on them as a marker. - */ - err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode); + put_user_try { + put_user_ex(ptr_to_compat(restorer), &frame->pretcode); + + /* + * These are actually not used anymore, but left because some + * gdb versions depend on them as a marker. + */ + put_user_ex(*((u64 *)&code), (u64 *)frame->retcode); + } put_user_catch(err); + if (err) return -EFAULT; @@ -496,41 +522,40 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) return -EFAULT; - err |= __put_user(sig, &frame->sig); - err |= __put_user(ptr_to_compat(&frame->info), &frame->pinfo); - err |= __put_user(ptr_to_compat(&frame->uc), &frame->puc); - err |= copy_siginfo_to_user32(&frame->info, info); - if (err) - return -EFAULT; + put_user_try { + put_user_ex(sig, &frame->sig); + put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo); + put_user_ex(ptr_to_compat(&frame->uc), &frame->puc); + err |= copy_siginfo_to_user32(&frame->info, info); - /* Create the ucontext. */ - if (cpu_has_xsave) - err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags); - else - err |= __put_user(0, &frame->uc.uc_flags); - err |= __put_user(0, &frame->uc.uc_link); - err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - if (err) - return -EFAULT; + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + if (ka->sa.sa_flags & SA_RESTORER) + restorer = ka->sa.sa_restorer; + else + restorer = VDSO32_SYMBOL(current->mm->context.vdso, + rt_sigreturn); + put_user_ex(ptr_to_compat(restorer), &frame->pretcode); + + /* + * Not actually used anymore, but left because some gdb + * versions need it. + */ + put_user_ex(*((u64 *)&code), (u64 *)frame->retcode); + } put_user_catch(err); - if (ka->sa.sa_flags & SA_RESTORER) - restorer = ka->sa.sa_restorer; - else - restorer = VDSO32_SYMBOL(current->mm->context.vdso, - rt_sigreturn); - err |= __put_user(ptr_to_compat(restorer), &frame->pretcode); - - /* - * Not actually used anymore, but left because some gdb - * versions need it. - */ - err |= __put_user(*((u64 *)&code), (u64 *)frame->retcode); if (err) return -EFAULT; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 5a0d76dc56a..097a6b64c24 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -112,8 +112,8 @@ ENTRY(ia32_sysenter_target) CFI_DEF_CFA rsp,0 CFI_REGISTER rsp,rbp SWAPGS_UNSAFE_STACK - movq %gs:pda_kernelstack, %rsp - addq $(PDA_STACKOFFSET),%rsp + movq PER_CPU_VAR(kernel_stack), %rsp + addq $(KERNEL_STACK_OFFSET),%rsp /* * No need to follow this irqs on/off section: the syscall * disabled irqs, here we enable it straight after entry: @@ -273,13 +273,13 @@ ENDPROC(ia32_sysenter_target) ENTRY(ia32_cstar_target) CFI_STARTPROC32 simple CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,PDA_STACKOFFSET + CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET CFI_REGISTER rip,rcx /*CFI_REGISTER rflags,r11*/ SWAPGS_UNSAFE_STACK movl %esp,%r8d CFI_REGISTER rsp,r8 - movq %gs:pda_kernelstack,%rsp + movq PER_CPU_VAR(kernel_stack),%rsp /* * No need to follow this irqs on/off section: the syscall * disabled irqs and here we enable it straight after entry: diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h index 37822206083..bb70e397aa8 100644 --- a/arch/x86/include/asm/a.out-core.h +++ b/arch/x86/include/asm/a.out-core.h @@ -23,8 +23,6 @@ */ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) { - u16 gs; - /* changed the size calculations - should hopefully work better. lbt */ dump->magic = CMAGIC; dump->start_code = 0; @@ -57,7 +55,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) dump->regs.ds = (u16)regs->ds; dump->regs.es = (u16)regs->es; dump->regs.fs = (u16)regs->fs; - savesegment(gs, gs); + dump->regs.gs = get_user_gs(regs); dump->regs.orig_ax = regs->orig_ax; dump->regs.ip = regs->ip; dump->regs.cs = (u16)regs->cs; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index ab1d51a8855..fba49f66228 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -33,7 +33,13 @@ } while (0) +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) extern void generic_apic_probe(void); +#else +static inline void generic_apic_probe(void) +{ +} +#endif #ifdef CONFIG_X86_LOCAL_APIC @@ -41,6 +47,21 @@ extern unsigned int apic_verbosity; extern int local_apic_timer_c2_ok; extern int disable_apic; + +#ifdef CONFIG_SMP +extern void __inquire_remote_apic(int apicid); +#else /* CONFIG_SMP */ +static inline void __inquire_remote_apic(int apicid) +{ +} +#endif /* CONFIG_SMP */ + +static inline void default_inquire_remote_apic(int apicid) +{ + if (apic_verbosity >= APIC_DEBUG) + __inquire_remote_apic(apicid); +} + /* * Basic functions accessing APICs. */ @@ -124,12 +145,35 @@ struct apic_ops { extern struct apic_ops *apic_ops; -#define apic_read (apic_ops->read) -#define apic_write (apic_ops->write) -#define apic_icr_read (apic_ops->icr_read) -#define apic_icr_write (apic_ops->icr_write) -#define apic_wait_icr_idle (apic_ops->wait_icr_idle) -#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle) +static inline u32 apic_read(u32 reg) +{ + return apic_ops->read(reg); +} + +static inline void apic_write(u32 reg, u32 val) +{ + apic_ops->write(reg, val); +} + +static inline u64 apic_icr_read(void) +{ + return apic_ops->icr_read(); +} + +static inline void apic_icr_write(u32 low, u32 high) +{ + apic_ops->icr_write(low, high); +} + +static inline void apic_wait_icr_idle(void) +{ + apic_ops->wait_icr_idle(); +} + +static inline u32 safe_apic_wait_icr_idle(void) +{ + return apic_ops->safe_wait_icr_idle(); +} extern int get_physical_broadcast(void); @@ -196,4 +240,22 @@ static inline void disable_local_APIC(void) { } #endif /* !CONFIG_X86_LOCAL_APIC */ +#ifdef CONFIG_X86_64 +#define SET_APIC_ID(x) (apic->set_apic_id(x)) +#else + +#ifdef CONFIG_X86_LOCAL_APIC +static inline unsigned default_get_apic_id(unsigned long x) +{ + unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); + + if (APIC_XAPIC(ver)) + return (x >> 24) & 0xFF; + else + return (x >> 24) & 0x0F; +} +#endif + +#endif + #endif /* _ASM_X86_APIC_H */ diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h new file mode 100644 index 00000000000..82f613c607c --- /dev/null +++ b/arch/x86/include/asm/apicnum.h @@ -0,0 +1,12 @@ +#ifndef _ASM_X86_APICNUM_H +#define _ASM_X86_APICNUM_H + +/* define MAX_IO_APICS */ +#ifdef CONFIG_X86_32 +# define MAX_IO_APICS 64 +#else +# define MAX_IO_APICS 128 +# define MAX_LOCAL_APIC 32768 +#endif + +#endif /* _ASM_X86_APICNUM_H */ diff --git a/arch/x86/include/asm/mach-default/apm.h b/arch/x86/include/asm/apm.h index 20370c6db74..20370c6db74 100644 --- a/arch/x86/include/asm/mach-default/apm.h +++ b/arch/x86/include/asm/apm.h diff --git a/arch/x86/include/asm/bigsmp/apic.h b/arch/x86/include/asm/bigsmp/apic.h deleted file mode 100644 index d8dd9f53791..00000000000 --- a/arch/x86/include/asm/bigsmp/apic.h +++ /dev/null @@ -1,155 +0,0 @@ -#ifndef __ASM_MACH_APIC_H -#define __ASM_MACH_APIC_H - -#define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu)) -#define esr_disable (1) - -static inline int apic_id_registered(void) -{ - return (1); -} - -static inline const cpumask_t *target_cpus(void) -{ -#ifdef CONFIG_SMP - return &cpu_online_map; -#else - return &cpumask_of_cpu(0); -#endif -} - -#undef APIC_DEST_LOGICAL -#define APIC_DEST_LOGICAL 0 -#define APIC_DFR_VALUE (APIC_DFR_FLAT) -#define INT_DELIVERY_MODE (dest_Fixed) -#define INT_DEST_MODE (0) /* phys delivery to target proc */ -#define NO_BALANCE_IRQ (0) - -static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid) -{ - return (0); -} - -static inline unsigned long check_apicid_present(int bit) -{ - return (1); -} - -static inline unsigned long calculate_ldr(int cpu) -{ - unsigned long val, id; - val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - id = xapic_phys_to_log_apicid(cpu); - val |= SET_APIC_LOGICAL_ID(id); - return val; -} - -/* - * Set up the logical destination ID. - * - * Intel recommends to set DFR, LDR and TPR before enabling - * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel - * document number 292116). So here it goes... - */ -static inline void init_apic_ldr(void) -{ - unsigned long val; - int cpu = smp_processor_id(); - - apic_write(APIC_DFR, APIC_DFR_VALUE); - val = calculate_ldr(cpu); - apic_write(APIC_LDR, val); -} - -static inline void setup_apic_routing(void) -{ - printk("Enabling APIC mode: %s. Using %d I/O APICs\n", - "Physflat", nr_ioapics); -} - -static inline int multi_timer_check(int apic, int irq) -{ - return (0); -} - -static inline int apicid_to_node(int logical_apicid) -{ - return apicid_2_node[hard_smp_processor_id()]; -} - -static inline int cpu_present_to_apicid(int mps_cpu) -{ - if (mps_cpu < nr_cpu_ids) - return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu); - - return BAD_APICID; -} - -static inline physid_mask_t apicid_to_cpu_present(int phys_apicid) -{ - return physid_mask_of_physid(phys_apicid); -} - -extern u8 cpu_2_logical_apicid[]; -/* Mapping from cpu number to logical apicid */ -static inline int cpu_to_logical_apicid(int cpu) -{ - if (cpu >= nr_cpu_ids) - return BAD_APICID; - return cpu_physical_id(cpu); -} - -static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map) -{ - /* For clustered we don't have a good way to do this yet - hack */ - return physids_promote(0xFFL); -} - -static inline void setup_portio_remap(void) -{ -} - -static inline void enable_apic_mode(void) -{ -} - -static inline int check_phys_apicid_present(int boot_cpu_physical_apicid) -{ - return (1); -} - -/* As we are using single CPU as destination, pick only one CPU here */ -static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask) -{ - int cpu; - int apicid; - - cpu = first_cpu(*cpumask); - apicid = cpu_to_logical_apicid(cpu); - return apicid; -} - -static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - if (cpu < nr_cpu_ids) - return cpu_to_logical_apicid(cpu); - - return BAD_APICID; -} - -static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - -#endif /* __ASM_MACH_APIC_H */ diff --git a/arch/x86/include/asm/bigsmp/apicdef.h b/arch/x86/include/asm/bigsmp/apicdef.h deleted file mode 100644 index 392c3f5ef2f..00000000000 --- a/arch/x86/include/asm/bigsmp/apicdef.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef __ASM_MACH_APICDEF_H -#define __ASM_MACH_APICDEF_H - -#define APIC_ID_MASK (0xFF<<24) - -static inline unsigned get_apic_id(unsigned long x) -{ - return (((x)>>24)&0xFF); -} - -#define GET_APIC_ID(x) get_apic_id(x) - -#endif diff --git a/arch/x86/include/asm/bigsmp/ipi.h b/arch/x86/include/asm/bigsmp/ipi.h deleted file mode 100644 index 27fcd01b3ae..00000000000 --- a/arch/x86/include/asm/bigsmp/ipi.h +++ /dev/null @@ -1,22 +0,0 @@ -#ifndef __ASM_MACH_IPI_H -#define __ASM_MACH_IPI_H - -void send_IPI_mask_sequence(const struct cpumask *mask, int vector); -void send_IPI_mask_allbutself(const struct cpumask *mask, int vector); - -static inline void send_IPI_mask(const struct cpumask *mask, int vector) -{ - send_IPI_mask_sequence(mask, vector); -} - -static inline void send_IPI_allbutself(int vector) -{ - send_IPI_mask_allbutself(cpu_online_mask, vector); -} - -static inline void send_IPI_all(int vector) -{ - send_IPI_mask(cpu_online_mask, vector); -} - -#endif /* __ASM_MACH_IPI_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index f03b23e3286..b185091bf19 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -32,10 +32,6 @@ extern void arch_unregister_cpu(int); DECLARE_PER_CPU(int, cpu_state); -#ifdef CONFIG_X86_HAS_BOOT_CPU_ID -extern unsigned char boot_cpu_id; -#else -#define boot_cpu_id 0 -#endif +extern unsigned int boot_cpu_id; #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ea408dcba51..7301e60dc4a 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -93,6 +93,7 @@ #define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */ +#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */ diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index 26c6dad9047..a7f3c75f8ad 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -10,6 +10,8 @@ extern cpumask_var_t cpu_callout_mask; extern cpumask_var_t cpu_initialized_mask; extern cpumask_var_t cpu_sibling_setup_mask; +extern void setup_cpu_local_masks(void); + #else /* CONFIG_X86_32 */ extern cpumask_t cpu_callin_map; @@ -22,6 +24,8 @@ extern cpumask_t cpu_sibling_setup_map; #define cpu_initialized_mask ((struct cpumask *)&cpu_initialized) #define cpu_sibling_setup_mask ((struct cpumask *)&cpu_sibling_setup_map) +static inline void setup_cpu_local_masks(void) { } + #endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index 0930b4f8d67..c68c361697e 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -1,39 +1,21 @@ #ifndef _ASM_X86_CURRENT_H #define _ASM_X86_CURRENT_H -#ifdef CONFIG_X86_32 #include <linux/compiler.h> #include <asm/percpu.h> +#ifndef __ASSEMBLY__ struct task_struct; DECLARE_PER_CPU(struct task_struct *, current_task); -static __always_inline struct task_struct *get_current(void) -{ - return x86_read_percpu(current_task); -} - -#else /* X86_32 */ - -#ifndef __ASSEMBLY__ -#include <asm/pda.h> - -struct task_struct; static __always_inline struct task_struct *get_current(void) { - return read_pda(pcurrent); + return percpu_read(current_task); } -#else /* __ASSEMBLY__ */ - -#include <asm/asm-offsets.h> -#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg +#define current get_current() #endif /* __ASSEMBLY__ */ -#endif /* X86_32 */ - -#define current get_current() - #endif /* _ASM_X86_CURRENT_H */ diff --git a/arch/x86/include/asm/mach-default/do_timer.h b/arch/x86/include/asm/do_timer.h index 23ecda0b28a..23ecda0b28a 100644 --- a/arch/x86/include/asm/mach-default/do_timer.h +++ b/arch/x86/include/asm/do_timer.h diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index f51a3ddde01..83c1bc8d2e8 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -112,7 +112,7 @@ extern unsigned int vdso_enabled; * now struct_user_regs, they are different) */ -#define ELF_CORE_COPY_REGS(pr_reg, regs) \ +#define ELF_CORE_COPY_REGS_COMMON(pr_reg, regs) \ do { \ pr_reg[0] = regs->bx; \ pr_reg[1] = regs->cx; \ @@ -124,7 +124,6 @@ do { \ pr_reg[7] = regs->ds & 0xffff; \ pr_reg[8] = regs->es & 0xffff; \ pr_reg[9] = regs->fs & 0xffff; \ - savesegment(gs, pr_reg[10]); \ pr_reg[11] = regs->orig_ax; \ pr_reg[12] = regs->ip; \ pr_reg[13] = regs->cs & 0xffff; \ @@ -133,6 +132,18 @@ do { \ pr_reg[16] = regs->ss & 0xffff; \ } while (0); +#define ELF_CORE_COPY_REGS(pr_reg, regs) \ +do { \ + ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\ + pr_reg[10] = get_user_gs(regs); \ +} while (0); + +#define ELF_CORE_COPY_KERNEL_REGS(pr_reg, regs) \ +do { \ + ELF_CORE_COPY_REGS_COMMON(pr_reg, regs);\ + savesegment(gs, pr_reg[10]); \ +} while (0); + #define ELF_PLATFORM (utsname()->machine) #define set_personality_64bit() do { } while (0) diff --git a/arch/x86/include/asm/mach-default/entry_arch.h b/arch/x86/include/asm/entry_arch.h index 6b1add8e31d..854d538ae85 100644 --- a/arch/x86/include/asm/mach-default/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -9,12 +9,28 @@ * is no hardware IRQ pin equivalent for them, they are triggered * through the ICC by us (IPIs) */ -#ifdef CONFIG_X86_SMP +#ifdef CONFIG_SMP BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR) -BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR) BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR) BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR) BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR) + +BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0, + smp_invalidate_interrupt) +BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1, + smp_invalidate_interrupt) +BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2, + smp_invalidate_interrupt) +BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3, + smp_invalidate_interrupt) +BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4, + smp_invalidate_interrupt) +BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5, + smp_invalidate_interrupt) +BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6, + smp_invalidate_interrupt) +BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7, + smp_invalidate_interrupt) #endif /* @@ -25,10 +41,15 @@ BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR) * a much simpler SMP time architecture: */ #ifdef CONFIG_X86_LOCAL_APIC + BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR) BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR) BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR) +#ifdef CONFIG_PERF_COUNTERS +BUILD_INTERRUPT(perf_counter_interrupt, LOCAL_PERF_VECTOR) +#endif + #ifdef CONFIG_X86_MCE_P4THERMAL BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR) #endif diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h deleted file mode 100644 index c58b9cc7446..00000000000 --- a/arch/x86/include/asm/es7000/apic.h +++ /dev/null @@ -1,242 +0,0 @@ -#ifndef __ASM_ES7000_APIC_H -#define __ASM_ES7000_APIC_H - -#include <linux/gfp.h> - -#define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu) -#define esr_disable (1) - -static inline int apic_id_registered(void) -{ - return (1); -} - -static inline const cpumask_t *target_cpus_cluster(void) -{ - return &CPU_MASK_ALL; -} - -static inline const cpumask_t *target_cpus(void) -{ - return &cpumask_of_cpu(smp_processor_id()); -} - -#define APIC_DFR_VALUE_CLUSTER (APIC_DFR_CLUSTER) -#define INT_DELIVERY_MODE_CLUSTER (dest_LowestPrio) -#define INT_DEST_MODE_CLUSTER (1) /* logical delivery broadcast to all procs */ -#define NO_BALANCE_IRQ_CLUSTER (1) - -#define APIC_DFR_VALUE (APIC_DFR_FLAT) -#define INT_DELIVERY_MODE (dest_Fixed) -#define INT_DEST_MODE (0) /* phys delivery to target procs */ -#define NO_BALANCE_IRQ (0) -#undef APIC_DEST_LOGICAL -#define APIC_DEST_LOGICAL 0x0 - -static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid) -{ - return 0; -} -static inline unsigned long check_apicid_present(int bit) -{ - return physid_isset(bit, phys_cpu_present_map); -} - -#define apicid_cluster(apicid) (apicid & 0xF0) - -static inline unsigned long calculate_ldr(int cpu) -{ - unsigned long id; - id = xapic_phys_to_log_apicid(cpu); - return (SET_APIC_LOGICAL_ID(id)); -} - -/* - * Set up the logical destination ID. - * - * Intel recommends to set DFR, LdR and TPR before enabling - * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel - * document number 292116). So here it goes... - */ -static inline void init_apic_ldr_cluster(void) -{ - unsigned long val; - int cpu = smp_processor_id(); - - apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER); - val = calculate_ldr(cpu); - apic_write(APIC_LDR, val); -} - -static inline void init_apic_ldr(void) -{ - unsigned long val; - int cpu = smp_processor_id(); - - apic_write(APIC_DFR, APIC_DFR_VALUE); - val = calculate_ldr(cpu); - apic_write(APIC_LDR, val); -} - -extern int apic_version [MAX_APICS]; -static inline void setup_apic_routing(void) -{ - int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id()); - printk("Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n", - (apic_version[apic] == 0x14) ? - "Physical Cluster" : "Logical Cluster", - nr_ioapics, cpus_addr(*target_cpus())[0]); -} - -static inline int multi_timer_check(int apic, int irq) -{ - return 0; -} - -static inline int apicid_to_node(int logical_apicid) -{ - return 0; -} - - -static inline int cpu_present_to_apicid(int mps_cpu) -{ - if (!mps_cpu) - return boot_cpu_physical_apicid; - else if (mps_cpu < nr_cpu_ids) - return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu); - else - return BAD_APICID; -} - -static inline physid_mask_t apicid_to_cpu_present(int phys_apicid) -{ - static int id = 0; - physid_mask_t mask; - mask = physid_mask_of_physid(id); - ++id; - return mask; -} - -extern u8 cpu_2_logical_apicid[]; -/* Mapping from cpu number to logical apicid */ -static inline int cpu_to_logical_apicid(int cpu) -{ -#ifdef CONFIG_SMP - if (cpu >= nr_cpu_ids) - return BAD_APICID; - return (int)cpu_2_logical_apicid[cpu]; -#else - return logical_smp_processor_id(); -#endif -} - -static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map) -{ - /* For clustered we don't have a good way to do this yet - hack */ - return physids_promote(0xff); -} - - -static inline void setup_portio_remap(void) -{ -} - -extern unsigned int boot_cpu_physical_apicid; -static inline int check_phys_apicid_present(int cpu_physical_apicid) -{ - boot_cpu_physical_apicid = read_apic_id(); - return (1); -} - -static inline unsigned int -cpu_mask_to_apicid_cluster(const struct cpumask *cpumask) -{ - int num_bits_set; - int cpus_found = 0; - int cpu; - int apicid; - - num_bits_set = cpumask_weight(cpumask); - /* Return id to all */ - if (num_bits_set == nr_cpu_ids) - return 0xFF; - /* - * The cpus in the mask must all be on the apic cluster. If are not - * on the same apicid cluster return default value of TARGET_CPUS. - */ - cpu = cpumask_first(cpumask); - apicid = cpu_to_logical_apicid(cpu); - while (cpus_found < num_bits_set) { - if (cpumask_test_cpu(cpu, cpumask)) { - int new_apicid = cpu_to_logical_apicid(cpu); - if (apicid_cluster(apicid) != - apicid_cluster(new_apicid)){ - printk ("%s: Not a valid mask!\n", __func__); - return 0xFF; - } - apicid = new_apicid; - cpus_found++; - } - cpu++; - } - return apicid; -} - -static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask) -{ - int num_bits_set; - int cpus_found = 0; - int cpu; - int apicid; - - num_bits_set = cpus_weight(*cpumask); - /* Return id to all */ - if (num_bits_set == nr_cpu_ids) - return cpu_to_logical_apicid(0); - /* - * The cpus in the mask must all be on the apic cluster. If are not - * on the same apicid cluster return default value of TARGET_CPUS. - */ - cpu = first_cpu(*cpumask); - apicid = cpu_to_logical_apicid(cpu); - while (cpus_found < num_bits_set) { - if (cpu_isset(cpu, *cpumask)) { - int new_apicid = cpu_to_logical_apicid(cpu); - if (apicid_cluster(apicid) != - apicid_cluster(new_apicid)){ - printk ("%s: Not a valid mask!\n", __func__); - return cpu_to_logical_apicid(0); - } - apicid = new_apicid; - cpus_found++; - } - cpu++; - } - return apicid; -} - - -static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask, - const struct cpumask *andmask) -{ - int apicid = cpu_to_logical_apicid(0); - cpumask_var_t cpumask; - - if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) - return apicid; - - cpumask_and(cpumask, inmask, andmask); - cpumask_and(cpumask, cpumask, cpu_online_mask); - apicid = cpu_mask_to_apicid(cpumask); - - free_cpumask_var(cpumask); - return apicid; -} - -static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - -#endif /* __ASM_ES7000_APIC_H */ diff --git a/arch/x86/include/asm/es7000/apicdef.h b/arch/x86/include/asm/es7000/apicdef.h deleted file mode 100644 index 8b234a3cb85..00000000000 --- a/arch/x86/include/asm/es7000/apicdef.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef __ASM_ES7000_APICDEF_H -#define __ASM_ES7000_APICDEF_H - -#define APIC_ID_MASK (0xFF<<24) - -static inline unsigned get_apic_id(unsigned long x) -{ - return (((x)>>24)&0xFF); -} - -#define GET_APIC_ID(x) get_apic_id(x) - -#endif diff --git a/arch/x86/include/asm/es7000/ipi.h b/arch/x86/include/asm/es7000/ipi.h deleted file mode 100644 index 7e8ed24d4b8..00000000000 --- a/arch/x86/include/asm/es7000/ipi.h +++ /dev/null @@ -1,22 +0,0 @@ -#ifndef __ASM_ES7000_IPI_H -#define __ASM_ES7000_IPI_H - -void send_IPI_mask_sequence(const struct cpumask *mask, int vector); -void send_IPI_mask_allbutself(const struct cpumask *mask, int vector); - -static inline void send_IPI_mask(const struct cpumask *mask, int vector) -{ - send_IPI_mask_sequence(mask, vector); -} - -static inline void send_IPI_allbutself(int vector) -{ - send_IPI_mask_allbutself(cpu_online_mask, vector); -} - -static inline void send_IPI_all(int vector) -{ - send_IPI_mask(cpu_online_mask, vector); -} - -#endif /* __ASM_ES7000_IPI_H */ diff --git a/arch/x86/include/asm/es7000/mpparse.h b/arch/x86/include/asm/es7000/mpparse.h deleted file mode 100644 index c1629b090ec..00000000000 --- a/arch/x86/include/asm/es7000/mpparse.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef __ASM_ES7000_MPPARSE_H -#define __ASM_ES7000_MPPARSE_H - -#include <linux/acpi.h> - -extern int parse_unisys_oem (char *oemptr); -extern int find_unisys_acpi_oem_table(unsigned long *oem_addr); -extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr); -extern void setup_unisys(void); - -#ifndef CONFIG_X86_GENERICARCH -extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id); -extern int mps_oem_check(struct mpc_table *mpc, char *oem, char *productid); -#endif - -#ifdef CONFIG_ACPI - -static inline int es7000_check_dsdt(void) -{ - struct acpi_table_header header; - - if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) && - !strncmp(header.oem_id, "UNISYS", 6)) - return 1; - return 0; -} -#endif - -#endif /* __ASM_MACH_MPPARSE_H */ diff --git a/arch/x86/include/asm/es7000/wakecpu.h b/arch/x86/include/asm/es7000/wakecpu.h deleted file mode 100644 index 78f0daaee43..00000000000 --- a/arch/x86/include/asm/es7000/wakecpu.h +++ /dev/null @@ -1,37 +0,0 @@ -#ifndef __ASM_ES7000_WAKECPU_H -#define __ASM_ES7000_WAKECPU_H - -#define TRAMPOLINE_PHYS_LOW 0x467 -#define TRAMPOLINE_PHYS_HIGH 0x469 - -static inline void wait_for_init_deassert(atomic_t *deassert) -{ -#ifndef CONFIG_ES7000_CLUSTERED_APIC - while (!atomic_read(deassert)) - cpu_relax(); -#endif - return; -} - -/* Nothing to do for most platforms, since cleared by the INIT cycle */ -static inline void smp_callin_clear_local_apic(void) -{ -} - -static inline void store_NMI_vector(unsigned short *high, unsigned short *low) -{ -} - -static inline void restore_NMI_vector(unsigned short *high, unsigned short *low) -{ -} - -extern void __inquire_remote_apic(int apicid); - -static inline void inquire_remote_apic(int apicid) -{ - if (apic_verbosity >= APIC_DEBUG) - __inquire_remote_apic(apicid); -} - -#endif /* __ASM_MACH_WAKECPU_H */ diff --git a/arch/x86/include/asm/genapic.h b/arch/x86/include/asm/genapic.h index d48bee663a6..273b99452ae 100644 --- a/arch/x86/include/asm/genapic.h +++ b/arch/x86/include/asm/genapic.h @@ -1,5 +1,263 @@ +#ifndef _ASM_X86_GENAPIC_H +#define _ASM_X86_GENAPIC_H + +#include <linux/cpumask.h> + +#include <asm/mpspec.h> +#include <asm/atomic.h> + +/* + * Copyright 2004 James Cleverdon, IBM. + * Subject to the GNU Public License, v.2 + * + * Generic APIC sub-arch data struct. + * + * Hacked for x86-64 by James Cleverdon from i386 architecture code by + * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and + * James Cleverdon. + */ +struct genapic { + char *name; + + int (*probe)(void); + int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); + int (*apic_id_registered)(void); + + u32 irq_delivery_mode; + u32 irq_dest_mode; + + const struct cpumask *(*target_cpus)(void); + + int disable_esr; + + int dest_logical; + unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid); + unsigned long (*check_apicid_present)(int apicid); + + void (*vector_allocation_domain)(int cpu, struct cpumask *retmask); + void (*init_apic_ldr)(void); + + physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map); + + void (*setup_apic_routing)(void); + int (*multi_timer_check)(int apic, int irq); + int (*apicid_to_node)(int logical_apicid); + int (*cpu_to_logical_apicid)(int cpu); + int (*cpu_present_to_apicid)(int mps_cpu); + physid_mask_t (*apicid_to_cpu_present)(int phys_apicid); + void (*setup_portio_remap)(void); + int (*check_phys_apicid_present)(int boot_cpu_physical_apicid); + void (*enable_apic_mode)(void); + int (*phys_pkg_id)(int cpuid_apic, int index_msb); + + /* + * When one of the next two hooks returns 1 the genapic + * is switched to this. Essentially they are additional + * probe functions: + */ + int (*mps_oem_check)(struct mpc_table *mpc, char *oem, char *productid); + + unsigned int (*get_apic_id)(unsigned long x); + unsigned long (*set_apic_id)(unsigned int id); + unsigned long apic_id_mask; + + unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask); + unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, + const struct cpumask *andmask); + + /* ipi */ + void (*send_IPI_mask)(const struct cpumask *mask, int vector); + void (*send_IPI_mask_allbutself)(const struct cpumask *mask, + int vector); + void (*send_IPI_allbutself)(int vector); + void (*send_IPI_all)(int vector); + void (*send_IPI_self)(int vector); + + /* wakeup_secondary_cpu */ + int (*wakeup_cpu)(int apicid, unsigned long start_eip); + + int trampoline_phys_low; + int trampoline_phys_high; + + void (*wait_for_init_deassert)(atomic_t *deassert); + void (*smp_callin_clear_local_apic)(void); + void (*store_NMI_vector)(unsigned short *high, unsigned short *low); + void (*inquire_remote_apic)(int apicid); +}; + +extern struct genapic *apic; + +/* + * Warm reset vector default position: + */ +#define DEFAULT_TRAMPOLINE_PHYS_LOW 0x467 +#define DEFAULT_TRAMPOLINE_PHYS_HIGH 0x469 + #ifdef CONFIG_X86_32 -# include "genapic_32.h" +extern void es7000_update_genapic_to_cluster(void); #else -# include "genapic_64.h" +extern struct genapic apic_flat; +extern struct genapic apic_physflat; +extern struct genapic apic_x2apic_cluster; +extern struct genapic apic_x2apic_phys; +extern int default_acpi_madt_oem_check(char *, char *); + +extern void apic_send_IPI_self(int vector); + +extern struct genapic apic_x2apic_uv_x; +DECLARE_PER_CPU(int, x2apic_extra_bits); + +extern void default_setup_apic_routing(void); + +extern int default_cpu_present_to_apicid(int mps_cpu); +extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid); #endif + +static inline void default_wait_for_init_deassert(atomic_t *deassert) +{ + while (!atomic_read(deassert)) + cpu_relax(); + return; +} + +extern void generic_bigsmp_probe(void); + + +#ifdef CONFIG_X86_LOCAL_APIC + +#include <asm/smp.h> + +#define APIC_DFR_VALUE (APIC_DFR_FLAT) + +static inline const struct cpumask *default_target_cpus(void) +{ +#ifdef CONFIG_SMP + return cpu_online_mask; +#else + return cpumask_of(0); +#endif +} + +DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid); + + +static inline unsigned int read_apic_id(void) +{ + unsigned int reg; + + reg = apic_read(APIC_ID); + + return apic->get_apic_id(reg); +} + +#ifdef CONFIG_X86_64 +extern void default_setup_apic_routing(void); +#else + +/* + * Set up the logical destination ID. + * + * Intel recommends to set DFR, LDR and TPR before enabling + * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel + * document number 292116). So here it goes... + */ +extern void default_init_apic_ldr(void); + +static inline int default_apic_id_registered(void) +{ + return physid_isset(read_apic_id(), phys_cpu_present_map); +} + +static inline unsigned int +default_cpu_mask_to_apicid(const struct cpumask *cpumask) +{ + return cpumask_bits(cpumask)[0]; +} + +static inline unsigned int +default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask) +{ + unsigned long mask1 = cpumask_bits(cpumask)[0]; + unsigned long mask2 = cpumask_bits(andmask)[0]; + unsigned long mask3 = cpumask_bits(cpu_online_mask)[0]; + + return (unsigned int)(mask1 & mask2 & mask3); +} + +static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} + +static inline void default_setup_apic_routing(void) +{ +#ifdef CONFIG_X86_IO_APIC + printk("Enabling APIC mode: %s. Using %d I/O APICs\n", + "Flat", nr_ioapics); +#endif +} + +extern int default_apicid_to_node(int logical_apicid); + +#endif + +static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid) +{ + return physid_isset(apicid, bitmap); +} + +static inline unsigned long default_check_apicid_present(int bit) +{ + return physid_isset(bit, phys_cpu_present_map); +} + +static inline physid_mask_t default_ioapic_phys_id_map(physid_mask_t phys_map) +{ + return phys_map; +} + +/* Mapping from cpu number to logical apicid */ +static inline int default_cpu_to_logical_apicid(int cpu) +{ + return 1 << cpu; +} + +static inline int __default_cpu_present_to_apicid(int mps_cpu) +{ + if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) + return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu); + else + return BAD_APICID; +} + +static inline int +__default_check_phys_apicid_present(int boot_cpu_physical_apicid) +{ + return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map); +} + +#ifdef CONFIG_X86_32 +static inline int default_cpu_present_to_apicid(int mps_cpu) +{ + return __default_cpu_present_to_apicid(mps_cpu); +} + +static inline int +default_check_phys_apicid_present(int boot_cpu_physical_apicid) +{ + return __default_check_phys_apicid_present(boot_cpu_physical_apicid); +} +#else +extern int default_cpu_present_to_apicid(int mps_cpu); +extern int default_check_phys_apicid_present(int boot_cpu_physical_apicid); +#endif + +static inline physid_mask_t default_apicid_to_cpu_present(int phys_apicid) +{ + return physid_mask_of_physid(phys_apicid); +} + +#endif /* CONFIG_X86_LOCAL_APIC */ + +#endif /* _ASM_X86_GENAPIC_64_H */ diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h deleted file mode 100644 index 2c05b737ee2..00000000000 --- a/arch/x86/include/asm/genapic_32.h +++ /dev/null @@ -1,148 +0,0 @@ -#ifndef _ASM_X86_GENAPIC_32_H -#define _ASM_X86_GENAPIC_32_H - -#include <asm/mpspec.h> -#include <asm/atomic.h> - -/* - * Generic APIC driver interface. - * - * An straight forward mapping of the APIC related parts of the - * x86 subarchitecture interface to a dynamic object. - * - * This is used by the "generic" x86 subarchitecture. - * - * Copyright 2003 Andi Kleen, SuSE Labs. - */ - -struct mpc_bus; -struct mpc_table; -struct mpc_cpu; - -struct genapic { - char *name; - int (*probe)(void); - - int (*apic_id_registered)(void); - const struct cpumask *(*target_cpus)(void); - int int_delivery_mode; - int int_dest_mode; - int ESR_DISABLE; - int apic_destination_logical; - unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid); - unsigned long (*check_apicid_present)(int apicid); - int no_balance_irq; - int no_ioapic_check; - void (*init_apic_ldr)(void); - physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map); - - void (*setup_apic_routing)(void); - int (*multi_timer_check)(int apic, int irq); - int (*apicid_to_node)(int logical_apicid); - int (*cpu_to_logical_apicid)(int cpu); - int (*cpu_present_to_apicid)(int mps_cpu); - physid_mask_t (*apicid_to_cpu_present)(int phys_apicid); - void (*setup_portio_remap)(void); - int (*check_phys_apicid_present)(int boot_cpu_physical_apicid); - void (*enable_apic_mode)(void); - u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb); - - /* mpparse */ - /* When one of the next two hooks returns 1 the genapic - is switched to this. Essentially they are additional probe - functions. */ - int (*mps_oem_check)(struct mpc_table *mpc, char *oem, - char *productid); - int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); - - unsigned (*get_apic_id)(unsigned long x); - unsigned long apic_id_mask; - unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask); - unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, - const struct cpumask *andmask); - void (*vector_allocation_domain)(int cpu, struct cpumask *retmask); - -#ifdef CONFIG_SMP - /* ipi */ - void (*send_IPI_mask)(const struct cpumask *mask, int vector); - void (*send_IPI_mask_allbutself)(const struct cpumask *mask, - int vector); - void (*send_IPI_allbutself)(int vector); - void (*send_IPI_all)(int vector); -#endif - int (*wakeup_cpu)(int apicid, unsigned long start_eip); - int trampoline_phys_low; - int trampoline_phys_high; - void (*wait_for_init_deassert)(atomic_t *deassert); - void (*smp_callin_clear_local_apic)(void); - void (*store_NMI_vector)(unsigned short *high, unsigned short *low); - void (*restore_NMI_vector)(unsigned short *high, unsigned short *low); - void (*inquire_remote_apic)(int apicid); -}; - -#define APICFUNC(x) .x = x, - -/* More functions could be probably marked IPIFUNC and save some space - in UP GENERICARCH kernels, but I don't have the nerve right now - to untangle this mess. -AK */ -#ifdef CONFIG_SMP -#define IPIFUNC(x) APICFUNC(x) -#else -#define IPIFUNC(x) -#endif - -#define APIC_INIT(aname, aprobe) \ -{ \ - .name = aname, \ - .probe = aprobe, \ - .int_delivery_mode = INT_DELIVERY_MODE, \ - .int_dest_mode = INT_DEST_MODE, \ - .no_balance_irq = NO_BALANCE_IRQ, \ - .ESR_DISABLE = esr_disable, \ - .apic_destination_logical = APIC_DEST_LOGICAL, \ - APICFUNC(apic_id_registered) \ - APICFUNC(target_cpus) \ - APICFUNC(check_apicid_used) \ - APICFUNC(check_apicid_present) \ - APICFUNC(init_apic_ldr) \ - APICFUNC(ioapic_phys_id_map) \ - APICFUNC(setup_apic_routing) \ - APICFUNC(multi_timer_check) \ - APICFUNC(apicid_to_node) \ - APICFUNC(cpu_to_logical_apicid) \ - APICFUNC(cpu_present_to_apicid) \ - APICFUNC(apicid_to_cpu_present) \ - APICFUNC(setup_portio_remap) \ - APICFUNC(check_phys_apicid_present) \ - APICFUNC(mps_oem_check) \ - APICFUNC(get_apic_id) \ - .apic_id_mask = APIC_ID_MASK, \ - APICFUNC(cpu_mask_to_apicid) \ - APICFUNC(cpu_mask_to_apicid_and) \ - APICFUNC(vector_allocation_domain) \ - APICFUNC(acpi_madt_oem_check) \ - IPIFUNC(send_IPI_mask) \ - IPIFUNC(send_IPI_allbutself) \ - IPIFUNC(send_IPI_all) \ - APICFUNC(enable_apic_mode) \ - APICFUNC(phys_pkg_id) \ - .trampoline_phys_low = TRAMPOLINE_PHYS_LOW, \ - .trampoline_phys_high = TRAMPOLINE_PHYS_HIGH, \ - APICFUNC(wait_for_init_deassert) \ - APICFUNC(smp_callin_clear_local_apic) \ - APICFUNC(store_NMI_vector) \ - APICFUNC(restore_NMI_vector) \ - APICFUNC(inquire_remote_apic) \ -} - -extern struct genapic *genapic; -extern void es7000_update_genapic_to_cluster(void); - -enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; -#define get_uv_system_type() UV_NONE -#define is_uv_system() 0 -#define uv_wakeup_secondary(a, b) 1 -#define uv_system_init() do {} while (0) - - -#endif /* _ASM_X86_GENAPIC_32_H */ diff --git a/arch/x86/include/asm/genapic_64.h b/arch/x86/include/asm/genapic_64.h deleted file mode 100644 index adf32fb56aa..00000000000 --- a/arch/x86/include/asm/genapic_64.h +++ /dev/null @@ -1,66 +0,0 @@ -#ifndef _ASM_X86_GENAPIC_64_H -#define _ASM_X86_GENAPIC_64_H - -#include <linux/cpumask.h> - -/* - * Copyright 2004 James Cleverdon, IBM. - * Subject to the GNU Public License, v.2 - * - * Generic APIC sub-arch data struct. - * - * Hacked for x86-64 by James Cleverdon from i386 architecture code by - * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and - * James Cleverdon. - */ - -struct genapic { - char *name; - int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); - u32 int_delivery_mode; - u32 int_dest_mode; - int (*apic_id_registered)(void); - const struct cpumask *(*target_cpus)(void); - void (*vector_allocation_domain)(int cpu, struct cpumask *retmask); - void (*init_apic_ldr)(void); - /* ipi */ - void (*send_IPI_mask)(const struct cpumask *mask, int vector); - void (*send_IPI_mask_allbutself)(const struct cpumask *mask, - int vector); - void (*send_IPI_allbutself)(int vector); - void (*send_IPI_all)(int vector); - void (*send_IPI_self)(int vector); - /* */ - unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask); - unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, - const struct cpumask *andmask); - unsigned int (*phys_pkg_id)(int index_msb); - unsigned int (*get_apic_id)(unsigned long x); - unsigned long (*set_apic_id)(unsigned int id); - unsigned long apic_id_mask; - /* wakeup_secondary_cpu */ - int (*wakeup_cpu)(int apicid, unsigned long start_eip); -}; - -extern struct genapic *genapic; - -extern struct genapic apic_flat; -extern struct genapic apic_physflat; -extern struct genapic apic_x2apic_cluster; -extern struct genapic apic_x2apic_phys; -extern int acpi_madt_oem_check(char *, char *); - -extern void apic_send_IPI_self(int vector); -enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; -extern enum uv_system_type get_uv_system_type(void); -extern int is_uv_system(void); - -extern struct genapic apic_x2apic_uv_x; -DECLARE_PER_CPU(int, x2apic_extra_bits); -extern void uv_cpu_init(void); -extern void uv_system_init(void); -extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip); - -extern void setup_apic_routing(void); - -#endif /* _ASM_X86_GENAPIC_64_H */ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 000787df66e..176f058e715 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -1,11 +1,52 @@ -#ifdef CONFIG_X86_32 -# include "hardirq_32.h" -#else -# include "hardirq_64.h" +#ifndef _ASM_X86_HARDIRQ_H +#define _ASM_X86_HARDIRQ_H + +#include <linux/threads.h> +#include <linux/irq.h> + +typedef struct { + unsigned int __softirq_pending; + unsigned int __nmi_count; /* arch dependent */ + unsigned int irq0_irqs; +#ifdef CONFIG_X86_LOCAL_APIC + unsigned int apic_timer_irqs; /* arch dependent */ + unsigned int irq_spurious_count; +#endif +#ifdef CONFIG_SMP + unsigned int irq_resched_count; + unsigned int irq_call_count; + unsigned int irq_tlb_count; +#endif +#ifdef CONFIG_X86_MCE + unsigned int irq_thermal_count; +# ifdef CONFIG_X86_64 + unsigned int irq_threshold_count; +# endif #endif +} ____cacheline_aligned irq_cpustat_t; + +DECLARE_PER_CPU(irq_cpustat_t, irq_stat); + +/* We can have at most NR_VECTORS irqs routed to a cpu at a time */ +#define MAX_HARDIRQS_PER_CPU NR_VECTORS + +#define __ARCH_IRQ_STAT + +#define inc_irq_stat(member) percpu_add(irq_stat.member, 1) + +#define local_softirq_pending() percpu_read(irq_stat.__softirq_pending) + +#define __ARCH_SET_SOFTIRQ_PENDING + +#define set_softirq_pending(x) percpu_write(irq_stat.__softirq_pending, (x)) +#define or_softirq_pending(x) percpu_or(irq_stat.__softirq_pending, (x)) + +extern void ack_bad_irq(unsigned int irq); extern u64 arch_irq_stat_cpu(unsigned int cpu); #define arch_irq_stat_cpu arch_irq_stat_cpu extern u64 arch_irq_stat(void); #define arch_irq_stat arch_irq_stat + +#endif /* _ASM_X86_HARDIRQ_H */ diff --git a/arch/x86/include/asm/hardirq_32.h b/arch/x86/include/asm/hardirq_32.h deleted file mode 100644 index d4b5d731073..00000000000 --- a/arch/x86/include/asm/hardirq_32.h +++ /dev/null @@ -1,33 +0,0 @@ -#ifndef _ASM_X86_HARDIRQ_32_H -#define _ASM_X86_HARDIRQ_32_H - -#include <linux/threads.h> -#include <linux/irq.h> - -typedef struct { - unsigned int __softirq_pending; - unsigned long idle_timestamp; - unsigned int __nmi_count; /* arch dependent */ - unsigned int apic_timer_irqs; /* arch dependent */ - unsigned int irq0_irqs; - unsigned int irq_resched_count; - unsigned int irq_call_count; - unsigned int irq_tlb_count; - unsigned int irq_thermal_count; - unsigned int irq_spurious_count; -} ____cacheline_aligned irq_cpustat_t; - -DECLARE_PER_CPU(irq_cpustat_t, irq_stat); - -/* We can have at most NR_VECTORS irqs routed to a cpu at a time */ -#define MAX_HARDIRQS_PER_CPU NR_VECTORS - -#define __ARCH_IRQ_STAT -#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member) - -#define inc_irq_stat(member) (__get_cpu_var(irq_stat).member++) - -void ack_bad_irq(unsigned int irq); -#include <linux/irq_cpustat.h> - -#endif /* _ASM_X86_HARDIRQ_32_H */ diff --git a/arch/x86/include/asm/hardirq_64.h b/arch/x86/include/asm/hardirq_64.h deleted file mode 100644 index b5a6b5d5670..00000000000 --- a/arch/x86/include/asm/hardirq_64.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef _ASM_X86_HARDIRQ_64_H -#define _ASM_X86_HARDIRQ_64_H - -#include <linux/threads.h> -#include <linux/irq.h> -#include <asm/pda.h> -#include <asm/apic.h> - -/* We can have at most NR_VECTORS irqs routed to a cpu at a time */ -#define MAX_HARDIRQS_PER_CPU NR_VECTORS - -#define __ARCH_IRQ_STAT 1 - -#define inc_irq_stat(member) add_pda(member, 1) - -#define local_softirq_pending() read_pda(__softirq_pending) - -#define __ARCH_SET_SOFTIRQ_PENDING 1 - -#define set_softirq_pending(x) write_pda(__softirq_pending, (x)) -#define or_softirq_pending(x) or_pda(__softirq_pending, (x)) - -extern void ack_bad_irq(unsigned int irq); - -#endif /* _ASM_X86_HARDIRQ_64_H */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 8de644b6b95..370e1c83bb4 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -25,8 +25,6 @@ #include <asm/irq.h> #include <asm/sections.h> -#define platform_legacy_irq(irq) ((irq) < 16) - /* Interrupt handlers registered during init_IRQ */ extern void apic_timer_interrupt(void); extern void error_interrupt(void); @@ -58,7 +56,7 @@ extern void make_8259A_irq(unsigned int irq); extern void init_8259A(int aeoi); /* IOAPIC */ -#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs)) +#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs)) extern unsigned long io_apic_irqs; extern void init_VISWS_APIC_irqs(void); @@ -67,15 +65,7 @@ extern void disable_IO_APIC(void); extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn); extern void setup_ioapic_dest(void); -#ifdef CONFIG_X86_64 extern void enable_IO_APIC(void); -#endif - -/* IPI functions */ -#ifdef CONFIG_X86_32 -extern void send_IPI_self(int vector); -#endif -extern void send_IPI(int dest, int vector); /* Statistics */ extern atomic_t irq_err_count; @@ -84,21 +74,11 @@ extern atomic_t irq_mis_count; /* EISA */ extern void eisa_set_level_irq(unsigned int irq); -/* Voyager functions */ -extern asmlinkage void vic_cpi_interrupt(void); -extern asmlinkage void vic_sys_interrupt(void); -extern asmlinkage void vic_cmn_interrupt(void); -extern asmlinkage void qic_timer_interrupt(void); -extern asmlinkage void qic_invalidate_interrupt(void); -extern asmlinkage void qic_reschedule_interrupt(void); -extern asmlinkage void qic_enable_irq_interrupt(void); -extern asmlinkage void qic_call_function_interrupt(void); - /* SMP */ extern void smp_apic_timer_interrupt(struct pt_regs *); extern void smp_spurious_interrupt(struct pt_regs *); extern void smp_error_interrupt(struct pt_regs *); -#ifdef CONFIG_X86_SMP +#ifdef CONFIG_SMP extern void smp_reschedule_interrupt(struct pt_regs *); extern void smp_call_function_interrupt(struct pt_regs *); extern void smp_call_function_single_interrupt(struct pt_regs *); diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 76797f4783b..f710ec2370e 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -91,7 +91,7 @@ extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr); extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, unsigned long prot_val); -extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size); +extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); /* * early_ioremap() and early_iounmap() are for temporary early boot-time diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 08ec793aa04..59cb4a1317b 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -143,15 +143,6 @@ extern int noioapicreroute; /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */ extern int timer_through_8259; -static inline void disable_ioapic_setup(void) -{ -#ifdef CONFIG_PCI - noioapicquirk = 1; - noioapicreroute = -1; -#endif - skip_ioapic_setup = 1; -} - /* * If we use the IO-APIC for IRQ routing, disable automatic * assignment of PCI IRQ's. @@ -178,6 +169,12 @@ extern void reinit_intr_remapped_IO_APIC(int); extern void probe_nr_irqs_gsi(void); +extern int setup_ioapic_entry(int apic, int irq, + struct IO_APIC_route_entry *entry, + unsigned int destination, int trigger, + int polarity, int vector); +extern void ioapic_write_entry(int apic, int pin, + struct IO_APIC_route_entry e); #else /* !CONFIG_X86_IO_APIC */ #define io_apic_assign_pci_irqs 0 static const int timer_through_8259 = 0; diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index c745a306f7d..5f2efc5d992 100644 --- a/arch/x86/include/asm/ipi.h +++ b/arch/x86/include/asm/ipi.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_IPI_H #define _ASM_X86_IPI_H +#ifdef CONFIG_X86_LOCAL_APIC + /* * Copyright 2004 James Cleverdon, IBM. * Subject to the GNU Public License, v.2 @@ -55,8 +57,8 @@ static inline void __xapic_wait_icr_idle(void) cpu_relax(); } -static inline void __send_IPI_shortcut(unsigned int shortcut, int vector, - unsigned int dest) +static inline void +__default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest) { /* * Subtle. In the case of the 'never do double writes' workaround @@ -87,8 +89,8 @@ static inline void __send_IPI_shortcut(unsigned int shortcut, int vector, * This is used to send an IPI with no shorthand notation (the destination is * specified in bits 56 to 63 of the ICR). */ -static inline void __send_IPI_dest_field(unsigned int mask, int vector, - unsigned int dest) +static inline void + __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest) { unsigned long cfg; @@ -117,41 +119,46 @@ static inline void __send_IPI_dest_field(unsigned int mask, int vector, native_apic_mem_write(APIC_ICR, cfg); } -static inline void send_IPI_mask_sequence(const struct cpumask *mask, - int vector) -{ - unsigned long flags; - unsigned long query_cpu; +extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, + int vector); +extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, + int vector); +#include <asm/genapic.h> - /* - * Hack. The clustered APIC addressing mode doesn't allow us to send - * to an arbitrary mask, so I do a unicast to each CPU instead. - * - mbligh - */ - local_irq_save(flags); - for_each_cpu(query_cpu, mask) { - __send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu), - vector, APIC_DEST_PHYSICAL); - } - local_irq_restore(flags); +extern void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, + int vector); +extern void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, + int vector); + +/* Avoid include hell */ +#define NMI_VECTOR 0x02 + +extern int no_broadcast; + +static inline void __default_local_send_IPI_allbutself(int vector) +{ + if (no_broadcast || vector == NMI_VECTOR) + apic->send_IPI_mask_allbutself(cpu_online_mask, vector); + else + __default_send_IPI_shortcut(APIC_DEST_ALLBUT, vector, apic->dest_logical); } -static inline void send_IPI_mask_allbutself(const struct cpumask *mask, - int vector) +static inline void __default_local_send_IPI_all(int vector) { - unsigned long flags; - unsigned int query_cpu; - unsigned int this_cpu = smp_processor_id(); - - /* See Hack comment above */ - - local_irq_save(flags); - for_each_cpu(query_cpu, mask) - if (query_cpu != this_cpu) - __send_IPI_dest_field( - per_cpu(x86_cpu_to_apicid, query_cpu), - vector, APIC_DEST_PHYSICAL); - local_irq_restore(flags); + if (no_broadcast || vector == NMI_VECTOR) + apic->send_IPI_mask(cpu_online_mask, vector); + else + __default_send_IPI_shortcut(APIC_DEST_ALLINC, vector, apic->dest_logical); } +#ifdef CONFIG_X86_32 +extern void default_send_IPI_mask_logical(const struct cpumask *mask, + int vector); +extern void default_send_IPI_allbutself(int vector); +extern void default_send_IPI_all(int vector); +extern void default_send_IPI_self(int vector); +#endif + +#endif + #endif /* _ASM_X86_IPI_H */ diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 592688ed04d..107eb219669 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -36,9 +36,11 @@ static inline int irq_canonicalize(int irq) extern void fixup_irqs(void); #endif -extern unsigned int do_IRQ(struct pt_regs *regs); extern void init_IRQ(void); extern void native_init_IRQ(void); +extern bool handle_irq(unsigned irq, struct pt_regs *regs); + +extern unsigned int do_IRQ(struct pt_regs *regs); /* Interrupt vector management */ extern DECLARE_BITMAP(used_vectors, NR_VECTORS); diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h index 89c898ab298..77843225b7e 100644 --- a/arch/x86/include/asm/irq_regs.h +++ b/arch/x86/include/asm/irq_regs.h @@ -1,5 +1,31 @@ -#ifdef CONFIG_X86_32 -# include "irq_regs_32.h" -#else -# include "irq_regs_64.h" -#endif +/* + * Per-cpu current frame pointer - the location of the last exception frame on + * the stack, stored in the per-cpu area. + * + * Jeremy Fitzhardinge <jeremy@goop.org> + */ +#ifndef _ASM_X86_IRQ_REGS_H +#define _ASM_X86_IRQ_REGS_H + +#include <asm/percpu.h> + +#define ARCH_HAS_OWN_IRQ_REGS + +DECLARE_PER_CPU(struct pt_regs *, irq_regs); + +static inline struct pt_regs *get_irq_regs(void) +{ + return percpu_read(irq_regs); +} + +static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs) +{ + struct pt_regs *old_regs; + + old_regs = get_irq_regs(); + percpu_write(irq_regs, new_regs); + + return old_regs; +} + +#endif /* _ASM_X86_IRQ_REGS_32_H */ diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h deleted file mode 100644 index 86afd747345..00000000000 --- a/arch/x86/include/asm/irq_regs_32.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * Per-cpu current frame pointer - the location of the last exception frame on - * the stack, stored in the per-cpu area. - * - * Jeremy Fitzhardinge <jeremy@goop.org> - */ -#ifndef _ASM_X86_IRQ_REGS_32_H -#define _ASM_X86_IRQ_REGS_32_H - -#include <asm/percpu.h> - -#define ARCH_HAS_OWN_IRQ_REGS - -DECLARE_PER_CPU(struct pt_regs *, irq_regs); - -static inline struct pt_regs *get_irq_regs(void) -{ - return x86_read_percpu(irq_regs); -} - -static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs) -{ - struct pt_regs *old_regs; - - old_regs = get_irq_regs(); - x86_write_percpu(irq_regs, new_regs); - - return old_regs; -} - -#endif /* _ASM_X86_IRQ_REGS_32_H */ diff --git a/arch/x86/include/asm/irq_regs_64.h b/arch/x86/include/asm/irq_regs_64.h deleted file mode 100644 index 3dd9c0b7027..00000000000 --- a/arch/x86/include/asm/irq_regs_64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/irq_regs.h> diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index f7ff65032b9..b07278c55e9 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -1,47 +1,69 @@ #ifndef _ASM_X86_IRQ_VECTORS_H #define _ASM_X86_IRQ_VECTORS_H -#include <linux/threads.h> +/* + * Linux IRQ vector layout. + * + * There are 256 IDT entries (per CPU - each entry is 8 bytes) which can + * be defined by Linux. They are used as a jump table by the CPU when a + * given vector is triggered - by a CPU-external, CPU-internal or + * software-triggered event. + * + * Linux sets the kernel code address each entry jumps to early during + * bootup, and never changes them. This is the general layout of the + * IDT entries: + * + * Vectors 0 ... 31 : system traps and exceptions - hardcoded events + * Vectors 32 ... 127 : device interrupts + * Vector 128 : legacy int80 syscall interface + * Vectors 129 ... 237 : device interrupts + * Vectors 238 ... 255 : special interrupts + * + * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table. + * + * This file enumerates the exact layout of them: + */ -#define NMI_VECTOR 0x02 +#define NMI_VECTOR 0x02 /* * IDT vectors usable for external interrupt sources start * at 0x20: */ -#define FIRST_EXTERNAL_VECTOR 0x20 +#define FIRST_EXTERNAL_VECTOR 0x20 #ifdef CONFIG_X86_32 -# define SYSCALL_VECTOR 0x80 +# define SYSCALL_VECTOR 0x80 #else -# define IA32_SYSCALL_VECTOR 0x80 +# define IA32_SYSCALL_VECTOR 0x80 #endif /* * Reserve the lowest usable priority level 0x20 - 0x2f for triggering * cleanup after irq migration. */ -#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR +#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR /* * Vectors 0x30-0x3f are used for ISA interrupts. */ -#define IRQ0_VECTOR (FIRST_EXTERNAL_VECTOR + 0x10) -#define IRQ1_VECTOR (IRQ0_VECTOR + 1) -#define IRQ2_VECTOR (IRQ0_VECTOR + 2) -#define IRQ3_VECTOR (IRQ0_VECTOR + 3) -#define IRQ4_VECTOR (IRQ0_VECTOR + 4) -#define IRQ5_VECTOR (IRQ0_VECTOR + 5) -#define IRQ6_VECTOR (IRQ0_VECTOR + 6) -#define IRQ7_VECTOR (IRQ0_VECTOR + 7) -#define IRQ8_VECTOR (IRQ0_VECTOR + 8) -#define IRQ9_VECTOR (IRQ0_VECTOR + 9) -#define IRQ10_VECTOR (IRQ0_VECTOR + 10) -#define IRQ11_VECTOR (IRQ0_VECTOR + 11) -#define IRQ12_VECTOR (IRQ0_VECTOR + 12) -#define IRQ13_VECTOR (IRQ0_VECTOR + 13) -#define IRQ14_VECTOR (IRQ0_VECTOR + 14) -#define IRQ15_VECTOR (IRQ0_VECTOR + 15) +#define IRQ0_VECTOR (FIRST_EXTERNAL_VECTOR + 0x10) + +#define IRQ1_VECTOR (IRQ0_VECTOR + 1) +#define IRQ2_VECTOR (IRQ0_VECTOR + 2) +#define IRQ3_VECTOR (IRQ0_VECTOR + 3) +#define IRQ4_VECTOR (IRQ0_VECTOR + 4) +#define IRQ5_VECTOR (IRQ0_VECTOR + 5) +#define IRQ6_VECTOR (IRQ0_VECTOR + 6) +#define IRQ7_VECTOR (IRQ0_VECTOR + 7) +#define IRQ8_VECTOR (IRQ0_VECTOR + 8) +#define IRQ9_VECTOR (IRQ0_VECTOR + 9) +#define IRQ10_VECTOR (IRQ0_VECTOR + 10) +#define IRQ11_VECTOR (IRQ0_VECTOR + 11) +#define IRQ12_VECTOR (IRQ0_VECTOR + 12) +#define IRQ13_VECTOR (IRQ0_VECTOR + 13) +#define IRQ14_VECTOR (IRQ0_VECTOR + 14) +#define IRQ15_VECTOR (IRQ0_VECTOR + 15) /* * Special IRQ vectors used by the SMP architecture, 0xf0-0xff @@ -49,119 +71,98 @@ * some of the following vectors are 'rare', they are merged * into a single vector (CALL_FUNCTION_VECTOR) to save vector space. * TLB, reschedule and local APIC vectors are performance-critical. - * - * Vectors 0xf0-0xfa are free (reserved for future Linux use). */ -#ifdef CONFIG_X86_32 - -# define SPURIOUS_APIC_VECTOR 0xff -# define ERROR_APIC_VECTOR 0xfe -# define INVALIDATE_TLB_VECTOR 0xfd -# define RESCHEDULE_VECTOR 0xfc -# define CALL_FUNCTION_VECTOR 0xfb -# define CALL_FUNCTION_SINGLE_VECTOR 0xfa -# define THERMAL_APIC_VECTOR 0xf0 - -#else #define SPURIOUS_APIC_VECTOR 0xff +/* + * Sanity check + */ +#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F) +# error SPURIOUS_APIC_VECTOR definition error +#endif + #define ERROR_APIC_VECTOR 0xfe #define RESCHEDULE_VECTOR 0xfd #define CALL_FUNCTION_VECTOR 0xfc #define CALL_FUNCTION_SINGLE_VECTOR 0xfb #define THERMAL_APIC_VECTOR 0xfa -#define THRESHOLD_APIC_VECTOR 0xf9 -#define UV_BAU_MESSAGE 0xf8 -#define INVALIDATE_TLB_VECTOR_END 0xf7 -#define INVALIDATE_TLB_VECTOR_START 0xf0 /* f0-f7 used for TLB flush */ - -#define NUM_INVALIDATE_TLB_VECTORS 8 +#ifdef CONFIG_X86_32 +/* 0xf8 - 0xf9 : free */ +#else +# define THRESHOLD_APIC_VECTOR 0xf9 +# define UV_BAU_MESSAGE 0xf8 #endif +/* f0-f7 used for spreading out TLB flushes: */ +#define INVALIDATE_TLB_VECTOR_END 0xf7 +#define INVALIDATE_TLB_VECTOR_START 0xf0 +#define NUM_INVALIDATE_TLB_VECTORS 8 + /* * Local APIC timer IRQ vector is on a different priority level, * to work around the 'lost local interrupt if more than 2 IRQ * sources per level' errata. */ -#define LOCAL_TIMER_VECTOR 0xef +#define LOCAL_TIMER_VECTOR 0xef + +/* + * Performance monitoring interrupt vector: + */ +#define LOCAL_PERF_VECTOR 0xee /* * First APIC vector available to drivers: (vectors 0x30-0xee) we * start at 0x31(0x41) to spread out vectors evenly between priority * levels. (0x80 is the syscall vector) */ -#define FIRST_DEVICE_VECTOR (IRQ15_VECTOR + 2) - -#define NR_VECTORS 256 +#define FIRST_DEVICE_VECTOR (IRQ15_VECTOR + 2) -#define FPU_IRQ 13 +#define NR_VECTORS 256 -#define FIRST_VM86_IRQ 3 -#define LAST_VM86_IRQ 15 -#define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15) +#define FPU_IRQ 13 -#define NR_IRQS_LEGACY 16 +#define FIRST_VM86_IRQ 3 +#define LAST_VM86_IRQ 15 -#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER) - -#ifndef CONFIG_SPARSE_IRQ -# if NR_CPUS < MAX_IO_APICS -# define NR_IRQS (NR_VECTORS + (32 * NR_CPUS)) -# else -# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS)) -# endif -#else -# if (8 * NR_CPUS) > (32 * MAX_IO_APICS) -# define NR_IRQS (NR_VECTORS + (8 * NR_CPUS)) -# else -# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS)) -# endif +#ifndef __ASSEMBLY__ +static inline int invalid_vm86_irq(int irq) +{ + return irq < 3 || irq > 15; +} #endif -#elif defined(CONFIG_X86_VOYAGER) - -# define NR_IRQS 224 +/* + * Size the maximum number of interrupts. + * + * If the irq_desc[] array has a sparse layout, we can size things + * generously - it scales up linearly with the maximum number of CPUs, + * and the maximum number of IO-APICs, whichever is higher. + * + * In other cases we size more conservatively, to not create too large + * static arrays. + */ -#else /* IO_APIC || VOYAGER */ +#define NR_IRQS_LEGACY 16 -# define NR_IRQS 16 +#define CPU_VECTOR_LIMIT ( 8 * NR_CPUS ) +#define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS ) +#ifdef CONFIG_X86_IO_APIC +# ifdef CONFIG_SPARSE_IRQ +# define NR_IRQS \ + (CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \ + (NR_VECTORS + CPU_VECTOR_LIMIT) : \ + (NR_VECTORS + IO_APIC_VECTOR_LIMIT)) +# else +# if NR_CPUS < MAX_IO_APICS +# define NR_IRQS (NR_VECTORS + 4*CPU_VECTOR_LIMIT) +# else +# define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT) +# endif +# endif +#else /* !CONFIG_X86_IO_APIC: */ +# define NR_IRQS NR_IRQS_LEGACY #endif -/* Voyager specific defines */ -/* These define the CPIs we use in linux */ -#define VIC_CPI_LEVEL0 0 -#define VIC_CPI_LEVEL1 1 -/* now the fake CPIs */ -#define VIC_TIMER_CPI 2 -#define VIC_INVALIDATE_CPI 3 -#define VIC_RESCHEDULE_CPI 4 -#define VIC_ENABLE_IRQ_CPI 5 -#define VIC_CALL_FUNCTION_CPI 6 -#define VIC_CALL_FUNCTION_SINGLE_CPI 7 - -/* Now the QIC CPIs: Since we don't need the two initial levels, - * these are 2 less than the VIC CPIs */ -#define QIC_CPI_OFFSET 1 -#define QIC_TIMER_CPI (VIC_TIMER_CPI - QIC_CPI_OFFSET) -#define QIC_INVALIDATE_CPI (VIC_INVALIDATE_CPI - QIC_CPI_OFFSET) -#define QIC_RESCHEDULE_CPI (VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET) -#define QIC_ENABLE_IRQ_CPI (VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET) -#define QIC_CALL_FUNCTION_CPI (VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET) -#define QIC_CALL_FUNCTION_SINGLE_CPI (VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET) - -#define VIC_START_FAKE_CPI VIC_TIMER_CPI -#define VIC_END_FAKE_CPI VIC_CALL_FUNCTION_SINGLE_CPI - -/* this is the SYS_INT CPI. */ -#define VIC_SYS_INT 8 -#define VIC_CMN_INT 15 - -/* This is the boot CPI for alternate processors. It gets overwritten - * by the above once the system has activated all available processors */ -#define VIC_CPU_BOOT_CPI VIC_CPI_LEVEL0 -#define VIC_CPU_BOOT_ERRATA_CPI (VIC_CPI_LEVEL0 + 8) - - #endif /* _ASM_X86_IRQ_VECTORS_H */ diff --git a/arch/x86/include/asm/mach-default/mach_apic.h b/arch/x86/include/asm/mach-default/mach_apic.h deleted file mode 100644 index cc09cbbee27..00000000000 --- a/arch/x86/include/asm/mach-default/mach_apic.h +++ /dev/null @@ -1,168 +0,0 @@ -#ifndef _ASM_X86_MACH_DEFAULT_MACH_APIC_H -#define _ASM_X86_MACH_DEFAULT_MACH_APIC_H - -#ifdef CONFIG_X86_LOCAL_APIC - -#include <mach_apicdef.h> -#include <asm/smp.h> - -#define APIC_DFR_VALUE (APIC_DFR_FLAT) - -static inline const struct cpumask *target_cpus(void) -{ -#ifdef CONFIG_SMP - return cpu_online_mask; -#else - return cpumask_of(0); -#endif -} - -#define NO_BALANCE_IRQ (0) -#define esr_disable (0) - -#ifdef CONFIG_X86_64 -#include <asm/genapic.h> -#define INT_DELIVERY_MODE (genapic->int_delivery_mode) -#define INT_DEST_MODE (genapic->int_dest_mode) -#define TARGET_CPUS (genapic->target_cpus()) -#define apic_id_registered (genapic->apic_id_registered) -#define init_apic_ldr (genapic->init_apic_ldr) -#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid) -#define cpu_mask_to_apicid_and (genapic->cpu_mask_to_apicid_and) -#define phys_pkg_id (genapic->phys_pkg_id) -#define vector_allocation_domain (genapic->vector_allocation_domain) -#define read_apic_id() (GET_APIC_ID(apic_read(APIC_ID))) -#define send_IPI_self (genapic->send_IPI_self) -#define wakeup_secondary_cpu (genapic->wakeup_cpu) -extern void setup_apic_routing(void); -#else -#define INT_DELIVERY_MODE dest_LowestPrio -#define INT_DEST_MODE 1 /* logical delivery broadcast to all procs */ -#define TARGET_CPUS (target_cpus()) -#define wakeup_secondary_cpu wakeup_secondary_cpu_via_init -/* - * Set up the logical destination ID. - * - * Intel recommends to set DFR, LDR and TPR before enabling - * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel - * document number 292116). So here it goes... - */ -static inline void init_apic_ldr(void) -{ - unsigned long val; - - apic_write(APIC_DFR, APIC_DFR_VALUE); - val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); - apic_write(APIC_LDR, val); -} - -static inline int apic_id_registered(void) -{ - return physid_isset(read_apic_id(), phys_cpu_present_map); -} - -static inline unsigned int cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - return cpumask_bits(cpumask)[0]; -} - -static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - unsigned long mask1 = cpumask_bits(cpumask)[0]; - unsigned long mask2 = cpumask_bits(andmask)[0]; - unsigned long mask3 = cpumask_bits(cpu_online_mask)[0]; - - return (unsigned int)(mask1 & mask2 & mask3); -} - -static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - -static inline void setup_apic_routing(void) -{ -#ifdef CONFIG_X86_IO_APIC - printk("Enabling APIC mode: %s. Using %d I/O APICs\n", - "Flat", nr_ioapics); -#endif -} - -static inline int apicid_to_node(int logical_apicid) -{ -#ifdef CONFIG_SMP - return apicid_2_node[hard_smp_processor_id()]; -#else - return 0; -#endif -} - -static inline void vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - *retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } }; -} -#endif - -static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid) -{ - return physid_isset(apicid, bitmap); -} - -static inline unsigned long check_apicid_present(int bit) -{ - return physid_isset(bit, phys_cpu_present_map); -} - -static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map) -{ - return phys_map; -} - -static inline int multi_timer_check(int apic, int irq) -{ - return 0; -} - -/* Mapping from cpu number to logical apicid */ -static inline int cpu_to_logical_apicid(int cpu) -{ - return 1 << cpu; -} - -static inline int cpu_present_to_apicid(int mps_cpu) -{ - if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) - return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu); - else - return BAD_APICID; -} - -static inline physid_mask_t apicid_to_cpu_present(int phys_apicid) -{ - return physid_mask_of_physid(phys_apicid); -} - -static inline void setup_portio_remap(void) -{ -} - -static inline int check_phys_apicid_present(int boot_cpu_physical_apicid) -{ - return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map); -} - -static inline void enable_apic_mode(void) -{ -} -#endif /* CONFIG_X86_LOCAL_APIC */ -#endif /* _ASM_X86_MACH_DEFAULT_MACH_APIC_H */ diff --git a/arch/x86/include/asm/mach-default/mach_apicdef.h b/arch/x86/include/asm/mach-default/mach_apicdef.h deleted file mode 100644 index 53179936d6c..00000000000 --- a/arch/x86/include/asm/mach-default/mach_apicdef.h +++ /dev/null @@ -1,24 +0,0 @@ -#ifndef _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H -#define _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H - -#include <asm/apic.h> - -#ifdef CONFIG_X86_64 -#define APIC_ID_MASK (genapic->apic_id_mask) -#define GET_APIC_ID(x) (genapic->get_apic_id(x)) -#define SET_APIC_ID(x) (genapic->set_apic_id(x)) -#else -#define APIC_ID_MASK (0xF<<24) -static inline unsigned get_apic_id(unsigned long x) -{ - unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); - if (APIC_XAPIC(ver)) - return (((x)>>24)&0xFF); - else - return (((x)>>24)&0xF); -} - -#define GET_APIC_ID(x) get_apic_id(x) -#endif - -#endif /* _ASM_X86_MACH_DEFAULT_MACH_APICDEF_H */ diff --git a/arch/x86/include/asm/mach-default/mach_ipi.h b/arch/x86/include/asm/mach-default/mach_ipi.h deleted file mode 100644 index 191312d155d..00000000000 --- a/arch/x86/include/asm/mach-default/mach_ipi.h +++ /dev/null @@ -1,64 +0,0 @@ -#ifndef _ASM_X86_MACH_DEFAULT_MACH_IPI_H -#define _ASM_X86_MACH_DEFAULT_MACH_IPI_H - -/* Avoid include hell */ -#define NMI_VECTOR 0x02 - -void send_IPI_mask_bitmask(const struct cpumask *mask, int vector); -void send_IPI_mask_allbutself(const struct cpumask *mask, int vector); -void __send_IPI_shortcut(unsigned int shortcut, int vector); - -extern int no_broadcast; - -#ifdef CONFIG_X86_64 -#include <asm/genapic.h> -#define send_IPI_mask (genapic->send_IPI_mask) -#define send_IPI_mask_allbutself (genapic->send_IPI_mask_allbutself) -#else -static inline void send_IPI_mask(const struct cpumask *mask, int vector) -{ - send_IPI_mask_bitmask(mask, vector); -} -void send_IPI_mask_allbutself(const struct cpumask *mask, int vector); -#endif - -static inline void __local_send_IPI_allbutself(int vector) -{ - if (no_broadcast || vector == NMI_VECTOR) - send_IPI_mask_allbutself(cpu_online_mask, vector); - else - __send_IPI_shortcut(APIC_DEST_ALLBUT, vector); -} - -static inline void __local_send_IPI_all(int vector) -{ - if (no_broadcast || vector == NMI_VECTOR) - send_IPI_mask(cpu_online_mask, vector); - else - __send_IPI_shortcut(APIC_DEST_ALLINC, vector); -} - -#ifdef CONFIG_X86_64 -#define send_IPI_allbutself (genapic->send_IPI_allbutself) -#define send_IPI_all (genapic->send_IPI_all) -#else -static inline void send_IPI_allbutself(int vector) -{ - /* - * if there are no other CPUs in the system then we get an APIC send - * error if we try to broadcast, thus avoid sending IPIs in this case. - */ - if (!(num_online_cpus() > 1)) - return; - - __local_send_IPI_allbutself(vector); - return; -} - -static inline void send_IPI_all(int vector) -{ - __local_send_IPI_all(vector); -} -#endif - -#endif /* _ASM_X86_MACH_DEFAULT_MACH_IPI_H */ diff --git a/arch/x86/include/asm/mach-default/mach_mpparse.h b/arch/x86/include/asm/mach-default/mach_mpparse.h deleted file mode 100644 index c70a263d68c..00000000000 --- a/arch/x86/include/asm/mach-default/mach_mpparse.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H -#define _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H - -static inline int -mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) -{ - return 0; -} - -/* Hook from generic ACPI tables.c */ -static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - return 0; -} - - -#endif /* _ASM_X86_MACH_DEFAULT_MACH_MPPARSE_H */ diff --git a/arch/x86/include/asm/mach-default/mach_mpspec.h b/arch/x86/include/asm/mach-default/mach_mpspec.h deleted file mode 100644 index e85ede686be..00000000000 --- a/arch/x86/include/asm/mach-default/mach_mpspec.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H -#define _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H - -#define MAX_IRQ_SOURCES 256 - -#if CONFIG_BASE_SMALL == 0 -#define MAX_MP_BUSSES 256 -#else -#define MAX_MP_BUSSES 32 -#endif - -#endif /* _ASM_X86_MACH_DEFAULT_MACH_MPSPEC_H */ diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h deleted file mode 100644 index 89897a6a65b..00000000000 --- a/arch/x86/include/asm/mach-default/mach_wakecpu.h +++ /dev/null @@ -1,41 +0,0 @@ -#ifndef _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H -#define _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H - -#define TRAMPOLINE_PHYS_LOW (0x467) -#define TRAMPOLINE_PHYS_HIGH (0x469) - -static inline void wait_for_init_deassert(atomic_t *deassert) -{ - while (!atomic_read(deassert)) - cpu_relax(); - return; -} - -/* Nothing to do for most platforms, since cleared by the INIT cycle */ -static inline void smp_callin_clear_local_apic(void) -{ -} - -static inline void store_NMI_vector(unsigned short *high, unsigned short *low) -{ -} - -static inline void restore_NMI_vector(unsigned short *high, unsigned short *low) -{ -} - -#ifdef CONFIG_SMP -extern void __inquire_remote_apic(int apicid); -#else /* CONFIG_SMP */ -static inline void __inquire_remote_apic(int apicid) -{ -} -#endif /* CONFIG_SMP */ - -static inline void inquire_remote_apic(int apicid) -{ - if (apic_verbosity >= APIC_DEBUG) - __inquire_remote_apic(apicid); -} - -#endif /* _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H */ diff --git a/arch/x86/include/asm/mach-generic/gpio.h b/arch/x86/include/asm/mach-generic/gpio.h deleted file mode 100644 index 995c45efdb3..00000000000 --- a/arch/x86/include/asm/mach-generic/gpio.h +++ /dev/null @@ -1,15 +0,0 @@ -#ifndef _ASM_X86_MACH_GENERIC_GPIO_H -#define _ASM_X86_MACH_GENERIC_GPIO_H - -int gpio_request(unsigned gpio, const char *label); -void gpio_free(unsigned gpio); -int gpio_direction_input(unsigned gpio); -int gpio_direction_output(unsigned gpio, int value); -int gpio_get_value(unsigned gpio); -void gpio_set_value(unsigned gpio, int value); -int gpio_to_irq(unsigned gpio); -int irq_to_gpio(unsigned irq); - -#include <asm-generic/gpio.h> /* cansleep wrappers */ - -#endif /* _ASM_X86_MACH_GENERIC_GPIO_H */ diff --git a/arch/x86/include/asm/mach-generic/mach_apic.h b/arch/x86/include/asm/mach-generic/mach_apic.h deleted file mode 100644 index 48553e958ad..00000000000 --- a/arch/x86/include/asm/mach-generic/mach_apic.h +++ /dev/null @@ -1,35 +0,0 @@ -#ifndef _ASM_X86_MACH_GENERIC_MACH_APIC_H -#define _ASM_X86_MACH_GENERIC_MACH_APIC_H - -#include <asm/genapic.h> - -#define esr_disable (genapic->ESR_DISABLE) -#define NO_BALANCE_IRQ (genapic->no_balance_irq) -#define INT_DELIVERY_MODE (genapic->int_delivery_mode) -#define INT_DEST_MODE (genapic->int_dest_mode) -#undef APIC_DEST_LOGICAL -#define APIC_DEST_LOGICAL (genapic->apic_destination_logical) -#define TARGET_CPUS (genapic->target_cpus()) -#define apic_id_registered (genapic->apic_id_registered) -#define init_apic_ldr (genapic->init_apic_ldr) -#define ioapic_phys_id_map (genapic->ioapic_phys_id_map) -#define setup_apic_routing (genapic->setup_apic_routing) -#define multi_timer_check (genapic->multi_timer_check) -#define apicid_to_node (genapic->apicid_to_node) -#define cpu_to_logical_apicid (genapic->cpu_to_logical_apicid) -#define cpu_present_to_apicid (genapic->cpu_present_to_apicid) -#define apicid_to_cpu_present (genapic->apicid_to_cpu_present) -#define setup_portio_remap (genapic->setup_portio_remap) -#define check_apicid_present (genapic->check_apicid_present) -#define check_phys_apicid_present (genapic->check_phys_apicid_present) -#define check_apicid_used (genapic->check_apicid_used) -#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid) -#define cpu_mask_to_apicid_and (genapic->cpu_mask_to_apicid_and) -#define vector_allocation_domain (genapic->vector_allocation_domain) -#define enable_apic_mode (genapic->enable_apic_mode) -#define phys_pkg_id (genapic->phys_pkg_id) -#define wakeup_secondary_cpu (genapic->wakeup_cpu) - -extern void generic_bigsmp_probe(void); - -#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */ diff --git a/arch/x86/include/asm/mach-generic/mach_apicdef.h b/arch/x86/include/asm/mach-generic/mach_apicdef.h deleted file mode 100644 index 68041f3802f..00000000000 --- a/arch/x86/include/asm/mach-generic/mach_apicdef.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_X86_MACH_GENERIC_MACH_APICDEF_H -#define _ASM_X86_MACH_GENERIC_MACH_APICDEF_H - -#ifndef APIC_DEFINITION -#include <asm/genapic.h> - -#define GET_APIC_ID (genapic->get_apic_id) -#define APIC_ID_MASK (genapic->apic_id_mask) -#endif - -#endif /* _ASM_X86_MACH_GENERIC_MACH_APICDEF_H */ diff --git a/arch/x86/include/asm/mach-generic/mach_ipi.h b/arch/x86/include/asm/mach-generic/mach_ipi.h deleted file mode 100644 index ffd637e3c3d..00000000000 --- a/arch/x86/include/asm/mach-generic/mach_ipi.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _ASM_X86_MACH_GENERIC_MACH_IPI_H -#define _ASM_X86_MACH_GENERIC_MACH_IPI_H - -#include <asm/genapic.h> - -#define send_IPI_mask (genapic->send_IPI_mask) -#define send_IPI_allbutself (genapic->send_IPI_allbutself) -#define send_IPI_all (genapic->send_IPI_all) - -#endif /* _ASM_X86_MACH_GENERIC_MACH_IPI_H */ diff --git a/arch/x86/include/asm/mach-generic/mach_mpparse.h b/arch/x86/include/asm/mach-generic/mach_mpparse.h deleted file mode 100644 index 9444ab8dca9..00000000000 --- a/arch/x86/include/asm/mach-generic/mach_mpparse.h +++ /dev/null @@ -1,9 +0,0 @@ -#ifndef _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H -#define _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H - - -extern int mps_oem_check(struct mpc_table *, char *, char *); - -extern int acpi_madt_oem_check(char *, char *); - -#endif /* _ASM_X86_MACH_GENERIC_MACH_MPPARSE_H */ diff --git a/arch/x86/include/asm/mach-generic/mach_mpspec.h b/arch/x86/include/asm/mach-generic/mach_mpspec.h deleted file mode 100644 index 3bc40722657..00000000000 --- a/arch/x86/include/asm/mach-generic/mach_mpspec.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H -#define _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H - -#define MAX_IRQ_SOURCES 256 - -/* Summit or generic (i.e. installer) kernels need lots of bus entries. */ -/* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */ -#define MAX_MP_BUSSES 260 - -extern void numaq_mps_oem_check(struct mpc_table *, char *, char *); - -#endif /* _ASM_X86_MACH_GENERIC_MACH_MPSPEC_H */ diff --git a/arch/x86/include/asm/mach-generic/mach_wakecpu.h b/arch/x86/include/asm/mach-generic/mach_wakecpu.h deleted file mode 100644 index 1ab16b168c8..00000000000 --- a/arch/x86/include/asm/mach-generic/mach_wakecpu.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H -#define _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H - -#define TRAMPOLINE_PHYS_LOW (genapic->trampoline_phys_low) -#define TRAMPOLINE_PHYS_HIGH (genapic->trampoline_phys_high) -#define wait_for_init_deassert (genapic->wait_for_init_deassert) -#define smp_callin_clear_local_apic (genapic->smp_callin_clear_local_apic) -#define store_NMI_vector (genapic->store_NMI_vector) -#define restore_NMI_vector (genapic->restore_NMI_vector) -#define inquire_remote_apic (genapic->inquire_remote_apic) - -#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */ diff --git a/arch/x86/include/asm/mach-rdc321x/gpio.h b/arch/x86/include/asm/mach-rdc321x/gpio.h deleted file mode 100644 index c210ab5788b..00000000000 --- a/arch/x86/include/asm/mach-rdc321x/gpio.h +++ /dev/null @@ -1,60 +0,0 @@ -#ifndef _ASM_X86_MACH_RDC321X_GPIO_H -#define _ASM_X86_MACH_RDC321X_GPIO_H - -#include <linux/kernel.h> - -extern int rdc_gpio_get_value(unsigned gpio); -extern void rdc_gpio_set_value(unsigned gpio, int value); -extern int rdc_gpio_direction_input(unsigned gpio); -extern int rdc_gpio_direction_output(unsigned gpio, int value); -extern int rdc_gpio_request(unsigned gpio, const char *label); -extern void rdc_gpio_free(unsigned gpio); -extern void __init rdc321x_gpio_setup(void); - -/* Wrappers for the arch-neutral GPIO API */ - -static inline int gpio_request(unsigned gpio, const char *label) -{ - return rdc_gpio_request(gpio, label); -} - -static inline void gpio_free(unsigned gpio) -{ - might_sleep(); - rdc_gpio_free(gpio); -} - -static inline int gpio_direction_input(unsigned gpio) -{ - return rdc_gpio_direction_input(gpio); -} - -static inline int gpio_direction_output(unsigned gpio, int value) -{ - return rdc_gpio_direction_output(gpio, value); -} - -static inline int gpio_get_value(unsigned gpio) -{ - return rdc_gpio_get_value(gpio); -} - -static inline void gpio_set_value(unsigned gpio, int value) -{ - rdc_gpio_set_value(gpio, value); -} - -static inline int gpio_to_irq(unsigned gpio) -{ - return gpio; -} - -static inline int irq_to_gpio(unsigned irq) -{ - return irq; -} - -/* For cansleep */ -#include <asm-generic/gpio.h> - -#endif /* _ASM_X86_MACH_RDC321X_GPIO_H */ diff --git a/arch/x86/include/asm/mach-default/mach_timer.h b/arch/x86/include/asm/mach_timer.h index 853728519ae..853728519ae 100644 --- a/arch/x86/include/asm/mach-default/mach_timer.h +++ b/arch/x86/include/asm/mach_timer.h diff --git a/arch/x86/include/asm/mach-default/mach_traps.h b/arch/x86/include/asm/mach_traps.h index f7920601e47..f7920601e47 100644 --- a/arch/x86/include/asm/mach-default/mach_traps.h +++ b/arch/x86/include/asm/mach_traps.h diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h index 5a65b107ad5..031f6266f42 100644 --- a/arch/x86/include/asm/math_emu.h +++ b/arch/x86/include/asm/math_emu.h @@ -1,31 +1,18 @@ #ifndef _ASM_X86_MATH_EMU_H #define _ASM_X86_MATH_EMU_H +#include <asm/ptrace.h> +#include <asm/vm86.h> + /* This structure matches the layout of the data saved to the stack following a device-not-present interrupt, part of it saved automatically by the 80386/80486. */ -struct info { +struct math_emu_info { long ___orig_eip; - long ___ebx; - long ___ecx; - long ___edx; - long ___esi; - long ___edi; - long ___ebp; - long ___eax; - long ___ds; - long ___es; - long ___fs; - long ___orig_eax; - long ___eip; - long ___cs; - long ___eflags; - long ___esp; - long ___ss; - long ___vm86_es; /* This and the following only in vm86 mode */ - long ___vm86_ds; - long ___vm86_fs; - long ___vm86_gs; + union { + struct pt_regs *regs; + struct kernel_vm86_regs *vm86; + }; }; #endif /* _ASM_X86_MATH_EMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 8aeeb3fd73d..f923203dc39 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -21,11 +21,54 @@ static inline void paravirt_activate_mm(struct mm_struct *prev, int init_new_context(struct task_struct *tsk, struct mm_struct *mm); void destroy_context(struct mm_struct *mm); -#ifdef CONFIG_X86_32 -# include "mmu_context_32.h" -#else -# include "mmu_context_64.h" + +static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ +#ifdef CONFIG_SMP + if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) + percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY); +#endif +} + +static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk) +{ + unsigned cpu = smp_processor_id(); + + if (likely(prev != next)) { + /* stop flush ipis for the previous mm */ + cpu_clear(cpu, prev->cpu_vm_mask); +#ifdef CONFIG_SMP + percpu_write(cpu_tlbstate.state, TLBSTATE_OK); + percpu_write(cpu_tlbstate.active_mm, next); #endif + cpu_set(cpu, next->cpu_vm_mask); + + /* Re-load page tables */ + load_cr3(next->pgd); + + /* + * load the LDT, if the LDT is different: + */ + if (unlikely(prev->context.ldt != next->context.ldt)) + load_LDT_nolock(&next->context); + } +#ifdef CONFIG_SMP + else { + percpu_write(cpu_tlbstate.state, TLBSTATE_OK); + BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next); + + if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) { + /* We were in lazy tlb mode and leave_mm disabled + * tlb flush IPI delivery. We must reload CR3 + * to make sure to use no freed page tables. + */ + load_cr3(next->pgd); + load_LDT_nolock(&next->context); + } + } +#endif +} #define activate_mm(prev, next) \ do { \ @@ -33,5 +76,17 @@ do { \ switch_mm((prev), (next), NULL); \ } while (0); +#ifdef CONFIG_X86_32 +#define deactivate_mm(tsk, mm) \ +do { \ + lazy_load_gs(0); \ +} while (0) +#else +#define deactivate_mm(tsk, mm) \ +do { \ + load_gs_index(0); \ + loadsegment(fs, 0); \ +} while (0) +#endif #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h deleted file mode 100644 index 7e98ce1d2c0..00000000000 --- a/arch/x86/include/asm/mmu_context_32.h +++ /dev/null @@ -1,55 +0,0 @@ -#ifndef _ASM_X86_MMU_CONTEXT_32_H -#define _ASM_X86_MMU_CONTEXT_32_H - -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ -#ifdef CONFIG_SMP - if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK) - x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY); -#endif -} - -static inline void switch_mm(struct mm_struct *prev, - struct mm_struct *next, - struct task_struct *tsk) -{ - int cpu = smp_processor_id(); - - if (likely(prev != next)) { - /* stop flush ipis for the previous mm */ - cpu_clear(cpu, prev->cpu_vm_mask); -#ifdef CONFIG_SMP - x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK); - x86_write_percpu(cpu_tlbstate.active_mm, next); -#endif - cpu_set(cpu, next->cpu_vm_mask); - - /* Re-load page tables */ - load_cr3(next->pgd); - - /* - * load the LDT, if the LDT is different: - */ - if (unlikely(prev->context.ldt != next->context.ldt)) - load_LDT_nolock(&next->context); - } -#ifdef CONFIG_SMP - else { - x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK); - BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next); - - if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) { - /* We were in lazy tlb mode and leave_mm disabled - * tlb flush IPI delivery. We must reload %cr3. - */ - load_cr3(next->pgd); - load_LDT_nolock(&next->context); - } - } -#endif -} - -#define deactivate_mm(tsk, mm) \ - asm("movl %0,%%gs": :"r" (0)); - -#endif /* _ASM_X86_MMU_CONTEXT_32_H */ diff --git a/arch/x86/include/asm/mmu_context_64.h b/arch/x86/include/asm/mmu_context_64.h deleted file mode 100644 index 677d36e9540..00000000000 --- a/arch/x86/include/asm/mmu_context_64.h +++ /dev/null @@ -1,54 +0,0 @@ -#ifndef _ASM_X86_MMU_CONTEXT_64_H -#define _ASM_X86_MMU_CONTEXT_64_H - -#include <asm/pda.h> - -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ -#ifdef CONFIG_SMP - if (read_pda(mmu_state) == TLBSTATE_OK) - write_pda(mmu_state, TLBSTATE_LAZY); -#endif -} - -static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, - struct task_struct *tsk) -{ - unsigned cpu = smp_processor_id(); - if (likely(prev != next)) { - /* stop flush ipis for the previous mm */ - cpu_clear(cpu, prev->cpu_vm_mask); -#ifdef CONFIG_SMP - write_pda(mmu_state, TLBSTATE_OK); - write_pda(active_mm, next); -#endif - cpu_set(cpu, next->cpu_vm_mask); - load_cr3(next->pgd); - - if (unlikely(next->context.ldt != prev->context.ldt)) - load_LDT_nolock(&next->context); - } -#ifdef CONFIG_SMP - else { - write_pda(mmu_state, TLBSTATE_OK); - if (read_pda(active_mm) != next) - BUG(); - if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) { - /* We were in lazy tlb mode and leave_mm disabled - * tlb flush IPI delivery. We must reload CR3 - * to make sure to use no freed page tables. - */ - load_cr3(next->pgd); - load_LDT_nolock(&next->context); - } - } -#endif -} - -#define deactivate_mm(tsk, mm) \ -do { \ - load_gs_index(0); \ - asm volatile("movl %0,%%fs"::"r"(0)); \ -} while (0) - -#endif /* _ASM_X86_MMU_CONTEXT_64_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 62d14ce3cd0..5916c8df09d 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -9,7 +9,18 @@ extern int apic_version[MAX_APICS]; extern int pic_mode; #ifdef CONFIG_X86_32 -#include <mach_mpspec.h> + +/* + * Summit or generic (i.e. installer) kernels need lots of bus entries. + * Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. + */ +#if CONFIG_BASE_SMALL == 0 +# define MAX_MP_BUSSES 260 +#else +# define MAX_MP_BUSSES 32 +#endif + +#define MAX_IRQ_SOURCES 256 extern unsigned int def_to_bigsmp; extern u8 apicid_2_node[]; @@ -20,15 +31,15 @@ extern int mp_bus_id_to_local[MAX_MP_BUSSES]; extern int quad_local_to_mp_bus_id [NR_CPUS/4][4]; #endif -#define MAX_APICID 256 +#define MAX_APICID 256 -#else +#else /* CONFIG_X86_64: */ -#define MAX_MP_BUSSES 256 +#define MAX_MP_BUSSES 256 /* Each PCI slot may be a combo card with its own bus. 4 IRQ pins per slot. */ -#define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4) +#define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4) -#endif +#endif /* CONFIG_X86_64 */ extern void early_find_smp_config(void); extern void early_get_smp_config(void); @@ -45,11 +56,13 @@ extern int smp_found_config; extern int mpc_default_type; extern unsigned long mp_lapic_addr; -extern void find_smp_config(void); extern void get_smp_config(void); + #ifdef CONFIG_X86_MPPARSE +extern void find_smp_config(void); extern void early_reserve_e820_mpc_new(void); #else +static inline void find_smp_config(void) { } static inline void early_reserve_e820_mpc_new(void) { } #endif @@ -60,9 +73,12 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi); extern void mp_config_acpi_legacy_irqs(void); extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low); +extern int acpi_probe_gsi(void); #ifdef CONFIG_X86_IO_APIC extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin, u32 gsi, int triggering, int polarity); +extern int mp_find_ioapic(int gsi); +extern int mp_find_ioapic_pin(int ioapic, int gsi); #else static inline int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin, @@ -71,6 +87,11 @@ mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin, return 0; } #endif +#else /* !CONFIG_ACPI: */ +static inline int acpi_probe_gsi(void) +{ + return 0; +} #endif /* CONFIG_ACPI */ #define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_APICS) @@ -142,4 +163,10 @@ static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map) extern physid_mask_t phys_cpu_present_map; +extern int generic_mps_oem_check(struct mpc_table *, char *, char *); + +extern int default_acpi_madt_oem_check(char *, char *); + +extern void numaq_mps_oem_check(struct mpc_table *, char *, char *); + #endif /* _ASM_X86_MPSPEC_H */ diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h index 1e8bd30b4c1..9f0a5f5d29e 100644 --- a/arch/x86/include/asm/numaq.h +++ b/arch/x86/include/asm/numaq.h @@ -31,6 +31,8 @@ extern int found_numaq; extern int get_memcfg_numaq(void); +extern void *xquad_portio; + /* * SYS_CFG_DATA_PRIV_ADDR, struct eachquadmem, and struct sys_cfg_data are the */ diff --git a/arch/x86/include/asm/numaq/apic.h b/arch/x86/include/asm/numaq/apic.h deleted file mode 100644 index bf37bc49bd8..00000000000 --- a/arch/x86/include/asm/numaq/apic.h +++ /dev/null @@ -1,142 +0,0 @@ -#ifndef __ASM_NUMAQ_APIC_H -#define __ASM_NUMAQ_APIC_H - -#include <asm/io.h> -#include <linux/mmzone.h> -#include <linux/nodemask.h> - -#define APIC_DFR_VALUE (APIC_DFR_CLUSTER) - -static inline const cpumask_t *target_cpus(void) -{ - return &CPU_MASK_ALL; -} - -#define NO_BALANCE_IRQ (1) -#define esr_disable (1) - -#define INT_DELIVERY_MODE dest_LowestPrio -#define INT_DEST_MODE 0 /* physical delivery on LOCAL quad */ - -static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid) -{ - return physid_isset(apicid, bitmap); -} -static inline unsigned long check_apicid_present(int bit) -{ - return physid_isset(bit, phys_cpu_present_map); -} -#define apicid_cluster(apicid) (apicid & 0xF0) - -static inline int apic_id_registered(void) -{ - return 1; -} - -static inline void init_apic_ldr(void) -{ - /* Already done in NUMA-Q firmware */ -} - -static inline void setup_apic_routing(void) -{ - printk("Enabling APIC mode: %s. Using %d I/O APICs\n", - "NUMA-Q", nr_ioapics); -} - -/* - * Skip adding the timer int on secondary nodes, which causes - * a small but painful rift in the time-space continuum. - */ -static inline int multi_timer_check(int apic, int irq) -{ - return apic != 0 && irq == 0; -} - -static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map) -{ - /* We don't have a good way to do this yet - hack */ - return physids_promote(0xFUL); -} - -/* Mapping from cpu number to logical apicid */ -extern u8 cpu_2_logical_apicid[]; -static inline int cpu_to_logical_apicid(int cpu) -{ - if (cpu >= nr_cpu_ids) - return BAD_APICID; - return (int)cpu_2_logical_apicid[cpu]; -} - -/* - * Supporting over 60 cpus on NUMA-Q requires a locality-dependent - * cpu to APIC ID relation to properly interact with the intelligent - * mode of the cluster controller. - */ -static inline int cpu_present_to_apicid(int mps_cpu) -{ - if (mps_cpu < 60) - return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3)); - else - return BAD_APICID; -} - -static inline int apicid_to_node(int logical_apicid) -{ - return logical_apicid >> 4; -} - -static inline physid_mask_t apicid_to_cpu_present(int logical_apicid) -{ - int node = apicid_to_node(logical_apicid); - int cpu = __ffs(logical_apicid & 0xf); - - return physid_mask_of_physid(cpu + 4*node); -} - -extern void *xquad_portio; - -static inline void setup_portio_remap(void) -{ - int num_quads = num_online_nodes(); - - if (num_quads <= 1) - return; - - printk("Remapping cross-quad port I/O for %d quads\n", num_quads); - xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD); - printk("xquad_portio vaddr 0x%08lx, len %08lx\n", - (u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD); -} - -static inline int check_phys_apicid_present(int boot_cpu_physical_apicid) -{ - return (1); -} - -static inline void enable_apic_mode(void) -{ -} - -/* - * We use physical apicids here, not logical, so just return the default - * physical broadcast to stop people from breaking us - */ -static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask) -{ - return (int) 0xF; -} - -static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - return (int) 0xF; -} - -/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */ -static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - -#endif /* __ASM_NUMAQ_APIC_H */ diff --git a/arch/x86/include/asm/numaq/apicdef.h b/arch/x86/include/asm/numaq/apicdef.h deleted file mode 100644 index e012a46cc22..00000000000 --- a/arch/x86/include/asm/numaq/apicdef.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef __ASM_NUMAQ_APICDEF_H -#define __ASM_NUMAQ_APICDEF_H - - -#define APIC_ID_MASK (0xF<<24) - -static inline unsigned get_apic_id(unsigned long x) -{ - return (((x)>>24)&0x0F); -} - -#define GET_APIC_ID(x) get_apic_id(x) - -#endif diff --git a/arch/x86/include/asm/numaq/ipi.h b/arch/x86/include/asm/numaq/ipi.h deleted file mode 100644 index a8374c65277..00000000000 --- a/arch/x86/include/asm/numaq/ipi.h +++ /dev/null @@ -1,22 +0,0 @@ -#ifndef __ASM_NUMAQ_IPI_H -#define __ASM_NUMAQ_IPI_H - -void send_IPI_mask_sequence(const struct cpumask *mask, int vector); -void send_IPI_mask_allbutself(const struct cpumask *mask, int vector); - -static inline void send_IPI_mask(const struct cpumask *mask, int vector) -{ - send_IPI_mask_sequence(mask, vector); -} - -static inline void send_IPI_allbutself(int vector) -{ - send_IPI_mask_allbutself(cpu_online_mask, vector); -} - -static inline void send_IPI_all(int vector) -{ - send_IPI_mask(cpu_online_mask, vector); -} - -#endif /* __ASM_NUMAQ_IPI_H */ diff --git a/arch/x86/include/asm/numaq/mpparse.h b/arch/x86/include/asm/numaq/mpparse.h deleted file mode 100644 index a2eeefcd1cc..00000000000 --- a/arch/x86/include/asm/numaq/mpparse.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_NUMAQ_MPPARSE_H -#define __ASM_NUMAQ_MPPARSE_H - -extern void numaq_mps_oem_check(struct mpc_table *, char *, char *); - -#endif /* __ASM_NUMAQ_MPPARSE_H */ diff --git a/arch/x86/include/asm/numaq/wakecpu.h b/arch/x86/include/asm/numaq/wakecpu.h deleted file mode 100644 index 6f499df8edd..00000000000 --- a/arch/x86/include/asm/numaq/wakecpu.h +++ /dev/null @@ -1,45 +0,0 @@ -#ifndef __ASM_NUMAQ_WAKECPU_H -#define __ASM_NUMAQ_WAKECPU_H - -/* This file copes with machines that wakeup secondary CPUs by NMIs */ - -#define TRAMPOLINE_PHYS_LOW (0x8) -#define TRAMPOLINE_PHYS_HIGH (0xa) - -/* We don't do anything here because we use NMI's to boot instead */ -static inline void wait_for_init_deassert(atomic_t *deassert) -{ -} - -/* - * Because we use NMIs rather than the INIT-STARTUP sequence to - * bootstrap the CPUs, the APIC may be in a weird state. Kick it. - */ -static inline void smp_callin_clear_local_apic(void) -{ - clear_local_APIC(); -} - -static inline void store_NMI_vector(unsigned short *high, unsigned short *low) -{ - printk("Storing NMI vector\n"); - *high = - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)); - *low = - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)); -} - -static inline void restore_NMI_vector(unsigned short *high, unsigned short *low) -{ - printk("Restoring NMI vector\n"); - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = - *high; - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = - *low; -} - -static inline void inquire_remote_apic(int apicid) -{ -} - -#endif /* __ASM_NUMAQ_WAKECPU_H */ diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index e9873a2e869..6b9810859da 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -147,7 +147,7 @@ static inline pteval_t native_pte_val(pte_t pte) return pte.pte; } -static inline pteval_t native_pte_flags(pte_t pte) +static inline pteval_t pte_flags(pte_t pte) { return native_pte_val(pte) & PTE_FLAGS_MASK; } @@ -173,7 +173,6 @@ static inline pteval_t native_pte_flags(pte_t pte) #endif #define pte_val(x) native_pte_val(x) -#define pte_flags(x) native_pte_flags(x) #define __pte(x) native_make_pte(x) #endif /* CONFIG_PARAVIRT */ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 5ebca29f44f..e27fdbe5f9e 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -13,8 +13,8 @@ #define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1) #define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER) -#define IRQSTACK_ORDER 2 -#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER) +#define IRQ_STACK_ORDER 2 +#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER) #define STACKFAULT_STACK 1 #define DOUBLEFAULT_STACK 2 diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 32bc6c2c138..1c244b64573 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -12,21 +12,38 @@ #define CLBR_EAX (1 << 0) #define CLBR_ECX (1 << 1) #define CLBR_EDX (1 << 2) +#define CLBR_EDI (1 << 3) -#ifdef CONFIG_X86_64 -#define CLBR_RSI (1 << 3) -#define CLBR_RDI (1 << 4) +#ifdef CONFIG_X86_32 +/* CLBR_ANY should match all regs platform has. For i386, that's just it */ +#define CLBR_ANY ((1 << 4) - 1) + +#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX) +#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX) +#define CLBR_SCRATCH (0) +#else +#define CLBR_RAX CLBR_EAX +#define CLBR_RCX CLBR_ECX +#define CLBR_RDX CLBR_EDX +#define CLBR_RDI CLBR_EDI +#define CLBR_RSI (1 << 4) #define CLBR_R8 (1 << 5) #define CLBR_R9 (1 << 6) #define CLBR_R10 (1 << 7) #define CLBR_R11 (1 << 8) + #define CLBR_ANY ((1 << 9) - 1) + +#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \ + CLBR_RCX | CLBR_R8 | CLBR_R9) +#define CLBR_RET_REG (CLBR_RAX) +#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11) + #include <asm/desc_defs.h> -#else -/* CLBR_ANY should match all regs platform has. For i386, that's just it */ -#define CLBR_ANY ((1 << 3) - 1) #endif /* X86_64 */ +#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG) + #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/cpumask.h> @@ -40,6 +57,14 @@ struct tss_struct; struct mm_struct; struct desc_struct; +/* + * Wrapper type for pointers to code which uses the non-standard + * calling convention. See PV_CALL_SAVE_REGS_THUNK below. + */ +struct paravirt_callee_save { + void *func; +}; + /* general info */ struct pv_info { unsigned int kernel_rpl; @@ -189,11 +214,15 @@ struct pv_irq_ops { * expected to use X86_EFLAGS_IF; all other bits * returned from save_fl are undefined, and may be ignored by * restore_fl. + * + * NOTE: These functions callers expect the callee to preserve + * more registers than the standard C calling convention. */ - unsigned long (*save_fl)(void); - void (*restore_fl)(unsigned long); - void (*irq_disable)(void); - void (*irq_enable)(void); + struct paravirt_callee_save save_fl; + struct paravirt_callee_save restore_fl; + struct paravirt_callee_save irq_disable; + struct paravirt_callee_save irq_enable; + void (*safe_halt)(void); void (*halt)(void); @@ -244,7 +273,8 @@ struct pv_mmu_ops { void (*flush_tlb_user)(void); void (*flush_tlb_kernel)(void); void (*flush_tlb_single)(unsigned long addr); - void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm, + void (*flush_tlb_others)(const struct cpumask *cpus, + struct mm_struct *mm, unsigned long va); /* Hooks for allocating and freeing a pagetable top-level */ @@ -278,12 +308,11 @@ struct pv_mmu_ops { void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); - pteval_t (*pte_val)(pte_t); - pteval_t (*pte_flags)(pte_t); - pte_t (*make_pte)(pteval_t pte); + struct paravirt_callee_save pte_val; + struct paravirt_callee_save make_pte; - pgdval_t (*pgd_val)(pgd_t); - pgd_t (*make_pgd)(pgdval_t pgd); + struct paravirt_callee_save pgd_val; + struct paravirt_callee_save make_pgd; #if PAGETABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE @@ -298,12 +327,12 @@ struct pv_mmu_ops { void (*set_pud)(pud_t *pudp, pud_t pudval); - pmdval_t (*pmd_val)(pmd_t); - pmd_t (*make_pmd)(pmdval_t pmd); + struct paravirt_callee_save pmd_val; + struct paravirt_callee_save make_pmd; #if PAGETABLE_LEVELS == 4 - pudval_t (*pud_val)(pud_t); - pud_t (*make_pud)(pudval_t pud); + struct paravirt_callee_save pud_val; + struct paravirt_callee_save make_pud; void (*set_pgd)(pgd_t *pudp, pgd_t pgdval); #endif /* PAGETABLE_LEVELS == 4 */ @@ -388,6 +417,8 @@ extern struct pv_lock_ops pv_lock_ops; asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") unsigned paravirt_patch_nop(void); +unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); +unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len); unsigned paravirt_patch_ignore(unsigned len); unsigned paravirt_patch_call(void *insnbuf, const void *target, u16 tgt_clobbers, @@ -479,25 +510,45 @@ int paravirt_disable_iospace(void); * makes sure the incoming and outgoing types are always correct. */ #ifdef CONFIG_X86_32 -#define PVOP_VCALL_ARGS unsigned long __eax, __edx, __ecx +#define PVOP_VCALL_ARGS \ + unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx #define PVOP_CALL_ARGS PVOP_VCALL_ARGS + +#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x)) +#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x)) +#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x)) + #define PVOP_VCALL_CLOBBERS "=a" (__eax), "=d" (__edx), \ "=c" (__ecx) #define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS + +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), "=d" (__edx) +#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS + #define EXTRA_CLOBBERS #define VEXTRA_CLOBBERS -#else -#define PVOP_VCALL_ARGS unsigned long __edi, __esi, __edx, __ecx +#else /* CONFIG_X86_64 */ +#define PVOP_VCALL_ARGS \ + unsigned long __edi = __edi, __esi = __esi, \ + __edx = __edx, __ecx = __ecx #define PVOP_CALL_ARGS PVOP_VCALL_ARGS, __eax + +#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x)) +#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x)) +#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x)) +#define PVOP_CALL_ARG4(x) "c" ((unsigned long)(x)) + #define PVOP_VCALL_CLOBBERS "=D" (__edi), \ "=S" (__esi), "=d" (__edx), \ "=c" (__ecx) - #define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax) +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax) +#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS + #define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11" #define VEXTRA_CLOBBERS , "rax", "r8", "r9", "r10", "r11" -#endif +#endif /* CONFIG_X86_32 */ #ifdef CONFIG_PARAVIRT_DEBUG #define PVOP_TEST_NULL(op) BUG_ON(op == NULL) @@ -505,10 +556,11 @@ int paravirt_disable_iospace(void); #define PVOP_TEST_NULL(op) ((void)op) #endif -#define __PVOP_CALL(rettype, op, pre, post, ...) \ +#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \ + pre, post, ...) \ ({ \ rettype __ret; \ - PVOP_CALL_ARGS; \ + PVOP_CALL_ARGS; \ PVOP_TEST_NULL(op); \ /* This is 32-bit specific, but is okay in 64-bit */ \ /* since this condition will never hold */ \ @@ -516,70 +568,113 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : PVOP_CALL_CLOBBERS \ + : call_clbr \ : paravirt_type(op), \ - paravirt_clobber(CLBR_ANY), \ + paravirt_clobber(clbr), \ ##__VA_ARGS__ \ - : "memory", "cc" EXTRA_CLOBBERS); \ + : "memory", "cc" extra_clbr); \ __ret = (rettype)((((u64)__edx) << 32) | __eax); \ } else { \ asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : PVOP_CALL_CLOBBERS \ + : call_clbr \ : paravirt_type(op), \ - paravirt_clobber(CLBR_ANY), \ + paravirt_clobber(clbr), \ ##__VA_ARGS__ \ - : "memory", "cc" EXTRA_CLOBBERS); \ + : "memory", "cc" extra_clbr); \ __ret = (rettype)__eax; \ } \ __ret; \ }) -#define __PVOP_VCALL(op, pre, post, ...) \ + +#define __PVOP_CALL(rettype, op, pre, post, ...) \ + ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \ + EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__) + +#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \ + ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \ + PVOP_CALLEE_CLOBBERS, , \ + pre, post, ##__VA_ARGS__) + + +#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \ ({ \ PVOP_VCALL_ARGS; \ PVOP_TEST_NULL(op); \ asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : PVOP_VCALL_CLOBBERS \ + : call_clbr \ : paravirt_type(op), \ - paravirt_clobber(CLBR_ANY), \ + paravirt_clobber(clbr), \ ##__VA_ARGS__ \ - : "memory", "cc" VEXTRA_CLOBBERS); \ + : "memory", "cc" extra_clbr); \ }) +#define __PVOP_VCALL(op, pre, post, ...) \ + ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \ + VEXTRA_CLOBBERS, \ + pre, post, ##__VA_ARGS__) + +#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...) \ + ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \ + PVOP_VCALLEE_CLOBBERS, , \ + pre, post, ##__VA_ARGS__) + + + #define PVOP_CALL0(rettype, op) \ __PVOP_CALL(rettype, op, "", "") #define PVOP_VCALL0(op) \ __PVOP_VCALL(op, "", "") +#define PVOP_CALLEE0(rettype, op) \ + __PVOP_CALLEESAVE(rettype, op, "", "") +#define PVOP_VCALLEE0(op) \ + __PVOP_VCALLEESAVE(op, "", "") + + #define PVOP_CALL1(rettype, op, arg1) \ - __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1))) + __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1)) #define PVOP_VCALL1(op, arg1) \ - __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1))) + __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1)) + +#define PVOP_CALLEE1(rettype, op, arg1) \ + __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1)) +#define PVOP_VCALLEE1(op, arg1) \ + __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1)) + #define PVOP_CALL2(rettype, op, arg1, arg2) \ - __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), \ - "1" ((unsigned long)(arg2))) + __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2)) #define PVOP_VCALL2(op, arg1, arg2) \ - __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), \ - "1" ((unsigned long)(arg2))) + __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2)) + +#define PVOP_CALLEE2(rettype, op, arg1, arg2) \ + __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2)) +#define PVOP_VCALLEE2(op, arg1, arg2) \ + __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2)) + #define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \ - __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), \ - "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3))) + __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) #define PVOP_VCALL3(op, arg1, arg2, arg3) \ - __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), \ - "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3))) + __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) /* This is the only difference in x86_64. We can make it much simpler */ #ifdef CONFIG_X86_32 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ __PVOP_CALL(rettype, op, \ "push %[_arg4];", "lea 4(%%esp),%%esp;", \ - "0" ((u32)(arg1)), "1" ((u32)(arg2)), \ - "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4))) + PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4))) #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ __PVOP_VCALL(op, \ "push %[_arg4];", "lea 4(%%esp),%%esp;", \ @@ -587,13 +682,13 @@ int paravirt_disable_iospace(void); "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4))) #else #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ - __PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), \ - "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)), \ - "3"((unsigned long)(arg4))) + __PVOP_CALL(rettype, op, "", "", \ + PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ - __PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), \ - "1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)), \ - "3"((unsigned long)(arg4))) + __PVOP_VCALL(op, "", "", \ + PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) #endif static inline int paravirt_enabled(void) @@ -984,10 +1079,11 @@ static inline void __flush_tlb_single(unsigned long addr) PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr); } -static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, +static inline void flush_tlb_others(const struct cpumask *cpumask, + struct mm_struct *mm, unsigned long va) { - PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va); + PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, cpumask, mm, va); } static inline int paravirt_pgd_alloc(struct mm_struct *mm) @@ -1059,13 +1155,13 @@ static inline pte_t __pte(pteval_t val) pteval_t ret; if (sizeof(pteval_t) > sizeof(long)) - ret = PVOP_CALL2(pteval_t, - pv_mmu_ops.make_pte, - val, (u64)val >> 32); + ret = PVOP_CALLEE2(pteval_t, + pv_mmu_ops.make_pte, + val, (u64)val >> 32); else - ret = PVOP_CALL1(pteval_t, - pv_mmu_ops.make_pte, - val); + ret = PVOP_CALLEE1(pteval_t, + pv_mmu_ops.make_pte, + val); return (pte_t) { .pte = ret }; } @@ -1075,29 +1171,12 @@ static inline pteval_t pte_val(pte_t pte) pteval_t ret; if (sizeof(pteval_t) > sizeof(long)) - ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_val, - pte.pte, (u64)pte.pte >> 32); - else - ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_val, - pte.pte); - - return ret; -} - -static inline pteval_t pte_flags(pte_t pte) -{ - pteval_t ret; - - if (sizeof(pteval_t) > sizeof(long)) - ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags, - pte.pte, (u64)pte.pte >> 32); + ret = PVOP_CALLEE2(pteval_t, pv_mmu_ops.pte_val, + pte.pte, (u64)pte.pte >> 32); else - ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags, - pte.pte); + ret = PVOP_CALLEE1(pteval_t, pv_mmu_ops.pte_val, + pte.pte); -#ifdef CONFIG_PARAVIRT_DEBUG - BUG_ON(ret & PTE_PFN_MASK); -#endif return ret; } @@ -1106,11 +1185,11 @@ static inline pgd_t __pgd(pgdval_t val) pgdval_t ret; if (sizeof(pgdval_t) > sizeof(long)) - ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.make_pgd, - val, (u64)val >> 32); + ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.make_pgd, + val, (u64)val >> 32); else - ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.make_pgd, - val); + ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.make_pgd, + val); return (pgd_t) { ret }; } @@ -1120,11 +1199,11 @@ static inline pgdval_t pgd_val(pgd_t pgd) pgdval_t ret; if (sizeof(pgdval_t) > sizeof(long)) - ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.pgd_val, - pgd.pgd, (u64)pgd.pgd >> 32); + ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.pgd_val, + pgd.pgd, (u64)pgd.pgd >> 32); else - ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.pgd_val, - pgd.pgd); + ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.pgd_val, + pgd.pgd); return ret; } @@ -1188,11 +1267,11 @@ static inline pmd_t __pmd(pmdval_t val) pmdval_t ret; if (sizeof(pmdval_t) > sizeof(long)) - ret = PVOP_CALL2(pmdval_t, pv_mmu_ops.make_pmd, - val, (u64)val >> 32); + ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.make_pmd, + val, (u64)val >> 32); else - ret = PVOP_CALL1(pmdval_t, pv_mmu_ops.make_pmd, - val); + ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.make_pmd, + val); return (pmd_t) { ret }; } @@ -1202,11 +1281,11 @@ static inline pmdval_t pmd_val(pmd_t pmd) pmdval_t ret; if (sizeof(pmdval_t) > sizeof(long)) - ret = PVOP_CALL2(pmdval_t, pv_mmu_ops.pmd_val, - pmd.pmd, (u64)pmd.pmd >> 32); + ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.pmd_val, + pmd.pmd, (u64)pmd.pmd >> 32); else - ret = PVOP_CALL1(pmdval_t, pv_mmu_ops.pmd_val, - pmd.pmd); + ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.pmd_val, + pmd.pmd); return ret; } @@ -1228,11 +1307,11 @@ static inline pud_t __pud(pudval_t val) pudval_t ret; if (sizeof(pudval_t) > sizeof(long)) - ret = PVOP_CALL2(pudval_t, pv_mmu_ops.make_pud, - val, (u64)val >> 32); + ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.make_pud, + val, (u64)val >> 32); else - ret = PVOP_CALL1(pudval_t, pv_mmu_ops.make_pud, - val); + ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.make_pud, + val); return (pud_t) { ret }; } @@ -1242,11 +1321,11 @@ static inline pudval_t pud_val(pud_t pud) pudval_t ret; if (sizeof(pudval_t) > sizeof(long)) - ret = PVOP_CALL2(pudval_t, pv_mmu_ops.pud_val, - pud.pud, (u64)pud.pud >> 32); + ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.pud_val, + pud.pud, (u64)pud.pud >> 32); else - ret = PVOP_CALL1(pudval_t, pv_mmu_ops.pud_val, - pud.pud); + ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.pud_val, + pud.pud); return ret; } @@ -1387,6 +1466,9 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, } void _paravirt_nop(void); +u32 _paravirt_ident_32(u32); +u64 _paravirt_ident_64(u64); + #define paravirt_nop ((void *)_paravirt_nop) #ifdef CONFIG_SMP @@ -1400,6 +1482,7 @@ static inline int __raw_spin_is_contended(struct raw_spinlock *lock) { return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock); } +#define __raw_spin_is_contended __raw_spin_is_contended static __always_inline void __raw_spin_lock(struct raw_spinlock *lock) { @@ -1436,12 +1519,37 @@ extern struct paravirt_patch_site __parainstructions[], __parainstructions_end[]; #ifdef CONFIG_X86_32 -#define PV_SAVE_REGS "pushl %%ecx; pushl %%edx;" -#define PV_RESTORE_REGS "popl %%edx; popl %%ecx" +#define PV_SAVE_REGS "pushl %ecx; pushl %edx;" +#define PV_RESTORE_REGS "popl %edx; popl %ecx;" + +/* save and restore all caller-save registers, except return value */ +#define PV_SAVE_ALL_CALLER_REGS "pushl %ecx;" +#define PV_RESTORE_ALL_CALLER_REGS "popl %ecx;" + #define PV_FLAGS_ARG "0" #define PV_EXTRA_CLOBBERS #define PV_VEXTRA_CLOBBERS #else +/* save and restore all caller-save registers, except return value */ +#define PV_SAVE_ALL_CALLER_REGS \ + "push %rcx;" \ + "push %rdx;" \ + "push %rsi;" \ + "push %rdi;" \ + "push %r8;" \ + "push %r9;" \ + "push %r10;" \ + "push %r11;" +#define PV_RESTORE_ALL_CALLER_REGS \ + "pop %r11;" \ + "pop %r10;" \ + "pop %r9;" \ + "pop %r8;" \ + "pop %rdi;" \ + "pop %rsi;" \ + "pop %rdx;" \ + "pop %rcx;" + /* We save some registers, but all of them, that's too much. We clobber all * caller saved registers but the argument parameter */ #define PV_SAVE_REGS "pushq %%rdi;" @@ -1451,52 +1559,76 @@ extern struct paravirt_patch_site __parainstructions[], #define PV_FLAGS_ARG "D" #endif +/* + * Generate a thunk around a function which saves all caller-save + * registers except for the return value. This allows C functions to + * be called from assembler code where fewer than normal registers are + * available. It may also help code generation around calls from C + * code if the common case doesn't use many registers. + * + * When a callee is wrapped in a thunk, the caller can assume that all + * arg regs and all scratch registers are preserved across the + * call. The return value in rax/eax will not be saved, even for void + * functions. + */ +#define PV_CALLEE_SAVE_REGS_THUNK(func) \ + extern typeof(func) __raw_callee_save_##func; \ + static void *__##func##__ __used = func; \ + \ + asm(".pushsection .text;" \ + "__raw_callee_save_" #func ": " \ + PV_SAVE_ALL_CALLER_REGS \ + "call " #func ";" \ + PV_RESTORE_ALL_CALLER_REGS \ + "ret;" \ + ".popsection") + +/* Get a reference to a callee-save function */ +#define PV_CALLEE_SAVE(func) \ + ((struct paravirt_callee_save) { __raw_callee_save_##func }) + +/* Promise that "func" already uses the right calling convention */ +#define __PV_IS_CALLEE_SAVE(func) \ + ((struct paravirt_callee_save) { func }) + static inline unsigned long __raw_local_save_flags(void) { unsigned long f; - asm volatile(paravirt_alt(PV_SAVE_REGS - PARAVIRT_CALL - PV_RESTORE_REGS) + asm volatile(paravirt_alt(PARAVIRT_CALL) : "=a"(f) : paravirt_type(pv_irq_ops.save_fl), paravirt_clobber(CLBR_EAX) - : "memory", "cc" PV_VEXTRA_CLOBBERS); + : "memory", "cc"); return f; } static inline void raw_local_irq_restore(unsigned long f) { - asm volatile(paravirt_alt(PV_SAVE_REGS - PARAVIRT_CALL - PV_RESTORE_REGS) + asm volatile(paravirt_alt(PARAVIRT_CALL) : "=a"(f) : PV_FLAGS_ARG(f), paravirt_type(pv_irq_ops.restore_fl), paravirt_clobber(CLBR_EAX) - : "memory", "cc" PV_EXTRA_CLOBBERS); + : "memory", "cc"); } static inline void raw_local_irq_disable(void) { - asm volatile(paravirt_alt(PV_SAVE_REGS - PARAVIRT_CALL - PV_RESTORE_REGS) + asm volatile(paravirt_alt(PARAVIRT_CALL) : : paravirt_type(pv_irq_ops.irq_disable), paravirt_clobber(CLBR_EAX) - : "memory", "eax", "cc" PV_EXTRA_CLOBBERS); + : "memory", "eax", "cc"); } static inline void raw_local_irq_enable(void) { - asm volatile(paravirt_alt(PV_SAVE_REGS - PARAVIRT_CALL - PV_RESTORE_REGS) + asm volatile(paravirt_alt(PARAVIRT_CALL) : : paravirt_type(pv_irq_ops.irq_enable), paravirt_clobber(CLBR_EAX) - : "memory", "eax", "cc" PV_EXTRA_CLOBBERS); + : "memory", "eax", "cc"); } static inline unsigned long __raw_local_irq_save(void) @@ -1539,33 +1671,49 @@ static inline unsigned long __raw_local_irq_save(void) .popsection +#define COND_PUSH(set, mask, reg) \ + .if ((~(set)) & mask); push %reg; .endif +#define COND_POP(set, mask, reg) \ + .if ((~(set)) & mask); pop %reg; .endif + #ifdef CONFIG_X86_64 -#define PV_SAVE_REGS \ - push %rax; \ - push %rcx; \ - push %rdx; \ - push %rsi; \ - push %rdi; \ - push %r8; \ - push %r9; \ - push %r10; \ - push %r11 -#define PV_RESTORE_REGS \ - pop %r11; \ - pop %r10; \ - pop %r9; \ - pop %r8; \ - pop %rdi; \ - pop %rsi; \ - pop %rdx; \ - pop %rcx; \ - pop %rax + +#define PV_SAVE_REGS(set) \ + COND_PUSH(set, CLBR_RAX, rax); \ + COND_PUSH(set, CLBR_RCX, rcx); \ + COND_PUSH(set, CLBR_RDX, rdx); \ + COND_PUSH(set, CLBR_RSI, rsi); \ + COND_PUSH(set, CLBR_RDI, rdi); \ + COND_PUSH(set, CLBR_R8, r8); \ + COND_PUSH(set, CLBR_R9, r9); \ + COND_PUSH(set, CLBR_R10, r10); \ + COND_PUSH(set, CLBR_R11, r11) +#define PV_RESTORE_REGS(set) \ + COND_POP(set, CLBR_R11, r11); \ + COND_POP(set, CLBR_R10, r10); \ + COND_POP(set, CLBR_R9, r9); \ + COND_POP(set, CLBR_R8, r8); \ + COND_POP(set, CLBR_RDI, rdi); \ + COND_POP(set, CLBR_RSI, rsi); \ + COND_POP(set, CLBR_RDX, rdx); \ + COND_POP(set, CLBR_RCX, rcx); \ + COND_POP(set, CLBR_RAX, rax) + #define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 8) #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8) #define PARA_INDIRECT(addr) *addr(%rip) #else -#define PV_SAVE_REGS pushl %eax; pushl %edi; pushl %ecx; pushl %edx -#define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax +#define PV_SAVE_REGS(set) \ + COND_PUSH(set, CLBR_EAX, eax); \ + COND_PUSH(set, CLBR_EDI, edi); \ + COND_PUSH(set, CLBR_ECX, ecx); \ + COND_PUSH(set, CLBR_EDX, edx) +#define PV_RESTORE_REGS(set) \ + COND_POP(set, CLBR_EDX, edx); \ + COND_POP(set, CLBR_ECX, ecx); \ + COND_POP(set, CLBR_EDI, edi); \ + COND_POP(set, CLBR_EAX, eax) + #define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 4) #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4) #define PARA_INDIRECT(addr) *%cs:addr @@ -1577,15 +1725,15 @@ static inline unsigned long __raw_local_irq_save(void) #define DISABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \ - PV_SAVE_REGS; \ + PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \ - PV_RESTORE_REGS;) \ + PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #define ENABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \ - PV_SAVE_REGS; \ + PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ - PV_RESTORE_REGS;) + PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #define USERGS_SYSRET32 \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \ @@ -1615,11 +1763,15 @@ static inline unsigned long __raw_local_irq_save(void) PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ swapgs) +/* + * Note: swapgs is very special, and in practise is either going to be + * implemented with a single "swapgs" instruction or something very + * special. Either way, we don't need to save any registers for + * it. + */ #define SWAPGS \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ - PV_SAVE_REGS; \ - call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \ - PV_RESTORE_REGS \ + call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs) \ ) #define GET_CR2_INTO_RCX \ diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index b8493b3b989..9709fdff661 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -5,10 +5,8 @@ #ifdef CONFIG_X86_PAT extern int pat_enabled; -extern void validate_pat_support(struct cpuinfo_x86 *c); #else static const int pat_enabled; -static inline void validate_pat_support(struct cpuinfo_x86 *c) { } #endif extern void pat_init(void); @@ -17,6 +15,4 @@ extern int reserve_memtype(u64 start, u64 end, unsigned long req_type, unsigned long *ret_type); extern int free_memtype(u64 start, u64 end); -extern void pat_disable(char *reason); - #endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/mach-default/pci-functions.h b/arch/x86/include/asm/pci-functions.h index ed0bab42735..ed0bab42735 100644 --- a/arch/x86/include/asm/mach-default/pci-functions.h +++ b/arch/x86/include/asm/pci-functions.h diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h deleted file mode 100644 index 2fbfff88df3..00000000000 --- a/arch/x86/include/asm/pda.h +++ /dev/null @@ -1,137 +0,0 @@ -#ifndef _ASM_X86_PDA_H -#define _ASM_X86_PDA_H - -#ifndef __ASSEMBLY__ -#include <linux/stddef.h> -#include <linux/types.h> -#include <linux/cache.h> -#include <asm/page.h> - -/* Per processor datastructure. %gs points to it while the kernel runs */ -struct x8664_pda { - struct task_struct *pcurrent; /* 0 Current process */ - unsigned long data_offset; /* 8 Per cpu data offset from linker - address */ - unsigned long kernelstack; /* 16 top of kernel stack for current */ - unsigned long oldrsp; /* 24 user rsp for system call */ - int irqcount; /* 32 Irq nesting counter. Starts -1 */ - unsigned int cpunumber; /* 36 Logical CPU number */ -#ifdef CONFIG_CC_STACKPROTECTOR - unsigned long stack_canary; /* 40 stack canary value */ - /* gcc-ABI: this canary MUST be at - offset 40!!! */ -#endif - char *irqstackptr; - short nodenumber; /* number of current node (32k max) */ - short in_bootmem; /* pda lives in bootmem */ - unsigned int __softirq_pending; - unsigned int __nmi_count; /* number of NMI on this CPUs */ - short mmu_state; - short isidle; - struct mm_struct *active_mm; - unsigned apic_timer_irqs; - unsigned irq0_irqs; - unsigned irq_resched_count; - unsigned irq_call_count; - unsigned irq_tlb_count; - unsigned irq_thermal_count; - unsigned irq_threshold_count; - unsigned irq_spurious_count; -} ____cacheline_aligned_in_smp; - -extern struct x8664_pda **_cpu_pda; -extern void pda_init(int); - -#define cpu_pda(i) (_cpu_pda[i]) - -/* - * There is no fast way to get the base address of the PDA, all the accesses - * have to mention %fs/%gs. So it needs to be done this Torvaldian way. - */ -extern void __bad_pda_field(void) __attribute__((noreturn)); - -/* - * proxy_pda doesn't actually exist, but tell gcc it is accessed for - * all PDA accesses so it gets read/write dependencies right. - */ -extern struct x8664_pda _proxy_pda; - -#define pda_offset(field) offsetof(struct x8664_pda, field) - -#define pda_to_op(op, field, val) \ -do { \ - typedef typeof(_proxy_pda.field) T__; \ - if (0) { T__ tmp__; tmp__ = (val); } /* type checking */ \ - switch (sizeof(_proxy_pda.field)) { \ - case 2: \ - asm(op "w %1,%%gs:%c2" : \ - "+m" (_proxy_pda.field) : \ - "ri" ((T__)val), \ - "i"(pda_offset(field))); \ - break; \ - case 4: \ - asm(op "l %1,%%gs:%c2" : \ - "+m" (_proxy_pda.field) : \ - "ri" ((T__)val), \ - "i" (pda_offset(field))); \ - break; \ - case 8: \ - asm(op "q %1,%%gs:%c2": \ - "+m" (_proxy_pda.field) : \ - "ri" ((T__)val), \ - "i"(pda_offset(field))); \ - break; \ - default: \ - __bad_pda_field(); \ - } \ -} while (0) - -#define pda_from_op(op, field) \ -({ \ - typeof(_proxy_pda.field) ret__; \ - switch (sizeof(_proxy_pda.field)) { \ - case 2: \ - asm(op "w %%gs:%c1,%0" : \ - "=r" (ret__) : \ - "i" (pda_offset(field)), \ - "m" (_proxy_pda.field)); \ - break; \ - case 4: \ - asm(op "l %%gs:%c1,%0": \ - "=r" (ret__): \ - "i" (pda_offset(field)), \ - "m" (_proxy_pda.field)); \ - break; \ - case 8: \ - asm(op "q %%gs:%c1,%0": \ - "=r" (ret__) : \ - "i" (pda_offset(field)), \ - "m" (_proxy_pda.field)); \ - break; \ - default: \ - __bad_pda_field(); \ - } \ - ret__; \ -}) - -#define read_pda(field) pda_from_op("mov", field) -#define write_pda(field, val) pda_to_op("mov", field, val) -#define add_pda(field, val) pda_to_op("add", field, val) -#define sub_pda(field, val) pda_to_op("sub", field, val) -#define or_pda(field, val) pda_to_op("or", field, val) - -/* This is not atomic against other CPUs -- CPU preemption needs to be off */ -#define test_and_clear_bit_pda(bit, field) \ -({ \ - int old__; \ - asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0" \ - : "=r" (old__), "+m" (_proxy_pda.field) \ - : "dIr" (bit), "i" (pda_offset(field)) : "memory");\ - old__; \ -}) - -#endif - -#define PDA_STACKOFFSET (5*8) - -#endif /* _ASM_X86_PDA_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index ece72053ba6..aee103b26d0 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -2,53 +2,12 @@ #define _ASM_X86_PERCPU_H #ifdef CONFIG_X86_64 -#include <linux/compiler.h> - -/* Same as asm-generic/percpu.h, except that we store the per cpu offset - in the PDA. Longer term the PDA and every per cpu variable - should be just put into a single section and referenced directly - from %gs */ - -#ifdef CONFIG_SMP -#include <asm/pda.h> - -#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset) -#define __my_cpu_offset read_pda(data_offset) - -#define per_cpu_offset(x) (__per_cpu_offset(x)) - +#define __percpu_seg gs +#define __percpu_mov_op movq +#else +#define __percpu_seg fs +#define __percpu_mov_op movl #endif -#include <asm-generic/percpu.h> - -DECLARE_PER_CPU(struct x8664_pda, pda); - -/* - * These are supposed to be implemented as a single instruction which - * operates on the per-cpu data base segment. x86-64 doesn't have - * that yet, so this is a fairly inefficient workaround for the - * meantime. The single instruction is atomic with respect to - * preemption and interrupts, so we need to explicitly disable - * interrupts here to achieve the same effect. However, because it - * can be used from within interrupt-disable/enable, we can't actually - * disable interrupts; disabling preemption is enough. - */ -#define x86_read_percpu(var) \ - ({ \ - typeof(per_cpu_var(var)) __tmp; \ - preempt_disable(); \ - __tmp = __get_cpu_var(var); \ - preempt_enable(); \ - __tmp; \ - }) - -#define x86_write_percpu(var, val) \ - do { \ - preempt_disable(); \ - __get_cpu_var(var) = (val); \ - preempt_enable(); \ - } while(0) - -#else /* CONFIG_X86_64 */ #ifdef __ASSEMBLY__ @@ -65,47 +24,48 @@ DECLARE_PER_CPU(struct x8664_pda, pda); * PER_CPU(cpu_gdt_descr, %ebx) */ #ifdef CONFIG_SMP -#define PER_CPU(var, reg) \ - movl %fs:per_cpu__##this_cpu_off, reg; \ +#define PER_CPU(var, reg) \ + __percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg; \ lea per_cpu__##var(reg), reg -#define PER_CPU_VAR(var) %fs:per_cpu__##var +#define PER_CPU_VAR(var) %__percpu_seg:per_cpu__##var #else /* ! SMP */ -#define PER_CPU(var, reg) \ - movl $per_cpu__##var, reg +#define PER_CPU(var, reg) \ + __percpu_mov_op $per_cpu__##var, reg #define PER_CPU_VAR(var) per_cpu__##var #endif /* SMP */ +#ifdef CONFIG_X86_64_SMP +#define INIT_PER_CPU_VAR(var) init_per_cpu__##var +#else +#define INIT_PER_CPU_VAR(var) per_cpu__##var +#endif + #else /* ...!ASSEMBLY */ +#include <linux/stringify.h> + +#ifdef CONFIG_SMP +#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x +#define __my_cpu_offset percpu_read(this_cpu_off) +#else +#define __percpu_arg(x) "%" #x +#endif + /* - * PER_CPU finds an address of a per-cpu variable. + * Initialized pointers to per-cpu variables needed for the boot + * processor need to use these macros to get the proper address + * offset from __per_cpu_load on SMP. * - * Args: - * var - variable name - * cpu - 32bit register containing the current CPU number - * - * The resulting address is stored in the "cpu" argument. - * - * Example: - * PER_CPU(cpu_gdt_descr, %ebx) + * There also must be an entry in vmlinux_64.lds.S */ -#ifdef CONFIG_SMP - -#define __my_cpu_offset x86_read_percpu(this_cpu_off) - -/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */ -#define __percpu_seg "%%fs:" - -#else /* !SMP */ - -#define __percpu_seg "" - -#endif /* SMP */ - -#include <asm-generic/percpu.h> +#define DECLARE_INIT_PER_CPU(var) \ + extern typeof(per_cpu_var(var)) init_per_cpu_var(var) -/* We can use this directly for local CPU (faster). */ -DECLARE_PER_CPU(unsigned long, this_cpu_off); +#ifdef CONFIG_X86_64_SMP +#define init_per_cpu_var(var) init_per_cpu__##var +#else +#define init_per_cpu_var(var) per_cpu_var(var) +#endif /* For arch-specific code, we can use direct single-insn ops (they * don't give an lvalue though). */ @@ -120,20 +80,25 @@ do { \ } \ switch (sizeof(var)) { \ case 1: \ - asm(op "b %1,"__percpu_seg"%0" \ + asm(op "b %1,"__percpu_arg(0) \ : "+m" (var) \ : "ri" ((T__)val)); \ break; \ case 2: \ - asm(op "w %1,"__percpu_seg"%0" \ + asm(op "w %1,"__percpu_arg(0) \ : "+m" (var) \ : "ri" ((T__)val)); \ break; \ case 4: \ - asm(op "l %1,"__percpu_seg"%0" \ + asm(op "l %1,"__percpu_arg(0) \ : "+m" (var) \ : "ri" ((T__)val)); \ break; \ + case 8: \ + asm(op "q %1,"__percpu_arg(0) \ + : "+m" (var) \ + : "re" ((T__)val)); \ + break; \ default: __bad_percpu_size(); \ } \ } while (0) @@ -143,17 +108,22 @@ do { \ typeof(var) ret__; \ switch (sizeof(var)) { \ case 1: \ - asm(op "b "__percpu_seg"%1,%0" \ + asm(op "b "__percpu_arg(1)",%0" \ : "=r" (ret__) \ : "m" (var)); \ break; \ case 2: \ - asm(op "w "__percpu_seg"%1,%0" \ + asm(op "w "__percpu_arg(1)",%0" \ : "=r" (ret__) \ : "m" (var)); \ break; \ case 4: \ - asm(op "l "__percpu_seg"%1,%0" \ + asm(op "l "__percpu_arg(1)",%0" \ + : "=r" (ret__) \ + : "m" (var)); \ + break; \ + case 8: \ + asm(op "q "__percpu_arg(1)",%0" \ : "=r" (ret__) \ : "m" (var)); \ break; \ @@ -162,13 +132,30 @@ do { \ ret__; \ }) -#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var) -#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val) -#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val) -#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val) -#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val) +#define percpu_read(var) percpu_from_op("mov", per_cpu__##var) +#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val) +#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val) +#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val) +#define percpu_and(var, val) percpu_to_op("and", per_cpu__##var, val) +#define percpu_or(var, val) percpu_to_op("or", per_cpu__##var, val) +#define percpu_xor(var, val) percpu_to_op("xor", per_cpu__##var, val) + +/* This is not atomic against other CPUs -- CPU preemption needs to be off */ +#define x86_test_and_clear_bit_percpu(bit, var) \ +({ \ + int old__; \ + asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0" \ + : "=r" (old__), "+m" (per_cpu__##var) \ + : "dIr" (bit)); \ + old__; \ +}) + +#include <asm-generic/percpu.h> + +/* We can use this directly for local CPU (faster). */ +DECLARE_PER_CPU(unsigned long, this_cpu_off); + #endif /* !__ASSEMBLY__ */ -#endif /* !CONFIG_X86_64 */ #ifdef CONFIG_SMP @@ -195,9 +182,9 @@ do { \ #define early_per_cpu_ptr(_name) (_name##_early_ptr) #define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx]) #define early_per_cpu(_name, _cpu) \ - (early_per_cpu_ptr(_name) ? \ - early_per_cpu_ptr(_name)[_cpu] : \ - per_cpu(_name, _cpu)) + *(early_per_cpu_ptr(_name) ? \ + &early_per_cpu_ptr(_name)[_cpu] : \ + &per_cpu(_name, _cpu)) #else /* !CONFIG_SMP */ #define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 06bbcbd66e9..6f7c102018b 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -240,78 +240,106 @@ static inline int pmd_large(pmd_t pte) (_PAGE_PSE | _PAGE_PRESENT); } +static inline pte_t pte_set_flags(pte_t pte, pteval_t set) +{ + pteval_t v = native_pte_val(pte); + + return native_make_pte(v | set); +} + +static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) +{ + pteval_t v = native_pte_val(pte); + + return native_make_pte(v & ~clear); +} + static inline pte_t pte_mkclean(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_DIRTY); + return pte_clear_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkold(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_ACCESSED); + return pte_clear_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_wrprotect(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_RW); + return pte_clear_flags(pte, _PAGE_RW); } static inline pte_t pte_mkexec(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_NX); + return pte_clear_flags(pte, _PAGE_NX); } static inline pte_t pte_mkdirty(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_DIRTY); + return pte_set_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_ACCESSED); + return pte_set_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkwrite(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_RW); + return pte_set_flags(pte, _PAGE_RW); } static inline pte_t pte_mkhuge(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_PSE); + return pte_set_flags(pte, _PAGE_PSE); } static inline pte_t pte_clrhuge(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_PSE); + return pte_clear_flags(pte, _PAGE_PSE); } static inline pte_t pte_mkglobal(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_GLOBAL); + return pte_set_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_clrglobal(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_GLOBAL); + return pte_clear_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_mkspecial(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_SPECIAL); + return pte_set_flags(pte, _PAGE_SPECIAL); } extern pteval_t __supported_pte_mask; +/* + * Mask out unsupported bits in a present pgprot. Non-present pgprots + * can use those bits for other purposes, so leave them be. + */ +static inline pgprotval_t massage_pgprot(pgprot_t pgprot) +{ + pgprotval_t protval = pgprot_val(pgprot); + + if (protval & _PAGE_PRESENT) + protval &= __supported_pte_mask; + + return protval; +} + static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { - return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) | - pgprot_val(pgprot)) & __supported_pte_mask); + return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) | + massage_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) | - pgprot_val(pgprot)) & __supported_pte_mask); + return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) | + massage_pgprot(pgprot)); } static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) @@ -323,7 +351,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * the newprot (if present): */ val &= _PAGE_CHG_MASK; - val |= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask; + val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK; return __pte(val); } @@ -339,7 +367,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK) -#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask) +#define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline int is_new_memtype_allowed(unsigned long flags, unsigned long new_flags) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index ba09289acca..1df9637dfda 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -11,7 +11,6 @@ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> -#include <asm/pda.h> extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; diff --git a/arch/x86/include/asm/prctl.h b/arch/x86/include/asm/prctl.h index a8894647dd9..3ac5032fae0 100644 --- a/arch/x86/include/asm/prctl.h +++ b/arch/x86/include/asm/prctl.h @@ -6,8 +6,4 @@ #define ARCH_GET_FS 0x1003 #define ARCH_GET_GS 0x1004 -#ifdef CONFIG_X86_64 -extern long sys_arch_prctl(int, unsigned long); -#endif /* CONFIG_X86_64 */ - #endif /* _ASM_X86_PRCTL_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 091cd8855f2..a0133838b67 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -73,7 +73,7 @@ struct cpuinfo_x86 { char pad0; #else /* Number of 4K pages in DTLB/ITLB combined(in pages): */ - int x86_tlbsize; + int x86_tlbsize; __u8 x86_virt_bits; __u8 x86_phys_bits; #endif @@ -353,7 +353,7 @@ struct i387_soft_struct { u8 no_update; u8 rm; u8 alimit; - struct info *info; + struct math_emu_info *info; u32 entry_eip; }; @@ -378,7 +378,29 @@ union thread_xstate { #ifdef CONFIG_X86_64 DECLARE_PER_CPU(struct orig_ist, orig_ist); + +union irq_stack_union { + char irq_stack[IRQ_STACK_SIZE]; + /* + * GCC hardcodes the stack canary as %gs:40. Since the + * irq_stack is the object at %gs:0, we reserve the bottom + * 48 bytes of the irq stack for the canary. + */ + struct { + char gs_base[40]; + unsigned long stack_canary; + }; +}; + +DECLARE_PER_CPU(union irq_stack_union, irq_stack_union); +DECLARE_INIT_PER_CPU(irq_stack_union); + +DECLARE_PER_CPU(char *, irq_stack_ptr); +#else /* X86_64 */ +#ifdef CONFIG_CC_STACKPROTECTOR +DECLARE_PER_CPU(unsigned long, stack_canary); #endif +#endif /* X86_64 */ extern void print_cpu_info(struct cpuinfo_x86 *); extern unsigned int xstate_size; @@ -752,9 +774,9 @@ extern int sysenter_setup(void); extern struct desc_ptr early_gdt_descr; extern void cpu_set_gdt(int); -extern void switch_to_new_gdt(void); +extern void switch_to_new_gdt(int); +extern void load_percpu_segment(int); extern void cpu_init(void); -extern void init_gdt(int cpu); static inline unsigned long get_debugctlmsr(void) { diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index d6a22f92ba7..49fb3ecf3bb 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -18,11 +18,7 @@ extern void syscall32_cpu_init(void); extern void check_efer(void); -#ifdef CONFIG_X86_BIOS_REBOOT extern int reboot_force; -#else -static const int reboot_force = 0; -#endif long do_arch_prctl(struct task_struct *task, int code, unsigned long addr); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 6d34d954c22..e304b66abee 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -28,7 +28,7 @@ struct pt_regs { int xds; int xes; int xfs; - /* int gs; */ + int xgs; long orig_eax; long eip; int xcs; @@ -50,7 +50,7 @@ struct pt_regs { unsigned long ds; unsigned long es; unsigned long fs; - /* int gs; */ + unsigned long gs; unsigned long orig_ax; unsigned long ip; unsigned long cs; diff --git a/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h b/arch/x86/include/asm/rdc321x_defs.h index c8e9c8bed3d..c8e9c8bed3d 100644 --- a/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h +++ b/arch/x86/include/asm/rdc321x_defs.h diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 1dc1b51ac62..14e0ed86a6f 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -61,7 +61,7 @@ * * 26 - ESPFIX small SS * 27 - per-cpu [ offset to per-cpu data area ] - * 28 - unused + * 28 - stack_canary-20 [ for stack protector ] * 29 - unused * 30 - unused * 31 - TSS for double fault handler @@ -95,6 +95,13 @@ #define __KERNEL_PERCPU 0 #endif +#define GDT_ENTRY_STACK_CANARY (GDT_ENTRY_KERNEL_BASE + 16) +#ifdef CONFIG_CC_STACKPROTECTOR +#define __KERNEL_STACK_CANARY (GDT_ENTRY_STACK_CANARY * 8) +#else +#define __KERNEL_STACK_CANARY 0 +#endif + #define GDT_ENTRY_DOUBLEFAULT_TSS 31 /* diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index ebe858cdc8a..45b40278b58 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_SETUP_H #define _ASM_X86_SETUP_H +#ifdef __KERNEL__ + #define COMMAND_LINE_SIZE 2048 #ifndef __ASSEMBLY__ @@ -8,10 +10,8 @@ /* Interrupt control for vSMPowered x86_64 systems */ void vsmp_init(void); - void setup_bios_corruption_check(void); - #ifdef CONFIG_X86_VISWS extern void visws_early_detect(void); extern int is_visws_box(void); @@ -43,7 +43,7 @@ struct x86_quirks { void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); void (*mpc_oem_pci_bus)(struct mpc_bus *m); void (*smp_read_mpc_oem)(struct mpc_oemtable *oemtable, - unsigned short oemsize); + unsigned short oemsize); int (*setup_ioapic_ids)(void); int (*update_genapic)(void); }; @@ -56,8 +56,6 @@ extern unsigned long saved_video_mode; #endif #endif /* __ASSEMBLY__ */ -#ifdef __KERNEL__ - #ifdef __i386__ #include <linux/pfn.h> @@ -100,7 +98,6 @@ extern unsigned long init_pg_tables_start; extern unsigned long init_pg_tables_end; #else -void __init x86_64_init_pda(void); void __init x86_64_start_kernel(char *real_mode); void __init x86_64_start_reservations(char *real_mode_data); diff --git a/arch/x86/include/asm/mach-default/setup_arch.h b/arch/x86/include/asm/setup_arch.h index 38846208b54..38846208b54 100644 --- a/arch/x86/include/asm/mach-default/setup_arch.h +++ b/arch/x86/include/asm/setup_arch.h diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index a8cea7b0943..47d0e21f2b9 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -15,21 +15,16 @@ # include <asm/io_apic.h> # endif #endif -#include <asm/pda.h> #include <asm/thread_info.h> #include <asm/cpumask.h> -extern int __cpuinit get_local_pda(int cpu); - extern int smp_num_siblings; extern unsigned int num_processors; DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); DECLARE_PER_CPU(cpumask_t, cpu_core_map); DECLARE_PER_CPU(u16, cpu_llc_id); -#ifdef CONFIG_X86_32 DECLARE_PER_CPU(int, cpu_number); -#endif static inline struct cpumask *cpu_sibling_mask(int cpu) { @@ -162,11 +157,11 @@ extern unsigned disabled_cpus __cpuinitdata; * from the initial startup. We map APIC_BASE very early in page_setup(), * so this is correct in the x86 case. */ -#define raw_smp_processor_id() (x86_read_percpu(cpu_number)) +#define raw_smp_processor_id() (percpu_read(cpu_number)) extern int safe_smp_processor_id(void); #elif defined(CONFIG_X86_64_SMP) -#define raw_smp_processor_id() read_pda(cpunumber) +#define raw_smp_processor_id() (percpu_read(cpu_number)) #define stack_smp_processor_id() \ ({ \ @@ -187,28 +182,9 @@ static inline int logical_smp_processor_id(void) return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR)); } -#include <mach_apicdef.h> -static inline unsigned int read_apic_id(void) -{ - unsigned int reg; - - reg = *(u32 *)(APIC_BASE + APIC_ID); - - return GET_APIC_ID(reg); -} #endif - -# if defined(APIC_DEFINITION) || defined(CONFIG_X86_64) extern int hard_smp_processor_id(void); -# else -#include <mach_apicdef.h> -static inline int hard_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return read_apic_id(); -} -# endif /* APIC_DEFINITION */ #else /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/include/asm/mach-default/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h index 23bf52103b8..1def6011490 100644 --- a/arch/x86/include/asm/mach-default/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -13,10 +13,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) CMOS_WRITE(0xa, 0xf); local_flush_tlb(); pr_debug("1.\n"); - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = + *((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_high)) = start_eip >> 4; pr_debug("2.\n"); - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = + *((volatile unsigned short *)phys_to_virt(apic->trampoline_phys_low)) = start_eip & 0xf; pr_debug("3.\n"); } @@ -34,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void) */ CMOS_WRITE(0, 0xf); - *((volatile long *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; + *((volatile long *)phys_to_virt(apic->trampoline_phys_low)) = 0; } static inline void __init smpboot_setup_io_apic(void) diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 2bd6b111a41..3a569665668 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -183,6 +183,7 @@ static inline int __raw_spin_is_contended(raw_spinlock_t *lock) { return __ticket_spin_is_contended(lock); } +#define __raw_spin_is_contended __raw_spin_is_contended static __always_inline void __raw_spin_lock(raw_spinlock_t *lock) { @@ -267,8 +268,7 @@ static inline int __raw_read_trylock(raw_rwlock_t *lock) { atomic_t *count = (atomic_t *)lock; - atomic_dec(count); - if (atomic_read(count) >= 0) + if (atomic_dec_return(count) >= 0) return 1; atomic_inc(count); return 0; diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h new file mode 100644 index 00000000000..c2d742c6e15 --- /dev/null +++ b/arch/x86/include/asm/stackprotector.h @@ -0,0 +1,124 @@ +/* + * GCC stack protector support. + * + * Stack protector works by putting predefined pattern at the start of + * the stack frame and verifying that it hasn't been overwritten when + * returning from the function. The pattern is called stack canary + * and unfortunately gcc requires it to be at a fixed offset from %gs. + * On x86_64, the offset is 40 bytes and on x86_32 20 bytes. x86_64 + * and x86_32 use segment registers differently and thus handles this + * requirement differently. + * + * On x86_64, %gs is shared by percpu area and stack canary. All + * percpu symbols are zero based and %gs points to the base of percpu + * area. The first occupant of the percpu area is always + * irq_stack_union which contains stack_canary at offset 40. Userland + * %gs is always saved and restored on kernel entry and exit using + * swapgs, so stack protector doesn't add any complexity there. + * + * On x86_32, it's slightly more complicated. As in x86_64, %gs is + * used for userland TLS. Unfortunately, some processors are much + * slower at loading segment registers with different value when + * entering and leaving the kernel, so the kernel uses %fs for percpu + * area and manages %gs lazily so that %gs is switched only when + * necessary, usually during task switch. + * + * As gcc requires the stack canary at %gs:20, %gs can't be managed + * lazily if stack protector is enabled, so the kernel saves and + * restores userland %gs on kernel entry and exit. This behavior is + * controlled by CONFIG_X86_32_LAZY_GS and accessors are defined in + * system.h to hide the details. + */ + +#ifndef _ASM_STACKPROTECTOR_H +#define _ASM_STACKPROTECTOR_H 1 + +#ifdef CONFIG_CC_STACKPROTECTOR + +#include <asm/tsc.h> +#include <asm/processor.h> +#include <asm/percpu.h> +#include <asm/system.h> +#include <asm/desc.h> +#include <linux/random.h> + +/* + * 24 byte read-only segment initializer for stack canary. Linker + * can't handle the address bit shifting. Address will be set in + * head_32 for boot CPU and setup_per_cpu_areas() for others. + */ +#define GDT_STACK_CANARY_INIT \ + [GDT_ENTRY_STACK_CANARY] = { { { 0x00000018, 0x00409000 } } }, + +/* + * Initialize the stackprotector canary value. + * + * NOTE: this must only be called from functions that never return, + * and it must always be inlined. + */ +static __always_inline void boot_init_stack_canary(void) +{ + u64 canary; + u64 tsc; + +#ifdef CONFIG_X86_64 + BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40); +#endif + /* + * We both use the random pool and the current TSC as a source + * of randomness. The TSC only matters for very early init, + * there it already has some randomness on most systems. Later + * on during the bootup the random pool has true entropy too. + */ + get_random_bytes(&canary, sizeof(canary)); + tsc = __native_read_tsc(); + canary += tsc + (tsc << 32UL); + + current->stack_canary = canary; +#ifdef CONFIG_X86_64 + percpu_write(irq_stack_union.stack_canary, canary); +#else + percpu_write(stack_canary, canary); +#endif +} + +static inline void setup_stack_canary_segment(int cpu) +{ +#ifdef CONFIG_X86_32 + unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu) - 20; + struct desc_struct *gdt_table = get_cpu_gdt_table(cpu); + struct desc_struct desc; + + desc = gdt_table[GDT_ENTRY_STACK_CANARY]; + desc.base0 = canary & 0xffff; + desc.base1 = (canary >> 16) & 0xff; + desc.base2 = (canary >> 24) & 0xff; + write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S); +#endif +} + +static inline void load_stack_canary_segment(void) +{ +#ifdef CONFIG_X86_32 + asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory"); +#endif +} + +#else /* CC_STACKPROTECTOR */ + +#define GDT_STACK_CANARY_INIT + +/* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */ + +static inline void setup_stack_canary_segment(int cpu) +{ } + +static inline void load_stack_canary_segment(void) +{ +#ifdef CONFIG_X86_32 + asm volatile ("mov %0, %%gs" : : "r" (0)); +#endif +} + +#endif /* CC_STACKPROTECTOR */ +#endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/x86/include/asm/summit/apic.h b/arch/x86/include/asm/summit/apic.h deleted file mode 100644 index 93d2c8667cf..00000000000 --- a/arch/x86/include/asm/summit/apic.h +++ /dev/null @@ -1,202 +0,0 @@ -#ifndef __ASM_SUMMIT_APIC_H -#define __ASM_SUMMIT_APIC_H - -#include <asm/smp.h> -#include <linux/gfp.h> - -#define esr_disable (1) -#define NO_BALANCE_IRQ (0) - -/* In clustered mode, the high nibble of APIC ID is a cluster number. - * The low nibble is a 4-bit bitmap. */ -#define XAPIC_DEST_CPUS_SHIFT 4 -#define XAPIC_DEST_CPUS_MASK ((1u << XAPIC_DEST_CPUS_SHIFT) - 1) -#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT) - -#define APIC_DFR_VALUE (APIC_DFR_CLUSTER) - -static inline const cpumask_t *target_cpus(void) -{ - /* CPU_MASK_ALL (0xff) has undefined behaviour with - * dest_LowestPrio mode logical clustered apic interrupt routing - * Just start on cpu 0. IRQ balancing will spread load - */ - return &cpumask_of_cpu(0); -} - -#define INT_DELIVERY_MODE (dest_LowestPrio) -#define INT_DEST_MODE 1 /* logical delivery broadcast to all procs */ - -static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid) -{ - return 0; -} - -/* we don't use the phys_cpu_present_map to indicate apicid presence */ -static inline unsigned long check_apicid_present(int bit) -{ - return 1; -} - -#define apicid_cluster(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK) - -extern u8 cpu_2_logical_apicid[]; - -static inline void init_apic_ldr(void) -{ - unsigned long val, id; - int count = 0; - u8 my_id = (u8)hard_smp_processor_id(); - u8 my_cluster = (u8)apicid_cluster(my_id); -#ifdef CONFIG_SMP - u8 lid; - int i; - - /* Create logical APIC IDs by counting CPUs already in cluster. */ - for (count = 0, i = nr_cpu_ids; --i >= 0; ) { - lid = cpu_2_logical_apicid[i]; - if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster) - ++count; - } -#endif - /* We only have a 4 wide bitmap in cluster mode. If a deranged - * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */ - BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT); - id = my_cluster | (1UL << count); - apic_write(APIC_DFR, APIC_DFR_VALUE); - val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - val |= SET_APIC_LOGICAL_ID(id); - apic_write(APIC_LDR, val); -} - -static inline int multi_timer_check(int apic, int irq) -{ - return 0; -} - -static inline int apic_id_registered(void) -{ - return 1; -} - -static inline void setup_apic_routing(void) -{ - printk("Enabling APIC mode: Summit. Using %d I/O APICs\n", - nr_ioapics); -} - -static inline int apicid_to_node(int logical_apicid) -{ -#ifdef CONFIG_SMP - return apicid_2_node[hard_smp_processor_id()]; -#else - return 0; -#endif -} - -/* Mapping from cpu number to logical apicid */ -static inline int cpu_to_logical_apicid(int cpu) -{ -#ifdef CONFIG_SMP - if (cpu >= nr_cpu_ids) - return BAD_APICID; - return (int)cpu_2_logical_apicid[cpu]; -#else - return logical_smp_processor_id(); -#endif -} - -static inline int cpu_present_to_apicid(int mps_cpu) -{ - if (mps_cpu < nr_cpu_ids) - return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu); - else - return BAD_APICID; -} - -static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_id_map) -{ - /* For clustered we don't have a good way to do this yet - hack */ - return physids_promote(0x0F); -} - -static inline physid_mask_t apicid_to_cpu_present(int apicid) -{ - return physid_mask_of_physid(0); -} - -static inline void setup_portio_remap(void) -{ -} - -static inline int check_phys_apicid_present(int boot_cpu_physical_apicid) -{ - return 1; -} - -static inline void enable_apic_mode(void) -{ -} - -static inline unsigned int cpu_mask_to_apicid(const cpumask_t *cpumask) -{ - int num_bits_set; - int cpus_found = 0; - int cpu; - int apicid; - - num_bits_set = cpus_weight(*cpumask); - /* Return id to all */ - if (num_bits_set >= nr_cpu_ids) - return (int) 0xFF; - /* - * The cpus in the mask must all be on the apic cluster. If are not - * on the same apicid cluster return default value of TARGET_CPUS. - */ - cpu = first_cpu(*cpumask); - apicid = cpu_to_logical_apicid(cpu); - while (cpus_found < num_bits_set) { - if (cpu_isset(cpu, *cpumask)) { - int new_apicid = cpu_to_logical_apicid(cpu); - if (apicid_cluster(apicid) != - apicid_cluster(new_apicid)){ - printk ("%s: Not a valid mask!\n", __func__); - return 0xFF; - } - apicid = apicid | new_apicid; - cpus_found++; - } - cpu++; - } - return apicid; -} - -static inline unsigned int cpu_mask_to_apicid_and(const struct cpumask *inmask, - const struct cpumask *andmask) -{ - int apicid = cpu_to_logical_apicid(0); - cpumask_var_t cpumask; - - if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) - return apicid; - - cpumask_and(cpumask, inmask, andmask); - cpumask_and(cpumask, cpumask, cpu_online_mask); - apicid = cpu_mask_to_apicid(cpumask); - - free_cpumask_var(cpumask); - return apicid; -} - -/* cpuid returns the value latched in the HW at reset, not the APIC ID - * register's value. For any box whose BIOS changes APIC IDs, like - * clustered APIC systems, we must use hard_smp_processor_id. - * - * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID. - */ -static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return hard_smp_processor_id() >> index_msb; -} - -#endif /* __ASM_SUMMIT_APIC_H */ diff --git a/arch/x86/include/asm/summit/apicdef.h b/arch/x86/include/asm/summit/apicdef.h deleted file mode 100644 index f3fbca1f61c..00000000000 --- a/arch/x86/include/asm/summit/apicdef.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef __ASM_SUMMIT_APICDEF_H -#define __ASM_SUMMIT_APICDEF_H - -#define APIC_ID_MASK (0xFF<<24) - -static inline unsigned get_apic_id(unsigned long x) -{ - return (x>>24)&0xFF; -} - -#define GET_APIC_ID(x) get_apic_id(x) - -#endif diff --git a/arch/x86/include/asm/summit/ipi.h b/arch/x86/include/asm/summit/ipi.h deleted file mode 100644 index a8a2c24f50c..00000000000 --- a/arch/x86/include/asm/summit/ipi.h +++ /dev/null @@ -1,26 +0,0 @@ -#ifndef __ASM_SUMMIT_IPI_H -#define __ASM_SUMMIT_IPI_H - -void send_IPI_mask_sequence(const cpumask_t *mask, int vector); -void send_IPI_mask_allbutself(const cpumask_t *mask, int vector); - -static inline void send_IPI_mask(const cpumask_t *mask, int vector) -{ - send_IPI_mask_sequence(mask, vector); -} - -static inline void send_IPI_allbutself(int vector) -{ - cpumask_t mask = cpu_online_map; - cpu_clear(smp_processor_id(), mask); - - if (!cpus_empty(mask)) - send_IPI_mask(&mask, vector); -} - -static inline void send_IPI_all(int vector) -{ - send_IPI_mask(&cpu_online_map, vector); -} - -#endif /* __ASM_SUMMIT_IPI_H */ diff --git a/arch/x86/include/asm/summit/mpparse.h b/arch/x86/include/asm/summit/mpparse.h deleted file mode 100644 index 380e86c0236..00000000000 --- a/arch/x86/include/asm/summit/mpparse.h +++ /dev/null @@ -1,109 +0,0 @@ -#ifndef __ASM_SUMMIT_MPPARSE_H -#define __ASM_SUMMIT_MPPARSE_H - -#include <asm/tsc.h> - -extern int use_cyclone; - -#ifdef CONFIG_X86_SUMMIT_NUMA -extern void setup_summit(void); -#else -#define setup_summit() {} -#endif - -static inline int mps_oem_check(struct mpc_table *mpc, char *oem, - char *productid) -{ - if (!strncmp(oem, "IBM ENSW", 8) && - (!strncmp(productid, "VIGIL SMP", 9) - || !strncmp(productid, "EXA", 3) - || !strncmp(productid, "RUTHLESS SMP", 12))){ - mark_tsc_unstable("Summit based system"); - use_cyclone = 1; /*enable cyclone-timer*/ - setup_summit(); - return 1; - } - return 0; -} - -/* Hook from generic ACPI tables.c */ -static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - if (!strncmp(oem_id, "IBM", 3) && - (!strncmp(oem_table_id, "SERVIGIL", 8) - || !strncmp(oem_table_id, "EXA", 3))){ - mark_tsc_unstable("Summit based system"); - use_cyclone = 1; /*enable cyclone-timer*/ - setup_summit(); - return 1; - } - return 0; -} - -struct rio_table_hdr { - unsigned char version; /* Version number of this data structure */ - /* Version 3 adds chassis_num & WP_index */ - unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil) */ - unsigned char num_rio_dev; /* # of RIO I/O devices (Cyclones and Winnipegs) */ -} __attribute__((packed)); - -struct scal_detail { - unsigned char node_id; /* Scalability Node ID */ - unsigned long CBAR; /* Address of 1MB register space */ - unsigned char port0node; /* Node ID port connected to: 0xFF=None */ - unsigned char port0port; /* Port num port connected to: 0,1,2, or 0xFF=None */ - unsigned char port1node; /* Node ID port connected to: 0xFF = None */ - unsigned char port1port; /* Port num port connected to: 0,1,2, or 0xFF=None */ - unsigned char port2node; /* Node ID port connected to: 0xFF = None */ - unsigned char port2port; /* Port num port connected to: 0,1,2, or 0xFF=None */ - unsigned char chassis_num; /* 1 based Chassis number (1 = boot node) */ -} __attribute__((packed)); - -struct rio_detail { - unsigned char node_id; /* RIO Node ID */ - unsigned long BBAR; /* Address of 1MB register space */ - unsigned char type; /* Type of device */ - unsigned char owner_id; /* For WPEG: Node ID of Cyclone that owns this WPEG*/ - /* For CYC: Node ID of Twister that owns this CYC */ - unsigned char port0node; /* Node ID port connected to: 0xFF=None */ - unsigned char port0port; /* Port num port connected to: 0,1,2, or 0xFF=None */ - unsigned char port1node; /* Node ID port connected to: 0xFF=None */ - unsigned char port1port; /* Port num port connected to: 0,1,2, or 0xFF=None */ - unsigned char first_slot; /* For WPEG: Lowest slot number below this WPEG */ - /* For CYC: 0 */ - unsigned char status; /* For WPEG: Bit 0 = 1 : the XAPIC is used */ - /* = 0 : the XAPIC is not used, ie:*/ - /* ints fwded to another XAPIC */ - /* Bits1:7 Reserved */ - /* For CYC: Bits0:7 Reserved */ - unsigned char WP_index; /* For WPEG: WPEG instance index - lower ones have */ - /* lower slot numbers/PCI bus numbers */ - /* For CYC: No meaning */ - unsigned char chassis_num; /* 1 based Chassis number */ - /* For LookOut WPEGs this field indicates the */ - /* Expansion Chassis #, enumerated from Boot */ - /* Node WPEG external port, then Boot Node CYC */ - /* external port, then Next Vigil chassis WPEG */ - /* external port, etc. */ - /* Shared Lookouts have only 1 chassis number (the */ - /* first one assigned) */ -} __attribute__((packed)); - - -typedef enum { - CompatTwister = 0, /* Compatibility Twister */ - AltTwister = 1, /* Alternate Twister of internal 8-way */ - CompatCyclone = 2, /* Compatibility Cyclone */ - AltCyclone = 3, /* Alternate Cyclone of internal 8-way */ - CompatWPEG = 4, /* Compatibility WPEG */ - AltWPEG = 5, /* Second Planar WPEG */ - LookOutAWPEG = 6, /* LookOut WPEG */ - LookOutBWPEG = 7, /* LookOut WPEG */ -} node_type; - -static inline int is_WPEG(struct rio_detail *rio){ - return (rio->type == CompatWPEG || rio->type == AltWPEG || - rio->type == LookOutAWPEG || rio->type == LookOutBWPEG); -} - -#endif /* __ASM_SUMMIT_MPPARSE_H */ diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index c0b0bda754e..68b1be10cfa 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -29,21 +29,21 @@ asmlinkage int sys_get_thread_area(struct user_desc __user *); /* X86_32 only */ #ifdef CONFIG_X86_32 /* kernel/process_32.c */ -asmlinkage int sys_fork(struct pt_regs); -asmlinkage int sys_clone(struct pt_regs); -asmlinkage int sys_vfork(struct pt_regs); -asmlinkage int sys_execve(struct pt_regs); +int sys_fork(struct pt_regs *); +int sys_clone(struct pt_regs *); +int sys_vfork(struct pt_regs *); +int sys_execve(struct pt_regs *); /* kernel/signal_32.c */ asmlinkage int sys_sigsuspend(int, int, old_sigset_t); asmlinkage int sys_sigaction(int, const struct old_sigaction __user *, struct old_sigaction __user *); -asmlinkage int sys_sigaltstack(unsigned long); -asmlinkage unsigned long sys_sigreturn(unsigned long); -asmlinkage int sys_rt_sigreturn(unsigned long); +int sys_sigaltstack(struct pt_regs *); +unsigned long sys_sigreturn(struct pt_regs *); +long sys_rt_sigreturn(struct pt_regs *); /* kernel/ioport.c */ -asmlinkage long sys_iopl(unsigned long); +long sys_iopl(struct pt_regs *); /* kernel/sys_i386_32.c */ asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long, @@ -59,8 +59,8 @@ struct oldold_utsname; asmlinkage int sys_olduname(struct oldold_utsname __user *); /* kernel/vm86_32.c */ -asmlinkage int sys_vm86old(struct pt_regs); -asmlinkage int sys_vm86(struct pt_regs); +int sys_vm86old(struct pt_regs *); +int sys_vm86(struct pt_regs *); #else /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index 8e626ea33a1..c00bfdbdd45 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -23,6 +23,20 @@ struct task_struct *__switch_to(struct task_struct *prev, #ifdef CONFIG_X86_32 +#ifdef CONFIG_CC_STACKPROTECTOR +#define __switch_canary \ + "movl %P[task_canary](%[next]), %%ebx\n\t" \ + "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" +#define __switch_canary_oparam \ + , [stack_canary] "=m" (per_cpu_var(stack_canary)) +#define __switch_canary_iparam \ + , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) +#else /* CC_STACKPROTECTOR */ +#define __switch_canary +#define __switch_canary_oparam +#define __switch_canary_iparam +#endif /* CC_STACKPROTECTOR */ + /* * Saving eflags is important. It switches not only IOPL between tasks, * it also protects other tasks from NT leaking through sysenter etc. @@ -44,6 +58,7 @@ do { \ "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ "pushl %[next_ip]\n\t" /* restore EIP */ \ + __switch_canary \ "jmp __switch_to\n" /* regparm call */ \ "1:\t" \ "popl %%ebp\n\t" /* restore EBP */ \ @@ -58,6 +73,8 @@ do { \ "=b" (ebx), "=c" (ecx), "=d" (edx), \ "=S" (esi), "=D" (edi) \ \ + __switch_canary_oparam \ + \ /* input parameters: */ \ : [next_sp] "m" (next->thread.sp), \ [next_ip] "m" (next->thread.ip), \ @@ -66,6 +83,8 @@ do { \ [prev] "a" (prev), \ [next] "d" (next) \ \ + __switch_canary_iparam \ + \ : /* reloaded segment registers */ \ "memory"); \ } while (0) @@ -86,27 +105,44 @@ do { \ , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ "r12", "r13", "r14", "r15" +#ifdef CONFIG_CC_STACKPROTECTOR +#define __switch_canary \ + "movq %P[task_canary](%%rsi),%%r8\n\t" \ + "movq %%r8,"__percpu_arg([gs_canary])"\n\t" +#define __switch_canary_oparam \ + , [gs_canary] "=m" (per_cpu_var(irq_stack_union.stack_canary)) +#define __switch_canary_iparam \ + , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) +#else /* CC_STACKPROTECTOR */ +#define __switch_canary +#define __switch_canary_oparam +#define __switch_canary_iparam +#endif /* CC_STACKPROTECTOR */ + /* Save restore flags to clear handle leaking NT */ #define switch_to(prev, next, last) \ - asm volatile(SAVE_CONTEXT \ + asm volatile(SAVE_CONTEXT \ "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ "call __switch_to\n\t" \ ".globl thread_return\n" \ "thread_return:\n\t" \ - "movq %%gs:%P[pda_pcurrent],%%rsi\n\t" \ + "movq "__percpu_arg([current_task])",%%rsi\n\t" \ + __switch_canary \ "movq %P[thread_info](%%rsi),%%r8\n\t" \ - LOCK_PREFIX "btr %[tif_fork],%P[ti_flags](%%r8)\n\t" \ "movq %%rax,%%rdi\n\t" \ - "jc ret_from_fork\n\t" \ + "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ + "jnz ret_from_fork\n\t" \ RESTORE_CONTEXT \ : "=a" (last) \ + __switch_canary_oparam \ : [next] "S" (next), [prev] "D" (prev), \ [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ [ti_flags] "i" (offsetof(struct thread_info, flags)), \ - [tif_fork] "i" (TIF_FORK), \ + [_tif_fork] "i" (_TIF_FORK), \ [thread_info] "i" (offsetof(struct task_struct, stack)), \ - [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent)) \ + [current_task] "m" (per_cpu_var(current_task)) \ + __switch_canary_iparam \ : "memory", "cc" __EXTRA_CLOBBER) #endif @@ -165,6 +201,25 @@ extern void native_load_gs_index(unsigned); #define savesegment(seg, value) \ asm("mov %%" #seg ",%0":"=r" (value) : : "memory") +/* + * x86_32 user gs accessors. + */ +#ifdef CONFIG_X86_32 +#ifdef CONFIG_X86_32_LAZY_GS +#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;}) +#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) +#define task_user_gs(tsk) ((tsk)->thread.gs) +#define lazy_save_gs(v) savesegment(gs, (v)) +#define lazy_load_gs(v) loadsegment(gs, (v)) +#else /* X86_32_LAZY_GS */ +#define get_user_gs(regs) (u16)((regs)->gs) +#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) +#define task_user_gs(tsk) (task_pt_regs(tsk)->gs) +#define lazy_save_gs(v) do { } while (0) +#define lazy_load_gs(v) do { } while (0) +#endif /* X86_32_LAZY_GS */ +#endif /* X86_32 */ + static inline unsigned long get_limit(unsigned long segment) { unsigned long __limit; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 98789647baa..df9d5f78385 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -40,6 +40,7 @@ struct thread_info { */ __u8 supervisor_stack[0]; #endif + int uaccess_err; }; #define INIT_THREAD_INFO(tsk) \ @@ -194,25 +195,21 @@ static inline struct thread_info *current_thread_info(void) #else /* X86_32 */ -#include <asm/pda.h> +#include <asm/percpu.h> +#define KERNEL_STACK_OFFSET (5*8) /* * macros/functions for gaining access to the thread information structure * preempt_count needs to be 1 initially, until the scheduler is functional. */ #ifndef __ASSEMBLY__ -static inline struct thread_info *current_thread_info(void) -{ - struct thread_info *ti; - ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE); - return ti; -} +DECLARE_PER_CPU(unsigned long, kernel_stack); -/* do not use in interrupt context */ -static inline struct thread_info *stack_thread_info(void) +static inline struct thread_info *current_thread_info(void) { struct thread_info *ti; - asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1))); + ti = (void *)(percpu_read(kernel_stack) + + KERNEL_STACK_OFFSET - THREAD_SIZE); return ti; } @@ -220,8 +217,8 @@ static inline struct thread_info *stack_thread_info(void) /* how to get the thread information struct from ASM */ #define GET_THREAD_INFO(reg) \ - movq %gs:pda_kernelstack,reg ; \ - subq $(THREAD_SIZE-PDA_STACKOFFSET),reg + movq PER_CPU_VAR(kernel_stack),reg ; \ + subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg #endif diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index aed0b700b83..d3539f998f8 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -113,7 +113,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, __flush_tlb(); } -static inline void native_flush_tlb_others(const cpumask_t *cpumask, +static inline void native_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va) { @@ -142,31 +142,28 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, flush_tlb_mm(vma->vm_mm); } -void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm, - unsigned long va); +void native_flush_tlb_others(const struct cpumask *cpumask, + struct mm_struct *mm, unsigned long va); #define TLBSTATE_OK 1 #define TLBSTATE_LAZY 2 -#ifdef CONFIG_X86_32 struct tlb_state { struct mm_struct *active_mm; int state; - char __cacheline_padding[L1_CACHE_BYTES-8]; }; DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate); -void reset_lazy_tlbstate(void); -#else static inline void reset_lazy_tlbstate(void) { + percpu_write(cpu_tlbstate.state, 0); + percpu_write(cpu_tlbstate.active_mm, &init_mm); } -#endif #endif /* SMP */ #ifndef CONFIG_PARAVIRT -#define flush_tlb_others(mask, mm, va) native_flush_tlb_others(&mask, mm, va) +#define flush_tlb_others(mask, mm, va) native_flush_tlb_others(mask, mm, va) #endif static inline void flush_tlb_kernel_range(unsigned long start, diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 4e2f2e0aab2..77cfb2cfb38 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -74,6 +74,8 @@ static inline const struct cpumask *cpumask_of_node(int node) return &node_to_cpumask_map[node]; } +static inline void setup_node_to_cpumask_map(void) { } + #else /* CONFIG_X86_64 */ /* Mappings between node number and cpus on that node. */ @@ -83,7 +85,8 @@ extern cpumask_t *node_to_cpumask_map; DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); /* Returns the number of the current Node. */ -#define numa_node_id() read_pda(nodenumber) +DECLARE_PER_CPU(int, node_number); +#define numa_node_id() percpu_read(node_number) #ifdef CONFIG_DEBUG_PER_CPU_MAPS extern int cpu_to_node(int cpu); @@ -102,10 +105,7 @@ static inline int cpu_to_node(int cpu) /* Same function but used if called before per_cpu areas are setup */ static inline int early_cpu_to_node(int cpu) { - if (early_per_cpu_ptr(x86_cpu_to_node_map)) - return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; - - return per_cpu(x86_cpu_to_node_map, cpu); + return early_per_cpu(x86_cpu_to_node_map, cpu); } /* Returns a pointer to the cpumask of CPUs on Node 'node'. */ @@ -122,6 +122,8 @@ static inline cpumask_t node_to_cpumask(int node) #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ +extern void setup_node_to_cpumask_map(void); + /* * Replace default node_to_cpumask_ptr with optimized version * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)" @@ -192,9 +194,20 @@ extern int __node_distance(int, int); #else /* !CONFIG_NUMA */ -#define numa_node_id() 0 -#define cpu_to_node(cpu) 0 -#define early_cpu_to_node(cpu) 0 +static inline int numa_node_id(void) +{ + return 0; +} + +static inline int cpu_to_node(int cpu) +{ + return 0; +} + +static inline int early_cpu_to_node(int cpu) +{ + return 0; +} static inline const cpumask_t *cpumask_of_node(int node) { @@ -209,6 +222,8 @@ static inline int node_to_first_cpu(int node) return first_cpu(cpu_online_map); } +static inline void setup_node_to_cpumask_map(void) { } + /* * Replace default node_to_cpumask_ptr with optimized version * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)" diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h index 780ba0ab94f..90f06c25221 100644 --- a/arch/x86/include/asm/trampoline.h +++ b/arch/x86/include/asm/trampoline.h @@ -13,6 +13,7 @@ extern unsigned char *trampoline_base; extern unsigned long init_rsp; extern unsigned long initial_code; +extern unsigned long initial_gs; #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE) #define TRAMPOLINE_BASE 0x6000 diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 2ee0a3bceed..0d5342515b8 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -77,7 +77,7 @@ extern int panic_on_unrecovered_nmi; extern int kstack_depth_to_print; void math_error(void __user *); -asmlinkage void math_emulate(long); +void math_emulate(struct math_emu_info *); #ifdef CONFIG_X86_32 unsigned long patch_espfix_desc(unsigned long, unsigned long); #else diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 69d2757cca9..b685ece89d5 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -186,7 +186,7 @@ extern int __get_user_bad(void); #ifdef CONFIG_X86_32 -#define __put_user_asm_u64(x, addr, err) \ +#define __put_user_asm_u64(x, addr, err, errret) \ asm volatile("1: movl %%eax,0(%2)\n" \ "2: movl %%edx,4(%2)\n" \ "3:\n" \ @@ -197,14 +197,24 @@ extern int __get_user_bad(void); _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ : "=r" (err) \ - : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err)) + : "A" (x), "r" (addr), "i" (errret), "0" (err)) + +#define __put_user_asm_ex_u64(x, addr) \ + asm volatile("1: movl %%eax,0(%1)\n" \ + "2: movl %%edx,4(%1)\n" \ + "3:\n" \ + _ASM_EXTABLE(1b, 2b - 1b) \ + _ASM_EXTABLE(2b, 3b - 2b) \ + : : "A" (x), "r" (addr)) #define __put_user_x8(x, ptr, __ret_pu) \ asm volatile("call __put_user_8" : "=a" (__ret_pu) \ : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") #else -#define __put_user_asm_u64(x, ptr, retval) \ - __put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT) +#define __put_user_asm_u64(x, ptr, retval, errret) \ + __put_user_asm(x, ptr, retval, "q", "", "Zr", errret) +#define __put_user_asm_ex_u64(x, addr) \ + __put_user_asm_ex(x, addr, "q", "", "Zr") #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu) #endif @@ -279,7 +289,29 @@ do { \ __put_user_asm(x, ptr, retval, "l", "k", "ir", errret); \ break; \ case 8: \ - __put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval); \ + __put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval, \ + errret); \ + break; \ + default: \ + __put_user_bad(); \ + } \ +} while (0) + +#define __put_user_size_ex(x, ptr, size) \ +do { \ + __chk_user_ptr(ptr); \ + switch (size) { \ + case 1: \ + __put_user_asm_ex(x, ptr, "b", "b", "iq"); \ + break; \ + case 2: \ + __put_user_asm_ex(x, ptr, "w", "w", "ir"); \ + break; \ + case 4: \ + __put_user_asm_ex(x, ptr, "l", "k", "ir"); \ + break; \ + case 8: \ + __put_user_asm_ex_u64((__typeof__(*ptr))(x), ptr); \ break; \ default: \ __put_user_bad(); \ @@ -311,9 +343,12 @@ do { \ #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, retval, errret) (x) = __get_user_bad() +#define __get_user_asm_ex_u64(x, ptr) (x) = __get_user_bad() #else #define __get_user_asm_u64(x, ptr, retval, errret) \ __get_user_asm(x, ptr, retval, "q", "", "=r", errret) +#define __get_user_asm_ex_u64(x, ptr) \ + __get_user_asm_ex(x, ptr, "q", "", "=r") #endif #define __get_user_size(x, ptr, size, retval, errret) \ @@ -350,6 +385,33 @@ do { \ : "=r" (err), ltype(x) \ : "m" (__m(addr)), "i" (errret), "0" (err)) +#define __get_user_size_ex(x, ptr, size) \ +do { \ + __chk_user_ptr(ptr); \ + switch (size) { \ + case 1: \ + __get_user_asm_ex(x, ptr, "b", "b", "=q"); \ + break; \ + case 2: \ + __get_user_asm_ex(x, ptr, "w", "w", "=r"); \ + break; \ + case 4: \ + __get_user_asm_ex(x, ptr, "l", "k", "=r"); \ + break; \ + case 8: \ + __get_user_asm_ex_u64(x, ptr); \ + break; \ + default: \ + (x) = __get_user_bad(); \ + } \ +} while (0) + +#define __get_user_asm_ex(x, addr, itype, rtype, ltype) \ + asm volatile("1: mov"itype" %1,%"rtype"0\n" \ + "2:\n" \ + _ASM_EXTABLE(1b, 2b - 1b) \ + : ltype(x) : "m" (__m(addr))) + #define __put_user_nocheck(x, ptr, size) \ ({ \ int __pu_err; \ @@ -385,6 +447,26 @@ struct __large_struct { unsigned long buf[100]; }; _ASM_EXTABLE(1b, 3b) \ : "=r"(err) \ : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err)) + +#define __put_user_asm_ex(x, addr, itype, rtype, ltype) \ + asm volatile("1: mov"itype" %"rtype"0,%1\n" \ + "2:\n" \ + _ASM_EXTABLE(1b, 2b - 1b) \ + : : ltype(x), "m" (__m(addr))) + +/* + * uaccess_try and catch + */ +#define uaccess_try do { \ + int prev_err = current_thread_info()->uaccess_err; \ + current_thread_info()->uaccess_err = 0; \ + barrier(); + +#define uaccess_catch(err) \ + (err) |= current_thread_info()->uaccess_err; \ + current_thread_info()->uaccess_err = prev_err; \ +} while (0) + /** * __get_user: - Get a simple variable from user space, with less checking. * @x: Variable to store result. @@ -408,6 +490,7 @@ struct __large_struct { unsigned long buf[100]; }; #define __get_user(x, ptr) \ __get_user_nocheck((x), (ptr), sizeof(*(ptr))) + /** * __put_user: - Write a simple value into user space, with less checking. * @x: Value to copy to user space. @@ -435,6 +518,45 @@ struct __large_struct { unsigned long buf[100]; }; #define __put_user_unaligned __put_user /* + * {get|put}_user_try and catch + * + * get_user_try { + * get_user_ex(...); + * } get_user_catch(err) + */ +#define get_user_try uaccess_try +#define get_user_catch(err) uaccess_catch(err) + +#define get_user_ex(x, ptr) do { \ + unsigned long __gue_val; \ + __get_user_size_ex((__gue_val), (ptr), (sizeof(*(ptr)))); \ + (x) = (__force __typeof__(*(ptr)))__gue_val; \ +} while (0) + +#ifdef CONFIG_X86_WP_WORKS_OK + +#define put_user_try uaccess_try +#define put_user_catch(err) uaccess_catch(err) + +#define put_user_ex(x, ptr) \ + __put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) + +#else /* !CONFIG_X86_WP_WORKS_OK */ + +#define put_user_try do { \ + int __uaccess_err = 0; + +#define put_user_catch(err) \ + (err) |= __uaccess_err; \ +} while (0) + +#define put_user_ex(x, ptr) do { \ + __uaccess_err |= __put_user(x, ptr); \ +} while (0) + +#endif /* CONFIG_X86_WP_WORKS_OK */ + +/* * movsl can be slow when source and dest are not both 8-byte aligned */ #ifdef CONFIG_X86_INTEL_USERCOPY diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h new file mode 100644 index 00000000000..8242bf96581 --- /dev/null +++ b/arch/x86/include/asm/uv/uv.h @@ -0,0 +1,36 @@ +#ifndef _ASM_X86_UV_UV_H +#define _ASM_X86_UV_UV_H + +enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; + +struct cpumask; +struct mm_struct; + +#ifdef CONFIG_X86_UV + +extern enum uv_system_type get_uv_system_type(void); +extern int is_uv_system(void); +extern void uv_cpu_init(void); +extern void uv_system_init(void); +extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip); +extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, + struct mm_struct *mm, + unsigned long va, + unsigned int cpu); + +#else /* X86_UV */ + +static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } +static inline int is_uv_system(void) { return 0; } +static inline void uv_cpu_init(void) { } +static inline void uv_system_init(void) { } +static inline int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip) +{ return 1; } +static inline const struct cpumask * +uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, + unsigned long va, unsigned int cpu) +{ return cpumask; } + +#endif /* X86_UV */ + +#endif /* _ASM_X86_UV_UV_H */ diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 50423c7b56b..9b0e61bf7a8 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -325,7 +325,6 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits) #define cpubit_isset(cpu, bau_local_cpumask) \ test_bit((cpu), (bau_local_cpumask).bits) -extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long); extern void uv_bau_message_intr1(void); extern void uv_bau_timeout_intr1(void); diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h index b3e64730762..c1635d43616 100644 --- a/arch/x86/include/asm/voyager.h +++ b/arch/x86/include/asm/voyager.h @@ -527,3 +527,45 @@ extern void voyager_smp_intr_init(void); #define VOYAGER_PSI_SUBREAD 2 #define VOYAGER_PSI_SUBWRITE 3 extern void voyager_cat_psi(__u8, __u16, __u8 *); + +/* These define the CPIs we use in linux */ +#define VIC_CPI_LEVEL0 0 +#define VIC_CPI_LEVEL1 1 +/* now the fake CPIs */ +#define VIC_TIMER_CPI 2 +#define VIC_INVALIDATE_CPI 3 +#define VIC_RESCHEDULE_CPI 4 +#define VIC_ENABLE_IRQ_CPI 5 +#define VIC_CALL_FUNCTION_CPI 6 +#define VIC_CALL_FUNCTION_SINGLE_CPI 7 + +/* Now the QIC CPIs: Since we don't need the two initial levels, + * these are 2 less than the VIC CPIs */ +#define QIC_CPI_OFFSET 1 +#define QIC_TIMER_CPI (VIC_TIMER_CPI - QIC_CPI_OFFSET) +#define QIC_INVALIDATE_CPI (VIC_INVALIDATE_CPI - QIC_CPI_OFFSET) +#define QIC_RESCHEDULE_CPI (VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET) +#define QIC_ENABLE_IRQ_CPI (VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET) +#define QIC_CALL_FUNCTION_CPI (VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET) +#define QIC_CALL_FUNCTION_SINGLE_CPI (VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET) + +#define VIC_START_FAKE_CPI VIC_TIMER_CPI +#define VIC_END_FAKE_CPI VIC_CALL_FUNCTION_SINGLE_CPI + +/* this is the SYS_INT CPI. */ +#define VIC_SYS_INT 8 +#define VIC_CMN_INT 15 + +/* This is the boot CPI for alternate processors. It gets overwritten + * by the above once the system has activated all available processors */ +#define VIC_CPU_BOOT_CPI VIC_CPI_LEVEL0 +#define VIC_CPU_BOOT_ERRATA_CPI (VIC_CPI_LEVEL0 + 8) + +extern asmlinkage void vic_cpi_interrupt(void); +extern asmlinkage void vic_sys_interrupt(void); +extern asmlinkage void vic_cmn_interrupt(void); +extern asmlinkage void qic_timer_interrupt(void); +extern asmlinkage void qic_invalidate_interrupt(void); +extern asmlinkage void qic_reschedule_interrupt(void); +extern asmlinkage void qic_enable_irq_interrupt(void); +extern asmlinkage void qic_call_function_interrupt(void); diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index 19144184983..1df35417c41 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -15,10 +15,4 @@ static inline int xen_irqs_disabled(struct pt_regs *regs) return raw_irqs_disabled_flags(regs->flags); } -static inline void xen_do_IRQ(int irq, struct pt_regs *regs) -{ - regs->orig_ax = ~irq; - do_IRQ(regs); -} - #endif /* _ASM_X86_XEN_EVENTS_H */ diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 7ef617ef1df..4bd990ee43d 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -137,7 +137,7 @@ static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot) pte_t pte; pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) | - (pgprot_val(pgprot) & __supported_pte_mask); + massage_pgprot(pgprot); return pte; } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index d364df03c1d..24f357e7557 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -23,13 +23,14 @@ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp) CFLAGS_hpet.o := $(nostackp) CFLAGS_tsc.o := $(nostackp) +CFLAGS_paravirt.o := $(nostackp) obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time_$(BITS).o ioport.o ldt.o dumpstack.o -obj-y += setup.o i8259.o irqinit_$(BITS).o setup_percpu.o +obj-y += setup.o i8259.o irqinit_$(BITS).o obj-$(CONFIG_X86_VISWS) += visws_quirks.o -obj-$(CONFIG_X86_32) += probe_roms_32.o +obj-$(CONFIG_X86_32) += probe_32.o probe_roms_32.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o @@ -49,20 +50,20 @@ obj-y += step.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += cpu/ obj-y += acpi/ -obj-$(CONFIG_X86_BIOS_REBOOT) += reboot.o +obj-y += reboot.o obj-$(CONFIG_MCA) += mca_32.o obj-$(CONFIG_X86_MSR) += msr.o obj-$(CONFIG_X86_CPUID) += cpuid.o obj-$(CONFIG_PCI) += early-quirks.o apm-y := apm_32.o obj-$(CONFIG_APM) += apm.o -obj-$(CONFIG_X86_SMP) += smp.o -obj-$(CONFIG_X86_SMP) += smpboot.o tsc_sync.o ipi.o tlb_$(BITS).o -obj-$(CONFIG_X86_32_SMP) += smpcommon.o -obj-$(CONFIG_X86_64_SMP) += tsc_sync.o smpcommon.o +obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_SMP) += smpboot.o tsc_sync.o ipi.o +obj-$(CONFIG_SMP) += setup_percpu.o +obj-$(CONFIG_X86_64_SMP) += tsc_sync.o obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o obj-$(CONFIG_X86_MPPARSE) += mpparse.o -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o ipi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o @@ -70,9 +71,10 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o +obj-$(CONFIG_X86_BIGSMP) += bigsmp_32.o obj-$(CONFIG_X86_NUMAQ) += numaq_32.o obj-$(CONFIG_X86_ES7000) += es7000_32.o -obj-$(CONFIG_X86_SUMMIT_NUMA) += summit_32.o +obj-$(CONFIG_X86_SUMMIT) += summit_32.o obj-y += vsmp_64.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_MODULES) += module_$(BITS).o @@ -114,10 +116,11 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o # NB rename without _64 ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) - obj-y += genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o - obj-y += bios_uv.o uv_irq.o uv_sysfs.o + obj-y += genapic_64.o genapic_flat_64.o obj-y += genx2apic_cluster.o obj-y += genx2apic_phys.o + obj-$(CONFIG_X86_UV) += genx2apic_uv_x.o tlb_uv.o + obj-$(CONFIG_X86_UV) += bios_uv.o uv_irq.o uv_sysfs.o obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o obj-$(CONFIG_AUDIT) += audit_64.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4cb5964f149..bba162c81d5 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -42,10 +42,6 @@ #include <asm/mpspec.h> #include <asm/smp.h> -#ifdef CONFIG_X86_LOCAL_APIC -# include <mach_apic.h> -#endif - static int __initdata acpi_force = 0; u32 acpi_rsdt_forced; #ifdef CONFIG_ACPI @@ -56,16 +52,7 @@ int acpi_disabled = 1; EXPORT_SYMBOL(acpi_disabled); #ifdef CONFIG_X86_64 - -#include <asm/proto.h> - -#else /* X86 */ - -#ifdef CONFIG_X86_LOCAL_APIC -#include <mach_apic.h> -#include <mach_mpparse.h> -#endif /* CONFIG_X86_LOCAL_APIC */ - +# include <asm/proto.h> #endif /* X86 */ #define BAD_MADT_ENTRY(entry, end) ( \ @@ -239,7 +226,8 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) madt->address); } - acpi_madt_oem_check(madt->header.oem_id, madt->header.oem_table_id); + default_acpi_madt_oem_check(madt->header.oem_id, + madt->header.oem_table_id); return 0; } @@ -884,7 +872,7 @@ static struct { DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1); } mp_ioapic_routing[MAX_IO_APICS]; -static int mp_find_ioapic(int gsi) +int mp_find_ioapic(int gsi) { int i = 0; @@ -899,6 +887,16 @@ static int mp_find_ioapic(int gsi) return -1; } +int mp_find_ioapic_pin(int ioapic, int gsi) +{ + if (WARN_ON(ioapic == -1)) + return -1; + if (WARN_ON(gsi > mp_ioapic_routing[ioapic].gsi_end)) + return -1; + + return gsi - mp_ioapic_routing[ioapic].gsi_base; +} + static u8 __init uniq_ioapic_id(u8 id) { #ifdef CONFIG_X86_32 @@ -973,6 +971,29 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) nr_ioapics++; } +int __init acpi_probe_gsi(void) +{ + int idx; + int gsi; + int max_gsi = 0; + + if (acpi_disabled) + return 0; + + if (!acpi_ioapic) + return 0; + + max_gsi = 0; + for (idx = 0; idx < nr_ioapics; idx++) { + gsi = mp_ioapic_routing[idx].gsi_end; + + if (gsi > max_gsi) + max_gsi = gsi; + } + + return max_gsi + 1; +} + static void assign_to_mp_irq(struct mpc_intsrc *m, struct mpc_intsrc *mp_irq) { @@ -1011,7 +1032,7 @@ void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) ioapic = mp_find_ioapic(gsi); if (ioapic < 0) return; - pin = gsi - mp_ioapic_routing[ioapic].gsi_base; + pin = mp_find_ioapic_pin(ioapic, gsi); /* * TBD: This check is for faulty timer entries, where the override @@ -1131,7 +1152,7 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity) return gsi; } - ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base; + ioapic_pin = mp_find_ioapic_pin(ioapic, gsi); #ifdef CONFIG_X86_32 if (ioapic_renumber_irq) @@ -1220,7 +1241,7 @@ int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin, mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3); ioapic = mp_find_ioapic(gsi); mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id; - mp_irq.dstirq = gsi - mp_ioapic_routing[ioapic].gsi_base; + mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi); save_mp_irq(&mp_irq); #endif @@ -1347,7 +1368,7 @@ static void __init acpi_process_madt(void) if (!error) { acpi_lapic = 1; -#ifdef CONFIG_X86_GENERICARCH +#ifdef CONFIG_X86_BIGSMP generic_bigsmp_probe(); #endif /* @@ -1359,9 +1380,8 @@ static void __init acpi_process_madt(void) acpi_ioapic = 1; smp_found_config = 1; -#ifdef CONFIG_X86_32 - setup_apic_routing(); -#endif + if (apic->setup_apic_routing) + apic->setup_apic_routing(); } } if (error == -EINVAL) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index a60c1f3bcb8..7c243a2c511 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -101,6 +101,7 @@ int acpi_save_state_mem(void) stack_start.sp = temp_stack + sizeof(temp_stack); early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(smp_processor_id()); + initial_gs = per_cpu_offset(smp_processor_id()); #endif initial_code = (unsigned long)wakeup_long64; saved_magic = 0x123456789abcdef0; diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c index 115449f869e..8bd801db24d 100644 --- a/arch/x86/kernel/apic.c +++ b/arch/x86/kernel/apic.c @@ -1,7 +1,7 @@ /* * Local APIC handling, local APIC timers * - * (c) 1999, 2000 Ingo Molnar <mingo@redhat.com> + * (c) 1999, 2000, 2009 Ingo Molnar <mingo@redhat.com> * * Fixes * Maciej W. Rozycki : Bits for genuine 82489DX APICs; @@ -14,51 +14,71 @@ * Mikael Pettersson : PM converted to driver model. */ -#include <linux/init.h> - -#include <linux/mm.h> -#include <linux/delay.h> -#include <linux/bootmem.h> -#include <linux/interrupt.h> -#include <linux/mc146818rtc.h> #include <linux/kernel_stat.h> -#include <linux/sysdev.h> -#include <linux/ioport.h> -#include <linux/cpu.h> -#include <linux/clockchips.h> +#include <linux/mc146818rtc.h> #include <linux/acpi_pmtmr.h> +#include <linux/clockchips.h> +#include <linux/interrupt.h> +#include <linux/bootmem.h> +#include <linux/ftrace.h> +#include <linux/ioport.h> #include <linux/module.h> -#include <linux/dmi.h> +#include <linux/sysdev.h> +#include <linux/delay.h> +#include <linux/timex.h> #include <linux/dmar.h> -#include <linux/ftrace.h> -#include <linux/smp.h> +#include <linux/init.h> +#include <linux/cpu.h> +#include <linux/dmi.h> #include <linux/nmi.h> -#include <linux/timex.h> +#include <linux/smp.h> +#include <linux/mm.h> -#include <asm/atomic.h> -#include <asm/mtrr.h> -#include <asm/mpspec.h> -#include <asm/desc.h> #include <asm/arch_hooks.h> -#include <asm/hpet.h> #include <asm/pgalloc.h> +#include <asm/genapic.h> +#include <asm/atomic.h> +#include <asm/mpspec.h> #include <asm/i8253.h> -#include <asm/idle.h> +#include <asm/i8259.h> #include <asm/proto.h> #include <asm/apic.h> -#include <asm/i8259.h> +#include <asm/desc.h> +#include <asm/hpet.h> +#include <asm/idle.h> +#include <asm/mtrr.h> #include <asm/smp.h> -#include <mach_apic.h> -#include <mach_apicdef.h> -#include <mach_ipi.h> +unsigned int num_processors; + +unsigned disabled_cpus __cpuinitdata; + +/* Processor that is doing the boot up */ +unsigned int boot_cpu_physical_apicid = -1U; /* - * Sanity check + * The highest APIC ID seen during enumeration. + * + * This determines the messaging protocol we can use: if all APIC IDs + * are in the 0 ... 7 range, then we can use logical addressing which + * has some performance advantages (better broadcasting). + * + * If there's an APIC ID above 8, we use physical addressing. */ -#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F) -# error SPURIOUS_APIC_VECTOR definition error -#endif +unsigned int max_physical_apicid; + +/* + * Bitmask of physically existing CPUs: + */ +physid_mask_t phys_cpu_present_map; + +/* + * Map cpu index to physical APIC ID + */ +DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID); +DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid); #ifdef CONFIG_X86_32 /* @@ -457,7 +477,7 @@ static void lapic_timer_setup(enum clock_event_mode mode, static void lapic_timer_broadcast(const struct cpumask *mask) { #ifdef CONFIG_SMP - send_IPI_mask(mask, LOCAL_TIMER_VECTOR); + apic->send_IPI_mask(mask, LOCAL_TIMER_VECTOR); #endif } @@ -991,11 +1011,11 @@ int __init verify_local_APIC(void) */ reg0 = apic_read(APIC_ID); apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0); - apic_write(APIC_ID, reg0 ^ APIC_ID_MASK); + apic_write(APIC_ID, reg0 ^ apic->apic_id_mask); reg1 = apic_read(APIC_ID); apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1); apic_write(APIC_ID, reg0); - if (reg1 != (reg0 ^ APIC_ID_MASK)) + if (reg1 != (reg0 ^ apic->apic_id_mask)) return 0; /* @@ -1089,7 +1109,7 @@ static void __cpuinit lapic_setup_esr(void) return; } - if (esr_disable) { + if (apic->disable_esr) { /* * Something untraceable is creating bad interrupts on * secondary quads ... for the moment, just leave the @@ -1130,9 +1150,14 @@ void __cpuinit setup_local_APIC(void) unsigned int value; int i, j; + if (disable_apic) { + arch_disable_smp_support(); + return; + } + #ifdef CONFIG_X86_32 /* Pound the ESR really hard over the head with a big hammer - mbligh */ - if (lapic_is_integrated() && esr_disable) { + if (lapic_is_integrated() && apic->disable_esr) { apic_write(APIC_ESR, 0); apic_write(APIC_ESR, 0); apic_write(APIC_ESR, 0); @@ -1146,7 +1171,7 @@ void __cpuinit setup_local_APIC(void) * Double-check whether this APIC is really registered. * This is meaningless in clustered apic mode, so we skip it. */ - if (!apic_id_registered()) + if (!apic->apic_id_registered()) BUG(); /* @@ -1154,7 +1179,7 @@ void __cpuinit setup_local_APIC(void) * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel * document number 292116). So here it goes... */ - init_apic_ldr(); + apic->init_apic_ldr(); /* * Set Task Priority to 'accept all'. We never change this @@ -1570,11 +1595,11 @@ int apic_version[MAX_APICS]; int __init APIC_init_uniprocessor(void) { -#ifdef CONFIG_X86_64 if (disable_apic) { pr_info("Apic disabled\n"); return -1; } +#ifdef CONFIG_X86_64 if (!cpu_has_apic) { disable_apic = 1; pr_info("Apic disabled by BIOS\n"); @@ -1600,7 +1625,7 @@ int __init APIC_init_uniprocessor(void) enable_IR_x2apic(); #endif #ifdef CONFIG_X86_64 - setup_apic_routing(); + default_setup_apic_routing(); #endif verify_local_APIC(); @@ -1738,7 +1763,8 @@ void __init connect_bsp_APIC(void) outb(0x01, 0x23); } #endif - enable_apic_mode(); + if (apic->enable_apic_mode) + apic->enable_apic_mode(); } /** @@ -1876,29 +1902,39 @@ void __cpuinit generic_processor_info(int apicid, int version) } #endif -#if defined(CONFIG_X86_SMP) || defined(CONFIG_X86_64) - /* are we being called early in kernel startup? */ - if (early_per_cpu_ptr(x86_cpu_to_apicid)) { - u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); - u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid); - - cpu_to_apicid[cpu] = apicid; - bios_cpu_apicid[cpu] = apicid; - } else { - per_cpu(x86_cpu_to_apicid, cpu) = apicid; - per_cpu(x86_bios_cpu_apicid, cpu) = apicid; - } +#if defined(CONFIG_SMP) || defined(CONFIG_X86_64) + early_per_cpu(x86_cpu_to_apicid, cpu) = apicid; + early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid; #endif set_cpu_possible(cpu, true); set_cpu_present(cpu, true); } -#ifdef CONFIG_X86_64 int hard_smp_processor_id(void) { return read_apic_id(); } + +void default_init_apic_ldr(void) +{ + unsigned long val; + + apic_write(APIC_DFR, APIC_DFR_VALUE); + val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; + val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); + apic_write(APIC_LDR, val); +} + +#ifdef CONFIG_X86_32 +int default_apicid_to_node(int logical_apicid) +{ +#ifdef CONFIG_SMP + return apicid_2_node[hard_smp_processor_id()]; +#else + return 0; +#endif +} #endif /* diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 98807bb095a..37ba5f85b71 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -301,7 +301,7 @@ extern int (*console_blank_hook)(int); */ #define APM_ZERO_SEGS -#include "apm.h" +#include <asm/apm.h> /* * Define to re-initialize the interrupt 0 timer to 100 Hz after a suspend. diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index ee4df08feee..fbf2f33e308 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -75,6 +75,7 @@ void foo(void) OFFSET(PT_DS, pt_regs, ds); OFFSET(PT_ES, pt_regs, es); OFFSET(PT_FS, pt_regs, fs); + OFFSET(PT_GS, pt_regs, gs); OFFSET(PT_ORIG_EAX, pt_regs, orig_ax); OFFSET(PT_EIP, pt_regs, ip); OFFSET(PT_CS, pt_regs, cs); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 1d41d3f1edb..8793ab33e2c 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -11,7 +11,6 @@ #include <linux/hardirq.h> #include <linux/suspend.h> #include <linux/kbuild.h> -#include <asm/pda.h> #include <asm/processor.h> #include <asm/segment.h> #include <asm/thread_info.h> @@ -48,16 +47,6 @@ int main(void) #endif BLANK(); #undef ENTRY -#define ENTRY(entry) DEFINE(pda_ ## entry, offsetof(struct x8664_pda, entry)) - ENTRY(kernelstack); - ENTRY(oldrsp); - ENTRY(pcurrent); - ENTRY(irqcount); - ENTRY(cpunumber); - ENTRY(irqstackptr); - ENTRY(data_offset); - BLANK(); -#undef ENTRY #ifdef CONFIG_PARAVIRT BLANK(); OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); diff --git a/arch/x86/kernel/bigsmp_32.c b/arch/x86/kernel/bigsmp_32.c new file mode 100644 index 00000000000..47a62f46afd --- /dev/null +++ b/arch/x86/kernel/bigsmp_32.c @@ -0,0 +1,266 @@ +/* + * APIC driver for "bigsmp" XAPIC machines with more than 8 virtual CPUs. + * Drives the local APIC in "clustered mode". + */ +#define APIC_DEFINITION 1 +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <asm/mpspec.h> +#include <asm/genapic.h> +#include <asm/fixmap.h> +#include <asm/apicdef.h> +#include <asm/ipi.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/dmi.h> +#include <linux/smp.h> + + +static inline unsigned bigsmp_get_apic_id(unsigned long x) +{ + return (x >> 24) & 0xFF; +} + +#define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu)) + +static inline int bigsmp_apic_id_registered(void) +{ + return 1; +} + +static inline const cpumask_t *bigsmp_target_cpus(void) +{ +#ifdef CONFIG_SMP + return &cpu_online_map; +#else + return &cpumask_of_cpu(0); +#endif +} + +#define APIC_DFR_VALUE (APIC_DFR_FLAT) + +static inline unsigned long +bigsmp_check_apicid_used(physid_mask_t bitmap, int apicid) +{ + return 0; +} + +static inline unsigned long bigsmp_check_apicid_present(int bit) +{ + return 1; +} + +static inline unsigned long calculate_ldr(int cpu) +{ + unsigned long val, id; + val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; + id = xapic_phys_to_log_apicid(cpu); + val |= SET_APIC_LOGICAL_ID(id); + return val; +} + +/* + * Set up the logical destination ID. + * + * Intel recommends to set DFR, LDR and TPR before enabling + * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel + * document number 292116). So here it goes... + */ +static inline void bigsmp_init_apic_ldr(void) +{ + unsigned long val; + int cpu = smp_processor_id(); + + apic_write(APIC_DFR, APIC_DFR_VALUE); + val = calculate_ldr(cpu); + apic_write(APIC_LDR, val); +} + +static inline void bigsmp_setup_apic_routing(void) +{ + printk("Enabling APIC mode: %s. Using %d I/O APICs\n", + "Physflat", nr_ioapics); +} + +static inline int bigsmp_apicid_to_node(int logical_apicid) +{ + return apicid_2_node[hard_smp_processor_id()]; +} + +static inline int bigsmp_cpu_present_to_apicid(int mps_cpu) +{ + if (mps_cpu < nr_cpu_ids) + return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu); + + return BAD_APICID; +} + +static inline physid_mask_t bigsmp_apicid_to_cpu_present(int phys_apicid) +{ + return physid_mask_of_physid(phys_apicid); +} + +extern u8 cpu_2_logical_apicid[]; +/* Mapping from cpu number to logical apicid */ +static inline int bigsmp_cpu_to_logical_apicid(int cpu) +{ + if (cpu >= nr_cpu_ids) + return BAD_APICID; + return cpu_physical_id(cpu); +} + +static inline physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map) +{ + /* For clustered we don't have a good way to do this yet - hack */ + return physids_promote(0xFFL); +} + +static inline void bigsmp_setup_portio_remap(void) +{ +} + +static inline int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid) +{ + return 1; +} + +/* As we are using single CPU as destination, pick only one CPU here */ +static inline unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask) +{ + return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask)); +} + +static inline unsigned int +bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask) +{ + int cpu; + + /* + * We're using fixed IRQ delivery, can only return one phys APIC ID. + * May as well be the first. + */ + for_each_cpu_and(cpu, cpumask, andmask) { + if (cpumask_test_cpu(cpu, cpu_online_mask)) + break; + } + if (cpu < nr_cpu_ids) + return bigsmp_cpu_to_logical_apicid(cpu); + + return BAD_APICID; +} + +static inline int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} + +static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector) +{ + default_send_IPI_mask_sequence_phys(mask, vector); +} + +static inline void bigsmp_send_IPI_allbutself(int vector) +{ + default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); +} + +static inline void bigsmp_send_IPI_all(int vector) +{ + bigsmp_send_IPI_mask(cpu_online_mask, vector); +} + +static int dmi_bigsmp; /* can be set by dmi scanners */ + +static int hp_ht_bigsmp(const struct dmi_system_id *d) +{ + printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident); + dmi_bigsmp = 1; + return 0; +} + + +static const struct dmi_system_id bigsmp_dmi_table[] = { + { hp_ht_bigsmp, "HP ProLiant DL760 G2", + { DMI_MATCH(DMI_BIOS_VENDOR, "HP"), + DMI_MATCH(DMI_BIOS_VERSION, "P44-"),} + }, + + { hp_ht_bigsmp, "HP ProLiant DL740", + { DMI_MATCH(DMI_BIOS_VENDOR, "HP"), + DMI_MATCH(DMI_BIOS_VERSION, "P47-"),} + }, + { } +}; + +static void bigsmp_vector_allocation_domain(int cpu, cpumask_t *retmask) +{ + cpus_clear(*retmask); + cpu_set(cpu, *retmask); +} + +static int probe_bigsmp(void) +{ + if (def_to_bigsmp) + dmi_bigsmp = 1; + else + dmi_check_system(bigsmp_dmi_table); + return dmi_bigsmp; +} + +struct genapic apic_bigsmp = { + + .name = "bigsmp", + .probe = probe_bigsmp, + .acpi_madt_oem_check = NULL, + .apic_id_registered = bigsmp_apic_id_registered, + + .irq_delivery_mode = dest_Fixed, + /* phys delivery to target CPU: */ + .irq_dest_mode = 0, + + .target_cpus = bigsmp_target_cpus, + .disable_esr = 1, + .dest_logical = 0, + .check_apicid_used = bigsmp_check_apicid_used, + .check_apicid_present = bigsmp_check_apicid_present, + + .vector_allocation_domain = bigsmp_vector_allocation_domain, + .init_apic_ldr = bigsmp_init_apic_ldr, + + .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, + .setup_apic_routing = bigsmp_setup_apic_routing, + .multi_timer_check = NULL, + .apicid_to_node = bigsmp_apicid_to_node, + .cpu_to_logical_apicid = bigsmp_cpu_to_logical_apicid, + .cpu_present_to_apicid = bigsmp_cpu_present_to_apicid, + .apicid_to_cpu_present = bigsmp_apicid_to_cpu_present, + .setup_portio_remap = NULL, + .check_phys_apicid_present = bigsmp_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = bigsmp_phys_pkg_id, + .mps_oem_check = NULL, + + .get_apic_id = bigsmp_get_apic_id, + .set_apic_id = NULL, + .apic_id_mask = 0xFF << 24, + + .cpu_mask_to_apicid = bigsmp_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = bigsmp_cpu_mask_to_apicid_and, + + .send_IPI_mask = bigsmp_send_IPI_mask, + .send_IPI_mask_allbutself = NULL, + .send_IPI_allbutself = bigsmp_send_IPI_allbutself, + .send_IPI_all = bigsmp_send_IPI_all, + .send_IPI_self = default_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + + .wait_for_init_deassert = default_wait_for_init_deassert, + + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = default_inquire_remote_apic, +}; diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index 2cf23634b6d..e48640cfac0 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -7,7 +7,7 @@ #include <asm/pat.h> #include <asm/processor.h> -#include <mach_apic.h> +#include <asm/genapic.h> struct cpuid_bit { u16 feature; @@ -69,7 +69,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) */ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_SMP +#ifdef CONFIG_SMP unsigned int eax, ebx, ecx, edx, sub_index; unsigned int ht_mask_width, core_plus_mask_width; unsigned int core_select_mask, core_level_siblings; @@ -116,22 +116,14 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width; -#ifdef CONFIG_X86_32 - c->cpu_core_id = phys_pkg_id(c->initial_apicid, ht_mask_width) + c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width) & core_select_mask; - c->phys_proc_id = phys_pkg_id(c->initial_apicid, core_plus_mask_width); + c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, core_plus_mask_width); /* * Reinit the apicid, now that we have extended initial_apicid. */ - c->apicid = phys_pkg_id(c->initial_apicid, 0); -#else - c->cpu_core_id = phys_pkg_id(ht_mask_width) & core_select_mask; - c->phys_proc_id = phys_pkg_id(core_plus_mask_width); - /* - * Reinit the apicid, now that we have extended initial_apicid. - */ - c->apicid = phys_pkg_id(0); -#endif + c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); + c->x86_max_cores = (core_level_siblings / smp_num_siblings); @@ -143,37 +135,3 @@ void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) return; #endif } - -#ifdef CONFIG_X86_PAT -void __cpuinit validate_pat_support(struct cpuinfo_x86 *c) -{ - if (!cpu_has_pat) - pat_disable("PAT not supported by CPU."); - - switch (c->x86_vendor) { - case X86_VENDOR_INTEL: - /* - * There is a known erratum on Pentium III and Core Solo - * and Core Duo CPUs. - * " Page with PAT set to WC while associated MTRR is UC - * may consolidate to UC " - * Because of this erratum, it is better to stick with - * setting WC in MTRR rather than using PAT on these CPUs. - * - * Enable PAT WC only on P4, Core 2 or later CPUs. - */ - if (c->x86 > 0x6 || (c->x86 == 6 && c->x86_model >= 15)) - return; - - pat_disable("PAT WC disabled due to known CPU erratum."); - return; - - case X86_VENDOR_AMD: - case X86_VENDOR_CENTAUR: - case X86_VENDOR_TRANSMETA: - return; - } - - pat_disable("PAT disabled. Not yet verified on this CPU type."); -} -#endif diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 7c878f6aa91..ff4d7b9e32e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -12,7 +12,7 @@ # include <asm/cacheflush.h> #endif -#include <mach_apic.h> +#include <asm/genapic.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3f272d42d09..e8f4a386bd9 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -26,11 +26,11 @@ #ifdef CONFIG_X86_LOCAL_APIC #include <asm/mpspec.h> #include <asm/apic.h> -#include <mach_apic.h> #include <asm/genapic.h> +#include <asm/genapic.h> +#include <asm/uv/uv.h> #endif -#include <asm/pda.h> #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/desc.h> @@ -39,6 +39,7 @@ #include <asm/sections.h> #include <asm/setup.h> #include <asm/hypervisor.h> +#include <asm/stackprotector.h> #include "cpu.h" @@ -52,6 +53,15 @@ cpumask_var_t cpu_initialized_mask; /* representing cpus for which sibling maps can be computed */ cpumask_var_t cpu_sibling_setup_mask; +/* correctly size the local cpu masks */ +void __init setup_cpu_local_masks(void) +{ + alloc_bootmem_cpumask_var(&cpu_initialized_mask); + alloc_bootmem_cpumask_var(&cpu_callin_mask); + alloc_bootmem_cpumask_var(&cpu_callout_mask); + alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); +} + #else /* CONFIG_X86_32 */ cpumask_t cpu_callin_map; @@ -64,23 +74,23 @@ cpumask_t cpu_sibling_setup_map; static struct cpu_dev *this_cpu __cpuinitdata; +DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { #ifdef CONFIG_X86_64 -/* We need valid kernel segments for data and code in long mode too - * IRET will check the segment types kkeil 2000/10/28 - * Also sysret mandates a special GDT layout - */ -/* The TLS descriptors are currently at a different place compared to i386. - Hopefully nobody expects them at a fixed place (Wine?) */ -DEFINE_PER_CPU(struct gdt_page, gdt_page) = { .gdt = { + /* + * We need valid kernel segments for data and code in long mode too + * IRET will check the segment types kkeil 2000/10/28 + * Also sysret mandates a special GDT layout + * + * The TLS descriptors are currently at a different place compared to i386. + * Hopefully nobody expects them at a fixed place (Wine?) + */ [GDT_ENTRY_KERNEL32_CS] = { { { 0x0000ffff, 0x00cf9b00 } } }, [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00af9b00 } } }, [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9300 } } }, [GDT_ENTRY_DEFAULT_USER32_CS] = { { { 0x0000ffff, 0x00cffb00 } } }, [GDT_ENTRY_DEFAULT_USER_DS] = { { { 0x0000ffff, 0x00cff300 } } }, [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00affb00 } } }, -} }; #else -DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { [GDT_ENTRY_KERNEL_CS] = { { { 0x0000ffff, 0x00cf9a00 } } }, [GDT_ENTRY_KERNEL_DS] = { { { 0x0000ffff, 0x00cf9200 } } }, [GDT_ENTRY_DEFAULT_USER_CS] = { { { 0x0000ffff, 0x00cffa00 } } }, @@ -112,9 +122,10 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { [GDT_ENTRY_APMBIOS_BASE+2] = { { { 0x0000ffff, 0x00409200 } } }, [GDT_ENTRY_ESPFIX_SS] = { { { 0x00000000, 0x00c09200 } } }, - [GDT_ENTRY_PERCPU] = { { { 0x00000000, 0x00000000 } } }, -} }; + [GDT_ENTRY_PERCPU] = { { { 0x0000ffff, 0x00cf9200 } } }, + GDT_STACK_CANARY_INIT #endif +} }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); #ifdef CONFIG_X86_32 @@ -215,6 +226,49 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) #endif /* + * Some CPU features depend on higher CPUID levels, which may not always + * be available due to CPUID level capping or broken virtualization + * software. Add those features to this table to auto-disable them. + */ +struct cpuid_dependent_feature { + u32 feature; + u32 level; +}; +static const struct cpuid_dependent_feature __cpuinitconst +cpuid_dependent_features[] = { + { X86_FEATURE_MWAIT, 0x00000005 }, + { X86_FEATURE_DCA, 0x00000009 }, + { X86_FEATURE_XSAVE, 0x0000000d }, + { 0, 0 } +}; + +static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) +{ + const struct cpuid_dependent_feature *df; + for (df = cpuid_dependent_features; df->feature; df++) { + /* + * Note: cpuid_level is set to -1 if unavailable, but + * extended_extended_level is set to 0 if unavailable + * and the legitimate extended levels are all negative + * when signed; hence the weird messing around with + * signs here... + */ + if (cpu_has(c, df->feature) && + ((s32)df->feature < 0 ? + (u32)df->feature > (u32)c->extended_cpuid_level : + (s32)df->feature > (s32)c->cpuid_level)) { + clear_cpu_cap(c, df->feature); + if (warn) + printk(KERN_WARNING + "CPU: CPU feature %s disabled " + "due to lack of CPUID level 0x%x\n", + x86_cap_flags[df->feature], + df->level); + } + } +} + +/* * Naming convention should be: <Name> [(<Codename>)] * This table only is used unless init_<vendor>() below doesn't set it; * in particular, if CPUID levels 0x80000002..4 are supported, this isn't used @@ -244,18 +298,29 @@ static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c) __u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata; +void load_percpu_segment(int cpu) +{ +#ifdef CONFIG_X86_32 + loadsegment(fs, __KERNEL_PERCPU); +#else + loadsegment(gs, 0); + wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu)); +#endif + load_stack_canary_segment(); +} + /* Current gdt points %fs at the "master" per-cpu area: after this, * it's on the real one. */ -void switch_to_new_gdt(void) +void switch_to_new_gdt(int cpu) { struct desc_ptr gdt_descr; - gdt_descr.address = (long)get_cpu_gdt_table(smp_processor_id()); + gdt_descr.address = (long)get_cpu_gdt_table(cpu); gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); -#ifdef CONFIG_X86_32 - asm("mov %0, %%fs" : : "r" (__KERNEL_PERCPU) : "memory"); -#endif + /* Reload the per-cpu base */ + + load_percpu_segment(cpu); } static struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; @@ -385,11 +450,7 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) } index_msb = get_count_order(smp_num_siblings); -#ifdef CONFIG_X86_64 - c->phys_proc_id = phys_pkg_id(index_msb); -#else - c->phys_proc_id = phys_pkg_id(c->initial_apicid, index_msb); -#endif + c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb); smp_num_siblings = smp_num_siblings / c->x86_max_cores; @@ -397,13 +458,8 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) core_bits = get_count_order(c->x86_max_cores); -#ifdef CONFIG_X86_64 - c->cpu_core_id = phys_pkg_id(index_msb) & + c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) & ((1 << core_bits) - 1); -#else - c->cpu_core_id = phys_pkg_id(c->initial_apicid, index_msb) & - ((1 << core_bits) - 1); -#endif } out: @@ -572,11 +628,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_early_init) this_cpu->c_early_init(c); - validate_pat_support(c); - #ifdef CONFIG_SMP c->cpu_index = boot_cpu_id; #endif + filter_cpuid_features(c, false); } void __init early_cpu_init(void) @@ -639,7 +694,7 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; #ifdef CONFIG_X86_32 # ifdef CONFIG_X86_HT - c->apicid = phys_pkg_id(c->initial_apicid, 0); + c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); # else c->apicid = c->initial_apicid; # endif @@ -686,7 +741,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_identify(c); #ifdef CONFIG_X86_64 - c->apicid = phys_pkg_id(0); + c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); #endif /* @@ -710,6 +765,9 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) * we do "generic changes." */ + /* Filter out anything that depends on CPUID levels we don't have */ + filter_cpuid_features(c, true); + /* If the model name is still unset, do table lookup. */ if (!c->x86_model_id[0]) { char *p; @@ -879,54 +937,22 @@ static __init int setup_disablecpuid(char *arg) __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 -struct x8664_pda **_cpu_pda __read_mostly; -EXPORT_SYMBOL(_cpu_pda); - struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table }; -static char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss; - -void __cpuinit pda_init(int cpu) -{ - struct x8664_pda *pda = cpu_pda(cpu); +DEFINE_PER_CPU_FIRST(union irq_stack_union, + irq_stack_union) __aligned(PAGE_SIZE); +DEFINE_PER_CPU(char *, irq_stack_ptr) = + init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; - /* Setup up data that may be needed in __get_free_pages early */ - loadsegment(fs, 0); - loadsegment(gs, 0); - /* Memory clobbers used to order PDA accessed */ - mb(); - wrmsrl(MSR_GS_BASE, pda); - mb(); - - pda->cpunumber = cpu; - pda->irqcount = -1; - pda->kernelstack = (unsigned long)stack_thread_info() - - PDA_STACKOFFSET + THREAD_SIZE; - pda->active_mm = &init_mm; - pda->mmu_state = 0; - - if (cpu == 0) { - /* others are initialized in smpboot.c */ - pda->pcurrent = &init_task; - pda->irqstackptr = boot_cpu_stack; - pda->irqstackptr += IRQSTACKSIZE - 64; - } else { - if (!pda->irqstackptr) { - pda->irqstackptr = (char *) - __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER); - if (!pda->irqstackptr) - panic("cannot allocate irqstack for cpu %d", - cpu); - pda->irqstackptr += IRQSTACKSIZE - 64; - } +DEFINE_PER_CPU(unsigned long, kernel_stack) = + (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE; +EXPORT_PER_CPU_SYMBOL(kernel_stack); - if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE) - pda->nodenumber = cpu_to_node(cpu); - } -} +DEFINE_PER_CPU(unsigned int, irq_count) = -1; -static char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + - DEBUG_STKSZ] __page_aligned_bss; +static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks + [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]) + __aligned(PAGE_SIZE); extern asmlinkage void ignore_sysret(void); @@ -959,16 +985,21 @@ unsigned long kernel_eflags; */ DEFINE_PER_CPU(struct orig_ist, orig_ist); -#else +#else /* x86_64 */ + +#ifdef CONFIG_CC_STACKPROTECTOR +DEFINE_PER_CPU(unsigned long, stack_canary); +#endif -/* Make sure %fs is initialized properly in idle threads */ +/* Make sure %fs and %gs are initialized properly in idle threads */ struct pt_regs * __cpuinit idle_regs(struct pt_regs *regs) { memset(regs, 0, sizeof(struct pt_regs)); regs->fs = __KERNEL_PERCPU; + regs->gs = __KERNEL_STACK_CANARY; return regs; } -#endif +#endif /* x86_64 */ /* * cpu_init() initializes state that is per-CPU. Some data is already @@ -984,15 +1015,14 @@ void __cpuinit cpu_init(void) struct tss_struct *t = &per_cpu(init_tss, cpu); struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu); unsigned long v; - char *estacks = NULL; struct task_struct *me; int i; - /* CPU 0 is initialised in head64.c */ - if (cpu != 0) - pda_init(cpu); - else - estacks = boot_exception_stacks; +#ifdef CONFIG_NUMA + if (cpu != 0 && percpu_read(node_number) == 0 && + cpu_to_node(cpu) != NUMA_NO_NODE) + percpu_write(node_number, cpu_to_node(cpu)); +#endif me = current; @@ -1008,7 +1038,9 @@ void __cpuinit cpu_init(void) * and set up the GDT descriptor: */ - switch_to_new_gdt(); + switch_to_new_gdt(cpu); + loadsegment(fs, 0); + load_idt((const struct desc_ptr *)&idt_descr); memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8); @@ -1026,18 +1058,13 @@ void __cpuinit cpu_init(void) * set up and load the per-CPU TSS */ if (!orig_ist->ist[0]) { - static const unsigned int order[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER, - [DEBUG_STACK - 1] = DEBUG_STACK_ORDER + static const unsigned int sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ }; + char *estacks = per_cpu(exception_stacks, cpu); for (v = 0; v < N_EXCEPTION_STACKS; v++) { - if (cpu) { - estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]); - if (!estacks) - panic("Cannot allocate exception " - "stack %ld %d\n", v, cpu); - } - estacks += PAGE_SIZE << order[v]; + estacks += sizes[v]; orig_ist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks; } @@ -1113,7 +1140,7 @@ void __cpuinit cpu_init(void) clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); load_idt(&idt_descr); - switch_to_new_gdt(); + switch_to_new_gdt(cpu); /* * Set up and load the per-CPU TSS and LDT @@ -1134,9 +1161,6 @@ void __cpuinit cpu_init(void) __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss); #endif - /* Clear %gs. */ - asm volatile ("mov %0, %%gs" : : "r" (0)); - /* Clear all 6 debug registers: */ set_debugreg(0, 0); set_debugreg(0, 1); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 5c28b37dea1..fb039cd345d 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -939,10 +939,25 @@ static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) free_cpumask_var(data->acpi_data.shared_cpu_map); } +static int get_transition_latency(struct powernow_k8_data *data) +{ + int max_latency = 0; + int i; + for (i = 0; i < data->acpi_data.state_count; i++) { + int cur_latency = data->acpi_data.states[i].transition_latency + + data->acpi_data.states[i].bus_master_latency; + if (cur_latency > max_latency) + max_latency = cur_latency; + } + /* value in usecs, needs to be in nanoseconds */ + return 1000 * max_latency; +} + #else static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; } static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; } static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; } +static int get_transition_latency(struct powernow_k8_data *data) { return 0; } #endif /* CONFIG_X86_POWERNOW_K8_ACPI */ /* Take a frequency, and issue the fid/vid transition command */ @@ -1173,7 +1188,13 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (rc) { goto err_out; } - } + /* Take a crude guess here. + * That guess was in microseconds, so multiply with 1000 */ + pol->cpuinfo.transition_latency = ( + ((data->rvo + 8) * data->vstable * VST_UNITS_20US) + + ((1 << data->irt) * 30)) * 1000; + } else /* ACPI _PSS objects available */ + pol->cpuinfo.transition_latency = get_transition_latency(data); /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; @@ -1204,11 +1225,6 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu)); data->available_cores = pol->cpus; - /* Take a crude guess here. - * That guess was in microseconds, so multiply with 1000 */ - pol->cpuinfo.transition_latency = (((data->rvo + 8) * data->vstable * VST_UNITS_20US) - + (3 * (1 << data->irt) * 10)) * 1000; - if (cpu_family == CPU_HW_PSTATE) pol->cur = find_khz_freq_from_pstate(data->powernow_table, data->currpstate); else diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 430e5c38a54..1f137a87d4b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -24,7 +24,7 @@ #ifdef CONFIG_X86_LOCAL_APIC #include <asm/mpspec.h> #include <asm/apic.h> -#include <mach_apic.h> +#include <asm/genapic.h> #endif static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) @@ -63,6 +63,18 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); } + /* + * There is a known erratum on Pentium III and Core Solo + * and Core Duo CPUs. + * " Page with PAT set to WC while associated MTRR is UC + * may consolidate to UC " + * Because of this erratum, it is better to stick with + * setting WC in MTRR rather than using PAT on these CPUs. + * + * Enable PAT WC only on P4, Core 2 or later CPUs. + */ + if (c->x86 == 6 && c->x86_model < 15) + clear_cpu_cap(c, X86_FEATURE_PAT); } #ifdef CONFIG_X86_32 @@ -291,6 +303,9 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) ds_init_intel(c); } + if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush) + set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR); + #ifdef CONFIG_X86_64 if (c->x86 == 15) c->x86_cache_alignment = c->x86_clflush_size * 2; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index da299eb85fc..7293508d8f5 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -147,7 +147,16 @@ struct _cpuid4_info { union _cpuid4_leaf_ecx ecx; unsigned long size; unsigned long can_disable; - cpumask_t shared_cpu_map; /* future?: only cpus/node is needed */ + DECLARE_BITMAP(shared_cpu_map, NR_CPUS); +}; + +/* subset of above _cpuid4_info w/o shared_cpu_map */ +struct _cpuid4_info_regs { + union _cpuid4_leaf_eax eax; + union _cpuid4_leaf_ebx ebx; + union _cpuid4_leaf_ecx ecx; + unsigned long size; + unsigned long can_disable; }; #ifdef CONFIG_PCI @@ -278,7 +287,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, } static void __cpuinit -amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf) +amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) { if (index < 3) return; @@ -286,7 +295,8 @@ amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf) } static int -__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) +__cpuinit cpuid4_cache_lookup_regs(int index, + struct _cpuid4_info_regs *this_leaf) { union _cpuid4_leaf_eax eax; union _cpuid4_leaf_ebx ebx; @@ -314,6 +324,15 @@ __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) return 0; } +static int +__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) +{ + struct _cpuid4_info_regs *leaf_regs = + (struct _cpuid4_info_regs *)this_leaf; + + return cpuid4_cache_lookup_regs(index, leaf_regs); +} + static int __cpuinit find_num_cache_leaves(void) { unsigned int eax, ebx, ecx, edx; @@ -353,11 +372,10 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) * parameters cpuid leaf to find the cache details */ for (i = 0; i < num_cache_leaves; i++) { - struct _cpuid4_info this_leaf; - + struct _cpuid4_info_regs this_leaf; int retval; - retval = cpuid4_cache_lookup(i, &this_leaf); + retval = cpuid4_cache_lookup_regs(i, &this_leaf); if (retval >= 0) { switch(this_leaf.eax.split.level) { case 1: @@ -506,17 +524,20 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing; if (num_threads_sharing == 1) - cpu_set(cpu, this_leaf->shared_cpu_map); + cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map)); else { index_msb = get_count_order(num_threads_sharing); for_each_online_cpu(i) { if (cpu_data(i).apicid >> index_msb == c->apicid >> index_msb) { - cpu_set(i, this_leaf->shared_cpu_map); + cpumask_set_cpu(i, + to_cpumask(this_leaf->shared_cpu_map)); if (i != cpu && per_cpu(cpuid4_info, i)) { - sibling_leaf = CPUID4_INFO_IDX(i, index); - cpu_set(cpu, sibling_leaf->shared_cpu_map); + sibling_leaf = + CPUID4_INFO_IDX(i, index); + cpumask_set_cpu(cpu, to_cpumask( + sibling_leaf->shared_cpu_map)); } } } @@ -528,9 +549,10 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) int sibling; this_leaf = CPUID4_INFO_IDX(cpu, index); - for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) { + for_each_cpu(sibling, to_cpumask(this_leaf->shared_cpu_map)) { sibling_leaf = CPUID4_INFO_IDX(sibling, index); - cpu_clear(cpu, sibling_leaf->shared_cpu_map); + cpumask_clear_cpu(cpu, + to_cpumask(sibling_leaf->shared_cpu_map)); } } #else @@ -635,8 +657,9 @@ static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf, int n = 0; if (len > 1) { - cpumask_t *mask = &this_leaf->shared_cpu_map; + const struct cpumask *mask; + mask = to_cpumask(this_leaf->shared_cpu_map); n = type? cpulist_scnprintf(buf, len-2, mask) : cpumask_scnprintf(buf, len-2, mask); @@ -699,7 +722,8 @@ static struct pci_dev *get_k8_northbridge(int node) static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf) { - int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map)); + const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map); + int node = cpu_to_node(cpumask_first(mask)); struct pci_dev *dev = NULL; ssize_t ret = 0; int i; @@ -733,7 +757,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf, size_t count) { - int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map)); + const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map); + int node = cpu_to_node(cpumask_first(mask)); struct pci_dev *dev = NULL; unsigned int ret, index, val; @@ -878,7 +903,7 @@ err_out: return -ENOMEM; } -static cpumask_t cache_dev_map = CPU_MASK_NONE; +static DECLARE_BITMAP(cache_dev_map, NR_CPUS); /* Add/Remove cache interface for CPU device */ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) @@ -918,7 +943,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) } kobject_uevent(&(this_object->kobj), KOBJ_ADD); } - cpu_set(cpu, cache_dev_map); + cpumask_set_cpu(cpu, to_cpumask(cache_dev_map)); kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD); return 0; @@ -931,9 +956,9 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev) if (per_cpu(cpuid4_info, cpu) == NULL) return; - if (!cpu_isset(cpu, cache_dev_map)) + if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map))) return; - cpu_clear(cpu, cache_dev_map); + cpumask_clear_cpu(cpu, to_cpumask(cache_dev_map)); for (i = 0; i < num_cache_leaves; i++) kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj)); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 8ae8c4ff094..4772e91e824 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -67,7 +67,7 @@ static struct threshold_block threshold_defaults = { struct threshold_bank { struct kobject *kobj; struct threshold_block *blocks; - cpumask_t cpus; + cpumask_var_t cpus; }; static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]); @@ -481,7 +481,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ - i = first_cpu(per_cpu(cpu_core_map, cpu)); + i = cpumask_first(&per_cpu(cpu_core_map, cpu)); /* first core not up yet */ if (cpu_data(i).cpu_core_id) @@ -501,7 +501,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out; - b->cpus = per_cpu(cpu_core_map, cpu); + cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu)); per_cpu(threshold_banks, cpu)[bank] = b; goto out; } @@ -512,15 +512,20 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) err = -ENOMEM; goto out; } + if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) { + kfree(b); + err = -ENOMEM; + goto out; + } b->kobj = kobject_create_and_add(name, &per_cpu(device_mce, cpu).kobj); if (!b->kobj) goto out_free; #ifndef CONFIG_SMP - b->cpus = CPU_MASK_ALL; + cpumask_setall(b->cpus); #else - b->cpus = per_cpu(cpu_core_map, cpu); + cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu)); #endif per_cpu(threshold_banks, cpu)[bank] = b; @@ -529,7 +534,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out_free; - for_each_cpu_mask_nr(i, b->cpus) { + for_each_cpu(i, b->cpus) { if (i == cpu) continue; @@ -545,6 +550,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) out_free: per_cpu(threshold_banks, cpu)[bank] = NULL; + free_cpumask_var(b->cpus); kfree(b); out: return err; @@ -619,7 +625,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) #endif /* remove all sibling symlinks before unregistering */ - for_each_cpu_mask_nr(i, b->cpus) { + for_each_cpu(i, b->cpus) { if (i == cpu) continue; @@ -632,6 +638,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) free_out: kobject_del(b->kobj); kobject_put(b->kobj); + free_cpumask_var(b->cpus); kfree(b); per_cpu(threshold_banks, cpu)[bank] = NULL; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index 4b48f251fd3..5e8c79e748a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -7,6 +7,7 @@ #include <linux/interrupt.h> #include <linux/percpu.h> #include <asm/processor.h> +#include <asm/apic.h> #include <asm/msr.h> #include <asm/mce.h> #include <asm/hw_irq.h> diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 11b93cabdf7..ad7f2a696f4 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -28,7 +28,7 @@ #include <asm/reboot.h> #include <asm/virtext.h> -#include <mach_ipi.h> +#include <asm/genapic.h> #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index c302d070704..d35db5993fd 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -106,7 +106,8 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); - unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr; + unsigned long *irq_stack_end = + (unsigned long *)per_cpu(irq_stack_ptr, cpu); unsigned used = 0; struct thread_info *tinfo; int graph = 0; @@ -160,23 +161,23 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, stack = (unsigned long *) estack_end[-2]; continue; } - if (irqstack_end) { - unsigned long *irqstack; - irqstack = irqstack_end - - (IRQSTACKSIZE - 64) / sizeof(*irqstack); + if (irq_stack_end) { + unsigned long *irq_stack; + irq_stack = irq_stack_end - + (IRQ_STACK_SIZE - 64) / sizeof(*irq_stack); - if (stack >= irqstack && stack < irqstack_end) { + if (stack >= irq_stack && stack < irq_stack_end) { if (ops->stack(data, "IRQ") < 0) break; bp = print_context_stack(tinfo, stack, bp, - ops, data, irqstack_end, &graph); + ops, data, irq_stack_end, &graph); /* * We link to the next stack (which would be * the process stack normally) the last * pointer (index -1 to end) in the IRQ stack: */ - stack = (unsigned long *) (irqstack_end[-1]); - irqstack_end = NULL; + stack = (unsigned long *) (irq_stack_end[-1]); + irq_stack_end = NULL; ops->stack(data, "EOI"); continue; } @@ -199,10 +200,10 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack; int i; const int cpu = smp_processor_id(); - unsigned long *irqstack_end = - (unsigned long *) (cpu_pda(cpu)->irqstackptr); - unsigned long *irqstack = - (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE); + unsigned long *irq_stack_end = + (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); + unsigned long *irq_stack = + (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE); /* * debugging aid: "show_stack(NULL, NULL);" prints the @@ -218,9 +219,9 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, stack = sp; for (i = 0; i < kstack_depth_to_print; i++) { - if (stack >= irqstack && stack <= irqstack_end) { - if (stack == irqstack_end) { - stack = (unsigned long *) (irqstack_end[-1]); + if (stack >= irq_stack && stack <= irq_stack_end) { + if (stack == irq_stack_end) { + stack = (unsigned long *) (irq_stack_end[-1]); printk(" <EOI> "); } } else { @@ -241,7 +242,7 @@ void show_registers(struct pt_regs *regs) int i; unsigned long sp; const int cpu = smp_processor_id(); - struct task_struct *cur = cpu_pda(cpu)->pcurrent; + struct task_struct *cur = current; sp = regs->sp; printk("CPU %d ", cpu); diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index 1119d247fe1..b205272ad39 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -366,10 +366,12 @@ void __init efi_init(void) SMBIOS_TABLE_GUID)) { efi.smbios = config_tables[i].table; printk(" SMBIOS=0x%lx ", config_tables[i].table); +#ifdef CONFIG_X86_UV } else if (!efi_guidcmp(config_tables[i].guid, UV_SYSTEM_TABLE_GUID)) { efi.uv_systab = config_tables[i].table; printk(" UVsystab=0x%lx ", config_tables[i].table); +#endif } else if (!efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID)) { efi.hcdp = config_tables[i].table; diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index 652c5287215..a4ee29127fd 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -36,6 +36,7 @@ #include <asm/proto.h> #include <asm/efi.h> #include <asm/cacheflush.h> +#include <asm/fixmap.h> static pgd_t save_pgd __initdata; static unsigned long efi_flags __initdata; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 46469029e9d..e9920683145 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -30,12 +30,13 @@ * 1C(%esp) - %ds * 20(%esp) - %es * 24(%esp) - %fs - * 28(%esp) - orig_eax - * 2C(%esp) - %eip - * 30(%esp) - %cs - * 34(%esp) - %eflags - * 38(%esp) - %oldesp - * 3C(%esp) - %oldss + * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS + * 2C(%esp) - orig_eax + * 30(%esp) - %eip + * 34(%esp) - %cs + * 38(%esp) - %eflags + * 3C(%esp) - %oldesp + * 40(%esp) - %oldss * * "current" is in register %ebx during any slow entries. */ @@ -101,121 +102,221 @@ #define resume_userspace_sig resume_userspace #endif -#define SAVE_ALL \ - cld; \ - pushl %fs; \ - CFI_ADJUST_CFA_OFFSET 4;\ - /*CFI_REL_OFFSET fs, 0;*/\ - pushl %es; \ - CFI_ADJUST_CFA_OFFSET 4;\ - /*CFI_REL_OFFSET es, 0;*/\ - pushl %ds; \ - CFI_ADJUST_CFA_OFFSET 4;\ - /*CFI_REL_OFFSET ds, 0;*/\ - pushl %eax; \ - CFI_ADJUST_CFA_OFFSET 4;\ - CFI_REL_OFFSET eax, 0;\ - pushl %ebp; \ - CFI_ADJUST_CFA_OFFSET 4;\ - CFI_REL_OFFSET ebp, 0;\ - pushl %edi; \ - CFI_ADJUST_CFA_OFFSET 4;\ - CFI_REL_OFFSET edi, 0;\ - pushl %esi; \ - CFI_ADJUST_CFA_OFFSET 4;\ - CFI_REL_OFFSET esi, 0;\ - pushl %edx; \ - CFI_ADJUST_CFA_OFFSET 4;\ - CFI_REL_OFFSET edx, 0;\ - pushl %ecx; \ - CFI_ADJUST_CFA_OFFSET 4;\ - CFI_REL_OFFSET ecx, 0;\ - pushl %ebx; \ - CFI_ADJUST_CFA_OFFSET 4;\ - CFI_REL_OFFSET ebx, 0;\ - movl $(__USER_DS), %edx; \ - movl %edx, %ds; \ - movl %edx, %es; \ - movl $(__KERNEL_PERCPU), %edx; \ +/* + * User gs save/restore + * + * %gs is used for userland TLS and kernel only uses it for stack + * canary which is required to be at %gs:20 by gcc. Read the comment + * at the top of stackprotector.h for more info. + * + * Local labels 98 and 99 are used. + */ +#ifdef CONFIG_X86_32_LAZY_GS + + /* unfortunately push/pop can't be no-op */ +.macro PUSH_GS + pushl $0 + CFI_ADJUST_CFA_OFFSET 4 +.endm +.macro POP_GS pop=0 + addl $(4 + \pop), %esp + CFI_ADJUST_CFA_OFFSET -(4 + \pop) +.endm +.macro POP_GS_EX +.endm + + /* all the rest are no-op */ +.macro PTGS_TO_GS +.endm +.macro PTGS_TO_GS_EX +.endm +.macro GS_TO_REG reg +.endm +.macro REG_TO_PTGS reg +.endm +.macro SET_KERNEL_GS reg +.endm + +#else /* CONFIG_X86_32_LAZY_GS */ + +.macro PUSH_GS + pushl %gs + CFI_ADJUST_CFA_OFFSET 4 + /*CFI_REL_OFFSET gs, 0*/ +.endm + +.macro POP_GS pop=0 +98: popl %gs + CFI_ADJUST_CFA_OFFSET -4 + /*CFI_RESTORE gs*/ + .if \pop <> 0 + add $\pop, %esp + CFI_ADJUST_CFA_OFFSET -\pop + .endif +.endm +.macro POP_GS_EX +.pushsection .fixup, "ax" +99: movl $0, (%esp) + jmp 98b +.section __ex_table, "a" + .align 4 + .long 98b, 99b +.popsection +.endm + +.macro PTGS_TO_GS +98: mov PT_GS(%esp), %gs +.endm +.macro PTGS_TO_GS_EX +.pushsection .fixup, "ax" +99: movl $0, PT_GS(%esp) + jmp 98b +.section __ex_table, "a" + .align 4 + .long 98b, 99b +.popsection +.endm + +.macro GS_TO_REG reg + movl %gs, \reg + /*CFI_REGISTER gs, \reg*/ +.endm +.macro REG_TO_PTGS reg + movl \reg, PT_GS(%esp) + /*CFI_REL_OFFSET gs, PT_GS*/ +.endm +.macro SET_KERNEL_GS reg + movl $(__KERNEL_STACK_CANARY), \reg + movl \reg, %gs +.endm + +#endif /* CONFIG_X86_32_LAZY_GS */ + +.macro SAVE_ALL + cld + PUSH_GS + pushl %fs + CFI_ADJUST_CFA_OFFSET 4 + /*CFI_REL_OFFSET fs, 0;*/ + pushl %es + CFI_ADJUST_CFA_OFFSET 4 + /*CFI_REL_OFFSET es, 0;*/ + pushl %ds + CFI_ADJUST_CFA_OFFSET 4 + /*CFI_REL_OFFSET ds, 0;*/ + pushl %eax + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET eax, 0 + pushl %ebp + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ebp, 0 + pushl %edi + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET edi, 0 + pushl %esi + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET esi, 0 + pushl %edx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET edx, 0 + pushl %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx, 0 + pushl %ebx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ebx, 0 + movl $(__USER_DS), %edx + movl %edx, %ds + movl %edx, %es + movl $(__KERNEL_PERCPU), %edx movl %edx, %fs + SET_KERNEL_GS %edx +.endm -#define RESTORE_INT_REGS \ - popl %ebx; \ - CFI_ADJUST_CFA_OFFSET -4;\ - CFI_RESTORE ebx;\ - popl %ecx; \ - CFI_ADJUST_CFA_OFFSET -4;\ - CFI_RESTORE ecx;\ - popl %edx; \ - CFI_ADJUST_CFA_OFFSET -4;\ - CFI_RESTORE edx;\ - popl %esi; \ - CFI_ADJUST_CFA_OFFSET -4;\ - CFI_RESTORE esi;\ - popl %edi; \ - CFI_ADJUST_CFA_OFFSET -4;\ - CFI_RESTORE edi;\ - popl %ebp; \ - CFI_ADJUST_CFA_OFFSET -4;\ - CFI_RESTORE ebp;\ - popl %eax; \ - CFI_ADJUST_CFA_OFFSET -4;\ +.macro RESTORE_INT_REGS + popl %ebx + CFI_ADJUST_CFA_OFFSET -4 + CFI_RESTORE ebx + popl %ecx + CFI_ADJUST_CFA_OFFSET -4 + CFI_RESTORE ecx + popl %edx + CFI_ADJUST_CFA_OFFSET -4 + CFI_RESTORE edx + popl %esi + CFI_ADJUST_CFA_OFFSET -4 + CFI_RESTORE esi + popl %edi + CFI_ADJUST_CFA_OFFSET -4 + CFI_RESTORE edi + popl %ebp + CFI_ADJUST_CFA_OFFSET -4 + CFI_RESTORE ebp + popl %eax + CFI_ADJUST_CFA_OFFSET -4 CFI_RESTORE eax +.endm -#define RESTORE_REGS \ - RESTORE_INT_REGS; \ -1: popl %ds; \ - CFI_ADJUST_CFA_OFFSET -4;\ - /*CFI_RESTORE ds;*/\ -2: popl %es; \ - CFI_ADJUST_CFA_OFFSET -4;\ - /*CFI_RESTORE es;*/\ -3: popl %fs; \ - CFI_ADJUST_CFA_OFFSET -4;\ - /*CFI_RESTORE fs;*/\ -.pushsection .fixup,"ax"; \ -4: movl $0,(%esp); \ - jmp 1b; \ -5: movl $0,(%esp); \ - jmp 2b; \ -6: movl $0,(%esp); \ - jmp 3b; \ -.section __ex_table,"a";\ - .align 4; \ - .long 1b,4b; \ - .long 2b,5b; \ - .long 3b,6b; \ +.macro RESTORE_REGS pop=0 + RESTORE_INT_REGS +1: popl %ds + CFI_ADJUST_CFA_OFFSET -4 + /*CFI_RESTORE ds;*/ +2: popl %es + CFI_ADJUST_CFA_OFFSET -4 + /*CFI_RESTORE es;*/ +3: popl %fs + CFI_ADJUST_CFA_OFFSET -4 + /*CFI_RESTORE fs;*/ + POP_GS \pop +.pushsection .fixup, "ax" +4: movl $0, (%esp) + jmp 1b +5: movl $0, (%esp) + jmp 2b +6: movl $0, (%esp) + jmp 3b +.section __ex_table, "a" + .align 4 + .long 1b, 4b + .long 2b, 5b + .long 3b, 6b .popsection + POP_GS_EX +.endm -#define RING0_INT_FRAME \ - CFI_STARTPROC simple;\ - CFI_SIGNAL_FRAME;\ - CFI_DEF_CFA esp, 3*4;\ - /*CFI_OFFSET cs, -2*4;*/\ +.macro RING0_INT_FRAME + CFI_STARTPROC simple + CFI_SIGNAL_FRAME + CFI_DEF_CFA esp, 3*4 + /*CFI_OFFSET cs, -2*4;*/ CFI_OFFSET eip, -3*4 +.endm -#define RING0_EC_FRAME \ - CFI_STARTPROC simple;\ - CFI_SIGNAL_FRAME;\ - CFI_DEF_CFA esp, 4*4;\ - /*CFI_OFFSET cs, -2*4;*/\ +.macro RING0_EC_FRAME + CFI_STARTPROC simple + CFI_SIGNAL_FRAME + CFI_DEF_CFA esp, 4*4 + /*CFI_OFFSET cs, -2*4;*/ CFI_OFFSET eip, -3*4 +.endm -#define RING0_PTREGS_FRAME \ - CFI_STARTPROC simple;\ - CFI_SIGNAL_FRAME;\ - CFI_DEF_CFA esp, PT_OLDESP-PT_EBX;\ - /*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/\ - CFI_OFFSET eip, PT_EIP-PT_OLDESP;\ - /*CFI_OFFSET es, PT_ES-PT_OLDESP;*/\ - /*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/\ - CFI_OFFSET eax, PT_EAX-PT_OLDESP;\ - CFI_OFFSET ebp, PT_EBP-PT_OLDESP;\ - CFI_OFFSET edi, PT_EDI-PT_OLDESP;\ - CFI_OFFSET esi, PT_ESI-PT_OLDESP;\ - CFI_OFFSET edx, PT_EDX-PT_OLDESP;\ - CFI_OFFSET ecx, PT_ECX-PT_OLDESP;\ +.macro RING0_PTREGS_FRAME + CFI_STARTPROC simple + CFI_SIGNAL_FRAME + CFI_DEF_CFA esp, PT_OLDESP-PT_EBX + /*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/ + CFI_OFFSET eip, PT_EIP-PT_OLDESP + /*CFI_OFFSET es, PT_ES-PT_OLDESP;*/ + /*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/ + CFI_OFFSET eax, PT_EAX-PT_OLDESP + CFI_OFFSET ebp, PT_EBP-PT_OLDESP + CFI_OFFSET edi, PT_EDI-PT_OLDESP + CFI_OFFSET esi, PT_ESI-PT_OLDESP + CFI_OFFSET edx, PT_EDX-PT_OLDESP + CFI_OFFSET ecx, PT_ECX-PT_OLDESP CFI_OFFSET ebx, PT_EBX-PT_OLDESP +.endm ENTRY(ret_from_fork) CFI_STARTPROC @@ -362,6 +463,7 @@ sysenter_exit: xorl %ebp,%ebp TRACE_IRQS_ON 1: mov PT_FS(%esp), %fs + PTGS_TO_GS ENABLE_INTERRUPTS_SYSEXIT #ifdef CONFIG_AUDITSYSCALL @@ -410,6 +512,7 @@ sysexit_audit: .align 4 .long 1b,2b .popsection + PTGS_TO_GS_EX ENDPROC(ia32_sysenter_target) # system call handler stub @@ -452,8 +555,7 @@ restore_all: restore_nocheck: TRACE_IRQS_IRET restore_nocheck_notrace: - RESTORE_REGS - addl $4, %esp # skip orig_eax/error_code + RESTORE_REGS 4 # skip orig_eax/error_code CFI_ADJUST_CFA_OFFSET -4 irq_return: INTERRUPT_RETURN @@ -595,28 +697,50 @@ syscall_badsys: END(syscall_badsys) CFI_ENDPROC -#define FIXUP_ESPFIX_STACK \ - /* since we are on a wrong stack, we cant make it a C code :( */ \ - PER_CPU(gdt_page, %ebx); \ - GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah); \ - addl %esp, %eax; \ - pushl $__KERNEL_DS; \ - CFI_ADJUST_CFA_OFFSET 4; \ - pushl %eax; \ - CFI_ADJUST_CFA_OFFSET 4; \ - lss (%esp), %esp; \ - CFI_ADJUST_CFA_OFFSET -8; -#define UNWIND_ESPFIX_STACK \ - movl %ss, %eax; \ - /* see if on espfix stack */ \ - cmpw $__ESPFIX_SS, %ax; \ - jne 27f; \ - movl $__KERNEL_DS, %eax; \ - movl %eax, %ds; \ - movl %eax, %es; \ - /* switch to normal stack */ \ - FIXUP_ESPFIX_STACK; \ -27:; +/* + * System calls that need a pt_regs pointer. + */ +#define PTREGSCALL(name) \ + ALIGN; \ +ptregs_##name: \ + leal 4(%esp),%eax; \ + jmp sys_##name; + +PTREGSCALL(iopl) +PTREGSCALL(fork) +PTREGSCALL(clone) +PTREGSCALL(vfork) +PTREGSCALL(execve) +PTREGSCALL(sigaltstack) +PTREGSCALL(sigreturn) +PTREGSCALL(rt_sigreturn) +PTREGSCALL(vm86) +PTREGSCALL(vm86old) + +.macro FIXUP_ESPFIX_STACK + /* since we are on a wrong stack, we cant make it a C code :( */ + PER_CPU(gdt_page, %ebx) + GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah) + addl %esp, %eax + pushl $__KERNEL_DS + CFI_ADJUST_CFA_OFFSET 4 + pushl %eax + CFI_ADJUST_CFA_OFFSET 4 + lss (%esp), %esp + CFI_ADJUST_CFA_OFFSET -8 +.endm +.macro UNWIND_ESPFIX_STACK + movl %ss, %eax + /* see if on espfix stack */ + cmpw $__ESPFIX_SS, %ax + jne 27f + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %es + /* switch to normal stack */ + FIXUP_ESPFIX_STACK +27: +.endm /* * Build the entry stubs and pointer table with some assembler magic. @@ -672,7 +796,7 @@ common_interrupt: ENDPROC(common_interrupt) CFI_ENDPROC -#define BUILD_INTERRUPT(name, nr) \ +#define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ pushl $~(nr); \ @@ -680,13 +804,15 @@ ENTRY(name) \ SAVE_ALL; \ TRACE_IRQS_OFF \ movl %esp,%eax; \ - call smp_##name; \ + call fn; \ jmp ret_from_intr; \ CFI_ENDPROC; \ ENDPROC(name) +#define BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(name, nr, smp_##name) + /* The include is where all of the SMP etc. interrupts come from */ -#include "entry_arch.h" +#include <asm/entry_arch.h> ENTRY(coprocessor_error) RING0_INT_FRAME @@ -1068,7 +1194,10 @@ ENTRY(page_fault) CFI_ADJUST_CFA_OFFSET 4 ALIGN error_code: - /* the function address is in %fs's slot on the stack */ + /* the function address is in %gs's slot on the stack */ + pushl %fs + CFI_ADJUST_CFA_OFFSET 4 + /*CFI_REL_OFFSET fs, 0*/ pushl %es CFI_ADJUST_CFA_OFFSET 4 /*CFI_REL_OFFSET es, 0*/ @@ -1097,20 +1226,15 @@ error_code: CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET ebx, 0 cld - pushl %fs - CFI_ADJUST_CFA_OFFSET 4 - /*CFI_REL_OFFSET fs, 0*/ movl $(__KERNEL_PERCPU), %ecx movl %ecx, %fs UNWIND_ESPFIX_STACK - popl %ecx - CFI_ADJUST_CFA_OFFSET -4 - /*CFI_REGISTER es, ecx*/ - movl PT_FS(%esp), %edi # get the function address + GS_TO_REG %ecx + movl PT_GS(%esp), %edi # get the function address movl PT_ORIG_EAX(%esp), %edx # get the error code movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart - mov %ecx, PT_FS(%esp) - /*CFI_REL_OFFSET fs, ES*/ + REG_TO_PTGS %ecx + SET_KERNEL_GS %ecx movl $(__USER_DS), %ecx movl %ecx, %ds movl %ecx, %es @@ -1134,26 +1258,27 @@ END(page_fault) * by hand onto the new stack - while updating the return eip past * the instruction that would have done it for sysenter. */ -#define FIX_STACK(offset, ok, label) \ - cmpw $__KERNEL_CS,4(%esp); \ - jne ok; \ -label: \ - movl TSS_sysenter_sp0+offset(%esp),%esp; \ - CFI_DEF_CFA esp, 0; \ - CFI_UNDEFINED eip; \ - pushfl; \ - CFI_ADJUST_CFA_OFFSET 4; \ - pushl $__KERNEL_CS; \ - CFI_ADJUST_CFA_OFFSET 4; \ - pushl $sysenter_past_esp; \ - CFI_ADJUST_CFA_OFFSET 4; \ +.macro FIX_STACK offset ok label + cmpw $__KERNEL_CS, 4(%esp) + jne \ok +\label: + movl TSS_sysenter_sp0 + \offset(%esp), %esp + CFI_DEF_CFA esp, 0 + CFI_UNDEFINED eip + pushfl + CFI_ADJUST_CFA_OFFSET 4 + pushl $__KERNEL_CS + CFI_ADJUST_CFA_OFFSET 4 + pushl $sysenter_past_esp + CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET eip, 0 +.endm ENTRY(debug) RING0_INT_FRAME cmpl $ia32_sysenter_target,(%esp) jne debug_stack_correct - FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn) + FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn debug_stack_correct: pushl $-1 # mark this as an int CFI_ADJUST_CFA_OFFSET 4 @@ -1211,7 +1336,7 @@ nmi_stack_correct: nmi_stack_fixup: RING0_INT_FRAME - FIX_STACK(12,nmi_stack_correct, 1) + FIX_STACK 12, nmi_stack_correct, 1 jmp nmi_stack_correct nmi_debug_stack_check: @@ -1222,7 +1347,7 @@ nmi_debug_stack_check: jb nmi_stack_correct cmpl $debug_esp_fix_insn,(%esp) ja nmi_stack_correct - FIX_STACK(24,nmi_stack_correct, 1) + FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct nmi_espfix_stack: diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index a1346217e43..fbcf96b295f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -52,6 +52,7 @@ #include <asm/irqflags.h> #include <asm/paravirt.h> #include <asm/ftrace.h> +#include <asm/percpu.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -209,7 +210,7 @@ ENTRY(native_usergs_sysret64) /* %rsp:at FRAMEEND */ .macro FIXUP_TOP_OF_STACK tmp offset=0 - movq %gs:pda_oldrsp,\tmp + movq PER_CPU_VAR(old_rsp),\tmp movq \tmp,RSP+\offset(%rsp) movq $__USER_DS,SS+\offset(%rsp) movq $__USER_CS,CS+\offset(%rsp) @@ -220,7 +221,7 @@ ENTRY(native_usergs_sysret64) .macro RESTORE_TOP_OF_STACK tmp offset=0 movq RSP+\offset(%rsp),\tmp - movq \tmp,%gs:pda_oldrsp + movq \tmp,PER_CPU_VAR(old_rsp) movq EFLAGS+\offset(%rsp),\tmp movq \tmp,R11+\offset(%rsp) .endm @@ -336,15 +337,15 @@ ENTRY(save_args) je 1f SWAPGS /* - * irqcount is used to check if a CPU is already on an interrupt stack + * irq_count is used to check if a CPU is already on an interrupt stack * or not. While this is essentially redundant with preempt_count it is * a little cheaper to use a separate counter in the PDA (short of * moving irq_enter into assembly, which would be too much work) */ -1: incl %gs:pda_irqcount +1: incl PER_CPU_VAR(irq_count) jne 2f popq_cfi %rax /* move return address... */ - mov %gs:pda_irqstackptr,%rsp + mov PER_CPU_VAR(irq_stack_ptr),%rsp EMPTY_FRAME 0 pushq_cfi %rbp /* backlink for unwinder */ pushq_cfi %rax /* ... to the new stack */ @@ -409,6 +410,8 @@ END(save_paranoid) ENTRY(ret_from_fork) DEFAULT_FRAME + LOCK ; btr $TIF_FORK,TI_flags(%r8) + push kernel_eflags(%rip) CFI_ADJUST_CFA_OFFSET 8 popf # reset kernel eflags @@ -468,7 +471,7 @@ END(ret_from_fork) ENTRY(system_call) CFI_STARTPROC simple CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,PDA_STACKOFFSET + CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET CFI_REGISTER rip,rcx /*CFI_REGISTER rflags,r11*/ SWAPGS_UNSAFE_STACK @@ -479,8 +482,8 @@ ENTRY(system_call) */ ENTRY(system_call_after_swapgs) - movq %rsp,%gs:pda_oldrsp - movq %gs:pda_kernelstack,%rsp + movq %rsp,PER_CPU_VAR(old_rsp) + movq PER_CPU_VAR(kernel_stack),%rsp /* * No need to follow this irqs off/on section - it's straight * and short: @@ -523,7 +526,7 @@ sysret_check: CFI_REGISTER rip,rcx RESTORE_ARGS 0,-ARG_SKIP,1 /*CFI_REGISTER rflags,r11*/ - movq %gs:pda_oldrsp, %rsp + movq PER_CPU_VAR(old_rsp), %rsp USERGS_SYSRET64 CFI_RESTORE_STATE @@ -833,11 +836,11 @@ common_interrupt: XCPT_FRAME addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ interrupt do_IRQ - /* 0(%rsp): oldrsp-ARGOFFSET */ + /* 0(%rsp): old_rsp-ARGOFFSET */ ret_from_intr: DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - decl %gs:pda_irqcount + decl PER_CPU_VAR(irq_count) leaveq CFI_DEF_CFA_REGISTER rsp CFI_ADJUST_CFA_OFFSET -8 @@ -982,8 +985,10 @@ apicinterrupt IRQ_MOVE_CLEANUP_VECTOR \ irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt #endif +#ifdef CONFIG_X86_UV apicinterrupt UV_BAU_MESSAGE \ uv_bau_message_intr1 uv_bau_message_interrupt +#endif apicinterrupt LOCAL_TIMER_VECTOR \ apic_timer_interrupt smp_apic_timer_interrupt @@ -1073,10 +1078,10 @@ ENTRY(\sym) TRACE_IRQS_OFF movq %rsp,%rdi /* pt_regs pointer */ xorl %esi,%esi /* no error code */ - movq %gs:pda_data_offset, %rbp - subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp) + PER_CPU(init_tss, %rbp) + subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp) call \do_sym - addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp) + addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp) jmp paranoid_exit /* %ebx: no swapgs flag */ CFI_ENDPROC END(\sym) @@ -1138,7 +1143,7 @@ ENTRY(native_load_gs_index) CFI_STARTPROC pushf CFI_ADJUST_CFA_OFFSET 8 - DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI)) + DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) SWAPGS gs_change: movl %edi,%gs @@ -1260,14 +1265,14 @@ ENTRY(call_softirq) CFI_REL_OFFSET rbp,0 mov %rsp,%rbp CFI_DEF_CFA_REGISTER rbp - incl %gs:pda_irqcount - cmove %gs:pda_irqstackptr,%rsp + incl PER_CPU_VAR(irq_count) + cmove PER_CPU_VAR(irq_stack_ptr),%rsp push %rbp # backlink for old unwinder call __do_softirq leaveq CFI_DEF_CFA_REGISTER rsp CFI_ADJUST_CFA_OFFSET -8 - decl %gs:pda_irqcount + decl PER_CPU_VAR(irq_count) ret CFI_ENDPROC END(call_softirq) @@ -1297,15 +1302,15 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) movq %rdi, %rsp # we don't return, adjust the stack frame CFI_ENDPROC DEFAULT_FRAME -11: incl %gs:pda_irqcount +11: incl PER_CPU_VAR(irq_count) movq %rsp,%rbp CFI_DEF_CFA_REGISTER rbp - cmovzq %gs:pda_irqstackptr,%rsp + cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp pushq %rbp # backlink for old unwinder call xen_evtchn_do_upcall popq %rsp CFI_DEF_CFA_REGISTER rsp - decl %gs:pda_irqcount + decl PER_CPU_VAR(irq_count) jmp error_exit CFI_ENDPROC END(do_hypervisor_callback) diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c index 53699c931ad..d6184c12a18 100644 --- a/arch/x86/kernel/es7000_32.c +++ b/arch/x86/kernel/es7000_32.c @@ -40,7 +40,6 @@ #include <asm/smp.h> #include <asm/atomic.h> #include <asm/apicdef.h> -#include <mach_mpparse.h> #include <asm/genapic.h> #include <asm/setup.h> @@ -182,20 +181,16 @@ static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip) return 0; } -static void noop_wait_for_deassert(atomic_t *deassert_not_used) -{ -} - static int __init es7000_update_genapic(void) { - genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip; + apic->wakeup_cpu = wakeup_secondary_cpu_via_mip; /* MPENTIUMIII */ if (boot_cpu_data.x86 == 6 && (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) { es7000_update_genapic_to_cluster(); - genapic->wait_for_init_deassert = noop_wait_for_deassert; - genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip; + apic->wait_for_init_deassert = NULL; + apic->wakeup_cpu = wakeup_secondary_cpu_via_mip; } return 0; @@ -359,20 +354,449 @@ es7000_mip_write(struct mip_reg *mip_reg) return status; } -void __init -es7000_sw_apic(void) -{ - if (es7000_plat) { - int mip_status; - struct mip_reg es7000_mip_reg; - - printk("ES7000: Enabling APIC mode.\n"); - memset(&es7000_mip_reg, 0, sizeof(struct mip_reg)); - es7000_mip_reg.off_0 = MIP_SW_APIC; - es7000_mip_reg.off_38 = (MIP_VALID); - while ((mip_status = es7000_mip_write(&es7000_mip_reg)) != 0) - printk("es7000_sw_apic: command failed, status = %x\n", - mip_status); +void __init es7000_enable_apic_mode(void) +{ + struct mip_reg es7000_mip_reg; + int mip_status; + + if (!es7000_plat) return; + + printk("ES7000: Enabling APIC mode.\n"); + memset(&es7000_mip_reg, 0, sizeof(struct mip_reg)); + es7000_mip_reg.off_0 = MIP_SW_APIC; + es7000_mip_reg.off_38 = MIP_VALID; + + while ((mip_status = es7000_mip_write(&es7000_mip_reg)) != 0) { + printk("es7000_enable_apic_mode: command failed, status = %x\n", + mip_status); + } +} + +/* + * APIC driver for the Unisys ES7000 chipset. + */ +#define APIC_DEFINITION 1 +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <asm/mpspec.h> +#include <asm/genapic.h> +#include <asm/fixmap.h> +#include <asm/apicdef.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/acpi.h> +#include <linux/smp.h> +#include <asm/ipi.h> + +#define APIC_DFR_VALUE_CLUSTER (APIC_DFR_CLUSTER) +#define INT_DELIVERY_MODE_CLUSTER (dest_LowestPrio) +#define INT_DEST_MODE_CLUSTER (1) /* logical delivery broadcast to all procs */ + +#define APIC_DFR_VALUE (APIC_DFR_FLAT) + +extern void es7000_enable_apic_mode(void); +extern int apic_version [MAX_APICS]; +extern u8 cpu_2_logical_apicid[]; +extern unsigned int boot_cpu_physical_apicid; + +extern int parse_unisys_oem (char *oemptr); +extern int find_unisys_acpi_oem_table(unsigned long *oem_addr); +extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr); +extern void setup_unisys(void); + +#define apicid_cluster(apicid) (apicid & 0xF0) +#define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu) + +static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask) +{ + /* Careful. Some cpus do not strictly honor the set of cpus + * specified in the interrupt destination when using lowest + * priority interrupt delivery mode. + * + * In particular there was a hyperthreading cpu observed to + * deliver interrupts to the wrong hyperthread when only one + * hyperthread was specified in the interrupt desitination. + */ + *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; +} + + +static void es7000_wait_for_init_deassert(atomic_t *deassert) +{ +#ifndef CONFIG_ES7000_CLUSTERED_APIC + while (!atomic_read(deassert)) + cpu_relax(); +#endif + return; +} + +static unsigned int es7000_get_apic_id(unsigned long x) +{ + return (x >> 24) & 0xFF; +} + +#ifdef CONFIG_ACPI +static int es7000_check_dsdt(void) +{ + struct acpi_table_header header; + + if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) && + !strncmp(header.oem_id, "UNISYS", 6)) + return 1; + return 0; +} +#endif + +static void es7000_send_IPI_mask(const struct cpumask *mask, int vector) +{ + default_send_IPI_mask_sequence_phys(mask, vector); +} + +static void es7000_send_IPI_allbutself(int vector) +{ + default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); +} + +static void es7000_send_IPI_all(int vector) +{ + es7000_send_IPI_mask(cpu_online_mask, vector); +} + +static int es7000_apic_id_registered(void) +{ + return 1; +} + +static const cpumask_t *target_cpus_cluster(void) +{ + return &CPU_MASK_ALL; +} + +static const cpumask_t *es7000_target_cpus(void) +{ + return &cpumask_of_cpu(smp_processor_id()); +} + +static unsigned long +es7000_check_apicid_used(physid_mask_t bitmap, int apicid) +{ + return 0; +} +static unsigned long es7000_check_apicid_present(int bit) +{ + return physid_isset(bit, phys_cpu_present_map); +} + +static unsigned long calculate_ldr(int cpu) +{ + unsigned long id = xapic_phys_to_log_apicid(cpu); + + return (SET_APIC_LOGICAL_ID(id)); +} + +/* + * Set up the logical destination ID. + * + * Intel recommends to set DFR, LdR and TPR before enabling + * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel + * document number 292116). So here it goes... + */ +static void es7000_init_apic_ldr_cluster(void) +{ + unsigned long val; + int cpu = smp_processor_id(); + + apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER); + val = calculate_ldr(cpu); + apic_write(APIC_LDR, val); +} + +static void es7000_init_apic_ldr(void) +{ + unsigned long val; + int cpu = smp_processor_id(); + + apic_write(APIC_DFR, APIC_DFR_VALUE); + val = calculate_ldr(cpu); + apic_write(APIC_LDR, val); +} + +static void es7000_setup_apic_routing(void) +{ + int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id()); + printk("Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n", + (apic_version[apic] == 0x14) ? + "Physical Cluster" : "Logical Cluster", + nr_ioapics, cpus_addr(*es7000_target_cpus())[0]); +} + +static int es7000_apicid_to_node(int logical_apicid) +{ + return 0; +} + + +static int es7000_cpu_present_to_apicid(int mps_cpu) +{ + if (!mps_cpu) + return boot_cpu_physical_apicid; + else if (mps_cpu < nr_cpu_ids) + return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu); + else + return BAD_APICID; +} + +static physid_mask_t es7000_apicid_to_cpu_present(int phys_apicid) +{ + static int id = 0; + physid_mask_t mask; + + mask = physid_mask_of_physid(id); + ++id; + + return mask; +} + +/* Mapping from cpu number to logical apicid */ +static int es7000_cpu_to_logical_apicid(int cpu) +{ +#ifdef CONFIG_SMP + if (cpu >= nr_cpu_ids) + return BAD_APICID; + return (int)cpu_2_logical_apicid[cpu]; +#else + return logical_smp_processor_id(); +#endif +} + +static physid_mask_t es7000_ioapic_phys_id_map(physid_mask_t phys_map) +{ + /* For clustered we don't have a good way to do this yet - hack */ + return physids_promote(0xff); +} + +static int es7000_check_phys_apicid_present(int cpu_physical_apicid) +{ + boot_cpu_physical_apicid = read_apic_id(); + return (1); +} + +static unsigned int +es7000_cpu_mask_to_apicid_cluster(const struct cpumask *cpumask) +{ + int cpus_found = 0; + int num_bits_set; + int apicid; + int cpu; + + num_bits_set = cpumask_weight(cpumask); + /* Return id to all */ + if (num_bits_set == nr_cpu_ids) + return 0xFF; + /* + * The cpus in the mask must all be on the apic cluster. If are not + * on the same apicid cluster return default value of target_cpus(): + */ + cpu = cpumask_first(cpumask); + apicid = es7000_cpu_to_logical_apicid(cpu); + + while (cpus_found < num_bits_set) { + if (cpumask_test_cpu(cpu, cpumask)) { + int new_apicid = es7000_cpu_to_logical_apicid(cpu); + + if (apicid_cluster(apicid) != + apicid_cluster(new_apicid)) { + printk ("%s: Not a valid mask!\n", __func__); + + return 0xFF; + } + apicid = new_apicid; + cpus_found++; + } + cpu++; } + return apicid; } + +static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask) +{ + int cpus_found = 0; + int num_bits_set; + int apicid; + int cpu; + + num_bits_set = cpus_weight(*cpumask); + /* Return id to all */ + if (num_bits_set == nr_cpu_ids) + return es7000_cpu_to_logical_apicid(0); + /* + * The cpus in the mask must all be on the apic cluster. If are not + * on the same apicid cluster return default value of target_cpus(): + */ + cpu = first_cpu(*cpumask); + apicid = es7000_cpu_to_logical_apicid(cpu); + while (cpus_found < num_bits_set) { + if (cpu_isset(cpu, *cpumask)) { + int new_apicid = es7000_cpu_to_logical_apicid(cpu); + + if (apicid_cluster(apicid) != + apicid_cluster(new_apicid)) { + printk ("%s: Not a valid mask!\n", __func__); + + return es7000_cpu_to_logical_apicid(0); + } + apicid = new_apicid; + cpus_found++; + } + cpu++; + } + return apicid; +} + +static unsigned int +es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask, + const struct cpumask *andmask) +{ + int apicid = es7000_cpu_to_logical_apicid(0); + cpumask_var_t cpumask; + + if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) + return apicid; + + cpumask_and(cpumask, inmask, andmask); + cpumask_and(cpumask, cpumask, cpu_online_mask); + apicid = es7000_cpu_mask_to_apicid(cpumask); + + free_cpumask_var(cpumask); + + return apicid; +} + +static int es7000_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} + +void __init es7000_update_genapic_to_cluster(void) +{ + apic->target_cpus = target_cpus_cluster; + apic->irq_delivery_mode = INT_DELIVERY_MODE_CLUSTER; + apic->irq_dest_mode = INT_DEST_MODE_CLUSTER; + + apic->init_apic_ldr = es7000_init_apic_ldr_cluster; + + apic->cpu_mask_to_apicid = es7000_cpu_mask_to_apicid_cluster; +} + +static int probe_es7000(void) +{ + /* probed later in mptable/ACPI hooks */ + return 0; +} + +static __init int +es7000_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) +{ + if (mpc->oemptr) { + struct mpc_oemtable *oem_table = + (struct mpc_oemtable *)mpc->oemptr; + + if (!strncmp(oem, "UNISYS", 6)) + return parse_unisys_oem((char *)oem_table); + } + return 0; +} + +#ifdef CONFIG_ACPI +/* Hook from generic ACPI tables.c */ +static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + unsigned long oem_addr = 0; + int check_dsdt; + int ret = 0; + + /* check dsdt at first to avoid clear fix_map for oem_addr */ + check_dsdt = es7000_check_dsdt(); + + if (!find_unisys_acpi_oem_table(&oem_addr)) { + if (check_dsdt) + ret = parse_unisys_oem((char *)oem_addr); + else { + setup_unisys(); + ret = 1; + } + /* + * we need to unmap it + */ + unmap_unisys_acpi_oem_table(oem_addr); + } + return ret; +} +#else +static int __init es7000_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + return 0; +} +#endif + + +struct genapic apic_es7000 = { + + .name = "es7000", + .probe = probe_es7000, + .acpi_madt_oem_check = es7000_acpi_madt_oem_check, + .apic_id_registered = es7000_apic_id_registered, + + .irq_delivery_mode = dest_Fixed, + /* phys delivery to target CPUs: */ + .irq_dest_mode = 0, + + .target_cpus = es7000_target_cpus, + .disable_esr = 1, + .dest_logical = 0, + .check_apicid_used = es7000_check_apicid_used, + .check_apicid_present = es7000_check_apicid_present, + + .vector_allocation_domain = es7000_vector_allocation_domain, + .init_apic_ldr = es7000_init_apic_ldr, + + .ioapic_phys_id_map = es7000_ioapic_phys_id_map, + .setup_apic_routing = es7000_setup_apic_routing, + .multi_timer_check = NULL, + .apicid_to_node = es7000_apicid_to_node, + .cpu_to_logical_apicid = es7000_cpu_to_logical_apicid, + .cpu_present_to_apicid = es7000_cpu_present_to_apicid, + .apicid_to_cpu_present = es7000_apicid_to_cpu_present, + .setup_portio_remap = NULL, + .check_phys_apicid_present = es7000_check_phys_apicid_present, + .enable_apic_mode = es7000_enable_apic_mode, + .phys_pkg_id = es7000_phys_pkg_id, + .mps_oem_check = es7000_mps_oem_check, + + .get_apic_id = es7000_get_apic_id, + .set_apic_id = NULL, + .apic_id_mask = 0xFF << 24, + + .cpu_mask_to_apicid = es7000_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and, + + .send_IPI_mask = es7000_send_IPI_mask, + .send_IPI_mask_allbutself = NULL, + .send_IPI_allbutself = es7000_send_IPI_allbutself, + .send_IPI_all = es7000_send_IPI_all, + .send_IPI_self = default_send_IPI_self, + + .wakeup_cpu = NULL, + + .trampoline_phys_low = 0x467, + .trampoline_phys_high = 0x469, + + .wait_for_init_deassert = es7000_wait_for_init_deassert, + + /* Nothing to do for most platforms, since cleared by the INIT cycle: */ + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = default_inquire_remote_apic, +}; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1b43086b097..231bdd3c5b1 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -488,20 +488,21 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) * ignore such a protection. */ asm volatile( - "1: " _ASM_MOV " (%[parent_old]), %[old]\n" - "2: " _ASM_MOV " %[return_hooker], (%[parent_replaced])\n" + "1: " _ASM_MOV " (%[parent]), %[old]\n" + "2: " _ASM_MOV " %[return_hooker], (%[parent])\n" " movl $0, %[faulted]\n" + "3:\n" ".section .fixup, \"ax\"\n" - "3: movl $1, %[faulted]\n" + "4: movl $1, %[faulted]\n" + " jmp 3b\n" ".previous\n" - _ASM_EXTABLE(1b, 3b) - _ASM_EXTABLE(2b, 3b) + _ASM_EXTABLE(1b, 4b) + _ASM_EXTABLE(2b, 4b) - : [parent_replaced] "=r" (parent), [old] "=r" (old), - [faulted] "=r" (faulted) - : [parent_old] "0" (parent), [return_hooker] "r" (return_hooker) + : [old] "=r" (old), [faulted] "=r" (faulted) + : [parent] "r" (parent), [return_hooker] "r" (return_hooker) : "memory" ); diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c index 2bced78b0b8..820dea5d0eb 100644 --- a/arch/x86/kernel/genapic_64.c +++ b/arch/x86/kernel/genapic_64.c @@ -29,10 +29,12 @@ extern struct genapic apic_x2xpic_uv_x; extern struct genapic apic_x2apic_phys; extern struct genapic apic_x2apic_cluster; -struct genapic __read_mostly *genapic = &apic_flat; +struct genapic __read_mostly *apic = &apic_flat; static struct genapic *apic_probe[] __initdata = { +#ifdef CONFIG_X86_UV &apic_x2apic_uv_x, +#endif &apic_x2apic_phys, &apic_x2apic_cluster, &apic_physflat, @@ -42,17 +44,17 @@ static struct genapic *apic_probe[] __initdata = { /* * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode. */ -void __init setup_apic_routing(void) +void __init default_setup_apic_routing(void) { - if (genapic == &apic_x2apic_phys || genapic == &apic_x2apic_cluster) { + if (apic == &apic_x2apic_phys || apic == &apic_x2apic_cluster) { if (!intr_remapping_enabled) - genapic = &apic_flat; + apic = &apic_flat; } - if (genapic == &apic_flat) { + if (apic == &apic_flat) { if (max_physical_apicid >= 8) - genapic = &apic_physflat; - printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name); + apic = &apic_physflat; + printk(KERN_INFO "Setting APIC routing to %s\n", apic->name); } if (x86_quirks->update_genapic) @@ -63,18 +65,18 @@ void __init setup_apic_routing(void) void apic_send_IPI_self(int vector) { - __send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); + __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); } -int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) +int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { int i; for (i = 0; apic_probe[i]; ++i) { if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) { - genapic = apic_probe[i]; + apic = apic_probe[i]; printk(KERN_INFO "Setting APIC routing to %s.\n", - genapic->name); + apic->name); return 1; } } diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c index 34185488e4f..249d2d3c034 100644 --- a/arch/x86/kernel/genapic_flat_64.c +++ b/arch/x86/kernel/genapic_flat_64.c @@ -19,7 +19,6 @@ #include <asm/smp.h> #include <asm/ipi.h> #include <asm/genapic.h> -#include <mach_apicdef.h> #ifdef CONFIG_ACPI #include <acpi/acpi_bus.h> @@ -74,7 +73,7 @@ static inline void _flat_send_IPI_mask(unsigned long mask, int vector) unsigned long flags; local_irq_save(flags); - __send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL); + __default_send_IPI_dest_field(mask, vector, apic->dest_logical); local_irq_restore(flags); } @@ -85,14 +84,15 @@ static void flat_send_IPI_mask(const struct cpumask *cpumask, int vector) _flat_send_IPI_mask(mask, vector); } -static void flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, - int vector) +static void + flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { unsigned long mask = cpumask_bits(cpumask)[0]; int cpu = smp_processor_id(); if (cpu < BITS_PER_LONG) clear_bit(cpu, &mask); + _flat_send_IPI_mask(mask, vector); } @@ -114,23 +114,27 @@ static void flat_send_IPI_allbutself(int vector) _flat_send_IPI_mask(mask, vector); } } else if (num_online_cpus() > 1) { - __send_IPI_shortcut(APIC_DEST_ALLBUT, vector,APIC_DEST_LOGICAL); + __default_send_IPI_shortcut(APIC_DEST_ALLBUT, + vector, apic->dest_logical); } } static void flat_send_IPI_all(int vector) { - if (vector == NMI_VECTOR) + if (vector == NMI_VECTOR) { flat_send_IPI_mask(cpu_online_mask, vector); - else - __send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL); + } else { + __default_send_IPI_shortcut(APIC_DEST_ALLINC, + vector, apic->dest_logical); + } } -static unsigned int get_apic_id(unsigned long x) +static unsigned int flat_get_apic_id(unsigned long x) { unsigned int id; id = (((x)>>24) & 0xFFu); + return id; } @@ -146,7 +150,7 @@ static unsigned int read_xapic_id(void) { unsigned int id; - id = get_apic_id(apic_read(APIC_ID)); + id = flat_get_apic_id(apic_read(APIC_ID)); return id; } @@ -169,31 +173,62 @@ static unsigned int flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, return mask1 & mask2; } -static unsigned int phys_pkg_id(int index_msb) +static int flat_phys_pkg_id(int initial_apic_id, int index_msb) { return hard_smp_processor_id() >> index_msb; } struct genapic apic_flat = { - .name = "flat", - .acpi_madt_oem_check = flat_acpi_madt_oem_check, - .int_delivery_mode = dest_LowestPrio, - .int_dest_mode = (APIC_DEST_LOGICAL != 0), - .target_cpus = flat_target_cpus, - .vector_allocation_domain = flat_vector_allocation_domain, - .apic_id_registered = flat_apic_id_registered, - .init_apic_ldr = flat_init_apic_ldr, - .send_IPI_all = flat_send_IPI_all, - .send_IPI_allbutself = flat_send_IPI_allbutself, - .send_IPI_mask = flat_send_IPI_mask, - .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, - .send_IPI_self = apic_send_IPI_self, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, - .phys_pkg_id = phys_pkg_id, - .get_apic_id = get_apic_id, - .set_apic_id = set_apic_id, - .apic_id_mask = (0xFFu<<24), + .name = "flat", + .probe = NULL, + .acpi_madt_oem_check = flat_acpi_madt_oem_check, + .apic_id_registered = flat_apic_id_registered, + + .irq_delivery_mode = dest_LowestPrio, + .irq_dest_mode = 1, /* logical */ + + .target_cpus = flat_target_cpus, + .disable_esr = 0, + .dest_logical = APIC_DEST_LOGICAL, + .check_apicid_used = NULL, + .check_apicid_present = NULL, + + .vector_allocation_domain = flat_vector_allocation_domain, + .init_apic_ldr = flat_init_apic_ldr, + + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .multi_timer_check = NULL, + .apicid_to_node = NULL, + .cpu_to_logical_apicid = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .setup_portio_remap = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = flat_phys_pkg_id, + .mps_oem_check = NULL, + + .get_apic_id = flat_get_apic_id, + .set_apic_id = set_apic_id, + .apic_id_mask = 0xFFu << 24, + + .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + + .send_IPI_mask = flat_send_IPI_mask, + .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, + .send_IPI_allbutself = flat_send_IPI_allbutself, + .send_IPI_all = flat_send_IPI_all, + .send_IPI_self = apic_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + .wait_for_init_deassert = NULL, + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = NULL, }; /* @@ -232,18 +267,18 @@ static void physflat_vector_allocation_domain(int cpu, struct cpumask *retmask) static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector) { - send_IPI_mask_sequence(cpumask, vector); + default_send_IPI_mask_sequence_phys(cpumask, vector); } static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { - send_IPI_mask_allbutself(cpumask, vector); + default_send_IPI_mask_allbutself_phys(cpumask, vector); } static void physflat_send_IPI_allbutself(int vector) { - send_IPI_mask_allbutself(cpu_online_mask, vector); + default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); } static void physflat_send_IPI_all(int vector) @@ -276,32 +311,67 @@ physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, * We're using fixed IRQ delivery, can only return one phys APIC ID. * May as well be the first. */ - for_each_cpu_and(cpu, cpumask, andmask) + for_each_cpu_and(cpu, cpumask, andmask) { if (cpumask_test_cpu(cpu, cpu_online_mask)) break; + } if (cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_apicid, cpu); + return BAD_APICID; } struct genapic apic_physflat = { - .name = "physical flat", - .acpi_madt_oem_check = physflat_acpi_madt_oem_check, - .int_delivery_mode = dest_Fixed, - .int_dest_mode = (APIC_DEST_PHYSICAL != 0), - .target_cpus = physflat_target_cpus, - .vector_allocation_domain = physflat_vector_allocation_domain, - .apic_id_registered = flat_apic_id_registered, - .init_apic_ldr = flat_init_apic_ldr,/*not needed, but shouldn't hurt*/ - .send_IPI_all = physflat_send_IPI_all, - .send_IPI_allbutself = physflat_send_IPI_allbutself, - .send_IPI_mask = physflat_send_IPI_mask, - .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, - .send_IPI_self = apic_send_IPI_self, - .cpu_mask_to_apicid = physflat_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = physflat_cpu_mask_to_apicid_and, - .phys_pkg_id = phys_pkg_id, - .get_apic_id = get_apic_id, - .set_apic_id = set_apic_id, - .apic_id_mask = (0xFFu<<24), + + .name = "physical flat", + .probe = NULL, + .acpi_madt_oem_check = physflat_acpi_madt_oem_check, + .apic_id_registered = flat_apic_id_registered, + + .irq_delivery_mode = dest_Fixed, + .irq_dest_mode = 0, /* physical */ + + .target_cpus = physflat_target_cpus, + .disable_esr = 0, + .dest_logical = 0, + .check_apicid_used = NULL, + .check_apicid_present = NULL, + + .vector_allocation_domain = physflat_vector_allocation_domain, + /* not needed, but shouldn't hurt: */ + .init_apic_ldr = flat_init_apic_ldr, + + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .multi_timer_check = NULL, + .apicid_to_node = NULL, + .cpu_to_logical_apicid = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .setup_portio_remap = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = flat_phys_pkg_id, + .mps_oem_check = NULL, + + .get_apic_id = flat_get_apic_id, + .set_apic_id = set_apic_id, + .apic_id_mask = 0xFFu << 24, + + .cpu_mask_to_apicid = physflat_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = physflat_cpu_mask_to_apicid_and, + + .send_IPI_mask = physflat_send_IPI_mask, + .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, + .send_IPI_allbutself = physflat_send_IPI_allbutself, + .send_IPI_all = physflat_send_IPI_all, + .send_IPI_self = apic_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + .wait_for_init_deassert = NULL, + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = NULL, }; diff --git a/arch/x86/kernel/genx2apic_cluster.c b/arch/x86/kernel/genx2apic_cluster.c index 6ce497cc372..7c87156b641 100644 --- a/arch/x86/kernel/genx2apic_cluster.c +++ b/arch/x86/kernel/genx2apic_cluster.c @@ -36,8 +36,8 @@ static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask) cpumask_set_cpu(cpu, retmask); } -static void __x2apic_send_IPI_dest(unsigned int apicid, int vector, - unsigned int dest) +static void + __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest) { unsigned long cfg; @@ -57,45 +57,50 @@ static void __x2apic_send_IPI_dest(unsigned int apicid, int vector, */ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) { - unsigned long flags; unsigned long query_cpu; + unsigned long flags; local_irq_save(flags); - for_each_cpu(query_cpu, mask) + for_each_cpu(query_cpu, mask) { __x2apic_send_IPI_dest( per_cpu(x86_cpu_to_logical_apicid, query_cpu), - vector, APIC_DEST_LOGICAL); + vector, apic->dest_logical); + } local_irq_restore(flags); } -static void x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, - int vector) +static void + x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) { - unsigned long flags; - unsigned long query_cpu; unsigned long this_cpu = smp_processor_id(); + unsigned long query_cpu; + unsigned long flags; local_irq_save(flags); - for_each_cpu(query_cpu, mask) - if (query_cpu != this_cpu) - __x2apic_send_IPI_dest( + for_each_cpu(query_cpu, mask) { + if (query_cpu == this_cpu) + continue; + __x2apic_send_IPI_dest( per_cpu(x86_cpu_to_logical_apicid, query_cpu), - vector, APIC_DEST_LOGICAL); + vector, apic->dest_logical); + } local_irq_restore(flags); } static void x2apic_send_IPI_allbutself(int vector) { - unsigned long flags; - unsigned long query_cpu; unsigned long this_cpu = smp_processor_id(); + unsigned long query_cpu; + unsigned long flags; local_irq_save(flags); - for_each_online_cpu(query_cpu) - if (query_cpu != this_cpu) - __x2apic_send_IPI_dest( + for_each_online_cpu(query_cpu) { + if (query_cpu == this_cpu) + continue; + __x2apic_send_IPI_dest( per_cpu(x86_cpu_to_logical_apicid, query_cpu), - vector, APIC_DEST_LOGICAL); + vector, apic->dest_logical); + } local_irq_restore(flags); } @@ -111,21 +116,21 @@ static int x2apic_apic_id_registered(void) static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask) { - int cpu; - /* * We're using fixed IRQ delivery, can only return one logical APIC ID. * May as well be the first. */ - cpu = cpumask_first(cpumask); + int cpu = cpumask_first(cpumask); + if ((unsigned)cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_logical_apicid, cpu); else return BAD_APICID; } -static unsigned int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) +static unsigned int +x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask) { int cpu; @@ -133,15 +138,18 @@ static unsigned int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, * We're using fixed IRQ delivery, can only return one logical APIC ID. * May as well be the first. */ - for_each_cpu_and(cpu, cpumask, andmask) + for_each_cpu_and(cpu, cpumask, andmask) { if (cpumask_test_cpu(cpu, cpu_online_mask)) break; + } + if (cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_logical_apicid, cpu); + return BAD_APICID; } -static unsigned int get_apic_id(unsigned long x) +static unsigned int x2apic_cluster_phys_get_apic_id(unsigned long x) { unsigned int id; @@ -157,7 +165,7 @@ static unsigned long set_apic_id(unsigned int id) return x; } -static unsigned int phys_pkg_id(int index_msb) +static int x2apic_cluster_phys_pkg_id(int initial_apicid, int index_msb) { return current_cpu_data.initial_apicid >> index_msb; } @@ -172,27 +180,58 @@ static void init_x2apic_ldr(void) int cpu = smp_processor_id(); per_cpu(x86_cpu_to_logical_apicid, cpu) = apic_read(APIC_LDR); - return; } struct genapic apic_x2apic_cluster = { - .name = "cluster x2apic", - .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, - .int_delivery_mode = dest_LowestPrio, - .int_dest_mode = (APIC_DEST_LOGICAL != 0), - .target_cpus = x2apic_target_cpus, - .vector_allocation_domain = x2apic_vector_allocation_domain, - .apic_id_registered = x2apic_apic_id_registered, - .init_apic_ldr = init_x2apic_ldr, - .send_IPI_all = x2apic_send_IPI_all, - .send_IPI_allbutself = x2apic_send_IPI_allbutself, - .send_IPI_mask = x2apic_send_IPI_mask, - .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, - .send_IPI_self = x2apic_send_IPI_self, - .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, - .phys_pkg_id = phys_pkg_id, - .get_apic_id = get_apic_id, - .set_apic_id = set_apic_id, - .apic_id_mask = (0xFFFFFFFFu), + + .name = "cluster x2apic", + .probe = NULL, + .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, + .apic_id_registered = x2apic_apic_id_registered, + + .irq_delivery_mode = dest_LowestPrio, + .irq_dest_mode = 1, /* logical */ + + .target_cpus = x2apic_target_cpus, + .disable_esr = 0, + .dest_logical = APIC_DEST_LOGICAL, + .check_apicid_used = NULL, + .check_apicid_present = NULL, + + .vector_allocation_domain = x2apic_vector_allocation_domain, + .init_apic_ldr = init_x2apic_ldr, + + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .multi_timer_check = NULL, + .apicid_to_node = NULL, + .cpu_to_logical_apicid = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .setup_portio_remap = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = x2apic_cluster_phys_pkg_id, + .mps_oem_check = NULL, + + .get_apic_id = x2apic_cluster_phys_get_apic_id, + .set_apic_id = set_apic_id, + .apic_id_mask = 0xFFFFFFFFu, + + .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + + .send_IPI_mask = x2apic_send_IPI_mask, + .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, + .send_IPI_allbutself = x2apic_send_IPI_allbutself, + .send_IPI_all = x2apic_send_IPI_all, + .send_IPI_self = x2apic_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + .wait_for_init_deassert = NULL, + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = NULL, }; diff --git a/arch/x86/kernel/genx2apic_phys.c b/arch/x86/kernel/genx2apic_phys.c index 21bcc0e098b..5cbae8aa040 100644 --- a/arch/x86/kernel/genx2apic_phys.c +++ b/arch/x86/kernel/genx2apic_phys.c @@ -55,8 +55,8 @@ static void __x2apic_send_IPI_dest(unsigned int apicid, int vector, static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) { - unsigned long flags; unsigned long query_cpu; + unsigned long flags; local_irq_save(flags); for_each_cpu(query_cpu, mask) { @@ -66,12 +66,12 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) local_irq_restore(flags); } -static void x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, - int vector) +static void + x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) { - unsigned long flags; - unsigned long query_cpu; unsigned long this_cpu = smp_processor_id(); + unsigned long query_cpu; + unsigned long flags; local_irq_save(flags); for_each_cpu(query_cpu, mask) { @@ -85,16 +85,17 @@ static void x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, static void x2apic_send_IPI_allbutself(int vector) { - unsigned long flags; - unsigned long query_cpu; unsigned long this_cpu = smp_processor_id(); + unsigned long query_cpu; + unsigned long flags; local_irq_save(flags); - for_each_online_cpu(query_cpu) - if (query_cpu != this_cpu) - __x2apic_send_IPI_dest( - per_cpu(x86_cpu_to_apicid, query_cpu), - vector, APIC_DEST_PHYSICAL); + for_each_online_cpu(query_cpu) { + if (query_cpu == this_cpu) + continue; + __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu), + vector, APIC_DEST_PHYSICAL); + } local_irq_restore(flags); } @@ -110,21 +111,21 @@ static int x2apic_apic_id_registered(void) static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask) { - int cpu; - /* * We're using fixed IRQ delivery, can only return one phys APIC ID. * May as well be the first. */ - cpu = cpumask_first(cpumask); + int cpu = cpumask_first(cpumask); + if ((unsigned)cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_apicid, cpu); else return BAD_APICID; } -static unsigned int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) +static unsigned int +x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask) { int cpu; @@ -132,31 +133,28 @@ static unsigned int x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, * We're using fixed IRQ delivery, can only return one phys APIC ID. * May as well be the first. */ - for_each_cpu_and(cpu, cpumask, andmask) + for_each_cpu_and(cpu, cpumask, andmask) { if (cpumask_test_cpu(cpu, cpu_online_mask)) break; + } + if (cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_apicid, cpu); + return BAD_APICID; } -static unsigned int get_apic_id(unsigned long x) +static unsigned int x2apic_phys_get_apic_id(unsigned long x) { - unsigned int id; - - id = x; - return id; + return x; } static unsigned long set_apic_id(unsigned int id) { - unsigned long x; - - x = id; - return x; + return id; } -static unsigned int phys_pkg_id(int index_msb) +static int x2apic_phys_pkg_id(int initial_apicid, int index_msb) { return current_cpu_data.initial_apicid >> index_msb; } @@ -168,27 +166,58 @@ static void x2apic_send_IPI_self(int vector) static void init_x2apic_ldr(void) { - return; } struct genapic apic_x2apic_phys = { - .name = "physical x2apic", - .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, - .int_delivery_mode = dest_Fixed, - .int_dest_mode = (APIC_DEST_PHYSICAL != 0), - .target_cpus = x2apic_target_cpus, - .vector_allocation_domain = x2apic_vector_allocation_domain, - .apic_id_registered = x2apic_apic_id_registered, - .init_apic_ldr = init_x2apic_ldr, - .send_IPI_all = x2apic_send_IPI_all, - .send_IPI_allbutself = x2apic_send_IPI_allbutself, - .send_IPI_mask = x2apic_send_IPI_mask, - .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, - .send_IPI_self = x2apic_send_IPI_self, - .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, - .phys_pkg_id = phys_pkg_id, - .get_apic_id = get_apic_id, - .set_apic_id = set_apic_id, - .apic_id_mask = (0xFFFFFFFFu), + + .name = "physical x2apic", + .probe = NULL, + .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, + .apic_id_registered = x2apic_apic_id_registered, + + .irq_delivery_mode = dest_Fixed, + .irq_dest_mode = 0, /* physical */ + + .target_cpus = x2apic_target_cpus, + .disable_esr = 0, + .dest_logical = 0, + .check_apicid_used = NULL, + .check_apicid_present = NULL, + + .vector_allocation_domain = x2apic_vector_allocation_domain, + .init_apic_ldr = init_x2apic_ldr, + + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .multi_timer_check = NULL, + .apicid_to_node = NULL, + .cpu_to_logical_apicid = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .setup_portio_remap = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = x2apic_phys_pkg_id, + .mps_oem_check = NULL, + + .get_apic_id = x2apic_phys_get_apic_id, + .set_apic_id = set_apic_id, + .apic_id_mask = 0xFFFFFFFFu, + + .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + + .send_IPI_mask = x2apic_send_IPI_mask, + .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, + .send_IPI_allbutself = x2apic_send_IPI_allbutself, + .send_IPI_all = x2apic_send_IPI_all, + .send_IPI_self = x2apic_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + .wait_for_init_deassert = NULL, + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = NULL, }; diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c index b193e082f6c..6adb5e6f4d9 100644 --- a/arch/x86/kernel/genx2apic_uv_x.c +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -25,6 +25,7 @@ #include <asm/ipi.h> #include <asm/genapic.h> #include <asm/pgtable.h> +#include <asm/uv/uv.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> #include <asm/uv/bios.h> @@ -117,12 +118,13 @@ static void uv_send_IPI_one(int cpu, int vector) int pnode; apicid = per_cpu(x86_cpu_to_apicid, cpu); - lapicid = apicid & 0x3f; /* ZZZ macro needed */ + lapicid = apicid & 0x3f; /* ZZZ macro needed */ pnode = uv_apicid_to_pnode(apicid); - val = - (1UL << UVH_IPI_INT_SEND_SHFT) | (lapicid << - UVH_IPI_INT_APIC_ID_SHFT) | - (vector << UVH_IPI_INT_VECTOR_SHFT); + + val = ( 1UL << UVH_IPI_INT_SEND_SHFT ) | + ( lapicid << UVH_IPI_INT_APIC_ID_SHFT ) | + ( vector << UVH_IPI_INT_VECTOR_SHFT ); + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); } @@ -136,22 +138,24 @@ static void uv_send_IPI_mask(const struct cpumask *mask, int vector) static void uv_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) { - unsigned int cpu; unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; - for_each_cpu(cpu, mask) + for_each_cpu(cpu, mask) { if (cpu != this_cpu) uv_send_IPI_one(cpu, vector); + } } static void uv_send_IPI_allbutself(int vector) { - unsigned int cpu; unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; - for_each_online_cpu(cpu) + for_each_online_cpu(cpu) { if (cpu != this_cpu) uv_send_IPI_one(cpu, vector); + } } static void uv_send_IPI_all(int vector) @@ -170,21 +174,21 @@ static void uv_init_apic_ldr(void) static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask) { - int cpu; - /* * We're using fixed IRQ delivery, can only return one phys APIC ID. * May as well be the first. */ - cpu = cpumask_first(cpumask); + int cpu = cpumask_first(cpumask); + if ((unsigned)cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_apicid, cpu); else return BAD_APICID; } -static unsigned int uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) +static unsigned int +uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask) { int cpu; @@ -192,15 +196,17 @@ static unsigned int uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, * We're using fixed IRQ delivery, can only return one phys APIC ID. * May as well be the first. */ - for_each_cpu_and(cpu, cpumask, andmask) + for_each_cpu_and(cpu, cpumask, andmask) { if (cpumask_test_cpu(cpu, cpu_online_mask)) break; + } if (cpu < nr_cpu_ids) return per_cpu(x86_cpu_to_apicid, cpu); + return BAD_APICID; } -static unsigned int get_apic_id(unsigned long x) +static unsigned int x2apic_get_apic_id(unsigned long x) { unsigned int id; @@ -222,10 +228,10 @@ static unsigned long set_apic_id(unsigned int id) static unsigned int uv_read_apic_id(void) { - return get_apic_id(apic_read(APIC_ID)); + return x2apic_get_apic_id(apic_read(APIC_ID)); } -static unsigned int phys_pkg_id(int index_msb) +static int uv_phys_pkg_id(int initial_apicid, int index_msb) { return uv_read_apic_id() >> index_msb; } @@ -236,25 +242,57 @@ static void uv_send_IPI_self(int vector) } struct genapic apic_x2apic_uv_x = { - .name = "UV large system", - .acpi_madt_oem_check = uv_acpi_madt_oem_check, - .int_delivery_mode = dest_Fixed, - .int_dest_mode = (APIC_DEST_PHYSICAL != 0), - .target_cpus = uv_target_cpus, - .vector_allocation_domain = uv_vector_allocation_domain, - .apic_id_registered = uv_apic_id_registered, - .init_apic_ldr = uv_init_apic_ldr, - .send_IPI_all = uv_send_IPI_all, - .send_IPI_allbutself = uv_send_IPI_allbutself, - .send_IPI_mask = uv_send_IPI_mask, - .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself, - .send_IPI_self = uv_send_IPI_self, - .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, - .phys_pkg_id = phys_pkg_id, - .get_apic_id = get_apic_id, - .set_apic_id = set_apic_id, - .apic_id_mask = (0xFFFFFFFFu), + + .name = "UV large system", + .probe = NULL, + .acpi_madt_oem_check = uv_acpi_madt_oem_check, + .apic_id_registered = uv_apic_id_registered, + + .irq_delivery_mode = dest_Fixed, + .irq_dest_mode = 1, /* logical */ + + .target_cpus = uv_target_cpus, + .disable_esr = 0, + .dest_logical = APIC_DEST_LOGICAL, + .check_apicid_used = NULL, + .check_apicid_present = NULL, + + .vector_allocation_domain = uv_vector_allocation_domain, + .init_apic_ldr = uv_init_apic_ldr, + + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .multi_timer_check = NULL, + .apicid_to_node = NULL, + .cpu_to_logical_apicid = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .setup_portio_remap = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = uv_phys_pkg_id, + .mps_oem_check = NULL, + + .get_apic_id = x2apic_get_apic_id, + .set_apic_id = set_apic_id, + .apic_id_mask = 0xFFFFFFFFu, + + .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, + + .send_IPI_mask = uv_send_IPI_mask, + .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself, + .send_IPI_allbutself = uv_send_IPI_allbutself, + .send_IPI_all = uv_send_IPI_all, + .send_IPI_self = uv_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + .wait_for_init_deassert = NULL, + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = NULL, }; static __cpuinit void set_x2apic_extra_bits(int pnode) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index b9a4d8c4b93..f5b27224769 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -26,27 +26,6 @@ #include <asm/bios_ebda.h> #include <asm/trampoline.h> -/* boot cpu pda */ -static struct x8664_pda _boot_cpu_pda; - -#ifdef CONFIG_SMP -/* - * We install an empty cpu_pda pointer table to indicate to early users - * (numa_set_node) that the cpu_pda pointer table for cpus other than - * the boot cpu is not yet setup. - */ -static struct x8664_pda *__cpu_pda[NR_CPUS] __initdata; -#else -static struct x8664_pda *__cpu_pda[NR_CPUS] __read_mostly; -#endif - -void __init x86_64_init_pda(void) -{ - _cpu_pda = __cpu_pda; - cpu_pda(0) = &_boot_cpu_pda; - pda_init(0); -} - static void __init zap_identity_mappings(void) { pgd_t *pgd = pgd_offset_k(0UL); @@ -112,8 +91,6 @@ void __init x86_64_start_kernel(char * real_mode_data) if (console_loglevel == 10) early_printk("Kernel alive\n"); - x86_64_init_pda(); - x86_64_start_reservations(real_mode_data); } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index e835b4eea70..2a0aad7718d 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -19,6 +19,7 @@ #include <asm/asm-offsets.h> #include <asm/setup.h> #include <asm/processor-flags.h> +#include <asm/percpu.h> /* Physical address */ #define pa(X) ((X) - __PAGE_OFFSET) @@ -429,14 +430,34 @@ is386: movl $2,%ecx # set MP ljmp $(__KERNEL_CS),$1f 1: movl $(__KERNEL_DS),%eax # reload all the segment registers movl %eax,%ss # after changing gdt. - movl %eax,%fs # gets reset once there's real percpu movl $(__USER_DS),%eax # DS/ES contains default USER segment movl %eax,%ds movl %eax,%es - xorl %eax,%eax # Clear GS and LDT + movl $(__KERNEL_PERCPU), %eax + movl %eax,%fs # set this cpu's percpu + +#ifdef CONFIG_CC_STACKPROTECTOR + /* + * The linker can't handle this by relocation. Manually set + * base address in stack canary segment descriptor. + */ + cmpb $0,ready + jne 1f + movl $per_cpu__gdt_page,%eax + movl $per_cpu__stack_canary,%ecx + subl $20, %ecx + movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax) + shrl $16, %ecx + movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax) + movb %ch, 8 * GDT_ENTRY_STACK_CANARY + 7(%eax) +1: +#endif + movl $(__KERNEL_STACK_CANARY),%eax movl %eax,%gs + + xorl %eax,%eax # Clear LDT lldt %ax cld # gcc2 wants the direction flag cleared at all times @@ -446,8 +467,6 @@ is386: movl $2,%ecx # set MP movb $1, ready cmpb $0,%cl # the first CPU calls start_kernel je 1f - movl $(__KERNEL_PERCPU), %eax - movl %eax,%fs # set this cpu's percpu movl (stack_start), %esp 1: #endif /* CONFIG_SMP */ @@ -548,12 +567,8 @@ early_fault: pushl %eax pushl %edx /* trapno */ pushl $fault_msg -#ifdef CONFIG_EARLY_PRINTK - call early_printk -#else call printk #endif -#endif call dump_stack hlt_loop: hlt @@ -580,11 +595,10 @@ ignore_int: pushl 32(%esp) pushl 40(%esp) pushl $int_msg -#ifdef CONFIG_EARLY_PRINTK - call early_printk -#else call printk -#endif + + call dump_stack + addl $(5*4),%esp popl %ds popl %es @@ -660,7 +674,7 @@ early_recursion_flag: .long 0 int_msg: - .asciz "Unknown interrupt or fault at EIP %p %p %p\n" + .asciz "Unknown interrupt or fault at: %p %p %p\n" fault_msg: /* fault info: */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 0e275d49556..2e648e3a5ea 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -19,6 +19,7 @@ #include <asm/msr.h> #include <asm/cache.h> #include <asm/processor-flags.h> +#include <asm/percpu.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -226,12 +227,15 @@ ENTRY(secondary_startup_64) movl %eax,%fs movl %eax,%gs - /* - * Setup up a dummy PDA. this is just for some early bootup code - * that does in_interrupt() - */ + /* Set up %gs. + * + * The base of %gs always points to the bottom of the irqstack + * union. If the stack protector canary is enabled, it is + * located at %gs:40. Note that, on SMP, the boot cpu uses + * init data section till per cpu areas are set up. + */ movl $MSR_GS_BASE,%ecx - movq $empty_zero_page,%rax + movq initial_gs(%rip),%rax movq %rax,%rdx shrq $32,%rdx wrmsr @@ -257,6 +261,8 @@ ENTRY(secondary_startup_64) .align 8 ENTRY(initial_code) .quad x86_64_start_kernel + ENTRY(initial_gs) + .quad INIT_PER_CPU_VAR(irq_stack_union) __FINITDATA ENTRY(stack_start) @@ -401,7 +407,8 @@ NEXT_PAGE(level2_spare_pgt) .globl early_gdt_descr early_gdt_descr: .word GDT_ENTRIES*8-1 - .quad per_cpu__gdt_page +early_gdt_descr_base: + .quad INIT_PER_CPU_VAR(gdt_page) ENTRY(phys_base) /* This must match the first entry in level2_kernel_pgt */ diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 64d5ad0b8ad..388254f69a2 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -897,7 +897,7 @@ static unsigned long hpet_rtc_flags; static int hpet_prev_update_sec; static struct rtc_time hpet_alarm_time; static unsigned long hpet_pie_count; -static unsigned long hpet_t1_cmp; +static u32 hpet_t1_cmp; static unsigned long hpet_default_delta; static unsigned long hpet_pie_delta; static unsigned long hpet_pie_limit; @@ -905,6 +905,14 @@ static unsigned long hpet_pie_limit; static rtc_irq_handler irq_handler; /* + * Check that the hpet counter c1 is ahead of the c2 + */ +static inline int hpet_cnt_ahead(u32 c1, u32 c2) +{ + return (s32)(c2 - c1) < 0; +} + +/* * Registers a IRQ handler. */ int hpet_register_irq_handler(rtc_irq_handler handler) @@ -1075,7 +1083,7 @@ static void hpet_rtc_timer_reinit(void) hpet_t1_cmp += delta; hpet_writel(hpet_t1_cmp, HPET_T1_CMP); lost_ints++; - } while ((long)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0); + } while (!hpet_cnt_ahead(hpet_t1_cmp, hpet_readl(HPET_COUNTER))); if (lost_ints) { if (hpet_rtc_flags & RTC_PIE) diff --git a/arch/x86/kernel/i8237.c b/arch/x86/kernel/i8237.c index dbd6c1d1b63..b42ca694dc6 100644 --- a/arch/x86/kernel/i8237.c +++ b/arch/x86/kernel/i8237.c @@ -28,10 +28,10 @@ static int i8237A_resume(struct sys_device *dev) flags = claim_dma_lock(); - dma_outb(DMA1_RESET_REG, 0); - dma_outb(DMA2_RESET_REG, 0); + dma_outb(0, DMA1_RESET_REG); + dma_outb(0, DMA2_RESET_REG); - for (i = 0;i < 8;i++) { + for (i = 0; i < 8; i++) { set_dma_addr(i, 0x000000); /* DMA count is a bit weird so this is not 0 */ set_dma_count(i, 1); @@ -51,14 +51,14 @@ static int i8237A_suspend(struct sys_device *dev, pm_message_t state) } static struct sysdev_class i8237_sysdev_class = { - .name = "i8237", - .suspend = i8237A_suspend, - .resume = i8237A_resume, + .name = "i8237", + .suspend = i8237A_suspend, + .resume = i8237A_resume, }; static struct sys_device device_i8237A = { - .id = 0, - .cls = &i8237_sysdev_class, + .id = 0, + .cls = &i8237_sysdev_class, }; static int __init i8237A_init_sysfs(void) @@ -68,5 +68,4 @@ static int __init i8237A_init_sysfs(void) error = sysdev_register(&device_i8237A); return error; } - device_initcall(i8237A_init_sysfs); diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index 1c6fc33c1cb..7248ca11bdc 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -1,7 +1,7 @@ /* * Intel IO-APIC support for multi-Pentium hosts. * - * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo + * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * * Many thanks to Stig Venaas for trying out countless experimental * patches and reporting/debugging problems patiently! @@ -62,9 +62,7 @@ #include <asm/uv/uv_hub.h> #include <asm/uv/uv_irq.h> -#include <mach_ipi.h> -#include <mach_apic.h> -#include <mach_apicdef.h> +#include <asm/genapic.h> #define __apicdebuginit(type) static type __init @@ -100,10 +98,19 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); int skip_ioapic_setup; +void arch_disable_smp_support(void) +{ +#ifdef CONFIG_PCI + noioapicquirk = 1; + noioapicreroute = -1; +#endif + skip_ioapic_setup = 1; +} + static int __init parse_noapic(char *str) { /* disable IO-APIC */ - disable_ioapic_setup(); + arch_disable_smp_support(); return 0; } early_param("noapic", parse_noapic); @@ -357,7 +364,7 @@ set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask) if (!cfg->move_in_progress) { /* it means that domain is not changed */ - if (!cpumask_intersects(&desc->affinity, mask)) + if (!cpumask_intersects(desc->affinity, mask)) cfg->move_desc_pending = 1; } } @@ -479,7 +486,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) io_apic_write(apic, 0x10 + 2*pin, eu.w1); } -static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) +void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) { unsigned long flags; spin_lock_irqsave(&ioapic_lock, flags); @@ -514,11 +521,11 @@ static void send_cleanup_vector(struct irq_cfg *cfg) for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) cfg->move_cleanup_count++; for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) - send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR); + apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR); } else { cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask); cfg->move_cleanup_count = cpumask_weight(cleanup_mask); - send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); + apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); free_cpumask_var(cleanup_mask); } cfg->move_in_progress = 0; @@ -563,8 +570,9 @@ static int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask); /* - * Either sets desc->affinity to a valid value, and returns cpu_mask_to_apicid - * of that, or returns BAD_APICID and leaves desc->affinity untouched. + * Either sets desc->affinity to a valid value, and returns + * ->cpu_mask_to_apicid of that, or returns BAD_APICID and + * leaves desc->affinity untouched. */ static unsigned int set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask) @@ -580,9 +588,10 @@ set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask) if (assign_irq_vector(irq, cfg, mask)) return BAD_APICID; - cpumask_and(&desc->affinity, cfg->domain, mask); + cpumask_and(desc->affinity, cfg->domain, mask); set_extra_move_desc(desc, mask); - return cpu_mask_to_apicid_and(&desc->affinity, cpu_online_mask); + + return apic->cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask); } static void @@ -797,23 +806,6 @@ static void clear_IO_APIC (void) clear_IO_APIC_pin(apic, pin); } -#if !defined(CONFIG_SMP) && defined(CONFIG_X86_32) -void send_IPI_self(int vector) -{ - unsigned int cfg; - - /* - * Wait for idle. - */ - apic_wait_icr_idle(); - cfg = APIC_DM_FIXED | APIC_DEST_SELF | vector | APIC_DEST_LOGICAL; - /* - * Send the IPI. The write to APIC_ICR fires this off. - */ - apic_write(APIC_ICR, cfg); -} -#endif /* !CONFIG_SMP && CONFIG_X86_32*/ - #ifdef CONFIG_X86_32 /* * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to @@ -1316,7 +1308,7 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) int new_cpu; int vector, offset; - vector_allocation_domain(cpu, tmp_mask); + apic->vector_allocation_domain(cpu, tmp_mask); vector = current_vector; offset = current_offset; @@ -1486,10 +1478,10 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t handle_edge_irq, "edge"); } -static int setup_ioapic_entry(int apic, int irq, - struct IO_APIC_route_entry *entry, - unsigned int destination, int trigger, - int polarity, int vector) +int setup_ioapic_entry(int apic_id, int irq, + struct IO_APIC_route_entry *entry, + unsigned int destination, int trigger, + int polarity, int vector) { /* * add it to the IO-APIC irq-routing table: @@ -1498,25 +1490,25 @@ static int setup_ioapic_entry(int apic, int irq, #ifdef CONFIG_INTR_REMAP if (intr_remapping_enabled) { - struct intel_iommu *iommu = map_ioapic_to_ir(apic); + struct intel_iommu *iommu = map_ioapic_to_ir(apic_id); struct irte irte; struct IR_IO_APIC_route_entry *ir_entry = (struct IR_IO_APIC_route_entry *) entry; int index; if (!iommu) - panic("No mapping iommu for ioapic %d\n", apic); + panic("No mapping iommu for ioapic %d\n", apic_id); index = alloc_irte(iommu, irq, 1); if (index < 0) - panic("Failed to allocate IRTE for ioapic %d\n", apic); + panic("Failed to allocate IRTE for ioapic %d\n", apic_id); memset(&irte, 0, sizeof(irte)); irte.present = 1; - irte.dst_mode = INT_DEST_MODE; + irte.dst_mode = apic->irq_dest_mode; irte.trigger_mode = trigger; - irte.dlvry_mode = INT_DELIVERY_MODE; + irte.dlvry_mode = apic->irq_delivery_mode; irte.vector = vector; irte.dest_id = IRTE_DEST(destination); @@ -1529,8 +1521,8 @@ static int setup_ioapic_entry(int apic, int irq, } else #endif { - entry->delivery_mode = INT_DELIVERY_MODE; - entry->dest_mode = INT_DEST_MODE; + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; entry->dest = destination; } @@ -1547,7 +1539,7 @@ static int setup_ioapic_entry(int apic, int irq, return 0; } -static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, struct irq_desc *desc, +static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq_desc *desc, int trigger, int polarity) { struct irq_cfg *cfg; @@ -1559,22 +1551,22 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, struct irq_de cfg = desc->chip_data; - if (assign_irq_vector(irq, cfg, TARGET_CPUS)) + if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; - dest = cpu_mask_to_apicid_and(cfg->domain, TARGET_CPUS); + dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " "IRQ %d Mode:%i Active:%i)\n", - apic, mp_ioapics[apic].apicid, pin, cfg->vector, + apic_id, mp_ioapics[apic_id].apicid, pin, cfg->vector, irq, trigger, polarity); - if (setup_ioapic_entry(mp_ioapics[apic].apicid, irq, &entry, + if (setup_ioapic_entry(mp_ioapics[apic_id].apicid, irq, &entry, dest, trigger, polarity, cfg->vector)) { printk("Failed to setup ioapic entry for ioapic %d, pin %d\n", - mp_ioapics[apic].apicid, pin); + mp_ioapics[apic_id].apicid, pin); __clear_irq_vector(irq, cfg); return; } @@ -1583,12 +1575,12 @@ static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, struct irq_de if (irq < NR_IRQS_LEGACY) disable_8259A_irq(irq); - ioapic_write_entry(apic, pin, entry); + ioapic_write_entry(apic_id, pin, entry); } static void __init setup_IO_APIC_irqs(void) { - int apic, pin, idx, irq; + int apic_id, pin, idx, irq; int notcon = 0; struct irq_desc *desc; struct irq_cfg *cfg; @@ -1596,19 +1588,19 @@ static void __init setup_IO_APIC_irqs(void) apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); - for (apic = 0; apic < nr_ioapics; apic++) { - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { + for (apic_id = 0; apic_id < nr_ioapics; apic_id++) { + for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) { - idx = find_irq_entry(apic, pin, mp_INT); + idx = find_irq_entry(apic_id, pin, mp_INT); if (idx == -1) { if (!notcon) { notcon = 1; apic_printk(APIC_VERBOSE, KERN_DEBUG " %d-%d", - mp_ioapics[apic].apicid, pin); + mp_ioapics[apic_id].apicid, pin); } else apic_printk(APIC_VERBOSE, " %d-%d", - mp_ioapics[apic].apicid, pin); + mp_ioapics[apic_id].apicid, pin); continue; } if (notcon) { @@ -1617,20 +1609,25 @@ static void __init setup_IO_APIC_irqs(void) notcon = 0; } - irq = pin_2_irq(idx, apic, pin); -#ifdef CONFIG_X86_32 - if (multi_timer_check(apic, irq)) + irq = pin_2_irq(idx, apic_id, pin); + + /* + * Skip the timer IRQ if there's a quirk handler + * installed and if it returns 1: + */ + if (apic->multi_timer_check && + apic->multi_timer_check(apic_id, irq)) continue; -#endif + desc = irq_to_desc_alloc_cpu(irq, cpu); if (!desc) { printk(KERN_INFO "can not get irq_desc for %d\n", irq); continue; } cfg = desc->chip_data; - add_pin_to_irq_cpu(cfg, cpu, apic, pin); + add_pin_to_irq_cpu(cfg, cpu, apic_id, pin); - setup_IO_APIC_irq(apic, pin, irq, desc, + setup_IO_APIC_irq(apic_id, pin, irq, desc, irq_trigger(idx), irq_polarity(idx)); } } @@ -1643,7 +1640,7 @@ static void __init setup_IO_APIC_irqs(void) /* * Set up the timer pin, possibly with the 8259A-master behind. */ -static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin, +static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin, int vector) { struct IO_APIC_route_entry entry; @@ -1659,10 +1656,10 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin, * We use logical delivery to get the timer IRQ * to the first CPU. */ - entry.dest_mode = INT_DEST_MODE; - entry.mask = 1; /* mask IRQ now */ - entry.dest = cpu_mask_to_apicid(TARGET_CPUS); - entry.delivery_mode = INT_DELIVERY_MODE; + entry.dest_mode = apic->irq_dest_mode; + entry.mask = 0; /* don't mask IRQ for edge */ + entry.dest = apic->cpu_mask_to_apicid(apic->target_cpus()); + entry.delivery_mode = apic->irq_delivery_mode; entry.polarity = 0; entry.trigger = 0; entry.vector = vector; @@ -1676,7 +1673,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin, /* * Add it to the IO-APIC irq-routing table: */ - ioapic_write_entry(apic, pin, entry); + ioapic_write_entry(apic_id, pin, entry); } @@ -2089,7 +2086,7 @@ static void __init setup_ioapic_ids_from_mpc(void) { union IO_APIC_reg_00 reg_00; physid_mask_t phys_id_present_map; - int apic; + int apic_id; int i; unsigned char old_id; unsigned long flags; @@ -2108,26 +2105,26 @@ static void __init setup_ioapic_ids_from_mpc(void) * This is broken; anything with a real cpu count has to * circumvent this idiocy regardless. */ - phys_id_present_map = ioapic_phys_id_map(phys_cpu_present_map); + phys_id_present_map = apic->ioapic_phys_id_map(phys_cpu_present_map); /* * Set the IOAPIC ID to the value stored in the MPC table. */ - for (apic = 0; apic < nr_ioapics; apic++) { + for (apic_id = 0; apic_id < nr_ioapics; apic_id++) { /* Read the register 0 value */ spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); + reg_00.raw = io_apic_read(apic_id, 0); spin_unlock_irqrestore(&ioapic_lock, flags); - old_id = mp_ioapics[apic].apicid; + old_id = mp_ioapics[apic_id].apicid; - if (mp_ioapics[apic].apicid >= get_physical_broadcast()) { + if (mp_ioapics[apic_id].apicid >= get_physical_broadcast()) { printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n", - apic, mp_ioapics[apic].apicid); + apic_id, mp_ioapics[apic_id].apicid); printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", reg_00.bits.ID); - mp_ioapics[apic].apicid = reg_00.bits.ID; + mp_ioapics[apic_id].apicid = reg_00.bits.ID; } /* @@ -2135,10 +2132,10 @@ static void __init setup_ioapic_ids_from_mpc(void) * system must have a unique ID or we get lots of nice * 'stuck on smp_invalidate_needed IPI wait' messages. */ - if (check_apicid_used(phys_id_present_map, - mp_ioapics[apic].apicid)) { + if (apic->check_apicid_used(phys_id_present_map, + mp_ioapics[apic_id].apicid)) { printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n", - apic, mp_ioapics[apic].apicid); + apic_id, mp_ioapics[apic_id].apicid); for (i = 0; i < get_physical_broadcast(); i++) if (!physid_isset(i, phys_id_present_map)) break; @@ -2147,13 +2144,13 @@ static void __init setup_ioapic_ids_from_mpc(void) printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", i); physid_set(i, phys_id_present_map); - mp_ioapics[apic].apicid = i; + mp_ioapics[apic_id].apicid = i; } else { physid_mask_t tmp; - tmp = apicid_to_cpu_present(mp_ioapics[apic].apicid); + tmp = apic->apicid_to_cpu_present(mp_ioapics[apic_id].apicid); apic_printk(APIC_VERBOSE, "Setting %d in the " "phys_id_present_map\n", - mp_ioapics[apic].apicid); + mp_ioapics[apic_id].apicid); physids_or(phys_id_present_map, phys_id_present_map, tmp); } @@ -2162,11 +2159,11 @@ static void __init setup_ioapic_ids_from_mpc(void) * We need to adjust the IRQ routing table * if the ID changed. */ - if (old_id != mp_ioapics[apic].apicid) + if (old_id != mp_ioapics[apic_id].apicid) for (i = 0; i < mp_irq_entries; i++) if (mp_irqs[i].dstapic == old_id) mp_irqs[i].dstapic - = mp_ioapics[apic].apicid; + = mp_ioapics[apic_id].apicid; /* * Read the right value from the MPC table and @@ -2174,20 +2171,20 @@ static void __init setup_ioapic_ids_from_mpc(void) */ apic_printk(APIC_VERBOSE, KERN_INFO "...changing IO-APIC physical APIC ID to %d ...", - mp_ioapics[apic].apicid); + mp_ioapics[apic_id].apicid); - reg_00.bits.ID = mp_ioapics[apic].apicid; + reg_00.bits.ID = mp_ioapics[apic_id].apicid; spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0, reg_00.raw); + io_apic_write(apic_id, 0, reg_00.raw); spin_unlock_irqrestore(&ioapic_lock, flags); /* * Sanity check */ spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); + reg_00.raw = io_apic_read(apic_id, 0); spin_unlock_irqrestore(&ioapic_lock, flags); - if (reg_00.bits.ID != mp_ioapics[apic].apicid) + if (reg_00.bits.ID != mp_ioapics[apic_id].apicid) printk("could not set ID!\n"); else apic_printk(APIC_VERBOSE, " ok.\n"); @@ -2290,7 +2287,7 @@ static int ioapic_retrigger_irq(unsigned int irq) unsigned long flags; spin_lock_irqsave(&vector_lock, flags); - send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector); + apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector); spin_unlock_irqrestore(&vector_lock, flags); return 1; @@ -2298,7 +2295,7 @@ static int ioapic_retrigger_irq(unsigned int irq) #else static int ioapic_retrigger_irq(unsigned int irq) { - send_IPI_self(irq_cfg(irq)->vector); + apic->send_IPI_self(irq_cfg(irq)->vector); return 1; } @@ -2362,7 +2359,7 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) set_extra_move_desc(desc, mask); - dest = cpu_mask_to_apicid_and(cfg->domain, mask); + dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask); modify_ioapic_rte = desc->status & IRQ_LEVEL; if (modify_ioapic_rte) { @@ -2382,7 +2379,7 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) if (cfg->move_in_progress) send_cleanup_vector(cfg); - cpumask_copy(&desc->affinity, mask); + cpumask_copy(desc->affinity, mask); } static int migrate_irq_remapped_level_desc(struct irq_desc *desc) @@ -2404,11 +2401,11 @@ static int migrate_irq_remapped_level_desc(struct irq_desc *desc) } /* everthing is clear. we have right of way */ - migrate_ioapic_irq_desc(desc, &desc->pending_mask); + migrate_ioapic_irq_desc(desc, desc->pending_mask); ret = 0; desc->status &= ~IRQ_MOVE_PENDING; - cpumask_clear(&desc->pending_mask); + cpumask_clear(desc->pending_mask); unmask: unmask_IO_APIC_irq_desc(desc); @@ -2433,7 +2430,7 @@ static void ir_irq_migration(struct work_struct *work) continue; } - desc->chip->set_affinity(irq, &desc->pending_mask); + desc->chip->set_affinity(irq, desc->pending_mask); spin_unlock_irqrestore(&desc->lock, flags); } } @@ -2447,7 +2444,7 @@ static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc, { if (desc->status & IRQ_LEVEL) { desc->status |= IRQ_MOVE_PENDING; - cpumask_copy(&desc->pending_mask, mask); + cpumask_copy(desc->pending_mask, mask); migrate_irq_remapped_level_desc(desc); return; } @@ -2515,7 +2512,7 @@ static void irq_complete_move(struct irq_desc **descp) /* domain has not changed, but affinity did */ me = smp_processor_id(); - if (cpu_isset(me, desc->affinity)) { + if (cpumask_test_cpu(me, desc->affinity)) { *descp = desc = move_irq_desc(desc, me); /* get the new one */ cfg = desc->chip_data; @@ -2866,19 +2863,15 @@ static inline void __init check_timer(void) int cpu = boot_cpu_id; int apic1, pin1, apic2, pin2; unsigned long flags; - unsigned int ver; int no_pin1 = 0; local_irq_save(flags); - ver = apic_read(APIC_LVR); - ver = GET_APIC_VERSION(ver); - /* * get/set the timer IRQ vector: */ disable_8259A_irq(0); - assign_irq_vector(0, cfg, TARGET_CPUS); + assign_irq_vector(0, cfg, apic->target_cpus()); /* * As IRQ0 is to be enabled in the 8259A, the virtual @@ -2892,7 +2885,13 @@ static inline void __init check_timer(void) apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); init_8259A(1); #ifdef CONFIG_X86_32 - timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); + { + unsigned int ver; + + ver = apic_read(APIC_LVR); + ver = GET_APIC_VERSION(ver); + timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); + } #endif pin1 = find_isa_irq_pin(0, mp_INT); @@ -2931,8 +2930,17 @@ static inline void __init check_timer(void) if (no_pin1) { add_pin_to_irq_cpu(cfg, cpu, apic1, pin1); setup_timer_IRQ0_pin(apic1, pin1, cfg->vector); + } else { + /* for edge trigger, setup_IO_APIC_irq already + * leave it unmasked. + * so only need to unmask if it is level-trigger + * do we really have level trigger timer? + */ + int idx; + idx = find_irq_entry(apic1, pin1, mp_INT); + if (idx != -1 && irq_trigger(idx)) + unmask_IO_APIC_irq_desc(desc); } - unmask_IO_APIC_irq_desc(desc); if (timer_irq_works()) { if (nmi_watchdog == NMI_IO_APIC) { setup_nmi(); @@ -2946,6 +2954,7 @@ static inline void __init check_timer(void) if (intr_remapping_enabled) panic("timer doesn't work through Interrupt-remapped IO-APIC"); #endif + local_irq_disable(); clear_IO_APIC_pin(apic1, pin1); if (!no_pin1) apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: " @@ -2960,7 +2969,6 @@ static inline void __init check_timer(void) */ replace_pin_at_irq_cpu(cfg, cpu, apic1, pin1, apic2, pin2); setup_timer_IRQ0_pin(apic2, pin2, cfg->vector); - unmask_IO_APIC_irq_desc(desc); enable_8259A_irq(0); if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); @@ -2975,6 +2983,7 @@ static inline void __init check_timer(void) /* * Cleanup, just in case ... */ + local_irq_disable(); disable_8259A_irq(0); clear_IO_APIC_pin(apic2, pin2); apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n"); @@ -3000,6 +3009,7 @@ static inline void __init check_timer(void) apic_printk(APIC_QUIET, KERN_INFO "..... works.\n"); goto out; } + local_irq_disable(); disable_8259A_irq(0); apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector); apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n"); @@ -3017,6 +3027,7 @@ static inline void __init check_timer(void) apic_printk(APIC_QUIET, KERN_INFO "..... works.\n"); goto out; } + local_irq_disable(); apic_printk(APIC_QUIET, KERN_INFO "..... failed :(.\n"); panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a " "report. Then try booting with the 'noapic' option.\n"); @@ -3168,6 +3179,7 @@ static int __init ioapic_init_sysfs(void) device_initcall(ioapic_init_sysfs); +static int nr_irqs_gsi = NR_IRQS_LEGACY; /* * Dynamic irq allocate and deallocation */ @@ -3182,11 +3194,11 @@ unsigned int create_irq_nr(unsigned int irq_want) struct irq_desc *desc_new = NULL; irq = 0; - spin_lock_irqsave(&vector_lock, flags); - for (new = irq_want; new < NR_IRQS; new++) { - if (platform_legacy_irq(new)) - continue; + if (irq_want < nr_irqs_gsi) + irq_want = nr_irqs_gsi; + spin_lock_irqsave(&vector_lock, flags); + for (new = irq_want; new < nr_irqs; new++) { desc_new = irq_to_desc_alloc_cpu(new, cpu); if (!desc_new) { printk(KERN_INFO "can not get irq_desc for %d\n", new); @@ -3196,7 +3208,7 @@ unsigned int create_irq_nr(unsigned int irq_want) if (cfg_new->vector != 0) continue; - if (__assign_irq_vector(new, cfg_new, TARGET_CPUS) == 0) + if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0) irq = new; break; } @@ -3211,7 +3223,6 @@ unsigned int create_irq_nr(unsigned int irq_want) return irq; } -static int nr_irqs_gsi = NR_IRQS_LEGACY; int create_irq(void) { unsigned int irq_want; @@ -3258,12 +3269,15 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms int err; unsigned dest; + if (disable_apic) + return -ENXIO; + cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, TARGET_CPUS); + err = assign_irq_vector(irq, cfg, apic->target_cpus()); if (err) return err; - dest = cpu_mask_to_apicid_and(cfg->domain, TARGET_CPUS); + dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); #ifdef CONFIG_INTR_REMAP if (irq_remapped(irq)) { @@ -3277,9 +3291,9 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms memset (&irte, 0, sizeof(irte)); irte.present = 1; - irte.dst_mode = INT_DEST_MODE; + irte.dst_mode = apic->irq_dest_mode; irte.trigger_mode = 0; /* edge */ - irte.dlvry_mode = INT_DELIVERY_MODE; + irte.dlvry_mode = apic->irq_delivery_mode; irte.vector = cfg->vector; irte.dest_id = IRTE_DEST(dest); @@ -3297,10 +3311,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms msg->address_hi = MSI_ADDR_BASE_HI; msg->address_lo = MSI_ADDR_BASE_LO | - ((INT_DEST_MODE == 0) ? + ((apic->irq_dest_mode == 0) ? MSI_ADDR_DEST_MODE_PHYSICAL: MSI_ADDR_DEST_MODE_LOGICAL) | - ((INT_DELIVERY_MODE != dest_LowestPrio) ? + ((apic->irq_delivery_mode != dest_LowestPrio) ? MSI_ADDR_REDIRECTION_CPU: MSI_ADDR_REDIRECTION_LOWPRI) | MSI_ADDR_DEST_ID(dest); @@ -3308,7 +3322,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms msg->data = MSI_DATA_TRIGGER_EDGE | MSI_DATA_LEVEL_ASSERT | - ((INT_DELIVERY_MODE != dest_LowestPrio) ? + ((apic->irq_delivery_mode != dest_LowestPrio) ? MSI_DATA_DELIVERY_FIXED: MSI_DATA_DELIVERY_LOWPRI) | MSI_DATA_VECTOR(cfg->vector); @@ -3479,9 +3493,9 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) sub_handle = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { irq = create_irq_nr(irq_want); - irq_want++; if (irq == 0) return -1; + irq_want = irq + 1; #ifdef CONFIG_INTR_REMAP if (!intr_remapping_enabled) goto no_ir; @@ -3692,13 +3706,17 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) struct irq_cfg *cfg; int err; + if (disable_apic) + return -ENXIO; + cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, TARGET_CPUS); + err = assign_irq_vector(irq, cfg, apic->target_cpus()); if (!err) { struct ht_irq_msg msg; unsigned dest; - dest = cpu_mask_to_apicid_and(cfg->domain, TARGET_CPUS); + dest = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus()); msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); @@ -3706,11 +3724,11 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) HT_IRQ_LOW_BASE | HT_IRQ_LOW_DEST_ID(dest) | HT_IRQ_LOW_VECTOR(cfg->vector) | - ((INT_DEST_MODE == 0) ? + ((apic->irq_dest_mode == 0) ? HT_IRQ_LOW_DM_PHYSICAL : HT_IRQ_LOW_DM_LOGICAL) | HT_IRQ_LOW_RQEOI_EDGE | - ((INT_DELIVERY_MODE != dest_LowestPrio) ? + ((apic->irq_delivery_mode != dest_LowestPrio) ? HT_IRQ_LOW_MT_FIXED : HT_IRQ_LOW_MT_ARBITRATED) | HT_IRQ_LOW_IRQ_MASKED; @@ -3726,7 +3744,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) } #endif /* CONFIG_HT_IRQ */ -#ifdef CONFIG_X86_64 +#ifdef CONFIG_X86_UV /* * Re-target the irq to the specified CPU and enable the specified MMR located * on the specified blade to allow the sending of MSIs to the specified CPU. @@ -3758,12 +3776,12 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long)); entry->vector = cfg->vector; - entry->delivery_mode = INT_DELIVERY_MODE; - entry->dest_mode = INT_DEST_MODE; + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; entry->polarity = 0; entry->trigger = 0; entry->mask = 0; - entry->dest = cpu_mask_to_apicid(eligible_cpu); + entry->dest = apic->cpu_mask_to_apicid(eligible_cpu); mmr_pnode = uv_blade_to_pnode(mmr_blade); uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); @@ -3806,15 +3824,47 @@ int __init io_apic_get_redir_entries (int ioapic) void __init probe_nr_irqs_gsi(void) { - int idx; int nr = 0; - for (idx = 0; idx < nr_ioapics; idx++) - nr += io_apic_get_redir_entries(idx) + 1; - - if (nr > nr_irqs_gsi) + nr = acpi_probe_gsi(); + if (nr > nr_irqs_gsi) { nr_irqs_gsi = nr; + } else { + /* for acpi=off or acpi is not compiled in */ + int idx; + + nr = 0; + for (idx = 0; idx < nr_ioapics; idx++) + nr += io_apic_get_redir_entries(idx) + 1; + + if (nr > nr_irqs_gsi) + nr_irqs_gsi = nr; + } + + printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi); +} + +#ifdef CONFIG_SPARSE_IRQ +int __init arch_probe_nr_irqs(void) +{ + int nr; + + if (nr_irqs > (NR_VECTORS * nr_cpu_ids)) + nr_irqs = NR_VECTORS * nr_cpu_ids; + + nr = nr_irqs_gsi + 8 * nr_cpu_ids; +#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ) + /* + * for MSI and HT dyn irq + */ + nr += nr_irqs_gsi * 16; +#endif + if (nr < nr_irqs) + nr_irqs = nr; + + return 0; } +#endif /* -------------------------------------------------------------------------- ACPI-based IOAPIC Configuration @@ -3841,7 +3891,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) */ if (physids_empty(apic_id_map)) - apic_id_map = ioapic_phys_id_map(phys_cpu_present_map); + apic_id_map = apic->ioapic_phys_id_map(phys_cpu_present_map); spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(ioapic, 0); @@ -3857,10 +3907,10 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) * Every APIC in a system must have a unique ID or we get lots of nice * 'stuck on smp_invalidate_needed IPI wait' messages. */ - if (check_apicid_used(apic_id_map, apic_id)) { + if (apic->check_apicid_used(apic_id_map, apic_id)) { for (i = 0; i < get_physical_broadcast(); i++) { - if (!check_apicid_used(apic_id_map, i)) + if (!apic->check_apicid_used(apic_id_map, i)) break; } @@ -3873,7 +3923,7 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id) apic_id = i; } - tmp = apicid_to_cpu_present(apic_id); + tmp = apic->apicid_to_cpu_present(apic_id); physids_or(apic_id_map, apic_id_map, tmp); if (reg_00.bits.ID != apic_id) { @@ -3966,7 +4016,7 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity) /* * This function currently is only a helper for the i386 smp boot process where * we need to reprogram the ioredtbls to cater for the cpus which have come online - * so mask in all cases should simply be TARGET_CPUS + * so mask in all cases should simply be apic->target_cpus() */ #ifdef CONFIG_SMP void __init setup_ioapic_dest(void) @@ -4005,9 +4055,9 @@ void __init setup_ioapic_dest(void) */ if (desc->status & (IRQ_NO_BALANCING | IRQ_AFFINITY_SET)) - mask = &desc->affinity; + mask = desc->affinity; else - mask = TARGET_CPUS; + mask = apic->target_cpus(); #ifdef CONFIG_INTR_REMAP if (intr_remapping_enabled) diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index b12208f4dfe..e41980a373a 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -131,9 +131,8 @@ static int do_iopl(unsigned int level, struct pt_regs *regs) } #ifdef CONFIG_X86_32 -asmlinkage long sys_iopl(unsigned long regsp) +long sys_iopl(struct pt_regs *regs) { - struct pt_regs *regs = (struct pt_regs *)®sp; unsigned int level = regs->bx; struct thread_struct *t = ¤t->thread; int rc; diff --git a/arch/x86/kernel/ipi.c b/arch/x86/kernel/ipi.c index 285bbf8831f..dbf5445727a 100644 --- a/arch/x86/kernel/ipi.c +++ b/arch/x86/kernel/ipi.c @@ -17,147 +17,121 @@ #include <asm/mmu_context.h> #include <asm/apic.h> #include <asm/proto.h> +#include <asm/ipi.h> -#ifdef CONFIG_X86_32 -#include <mach_apic.h> -#include <mach_ipi.h> - -/* - * the following functions deal with sending IPIs between CPUs. - * - * We use 'broadcast', CPU->CPU IPIs and self-IPIs too. - */ - -static inline int __prepare_ICR(unsigned int shortcut, int vector) +void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector) { - unsigned int icr = shortcut | APIC_DEST_LOGICAL; - - switch (vector) { - default: - icr |= APIC_DM_FIXED | vector; - break; - case NMI_VECTOR: - icr |= APIC_DM_NMI; - break; + unsigned long query_cpu; + unsigned long flags; + + /* + * Hack. The clustered APIC addressing mode doesn't allow us to send + * to an arbitrary mask, so I do a unicast to each CPU instead. + * - mbligh + */ + local_irq_save(flags); + for_each_cpu(query_cpu, mask) { + __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, + query_cpu), vector, APIC_DEST_PHYSICAL); } - return icr; + local_irq_restore(flags); } -static inline int __prepare_ICR2(unsigned int mask) +void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, + int vector) { - return SET_APIC_DEST_FIELD(mask); -} + unsigned int this_cpu = smp_processor_id(); + unsigned int query_cpu; + unsigned long flags; -void __send_IPI_shortcut(unsigned int shortcut, int vector) -{ - /* - * Subtle. In the case of the 'never do double writes' workaround - * we have to lock out interrupts to be safe. As we don't care - * of the value read we use an atomic rmw access to avoid costly - * cli/sti. Otherwise we use an even cheaper single atomic write - * to the APIC. - */ - unsigned int cfg; + /* See Hack comment above */ - /* - * Wait for idle. - */ - apic_wait_icr_idle(); + local_irq_save(flags); + for_each_cpu(query_cpu, mask) { + if (query_cpu == this_cpu) + continue; + __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, + query_cpu), vector, APIC_DEST_PHYSICAL); + } + local_irq_restore(flags); +} - /* - * No need to touch the target chip field - */ - cfg = __prepare_ICR(shortcut, vector); +void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, + int vector) +{ + unsigned long flags; + unsigned int query_cpu; /* - * Send the IPI. The write to APIC_ICR fires this off. + * Hack. The clustered APIC addressing mode doesn't allow us to send + * to an arbitrary mask, so I do a unicasts to each CPU instead. This + * should be modified to do 1 message per cluster ID - mbligh */ - apic_write(APIC_ICR, cfg); -} -void send_IPI_self(int vector) -{ - __send_IPI_shortcut(APIC_DEST_SELF, vector); + local_irq_save(flags); + for_each_cpu(query_cpu, mask) + __default_send_IPI_dest_field( + apic->cpu_to_logical_apicid(query_cpu), vector, + apic->dest_logical); + local_irq_restore(flags); } -/* - * This is used to send an IPI with no shorthand notation (the destination is - * specified in bits 56 to 63 of the ICR). - */ -static inline void __send_IPI_dest_field(unsigned long mask, int vector) +void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, + int vector) { - unsigned long cfg; - - /* - * Wait for idle. - */ - if (unlikely(vector == NMI_VECTOR)) - safe_apic_wait_icr_idle(); - else - apic_wait_icr_idle(); - - /* - * prepare target chip field - */ - cfg = __prepare_ICR2(mask); - apic_write(APIC_ICR2, cfg); + unsigned long flags; + unsigned int query_cpu; + unsigned int this_cpu = smp_processor_id(); - /* - * program the ICR - */ - cfg = __prepare_ICR(0, vector); + /* See Hack comment above */ - /* - * Send the IPI. The write to APIC_ICR fires this off. - */ - apic_write(APIC_ICR, cfg); + local_irq_save(flags); + for_each_cpu(query_cpu, mask) { + if (query_cpu == this_cpu) + continue; + __default_send_IPI_dest_field( + apic->cpu_to_logical_apicid(query_cpu), vector, + apic->dest_logical); + } + local_irq_restore(flags); } +#ifdef CONFIG_X86_32 + /* * This is only used on smaller machines. */ -void send_IPI_mask_bitmask(const struct cpumask *cpumask, int vector) +void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector) { unsigned long mask = cpumask_bits(cpumask)[0]; unsigned long flags; local_irq_save(flags); WARN_ON(mask & ~cpumask_bits(cpu_online_mask)[0]); - __send_IPI_dest_field(mask, vector); + __default_send_IPI_dest_field(mask, vector, apic->dest_logical); local_irq_restore(flags); } -void send_IPI_mask_sequence(const struct cpumask *mask, int vector) +void default_send_IPI_allbutself(int vector) { - unsigned long flags; - unsigned int query_cpu; - /* - * Hack. The clustered APIC addressing mode doesn't allow us to send - * to an arbitrary mask, so I do a unicasts to each CPU instead. This - * should be modified to do 1 message per cluster ID - mbligh + * if there are no other CPUs in the system then we get an APIC send + * error if we try to broadcast, thus avoid sending IPIs in this case. */ + if (!(num_online_cpus() > 1)) + return; - local_irq_save(flags); - for_each_cpu(query_cpu, mask) - __send_IPI_dest_field(cpu_to_logical_apicid(query_cpu), vector); - local_irq_restore(flags); + __default_local_send_IPI_allbutself(vector); } -void send_IPI_mask_allbutself(const struct cpumask *mask, int vector) +void default_send_IPI_all(int vector) { - unsigned long flags; - unsigned int query_cpu; - unsigned int this_cpu = smp_processor_id(); - - /* See Hack comment above */ + __default_local_send_IPI_all(vector); +} - local_irq_save(flags); - for_each_cpu(query_cpu, mask) - if (query_cpu != this_cpu) - __send_IPI_dest_field(cpu_to_logical_apicid(query_cpu), - vector); - local_irq_restore(flags); +void default_send_IPI_self(int vector) +{ + __default_send_IPI_shortcut(APIC_DEST_SELF, vector, apic->dest_logical); } /* must come after the send_IPI functions above for inlining */ diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 3973e2df7f8..f13ca1650aa 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -6,10 +6,12 @@ #include <linux/kernel_stat.h> #include <linux/seq_file.h> #include <linux/smp.h> +#include <linux/ftrace.h> #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/irq.h> +#include <asm/idle.h> atomic_t irq_err_count; @@ -36,11 +38,7 @@ void ack_bad_irq(unsigned int irq) #endif } -#ifdef CONFIG_X86_32 -# define irq_stats(x) (&per_cpu(irq_stat, x)) -#else -# define irq_stats(x) cpu_pda(x) -#endif +#define irq_stats(x) (&per_cpu(irq_stat, x)) /* * /proc/interrupts printing: */ @@ -192,4 +190,40 @@ u64 arch_irq_stat(void) return sum; } + +/* + * do_IRQ handles all normal device IRQ's (the special + * SMP cross-CPU interrupts have their own specific + * handlers). + */ +unsigned int __irq_entry do_IRQ(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + /* high bit used in ret_from_ code */ + unsigned vector = ~regs->orig_ax; + unsigned irq; + + exit_idle(); + irq_enter(); + + irq = __get_cpu_var(vector_irq)[vector]; + + if (!handle_irq(irq, regs)) { +#ifdef CONFIG_X86_64 + if (!disable_apic) + ack_APIC_irq(); +#endif + + if (printk_ratelimit()) + printk(KERN_EMERG "%s: %d.%d No irq handler for vector (irq %d)\n", + __func__, smp_processor_id(), vector, irq); + } + + irq_exit(); + + set_irq_regs(old_regs); + return 1; +} + EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 74b9ff7341e..4beb9a13873 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -191,33 +191,16 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; } #endif -/* - * do_IRQ handles all normal device IRQ's (the special - * SMP cross-CPU interrupts have their own specific - * handlers). - */ -unsigned int do_IRQ(struct pt_regs *regs) +bool handle_irq(unsigned irq, struct pt_regs *regs) { - struct pt_regs *old_regs; - /* high bit used in ret_from_ code */ - int overflow; - unsigned vector = ~regs->orig_ax; struct irq_desc *desc; - unsigned irq; - - - old_regs = set_irq_regs(regs); - irq_enter(); - irq = __get_cpu_var(vector_irq)[vector]; + int overflow; overflow = check_stack_overflow(); desc = irq_to_desc(irq); - if (unlikely(!desc)) { - printk(KERN_EMERG "%s: cannot handle IRQ %d vector %#x cpu %d\n", - __func__, irq, vector, smp_processor_id()); - BUG(); - } + if (unlikely(!desc)) + return false; if (!execute_on_irq_stack(overflow, desc, irq)) { if (unlikely(overflow)) @@ -225,13 +208,11 @@ unsigned int do_IRQ(struct pt_regs *regs) desc->handle_irq(irq, desc); } - irq_exit(); - set_irq_regs(old_regs); - return 1; + return true; } #ifdef CONFIG_HOTPLUG_CPU -#include <mach_apic.h> +#include <asm/genapic.h> /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) @@ -248,7 +229,7 @@ void fixup_irqs(void) if (irq == 2) continue; - affinity = &desc->affinity; + affinity = desc->affinity; if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { printk("Breaking affinity for irq %i\n", irq); affinity = cpu_all_mask; diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 63c88e6ec02..977d8b43a0d 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -18,6 +18,13 @@ #include <linux/smp.h> #include <asm/io_apic.h> #include <asm/idle.h> +#include <asm/apic.h> + +DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); +EXPORT_PER_CPU_SYMBOL(irq_stat); + +DEFINE_PER_CPU(struct pt_regs *, irq_regs); +EXPORT_PER_CPU_SYMBOL(irq_regs); /* * Probabilistic stack overflow check: @@ -41,42 +48,18 @@ static inline void stack_overflow_check(struct pt_regs *regs) #endif } -/* - * do_IRQ handles all normal device IRQ's (the special - * SMP cross-CPU interrupts have their own specific - * handlers). - */ -asmlinkage unsigned int __irq_entry do_IRQ(struct pt_regs *regs) +bool handle_irq(unsigned irq, struct pt_regs *regs) { - struct pt_regs *old_regs = set_irq_regs(regs); struct irq_desc *desc; - /* high bit used in ret_from_ code */ - unsigned vector = ~regs->orig_ax; - unsigned irq; - - exit_idle(); - irq_enter(); - irq = __get_cpu_var(vector_irq)[vector]; - stack_overflow_check(regs); desc = irq_to_desc(irq); - if (likely(desc)) - generic_handle_irq_desc(irq, desc); - else { - if (!disable_apic) - ack_APIC_irq(); - - if (printk_ratelimit()) - printk(KERN_EMERG "%s: %d.%d No irq handler for vector\n", - __func__, smp_processor_id(), vector); - } - - irq_exit(); + if (unlikely(!desc)) + return false; - set_irq_regs(old_regs); - return 1; + generic_handle_irq_desc(irq, desc); + return true; } #ifdef CONFIG_HOTPLUG_CPU @@ -100,7 +83,7 @@ void fixup_irqs(void) /* interrupt's are disabled at this point */ spin_lock(&desc->lock); - affinity = &desc->affinity; + affinity = desc->affinity; if (!irq_has_action(irq) || cpumask_equal(affinity, cpu_online_mask)) { spin_unlock(&desc->lock); diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c index 10a09c2f182..bf629cadec1 100644 --- a/arch/x86/kernel/irqinit_32.c +++ b/arch/x86/kernel/irqinit_32.c @@ -78,6 +78,15 @@ void __init init_ISA_irqs(void) } } +/* + * IRQ2 is cascade interrupt to second interrupt controller + */ +static struct irqaction irq2 = { + .handler = no_action, + .mask = CPU_MASK_NONE, + .name = "cascade", +}; + DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... IRQ0_VECTOR - 1] = -1, [IRQ0_VECTOR] = 0, @@ -140,8 +149,15 @@ void __init native_init_IRQ(void) */ alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); - /* IPI for invalidation */ - alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt); + /* IPIs for invalidation */ + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6); + alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7); /* IPI for generic function call */ alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); @@ -169,6 +185,9 @@ void __init native_init_IRQ(void) alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); #endif + if (!acpi_ioapic) + setup_irq(2, &irq2); + /* setup after call gates are initialised (usually add in * the architecture specific gates) */ diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 10435a120d2..5c4f5548384 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -46,7 +46,7 @@ #include <asm/apicdef.h> #include <asm/system.h> -#include <mach_ipi.h> +#include <asm/genapic.h> /* * Put the error code here just in case the user cares: @@ -347,7 +347,7 @@ void kgdb_post_primary_code(struct pt_regs *regs, int e_vector, int err_code) */ void kgdb_roundup_cpus(unsigned long flags) { - send_IPI_allbutself(APIC_DM_NMI); + apic->send_IPI_allbutself(APIC_DM_NMI); } #endif diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index fa6bb263892..20076445319 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -3,7 +3,7 @@ * compliant MP-table parsing routines. * * (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk> - * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com> + * (c) 1998, 1999, 2000, 2009 Ingo Molnar <mingo@redhat.com> * (c) 2008 Alexey Starikovskiy <astarikovskiy@suse.de> */ @@ -29,12 +29,7 @@ #include <asm/setup.h> #include <asm/smp.h> -#include <mach_apic.h> -#ifdef CONFIG_X86_32 -#include <mach_apicdef.h> -#include <mach_mpparse.h> -#endif - +#include <asm/genapic.h> /* * Checksum an MP configuration block. */ @@ -292,16 +287,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) return 0; #ifdef CONFIG_X86_32 - /* - * need to make sure summit and es7000's mps_oem_check is safe to be - * called early via genericarch 's mps_oem_check - */ - if (early) { -#ifdef CONFIG_X86_NUMAQ - numaq_mps_oem_check(mpc, oem, str); -#endif - } else - mps_oem_check(mpc, oem, str); + generic_mps_oem_check(mpc, oem, str); #endif /* save the local APIC address, it might be non-default */ if (!acpi_lapic) @@ -386,13 +372,13 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) (*x86_quirks->mpc_record)++; } -#ifdef CONFIG_X86_GENERICARCH - generic_bigsmp_probe(); +#ifdef CONFIG_X86_BIGSMP + generic_bigsmp_probe(); #endif -#ifdef CONFIG_X86_32 - setup_apic_routing(); -#endif + if (apic->setup_apic_routing) + apic->setup_apic_routing(); + if (!num_processors) printk(KERN_ERR "MPTABLE: no processors registered!\n"); return num_processors; @@ -706,8 +692,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, #endif mpf_found = mpf; - printk(KERN_INFO "found SMP MP-table at [%p] %08lx\n", - mpf, virt_to_phys(mpf)); + printk(KERN_INFO "found SMP MP-table at [%p] %llx\n", + mpf, (u64)virt_to_phys(mpf)); if (!reserve) return 1; @@ -1025,7 +1011,7 @@ static int __init update_mp_table(void) if (!smp_check_mpc(mpc, oem, str)) return 0; - printk(KERN_INFO "mpf: %lx\n", virt_to_phys(mpf)); + printk(KERN_INFO "mpf: %llx\n", (u64)virt_to_phys(mpf)); printk(KERN_INFO "physptr: %x\n", mpf->physptr); if (mpc_new_phys && mpc->length > mpc_new_length) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 7228979f1e7..bdfad80c3cf 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -34,7 +34,7 @@ #include <asm/mce.h> -#include <mach_traps.h> +#include <asm/mach_traps.h> int unknown_nmi_panic; int nmi_watchdog_enabled; @@ -61,11 +61,7 @@ static int endflag __initdata; static inline unsigned int get_nmi_count(int cpu) { -#ifdef CONFIG_X86_64 - return cpu_pda(cpu)->__nmi_count; -#else - return nmi_count(cpu); -#endif + return per_cpu(irq_stat, cpu).__nmi_count; } static inline int mce_in_progress(void) @@ -82,12 +78,8 @@ static inline int mce_in_progress(void) */ static inline unsigned int get_timer_irqs(int cpu) { -#ifdef CONFIG_X86_64 - return read_pda(apic_timer_irqs) + read_pda(irq0_irqs); -#else return per_cpu(irq_stat, cpu).apic_timer_irqs + per_cpu(irq_stat, cpu).irq0_irqs; -#endif } #ifdef CONFIG_SMP diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c index f2191d4f271..0cc41a1d255 100644 --- a/arch/x86/kernel/numaq_32.c +++ b/arch/x86/kernel/numaq_32.c @@ -3,7 +3,7 @@ * * Copyright (C) 2002, IBM Corp. * - * All rights reserved. + * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -23,17 +23,18 @@ * Send feedback to <gone@us.ibm.com> */ -#include <linux/mm.h> +#include <linux/nodemask.h> #include <linux/bootmem.h> #include <linux/mmzone.h> #include <linux/module.h> -#include <linux/nodemask.h> -#include <asm/numaq.h> -#include <asm/topology.h> +#include <linux/mm.h> + #include <asm/processor.h> +#include <asm/topology.h> #include <asm/genapic.h> -#include <asm/e820.h> +#include <asm/numaq.h> #include <asm/setup.h> +#include <asm/e820.h> #define MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT)) @@ -91,19 +92,20 @@ static int __init numaq_pre_time_init(void) } int found_numaq; + /* * Have to match translation table entries to main table entries by counter * hence the mpc_record variable .... can't see a less disgusting way of * doing this .... */ struct mpc_config_translation { - unsigned char mpc_type; - unsigned char trans_len; - unsigned char trans_type; - unsigned char trans_quad; - unsigned char trans_global; - unsigned char trans_local; - unsigned short trans_reserved; + unsigned char mpc_type; + unsigned char trans_len; + unsigned char trans_type; + unsigned char trans_quad; + unsigned char trans_global; + unsigned char trans_local; + unsigned short trans_reserved; }; /* x86_quirks member */ @@ -236,7 +238,7 @@ static int __init numaq_setup_ioapic_ids(void) static int __init numaq_update_genapic(void) { - genapic->wakeup_cpu = wakeup_secondary_cpu_via_nmi; + apic->wakeup_cpu = wakeup_secondary_cpu_via_nmi; return 0; } @@ -291,3 +293,280 @@ int __init get_memcfg_numaq(void) smp_dump_qct(); return 1; } + +/* + * APIC driver for the IBM NUMAQ chipset. + */ +#define APIC_DEFINITION 1 +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <asm/mpspec.h> +#include <asm/genapic.h> +#include <asm/fixmap.h> +#include <asm/apicdef.h> +#include <asm/ipi.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/numa.h> +#include <linux/smp.h> +#include <asm/numaq.h> +#include <asm/io.h> +#include <linux/mmzone.h> +#include <linux/nodemask.h> + +#define NUMAQ_APIC_DFR_VALUE (APIC_DFR_CLUSTER) + +static inline unsigned int numaq_get_apic_id(unsigned long x) +{ + return (x >> 24) & 0x0F; +} + +static inline void numaq_send_IPI_mask(const struct cpumask *mask, int vector) +{ + default_send_IPI_mask_sequence_logical(mask, vector); +} + +static inline void numaq_send_IPI_allbutself(int vector) +{ + default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector); +} + +static inline void numaq_send_IPI_all(int vector) +{ + numaq_send_IPI_mask(cpu_online_mask, vector); +} + +extern void numaq_mps_oem_check(struct mpc_table *, char *, char *); + +#define NUMAQ_TRAMPOLINE_PHYS_LOW (0x8) +#define NUMAQ_TRAMPOLINE_PHYS_HIGH (0xa) + +/* + * Because we use NMIs rather than the INIT-STARTUP sequence to + * bootstrap the CPUs, the APIC may be in a weird state. Kick it: + */ +static inline void numaq_smp_callin_clear_local_apic(void) +{ + clear_local_APIC(); +} + +static inline void +numaq_store_NMI_vector(unsigned short *high, unsigned short *low) +{ + printk("Storing NMI vector\n"); + *high = + *((volatile unsigned short *)phys_to_virt(NUMAQ_TRAMPOLINE_PHYS_HIGH)); + *low = + *((volatile unsigned short *)phys_to_virt(NUMAQ_TRAMPOLINE_PHYS_LOW)); +} + +static inline const cpumask_t *numaq_target_cpus(void) +{ + return &CPU_MASK_ALL; +} + +static inline unsigned long +numaq_check_apicid_used(physid_mask_t bitmap, int apicid) +{ + return physid_isset(apicid, bitmap); +} + +static inline unsigned long numaq_check_apicid_present(int bit) +{ + return physid_isset(bit, phys_cpu_present_map); +} + +#define apicid_cluster(apicid) (apicid & 0xF0) + +static inline int numaq_apic_id_registered(void) +{ + return 1; +} + +static inline void numaq_init_apic_ldr(void) +{ + /* Already done in NUMA-Q firmware */ +} + +static inline void numaq_setup_apic_routing(void) +{ + printk("Enabling APIC mode: %s. Using %d I/O APICs\n", + "NUMA-Q", nr_ioapics); +} + +/* + * Skip adding the timer int on secondary nodes, which causes + * a small but painful rift in the time-space continuum. + */ +static inline int numaq_multi_timer_check(int apic, int irq) +{ + return apic != 0 && irq == 0; +} + +static inline physid_mask_t numaq_ioapic_phys_id_map(physid_mask_t phys_map) +{ + /* We don't have a good way to do this yet - hack */ + return physids_promote(0xFUL); +} + +/* Mapping from cpu number to logical apicid */ +extern u8 cpu_2_logical_apicid[]; + +static inline int numaq_cpu_to_logical_apicid(int cpu) +{ + if (cpu >= nr_cpu_ids) + return BAD_APICID; + return (int)cpu_2_logical_apicid[cpu]; +} + +/* + * Supporting over 60 cpus on NUMA-Q requires a locality-dependent + * cpu to APIC ID relation to properly interact with the intelligent + * mode of the cluster controller. + */ +static inline int numaq_cpu_present_to_apicid(int mps_cpu) +{ + if (mps_cpu < 60) + return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3)); + else + return BAD_APICID; +} + +static inline int numaq_apicid_to_node(int logical_apicid) +{ + return logical_apicid >> 4; +} + +static inline physid_mask_t numaq_apicid_to_cpu_present(int logical_apicid) +{ + int node = numaq_apicid_to_node(logical_apicid); + int cpu = __ffs(logical_apicid & 0xf); + + return physid_mask_of_physid(cpu + 4*node); +} + +/* Where the IO area was mapped on multiquad, always 0 otherwise */ +void *xquad_portio; + +static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid) +{ + return 1; +} + +/* + * We use physical apicids here, not logical, so just return the default + * physical broadcast to stop people from breaking us + */ +static inline unsigned int numaq_cpu_mask_to_apicid(const cpumask_t *cpumask) +{ + return 0x0F; +} + +static inline unsigned int +numaq_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask) +{ + return 0x0F; +} + +/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */ +static inline int numaq_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} +static int __numaq_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) +{ + numaq_mps_oem_check(mpc, oem, productid); + return found_numaq; +} + +static int probe_numaq(void) +{ + /* already know from get_memcfg_numaq() */ + return found_numaq; +} + +static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask) +{ + /* Careful. Some cpus do not strictly honor the set of cpus + * specified in the interrupt destination when using lowest + * priority interrupt delivery mode. + * + * In particular there was a hyperthreading cpu observed to + * deliver interrupts to the wrong hyperthread when only one + * hyperthread was specified in the interrupt desitination. + */ + *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; +} + +static void numaq_setup_portio_remap(void) +{ + int num_quads = num_online_nodes(); + + if (num_quads <= 1) + return; + + printk("Remapping cross-quad port I/O for %d quads\n", num_quads); + xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD); + printk("xquad_portio vaddr 0x%08lx, len %08lx\n", + (u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD); +} + +struct genapic apic_numaq = { + + .name = "NUMAQ", + .probe = probe_numaq, + .acpi_madt_oem_check = NULL, + .apic_id_registered = numaq_apic_id_registered, + + .irq_delivery_mode = dest_LowestPrio, + /* physical delivery on LOCAL quad: */ + .irq_dest_mode = 0, + + .target_cpus = numaq_target_cpus, + .disable_esr = 1, + .dest_logical = APIC_DEST_LOGICAL, + .check_apicid_used = numaq_check_apicid_used, + .check_apicid_present = numaq_check_apicid_present, + + .vector_allocation_domain = numaq_vector_allocation_domain, + .init_apic_ldr = numaq_init_apic_ldr, + + .ioapic_phys_id_map = numaq_ioapic_phys_id_map, + .setup_apic_routing = numaq_setup_apic_routing, + .multi_timer_check = numaq_multi_timer_check, + .apicid_to_node = numaq_apicid_to_node, + .cpu_to_logical_apicid = numaq_cpu_to_logical_apicid, + .cpu_present_to_apicid = numaq_cpu_present_to_apicid, + .apicid_to_cpu_present = numaq_apicid_to_cpu_present, + .setup_portio_remap = numaq_setup_portio_remap, + .check_phys_apicid_present = numaq_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = numaq_phys_pkg_id, + .mps_oem_check = __numaq_mps_oem_check, + + .get_apic_id = numaq_get_apic_id, + .set_apic_id = NULL, + .apic_id_mask = 0x0F << 24, + + .cpu_mask_to_apicid = numaq_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = numaq_cpu_mask_to_apicid_and, + + .send_IPI_mask = numaq_send_IPI_mask, + .send_IPI_mask_allbutself = NULL, + .send_IPI_allbutself = numaq_send_IPI_allbutself, + .send_IPI_all = numaq_send_IPI_all, + .send_IPI_self = default_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = NUMAQ_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = NUMAQ_TRAMPOLINE_PHYS_HIGH, + + /* We don't do anything here because we use NMI's to boot instead */ + .wait_for_init_deassert = NULL, + + .smp_callin_clear_local_apic = numaq_smp_callin_clear_local_apic, + .store_NMI_vector = numaq_store_NMI_vector, + .inquire_remote_apic = NULL, +}; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index e4c8fb60887..cea11c8e304 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -44,6 +44,17 @@ void _paravirt_nop(void) { } +/* identity function, which can be inlined */ +u32 _paravirt_ident_32(u32 x) +{ + return x; +} + +u64 _paravirt_ident_64(u64 x) +{ + return x; +} + static void __init default_banner(void) { printk(KERN_INFO "Booting paravirtualized kernel on %s\n", @@ -138,9 +149,16 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, if (opfunc == NULL) /* If there's no function, patch it with a ud2a (BUG) */ ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a)); - else if (opfunc == paravirt_nop) + else if (opfunc == _paravirt_nop) /* If the operation is a nop, then nop the callsite */ ret = paravirt_patch_nop(); + + /* identity functions just return their single argument */ + else if (opfunc == _paravirt_ident_32) + ret = paravirt_patch_ident_32(insnbuf, len); + else if (opfunc == _paravirt_ident_64) + ret = paravirt_patch_ident_64(insnbuf, len); + else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || @@ -292,10 +310,10 @@ struct pv_time_ops pv_time_ops = { struct pv_irq_ops pv_irq_ops = { .init_IRQ = native_init_IRQ, - .save_fl = native_save_fl, - .restore_fl = native_restore_fl, - .irq_disable = native_irq_disable, - .irq_enable = native_irq_enable, + .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), + .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), + .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), + .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .safe_halt = native_safe_halt, .halt = native_halt, #ifdef CONFIG_X86_64 @@ -373,6 +391,14 @@ struct pv_apic_ops pv_apic_ops = { #endif }; +#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) +/* 32-bit pagetable entries */ +#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32) +#else +/* 64-bit pagetable entries */ +#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64) +#endif + struct pv_mmu_ops pv_mmu_ops = { #ifndef CONFIG_X86_64 .pagetable_setup_start = native_pagetable_setup_start, @@ -424,22 +450,23 @@ struct pv_mmu_ops pv_mmu_ops = { .pmd_clear = native_pmd_clear, #endif .set_pud = native_set_pud, - .pmd_val = native_pmd_val, - .make_pmd = native_make_pmd, + + .pmd_val = PTE_IDENT, + .make_pmd = PTE_IDENT, #if PAGETABLE_LEVELS == 4 - .pud_val = native_pud_val, - .make_pud = native_make_pud, + .pud_val = PTE_IDENT, + .make_pud = PTE_IDENT, + .set_pgd = native_set_pgd, #endif #endif /* PAGETABLE_LEVELS >= 3 */ - .pte_val = native_pte_val, - .pte_flags = native_pte_flags, - .pgd_val = native_pgd_val, + .pte_val = PTE_IDENT, + .pgd_val = PTE_IDENT, - .make_pte = native_make_pte, - .make_pgd = native_make_pgd, + .make_pte = PTE_IDENT, + .make_pgd = PTE_IDENT, .dup_mmap = paravirt_nop, .exit_mmap = paravirt_nop, diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index 9fe644f4861..d9f32e6d6ab 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -12,6 +12,18 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc"); +unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) +{ + /* arg in %eax, return in %eax */ + return 0; +} + +unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) +{ + /* arg in %edx:%eax, return in %edx:%eax */ + return 0; +} + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 061d01df9ae..3f08f34f93e 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -19,6 +19,21 @@ DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl"); DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); +DEF_NATIVE(, mov32, "mov %edi, %eax"); +DEF_NATIVE(, mov64, "mov %rdi, %rax"); + +unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) +{ + return paravirt_patch_insns(insnbuf, len, + start__mov32, end__mov32); +} + +unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) +{ + return paravirt_patch_insns(insnbuf, len, + start__mov64, end__mov64); +} + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { diff --git a/arch/x86/kernel/probe_32.c b/arch/x86/kernel/probe_32.c new file mode 100644 index 00000000000..22337b75de6 --- /dev/null +++ b/arch/x86/kernel/probe_32.c @@ -0,0 +1,411 @@ +/* + * Default generic APIC driver. This handles up to 8 CPUs. + * + * Copyright 2003 Andi Kleen, SuSE Labs. + * Subject to the GNU Public License, v.2 + * + * Generic x86 APIC driver probe layer. + */ +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <asm/fixmap.h> +#include <asm/mpspec.h> +#include <asm/apicdef.h> +#include <asm/genapic.h> +#include <asm/setup.h> + +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <asm/mpspec.h> +#include <asm/genapic.h> +#include <asm/fixmap.h> +#include <asm/apicdef.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <asm/genapic.h> +#include <asm/ipi.h> + +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <asm/acpi.h> +#include <asm/arch_hooks.h> +#include <asm/e820.h> +#include <asm/setup.h> + +#include <asm/genapic.h> + +#ifdef CONFIG_HOTPLUG_CPU +#define DEFAULT_SEND_IPI (1) +#else +#define DEFAULT_SEND_IPI (0) +#endif + +int no_broadcast = DEFAULT_SEND_IPI; + +#ifdef CONFIG_X86_LOCAL_APIC + +static void default_vector_allocation_domain(int cpu, struct cpumask *retmask) +{ + /* + * Careful. Some cpus do not strictly honor the set of cpus + * specified in the interrupt destination when using lowest + * priority interrupt delivery mode. + * + * In particular there was a hyperthreading cpu observed to + * deliver interrupts to the wrong hyperthread when only one + * hyperthread was specified in the interrupt desitination. + */ + *retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } }; +} + +/* should be called last. */ +static int probe_default(void) +{ + return 1; +} + +struct genapic apic_default = { + + .name = "default", + .probe = probe_default, + .acpi_madt_oem_check = NULL, + .apic_id_registered = default_apic_id_registered, + + .irq_delivery_mode = dest_LowestPrio, + /* logical delivery broadcast to all CPUs: */ + .irq_dest_mode = 1, + + .target_cpus = default_target_cpus, + .disable_esr = 0, + .dest_logical = APIC_DEST_LOGICAL, + .check_apicid_used = default_check_apicid_used, + .check_apicid_present = default_check_apicid_present, + + .vector_allocation_domain = default_vector_allocation_domain, + .init_apic_ldr = default_init_apic_ldr, + + .ioapic_phys_id_map = default_ioapic_phys_id_map, + .setup_apic_routing = default_setup_apic_routing, + .multi_timer_check = NULL, + .apicid_to_node = default_apicid_to_node, + .cpu_to_logical_apicid = default_cpu_to_logical_apicid, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = default_apicid_to_cpu_present, + .setup_portio_remap = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = default_phys_pkg_id, + .mps_oem_check = NULL, + + .get_apic_id = default_get_apic_id, + .set_apic_id = NULL, + .apic_id_mask = 0x0F << 24, + + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + + .send_IPI_mask = default_send_IPI_mask_logical, + .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical, + .send_IPI_allbutself = default_send_IPI_allbutself, + .send_IPI_all = default_send_IPI_all, + .send_IPI_self = default_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + + .wait_for_init_deassert = default_wait_for_init_deassert, + + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = default_inquire_remote_apic, +}; + +extern struct genapic apic_numaq; +extern struct genapic apic_summit; +extern struct genapic apic_bigsmp; +extern struct genapic apic_es7000; +extern struct genapic apic_default; + +struct genapic *apic = &apic_default; + +static struct genapic *apic_probe[] __initdata = { +#ifdef CONFIG_X86_NUMAQ + &apic_numaq, +#endif +#ifdef CONFIG_X86_SUMMIT + &apic_summit, +#endif +#ifdef CONFIG_X86_BIGSMP + &apic_bigsmp, +#endif +#ifdef CONFIG_X86_ES7000 + &apic_es7000, +#endif + &apic_default, /* must be last */ + NULL, +}; + +static int cmdline_apic __initdata; +static int __init parse_apic(char *arg) +{ + int i; + + if (!arg) + return -EINVAL; + + for (i = 0; apic_probe[i]; i++) { + if (!strcmp(apic_probe[i]->name, arg)) { + apic = apic_probe[i]; + cmdline_apic = 1; + return 0; + } + } + + if (x86_quirks->update_genapic) + x86_quirks->update_genapic(); + + /* Parsed again by __setup for debug/verbose */ + return 0; +} +early_param("apic", parse_apic); + +void __init generic_bigsmp_probe(void) +{ +#ifdef CONFIG_X86_BIGSMP + /* + * This routine is used to switch to bigsmp mode when + * - There is no apic= option specified by the user + * - generic_apic_probe() has chosen apic_default as the sub_arch + * - we find more than 8 CPUs in acpi LAPIC listing with xAPIC support + */ + + if (!cmdline_apic && apic == &apic_default) { + if (apic_bigsmp.probe()) { + apic = &apic_bigsmp; + if (x86_quirks->update_genapic) + x86_quirks->update_genapic(); + printk(KERN_INFO "Overriding APIC driver with %s\n", + apic->name); + } + } +#endif +} + +void __init generic_apic_probe(void) +{ + if (!cmdline_apic) { + int i; + for (i = 0; apic_probe[i]; i++) { + if (apic_probe[i]->probe()) { + apic = apic_probe[i]; + break; + } + } + /* Not visible without early console */ + if (!apic_probe[i]) + panic("Didn't find an APIC driver"); + + if (x86_quirks->update_genapic) + x86_quirks->update_genapic(); + } + printk(KERN_INFO "Using APIC driver %s\n", apic->name); +} + +/* These functions can switch the APIC even after the initial ->probe() */ + +int __init +generic_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) +{ + int i; + + for (i = 0; apic_probe[i]; ++i) { + if (!apic_probe[i]->mps_oem_check) + continue; + if (!apic_probe[i]->mps_oem_check(mpc, oem, productid)) + continue; + + if (!cmdline_apic) { + apic = apic_probe[i]; + if (x86_quirks->update_genapic) + x86_quirks->update_genapic(); + printk(KERN_INFO "Switched to APIC driver `%s'.\n", + apic->name); + } + return 1; + } + return 0; +} + +int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + int i; + + for (i = 0; apic_probe[i]; ++i) { + if (!apic_probe[i]->acpi_madt_oem_check) + continue; + if (!apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) + continue; + + if (!cmdline_apic) { + apic = apic_probe[i]; + if (x86_quirks->update_genapic) + x86_quirks->update_genapic(); + printk(KERN_INFO "Switched to APIC driver `%s'.\n", + apic->name); + } + return 1; + } + return 0; +} + +#endif /* CONFIG_X86_LOCAL_APIC */ + +/** + * pre_intr_init_hook - initialisation prior to setting up interrupt vectors + * + * Description: + * Perform any necessary interrupt initialisation prior to setting up + * the "ordinary" interrupt call gates. For legacy reasons, the ISA + * interrupts should be initialised here if the machine emulates a PC + * in any way. + **/ +void __init pre_intr_init_hook(void) +{ + if (x86_quirks->arch_pre_intr_init) { + if (x86_quirks->arch_pre_intr_init()) + return; + } + init_ISA_irqs(); +} + +/** + * intr_init_hook - post gate setup interrupt initialisation + * + * Description: + * Fill in any interrupts that may have been left out by the general + * init_IRQ() routine. interrupts having to do with the machine rather + * than the devices on the I/O bus (like APIC interrupts in intel MP + * systems) are started here. + **/ +void __init intr_init_hook(void) +{ + if (x86_quirks->arch_intr_init) { + if (x86_quirks->arch_intr_init()) + return; + } +} + +/** + * pre_setup_arch_hook - hook called prior to any setup_arch() execution + * + * Description: + * generally used to activate any machine specific identification + * routines that may be needed before setup_arch() runs. On Voyager + * this is used to get the board revision and type. + **/ +void __init pre_setup_arch_hook(void) +{ +} + +/** + * trap_init_hook - initialise system specific traps + * + * Description: + * Called as the final act of trap_init(). Used in VISWS to initialise + * the various board specific APIC traps. + **/ +void __init trap_init_hook(void) +{ + if (x86_quirks->arch_trap_init) { + if (x86_quirks->arch_trap_init()) + return; + } +} + +static struct irqaction irq0 = { + .handler = timer_interrupt, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL, + .mask = CPU_MASK_NONE, + .name = "timer" +}; + +/** + * pre_time_init_hook - do any specific initialisations before. + * + **/ +void __init pre_time_init_hook(void) +{ + if (x86_quirks->arch_pre_time_init) + x86_quirks->arch_pre_time_init(); +} + +/** + * time_init_hook - do any specific initialisations for the system timer. + * + * Description: + * Must plug the system timer interrupt source at HZ into the IRQ listed + * in irq_vectors.h:TIMER_IRQ + **/ +void __init time_init_hook(void) +{ + if (x86_quirks->arch_time_init) { + /* + * A nonzero return code does not mean failure, it means + * that the architecture quirk does not want any + * generic (timer) setup to be performed after this: + */ + if (x86_quirks->arch_time_init()) + return; + } + + irq0.mask = cpumask_of_cpu(0); + setup_irq(0, &irq0); +} + +#ifdef CONFIG_MCA +/** + * mca_nmi_hook - hook into MCA specific NMI chain + * + * Description: + * The MCA (Microchannel Architecture) has an NMI chain for NMI sources + * along the MCA bus. Use this to hook into that chain if you will need + * it. + **/ +void mca_nmi_hook(void) +{ + /* + * If I recall correctly, there's a whole bunch of other things that + * we can do to check for NMI problems, but that's all I know about + * at the moment. + */ + pr_warning("NMI generated from unknown source!\n"); +} +#endif + +static __init int no_ipi_broadcast(char *str) +{ + get_option(&str, &no_broadcast); + pr_info("Using %s mode\n", + no_broadcast ? "No IPI Broadcast" : "IPI Broadcast"); + return 1; +} +__setup("no_ipi_broadcast=", no_ipi_broadcast); + +static int __init print_ipi_mode(void) +{ + pr_info("Using IPI %s mode\n", + no_broadcast ? "No-Shortcut" : "Shortcut"); + return 0; +} + +late_initcall(print_ipi_mode); + diff --git a/arch/x86/kernel/probe_roms_32.c b/arch/x86/kernel/probe_roms_32.c index 675a48c404a..071e7fea42e 100644 --- a/arch/x86/kernel/probe_roms_32.c +++ b/arch/x86/kernel/probe_roms_32.c @@ -18,7 +18,7 @@ #include <asm/setup.h> #include <asm/sections.h> #include <asm/io.h> -#include <setup_arch.h> +#include <asm/setup_arch.h> static struct resource system_rom_resource = { .name = "System ROM", diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e68bb9e3086..87b69d4fac1 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -180,6 +180,9 @@ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) trace_power_start(&it, POWER_CSTATE, (ax>>4)+1); if (!need_resched()) { + if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) + clflush((void *)¤t_thread_info()->flags); + __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); if (!need_resched()) @@ -194,6 +197,9 @@ static void mwait_idle(void) struct power_trace it; if (!need_resched()) { trace_power_start(&it, POWER_CSTATE, 1); + if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) + clflush((void *)¤t_thread_info()->flags); + __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); if (!need_resched()) @@ -344,7 +350,7 @@ static void c1e_idle(void) void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_SMP +#ifdef CONFIG_SMP if (pm_idle == poll_idle && smp_num_siblings > 1) { printk(KERN_WARNING "WARNING: polling idle and HT enabled," " performance may degrade.\n"); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a546f55c77b..fec79ad85dc 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -11,6 +11,7 @@ #include <stdarg.h> +#include <linux/stackprotector.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/sched.h> @@ -66,9 +67,6 @@ asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); -DEFINE_PER_CPU(int, cpu_number); -EXPORT_PER_CPU_SYMBOL(cpu_number); - /* * Return saved PC of a blocked thread. */ @@ -94,6 +92,15 @@ void cpu_idle(void) { int cpu = smp_processor_id(); + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. CPU0 already has it initialized but no harm in + * doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); + current_thread_info()->status |= TS_POLLING; /* endless idle loop with no priority at all */ @@ -111,7 +118,6 @@ void cpu_idle(void) play_dead(); local_irq_disable(); - __get_cpu_var(irq_stat).idle_timestamp = jiffies; /* Don't trace irqs off for idle */ stop_critical_timings(); pm_idle(); @@ -135,7 +141,7 @@ void __show_regs(struct pt_regs *regs, int all) if (user_mode_vm(regs)) { sp = regs->sp; ss = regs->ss & 0xffff; - savesegment(gs, gs); + gs = get_user_gs(regs); } else { sp = (unsigned long) (®s->sp); savesegment(ss, ss); @@ -216,6 +222,7 @@ int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) regs.ds = __USER_DS; regs.es = __USER_DS; regs.fs = __KERNEL_PERCPU; + regs.gs = __KERNEL_STACK_CANARY; regs.orig_ax = -1; regs.ip = (unsigned long) kernel_thread_helper; regs.cs = __KERNEL_CS | get_kernel_rpl(); @@ -308,7 +315,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, p->thread.ip = (unsigned long) ret_from_fork; - savesegment(gs, p->thread.gs); + task_user_gs(p) = get_user_gs(regs); tsk = current; if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { @@ -346,7 +353,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { - __asm__("movl %0, %%gs" : : "r"(0)); + set_user_gs(regs, 0); regs->fs = 0; set_fs(USER_DS); regs->ds = __USER_DS; @@ -543,7 +550,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * used %fs or %gs (it does not today), or if the kernel is * running inside of a hypervisor layer. */ - savesegment(gs, prev->gs); + lazy_save_gs(prev->gs); /* * Load the per-thread Thread-Local Storage descriptor. @@ -589,31 +596,31 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Restore %gs if needed (which is common) */ if (prev->gs | next->gs) - loadsegment(gs, next->gs); + lazy_load_gs(next->gs); - x86_write_percpu(current_task, next_p); + percpu_write(current_task, next_p); return prev_p; } -asmlinkage int sys_fork(struct pt_regs regs) +int sys_fork(struct pt_regs *regs) { - return do_fork(SIGCHLD, regs.sp, ®s, 0, NULL, NULL); + return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); } -asmlinkage int sys_clone(struct pt_regs regs) +int sys_clone(struct pt_regs *regs) { unsigned long clone_flags; unsigned long newsp; int __user *parent_tidptr, *child_tidptr; - clone_flags = regs.bx; - newsp = regs.cx; - parent_tidptr = (int __user *)regs.dx; - child_tidptr = (int __user *)regs.di; + clone_flags = regs->bx; + newsp = regs->cx; + parent_tidptr = (int __user *)regs->dx; + child_tidptr = (int __user *)regs->di; if (!newsp) - newsp = regs.sp; - return do_fork(clone_flags, newsp, ®s, 0, parent_tidptr, child_tidptr); + newsp = regs->sp; + return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr); } /* @@ -626,27 +633,27 @@ asmlinkage int sys_clone(struct pt_regs regs) * do not have enough call-clobbered registers to hold all * the information you need. */ -asmlinkage int sys_vfork(struct pt_regs regs) +int sys_vfork(struct pt_regs *regs) { - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.sp, ®s, 0, NULL, NULL); + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, NULL, NULL); } /* * sys_execve() executes a new program. */ -asmlinkage int sys_execve(struct pt_regs regs) +int sys_execve(struct pt_regs *regs) { int error; char *filename; - filename = getname((char __user *) regs.bx); + filename = getname((char __user *) regs->bx); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; error = do_execve(filename, - (char __user * __user *) regs.cx, - (char __user * __user *) regs.dx, - ®s); + (char __user * __user *) regs->cx, + (char __user * __user *) regs->dx, + regs); if (error == 0) { /* Make sure we don't return using sysenter.. */ set_thread_flag(TIF_IRET); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 416fb9282f4..836ef6575f0 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -16,6 +16,7 @@ #include <stdarg.h> +#include <linux/stackprotector.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/sched.h> @@ -40,13 +41,13 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> +#include <linux/dmi.h> #include <asm/pgtable.h> #include <asm/system.h> #include <asm/processor.h> #include <asm/i387.h> #include <asm/mmu_context.h> -#include <asm/pda.h> #include <asm/prctl.h> #include <asm/desc.h> #include <asm/proto.h> @@ -57,6 +58,12 @@ asmlinkage extern void ret_from_fork(void); +DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; +EXPORT_PER_CPU_SYMBOL(current_task); + +DEFINE_PER_CPU(unsigned long, old_rsp); +static DEFINE_PER_CPU(unsigned char, is_idle); + unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; static ATOMIC_NOTIFIER_HEAD(idle_notifier); @@ -75,13 +82,13 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister); void enter_idle(void) { - write_pda(isidle, 1); + percpu_write(is_idle, 1); atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL); } static void __exit_idle(void) { - if (test_and_clear_bit_pda(0, isidle) == 0) + if (x86_test_and_clear_bit_percpu(0, is_idle) == 0) return; atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL); } @@ -111,6 +118,16 @@ static inline void play_dead(void) void cpu_idle(void) { current_thread_info()->status |= TS_POLLING; + + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. CPU0 already has it initialized but no harm in + * doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); + /* endless idle loop with no priority at all */ while (1) { tick_nohz_stop_sched_tick(1); @@ -151,14 +168,18 @@ void __show_regs(struct pt_regs *regs, int all) unsigned long d0, d1, d2, d3, d6, d7; unsigned int fsindex, gsindex; unsigned int ds, cs, es; + const char *board; printk("\n"); print_modules(); - printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s\n", + board = dmi_get_system_info(DMI_PRODUCT_NAME); + if (!board) + board = ""; + printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s\n", current->pid, current->comm, print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); + init_utsname()->version, board); printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); printk_address(regs->ip, 1); printk(KERN_INFO "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, @@ -392,7 +413,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) load_gs_index(0); regs->ip = new_ip; regs->sp = new_sp; - write_pda(oldrsp, new_sp); + percpu_write(old_rsp, new_sp); regs->cs = __USER_CS; regs->ss = __USER_DS; regs->flags = 0x200; @@ -613,21 +634,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* * Switch the PDA and FPU contexts. */ - prev->usersp = read_pda(oldrsp); - write_pda(oldrsp, next->usersp); - write_pda(pcurrent, next_p); + prev->usersp = percpu_read(old_rsp); + percpu_write(old_rsp, next->usersp); + percpu_write(current_task, next_p); - write_pda(kernelstack, + percpu_write(kernel_stack, (unsigned long)task_stack_page(next_p) + - THREAD_SIZE - PDA_STACKOFFSET); -#ifdef CONFIG_CC_STACKPROTECTOR - write_pda(stack_canary, next_p->stack_canary); - /* - * Build time only check to make sure the stack_canary is at - * offset 40 in the pda; this is a gcc ABI requirement - */ - BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40); -#endif + THREAD_SIZE - KERNEL_STACK_OFFSET); /* * Now maybe reload the debug registers and handle I/O bitmaps diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 0a5df5f82fb..7ec39ab37a2 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -75,10 +75,7 @@ static inline bool invalid_selector(u16 value) static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) { BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0); - regno >>= 2; - if (regno > FS) - --regno; - return ®s->bx + regno; + return ®s->bx + (regno >> 2); } static u16 get_segment_reg(struct task_struct *task, unsigned long offset) @@ -90,9 +87,10 @@ static u16 get_segment_reg(struct task_struct *task, unsigned long offset) if (offset != offsetof(struct user_regs_struct, gs)) retval = *pt_regs_access(task_pt_regs(task), offset); else { - retval = task->thread.gs; if (task == current) - savesegment(gs, retval); + retval = get_user_gs(task_pt_regs(task)); + else + retval = task_user_gs(task); } return retval; } @@ -126,13 +124,10 @@ static int set_segment_reg(struct task_struct *task, break; case offsetof(struct user_regs_struct, gs): - task->thread.gs = value; if (task == current) - /* - * The user-mode %gs is not affected by - * kernel entry, so we must update the CPU. - */ - loadsegment(gs, value); + set_user_gs(task_pt_regs(task), value); + else + task_user_gs(task) = value; } return 0; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f8536fee5c1..32e8f0af292 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -24,7 +24,7 @@ # include <asm/iommu.h> #endif -#include <mach_ipi.h> +#include <asm/genapic.h> /* * Power off function, if any @@ -651,7 +651,7 @@ static int crash_nmi_callback(struct notifier_block *self, static void smp_send_nmi_allbutself(void) { - send_IPI_allbutself(NMI_VECTOR); + apic->send_IPI_allbutself(NMI_VECTOR); } static struct notifier_block crash_nmi_nb = { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f41c4486c27..8fce6c71451 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -81,7 +81,7 @@ #include <asm/io_apic.h> #include <asm/ist.h> #include <asm/vmi.h> -#include <setup_arch.h> +#include <asm/setup_arch.h> #include <asm/bios_ebda.h> #include <asm/cacheflush.h> #include <asm/processor.h> @@ -97,7 +97,7 @@ #include <asm/mmu_context.h> #include <asm/proto.h> -#include <mach_apic.h> +#include <asm/genapic.h> #include <asm/paravirt.h> #include <asm/hypervisor.h> @@ -112,6 +112,20 @@ #define ARCH_SETUP #endif +unsigned int boot_cpu_id __read_mostly; + +#ifdef CONFIG_X86_64 +int default_cpu_present_to_apicid(int mps_cpu) +{ + return __default_cpu_present_to_apicid(mps_cpu); +} + +int default_check_phys_apicid_present(int boot_cpu_physical_apicid) +{ + return __default_check_phys_apicid_present(boot_cpu_physical_apicid); +} +#endif + #ifndef CONFIG_DEBUG_BOOT_PARAMS struct boot_params __initdata boot_params; #else @@ -588,10 +602,9 @@ early_param("elfcorehdr", setup_elfcorehdr); static int __init default_update_genapic(void) { -#ifdef CONFIG_X86_SMP -# if defined(CONFIG_X86_GENERICARCH) || defined(CONFIG_X86_64) - genapic->wakeup_cpu = wakeup_secondary_cpu_via_init; -# endif +#ifdef CONFIG_SMP + if (!apic->wakeup_cpu) + apic->wakeup_cpu = wakeup_secondary_cpu_via_init; #endif return 0; @@ -607,7 +620,7 @@ struct x86_quirks *x86_quirks __initdata = &default_x86_quirks; static int __init dmi_low_memory_corruption(const struct dmi_system_id *d) { printk(KERN_NOTICE - "%s detected: BIOS may corrupt low RAM, working it around.\n", + "%s detected: BIOS may corrupt low RAM, working around it.\n", d->ident); e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED); @@ -892,12 +905,11 @@ void __init setup_arch(char **cmdline_p) */ acpi_reserve_bootmem(); #endif -#ifdef CONFIG_X86_FIND_SMP_CONFIG /* * Find and reserve possible boot-time SMP configuration: */ find_smp_config(); -#endif + reserve_crashkernel(); #ifdef CONFIG_X86_64 @@ -924,9 +936,7 @@ void __init setup_arch(char **cmdline_p) map_vsyscall(); #endif -#ifdef CONFIG_X86_GENERICARCH generic_apic_probe(); -#endif early_quirks(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index e4c32e1a0ba..d992e6cff73 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -13,146 +13,47 @@ #include <asm/mpspec.h> #include <asm/apicdef.h> #include <asm/highmem.h> +#include <asm/proto.h> #include <asm/cpumask.h> +#include <asm/cpu.h> +#include <asm/stackprotector.h> -#ifdef CONFIG_X86_LOCAL_APIC -unsigned int num_processors; -unsigned disabled_cpus __cpuinitdata; -/* Processor that is doing the boot up */ -unsigned int boot_cpu_physical_apicid = -1U; -EXPORT_SYMBOL(boot_cpu_physical_apicid); -unsigned int max_physical_apicid; - -/* Bitmask of physically existing CPUs */ -physid_mask_t phys_cpu_present_map; -#endif - -/* map cpu index to physical APIC ID */ -DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID); -DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID); -EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); -EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid); - -#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64) -#define X86_64_NUMA 1 - -/* map cpu index to node index */ -DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); -EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); - -/* which logical CPUs are on which nodes */ -cpumask_t *node_to_cpumask_map; -EXPORT_SYMBOL(node_to_cpumask_map); - -/* setup node_to_cpumask_map */ -static void __init setup_node_to_cpumask_map(void); - +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +# define DBG(x...) printk(KERN_DEBUG x) #else -static inline void setup_node_to_cpumask_map(void) { } +# define DBG(x...) #endif -#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP) -/* - * Copy data used in early init routines from the initial arrays to the - * per cpu data areas. These arrays then become expendable and the - * *_early_ptr's are zeroed indicating that the static arrays are gone. - */ -static void __init setup_per_cpu_maps(void) -{ - int cpu; +DEFINE_PER_CPU(int, cpu_number); +EXPORT_PER_CPU_SYMBOL(cpu_number); - for_each_possible_cpu(cpu) { - per_cpu(x86_cpu_to_apicid, cpu) = - early_per_cpu_map(x86_cpu_to_apicid, cpu); - per_cpu(x86_bios_cpu_apicid, cpu) = - early_per_cpu_map(x86_bios_cpu_apicid, cpu); -#ifdef X86_64_NUMA - per_cpu(x86_cpu_to_node_map, cpu) = - early_per_cpu_map(x86_cpu_to_node_map, cpu); +#ifdef CONFIG_X86_64 +#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load) +#else +#define BOOT_PERCPU_OFFSET 0 #endif - } - /* indicate the early static arrays will soon be gone */ - early_per_cpu_ptr(x86_cpu_to_apicid) = NULL; - early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL; -#ifdef X86_64_NUMA - early_per_cpu_ptr(x86_cpu_to_node_map) = NULL; -#endif -} +DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET; +EXPORT_PER_CPU_SYMBOL(this_cpu_off); -#ifdef CONFIG_X86_32 -/* - * Great future not-so-futuristic plan: make i386 and x86_64 do it - * the same way - */ -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { + [0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET, +}; EXPORT_SYMBOL(__per_cpu_offset); -static inline void setup_cpu_pda_map(void) { } - -#elif !defined(CONFIG_SMP) -static inline void setup_cpu_pda_map(void) { } - -#else /* CONFIG_SMP && CONFIG_X86_64 */ - -/* - * Allocate cpu_pda pointer table and array via alloc_bootmem. - */ -static void __init setup_cpu_pda_map(void) -{ - char *pda; - struct x8664_pda **new_cpu_pda; - unsigned long size; - int cpu; - - size = roundup(sizeof(struct x8664_pda), cache_line_size()); - - /* allocate cpu_pda array and pointer table */ - { - unsigned long tsize = nr_cpu_ids * sizeof(void *); - unsigned long asize = size * (nr_cpu_ids - 1); - tsize = roundup(tsize, cache_line_size()); - new_cpu_pda = alloc_bootmem(tsize + asize); - pda = (char *)new_cpu_pda + tsize; - } - - /* initialize pointer table to static pda's */ - for_each_possible_cpu(cpu) { - if (cpu == 0) { - /* leave boot cpu pda in place */ - new_cpu_pda[0] = cpu_pda(0); - continue; - } - new_cpu_pda[cpu] = (struct x8664_pda *)pda; - new_cpu_pda[cpu]->in_bootmem = 1; - pda += size; - } - - /* point to new pointer table */ - _cpu_pda = new_cpu_pda; -} - -#endif /* CONFIG_SMP && CONFIG_X86_64 */ - -#ifdef CONFIG_X86_64 - -/* correctly size the local cpu masks */ -static void __init setup_cpu_local_masks(void) +static inline void setup_percpu_segment(int cpu) { - alloc_bootmem_cpumask_var(&cpu_initialized_mask); - alloc_bootmem_cpumask_var(&cpu_callin_mask); - alloc_bootmem_cpumask_var(&cpu_callout_mask); - alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); -} - -#else /* CONFIG_X86_32 */ +#ifdef CONFIG_X86_32 + struct desc_struct gdt; -static inline void setup_cpu_local_masks(void) -{ + pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF, + 0x2 | DESCTYPE_S, 0x8); + gdt.s = 1; + write_gdt_entry(get_cpu_gdt_table(cpu), + GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S); +#endif } -#endif /* CONFIG_X86_32 */ - /* * Great future plan: * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data. @@ -160,18 +61,12 @@ static inline void setup_cpu_local_masks(void) */ void __init setup_per_cpu_areas(void) { - ssize_t size, old_size; + ssize_t size; char *ptr; int cpu; - unsigned long align = 1; - - /* Setup cpu_pda map */ - setup_cpu_pda_map(); /* Copy section for each CPU (we discard the original) */ - old_size = PERCPU_ENOUGH_ROOM; - align = max_t(unsigned long, PAGE_SIZE, align); - size = roundup(old_size, align); + size = roundup(PERCPU_ENOUGH_ROOM, PAGE_SIZE); pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n", NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids); @@ -180,30 +75,68 @@ void __init setup_per_cpu_areas(void) for_each_possible_cpu(cpu) { #ifndef CONFIG_NEED_MULTIPLE_NODES - ptr = __alloc_bootmem(size, align, - __pa(MAX_DMA_ADDRESS)); + ptr = alloc_bootmem_pages(size); #else int node = early_cpu_to_node(cpu); if (!node_online(node) || !NODE_DATA(node)) { - ptr = __alloc_bootmem(size, align, - __pa(MAX_DMA_ADDRESS)); + ptr = alloc_bootmem_pages(size); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d at %016lx\n", cpu, __pa(ptr)); } else { - ptr = __alloc_bootmem_node(NODE_DATA(node), size, align, - __pa(MAX_DMA_ADDRESS)); + ptr = alloc_bootmem_pages_node(NODE_DATA(node), size); pr_debug("per cpu data for cpu%d on node%d at %016lx\n", cpu, node, __pa(ptr)); } #endif + + memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start); per_cpu_offset(cpu) = ptr - __per_cpu_start; - memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); + per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu); + per_cpu(cpu_number, cpu) = cpu; + setup_percpu_segment(cpu); + setup_stack_canary_segment(cpu); + /* + * Copy data used in early init routines from the + * initial arrays to the per cpu data areas. These + * arrays then become expendable and the *_early_ptr's + * are zeroed indicating that the static arrays are + * gone. + */ +#ifdef CONFIG_X86_LOCAL_APIC + per_cpu(x86_cpu_to_apicid, cpu) = + early_per_cpu_map(x86_cpu_to_apicid, cpu); + per_cpu(x86_bios_cpu_apicid, cpu) = + early_per_cpu_map(x86_bios_cpu_apicid, cpu); +#endif +#ifdef CONFIG_X86_64 + per_cpu(irq_stack_ptr, cpu) = + per_cpu(irq_stack_union.irq_stack, cpu) + + IRQ_STACK_SIZE - 64; +#ifdef CONFIG_NUMA + per_cpu(x86_cpu_to_node_map, cpu) = + early_per_cpu_map(x86_cpu_to_node_map, cpu); +#endif +#endif + /* + * Up to this point, the boot CPU has been using .data.init + * area. Reload any changed state for the boot CPU. + */ + if (cpu == boot_cpu_id) + switch_to_new_gdt(cpu); + + DBG("PERCPU: cpu %4d %p\n", cpu, ptr); } - /* Setup percpu data maps */ - setup_per_cpu_maps(); + /* indicate the early static arrays will soon be gone */ +#ifdef CONFIG_X86_LOCAL_APIC + early_per_cpu_ptr(x86_cpu_to_apicid) = NULL; + early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL; +#endif +#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA) + early_per_cpu_ptr(x86_cpu_to_node_map) = NULL; +#endif /* Setup node to cpumask map */ setup_node_to_cpumask_map(); @@ -211,199 +144,3 @@ void __init setup_per_cpu_areas(void) /* Setup cpu initialized, callin, callout masks */ setup_cpu_local_masks(); } - -#endif - -#ifdef X86_64_NUMA - -/* - * Allocate node_to_cpumask_map based on number of available nodes - * Requires node_possible_map to be valid. - * - * Note: node_to_cpumask() is not valid until after this is done. - */ -static void __init setup_node_to_cpumask_map(void) -{ - unsigned int node, num = 0; - cpumask_t *map; - - /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) { - for_each_node_mask(node, node_possible_map) - num = node; - nr_node_ids = num + 1; - } - - /* allocate the map */ - map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t)); - - pr_debug("Node to cpumask map at %p for %d nodes\n", - map, nr_node_ids); - - /* node_to_cpumask() will now work */ - node_to_cpumask_map = map; -} - -void __cpuinit numa_set_node(int cpu, int node) -{ - int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); - - if (cpu_pda(cpu) && node != NUMA_NO_NODE) - cpu_pda(cpu)->nodenumber = node; - - if (cpu_to_node_map) - cpu_to_node_map[cpu] = node; - - else if (per_cpu_offset(cpu)) - per_cpu(x86_cpu_to_node_map, cpu) = node; - - else - pr_debug("Setting node for non-present cpu %d\n", cpu); -} - -void __cpuinit numa_clear_node(int cpu) -{ - numa_set_node(cpu, NUMA_NO_NODE); -} - -#ifndef CONFIG_DEBUG_PER_CPU_MAPS - -void __cpuinit numa_add_cpu(int cpu) -{ - cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); -} - -void __cpuinit numa_remove_cpu(int cpu) -{ - cpu_clear(cpu, node_to_cpumask_map[cpu_to_node(cpu)]); -} - -#else /* CONFIG_DEBUG_PER_CPU_MAPS */ - -/* - * --------- debug versions of the numa functions --------- - */ -static void __cpuinit numa_set_cpumask(int cpu, int enable) -{ - int node = cpu_to_node(cpu); - cpumask_t *mask; - char buf[64]; - - if (node_to_cpumask_map == NULL) { - printk(KERN_ERR "node_to_cpumask_map NULL\n"); - dump_stack(); - return; - } - - mask = &node_to_cpumask_map[node]; - if (enable) - cpu_set(cpu, *mask); - else - cpu_clear(cpu, *mask); - - cpulist_scnprintf(buf, sizeof(buf), mask); - printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", - enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf); -} - -void __cpuinit numa_add_cpu(int cpu) -{ - numa_set_cpumask(cpu, 1); -} - -void __cpuinit numa_remove_cpu(int cpu) -{ - numa_set_cpumask(cpu, 0); -} - -int cpu_to_node(int cpu) -{ - if (early_per_cpu_ptr(x86_cpu_to_node_map)) { - printk(KERN_WARNING - "cpu_to_node(%d): usage too early!\n", cpu); - dump_stack(); - return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; - } - return per_cpu(x86_cpu_to_node_map, cpu); -} -EXPORT_SYMBOL(cpu_to_node); - -/* - * Same function as cpu_to_node() but used if called before the - * per_cpu areas are setup. - */ -int early_cpu_to_node(int cpu) -{ - if (early_per_cpu_ptr(x86_cpu_to_node_map)) - return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; - - if (!per_cpu_offset(cpu)) { - printk(KERN_WARNING - "early_cpu_to_node(%d): no per_cpu area!\n", cpu); - dump_stack(); - return NUMA_NO_NODE; - } - return per_cpu(x86_cpu_to_node_map, cpu); -} - - -/* empty cpumask */ -static const cpumask_t cpu_mask_none; - -/* - * Returns a pointer to the bitmask of CPUs on Node 'node'. - */ -const cpumask_t *cpumask_of_node(int node) -{ - if (node_to_cpumask_map == NULL) { - printk(KERN_WARNING - "cpumask_of_node(%d): no node_to_cpumask_map!\n", - node); - dump_stack(); - return (const cpumask_t *)&cpu_online_map; - } - if (node >= nr_node_ids) { - printk(KERN_WARNING - "cpumask_of_node(%d): node > nr_node_ids(%d)\n", - node, nr_node_ids); - dump_stack(); - return &cpu_mask_none; - } - return &node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(cpumask_of_node); - -/* - * Returns a bitmask of CPUs on Node 'node'. - * - * Side note: this function creates the returned cpumask on the stack - * so with a high NR_CPUS count, excessive stack space is used. The - * node_to_cpumask_ptr function should be used whenever possible. - */ -cpumask_t node_to_cpumask(int node) -{ - if (node_to_cpumask_map == NULL) { - printk(KERN_WARNING - "node_to_cpumask(%d): no node_to_cpumask_map!\n", node); - dump_stack(); - return cpu_online_map; - } - if (node >= nr_node_ids) { - printk(KERN_WARNING - "node_to_cpumask(%d): node > nr_node_ids(%d)\n", - node, nr_node_ids); - dump_stack(); - return cpu_mask_none; - } - return node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(node_to_cpumask); - -/* - * --------- end of debug versions of the numa functions --------- - */ - -#endif /* CONFIG_DEBUG_PER_CPU_MAPS */ - -#endif /* X86_64_NUMA */ - diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index df0587f24c5..7cdcd16885e 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -50,27 +50,23 @@ # define FIX_EFLAGS __FIX_EFLAGS #endif -#define COPY(x) { \ - err |= __get_user(regs->x, &sc->x); \ -} +#define COPY(x) do { \ + get_user_ex(regs->x, &sc->x); \ +} while (0) -#define COPY_SEG(seg) { \ - unsigned short tmp; \ - err |= __get_user(tmp, &sc->seg); \ - regs->seg = tmp; \ -} +#define GET_SEG(seg) ({ \ + unsigned short tmp; \ + get_user_ex(tmp, &sc->seg); \ + tmp; \ +}) -#define COPY_SEG_CPL3(seg) { \ - unsigned short tmp; \ - err |= __get_user(tmp, &sc->seg); \ - regs->seg = tmp | 3; \ -} +#define COPY_SEG(seg) do { \ + regs->seg = GET_SEG(seg); \ +} while (0) -#define GET_SEG(seg) { \ - unsigned short tmp; \ - err |= __get_user(tmp, &sc->seg); \ - loadsegment(seg, tmp); \ -} +#define COPY_SEG_CPL3(seg) do { \ + regs->seg = GET_SEG(seg) | 3; \ +} while (0) static int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, @@ -83,45 +79,49 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, /* Always make any pending restarted system calls return -EINTR */ current_thread_info()->restart_block.fn = do_no_restart_syscall; + get_user_try { + #ifdef CONFIG_X86_32 - GET_SEG(gs); - COPY_SEG(fs); - COPY_SEG(es); - COPY_SEG(ds); + set_user_gs(regs, GET_SEG(gs)); + COPY_SEG(fs); + COPY_SEG(es); + COPY_SEG(ds); #endif /* CONFIG_X86_32 */ - COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); - COPY(dx); COPY(cx); COPY(ip); + COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); + COPY(dx); COPY(cx); COPY(ip); #ifdef CONFIG_X86_64 - COPY(r8); - COPY(r9); - COPY(r10); - COPY(r11); - COPY(r12); - COPY(r13); - COPY(r14); - COPY(r15); + COPY(r8); + COPY(r9); + COPY(r10); + COPY(r11); + COPY(r12); + COPY(r13); + COPY(r14); + COPY(r15); #endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_32 - COPY_SEG_CPL3(cs); - COPY_SEG_CPL3(ss); + COPY_SEG_CPL3(cs); + COPY_SEG_CPL3(ss); #else /* !CONFIG_X86_32 */ - /* Kernel saves and restores only the CS segment register on signals, - * which is the bare minimum needed to allow mixed 32/64-bit code. - * App's signal handler can save/restore other segments if needed. */ - COPY_SEG_CPL3(cs); + /* Kernel saves and restores only the CS segment register on signals, + * which is the bare minimum needed to allow mixed 32/64-bit code. + * App's signal handler can save/restore other segments if needed. */ + COPY_SEG_CPL3(cs); #endif /* CONFIG_X86_32 */ - err |= __get_user(tmpflags, &sc->flags); - regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); - regs->orig_ax = -1; /* disable syscall checks */ + get_user_ex(tmpflags, &sc->flags); + regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); + regs->orig_ax = -1; /* disable syscall checks */ + + get_user_ex(buf, &sc->fpstate); + err |= restore_i387_xstate(buf); - err |= __get_user(buf, &sc->fpstate); - err |= restore_i387_xstate(buf); + get_user_ex(*pax, &sc->ax); + } get_user_catch(err); - err |= __get_user(*pax, &sc->ax); return err; } @@ -131,57 +131,55 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, { int err = 0; -#ifdef CONFIG_X86_32 - { - unsigned int tmp; + put_user_try { - savesegment(gs, tmp); - err |= __put_user(tmp, (unsigned int __user *)&sc->gs); - } - err |= __put_user(regs->fs, (unsigned int __user *)&sc->fs); - err |= __put_user(regs->es, (unsigned int __user *)&sc->es); - err |= __put_user(regs->ds, (unsigned int __user *)&sc->ds); +#ifdef CONFIG_X86_32 + put_user_ex(get_user_gs(regs), (unsigned int __user *)&sc->gs); + put_user_ex(regs->fs, (unsigned int __user *)&sc->fs); + put_user_ex(regs->es, (unsigned int __user *)&sc->es); + put_user_ex(regs->ds, (unsigned int __user *)&sc->ds); #endif /* CONFIG_X86_32 */ - err |= __put_user(regs->di, &sc->di); - err |= __put_user(regs->si, &sc->si); - err |= __put_user(regs->bp, &sc->bp); - err |= __put_user(regs->sp, &sc->sp); - err |= __put_user(regs->bx, &sc->bx); - err |= __put_user(regs->dx, &sc->dx); - err |= __put_user(regs->cx, &sc->cx); - err |= __put_user(regs->ax, &sc->ax); + put_user_ex(regs->di, &sc->di); + put_user_ex(regs->si, &sc->si); + put_user_ex(regs->bp, &sc->bp); + put_user_ex(regs->sp, &sc->sp); + put_user_ex(regs->bx, &sc->bx); + put_user_ex(regs->dx, &sc->dx); + put_user_ex(regs->cx, &sc->cx); + put_user_ex(regs->ax, &sc->ax); #ifdef CONFIG_X86_64 - err |= __put_user(regs->r8, &sc->r8); - err |= __put_user(regs->r9, &sc->r9); - err |= __put_user(regs->r10, &sc->r10); - err |= __put_user(regs->r11, &sc->r11); - err |= __put_user(regs->r12, &sc->r12); - err |= __put_user(regs->r13, &sc->r13); - err |= __put_user(regs->r14, &sc->r14); - err |= __put_user(regs->r15, &sc->r15); + put_user_ex(regs->r8, &sc->r8); + put_user_ex(regs->r9, &sc->r9); + put_user_ex(regs->r10, &sc->r10); + put_user_ex(regs->r11, &sc->r11); + put_user_ex(regs->r12, &sc->r12); + put_user_ex(regs->r13, &sc->r13); + put_user_ex(regs->r14, &sc->r14); + put_user_ex(regs->r15, &sc->r15); #endif /* CONFIG_X86_64 */ - err |= __put_user(current->thread.trap_no, &sc->trapno); - err |= __put_user(current->thread.error_code, &sc->err); - err |= __put_user(regs->ip, &sc->ip); + put_user_ex(current->thread.trap_no, &sc->trapno); + put_user_ex(current->thread.error_code, &sc->err); + put_user_ex(regs->ip, &sc->ip); #ifdef CONFIG_X86_32 - err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs); - err |= __put_user(regs->flags, &sc->flags); - err |= __put_user(regs->sp, &sc->sp_at_signal); - err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss); + put_user_ex(regs->cs, (unsigned int __user *)&sc->cs); + put_user_ex(regs->flags, &sc->flags); + put_user_ex(regs->sp, &sc->sp_at_signal); + put_user_ex(regs->ss, (unsigned int __user *)&sc->ss); #else /* !CONFIG_X86_32 */ - err |= __put_user(regs->flags, &sc->flags); - err |= __put_user(regs->cs, &sc->cs); - err |= __put_user(0, &sc->gs); - err |= __put_user(0, &sc->fs); + put_user_ex(regs->flags, &sc->flags); + put_user_ex(regs->cs, &sc->cs); + put_user_ex(0, &sc->gs); + put_user_ex(0, &sc->fs); #endif /* CONFIG_X86_32 */ - err |= __put_user(fpstate, &sc->fpstate); + put_user_ex(fpstate, &sc->fpstate); - /* non-iBCS2 extensions.. */ - err |= __put_user(mask, &sc->oldmask); - err |= __put_user(current->thread.cr2, &sc->cr2); + /* non-iBCS2 extensions.. */ + put_user_ex(mask, &sc->oldmask); + put_user_ex(current->thread.cr2, &sc->cr2); + } put_user_catch(err); return err; } @@ -336,43 +334,41 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) return -EFAULT; - err |= __put_user(sig, &frame->sig); - err |= __put_user(&frame->info, &frame->pinfo); - err |= __put_user(&frame->uc, &frame->puc); - err |= copy_siginfo_to_user(&frame->info, info); - if (err) - return -EFAULT; - - /* Create the ucontext. */ - if (cpu_has_xsave) - err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags); - else - err |= __put_user(0, &frame->uc.uc_flags); - err |= __put_user(0, &frame->uc.uc_link); - err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - if (err) - return -EFAULT; + put_user_try { + put_user_ex(sig, &frame->sig); + put_user_ex(&frame->info, &frame->pinfo); + put_user_ex(&frame->uc, &frame->puc); + err |= copy_siginfo_to_user(&frame->info, info); - /* Set up to return from userspace. */ - restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); - if (ka->sa.sa_flags & SA_RESTORER) - restorer = ka->sa.sa_restorer; - err |= __put_user(restorer, &frame->pretcode); + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + /* Set up to return from userspace. */ + restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); + if (ka->sa.sa_flags & SA_RESTORER) + restorer = ka->sa.sa_restorer; + put_user_ex(restorer, &frame->pretcode); - /* - * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - err |= __put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode); + /* + * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 + * + * WE DO NOT USE IT ANY MORE! It's only left here for historical + * reasons and because gdb uses it as a signature to notice + * signal handler stack frames. + */ + put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode); + } put_user_catch(err); if (err) return -EFAULT; @@ -436,28 +432,30 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, return -EFAULT; } - /* Create the ucontext. */ - if (cpu_has_xsave) - err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags); - else - err |= __put_user(0, &frame->uc.uc_flags); - err |= __put_user(0, &frame->uc.uc_link); - err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - /* Set up to return from userspace. If provided, use a stub - already in userspace. */ - /* x86-64 should always use SA_RESTORER. */ - if (ka->sa.sa_flags & SA_RESTORER) { - err |= __put_user(ka->sa.sa_restorer, &frame->pretcode); - } else { - /* could use a vstub here */ - return -EFAULT; - } + put_user_try { + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + put_user_ex(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + put_user_ex(sas_ss_flags(regs->sp), + &frame->uc.uc_stack.ss_flags); + put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + /* x86-64 should always use SA_RESTORER. */ + if (ka->sa.sa_flags & SA_RESTORER) { + put_user_ex(ka->sa.sa_restorer, &frame->pretcode); + } else { + /* could use a vstub here */ + err |= -EFAULT; + } + } put_user_catch(err); if (err) return -EFAULT; @@ -509,31 +507,41 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) { struct k_sigaction new_ka, old_ka; - int ret; + int ret = 0; if (act) { old_sigset_t mask; - if (!access_ok(VERIFY_READ, act, sizeof(*act)) || - __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_restorer, &act->sa_restorer)) + if (!access_ok(VERIFY_READ, act, sizeof(*act))) return -EFAULT; - __get_user(new_ka.sa.sa_flags, &act->sa_flags); - __get_user(mask, &act->sa_mask); + get_user_try { + get_user_ex(new_ka.sa.sa_handler, &act->sa_handler); + get_user_ex(new_ka.sa.sa_flags, &act->sa_flags); + get_user_ex(mask, &act->sa_mask); + get_user_ex(new_ka.sa.sa_restorer, &act->sa_restorer); + } get_user_catch(ret); + + if (ret) + return -EFAULT; siginitset(&new_ka.sa.sa_mask, mask); } ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || - __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer)) + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact))) return -EFAULT; - __put_user(old_ka.sa.sa_flags, &oact->sa_flags); - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); + put_user_try { + put_user_ex(old_ka.sa.sa_handler, &oact->sa_handler); + put_user_ex(old_ka.sa.sa_flags, &oact->sa_flags); + put_user_ex(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); + put_user_ex(old_ka.sa.sa_restorer, &oact->sa_restorer); + } put_user_catch(ret); + + if (ret) + return -EFAULT; } return ret; @@ -541,14 +549,9 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, #endif /* CONFIG_X86_32 */ #ifdef CONFIG_X86_32 -asmlinkage int sys_sigaltstack(unsigned long bx) +int sys_sigaltstack(struct pt_regs *regs) { - /* - * This is needed to make gcc realize it doesn't own the - * "struct pt_regs" - */ - struct pt_regs *regs = (struct pt_regs *)&bx; - const stack_t __user *uss = (const stack_t __user *)bx; + const stack_t __user *uss = (const stack_t __user *)regs->bx; stack_t __user *uoss = (stack_t __user *)regs->cx; return do_sigaltstack(uss, uoss, regs->sp); @@ -566,14 +569,12 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, * Do a signal return; undo the signal stack. */ #ifdef CONFIG_X86_32 -asmlinkage unsigned long sys_sigreturn(unsigned long __unused) +unsigned long sys_sigreturn(struct pt_regs *regs) { struct sigframe __user *frame; - struct pt_regs *regs; unsigned long ax; sigset_t set; - regs = (struct pt_regs *) &__unused; frame = (struct sigframe __user *)(regs->sp - 8); if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) @@ -600,7 +601,7 @@ badframe: } #endif /* CONFIG_X86_32 */ -static long do_rt_sigreturn(struct pt_regs *regs) +long sys_rt_sigreturn(struct pt_regs *regs) { struct rt_sigframe __user *frame; unsigned long ax; @@ -631,25 +632,6 @@ badframe: return 0; } -#ifdef CONFIG_X86_32 -/* - * Note: do not pass in pt_regs directly as with tail-call optimization - * GCC will incorrectly stomp on the caller's frame and corrupt user-space - * register state: - */ -asmlinkage int sys_rt_sigreturn(unsigned long __unused) -{ - struct pt_regs *regs = (struct pt_regs *)&__unused; - - return do_rt_sigreturn(regs); -} -#else /* !CONFIG_X86_32 */ -asmlinkage long sys_rt_sigreturn(struct pt_regs *regs) -{ - return do_rt_sigreturn(regs); -} -#endif /* CONFIG_X86_32 */ - /* * OK, we're invoking a handler: */ diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index e6faa3316bd..eaaffae31cc 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -2,7 +2,7 @@ * Intel SMP support routines. * * (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk> - * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com> + * (c) 1998-99, 2000, 2009 Ingo Molnar <mingo@redhat.com> * (c) 2002,2003 Andi Kleen, SuSE Labs. * * i386 and x86_64 integration by Glauber Costa <gcosta@redhat.com> @@ -26,8 +26,7 @@ #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/proto.h> -#include <mach_ipi.h> -#include <mach_apic.h> +#include <asm/genapic.h> /* * Some notes on x86 processor bugs affecting SMP operation: * @@ -118,12 +117,12 @@ static void native_smp_send_reschedule(int cpu) WARN_ON(1); return; } - send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR); + apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR); } void native_send_call_func_single_ipi(int cpu) { - send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR); + apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR); } void native_send_call_func_ipi(const struct cpumask *mask) @@ -131,7 +130,7 @@ void native_send_call_func_ipi(const struct cpumask *mask) cpumask_var_t allbutself; if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) { - send_IPI_mask(mask, CALL_FUNCTION_VECTOR); + apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR); return; } @@ -140,9 +139,9 @@ void native_send_call_func_ipi(const struct cpumask *mask) if (cpumask_equal(mask, allbutself) && cpumask_equal(cpu_online_mask, cpu_callout_mask)) - send_IPI_allbutself(CALL_FUNCTION_VECTOR); + apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR); else - send_IPI_mask(mask, CALL_FUNCTION_VECTOR); + apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR); free_cpumask_var(allbutself); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6c2b8444b83..af57f88186e 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -2,7 +2,7 @@ * x86 SMP booting functions * * (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk> - * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com> + * (c) 1998, 1999, 2000, 2009 Ingo Molnar <mingo@redhat.com> * Copyright 2001 Andi Kleen, SuSE Labs. * * Much of the core SMP work is based on previous work by Thomas Radke, to @@ -62,11 +62,11 @@ #include <asm/vmi.h> #include <asm/genapic.h> #include <asm/setup.h> +#include <asm/uv/uv.h> #include <linux/mc146818rtc.h> -#include <mach_apic.h> -#include <mach_wakecpu.h> -#include <smpboot_hooks.h> +#include <asm/genapic.h> +#include <asm/smpboot_hooks.h> #ifdef CONFIG_X86_32 u8 apicid_2_node[MAX_APICID]; @@ -162,7 +162,7 @@ static void map_cpu_to_logical_apicid(void) { int cpu = smp_processor_id(); int apicid = logical_smp_processor_id(); - int node = apicid_to_node(apicid); + int node = apic->apicid_to_node(apicid); if (!node_online(node)) node = first_online_node; @@ -195,7 +195,8 @@ static void __cpuinit smp_callin(void) * our local APIC. We have to wait for the IPI or we'll * lock up on an APIC access. */ - wait_for_init_deassert(&init_deasserted); + if (apic->wait_for_init_deassert) + apic->wait_for_init_deassert(&init_deasserted); /* * (This works even if the APIC is not enabled.) @@ -242,7 +243,8 @@ static void __cpuinit smp_callin(void) */ pr_debug("CALLIN, before setup_local_APIC().\n"); - smp_callin_clear_local_apic(); + if (apic->smp_callin_clear_local_apic) + apic->smp_callin_clear_local_apic(); setup_local_APIC(); end_local_APIC_setup(); map_cpu_to_logical_apicid(); @@ -582,7 +584,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) /* Target chip */ /* Boot on the stack */ /* Kick the second */ - apic_icr_write(APIC_DM_NMI | APIC_DEST_LOGICAL, logical_apicid); + apic_icr_write(APIC_DM_NMI | apic->dest_logical, logical_apicid); pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); @@ -744,57 +746,11 @@ static void __cpuinit do_fork_idle(struct work_struct *work) complete(&c_idle->done); } -#ifdef CONFIG_X86_64 - -/* __ref because it's safe to call free_bootmem when after_bootmem == 0. */ -static void __ref free_bootmem_pda(struct x8664_pda *oldpda) -{ - if (!after_bootmem) - free_bootmem((unsigned long)oldpda, sizeof(*oldpda)); -} - -/* - * Allocate node local memory for the AP pda. - * - * Must be called after the _cpu_pda pointer table is initialized. - */ -int __cpuinit get_local_pda(int cpu) -{ - struct x8664_pda *oldpda, *newpda; - unsigned long size = sizeof(struct x8664_pda); - int node = cpu_to_node(cpu); - - if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem) - return 0; - - oldpda = cpu_pda(cpu); - newpda = kmalloc_node(size, GFP_ATOMIC, node); - if (!newpda) { - printk(KERN_ERR "Could not allocate node local PDA " - "for CPU %d on node %d\n", cpu, node); - - if (oldpda) - return 0; /* have a usable pda */ - else - return -1; - } - - if (oldpda) { - memcpy(newpda, oldpda, size); - free_bootmem_pda(oldpda); - } - - newpda->in_bootmem = 0; - cpu_pda(cpu) = newpda; - return 0; -} -#endif /* CONFIG_X86_64 */ - static int __cpuinit do_boot_cpu(int apicid, int cpu) /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. - * Returns zero if CPU booted OK, else error code from wakeup_secondary_cpu. + * Returns zero if CPU booted OK, else error code from ->wakeup_cpu. */ { unsigned long boot_error = 0; @@ -807,16 +763,6 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) }; INIT_WORK(&c_idle.work, do_fork_idle); -#ifdef CONFIG_X86_64 - /* Allocate node local memory for AP pdas */ - if (cpu > 0) { - boot_error = get_local_pda(cpu); - if (boot_error) - goto restore_state; - /* if can't get pda memory, can't start cpu */ - } -#endif - alternatives_smp_switch(1); c_idle.idle = get_idle_for_cpu(cpu); @@ -846,14 +792,16 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) set_idle_for_cpu(cpu, c_idle.idle); do_rest: -#ifdef CONFIG_X86_32 per_cpu(current_task, cpu) = c_idle.idle; - init_gdt(cpu); +#ifdef CONFIG_X86_32 /* Stack for startup_32 can be just as for start_secondary onwards */ irq_ctx_init(cpu); #else - cpu_pda(cpu)->pcurrent = c_idle.idle; clear_tsk_thread_flag(c_idle.idle, TIF_FORK); + initial_gs = per_cpu_offset(cpu); + per_cpu(kernel_stack, cpu) = + (unsigned long)task_stack_page(c_idle.idle) - + KERNEL_STACK_OFFSET + THREAD_SIZE; #endif early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); initial_code = (unsigned long)start_secondary; @@ -877,7 +825,8 @@ do_rest: pr_debug("Setting warm reset code and vector.\n"); - store_NMI_vector(&nmi_high, &nmi_low); + if (apic->store_NMI_vector) + apic->store_NMI_vector(&nmi_high, &nmi_low); smpboot_setup_warm_reset_vector(start_ip); /* @@ -892,7 +841,7 @@ do_rest: /* * Starting actual IPI sequence... */ - boot_error = wakeup_secondary_cpu(apicid, start_ip); + boot_error = apic->wakeup_cpu(apicid, start_ip); if (!boot_error) { /* @@ -926,13 +875,11 @@ do_rest: else /* trampoline code not run */ printk(KERN_ERR "Not responding.\n"); - if (get_uv_system_type() != UV_NON_UNIQUE_APIC) - inquire_remote_apic(apicid); + if (apic->inquire_remote_apic) + apic->inquire_remote_apic(apicid); } } -#ifdef CONFIG_X86_64 -restore_state: -#endif + if (boot_error) { /* Try to put things back the way they were before ... */ numa_remove_cpu(cpu); /* was set by numa_add_cpu */ @@ -960,7 +907,7 @@ restore_state: int __cpuinit native_cpu_up(unsigned int cpu) { - int apicid = cpu_present_to_apicid(cpu); + int apicid = apic->cpu_present_to_apicid(cpu); unsigned long flags; int err; @@ -1053,14 +1000,14 @@ static int __init smp_sanity_check(unsigned max_cpus) { preempt_disable(); -#if defined(CONFIG_X86_PC) && defined(CONFIG_X86_32) +#if !defined(CONFIG_X86_BIGSMP) && defined(CONFIG_X86_32) if (def_to_bigsmp && nr_cpu_ids > 8) { unsigned int cpu; unsigned nr; printk(KERN_WARNING "More than 8 CPUs detected - skipping them.\n" - "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n"); + "Use CONFIG_X86_BIGSMP.\n"); nr = 0; for_each_present_cpu(cpu) { @@ -1106,7 +1053,7 @@ static int __init smp_sanity_check(unsigned max_cpus) * Should not be necessary because the MP table should list the boot * CPU too, but we do it for the sake of robustness anyway. */ - if (!check_phys_apicid_present(boot_cpu_physical_apicid)) { + if (!apic->check_phys_apicid_present(boot_cpu_physical_apicid)) { printk(KERN_NOTICE "weird, boot CPU (#%d) not listed by the BIOS.\n", boot_cpu_physical_apicid); @@ -1124,6 +1071,7 @@ static int __init smp_sanity_check(unsigned max_cpus) printk(KERN_ERR "... forcing use of dummy APIC emulation." "(tell your hw vendor)\n"); smpboot_clear_io_apic(); + arch_disable_smp_support(); return -1; } @@ -1182,7 +1130,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) #ifdef CONFIG_X86_64 enable_IR_x2apic(); - setup_apic_routing(); + default_setup_apic_routing(); #endif if (smp_sanity_check(max_cpus) < 0) { @@ -1217,7 +1165,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) map_cpu_to_logical_apicid(); - setup_portio_remap(); + if (apic->setup_portio_remap) + apic->setup_portio_remap(); smpboot_setup_io_apic(); /* @@ -1239,10 +1188,7 @@ out: void __init native_smp_prepare_boot_cpu(void) { int me = smp_processor_id(); -#ifdef CONFIG_X86_32 - init_gdt(me); -#endif - switch_to_new_gdt(); + switch_to_new_gdt(me); /* already set me in cpu_online_mask in boot_cpu_init() */ cpumask_set_cpu(me, cpu_callout_mask); per_cpu(cpu_state, me) = CPU_ONLINE; diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c deleted file mode 100644 index 397e309839d..00000000000 --- a/arch/x86/kernel/smpcommon.c +++ /dev/null @@ -1,30 +0,0 @@ -/* - * SMP stuff which is common to all sub-architectures. - */ -#include <linux/module.h> -#include <asm/smp.h> - -#ifdef CONFIG_X86_32 -DEFINE_PER_CPU(unsigned long, this_cpu_off); -EXPORT_PER_CPU_SYMBOL(this_cpu_off); - -/* - * Initialize the CPU's GDT. This is either the boot CPU doing itself - * (still using the master per-cpu area), or a CPU doing it for a - * secondary which will soon come up. - */ -__cpuinit void init_gdt(int cpu) -{ - struct desc_struct gdt; - - pack_descriptor(&gdt, __per_cpu_offset[cpu], 0xFFFFF, - 0x2 | DESCTYPE_S, 0x8); - gdt.s = 1; - - write_gdt_entry(get_cpu_gdt_table(cpu), - GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S); - - per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu]; - per_cpu(cpu_number, cpu) = cpu; -} -#endif diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 10786af9554..f7bddc2e37d 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -1,7 +1,7 @@ /* * Stack trace management functions * - * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * Copyright (C) 2006-2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ #include <linux/sched.h> #include <linux/stacktrace.h> diff --git a/arch/x86/kernel/summit_32.c b/arch/x86/kernel/summit_32.c index 7b987852e87..1e733eff9b3 100644 --- a/arch/x86/kernel/summit_32.c +++ b/arch/x86/kernel/summit_32.c @@ -30,8 +30,364 @@ #include <linux/init.h> #include <asm/io.h> #include <asm/bios_ebda.h> -#include <asm/summit/mpparse.h> +/* + * APIC driver for the IBM "Summit" chipset. + */ +#define APIC_DEFINITION 1 +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <asm/mpspec.h> +#include <asm/apic.h> +#include <asm/smp.h> +#include <asm/genapic.h> +#include <asm/fixmap.h> +#include <asm/apicdef.h> +#include <asm/ipi.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/gfp.h> +#include <linux/smp.h> + +static inline unsigned summit_get_apic_id(unsigned long x) +{ + return (x >> 24) & 0xFF; +} + +static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector) +{ + default_send_IPI_mask_sequence_logical(mask, vector); +} + +static inline void summit_send_IPI_allbutself(int vector) +{ + cpumask_t mask = cpu_online_map; + cpu_clear(smp_processor_id(), mask); + + if (!cpus_empty(mask)) + summit_send_IPI_mask(&mask, vector); +} + +static inline void summit_send_IPI_all(int vector) +{ + summit_send_IPI_mask(&cpu_online_map, vector); +} + +#include <asm/tsc.h> + +extern int use_cyclone; + +#ifdef CONFIG_X86_SUMMIT_NUMA +extern void setup_summit(void); +#else +#define setup_summit() {} +#endif + +static inline int +summit_mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) +{ + if (!strncmp(oem, "IBM ENSW", 8) && + (!strncmp(productid, "VIGIL SMP", 9) + || !strncmp(productid, "EXA", 3) + || !strncmp(productid, "RUTHLESS SMP", 12))){ + mark_tsc_unstable("Summit based system"); + use_cyclone = 1; /*enable cyclone-timer*/ + setup_summit(); + return 1; + } + return 0; +} + +/* Hook from generic ACPI tables.c */ +static inline int summit_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + if (!strncmp(oem_id, "IBM", 3) && + (!strncmp(oem_table_id, "SERVIGIL", 8) + || !strncmp(oem_table_id, "EXA", 3))){ + mark_tsc_unstable("Summit based system"); + use_cyclone = 1; /*enable cyclone-timer*/ + setup_summit(); + return 1; + } + return 0; +} + +struct rio_table_hdr { + unsigned char version; /* Version number of this data structure */ + /* Version 3 adds chassis_num & WP_index */ + unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil) */ + unsigned char num_rio_dev; /* # of RIO I/O devices (Cyclones and Winnipegs) */ +} __attribute__((packed)); + +struct scal_detail { + unsigned char node_id; /* Scalability Node ID */ + unsigned long CBAR; /* Address of 1MB register space */ + unsigned char port0node; /* Node ID port connected to: 0xFF=None */ + unsigned char port0port; /* Port num port connected to: 0,1,2, or 0xFF=None */ + unsigned char port1node; /* Node ID port connected to: 0xFF = None */ + unsigned char port1port; /* Port num port connected to: 0,1,2, or 0xFF=None */ + unsigned char port2node; /* Node ID port connected to: 0xFF = None */ + unsigned char port2port; /* Port num port connected to: 0,1,2, or 0xFF=None */ + unsigned char chassis_num; /* 1 based Chassis number (1 = boot node) */ +} __attribute__((packed)); + +struct rio_detail { + unsigned char node_id; /* RIO Node ID */ + unsigned long BBAR; /* Address of 1MB register space */ + unsigned char type; /* Type of device */ + unsigned char owner_id; /* For WPEG: Node ID of Cyclone that owns this WPEG*/ + /* For CYC: Node ID of Twister that owns this CYC */ + unsigned char port0node; /* Node ID port connected to: 0xFF=None */ + unsigned char port0port; /* Port num port connected to: 0,1,2, or 0xFF=None */ + unsigned char port1node; /* Node ID port connected to: 0xFF=None */ + unsigned char port1port; /* Port num port connected to: 0,1,2, or 0xFF=None */ + unsigned char first_slot; /* For WPEG: Lowest slot number below this WPEG */ + /* For CYC: 0 */ + unsigned char status; /* For WPEG: Bit 0 = 1 : the XAPIC is used */ + /* = 0 : the XAPIC is not used, ie:*/ + /* ints fwded to another XAPIC */ + /* Bits1:7 Reserved */ + /* For CYC: Bits0:7 Reserved */ + unsigned char WP_index; /* For WPEG: WPEG instance index - lower ones have */ + /* lower slot numbers/PCI bus numbers */ + /* For CYC: No meaning */ + unsigned char chassis_num; /* 1 based Chassis number */ + /* For LookOut WPEGs this field indicates the */ + /* Expansion Chassis #, enumerated from Boot */ + /* Node WPEG external port, then Boot Node CYC */ + /* external port, then Next Vigil chassis WPEG */ + /* external port, etc. */ + /* Shared Lookouts have only 1 chassis number (the */ + /* first one assigned) */ +} __attribute__((packed)); + + +typedef enum { + CompatTwister = 0, /* Compatibility Twister */ + AltTwister = 1, /* Alternate Twister of internal 8-way */ + CompatCyclone = 2, /* Compatibility Cyclone */ + AltCyclone = 3, /* Alternate Cyclone of internal 8-way */ + CompatWPEG = 4, /* Compatibility WPEG */ + AltWPEG = 5, /* Second Planar WPEG */ + LookOutAWPEG = 6, /* LookOut WPEG */ + LookOutBWPEG = 7, /* LookOut WPEG */ +} node_type; + +static inline int is_WPEG(struct rio_detail *rio){ + return (rio->type == CompatWPEG || rio->type == AltWPEG || + rio->type == LookOutAWPEG || rio->type == LookOutBWPEG); +} + + +/* In clustered mode, the high nibble of APIC ID is a cluster number. + * The low nibble is a 4-bit bitmap. */ +#define XAPIC_DEST_CPUS_SHIFT 4 +#define XAPIC_DEST_CPUS_MASK ((1u << XAPIC_DEST_CPUS_SHIFT) - 1) +#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT) + +#define SUMMIT_APIC_DFR_VALUE (APIC_DFR_CLUSTER) + +static inline const cpumask_t *summit_target_cpus(void) +{ + /* CPU_MASK_ALL (0xff) has undefined behaviour with + * dest_LowestPrio mode logical clustered apic interrupt routing + * Just start on cpu 0. IRQ balancing will spread load + */ + return &cpumask_of_cpu(0); +} + +static inline unsigned long +summit_check_apicid_used(physid_mask_t bitmap, int apicid) +{ + return 0; +} + +/* we don't use the phys_cpu_present_map to indicate apicid presence */ +static inline unsigned long summit_check_apicid_present(int bit) +{ + return 1; +} + +#define apicid_cluster(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK) + +extern u8 cpu_2_logical_apicid[]; + +static inline void summit_init_apic_ldr(void) +{ + unsigned long val, id; + int count = 0; + u8 my_id = (u8)hard_smp_processor_id(); + u8 my_cluster = (u8)apicid_cluster(my_id); +#ifdef CONFIG_SMP + u8 lid; + int i; + + /* Create logical APIC IDs by counting CPUs already in cluster. */ + for (count = 0, i = nr_cpu_ids; --i >= 0; ) { + lid = cpu_2_logical_apicid[i]; + if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster) + ++count; + } +#endif + /* We only have a 4 wide bitmap in cluster mode. If a deranged + * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */ + BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT); + id = my_cluster | (1UL << count); + apic_write(APIC_DFR, SUMMIT_APIC_DFR_VALUE); + val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; + val |= SET_APIC_LOGICAL_ID(id); + apic_write(APIC_LDR, val); +} + +static inline int summit_apic_id_registered(void) +{ + return 1; +} + +static inline void summit_setup_apic_routing(void) +{ + printk("Enabling APIC mode: Summit. Using %d I/O APICs\n", + nr_ioapics); +} + +static inline int summit_apicid_to_node(int logical_apicid) +{ +#ifdef CONFIG_SMP + return apicid_2_node[hard_smp_processor_id()]; +#else + return 0; +#endif +} + +/* Mapping from cpu number to logical apicid */ +static inline int summit_cpu_to_logical_apicid(int cpu) +{ +#ifdef CONFIG_SMP + if (cpu >= nr_cpu_ids) + return BAD_APICID; + return (int)cpu_2_logical_apicid[cpu]; +#else + return logical_smp_processor_id(); +#endif +} + +static inline int summit_cpu_present_to_apicid(int mps_cpu) +{ + if (mps_cpu < nr_cpu_ids) + return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu); + else + return BAD_APICID; +} + +static inline physid_mask_t +summit_ioapic_phys_id_map(physid_mask_t phys_id_map) +{ + /* For clustered we don't have a good way to do this yet - hack */ + return physids_promote(0x0F); +} + +static inline physid_mask_t summit_apicid_to_cpu_present(int apicid) +{ + return physid_mask_of_physid(0); +} + +static inline void summit_setup_portio_remap(void) +{ +} + +static inline int summit_check_phys_apicid_present(int boot_cpu_physical_apicid) +{ + return 1; +} + +static inline unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask) +{ + int cpus_found = 0; + int num_bits_set; + int apicid; + int cpu; + + num_bits_set = cpus_weight(*cpumask); + /* Return id to all */ + if (num_bits_set >= nr_cpu_ids) + return 0xFF; + /* + * The cpus in the mask must all be on the apic cluster. If are not + * on the same apicid cluster return default value of target_cpus(): + */ + cpu = first_cpu(*cpumask); + apicid = summit_cpu_to_logical_apicid(cpu); + + while (cpus_found < num_bits_set) { + if (cpu_isset(cpu, *cpumask)) { + int new_apicid = summit_cpu_to_logical_apicid(cpu); + + if (apicid_cluster(apicid) != + apicid_cluster(new_apicid)) { + printk ("%s: Not a valid mask!\n", __func__); + + return 0xFF; + } + apicid = apicid | new_apicid; + cpus_found++; + } + cpu++; + } + return apicid; +} + +static inline unsigned int +summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, + const struct cpumask *andmask) +{ + int apicid = summit_cpu_to_logical_apicid(0); + cpumask_var_t cpumask; + + if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) + return apicid; + + cpumask_and(cpumask, inmask, andmask); + cpumask_and(cpumask, cpumask, cpu_online_mask); + apicid = summit_cpu_mask_to_apicid(cpumask); + + free_cpumask_var(cpumask); + + return apicid; +} + +/* + * cpuid returns the value latched in the HW at reset, not the APIC ID + * register's value. For any box whose BIOS changes APIC IDs, like + * clustered APIC systems, we must use hard_smp_processor_id. + * + * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID. + */ +static inline int summit_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return hard_smp_processor_id() >> index_msb; +} + +static int probe_summit(void) +{ + /* probed later in mptable/ACPI hooks */ + return 0; +} + +static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask) +{ + /* Careful. Some cpus do not strictly honor the set of cpus + * specified in the interrupt destination when using lowest + * priority interrupt delivery mode. + * + * In particular there was a hyperthreading cpu observed to + * deliver interrupts to the wrong hyperthread when only one + * hyperthread was specified in the interrupt desitination. + */ + *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; +} + +#ifdef CONFIG_X86_SUMMIT_NUMA static struct rio_table_hdr *rio_table_hdr __initdata; static struct scal_detail *scal_devs[MAX_NUMNODES] __initdata; static struct rio_detail *rio_devs[MAX_NUMNODES*4] __initdata; @@ -186,3 +542,61 @@ void __init setup_summit(void) next_wpeg = 0; } while (next_wpeg != 0); } +#endif + +struct genapic apic_summit = { + + .name = "summit", + .probe = probe_summit, + .acpi_madt_oem_check = summit_acpi_madt_oem_check, + .apic_id_registered = summit_apic_id_registered, + + .irq_delivery_mode = dest_LowestPrio, + /* logical delivery broadcast to all CPUs: */ + .irq_dest_mode = 1, + + .target_cpus = summit_target_cpus, + .disable_esr = 1, + .dest_logical = APIC_DEST_LOGICAL, + .check_apicid_used = summit_check_apicid_used, + .check_apicid_present = summit_check_apicid_present, + + .vector_allocation_domain = summit_vector_allocation_domain, + .init_apic_ldr = summit_init_apic_ldr, + + .ioapic_phys_id_map = summit_ioapic_phys_id_map, + .setup_apic_routing = summit_setup_apic_routing, + .multi_timer_check = NULL, + .apicid_to_node = summit_apicid_to_node, + .cpu_to_logical_apicid = summit_cpu_to_logical_apicid, + .cpu_present_to_apicid = summit_cpu_present_to_apicid, + .apicid_to_cpu_present = summit_apicid_to_cpu_present, + .setup_portio_remap = NULL, + .check_phys_apicid_present = summit_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = summit_phys_pkg_id, + .mps_oem_check = summit_mps_oem_check, + + .get_apic_id = summit_get_apic_id, + .set_apic_id = NULL, + .apic_id_mask = 0xFF << 24, + + .cpu_mask_to_apicid = summit_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = summit_cpu_mask_to_apicid_and, + + .send_IPI_mask = summit_send_IPI_mask, + .send_IPI_mask_allbutself = NULL, + .send_IPI_allbutself = summit_send_IPI_allbutself, + .send_IPI_all = summit_send_IPI_all, + .send_IPI_self = default_send_IPI_self, + + .wakeup_cpu = NULL, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + + .wait_for_init_deassert = default_wait_for_init_deassert, + + .smp_callin_clear_local_apic = NULL, + .store_NMI_vector = NULL, + .inquire_remote_apic = default_inquire_remote_apic, +}; diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index e2e86a08f31..3bdb64829b8 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -1,7 +1,7 @@ ENTRY(sys_call_table) .long sys_restart_syscall /* 0 - old "setup()" system call, used for restarting */ .long sys_exit - .long sys_fork + .long ptregs_fork .long sys_read .long sys_write .long sys_open /* 5 */ @@ -10,7 +10,7 @@ ENTRY(sys_call_table) .long sys_creat .long sys_link .long sys_unlink /* 10 */ - .long sys_execve + .long ptregs_execve .long sys_chdir .long sys_time .long sys_mknod @@ -109,17 +109,17 @@ ENTRY(sys_call_table) .long sys_newlstat .long sys_newfstat .long sys_uname - .long sys_iopl /* 110 */ + .long ptregs_iopl /* 110 */ .long sys_vhangup .long sys_ni_syscall /* old "idle" system call */ - .long sys_vm86old + .long ptregs_vm86old .long sys_wait4 .long sys_swapoff /* 115 */ .long sys_sysinfo .long sys_ipc .long sys_fsync - .long sys_sigreturn - .long sys_clone /* 120 */ + .long ptregs_sigreturn + .long ptregs_clone /* 120 */ .long sys_setdomainname .long sys_newuname .long sys_modify_ldt @@ -165,14 +165,14 @@ ENTRY(sys_call_table) .long sys_mremap .long sys_setresuid16 .long sys_getresuid16 /* 165 */ - .long sys_vm86 + .long ptregs_vm86 .long sys_ni_syscall /* Old sys_query_module */ .long sys_poll .long sys_nfsservctl .long sys_setresgid16 /* 170 */ .long sys_getresgid16 .long sys_prctl - .long sys_rt_sigreturn + .long ptregs_rt_sigreturn .long sys_rt_sigaction .long sys_rt_sigprocmask /* 175 */ .long sys_rt_sigpending @@ -185,11 +185,11 @@ ENTRY(sys_call_table) .long sys_getcwd .long sys_capget .long sys_capset /* 185 */ - .long sys_sigaltstack + .long ptregs_sigaltstack .long sys_sendfile .long sys_ni_syscall /* reserved for streams1 */ .long sys_ni_syscall /* reserved for streams2 */ - .long sys_vfork /* 190 */ + .long ptregs_vfork /* 190 */ .long sys_getrlimit .long sys_mmap2 .long sys_truncate64 diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c index 3985cac0ed4..764c74e871f 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time_32.c @@ -38,7 +38,7 @@ #include <asm/time.h> #include <asm/timer.h> -#include "do_timer.h" +#include <asm/do_timer.h> int timer_ack; diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c deleted file mode 100644 index ce505464224..00000000000 --- a/arch/x86/kernel/tlb_32.c +++ /dev/null @@ -1,256 +0,0 @@ -#include <linux/spinlock.h> -#include <linux/cpu.h> -#include <linux/interrupt.h> - -#include <asm/tlbflush.h> - -DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate) - ____cacheline_aligned = { &init_mm, 0, }; - -/* must come after the send_IPI functions above for inlining */ -#include <mach_ipi.h> - -/* - * Smarter SMP flushing macros. - * c/o Linus Torvalds. - * - * These mean you can really definitely utterly forget about - * writing to user space from interrupts. (Its not allowed anyway). - * - * Optimizations Manfred Spraul <manfred@colorfullife.com> - */ - -static cpumask_t flush_cpumask; -static struct mm_struct *flush_mm; -static unsigned long flush_va; -static DEFINE_SPINLOCK(tlbstate_lock); - -/* - * We cannot call mmdrop() because we are in interrupt context, - * instead update mm->cpu_vm_mask. - * - * We need to reload %cr3 since the page tables may be going - * away from under us.. - */ -void leave_mm(int cpu) -{ - BUG_ON(x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK); - cpu_clear(cpu, x86_read_percpu(cpu_tlbstate.active_mm)->cpu_vm_mask); - load_cr3(swapper_pg_dir); -} -EXPORT_SYMBOL_GPL(leave_mm); - -/* - * - * The flush IPI assumes that a thread switch happens in this order: - * [cpu0: the cpu that switches] - * 1) switch_mm() either 1a) or 1b) - * 1a) thread switch to a different mm - * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask); - * Stop ipi delivery for the old mm. This is not synchronized with - * the other cpus, but smp_invalidate_interrupt ignore flush ipis - * for the wrong mm, and in the worst case we perform a superfluous - * tlb flush. - * 1a2) set cpu_tlbstate to TLBSTATE_OK - * Now the smp_invalidate_interrupt won't call leave_mm if cpu0 - * was in lazy tlb mode. - * 1a3) update cpu_tlbstate[].active_mm - * Now cpu0 accepts tlb flushes for the new mm. - * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask); - * Now the other cpus will send tlb flush ipis. - * 1a4) change cr3. - * 1b) thread switch without mm change - * cpu_tlbstate[].active_mm is correct, cpu0 already handles - * flush ipis. - * 1b1) set cpu_tlbstate to TLBSTATE_OK - * 1b2) test_and_set the cpu bit in cpu_vm_mask. - * Atomically set the bit [other cpus will start sending flush ipis], - * and test the bit. - * 1b3) if the bit was 0: leave_mm was called, flush the tlb. - * 2) switch %%esp, ie current - * - * The interrupt must handle 2 special cases: - * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. - * - the cpu performs speculative tlb reads, i.e. even if the cpu only - * runs in kernel space, the cpu could load tlb entries for user space - * pages. - * - * The good news is that cpu_tlbstate is local to each cpu, no - * write/read ordering problems. - */ - -/* - * TLB flush IPI: - * - * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. - * 2) Leave the mm if we are in the lazy tlb mode. - */ - -void smp_invalidate_interrupt(struct pt_regs *regs) -{ - unsigned long cpu; - - cpu = get_cpu(); - - if (!cpu_isset(cpu, flush_cpumask)) - goto out; - /* - * This was a BUG() but until someone can quote me the - * line from the intel manual that guarantees an IPI to - * multiple CPUs is retried _only_ on the erroring CPUs - * its staying as a return - * - * BUG(); - */ - - if (flush_mm == x86_read_percpu(cpu_tlbstate.active_mm)) { - if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK) { - if (flush_va == TLB_FLUSH_ALL) - local_flush_tlb(); - else - __flush_tlb_one(flush_va); - } else - leave_mm(cpu); - } - ack_APIC_irq(); - smp_mb__before_clear_bit(); - cpu_clear(cpu, flush_cpumask); - smp_mb__after_clear_bit(); -out: - put_cpu_no_resched(); - inc_irq_stat(irq_tlb_count); -} - -void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, - unsigned long va) -{ - cpumask_t cpumask = *cpumaskp; - - /* - * A couple of (to be removed) sanity checks: - * - * - current CPU must not be in mask - * - mask must exist :) - */ - BUG_ON(cpus_empty(cpumask)); - BUG_ON(cpu_isset(smp_processor_id(), cpumask)); - BUG_ON(!mm); - -#ifdef CONFIG_HOTPLUG_CPU - /* If a CPU which we ran on has gone down, OK. */ - cpus_and(cpumask, cpumask, cpu_online_map); - if (unlikely(cpus_empty(cpumask))) - return; -#endif - - /* - * i'm not happy about this global shared spinlock in the - * MM hot path, but we'll see how contended it is. - * AK: x86-64 has a faster method that could be ported. - */ - spin_lock(&tlbstate_lock); - - flush_mm = mm; - flush_va = va; - cpus_or(flush_cpumask, cpumask, flush_cpumask); - - /* - * Make the above memory operations globally visible before - * sending the IPI. - */ - smp_mb(); - /* - * We have to send the IPI only to - * CPUs affected. - */ - send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR); - - while (!cpus_empty(flush_cpumask)) - /* nothing. lockup detection does not belong here */ - cpu_relax(); - - flush_mm = NULL; - flush_va = 0; - spin_unlock(&tlbstate_lock); -} - -void flush_tlb_current_task(void) -{ - struct mm_struct *mm = current->mm; - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - local_flush_tlb(); - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL); - preempt_enable(); -} - -void flush_tlb_mm(struct mm_struct *mm) -{ - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - if (current->active_mm == mm) { - if (current->mm) - local_flush_tlb(); - else - leave_mm(smp_processor_id()); - } - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL); - - preempt_enable(); -} - -void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) -{ - struct mm_struct *mm = vma->vm_mm; - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - if (current->active_mm == mm) { - if (current->mm) - __flush_tlb_one(va); - else - leave_mm(smp_processor_id()); - } - - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, va); - - preempt_enable(); -} -EXPORT_SYMBOL(flush_tlb_page); - -static void do_flush_tlb_all(void *info) -{ - unsigned long cpu = smp_processor_id(); - - __flush_tlb_all(); - if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_LAZY) - leave_mm(cpu); -} - -void flush_tlb_all(void) -{ - on_each_cpu(do_flush_tlb_all, NULL, 1); -} - -void reset_lazy_tlbstate(void) -{ - int cpu = raw_smp_processor_id(); - - per_cpu(cpu_tlbstate, cpu).state = 0; - per_cpu(cpu_tlbstate, cpu).active_mm = &init_mm; -} - diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 6812b829ed8..f396e61bcb3 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <asm/mmu_context.h> +#include <asm/uv/uv.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> #include <asm/uv/uv_bau.h> @@ -19,7 +20,7 @@ #include <asm/tsc.h> #include <asm/irq_vectors.h> -#include <mach_apic.h> +#include <asm/genapic.h> static struct bau_control **uv_bau_table_bases __read_mostly; static int uv_bau_retry_limit __read_mostly; @@ -210,14 +211,15 @@ static int uv_wait_completion(struct bau_desc *bau_desc, * * Send a broadcast and wait for a broadcast message to complete. * - * The cpumaskp mask contains the cpus the broadcast was sent to. + * The flush_mask contains the cpus the broadcast was sent to. * - * Returns 1 if all remote flushing was done. The mask is zeroed. - * Returns 0 if some remote flushing remains to be done. The mask is left - * unchanged. + * Returns NULL if all remote flushing was done. The mask is zeroed. + * Returns @flush_mask if some remote flushing remains to be done. The + * mask will have some bits still set. */ -int uv_flush_send_and_wait(int cpu, int this_blade, struct bau_desc *bau_desc, - cpumask_t *cpumaskp) +const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, + struct bau_desc *bau_desc, + struct cpumask *flush_mask) { int completion_status = 0; int right_shift; @@ -257,66 +259,76 @@ int uv_flush_send_and_wait(int cpu, int this_blade, struct bau_desc *bau_desc, * the cpu's, all of which are still in the mask. */ __get_cpu_var(ptcstats).ptc_i++; - return 0; + return flush_mask; } /* * Success, so clear the remote cpu's from the mask so we don't * use the IPI method of shootdown on them. */ - for_each_cpu_mask(bit, *cpumaskp) { + for_each_cpu(bit, flush_mask) { blade = uv_cpu_to_blade_id(bit); if (blade == this_blade) continue; - cpu_clear(bit, *cpumaskp); + cpumask_clear_cpu(bit, flush_mask); } - if (!cpus_empty(*cpumaskp)) - return 0; - return 1; + if (!cpumask_empty(flush_mask)) + return flush_mask; + return NULL; } /** * uv_flush_tlb_others - globally purge translation cache of a virtual * address or all TLB's - * @cpumaskp: mask of all cpu's in which the address is to be removed + * @cpumask: mask of all cpu's in which the address is to be removed * @mm: mm_struct containing virtual address range * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu) + * @cpu: the current cpu * * This is the entry point for initiating any UV global TLB shootdown. * * Purges the translation caches of all specified processors of the given * virtual address, or purges all TLB's on specified processors. * - * The caller has derived the cpumaskp from the mm_struct and has subtracted - * the local cpu from the mask. This function is called only if there - * are bits set in the mask. (e.g. flush_tlb_page()) + * The caller has derived the cpumask from the mm_struct. This function + * is called only if there are bits set in the mask. (e.g. flush_tlb_page()) * - * The cpumaskp is converted into a nodemask of the nodes containing + * The cpumask is converted into a nodemask of the nodes containing * the cpus. * - * Returns 1 if all remote flushing was done. - * Returns 0 if some remote flushing remains to be done. + * Note that this function should be called with preemption disabled. + * + * Returns NULL if all remote flushing was done. + * Returns pointer to cpumask if some remote flushing remains to be + * done. The returned pointer is valid till preemption is re-enabled. */ -int uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm, - unsigned long va) +const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, + struct mm_struct *mm, + unsigned long va, unsigned int cpu) { + static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); + struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask); int i; int bit; int blade; - int cpu; + int uv_cpu; int this_blade; int locals = 0; struct bau_desc *bau_desc; - cpu = uv_blade_processor_id(); + WARN_ON(!in_atomic()); + + cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); + + uv_cpu = uv_blade_processor_id(); this_blade = uv_numa_blade_id(); bau_desc = __get_cpu_var(bau_control).descriptor_base; - bau_desc += UV_ITEMS_PER_DESCRIPTOR * cpu; + bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu; bau_nodes_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); i = 0; - for_each_cpu_mask(bit, *cpumaskp) { + for_each_cpu(bit, flush_mask) { blade = uv_cpu_to_blade_id(bit); BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1)); if (blade == this_blade) { @@ -331,17 +343,17 @@ int uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm, * no off_node flushing; return status for local node */ if (locals) - return 0; + return flush_mask; else - return 1; + return NULL; } __get_cpu_var(ptcstats).requestor++; __get_cpu_var(ptcstats).ntargeted += i; bau_desc->payload.address = va; - bau_desc->payload.sending_cpu = smp_processor_id(); + bau_desc->payload.sending_cpu = cpu; - return uv_flush_send_and_wait(cpu, this_blade, bau_desc, cpumaskp); + return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask); } /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 98c2d055284..bde57f0f161 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -54,12 +54,11 @@ #include <asm/desc.h> #include <asm/i387.h> -#include <mach_traps.h> +#include <asm/mach_traps.h> #ifdef CONFIG_X86_64 #include <asm/pgalloc.h> #include <asm/proto.h> -#include <asm/pda.h> #else #include <asm/processor-flags.h> #include <asm/arch_hooks.h> @@ -896,7 +895,7 @@ asmlinkage void math_state_restore(void) EXPORT_SYMBOL_GPL(math_state_restore); #ifndef CONFIG_MATH_EMULATION -asmlinkage void math_emulate(long arg) +void math_emulate(struct math_emu_info *info) { printk(KERN_EMERG "math-emulation not enabled and no coprocessor found.\n"); @@ -907,12 +906,16 @@ asmlinkage void math_emulate(long arg) #endif /* CONFIG_MATH_EMULATION */ dotraplinkage void __kprobes -do_device_not_available(struct pt_regs *regs, long error) +do_device_not_available(struct pt_regs *regs, long error_code) { #ifdef CONFIG_X86_32 if (read_cr0() & X86_CR0_EM) { + struct math_emu_info info = { }; + conditional_sti(regs); - math_emulate(0); + + info.regs = regs; + math_emulate(&info); } else { math_state_restore(); /* interrupts still off */ conditional_sti(regs); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 599e5816863..83d53ce5d4c 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -773,7 +773,7 @@ __cpuinit int unsynchronized_tsc(void) if (!cpu_has_tsc || tsc_unstable) return 1; -#ifdef CONFIG_X86_SMP +#ifdef CONFIG_SMP if (apic_is_clustered_box()) return 1; #endif diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index d801d06af06..4fd646e6dd4 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -32,9 +32,9 @@ #include <asm/e820.h> #include <asm/io.h> -#include <mach_ipi.h> +#include <asm/genapic.h> -#include "mach_apic.h" +#include <asm/genapic.h> #include <linux/kernel_stat.h> @@ -200,7 +200,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) return; } - apic_cpus = apicid_to_cpu_present(m->apicid); + apic_cpus = apic->apicid_to_cpu_present(m->apicid); physids_or(phys_cpu_present_map, phys_cpu_present_map, apic_cpus); /* * Validate version diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 4eeb5cf9720..d7ac84e7fc1 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -158,7 +158,7 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) ret = KVM86->regs32; ret->fs = current->thread.saved_fs; - loadsegment(gs, current->thread.saved_gs); + set_user_gs(ret, current->thread.saved_gs); return ret; } @@ -197,9 +197,9 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); -asmlinkage int sys_vm86old(struct pt_regs regs) +int sys_vm86old(struct pt_regs *regs) { - struct vm86_struct __user *v86 = (struct vm86_struct __user *)regs.bx; + struct vm86_struct __user *v86 = (struct vm86_struct __user *)regs->bx; struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. * This remains on the stack until we @@ -218,7 +218,7 @@ asmlinkage int sys_vm86old(struct pt_regs regs) if (tmp) goto out; memset(&info.vm86plus, 0, (int)&info.regs32 - (int)&info.vm86plus); - info.regs32 = ®s; + info.regs32 = regs; tsk->thread.vm86_info = v86; do_sys_vm86(&info, tsk); ret = 0; /* we never return here */ @@ -227,7 +227,7 @@ out: } -asmlinkage int sys_vm86(struct pt_regs regs) +int sys_vm86(struct pt_regs *regs) { struct kernel_vm86_struct info; /* declare this _on top_, * this avoids wasting of stack space. @@ -239,12 +239,12 @@ asmlinkage int sys_vm86(struct pt_regs regs) struct vm86plus_struct __user *v86; tsk = current; - switch (regs.bx) { + switch (regs->bx) { case VM86_REQUEST_IRQ: case VM86_FREE_IRQ: case VM86_GET_IRQ_BITS: case VM86_GET_AND_RESET_IRQ: - ret = do_vm86_irq_handling(regs.bx, (int)regs.cx); + ret = do_vm86_irq_handling(regs->bx, (int)regs->cx); goto out; case VM86_PLUS_INSTALL_CHECK: /* @@ -261,14 +261,14 @@ asmlinkage int sys_vm86(struct pt_regs regs) ret = -EPERM; if (tsk->thread.saved_sp0) goto out; - v86 = (struct vm86plus_struct __user *)regs.cx; + v86 = (struct vm86plus_struct __user *)regs->cx; tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, offsetof(struct kernel_vm86_struct, regs32) - sizeof(info.regs)); ret = -EFAULT; if (tmp) goto out; - info.regs32 = ®s; + info.regs32 = regs; info.vm86plus.is_vm86pus = 1; tsk->thread.vm86_info = (struct vm86_struct __user *)v86; do_sys_vm86(&info, tsk); @@ -323,7 +323,7 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk info->regs32->ax = 0; tsk->thread.saved_sp0 = tsk->thread.sp0; tsk->thread.saved_fs = info->regs32->fs; - savesegment(gs, tsk->thread.saved_gs); + tsk->thread.saved_gs = get_user_gs(info->regs32); tss = &per_cpu(init_tss, get_cpu()); tsk->thread.sp0 = (unsigned long) &info->VM86_TSS_ESP0; diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 1d3302cc2dd..f052c84ecbe 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -321,6 +321,16 @@ static void vmi_release_pmd(unsigned long pfn) } /* + * We use the pgd_free hook for releasing the pgd page: + */ +static void vmi_pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + unsigned long pfn = __pa(pgd) >> PAGE_SHIFT; + + vmi_ops.release_page(pfn, VMI_PAGE_L2); +} + +/* * Helper macros for MMU update flags. We can defer updates until a flush * or page invalidation only if the update is to the current address space * (otherwise, there is no flush). We must check against init_mm, since @@ -670,10 +680,11 @@ static inline int __init activate_vmi(void) para_fill(pv_mmu_ops.write_cr2, SetCR2); para_fill(pv_mmu_ops.write_cr3, SetCR3); para_fill(pv_cpu_ops.write_cr4, SetCR4); - para_fill(pv_irq_ops.save_fl, GetInterruptMask); - para_fill(pv_irq_ops.restore_fl, SetInterruptMask); - para_fill(pv_irq_ops.irq_disable, DisableInterrupts); - para_fill(pv_irq_ops.irq_enable, EnableInterrupts); + + para_fill(pv_irq_ops.save_fl.func, GetInterruptMask); + para_fill(pv_irq_ops.restore_fl.func, SetInterruptMask); + para_fill(pv_irq_ops.irq_disable.func, DisableInterrupts); + para_fill(pv_irq_ops.irq_enable.func, EnableInterrupts); para_fill(pv_cpu_ops.wbinvd, WBINVD); para_fill(pv_cpu_ops.read_tsc, RDTSC); @@ -762,6 +773,7 @@ static inline int __init activate_vmi(void) if (vmi_ops.release_page) { pv_mmu_ops.release_pte = vmi_release_pte; pv_mmu_ops.release_pmd = vmi_release_pmd; + pv_mmu_ops.pgd_free = vmi_pgd_free; } /* Set linear is needed in all cases */ diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index c4c1f9e0940..a4791ef412d 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -256,7 +256,7 @@ void __devinit vmi_time_bsp_init(void) */ clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); local_irq_disable(); -#ifdef CONFIG_X86_SMP +#ifdef CONFIG_SMP /* * XXX handle_percpu_irq only defined for SMP; we need to switch over * to using it, since this is a local interrupt, which each CPU must diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S index 82c67559dde..3eba7f7bac0 100644 --- a/arch/x86/kernel/vmlinux_32.lds.S +++ b/arch/x86/kernel/vmlinux_32.lds.S @@ -178,14 +178,7 @@ SECTIONS __initramfs_end = .; } #endif - . = ALIGN(PAGE_SIZE); - .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { - __per_cpu_start = .; - *(.data.percpu.page_aligned) - *(.data.percpu) - *(.data.percpu.shared_aligned) - __per_cpu_end = .; - } + PERCPU(PAGE_SIZE) . = ALIGN(PAGE_SIZE); /* freed after init ends here */ diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S index 1a614c0e6be..087a7f2c639 100644 --- a/arch/x86/kernel/vmlinux_64.lds.S +++ b/arch/x86/kernel/vmlinux_64.lds.S @@ -5,6 +5,7 @@ #define LOAD_OFFSET __START_KERNEL_map #include <asm-generic/vmlinux.lds.h> +#include <asm/asm-offsets.h> #include <asm/page.h> #undef i386 /* in case the preprocessor is a 32bit one */ @@ -13,12 +14,15 @@ OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64") OUTPUT_ARCH(i386:x86-64) ENTRY(phys_startup_64) jiffies_64 = jiffies; -_proxy_pda = 1; PHDRS { text PT_LOAD FLAGS(5); /* R_E */ data PT_LOAD FLAGS(7); /* RWE */ user PT_LOAD FLAGS(7); /* RWE */ data.init PT_LOAD FLAGS(7); /* RWE */ +#ifdef CONFIG_SMP + percpu PT_LOAD FLAGS(7); /* RWE */ +#endif + data.init2 PT_LOAD FLAGS(7); /* RWE */ note PT_NOTE FLAGS(0); /* ___ */ } SECTIONS @@ -208,14 +212,28 @@ SECTIONS __initramfs_end = .; #endif +#ifdef CONFIG_SMP + /* + * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the + * output PHDR, so the next output section - __data_nosave - should + * start another section data.init2. Also, pda should be at the head of + * percpu area. Preallocate it and define the percpu offset symbol + * so that it can be accessed as a percpu variable. + */ + . = ALIGN(PAGE_SIZE); + PERCPU_VADDR(0, :percpu) +#else PERCPU(PAGE_SIZE) +#endif . = ALIGN(PAGE_SIZE); __init_end = .; . = ALIGN(PAGE_SIZE); __nosave_begin = .; - .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { *(.data.nosave) } + .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) { + *(.data.nosave) + } :data.init2 /* use another section data.init2, see PERCPU_VADDR() above */ . = ALIGN(PAGE_SIZE); __nosave_end = .; @@ -239,8 +257,21 @@ SECTIONS DWARF_DEBUG } + /* + * Per-cpu symbols which need to be offset from __per_cpu_load + * for the boot processor. + */ +#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load +INIT_PER_CPU(gdt_page); +INIT_PER_CPU(irq_stack_union); + /* * Build-time check on the image size: */ ASSERT((_end - _text <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE") + +#ifdef CONFIG_SMP +ASSERT((per_cpu__irq_stack_union == 0), + "irq_stack_union is not at start of per-cpu area"); +#endif diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index a688f3bfaec..c609205df59 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -37,6 +37,7 @@ static unsigned long vsmp_save_fl(void) flags &= ~X86_EFLAGS_IF; return flags; } +PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl); static void vsmp_restore_fl(unsigned long flags) { @@ -46,6 +47,7 @@ static void vsmp_restore_fl(unsigned long flags) flags |= X86_EFLAGS_AC; native_restore_fl(flags); } +PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl); static void vsmp_irq_disable(void) { @@ -53,6 +55,7 @@ static void vsmp_irq_disable(void) native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC); } +PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable); static void vsmp_irq_enable(void) { @@ -60,6 +63,7 @@ static void vsmp_irq_enable(void) native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC)); } +PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) @@ -90,10 +94,10 @@ static void __init set_vsmp_pv_ops(void) cap, ctl); if (cap & ctl & (1 << 4)) { /* Setup irq ops and turn on vSMP IRQ fastpath handling */ - pv_irq_ops.irq_disable = vsmp_irq_disable; - pv_irq_ops.irq_enable = vsmp_irq_enable; - pv_irq_ops.save_fl = vsmp_save_fl; - pv_irq_ops.restore_fl = vsmp_restore_fl; + pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); + pv_irq_ops.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable); + pv_irq_ops.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); + pv_irq_ops.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); pv_init_ops.patch = vsmp_patch; ctl &= ~(1 << 4); diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 695e426aa35..3909e3ba5ce 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -58,5 +58,3 @@ EXPORT_SYMBOL(__memcpy); EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(init_level4_pgt); EXPORT_SYMBOL(load_gs_index); - -EXPORT_SYMBOL(_proxy_pda); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 92f1c6f3e19..da2e314f61b 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -173,24 +173,29 @@ static unsigned long save_fl(void) { return lguest_data.irq_enabled; } +PV_CALLEE_SAVE_REGS_THUNK(save_fl); /* restore_flags() just sets the flags back to the value given. */ static void restore_fl(unsigned long flags) { lguest_data.irq_enabled = flags; } +PV_CALLEE_SAVE_REGS_THUNK(restore_fl); /* Interrupts go off... */ static void irq_disable(void) { lguest_data.irq_enabled = 0; } +PV_CALLEE_SAVE_REGS_THUNK(irq_disable); /* Interrupts go on... */ static void irq_enable(void) { lguest_data.irq_enabled = X86_EFLAGS_IF; } +PV_CALLEE_SAVE_REGS_THUNK(irq_enable); + /*:*/ /*M:003 Note that we don't check for outstanding interrupts when we re-enable * them (or when we unmask an interrupt). This seems to work for the moment, @@ -278,7 +283,7 @@ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu) /* There's one problem which normal hardware doesn't have: the Host * can't handle us removing entries we're currently using. So we clear * the GS register here: if it's needed it'll be reloaded anyway. */ - loadsegment(gs, 0); + lazy_load_gs(0); lazy_hcall(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu, 0); } @@ -984,10 +989,10 @@ __init void lguest_init(void) /* interrupt-related operations */ pv_irq_ops.init_IRQ = lguest_init_IRQ; - pv_irq_ops.save_fl = save_fl; - pv_irq_ops.restore_fl = restore_fl; - pv_irq_ops.irq_disable = irq_disable; - pv_irq_ops.irq_enable = irq_enable; + pv_irq_ops.save_fl = PV_CALLEE_SAVE(save_fl); + pv_irq_ops.restore_fl = PV_CALLEE_SAVE(restore_fl); + pv_irq_ops.irq_disable = PV_CALLEE_SAVE(irq_disable); + pv_irq_ops.irq_enable = PV_CALLEE_SAVE(irq_enable); pv_irq_ops.safe_halt = lguest_safe_halt; /* init-time operations */ diff --git a/arch/x86/mach-default/Makefile b/arch/x86/mach-default/Makefile deleted file mode 100644 index 012fe34459e..00000000000 --- a/arch/x86/mach-default/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -# -# Makefile for the linux kernel. -# - -obj-y := setup.o diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c deleted file mode 100644 index a265a7c6319..00000000000 --- a/arch/x86/mach-default/setup.c +++ /dev/null @@ -1,174 +0,0 @@ -/* - * Machine specific setup for generic - */ - -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <asm/acpi.h> -#include <asm/arch_hooks.h> -#include <asm/e820.h> -#include <asm/setup.h> - -#include <mach_ipi.h> - -#ifdef CONFIG_HOTPLUG_CPU -#define DEFAULT_SEND_IPI (1) -#else -#define DEFAULT_SEND_IPI (0) -#endif - -int no_broadcast = DEFAULT_SEND_IPI; - -/** - * pre_intr_init_hook - initialisation prior to setting up interrupt vectors - * - * Description: - * Perform any necessary interrupt initialisation prior to setting up - * the "ordinary" interrupt call gates. For legacy reasons, the ISA - * interrupts should be initialised here if the machine emulates a PC - * in any way. - **/ -void __init pre_intr_init_hook(void) -{ - if (x86_quirks->arch_pre_intr_init) { - if (x86_quirks->arch_pre_intr_init()) - return; - } - init_ISA_irqs(); -} - -/* - * IRQ2 is cascade interrupt to second interrupt controller - */ -static struct irqaction irq2 = { - .handler = no_action, - .mask = CPU_MASK_NONE, - .name = "cascade", -}; - -/** - * intr_init_hook - post gate setup interrupt initialisation - * - * Description: - * Fill in any interrupts that may have been left out by the general - * init_IRQ() routine. interrupts having to do with the machine rather - * than the devices on the I/O bus (like APIC interrupts in intel MP - * systems) are started here. - **/ -void __init intr_init_hook(void) -{ - if (x86_quirks->arch_intr_init) { - if (x86_quirks->arch_intr_init()) - return; - } - if (!acpi_ioapic) - setup_irq(2, &irq2); - -} - -/** - * pre_setup_arch_hook - hook called prior to any setup_arch() execution - * - * Description: - * generally used to activate any machine specific identification - * routines that may be needed before setup_arch() runs. On Voyager - * this is used to get the board revision and type. - **/ -void __init pre_setup_arch_hook(void) -{ -} - -/** - * trap_init_hook - initialise system specific traps - * - * Description: - * Called as the final act of trap_init(). Used in VISWS to initialise - * the various board specific APIC traps. - **/ -void __init trap_init_hook(void) -{ - if (x86_quirks->arch_trap_init) { - if (x86_quirks->arch_trap_init()) - return; - } -} - -static struct irqaction irq0 = { - .handler = timer_interrupt, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL, - .mask = CPU_MASK_NONE, - .name = "timer" -}; - -/** - * pre_time_init_hook - do any specific initialisations before. - * - **/ -void __init pre_time_init_hook(void) -{ - if (x86_quirks->arch_pre_time_init) - x86_quirks->arch_pre_time_init(); -} - -/** - * time_init_hook - do any specific initialisations for the system timer. - * - * Description: - * Must plug the system timer interrupt source at HZ into the IRQ listed - * in irq_vectors.h:TIMER_IRQ - **/ -void __init time_init_hook(void) -{ - if (x86_quirks->arch_time_init) { - /* - * A nonzero return code does not mean failure, it means - * that the architecture quirk does not want any - * generic (timer) setup to be performed after this: - */ - if (x86_quirks->arch_time_init()) - return; - } - - irq0.mask = cpumask_of_cpu(0); - setup_irq(0, &irq0); -} - -#ifdef CONFIG_MCA -/** - * mca_nmi_hook - hook into MCA specific NMI chain - * - * Description: - * The MCA (Microchannel Architecture) has an NMI chain for NMI sources - * along the MCA bus. Use this to hook into that chain if you will need - * it. - **/ -void mca_nmi_hook(void) -{ - /* - * If I recall correctly, there's a whole bunch of other things that - * we can do to check for NMI problems, but that's all I know about - * at the moment. - */ - pr_warning("NMI generated from unknown source!\n"); -} -#endif - -static __init int no_ipi_broadcast(char *str) -{ - get_option(&str, &no_broadcast); - pr_info("Using %s mode\n", - no_broadcast ? "No IPI Broadcast" : "IPI Broadcast"); - return 1; -} -__setup("no_ipi_broadcast=", no_ipi_broadcast); - -static int __init print_ipi_mode(void) -{ - pr_info("Using IPI %s mode\n", - no_broadcast ? "No-Shortcut" : "Shortcut"); - return 0; -} - -late_initcall(print_ipi_mode); - diff --git a/arch/x86/mach-generic/Makefile b/arch/x86/mach-generic/Makefile deleted file mode 100644 index 6730f4e7c74..00000000000 --- a/arch/x86/mach-generic/Makefile +++ /dev/null @@ -1,11 +0,0 @@ -# -# Makefile for the generic architecture -# - -EXTRA_CFLAGS := -Iarch/x86/kernel - -obj-y := probe.o default.o -obj-$(CONFIG_X86_NUMAQ) += numaq.o -obj-$(CONFIG_X86_SUMMIT) += summit.o -obj-$(CONFIG_X86_BIGSMP) += bigsmp.o -obj-$(CONFIG_X86_ES7000) += es7000.o diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c deleted file mode 100644 index bc4c7840b2a..00000000000 --- a/arch/x86/mach-generic/bigsmp.c +++ /dev/null @@ -1,60 +0,0 @@ -/* - * APIC driver for "bigsmp" XAPIC machines with more than 8 virtual CPUs. - * Drives the local APIC in "clustered mode". - */ -#define APIC_DEFINITION 1 -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <asm/mpspec.h> -#include <asm/genapic.h> -#include <asm/fixmap.h> -#include <asm/apicdef.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/dmi.h> -#include <asm/bigsmp/apicdef.h> -#include <linux/smp.h> -#include <asm/bigsmp/apic.h> -#include <asm/bigsmp/ipi.h> -#include <asm/mach-default/mach_mpparse.h> -#include <asm/mach-default/mach_wakecpu.h> - -static int dmi_bigsmp; /* can be set by dmi scanners */ - -static int hp_ht_bigsmp(const struct dmi_system_id *d) -{ - printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident); - dmi_bigsmp = 1; - return 0; -} - - -static const struct dmi_system_id bigsmp_dmi_table[] = { - { hp_ht_bigsmp, "HP ProLiant DL760 G2", - { DMI_MATCH(DMI_BIOS_VENDOR, "HP"), - DMI_MATCH(DMI_BIOS_VERSION, "P44-"),} - }, - - { hp_ht_bigsmp, "HP ProLiant DL740", - { DMI_MATCH(DMI_BIOS_VENDOR, "HP"), - DMI_MATCH(DMI_BIOS_VERSION, "P47-"),} - }, - { } -}; - -static void vector_allocation_domain(int cpu, cpumask_t *retmask) -{ - cpus_clear(*retmask); - cpu_set(cpu, *retmask); -} - -static int probe_bigsmp(void) -{ - if (def_to_bigsmp) - dmi_bigsmp = 1; - else - dmi_check_system(bigsmp_dmi_table); - return dmi_bigsmp; -} - -struct genapic apic_bigsmp = APIC_INIT("bigsmp", probe_bigsmp); diff --git a/arch/x86/mach-generic/default.c b/arch/x86/mach-generic/default.c deleted file mode 100644 index e63a4a76d8c..00000000000 --- a/arch/x86/mach-generic/default.c +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Default generic APIC driver. This handles up to 8 CPUs. - */ -#define APIC_DEFINITION 1 -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <asm/mpspec.h> -#include <asm/mach-default/mach_apicdef.h> -#include <asm/genapic.h> -#include <asm/fixmap.h> -#include <asm/apicdef.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <asm/mach-default/mach_apic.h> -#include <asm/mach-default/mach_ipi.h> -#include <asm/mach-default/mach_mpparse.h> -#include <asm/mach-default/mach_wakecpu.h> - -/* should be called last. */ -static int probe_default(void) -{ - return 1; -} - -struct genapic apic_default = APIC_INIT("default", probe_default); diff --git a/arch/x86/mach-generic/es7000.c b/arch/x86/mach-generic/es7000.c deleted file mode 100644 index c2ded144802..00000000000 --- a/arch/x86/mach-generic/es7000.c +++ /dev/null @@ -1,103 +0,0 @@ -/* - * APIC driver for the Unisys ES7000 chipset. - */ -#define APIC_DEFINITION 1 -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <asm/mpspec.h> -#include <asm/genapic.h> -#include <asm/fixmap.h> -#include <asm/apicdef.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/init.h> -#include <asm/es7000/apicdef.h> -#include <linux/smp.h> -#include <asm/es7000/apic.h> -#include <asm/es7000/ipi.h> -#include <asm/es7000/mpparse.h> -#include <asm/mach-default/mach_wakecpu.h> - -void __init es7000_update_genapic_to_cluster(void) -{ - genapic->target_cpus = target_cpus_cluster; - genapic->int_delivery_mode = INT_DELIVERY_MODE_CLUSTER; - genapic->int_dest_mode = INT_DEST_MODE_CLUSTER; - genapic->no_balance_irq = NO_BALANCE_IRQ_CLUSTER; - - genapic->init_apic_ldr = init_apic_ldr_cluster; - - genapic->cpu_mask_to_apicid = cpu_mask_to_apicid_cluster; -} - -static int probe_es7000(void) -{ - /* probed later in mptable/ACPI hooks */ - return 0; -} - -extern void es7000_sw_apic(void); -static void __init enable_apic_mode(void) -{ - es7000_sw_apic(); - return; -} - -static __init int -mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) -{ - if (mpc->oemptr) { - struct mpc_oemtable *oem_table = - (struct mpc_oemtable *)mpc->oemptr; - if (!strncmp(oem, "UNISYS", 6)) - return parse_unisys_oem((char *)oem_table); - } - return 0; -} - -#ifdef CONFIG_ACPI -/* Hook from generic ACPI tables.c */ -static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - unsigned long oem_addr = 0; - int check_dsdt; - int ret = 0; - - /* check dsdt at first to avoid clear fix_map for oem_addr */ - check_dsdt = es7000_check_dsdt(); - - if (!find_unisys_acpi_oem_table(&oem_addr)) { - if (check_dsdt) - ret = parse_unisys_oem((char *)oem_addr); - else { - setup_unisys(); - ret = 1; - } - /* - * we need to unmap it - */ - unmap_unisys_acpi_oem_table(oem_addr); - } - return ret; -} -#else -static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - return 0; -} -#endif - -static void vector_allocation_domain(int cpu, cpumask_t *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; -} - -struct genapic __initdata_refok apic_es7000 = APIC_INIT("es7000", probe_es7000); diff --git a/arch/x86/mach-generic/numaq.c b/arch/x86/mach-generic/numaq.c deleted file mode 100644 index 3679e225564..00000000000 --- a/arch/x86/mach-generic/numaq.c +++ /dev/null @@ -1,53 +0,0 @@ -/* - * APIC driver for the IBM NUMAQ chipset. - */ -#define APIC_DEFINITION 1 -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <asm/mpspec.h> -#include <asm/genapic.h> -#include <asm/fixmap.h> -#include <asm/apicdef.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/init.h> -#include <asm/numaq/apicdef.h> -#include <linux/smp.h> -#include <asm/numaq/apic.h> -#include <asm/numaq/ipi.h> -#include <asm/numaq/mpparse.h> -#include <asm/numaq/wakecpu.h> -#include <asm/numaq.h> - -static int mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) -{ - numaq_mps_oem_check(mpc, oem, productid); - return found_numaq; -} - -static int probe_numaq(void) -{ - /* already know from get_memcfg_numaq() */ - return found_numaq; -} - -/* Hook from generic ACPI tables.c */ -static int acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - return 0; -} - -static void vector_allocation_domain(int cpu, cpumask_t *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; -} - -struct genapic apic_numaq = APIC_INIT("NUMAQ", probe_numaq); diff --git a/arch/x86/mach-generic/probe.c b/arch/x86/mach-generic/probe.c deleted file mode 100644 index 15a38daef1a..00000000000 --- a/arch/x86/mach-generic/probe.c +++ /dev/null @@ -1,152 +0,0 @@ -/* - * Copyright 2003 Andi Kleen, SuSE Labs. - * Subject to the GNU Public License, v.2 - * - * Generic x86 APIC driver probe layer. - */ -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/init.h> -#include <linux/errno.h> -#include <asm/fixmap.h> -#include <asm/mpspec.h> -#include <asm/apicdef.h> -#include <asm/genapic.h> -#include <asm/setup.h> - -extern struct genapic apic_numaq; -extern struct genapic apic_summit; -extern struct genapic apic_bigsmp; -extern struct genapic apic_es7000; -extern struct genapic apic_default; - -struct genapic *genapic = &apic_default; - -static struct genapic *apic_probe[] __initdata = { -#ifdef CONFIG_X86_NUMAQ - &apic_numaq, -#endif -#ifdef CONFIG_X86_SUMMIT - &apic_summit, -#endif -#ifdef CONFIG_X86_BIGSMP - &apic_bigsmp, -#endif -#ifdef CONFIG_X86_ES7000 - &apic_es7000, -#endif - &apic_default, /* must be last */ - NULL, -}; - -static int cmdline_apic __initdata; -static int __init parse_apic(char *arg) -{ - int i; - - if (!arg) - return -EINVAL; - - for (i = 0; apic_probe[i]; i++) { - if (!strcmp(apic_probe[i]->name, arg)) { - genapic = apic_probe[i]; - cmdline_apic = 1; - return 0; - } - } - - if (x86_quirks->update_genapic) - x86_quirks->update_genapic(); - - /* Parsed again by __setup for debug/verbose */ - return 0; -} -early_param("apic", parse_apic); - -void __init generic_bigsmp_probe(void) -{ -#ifdef CONFIG_X86_BIGSMP - /* - * This routine is used to switch to bigsmp mode when - * - There is no apic= option specified by the user - * - generic_apic_probe() has chosen apic_default as the sub_arch - * - we find more than 8 CPUs in acpi LAPIC listing with xAPIC support - */ - - if (!cmdline_apic && genapic == &apic_default) { - if (apic_bigsmp.probe()) { - genapic = &apic_bigsmp; - if (x86_quirks->update_genapic) - x86_quirks->update_genapic(); - printk(KERN_INFO "Overriding APIC driver with %s\n", - genapic->name); - } - } -#endif -} - -void __init generic_apic_probe(void) -{ - if (!cmdline_apic) { - int i; - for (i = 0; apic_probe[i]; i++) { - if (apic_probe[i]->probe()) { - genapic = apic_probe[i]; - break; - } - } - /* Not visible without early console */ - if (!apic_probe[i]) - panic("Didn't find an APIC driver"); - - if (x86_quirks->update_genapic) - x86_quirks->update_genapic(); - } - printk(KERN_INFO "Using APIC driver %s\n", genapic->name); -} - -/* These functions can switch the APIC even after the initial ->probe() */ - -int __init mps_oem_check(struct mpc_table *mpc, char *oem, char *productid) -{ - int i; - for (i = 0; apic_probe[i]; ++i) { - if (apic_probe[i]->mps_oem_check(mpc, oem, productid)) { - if (!cmdline_apic) { - genapic = apic_probe[i]; - if (x86_quirks->update_genapic) - x86_quirks->update_genapic(); - printk(KERN_INFO "Switched to APIC driver `%s'.\n", - genapic->name); - } - return 1; - } - } - return 0; -} - -int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - int i; - for (i = 0; apic_probe[i]; ++i) { - if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) { - if (!cmdline_apic) { - genapic = apic_probe[i]; - if (x86_quirks->update_genapic) - x86_quirks->update_genapic(); - printk(KERN_INFO "Switched to APIC driver `%s'.\n", - genapic->name); - } - return 1; - } - } - return 0; -} - -int hard_smp_processor_id(void) -{ - return genapic->get_apic_id(*(unsigned long *)(APIC_BASE+APIC_ID)); -} diff --git a/arch/x86/mach-generic/summit.c b/arch/x86/mach-generic/summit.c deleted file mode 100644 index 2821ffc188b..00000000000 --- a/arch/x86/mach-generic/summit.c +++ /dev/null @@ -1,40 +0,0 @@ -/* - * APIC driver for the IBM "Summit" chipset. - */ -#define APIC_DEFINITION 1 -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <asm/mpspec.h> -#include <asm/genapic.h> -#include <asm/fixmap.h> -#include <asm/apicdef.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/init.h> -#include <asm/summit/apicdef.h> -#include <linux/smp.h> -#include <asm/summit/apic.h> -#include <asm/summit/ipi.h> -#include <asm/summit/mpparse.h> -#include <asm/mach-default/mach_wakecpu.h> - -static int probe_summit(void) -{ - /* probed later in mptable/ACPI hooks */ - return 0; -} - -static void vector_allocation_domain(int cpu, cpumask_t *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; -} - -struct genapic apic_summit = APIC_INIT("summit", probe_summit); diff --git a/arch/x86/mach-rdc321x/Makefile b/arch/x86/mach-rdc321x/Makefile deleted file mode 100644 index 8325b4ca431..00000000000 --- a/arch/x86/mach-rdc321x/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -# -# Makefile for the RDC321x specific parts of the kernel -# -obj-$(CONFIG_X86_RDC321X) := gpio.o platform.o - diff --git a/arch/x86/mach-rdc321x/gpio.c b/arch/x86/mach-rdc321x/gpio.c deleted file mode 100644 index 247f33d3a40..00000000000 --- a/arch/x86/mach-rdc321x/gpio.c +++ /dev/null @@ -1,194 +0,0 @@ -/* - * GPIO support for RDC SoC R3210/R8610 - * - * Copyright (C) 2007, Florian Fainelli <florian@openwrt.org> - * Copyright (C) 2008, Volker Weiss <dev@tintuc.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - */ - - -#include <linux/spinlock.h> -#include <linux/io.h> -#include <linux/types.h> -#include <linux/module.h> - -#include <asm/gpio.h> -#include <asm/mach-rdc321x/rdc321x_defs.h> - - -/* spin lock to protect our private copy of GPIO data register plus - the access to PCI conf registers. */ -static DEFINE_SPINLOCK(gpio_lock); - -/* copy of GPIO data registers */ -static u32 gpio_data_reg1; -static u32 gpio_data_reg2; - -static u32 gpio_request_data[2]; - - -static inline void rdc321x_conf_write(unsigned addr, u32 value) -{ - outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); - outl(value, RDC3210_CFGREG_DATA); -} - -static inline void rdc321x_conf_or(unsigned addr, u32 value) -{ - outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); - value |= inl(RDC3210_CFGREG_DATA); - outl(value, RDC3210_CFGREG_DATA); -} - -static inline u32 rdc321x_conf_read(unsigned addr) -{ - outl((1 << 31) | (7 << 11) | addr, RDC3210_CFGREG_ADDR); - - return inl(RDC3210_CFGREG_DATA); -} - -/* configure pin as GPIO */ -static void rdc321x_configure_gpio(unsigned gpio) -{ - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - rdc321x_conf_or(gpio < 32 - ? RDC321X_GPIO_CTRL_REG1 : RDC321X_GPIO_CTRL_REG2, - 1 << (gpio & 0x1f)); - spin_unlock_irqrestore(&gpio_lock, flags); -} - -/* initially setup the 2 copies of the gpio data registers. - This function must be called by the platform setup code. */ -void __init rdc321x_gpio_setup() -{ - /* this might not be, what others (BIOS, bootloader, etc.) - wrote to these registers before, but it's a good guess. Still - better than just using 0xffffffff. */ - - gpio_data_reg1 = rdc321x_conf_read(RDC321X_GPIO_DATA_REG1); - gpio_data_reg2 = rdc321x_conf_read(RDC321X_GPIO_DATA_REG2); -} - -/* determine, if gpio number is valid */ -static inline int rdc321x_is_gpio(unsigned gpio) -{ - return gpio <= RDC321X_MAX_GPIO; -} - -/* request GPIO */ -int rdc_gpio_request(unsigned gpio, const char *label) -{ - unsigned long flags; - - if (!rdc321x_is_gpio(gpio)) - return -EINVAL; - - spin_lock_irqsave(&gpio_lock, flags); - if (gpio_request_data[(gpio & 0x20) ? 1 : 0] & (1 << (gpio & 0x1f))) - goto inuse; - gpio_request_data[(gpio & 0x20) ? 1 : 0] |= (1 << (gpio & 0x1f)); - spin_unlock_irqrestore(&gpio_lock, flags); - - return 0; -inuse: - spin_unlock_irqrestore(&gpio_lock, flags); - return -EINVAL; -} -EXPORT_SYMBOL(rdc_gpio_request); - -/* release previously-claimed GPIO */ -void rdc_gpio_free(unsigned gpio) -{ - unsigned long flags; - - if (!rdc321x_is_gpio(gpio)) - return; - - spin_lock_irqsave(&gpio_lock, flags); - gpio_request_data[(gpio & 0x20) ? 1 : 0] &= ~(1 << (gpio & 0x1f)); - spin_unlock_irqrestore(&gpio_lock, flags); -} -EXPORT_SYMBOL(rdc_gpio_free); - -/* read GPIO pin */ -int rdc_gpio_get_value(unsigned gpio) -{ - u32 reg; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - reg = rdc321x_conf_read(gpio < 32 - ? RDC321X_GPIO_DATA_REG1 : RDC321X_GPIO_DATA_REG2); - spin_unlock_irqrestore(&gpio_lock, flags); - - return (1 << (gpio & 0x1f)) & reg ? 1 : 0; -} -EXPORT_SYMBOL(rdc_gpio_get_value); - -/* set GPIO pin to value */ -void rdc_gpio_set_value(unsigned gpio, int value) -{ - unsigned long flags; - u32 reg; - - reg = 1 << (gpio & 0x1f); - if (gpio < 32) { - spin_lock_irqsave(&gpio_lock, flags); - if (value) - gpio_data_reg1 |= reg; - else - gpio_data_reg1 &= ~reg; - rdc321x_conf_write(RDC321X_GPIO_DATA_REG1, gpio_data_reg1); - spin_unlock_irqrestore(&gpio_lock, flags); - } else { - spin_lock_irqsave(&gpio_lock, flags); - if (value) - gpio_data_reg2 |= reg; - else - gpio_data_reg2 &= ~reg; - rdc321x_conf_write(RDC321X_GPIO_DATA_REG2, gpio_data_reg2); - spin_unlock_irqrestore(&gpio_lock, flags); - } -} -EXPORT_SYMBOL(rdc_gpio_set_value); - -/* configure GPIO pin as input */ -int rdc_gpio_direction_input(unsigned gpio) -{ - if (!rdc321x_is_gpio(gpio)) - return -EINVAL; - - rdc321x_configure_gpio(gpio); - - return 0; -} -EXPORT_SYMBOL(rdc_gpio_direction_input); - -/* configure GPIO pin as output and set value */ -int rdc_gpio_direction_output(unsigned gpio, int value) -{ - if (!rdc321x_is_gpio(gpio)) - return -EINVAL; - - gpio_set_value(gpio, value); - rdc321x_configure_gpio(gpio); - - return 0; -} -EXPORT_SYMBOL(rdc_gpio_direction_output); diff --git a/arch/x86/mach-rdc321x/platform.c b/arch/x86/mach-rdc321x/platform.c deleted file mode 100644 index 4f4e50c3ad3..00000000000 --- a/arch/x86/mach-rdc321x/platform.c +++ /dev/null @@ -1,69 +0,0 @@ -/* - * Generic RDC321x platform devices - * - * Copyright (C) 2007 Florian Fainelli <florian@openwrt.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, - * Boston, MA 02110-1301, USA. - * - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/list.h> -#include <linux/device.h> -#include <linux/platform_device.h> -#include <linux/leds.h> - -#include <asm/gpio.h> - -/* LEDS */ -static struct gpio_led default_leds[] = { - { .name = "rdc:dmz", .gpio = 1, }, -}; - -static struct gpio_led_platform_data rdc321x_led_data = { - .num_leds = ARRAY_SIZE(default_leds), - .leds = default_leds, -}; - -static struct platform_device rdc321x_leds = { - .name = "leds-gpio", - .id = -1, - .dev = { - .platform_data = &rdc321x_led_data, - } -}; - -/* Watchdog */ -static struct platform_device rdc321x_wdt = { - .name = "rdc321x-wdt", - .id = -1, - .num_resources = 0, -}; - -static struct platform_device *rdc321x_devs[] = { - &rdc321x_leds, - &rdc321x_wdt -}; - -static int __init rdc_board_setup(void) -{ - rdc321x_gpio_setup(); - - return platform_add_devices(rdc321x_devs, ARRAY_SIZE(rdc321x_devs)); -} - -arch_initcall(rdc_board_setup); diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c index 7ffcdeec463..6f5a38c7f90 100644 --- a/arch/x86/mach-voyager/voyager_smp.c +++ b/arch/x86/mach-voyager/voyager_smp.c @@ -400,7 +400,7 @@ void __init find_smp_config(void) VOYAGER_SUS_IN_CONTROL_PORT); current_thread_info()->cpu = boot_cpu_id; - x86_write_percpu(cpu_number, boot_cpu_id); + percpu_write(cpu_number, boot_cpu_id); } /* @@ -528,7 +528,6 @@ static void __init do_boot_cpu(__u8 cpu) /* init_tasks (in sched.c) is indexed logically */ stack_start.sp = (void *)idle->thread.sp; - init_gdt(cpu); per_cpu(current_task, cpu) = idle; early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); irq_ctx_init(cpu); @@ -1745,14 +1744,13 @@ static void __init voyager_smp_prepare_cpus(unsigned int max_cpus) static void __cpuinit voyager_smp_prepare_boot_cpu(void) { - init_gdt(smp_processor_id()); - switch_to_new_gdt(); + int cpu = smp_processor_id(); + switch_to_new_gdt(cpu); cpu_online_map = cpumask_of_cpu(smp_processor_id()); cpu_callout_map = cpumask_of_cpu(smp_processor_id()); cpu_callin_map = CPU_MASK_NONE; cpu_present_map = cpumask_of_cpu(smp_processor_id()); - } static int __cpuinit voyager_cpu_up(unsigned int cpu) @@ -1779,7 +1777,6 @@ static void __init voyager_smp_cpus_done(unsigned int max_cpus) void __init smp_setup_processor_id(void) { current_thread_info()->cpu = hard_smp_processor_id(); - x86_write_percpu(cpu_number, hard_smp_processor_id()); } static void voyager_send_call_func(const struct cpumask *callmask) diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index c7b06feb139..5d87f586f8d 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -131,7 +131,7 @@ u_char emulating = 0; static int valid_prefix(u_char *Byte, u_char __user ** fpu_eip, overrides * override); -asmlinkage void math_emulate(long arg) +void math_emulate(struct math_emu_info *info) { u_char FPU_modrm, byte1; unsigned short code; @@ -161,7 +161,7 @@ asmlinkage void math_emulate(long arg) RE_ENTRANT_CHECK_ON; #endif /* RE_ENTRANT_CHECKING */ - SETUP_DATA_AREA(arg); + FPU_info = info; FPU_ORIG_EIP = FPU_EIP; @@ -659,7 +659,7 @@ static int valid_prefix(u_char *Byte, u_char __user **fpu_eip, } } -void math_abort(struct info *info, unsigned int signal) +void math_abort(struct math_emu_info *info, unsigned int signal) { FPU_EIP = FPU_ORIG_EIP; current->thread.trap_no = 16; diff --git a/arch/x86/math-emu/fpu_proto.h b/arch/x86/math-emu/fpu_proto.h index aa49b6a0d85..9779df436b7 100644 --- a/arch/x86/math-emu/fpu_proto.h +++ b/arch/x86/math-emu/fpu_proto.h @@ -51,8 +51,8 @@ extern void ffreep(void); extern void fst_i_(void); extern void fstp_i(void); /* fpu_entry.c */ -asmlinkage extern void math_emulate(long arg); -extern void math_abort(struct info *info, unsigned int signal); +extern void math_emulate(struct math_emu_info *info); +extern void math_abort(struct math_emu_info *info, unsigned int signal); /* fpu_etc.c */ extern void FPU_etc(void); /* fpu_tags.c */ diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 13488fa153e..50fa0ec2c8a 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -16,10 +16,6 @@ #include <linux/kernel.h> #include <linux/mm.h> -/* This sets the pointer FPU_info to point to the argument part - of the stack frame of math_emulate() */ -#define SETUP_DATA_AREA(arg) FPU_info = (struct info *) &arg - /* s is always from a cpu register, and the cpu does bounds checking * during register load --> no further bounds checks needed */ #define LDT_DESCRIPTOR(s) (((struct desc_struct *)current->mm->context.ldt)[(s) >> 3]) @@ -38,12 +34,12 @@ #define I387 (current->thread.xstate) #define FPU_info (I387->soft.info) -#define FPU_CS (*(unsigned short *) &(FPU_info->___cs)) -#define FPU_SS (*(unsigned short *) &(FPU_info->___ss)) -#define FPU_DS (*(unsigned short *) &(FPU_info->___ds)) -#define FPU_EAX (FPU_info->___eax) -#define FPU_EFLAGS (FPU_info->___eflags) -#define FPU_EIP (FPU_info->___eip) +#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs)) +#define FPU_SS (*(unsigned short *) &(FPU_info->regs->ss)) +#define FPU_DS (*(unsigned short *) &(FPU_info->regs->ds)) +#define FPU_EAX (FPU_info->regs->ax) +#define FPU_EFLAGS (FPU_info->regs->flags) +#define FPU_EIP (FPU_info->regs->ip) #define FPU_ORIG_EIP (FPU_info->___orig_eip) #define FPU_lookahead (I387->soft.lookahead) diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index d701e2b39e4..6ef5e99380f 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -29,46 +29,43 @@ #define FPU_WRITE_BIT 0x10 static int reg_offset[] = { - offsetof(struct info, ___eax), - offsetof(struct info, ___ecx), - offsetof(struct info, ___edx), - offsetof(struct info, ___ebx), - offsetof(struct info, ___esp), - offsetof(struct info, ___ebp), - offsetof(struct info, ___esi), - offsetof(struct info, ___edi) + offsetof(struct pt_regs, ax), + offsetof(struct pt_regs, cx), + offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, bx), + offsetof(struct pt_regs, sp), + offsetof(struct pt_regs, bp), + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, di) }; -#define REG_(x) (*(long *)(reg_offset[(x)]+(u_char *) FPU_info)) +#define REG_(x) (*(long *)(reg_offset[(x)] + (u_char *)FPU_info->regs)) static int reg_offset_vm86[] = { - offsetof(struct info, ___cs), - offsetof(struct info, ___vm86_ds), - offsetof(struct info, ___vm86_es), - offsetof(struct info, ___vm86_fs), - offsetof(struct info, ___vm86_gs), - offsetof(struct info, ___ss), - offsetof(struct info, ___vm86_ds) + offsetof(struct pt_regs, cs), + offsetof(struct kernel_vm86_regs, ds), + offsetof(struct kernel_vm86_regs, es), + offsetof(struct kernel_vm86_regs, fs), + offsetof(struct kernel_vm86_regs, gs), + offsetof(struct pt_regs, ss), + offsetof(struct kernel_vm86_regs, ds) }; #define VM86_REG_(x) (*(unsigned short *) \ - (reg_offset_vm86[((unsigned)x)]+(u_char *) FPU_info)) - -/* This dummy, gs is not saved on the stack. */ -#define ___GS ___ds + (reg_offset_vm86[((unsigned)x)] + (u_char *)FPU_info->regs)) static int reg_offset_pm[] = { - offsetof(struct info, ___cs), - offsetof(struct info, ___ds), - offsetof(struct info, ___es), - offsetof(struct info, ___fs), - offsetof(struct info, ___GS), - offsetof(struct info, ___ss), - offsetof(struct info, ___ds) + offsetof(struct pt_regs, cs), + offsetof(struct pt_regs, ds), + offsetof(struct pt_regs, es), + offsetof(struct pt_regs, fs), + offsetof(struct pt_regs, ds), /* dummy, not saved on stack */ + offsetof(struct pt_regs, ss), + offsetof(struct pt_regs, ds) }; #define PM_REG_(x) (*(unsigned short *) \ - (reg_offset_pm[((unsigned)x)]+(u_char *) FPU_info)) + (reg_offset_pm[((unsigned)x)] + (u_char *)FPU_info->regs)) /* Decode the SIB byte. This function assumes mod != 0 */ static int sib(int mod, unsigned long *fpu_eip) @@ -153,11 +150,9 @@ static long pm_address(u_char FPU_modrm, u_char segment, #endif /* PARANOID */ switch (segment) { - /* gs isn't used by the kernel, so it still has its - user-space value. */ case PREFIX_GS_ - 1: - /* N.B. - movl %seg, mem is a 2 byte write regardless of prefix */ - savesegment(gs, addr->selector); + /* user gs handling can be lazy, use special accessors */ + addr->selector = get_user_gs(FPU_info->regs); break; default: addr->selector = PM_REG_(segment); @@ -349,34 +344,34 @@ void __user *FPU_get_address_16(u_char FPU_modrm, unsigned long *fpu_eip, } switch (rm) { case 0: - address += FPU_info->___ebx + FPU_info->___esi; + address += FPU_info->regs->bx + FPU_info->regs->si; break; case 1: - address += FPU_info->___ebx + FPU_info->___edi; + address += FPU_info->regs->bx + FPU_info->regs->di; break; case 2: - address += FPU_info->___ebp + FPU_info->___esi; + address += FPU_info->regs->bp + FPU_info->regs->si; if (addr_modes.override.segment == PREFIX_DEFAULT) addr_modes.override.segment = PREFIX_SS_; break; case 3: - address += FPU_info->___ebp + FPU_info->___edi; + address += FPU_info->regs->bp + FPU_info->regs->di; if (addr_modes.override.segment == PREFIX_DEFAULT) addr_modes.override.segment = PREFIX_SS_; break; case 4: - address += FPU_info->___esi; + address += FPU_info->regs->si; break; case 5: - address += FPU_info->___edi; + address += FPU_info->regs->di; break; case 6: - address += FPU_info->___ebp; + address += FPU_info->regs->bp; if (addr_modes.override.segment == PREFIX_DEFAULT) addr_modes.override.segment = PREFIX_SS_; break; case 7: - address += FPU_info->___ebx; + address += FPU_info->regs->bx; break; } diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index d8cc96a2738..2b938a38491 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,6 +1,8 @@ obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o gup.o +obj-$(CONFIG_SMP) += tlb.o + obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 7e8db53528a..61b41ca3b5a 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -23,6 +23,12 @@ int fixup_exception(struct pt_regs *regs) fixup = search_exception_tables(regs->ip); if (fixup) { + /* If fixup is less than 16, it means uaccess error */ + if (fixup->fixup < 16) { + current_thread_info()->uaccess_err = -EFAULT; + regs->ip += fixup->fixup; + return 1; + } regs->ip = fixup->fixup; return 1; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index c76ef1d701c..2a9ea3aee49 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -26,6 +26,7 @@ #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/kdebug.h> +#include <linux/magic.h> #include <asm/system.h> #include <asm/desc.h> @@ -91,8 +92,8 @@ static inline int notify_page_fault(struct pt_regs *regs) * * Opcode checker based on code by Richard Brunner */ -static int is_prefetch(struct pt_regs *regs, unsigned long addr, - unsigned long error_code) +static int is_prefetch(struct pt_regs *regs, unsigned long error_code, + unsigned long addr) { unsigned char *instr; int scan_more = 1; @@ -409,17 +410,16 @@ static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, } #ifdef CONFIG_X86_64 -static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, - unsigned long error_code) +static noinline void pgtable_bad(struct pt_regs *regs, + unsigned long error_code, unsigned long address) { unsigned long flags = oops_begin(); int sig = SIGKILL; - struct task_struct *tsk; + struct task_struct *tsk = current; printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", - current->comm, address); + tsk->comm, address); dump_pagetable(address); - tsk = current; tsk->thread.cr2 = address; tsk->thread.trap_no = 14; tsk->thread.error_code = error_code; @@ -429,6 +429,196 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, } #endif +static noinline void no_context(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + struct task_struct *tsk = current; + unsigned long *stackend; + +#ifdef CONFIG_X86_64 + unsigned long flags; + int sig; +#endif + + /* Are we prepared to handle this kernel fault? */ + if (fixup_exception(regs)) + return; + + /* + * X86_32 + * Valid to do another page fault here, because if this fault + * had been triggered by is_prefetch fixup_exception would have + * handled it. + * + * X86_64 + * Hall of shame of CPU/BIOS bugs. + */ + if (is_prefetch(regs, error_code, address)) + return; + + if (is_errata93(regs, address)) + return; + + /* + * Oops. The kernel tried to access some bad page. We'll have to + * terminate things with extreme prejudice. + */ +#ifdef CONFIG_X86_32 + bust_spinlocks(1); +#else + flags = oops_begin(); +#endif + + show_fault_oops(regs, error_code, address); + + stackend = end_of_stack(tsk); + if (*stackend != STACK_END_MAGIC) + printk(KERN_ALERT "Thread overran stack, or stack corrupted\n"); + + tsk->thread.cr2 = address; + tsk->thread.trap_no = 14; + tsk->thread.error_code = error_code; + +#ifdef CONFIG_X86_32 + die("Oops", regs, error_code); + bust_spinlocks(0); + do_exit(SIGKILL); +#else + sig = SIGKILL; + if (__die("Oops", regs, error_code)) + sig = 0; + /* Executive summary in case the body of the oops scrolled away */ + printk(KERN_EMERG "CR2: %016lx\n", address); + oops_end(flags, regs, sig); +#endif +} + +static void __bad_area_nosemaphore(struct pt_regs *regs, + unsigned long error_code, unsigned long address, + int si_code) +{ + struct task_struct *tsk = current; + + /* User mode accesses just cause a SIGSEGV */ + if (error_code & PF_USER) { + /* + * It's possible to have interrupts off here. + */ + local_irq_enable(); + + /* + * Valid to do another page fault here because this one came + * from user space. + */ + if (is_prefetch(regs, error_code, address)) + return; + + if (is_errata100(regs, address)) + return; + + if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && + printk_ratelimit()) { + printk( + "%s%s[%d]: segfault at %lx ip %p sp %p error %lx", + task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, + tsk->comm, task_pid_nr(tsk), address, + (void *) regs->ip, (void *) regs->sp, error_code); + print_vma_addr(" in ", regs->ip); + printk("\n"); + } + + tsk->thread.cr2 = address; + /* Kernel addresses are always protection faults */ + tsk->thread.error_code = error_code | (address >= TASK_SIZE); + tsk->thread.trap_no = 14; + force_sig_info_fault(SIGSEGV, si_code, address, tsk); + return; + } + + if (is_f00f_bug(regs, address)) + return; + + no_context(regs, error_code, address); +} + +static noinline void bad_area_nosemaphore(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR); +} + +static void __bad_area(struct pt_regs *regs, + unsigned long error_code, unsigned long address, + int si_code) +{ + struct mm_struct *mm = current->mm; + + /* + * Something tried to access memory that isn't in our memory map.. + * Fix it, but check if it's kernel or user first.. + */ + up_read(&mm->mmap_sem); + + __bad_area_nosemaphore(regs, error_code, address, si_code); +} + +static noinline void bad_area(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area(regs, error_code, address, SEGV_MAPERR); +} + +static noinline void bad_area_access_error(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area(regs, error_code, address, SEGV_ACCERR); +} + +/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */ +static void out_of_memory(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + /* + * We ran out of memory, call the OOM killer, and return the userspace + * (which will retry the fault, or kill us if we got oom-killed). + */ + up_read(¤t->mm->mmap_sem); + pagefault_out_of_memory(); +} + +static void do_sigbus(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + struct task_struct *tsk = current; + struct mm_struct *mm = tsk->mm; + + up_read(&mm->mmap_sem); + + /* Kernel mode? Handle exceptions or die */ + if (!(error_code & PF_USER)) + no_context(regs, error_code, address); +#ifdef CONFIG_X86_32 + /* User space => ok to do another page fault */ + if (is_prefetch(regs, error_code, address)) + return; +#endif + tsk->thread.cr2 = address; + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 14; + force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); +} + +static noinline void mm_fault_error(struct pt_regs *regs, + unsigned long error_code, unsigned long address, unsigned int fault) +{ + if (fault & VM_FAULT_OOM) + out_of_memory(regs, error_code, address); + else if (fault & VM_FAULT_SIGBUS) + do_sigbus(regs, error_code, address); + else + BUG(); +} + static int spurious_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & PF_WRITE) && !pte_write(*pte)) @@ -448,8 +638,8 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. */ -static int spurious_fault(unsigned long address, - unsigned long error_code) +static noinline int spurious_fault(unsigned long error_code, + unsigned long address) { pgd_t *pgd; pud_t *pud; @@ -494,7 +684,7 @@ static int spurious_fault(unsigned long address, * * This assumes no large pages in there. */ -static int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { #ifdef CONFIG_X86_32 unsigned long pgd_paddr; @@ -573,6 +763,25 @@ static int vmalloc_fault(unsigned long address) int show_unhandled_signals = 1; +static inline int access_error(unsigned long error_code, int write, + struct vm_area_struct *vma) +{ + if (write) { + /* write, present and write, not present */ + if (unlikely(!(vma->vm_flags & VM_WRITE))) + return 1; + } else if (unlikely(error_code & PF_PROT)) { + /* read, present */ + return 1; + } else { + /* read, not present */ + if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))) + return 1; + } + + return 0; +} + /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate @@ -583,16 +792,12 @@ asmlinkage #endif void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) { + unsigned long address; struct task_struct *tsk; struct mm_struct *mm; struct vm_area_struct *vma; - unsigned long address; - int write, si_code; + int write; int fault; -#ifdef CONFIG_X86_64 - unsigned long flags; - int sig; -#endif tsk = current; mm = tsk->mm; @@ -601,8 +806,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) /* get the address */ address = read_cr2(); - si_code = SEGV_MAPERR; - if (unlikely(kmmio_fault(regs, address))) return; @@ -629,7 +832,7 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) return; /* Can handle a stale RO->RW TLB */ - if (spurious_fault(address, error_code)) + if (spurious_fault(error_code, address)) return; /* kprobes don't want to hook the spurious faults. */ @@ -639,13 +842,12 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock. */ - goto bad_area_nosemaphore; + bad_area_nosemaphore(regs, error_code, address); + return; } - /* kprobes don't want to hook the spurious faults. */ - if (notify_page_fault(regs)) + if (unlikely(notify_page_fault(regs))) return; - /* * It's safe to allow irq's after cr2 has been saved and the * vmalloc fault has been handled. @@ -661,15 +863,17 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) #ifdef CONFIG_X86_64 if (unlikely(error_code & PF_RSVD)) - pgtable_bad(address, regs, error_code); + pgtable_bad(regs, error_code, address); #endif /* * If we're in an interrupt, have no user context or are running in an * atomic region then we must not take the fault. */ - if (unlikely(in_atomic() || !mm)) - goto bad_area_nosemaphore; + if (unlikely(in_atomic() || !mm)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } /* * When running in the kernel we expect faults to occur only to @@ -687,20 +891,26 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * source. If this is invalid we can skip the address space check, * thus avoiding the deadlock. */ - if (!down_read_trylock(&mm->mmap_sem)) { + if (unlikely(!down_read_trylock(&mm->mmap_sem))) { if ((error_code & PF_USER) == 0 && - !search_exception_tables(regs->ip)) - goto bad_area_nosemaphore; + !search_exception_tables(regs->ip)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } down_read(&mm->mmap_sem); } vma = find_vma(mm, address); - if (!vma) - goto bad_area; - if (vma->vm_start <= address) + if (unlikely(!vma)) { + bad_area(regs, error_code, address); + return; + } + if (likely(vma->vm_start <= address)) goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; + if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { + bad_area(regs, error_code, address); + return; + } if (error_code & PF_USER) { /* * Accessing the stack below %sp is always a bug. @@ -708,31 +918,25 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * and pusha to work. ("enter $65535,$31" pushes * 32 pointers and then decrements %sp by 65535.) */ - if (address + 65536 + 32 * sizeof(unsigned long) < regs->sp) - goto bad_area; + if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) { + bad_area(regs, error_code, address); + return; + } } - if (expand_stack(vma, address)) - goto bad_area; -/* - * Ok, we have a good vm_area for this memory access, so - * we can handle it.. - */ + if (unlikely(expand_stack(vma, address))) { + bad_area(regs, error_code, address); + return; + } + + /* + * Ok, we have a good vm_area for this memory access, so + * we can handle it.. + */ good_area: - si_code = SEGV_ACCERR; - write = 0; - switch (error_code & (PF_PROT|PF_WRITE)) { - default: /* 3: write, present */ - /* fall through */ - case PF_WRITE: /* write, not present */ - if (!(vma->vm_flags & VM_WRITE)) - goto bad_area; - write++; - break; - case PF_PROT: /* read, present */ - goto bad_area; - case 0: /* read, not present */ - if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) - goto bad_area; + write = error_code & PF_WRITE; + if (unlikely(access_error(error_code, write, vma))) { + bad_area_access_error(regs, error_code, address); + return; } /* @@ -742,11 +946,8 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, write); if (unlikely(fault & VM_FAULT_ERROR)) { - if (fault & VM_FAULT_OOM) - goto out_of_memory; - else if (fault & VM_FAULT_SIGBUS) - goto do_sigbus; - BUG(); + mm_fault_error(regs, error_code, address, fault); + return; } if (fault & VM_FAULT_MAJOR) tsk->maj_flt++; @@ -764,128 +965,6 @@ good_area: } #endif up_read(&mm->mmap_sem); - return; - -/* - * Something tried to access memory that isn't in our memory map.. - * Fix it, but check if it's kernel or user first.. - */ -bad_area: - up_read(&mm->mmap_sem); - -bad_area_nosemaphore: - /* User mode accesses just cause a SIGSEGV */ - if (error_code & PF_USER) { - /* - * It's possible to have interrupts off here. - */ - local_irq_enable(); - - /* - * Valid to do another page fault here because this one came - * from user space. - */ - if (is_prefetch(regs, address, error_code)) - return; - - if (is_errata100(regs, address)) - return; - - if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && - printk_ratelimit()) { - printk( - "%s%s[%d]: segfault at %lx ip %p sp %p error %lx", - task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, - tsk->comm, task_pid_nr(tsk), address, - (void *) regs->ip, (void *) regs->sp, error_code); - print_vma_addr(" in ", regs->ip); - printk("\n"); - } - - tsk->thread.cr2 = address; - /* Kernel addresses are always protection faults */ - tsk->thread.error_code = error_code | (address >= TASK_SIZE); - tsk->thread.trap_no = 14; - force_sig_info_fault(SIGSEGV, si_code, address, tsk); - return; - } - - if (is_f00f_bug(regs, address)) - return; - -no_context: - /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs)) - return; - - /* - * X86_32 - * Valid to do another page fault here, because if this fault - * had been triggered by is_prefetch fixup_exception would have - * handled it. - * - * X86_64 - * Hall of shame of CPU/BIOS bugs. - */ - if (is_prefetch(regs, address, error_code)) - return; - - if (is_errata93(regs, address)) - return; - -/* - * Oops. The kernel tried to access some bad page. We'll have to - * terminate things with extreme prejudice. - */ -#ifdef CONFIG_X86_32 - bust_spinlocks(1); -#else - flags = oops_begin(); -#endif - - show_fault_oops(regs, error_code, address); - - tsk->thread.cr2 = address; - tsk->thread.trap_no = 14; - tsk->thread.error_code = error_code; - -#ifdef CONFIG_X86_32 - die("Oops", regs, error_code); - bust_spinlocks(0); - do_exit(SIGKILL); -#else - sig = SIGKILL; - if (__die("Oops", regs, error_code)) - sig = 0; - /* Executive summary in case the body of the oops scrolled away */ - printk(KERN_EMERG "CR2: %016lx\n", address); - oops_end(flags, regs, sig); -#endif - -out_of_memory: - /* - * We ran out of memory, call the OOM killer, and return the userspace - * (which will retry the fault, or kill us if we got oom-killed). - */ - up_read(&mm->mmap_sem); - pagefault_out_of_memory(); - return; - -do_sigbus: - up_read(&mm->mmap_sem); - - /* Kernel mode? Handle exceptions or die */ - if (!(error_code & PF_USER)) - goto no_context; -#ifdef CONFIG_X86_32 - /* User space => ok to do another page fault */ - if (is_prefetch(regs, address, error_code)) - return; -#endif - tsk->thread.cr2 = address; - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 14; - force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); } DEFINE_SPINLOCK(pgd_lock); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index af750ab973b..1448bcb7f22 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -367,7 +367,7 @@ EXPORT_SYMBOL(ioremap_nocache); * * Must be freed with iounmap. */ -void __iomem *ioremap_wc(unsigned long phys_addr, unsigned long size) +void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size) { if (pat_enabled) return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC, diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 56fe7124fbe..16582960056 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -4,7 +4,7 @@ * Based on code by Ingo Molnar and Andi Kleen, copyrighted * as follows: * - * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. + * Copyright 2003-2009 Red Hat Inc. * All Rights Reserved. * Copyright 2005 Andi Kleen, SUSE Labs. * Copyright 2007 Jiri Kosina, SUSE Labs. diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 71a14f89f89..deb1c1ab786 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -20,6 +20,12 @@ #include <asm/acpi.h> #include <asm/k8.h> +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +# define DBG(x...) printk(KERN_DEBUG x) +#else +# define DBG(x...) +#endif + struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -33,6 +39,21 @@ int numa_off __initdata; static unsigned long __initdata nodemap_addr; static unsigned long __initdata nodemap_size; +DEFINE_PER_CPU(int, node_number) = 0; +EXPORT_PER_CPU_SYMBOL(node_number); + +/* + * Map cpu index to node index + */ +DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); + +/* + * Which logical CPUs are on which nodes + */ +cpumask_t *node_to_cpumask_map; +EXPORT_SYMBOL(node_to_cpumask_map); + /* * Given a shift value, try to populate memnodemap[] * Returns : @@ -640,3 +661,199 @@ void __init init_cpu_to_node(void) #endif +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: node_to_cpumask() is not valid until after this is done. + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) + */ +void __init setup_node_to_cpumask_map(void) +{ + unsigned int node, num = 0; + cpumask_t *map; + + /* setup nr_node_ids if not done yet */ + if (nr_node_ids == MAX_NUMNODES) { + for_each_node_mask(node, node_possible_map) + num = node; + nr_node_ids = num + 1; + } + + /* allocate the map */ + map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t)); + DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids); + + pr_debug("Node to cpumask map at %p for %d nodes\n", + map, nr_node_ids); + + /* node_to_cpumask() will now work */ + node_to_cpumask_map = map; +} + +void __cpuinit numa_set_node(int cpu, int node) +{ + int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); + + /* early setting, no percpu area yet */ + if (cpu_to_node_map) { + cpu_to_node_map[cpu] = node; + return; + } + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS + if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) { + printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu); + dump_stack(); + return; + } +#endif + per_cpu(x86_cpu_to_node_map, cpu) = node; + + if (node != NUMA_NO_NODE) + per_cpu(node_number, cpu) = node; +} + +void __cpuinit numa_clear_node(int cpu) +{ + numa_set_node(cpu, NUMA_NO_NODE); +} + +#ifndef CONFIG_DEBUG_PER_CPU_MAPS + +void __cpuinit numa_add_cpu(int cpu) +{ + cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); +} + +#else /* CONFIG_DEBUG_PER_CPU_MAPS */ + +/* + * --------- debug versions of the numa functions --------- + */ +static void __cpuinit numa_set_cpumask(int cpu, int enable) +{ + int node = early_cpu_to_node(cpu); + cpumask_t *mask; + char buf[64]; + + if (node_to_cpumask_map == NULL) { + printk(KERN_ERR "node_to_cpumask_map NULL\n"); + dump_stack(); + return; + } + + mask = &node_to_cpumask_map[node]; + if (enable) + cpu_set(cpu, *mask); + else + cpu_clear(cpu, *mask); + + cpulist_scnprintf(buf, sizeof(buf), mask); + printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", + enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf); +} + +void __cpuinit numa_add_cpu(int cpu) +{ + numa_set_cpumask(cpu, 1); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + numa_set_cpumask(cpu, 0); +} + +int cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) { + printk(KERN_WARNING + "cpu_to_node(%d): usage too early!\n", cpu); + dump_stack(); + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + } + return per_cpu(x86_cpu_to_node_map, cpu); +} +EXPORT_SYMBOL(cpu_to_node); + +/* + * Same function as cpu_to_node() but used if called before the + * per_cpu areas are setup. + */ +int early_cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + + if (!cpu_possible(cpu)) { + printk(KERN_WARNING + "early_cpu_to_node(%d): no per_cpu area!\n", cpu); + dump_stack(); + return NUMA_NO_NODE; + } + return per_cpu(x86_cpu_to_node_map, cpu); +} + + +/* empty cpumask */ +static const cpumask_t cpu_mask_none; + +/* + * Returns a pointer to the bitmask of CPUs on Node 'node'. + */ +const cpumask_t *cpumask_of_node(int node) +{ + if (node_to_cpumask_map == NULL) { + printk(KERN_WARNING + "cpumask_of_node(%d): no node_to_cpumask_map!\n", + node); + dump_stack(); + return (const cpumask_t *)&cpu_online_map; + } + if (node >= nr_node_ids) { + printk(KERN_WARNING + "cpumask_of_node(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return &cpu_mask_none; + } + return &node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(cpumask_of_node); + +/* + * Returns a bitmask of CPUs on Node 'node'. + * + * Side note: this function creates the returned cpumask on the stack + * so with a high NR_CPUS count, excessive stack space is used. The + * node_to_cpumask_ptr function should be used whenever possible. + */ +cpumask_t node_to_cpumask(int node) +{ + if (node_to_cpumask_map == NULL) { + printk(KERN_WARNING + "node_to_cpumask(%d): no node_to_cpumask_map!\n", node); + dump_stack(); + return cpu_online_map; + } + if (node >= nr_node_ids) { + printk(KERN_WARNING + "node_to_cpumask(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return cpu_mask_none; + } + return node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(node_to_cpumask); + +/* + * --------- end of debug versions of the numa functions --------- + */ + +#endif /* CONFIG_DEBUG_PER_CPU_MAPS */ diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 7b61036427d..9127e31c726 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -30,7 +30,7 @@ #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; -void __cpuinit pat_disable(char *reason) +void __cpuinit pat_disable(const char *reason) { pat_enabled = 0; printk(KERN_INFO "%s\n", reason); @@ -42,6 +42,11 @@ static int __init nopat(char *str) return 0; } early_param("nopat", nopat); +#else +static inline void pat_disable(const char *reason) +{ + (void)reason; +} #endif @@ -78,16 +83,20 @@ void pat_init(void) if (!pat_enabled) return; - /* Paranoia check. */ - if (!cpu_has_pat && boot_pat_state) { - /* - * If this happens we are on a secondary CPU, but - * switched to PAT on the boot CPU. We have no way to - * undo PAT. - */ - printk(KERN_ERR "PAT enabled, " - "but not supported by secondary CPU\n"); - BUG(); + if (!cpu_has_pat) { + if (!boot_pat_state) { + pat_disable("PAT not supported by CPU."); + return; + } else { + /* + * If this happens we are on a secondary CPU, but + * switched to PAT on the boot CPU. We have no way to + * undo PAT. + */ + printk(KERN_ERR "PAT enabled, " + "but not supported by secondary CPU\n"); + BUG(); + } } /* Set PWT to Write-Combining. All other bits stay the same */ diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 09737c8af07..15df1baee10 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -21,6 +21,7 @@ #include <asm/numa.h> #include <asm/e820.h> #include <asm/genapic.h> +#include <asm/uv/uv.h> int acpi_numa __initdata; diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/mm/tlb.c index f8be6f1d2e4..14c5af4d11e 100644 --- a/arch/x86/kernel/tlb_64.c +++ b/arch/x86/mm/tlb.c @@ -1,24 +1,20 @@ #include <linux/init.h> #include <linux/mm.h> -#include <linux/delay.h> #include <linux/spinlock.h> #include <linux/smp.h> -#include <linux/kernel_stat.h> -#include <linux/mc146818rtc.h> #include <linux/interrupt.h> +#include <linux/module.h> -#include <asm/mtrr.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> -#include <asm/proto.h> -#include <asm/apicdef.h> -#include <asm/idle.h> -#include <asm/uv/uv_hub.h> -#include <asm/uv/uv_bau.h> +#include <asm/apic.h> +#include <asm/uv/uv.h> -#include <mach_ipi.h> +DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) + = { &init_mm, 0, }; + +#include <asm/genapic.h> /* * Smarter SMP flushing macros. * c/o Linus Torvalds. @@ -33,7 +29,7 @@ * To avoid global state use 8 different call vectors. * Each CPU uses a specific vector to trigger flushes on other * CPUs. Depending on the received vector the target CPUs look into - * the right per cpu variable for the flush data. + * the right array slot for the flush data. * * With more than 8 CPUs they are hashed to the 8 available * vectors. The limited global vector space forces us to this right now. @@ -43,18 +39,18 @@ union smp_flush_state { struct { - cpumask_t flush_cpumask; struct mm_struct *flush_mm; unsigned long flush_va; spinlock_t tlbstate_lock; + DECLARE_BITMAP(flush_cpumask, NR_CPUS); }; - char pad[SMP_CACHE_BYTES]; -} ____cacheline_aligned; + char pad[CONFIG_X86_INTERNODE_CACHE_BYTES]; +} ____cacheline_internodealigned_in_smp; /* State is put into the per CPU data section, but padded to a full cache line because other CPUs can access it and we don't want false sharing in the per cpu data segment. */ -static DEFINE_PER_CPU(union smp_flush_state, flush_state); +static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS]; /* * We cannot call mmdrop() because we are in interrupt context, @@ -62,9 +58,9 @@ static DEFINE_PER_CPU(union smp_flush_state, flush_state); */ void leave_mm(int cpu) { - if (read_pda(mmu_state) == TLBSTATE_OK) + if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) BUG(); - cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask); + cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask); load_cr3(swapper_pg_dir); } EXPORT_SYMBOL_GPL(leave_mm); @@ -117,10 +113,20 @@ EXPORT_SYMBOL_GPL(leave_mm); * Interrupts are disabled. */ -asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs) +/* + * FIXME: use of asmlinkage is not consistent. On x86_64 it's noop + * but still used for documentation purpose but the usage is slightly + * inconsistent. On x86_32, asmlinkage is regparm(0) but interrupt + * entry calls in with the first parameter in %eax. Maybe define + * intrlinkage? + */ +#ifdef CONFIG_X86_64 +asmlinkage +#endif +void smp_invalidate_interrupt(struct pt_regs *regs) { - int cpu; - int sender; + unsigned int cpu; + unsigned int sender; union smp_flush_state *f; cpu = smp_processor_id(); @@ -129,9 +135,9 @@ asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs) * Use that to determine where the sender put the data. */ sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START; - f = &per_cpu(flush_state, sender); + f = &flush_state[sender]; - if (!cpu_isset(cpu, f->flush_cpumask)) + if (!cpumask_test_cpu(cpu, to_cpumask(f->flush_cpumask))) goto out; /* * This was a BUG() but until someone can quote me the @@ -142,8 +148,8 @@ asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs) * BUG(); */ - if (f->flush_mm == read_pda(active_mm)) { - if (read_pda(mmu_state) == TLBSTATE_OK) { + if (f->flush_mm == percpu_read(cpu_tlbstate.active_mm)) { + if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { if (f->flush_va == TLB_FLUSH_ALL) local_flush_tlb(); else @@ -153,23 +159,21 @@ asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs) } out: ack_APIC_irq(); - cpu_clear(cpu, f->flush_cpumask); + smp_mb__before_clear_bit(); + cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask)); + smp_mb__after_clear_bit(); inc_irq_stat(irq_tlb_count); } -void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, - unsigned long va) +static void flush_tlb_others_ipi(const struct cpumask *cpumask, + struct mm_struct *mm, unsigned long va) { - int sender; + unsigned int sender; union smp_flush_state *f; - cpumask_t cpumask = *cpumaskp; - - if (is_uv_system() && uv_flush_tlb_others(&cpumask, mm, va)) - return; /* Caller has disabled preemption */ sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS; - f = &per_cpu(flush_state, sender); + f = &flush_state[sender]; /* * Could avoid this lock when @@ -180,7 +184,8 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, f->flush_mm = mm; f->flush_va = va; - cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask); + cpumask_andnot(to_cpumask(f->flush_cpumask), + cpumask, cpumask_of(smp_processor_id())); /* * Make the above memory operations globally visible before @@ -191,9 +196,10 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, * We have to send the IPI only to * CPUs affected. */ - send_IPI_mask(&cpumask, INVALIDATE_TLB_VECTOR_START + sender); + apic->send_IPI_mask(to_cpumask(f->flush_cpumask), + INVALIDATE_TLB_VECTOR_START + sender); - while (!cpus_empty(f->flush_cpumask)) + while (!cpumask_empty(to_cpumask(f->flush_cpumask))) cpu_relax(); f->flush_mm = NULL; @@ -201,12 +207,28 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, spin_unlock(&f->tlbstate_lock); } +void native_flush_tlb_others(const struct cpumask *cpumask, + struct mm_struct *mm, unsigned long va) +{ + if (is_uv_system()) { + unsigned int cpu; + + cpu = get_cpu(); + cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu); + if (cpumask) + flush_tlb_others_ipi(cpumask, mm, va); + put_cpu(); + return; + } + flush_tlb_others_ipi(cpumask, mm, va); +} + static int __cpuinit init_smp_flush(void) { int i; - for_each_possible_cpu(i) - spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock); + for (i = 0; i < ARRAY_SIZE(flush_state); i++) + spin_lock_init(&flush_state[i].tlbstate_lock); return 0; } @@ -215,25 +237,18 @@ core_initcall(init_smp_flush); void flush_tlb_current_task(void) { struct mm_struct *mm = current->mm; - cpumask_t cpu_mask; preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); local_flush_tlb(); - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL); + if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids) + flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL); preempt_enable(); } void flush_tlb_mm(struct mm_struct *mm) { - cpumask_t cpu_mask; - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); if (current->active_mm == mm) { if (current->mm) @@ -241,8 +256,8 @@ void flush_tlb_mm(struct mm_struct *mm) else leave_mm(smp_processor_id()); } - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, TLB_FLUSH_ALL); + if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids) + flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL); preempt_enable(); } @@ -250,11 +265,8 @@ void flush_tlb_mm(struct mm_struct *mm) void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) { struct mm_struct *mm = vma->vm_mm; - cpumask_t cpu_mask; preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); if (current->active_mm == mm) { if (current->mm) @@ -263,8 +275,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) leave_mm(smp_processor_id()); } - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, va); + if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids) + flush_tlb_others(&mm->cpu_vm_mask, mm, va); preempt_enable(); } @@ -274,7 +286,7 @@ static void do_flush_tlb_all(void *info) unsigned long cpu = smp_processor_id(); __flush_tlb_all(); - if (read_pda(mmu_state) == TLBSTATE_LAZY) + if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) leave_mm(cpu); } diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c index 2089354968a..5601e829c38 100644 --- a/arch/x86/pci/numaq_32.c +++ b/arch/x86/pci/numaq_32.c @@ -5,7 +5,7 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/nodemask.h> -#include <mach_apic.h> +#include <asm/genapic.h> #include <asm/mpspec.h> #include <asm/pci_x86.h> @@ -18,10 +18,6 @@ #define QUADLOCAL2BUS(quad,local) (quad_local_to_mp_bus_id[quad][local]) -/* Where the IO area was mapped on multiquad, always 0 otherwise */ -void *xquad_portio; -EXPORT_SYMBOL(xquad_portio); - #define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port) #define PCI_CONF1_MQ_ADDRESS(bus, devfn, reg) \ diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index b82cae970df..1c975cc9839 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -7,7 +7,7 @@ #include <linux/module.h> #include <linux/uaccess.h> #include <asm/pci_x86.h> -#include <asm/mach-default/pci-functions.h> +#include <asm/pci-functions.h> /* BIOS32 signature: "_32_" */ #define BIOS32_SIGNATURE (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24)) diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 4d6ef0a336d..16a9020c8f1 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -38,7 +38,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ - $(filter -g%,$(KBUILD_CFLAGS)) + $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) $(vobjs): KBUILD_CFLAGS += $(CFL) diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 6dcefba7836..3b767d03fd6 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -6,7 +6,8 @@ CFLAGS_REMOVE_irq.o = -pg endif obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ - time.o xen-asm_$(BITS).o grant-table.o suspend.o + time.o xen-asm.o xen-asm_$(BITS).o \ + grant-table.o suspend.o obj-$(CONFIG_SMP) += smp.o spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
\ No newline at end of file diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bea215230b2..95ff6a0e942 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -61,40 +61,13 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); enum xen_domain_type xen_domain_type = XEN_NATIVE; EXPORT_SYMBOL_GPL(xen_domain_type); -/* - * Identity map, in addition to plain kernel map. This needs to be - * large enough to allocate page table pages to allocate the rest. - * Each page can map 2MB. - */ -static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss; - -#ifdef CONFIG_X86_64 -/* l3 pud for userspace vsyscall mapping */ -static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; -#endif /* CONFIG_X86_64 */ - -/* - * Note about cr3 (pagetable base) values: - * - * xen_cr3 contains the current logical cr3 value; it contains the - * last set cr3. This may not be the current effective cr3, because - * its update may be being lazily deferred. However, a vcpu looking - * at its own cr3 can use this value knowing that it everything will - * be self-consistent. - * - * xen_current_cr3 contains the actual vcpu cr3; it is set once the - * hypercall to set the vcpu cr3 is complete (so it may be a little - * out of date, but it will never be set early). If one vcpu is - * looking at another vcpu's cr3 value, it should use this variable. - */ -DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */ -DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ - struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); struct shared_info xen_dummy_shared_info; +void *xen_initial_gdt; + /* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. @@ -114,14 +87,7 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; * * 0: not available, 1: available */ -static int have_vcpu_info_placement = -#ifdef CONFIG_X86_32 - 1 -#else - 0 -#endif - ; - +static int have_vcpu_info_placement = 1; static void xen_vcpu_setup(int cpu) { @@ -237,7 +203,7 @@ static unsigned long xen_get_debugreg(int reg) return HYPERVISOR_get_debugreg(reg); } -static void xen_leave_lazy(void) +void xen_leave_lazy(void) { paravirt_leave_lazy(paravirt_get_lazy_mode()); xen_mc_flush(); @@ -357,13 +323,14 @@ static void load_TLS_descriptor(struct thread_struct *t, static void xen_load_tls(struct thread_struct *t, unsigned int cpu) { /* - * XXX sleazy hack: If we're being called in a lazy-cpu zone, - * it means we're in a context switch, and %gs has just been - * saved. This means we can zero it out to prevent faults on - * exit from the hypervisor if the next process has no %gs. - * Either way, it has been saved, and the new value will get - * loaded properly. This will go away as soon as Xen has been - * modified to not save/restore %gs for normal hypercalls. + * XXX sleazy hack: If we're being called in a lazy-cpu zone + * and lazy gs handling is enabled, it means we're in a + * context switch, and %gs has just been saved. This means we + * can zero it out to prevent faults on exit from the + * hypervisor if the next process has no %gs. Either way, it + * has been saved, and the new value will get loaded properly. + * This will go away as soon as Xen has been modified to not + * save/restore %gs for normal hypercalls. * * On x86_64, this hack is not used for %gs, because gs points * to KERNEL_GS_BASE (and uses it for PDA references), so we @@ -375,7 +342,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu) */ if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) { #ifdef CONFIG_X86_32 - loadsegment(gs, 0); + lazy_load_gs(0); #else loadsegment(fs, 0); #endif @@ -598,83 +565,6 @@ static struct apic_ops xen_basic_apic_ops = { #endif -static void xen_flush_tlb(void) -{ - struct mmuext_op *op; - struct multicall_space mcs; - - preempt_disable(); - - mcs = xen_mc_entry(sizeof(*op)); - - op = mcs.args; - op->cmd = MMUEXT_TLB_FLUSH_LOCAL; - MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - - xen_mc_issue(PARAVIRT_LAZY_MMU); - - preempt_enable(); -} - -static void xen_flush_tlb_single(unsigned long addr) -{ - struct mmuext_op *op; - struct multicall_space mcs; - - preempt_disable(); - - mcs = xen_mc_entry(sizeof(*op)); - op = mcs.args; - op->cmd = MMUEXT_INVLPG_LOCAL; - op->arg1.linear_addr = addr & PAGE_MASK; - MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - - xen_mc_issue(PARAVIRT_LAZY_MMU); - - preempt_enable(); -} - -static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm, - unsigned long va) -{ - struct { - struct mmuext_op op; - cpumask_t mask; - } *args; - cpumask_t cpumask = *cpus; - struct multicall_space mcs; - - /* - * A couple of (to be removed) sanity checks: - * - * - current CPU must not be in mask - * - mask must exist :) - */ - BUG_ON(cpus_empty(cpumask)); - BUG_ON(cpu_isset(smp_processor_id(), cpumask)); - BUG_ON(!mm); - - /* If a CPU which we ran on has gone down, OK. */ - cpus_and(cpumask, cpumask, cpu_online_map); - if (cpus_empty(cpumask)) - return; - - mcs = xen_mc_entry(sizeof(*args)); - args = mcs.args; - args->mask = cpumask; - args->op.arg2.vcpumask = &args->mask; - - if (va == TLB_FLUSH_ALL) { - args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; - } else { - args->op.cmd = MMUEXT_INVLPG_MULTI; - args->op.arg1.linear_addr = va; - } - - MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); - - xen_mc_issue(PARAVIRT_LAZY_MMU); -} static void xen_clts(void) { @@ -700,21 +590,6 @@ static void xen_write_cr0(unsigned long cr0) xen_mc_issue(PARAVIRT_LAZY_CPU); } -static void xen_write_cr2(unsigned long cr2) -{ - x86_read_percpu(xen_vcpu)->arch.cr2 = cr2; -} - -static unsigned long xen_read_cr2(void) -{ - return x86_read_percpu(xen_vcpu)->arch.cr2; -} - -static unsigned long xen_read_cr2_direct(void) -{ - return x86_read_percpu(xen_vcpu_info.arch.cr2); -} - static void xen_write_cr4(unsigned long cr4) { cr4 &= ~X86_CR4_PGE; @@ -723,71 +598,6 @@ static void xen_write_cr4(unsigned long cr4) native_write_cr4(cr4); } -static unsigned long xen_read_cr3(void) -{ - return x86_read_percpu(xen_cr3); -} - -static void set_current_cr3(void *v) -{ - x86_write_percpu(xen_current_cr3, (unsigned long)v); -} - -static void __xen_write_cr3(bool kernel, unsigned long cr3) -{ - struct mmuext_op *op; - struct multicall_space mcs; - unsigned long mfn; - - if (cr3) - mfn = pfn_to_mfn(PFN_DOWN(cr3)); - else - mfn = 0; - - WARN_ON(mfn == 0 && kernel); - - mcs = __xen_mc_entry(sizeof(*op)); - - op = mcs.args; - op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR; - op->arg1.mfn = mfn; - - MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - - if (kernel) { - x86_write_percpu(xen_cr3, cr3); - - /* Update xen_current_cr3 once the batch has actually - been submitted. */ - xen_mc_callback(set_current_cr3, (void *)cr3); - } -} - -static void xen_write_cr3(unsigned long cr3) -{ - BUG_ON(preemptible()); - - xen_mc_batch(); /* disables interrupts */ - - /* Update while interrupts are disabled, so its atomic with - respect to ipis */ - x86_write_percpu(xen_cr3, cr3); - - __xen_write_cr3(true, cr3); - -#ifdef CONFIG_X86_64 - { - pgd_t *user_pgd = xen_get_user_pgd(__va(cr3)); - if (user_pgd) - __xen_write_cr3(false, __pa(user_pgd)); - else - __xen_write_cr3(false, 0); - } -#endif - - xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ -} - static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; @@ -829,185 +639,6 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) return ret; } -/* Early in boot, while setting up the initial pagetable, assume - everything is pinned. */ -static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) -{ -#ifdef CONFIG_FLATMEM - BUG_ON(mem_map); /* should only be used early */ -#endif - make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); -} - -/* Early release_pte assumes that all pts are pinned, since there's - only init_mm and anything attached to that is pinned. */ -static void xen_release_pte_init(unsigned long pfn) -{ - make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); -} - -static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) -{ - struct mmuext_op op; - op.cmd = cmd; - op.arg1.mfn = pfn_to_mfn(pfn); - if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) - BUG(); -} - -/* This needs to make sure the new pte page is pinned iff its being - attached to a pinned pagetable. */ -static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level) -{ - struct page *page = pfn_to_page(pfn); - - if (PagePinned(virt_to_page(mm->pgd))) { - SetPagePinned(page); - - vm_unmap_aliases(); - if (!PageHighMem(page)) { - make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn))); - if (level == PT_PTE && USE_SPLIT_PTLOCKS) - pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); - } else { - /* make sure there are no stray mappings of - this page */ - kmap_flush_unused(); - } - } -} - -static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn) -{ - xen_alloc_ptpage(mm, pfn, PT_PTE); -} - -static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn) -{ - xen_alloc_ptpage(mm, pfn, PT_PMD); -} - -static int xen_pgd_alloc(struct mm_struct *mm) -{ - pgd_t *pgd = mm->pgd; - int ret = 0; - - BUG_ON(PagePinned(virt_to_page(pgd))); - -#ifdef CONFIG_X86_64 - { - struct page *page = virt_to_page(pgd); - pgd_t *user_pgd; - - BUG_ON(page->private != 0); - - ret = -ENOMEM; - - user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - page->private = (unsigned long)user_pgd; - - if (user_pgd != NULL) { - user_pgd[pgd_index(VSYSCALL_START)] = - __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); - ret = 0; - } - - BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); - } -#endif - - return ret; -} - -static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ -#ifdef CONFIG_X86_64 - pgd_t *user_pgd = xen_get_user_pgd(pgd); - - if (user_pgd) - free_page((unsigned long)user_pgd); -#endif -} - -/* This should never happen until we're OK to use struct page */ -static void xen_release_ptpage(unsigned long pfn, unsigned level) -{ - struct page *page = pfn_to_page(pfn); - - if (PagePinned(page)) { - if (!PageHighMem(page)) { - if (level == PT_PTE && USE_SPLIT_PTLOCKS) - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); - make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); - } - ClearPagePinned(page); - } -} - -static void xen_release_pte(unsigned long pfn) -{ - xen_release_ptpage(pfn, PT_PTE); -} - -static void xen_release_pmd(unsigned long pfn) -{ - xen_release_ptpage(pfn, PT_PMD); -} - -#if PAGETABLE_LEVELS == 4 -static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) -{ - xen_alloc_ptpage(mm, pfn, PT_PUD); -} - -static void xen_release_pud(unsigned long pfn) -{ - xen_release_ptpage(pfn, PT_PUD); -} -#endif - -#ifdef CONFIG_HIGHPTE -static void *xen_kmap_atomic_pte(struct page *page, enum km_type type) -{ - pgprot_t prot = PAGE_KERNEL; - - if (PagePinned(page)) - prot = PAGE_KERNEL_RO; - - if (0 && PageHighMem(page)) - printk("mapping highpte %lx type %d prot %s\n", - page_to_pfn(page), type, - (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ"); - - return kmap_atomic_prot(page, type, prot); -} -#endif - -#ifdef CONFIG_X86_32 -static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte) -{ - /* If there's an existing pte, then don't allow _PAGE_RW to be set */ - if (pte_val_ma(*ptep) & _PAGE_PRESENT) - pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & - pte_val_ma(pte)); - - return pte; -} - -/* Init-time set_pte while constructing initial pagetables, which - doesn't allow RO pagetable pages to be remapped RW */ -static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) -{ - pte = mask_rw_pte(ptep, pte); - - xen_set_pte(ptep, pte); -} -#endif - -static __init void xen_pagetable_setup_start(pgd_t *base) -{ -} - void xen_setup_shared_info(void) { if (!xen_feature(XENFEAT_auto_translated_physmap)) { @@ -1028,37 +659,6 @@ void xen_setup_shared_info(void) xen_setup_mfn_list_list(); } -static __init void xen_pagetable_setup_done(pgd_t *base) -{ - xen_setup_shared_info(); -} - -static __init void xen_post_allocator_init(void) -{ - pv_mmu_ops.set_pte = xen_set_pte; - pv_mmu_ops.set_pmd = xen_set_pmd; - pv_mmu_ops.set_pud = xen_set_pud; -#if PAGETABLE_LEVELS == 4 - pv_mmu_ops.set_pgd = xen_set_pgd; -#endif - - /* This will work as long as patching hasn't happened yet - (which it hasn't) */ - pv_mmu_ops.alloc_pte = xen_alloc_pte; - pv_mmu_ops.alloc_pmd = xen_alloc_pmd; - pv_mmu_ops.release_pte = xen_release_pte; - pv_mmu_ops.release_pmd = xen_release_pmd; -#if PAGETABLE_LEVELS == 4 - pv_mmu_ops.alloc_pud = xen_alloc_pud; - pv_mmu_ops.release_pud = xen_release_pud; -#endif - -#ifdef CONFIG_X86_64 - SetPagePinned(virt_to_page(level3_user_vsyscall)); -#endif - xen_mark_init_mm_pinned(); -} - /* This is called once we have the cpu_possible_map */ void xen_setup_vcpu_info_placement(void) { @@ -1072,10 +672,10 @@ void xen_setup_vcpu_info_placement(void) if (have_vcpu_info_placement) { printk(KERN_INFO "Xen: using vcpu_info placement\n"); - pv_irq_ops.save_fl = xen_save_fl_direct; - pv_irq_ops.restore_fl = xen_restore_fl_direct; - pv_irq_ops.irq_disable = xen_irq_disable_direct; - pv_irq_ops.irq_enable = xen_irq_enable_direct; + pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); + pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct); + pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); + pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct); pv_mmu_ops.read_cr2 = xen_read_cr2_direct; } } @@ -1133,49 +733,6 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf, return ret; } -static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot) -{ - pte_t pte; - - phys >>= PAGE_SHIFT; - - switch (idx) { - case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: -#ifdef CONFIG_X86_F00F_BUG - case FIX_F00F_IDT: -#endif -#ifdef CONFIG_X86_32 - case FIX_WP_TEST: - case FIX_VDSO: -# ifdef CONFIG_HIGHMEM - case FIX_KMAP_BEGIN ... FIX_KMAP_END: -# endif -#else - case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE: -#endif -#ifdef CONFIG_X86_LOCAL_APIC - case FIX_APIC_BASE: /* maps dummy local APIC */ -#endif - pte = pfn_pte(phys, prot); - break; - - default: - pte = mfn_pte(phys, prot); - break; - } - - __native_set_fixmap(idx, pte); - -#ifdef CONFIG_X86_64 - /* Replicate changes to map the vsyscall page into the user - pagetable vsyscall mapping. */ - if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) { - unsigned long vaddr = __fix_to_virt(idx); - set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); - } -#endif -} - static const struct pv_info xen_info __initdata = { .paravirt_enabled = 1, .shared_kernel_pmd = 0, @@ -1271,87 +828,6 @@ static const struct pv_apic_ops xen_apic_ops __initdata = { #endif }; -static const struct pv_mmu_ops xen_mmu_ops __initdata = { - .pagetable_setup_start = xen_pagetable_setup_start, - .pagetable_setup_done = xen_pagetable_setup_done, - - .read_cr2 = xen_read_cr2, - .write_cr2 = xen_write_cr2, - - .read_cr3 = xen_read_cr3, - .write_cr3 = xen_write_cr3, - - .flush_tlb_user = xen_flush_tlb, - .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_single = xen_flush_tlb_single, - .flush_tlb_others = xen_flush_tlb_others, - - .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, - - .pgd_alloc = xen_pgd_alloc, - .pgd_free = xen_pgd_free, - - .alloc_pte = xen_alloc_pte_init, - .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pte_init, - .alloc_pmd_clone = paravirt_nop, - .release_pmd = xen_release_pte_init, - -#ifdef CONFIG_HIGHPTE - .kmap_atomic_pte = xen_kmap_atomic_pte, -#endif - -#ifdef CONFIG_X86_64 - .set_pte = xen_set_pte, -#else - .set_pte = xen_set_pte_init, -#endif - .set_pte_at = xen_set_pte_at, - .set_pmd = xen_set_pmd_hyper, - - .ptep_modify_prot_start = __ptep_modify_prot_start, - .ptep_modify_prot_commit = __ptep_modify_prot_commit, - - .pte_val = xen_pte_val, - .pte_flags = native_pte_flags, - .pgd_val = xen_pgd_val, - - .make_pte = xen_make_pte, - .make_pgd = xen_make_pgd, - -#ifdef CONFIG_X86_PAE - .set_pte_atomic = xen_set_pte_atomic, - .set_pte_present = xen_set_pte_at, - .pte_clear = xen_pte_clear, - .pmd_clear = xen_pmd_clear, -#endif /* CONFIG_X86_PAE */ - .set_pud = xen_set_pud_hyper, - - .make_pmd = xen_make_pmd, - .pmd_val = xen_pmd_val, - -#if PAGETABLE_LEVELS == 4 - .pud_val = xen_pud_val, - .make_pud = xen_make_pud, - .set_pgd = xen_set_pgd_hyper, - - .alloc_pud = xen_alloc_pte_init, - .release_pud = xen_release_pte_init, -#endif /* PAGETABLE_LEVELS == 4 */ - - .activate_mm = xen_activate_mm, - .dup_mmap = xen_dup_mmap, - .exit_mmap = xen_exit_mmap, - - .lazy_mode = { - .enter = paravirt_enter_lazy_mmu, - .leave = xen_leave_lazy, - }, - - .set_fixmap = xen_set_fixmap, -}; - static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; @@ -1394,223 +870,6 @@ static const struct machine_ops __initdata xen_machine_ops = { }; -static void __init xen_reserve_top(void) -{ -#ifdef CONFIG_X86_32 - unsigned long top = HYPERVISOR_VIRT_START; - struct xen_platform_parameters pp; - - if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0) - top = pp.virt_start; - - reserve_top_address(-top); -#endif /* CONFIG_X86_32 */ -} - -/* - * Like __va(), but returns address in the kernel mapping (which is - * all we have until the physical memory mapping has been set up. - */ -static void *__ka(phys_addr_t paddr) -{ -#ifdef CONFIG_X86_64 - return (void *)(paddr + __START_KERNEL_map); -#else - return __va(paddr); -#endif -} - -/* Convert a machine address to physical address */ -static unsigned long m2p(phys_addr_t maddr) -{ - phys_addr_t paddr; - - maddr &= PTE_PFN_MASK; - paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT; - - return paddr; -} - -/* Convert a machine address to kernel virtual */ -static void *m2v(phys_addr_t maddr) -{ - return __ka(m2p(maddr)); -} - -static void set_page_prot(void *addr, pgprot_t prot) -{ - unsigned long pfn = __pa(addr) >> PAGE_SHIFT; - pte_t pte = pfn_pte(pfn, prot); - - if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0)) - BUG(); -} - -static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) -{ - unsigned pmdidx, pteidx; - unsigned ident_pte; - unsigned long pfn; - - ident_pte = 0; - pfn = 0; - for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) { - pte_t *pte_page; - - /* Reuse or allocate a page of ptes */ - if (pmd_present(pmd[pmdidx])) - pte_page = m2v(pmd[pmdidx].pmd); - else { - /* Check for free pte pages */ - if (ident_pte == ARRAY_SIZE(level1_ident_pgt)) - break; - - pte_page = &level1_ident_pgt[ident_pte]; - ident_pte += PTRS_PER_PTE; - - pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE); - } - - /* Install mappings */ - for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { - pte_t pte; - - if (pfn > max_pfn_mapped) - max_pfn_mapped = pfn; - - if (!pte_none(pte_page[pteidx])) - continue; - - pte = pfn_pte(pfn, PAGE_KERNEL_EXEC); - pte_page[pteidx] = pte; - } - } - - for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE) - set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO); - - set_page_prot(pmd, PAGE_KERNEL_RO); -} - -#ifdef CONFIG_X86_64 -static void convert_pfn_mfn(void *v) -{ - pte_t *pte = v; - int i; - - /* All levels are converted the same way, so just treat them - as ptes. */ - for (i = 0; i < PTRS_PER_PTE; i++) - pte[i] = xen_make_pte(pte[i].pte); -} - -/* - * Set up the inital kernel pagetable. - * - * We can construct this by grafting the Xen provided pagetable into - * head_64.S's preconstructed pagetables. We copy the Xen L2's into - * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This - * means that only the kernel has a physical mapping to start with - - * but that's enough to get __va working. We need to fill in the rest - * of the physical mapping once some sort of allocator has been set - * up. - */ -static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, - unsigned long max_pfn) -{ - pud_t *l3; - pmd_t *l2; - - /* Zap identity mapping */ - init_level4_pgt[0] = __pgd(0); - - /* Pre-constructed entries are in pfn, so convert to mfn */ - convert_pfn_mfn(init_level4_pgt); - convert_pfn_mfn(level3_ident_pgt); - convert_pfn_mfn(level3_kernel_pgt); - - l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); - l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud); - - memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - - l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd); - l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud); - memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); - - /* Set up identity map */ - xen_map_identity_early(level2_ident_pgt, max_pfn); - - /* Make pagetable pieces RO */ - set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); - set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); - - /* Pin down new L4 */ - pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, - PFN_DOWN(__pa_symbol(init_level4_pgt))); - - /* Unpin Xen-provided one */ - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - - /* Switch over */ - pgd = init_level4_pgt; - - /* - * At this stage there can be no user pgd, and no page - * structure to attach it to, so make sure we just set kernel - * pgd. - */ - xen_mc_batch(); - __xen_write_cr3(true, __pa(pgd)); - xen_mc_issue(PARAVIRT_LAZY_CPU); - - reserve_early(__pa(xen_start_info->pt_base), - __pa(xen_start_info->pt_base + - xen_start_info->nr_pt_frames * PAGE_SIZE), - "XEN PAGETABLES"); - - return pgd; -} -#else /* !CONFIG_X86_64 */ -static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss; - -static __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, - unsigned long max_pfn) -{ - pmd_t *kernel_pmd; - - init_pg_tables_start = __pa(pgd); - init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE; - max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024); - - kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); - memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); - - xen_map_identity_early(level2_kernel_pgt, max_pfn); - - memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD); - set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY], - __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT)); - - set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); - set_page_prot(empty_zero_page, PAGE_KERNEL_RO); - - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - - xen_write_cr3(__pa(swapper_pg_dir)); - - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); - - return swapper_pg_dir; -} -#endif /* CONFIG_X86_64 */ - /* First C function to be called on Xen boot */ asmlinkage void __init xen_start_kernel(void) { @@ -1650,10 +909,18 @@ asmlinkage void __init xen_start_kernel(void) machine_ops = xen_machine_ops; #ifdef CONFIG_X86_64 - /* Disable until direct per-cpu data access. */ - have_vcpu_info_placement = 0; - x86_64_init_pda(); + /* + * Setup percpu state. We only need to do this for 64-bit + * because 32-bit already has %fs set properly. + */ + load_percpu_segment(0); #endif + /* + * The only reliable way to retain the initial address of the + * percpu gdt_page is to remember it here, so we can go and + * mark it RW later, when the initial percpu area is freed. + */ + xen_initial_gdt = &per_cpu(gdt_page, 0); xen_smp_init(); diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index bb042608c60..cfd17799bd6 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -19,27 +19,12 @@ void xen_force_evtchn_callback(void) (void)HYPERVISOR_xen_version(0, NULL); } -static void __init __xen_init_IRQ(void) -{ - int i; - - /* Create identity vector->irq map */ - for(i = 0; i < NR_VECTORS; i++) { - int cpu; - - for_each_possible_cpu(cpu) - per_cpu(vector_irq, cpu)[i] = i; - } - - xen_init_IRQ(); -} - static unsigned long xen_save_fl(void) { struct vcpu_info *vcpu; unsigned long flags; - vcpu = x86_read_percpu(xen_vcpu); + vcpu = percpu_read(xen_vcpu); /* flag has opposite sense of mask */ flags = !vcpu->evtchn_upcall_mask; @@ -50,6 +35,7 @@ static unsigned long xen_save_fl(void) */ return (-flags) & X86_EFLAGS_IF; } +PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl); static void xen_restore_fl(unsigned long flags) { @@ -62,7 +48,7 @@ static void xen_restore_fl(unsigned long flags) make sure we're don't switch CPUs between getting the vcpu pointer and updating the mask. */ preempt_disable(); - vcpu = x86_read_percpu(xen_vcpu); + vcpu = percpu_read(xen_vcpu); vcpu->evtchn_upcall_mask = flags; preempt_enable_no_resched(); @@ -76,6 +62,7 @@ static void xen_restore_fl(unsigned long flags) xen_force_evtchn_callback(); } } +PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl); static void xen_irq_disable(void) { @@ -83,9 +70,10 @@ static void xen_irq_disable(void) make sure we're don't switch CPUs between getting the vcpu pointer and updating the mask. */ preempt_disable(); - x86_read_percpu(xen_vcpu)->evtchn_upcall_mask = 1; + percpu_read(xen_vcpu)->evtchn_upcall_mask = 1; preempt_enable_no_resched(); } +PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable); static void xen_irq_enable(void) { @@ -96,7 +84,7 @@ static void xen_irq_enable(void) the caller is confused and is trying to re-enable interrupts on an indeterminate processor. */ - vcpu = x86_read_percpu(xen_vcpu); + vcpu = percpu_read(xen_vcpu); vcpu->evtchn_upcall_mask = 0; /* Doesn't matter if we get preempted here, because any @@ -106,6 +94,7 @@ static void xen_irq_enable(void) if (unlikely(vcpu->evtchn_upcall_pending)) xen_force_evtchn_callback(); } +PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable); static void xen_safe_halt(void) { @@ -123,11 +112,13 @@ static void xen_halt(void) } static const struct pv_irq_ops xen_irq_ops __initdata = { - .init_IRQ = __xen_init_IRQ, - .save_fl = xen_save_fl, - .restore_fl = xen_restore_fl, - .irq_disable = xen_irq_disable, - .irq_enable = xen_irq_enable, + .init_IRQ = xen_init_IRQ, + + .save_fl = PV_CALLEE_SAVE(xen_save_fl), + .restore_fl = PV_CALLEE_SAVE(xen_restore_fl), + .irq_disable = PV_CALLEE_SAVE(xen_irq_disable), + .irq_enable = PV_CALLEE_SAVE(xen_irq_enable), + .safe_halt = xen_safe_halt, .halt = xen_halt, #ifdef CONFIG_X86_64 diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 503c240e26c..d2e8ed1aff3 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -47,6 +47,7 @@ #include <asm/tlbflush.h> #include <asm/fixmap.h> #include <asm/mmu_context.h> +#include <asm/setup.h> #include <asm/paravirt.h> #include <asm/linkage.h> @@ -55,6 +56,8 @@ #include <xen/page.h> #include <xen/interface/xen.h> +#include <xen/interface/version.h> +#include <xen/hvc-console.h> #include "multicalls.h" #include "mmu.h" @@ -114,6 +117,37 @@ static inline void check_zero(void) #endif /* CONFIG_XEN_DEBUG_FS */ + +/* + * Identity map, in addition to plain kernel map. This needs to be + * large enough to allocate page table pages to allocate the rest. + * Each page can map 2MB. + */ +static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss; + +#ifdef CONFIG_X86_64 +/* l3 pud for userspace vsyscall mapping */ +static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; +#endif /* CONFIG_X86_64 */ + +/* + * Note about cr3 (pagetable base) values: + * + * xen_cr3 contains the current logical cr3 value; it contains the + * last set cr3. This may not be the current effective cr3, because + * its update may be being lazily deferred. However, a vcpu looking + * at its own cr3 can use this value knowing that it everything will + * be self-consistent. + * + * xen_current_cr3 contains the actual vcpu cr3; it is set once the + * hypercall to set the vcpu cr3 is complete (so it may be a little + * out of date, but it will never be set early). If one vcpu is + * looking at another vcpu's cr3 value, it should use this variable. + */ +DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */ +DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ + + /* * Just beyond the highest usermode address. STACK_TOP_MAX has a * redzone above it, so round it up to a PGD boundary. @@ -458,28 +492,33 @@ pteval_t xen_pte_val(pte_t pte) { return pte_mfn_to_pfn(pte.pte); } +PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val); pgdval_t xen_pgd_val(pgd_t pgd) { return pte_mfn_to_pfn(pgd.pgd); } +PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val); pte_t xen_make_pte(pteval_t pte) { pte = pte_pfn_to_mfn(pte); return native_make_pte(pte); } +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); return native_make_pgd(pgd); } +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd); pmdval_t xen_pmd_val(pmd_t pmd) { return pte_mfn_to_pfn(pmd.pmd); } +PV_CALLEE_SAVE_REGS_THUNK(xen_pmd_val); void xen_set_pud_hyper(pud_t *ptr, pud_t val) { @@ -556,12 +595,14 @@ pmd_t xen_make_pmd(pmdval_t pmd) pmd = pte_pfn_to_mfn(pmd); return native_make_pmd(pmd); } +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd); #if PAGETABLE_LEVELS == 4 pudval_t xen_pud_val(pud_t pud) { return pte_mfn_to_pfn(pud.pud); } +PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val); pud_t xen_make_pud(pudval_t pud) { @@ -569,6 +610,7 @@ pud_t xen_make_pud(pudval_t pud) return native_make_pud(pud); } +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pud); pgd_t *xen_get_user_pgd(pgd_t *pgd) { @@ -1063,18 +1105,14 @@ static void drop_other_mm_ref(void *info) struct mm_struct *mm = info; struct mm_struct *active_mm; -#ifdef CONFIG_X86_64 - active_mm = read_pda(active_mm); -#else - active_mm = __get_cpu_var(cpu_tlbstate).active_mm; -#endif + active_mm = percpu_read(cpu_tlbstate.active_mm); if (active_mm == mm) leave_mm(smp_processor_id()); /* If this cpu still has a stale cr3 reference, then make sure it has been flushed. */ - if (x86_read_percpu(xen_current_cr3) == __pa(mm->pgd)) { + if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) { load_cr3(swapper_pg_dir); arch_flush_lazy_cpu_mode(); } @@ -1156,6 +1194,709 @@ void xen_exit_mmap(struct mm_struct *mm) spin_unlock(&mm->page_table_lock); } +static __init void xen_pagetable_setup_start(pgd_t *base) +{ +} + +static __init void xen_pagetable_setup_done(pgd_t *base) +{ + xen_setup_shared_info(); +} + +static void xen_write_cr2(unsigned long cr2) +{ + percpu_read(xen_vcpu)->arch.cr2 = cr2; +} + +static unsigned long xen_read_cr2(void) +{ + return percpu_read(xen_vcpu)->arch.cr2; +} + +unsigned long xen_read_cr2_direct(void) +{ + return percpu_read(xen_vcpu_info.arch.cr2); +} + +static void xen_flush_tlb(void) +{ + struct mmuext_op *op; + struct multicall_space mcs; + + preempt_disable(); + + mcs = xen_mc_entry(sizeof(*op)); + + op = mcs.args; + op->cmd = MMUEXT_TLB_FLUSH_LOCAL; + MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); + + xen_mc_issue(PARAVIRT_LAZY_MMU); + + preempt_enable(); +} + +static void xen_flush_tlb_single(unsigned long addr) +{ + struct mmuext_op *op; + struct multicall_space mcs; + + preempt_disable(); + + mcs = xen_mc_entry(sizeof(*op)); + op = mcs.args; + op->cmd = MMUEXT_INVLPG_LOCAL; + op->arg1.linear_addr = addr & PAGE_MASK; + MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); + + xen_mc_issue(PARAVIRT_LAZY_MMU); + + preempt_enable(); +} + +static void xen_flush_tlb_others(const struct cpumask *cpus, + struct mm_struct *mm, unsigned long va) +{ + struct { + struct mmuext_op op; + DECLARE_BITMAP(mask, NR_CPUS); + } *args; + struct multicall_space mcs; + + BUG_ON(cpumask_empty(cpus)); + BUG_ON(!mm); + + mcs = xen_mc_entry(sizeof(*args)); + args = mcs.args; + args->op.arg2.vcpumask = to_cpumask(args->mask); + + /* Remove us, and any offline CPUS. */ + cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); + if (unlikely(cpumask_empty(to_cpumask(args->mask)))) + goto issue; + + if (va == TLB_FLUSH_ALL) { + args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; + } else { + args->op.cmd = MMUEXT_INVLPG_MULTI; + args->op.arg1.linear_addr = va; + } + + MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); + +issue: + xen_mc_issue(PARAVIRT_LAZY_MMU); +} + +static unsigned long xen_read_cr3(void) +{ + return percpu_read(xen_cr3); +} + +static void set_current_cr3(void *v) +{ + percpu_write(xen_current_cr3, (unsigned long)v); +} + +static void __xen_write_cr3(bool kernel, unsigned long cr3) +{ + struct mmuext_op *op; + struct multicall_space mcs; + unsigned long mfn; + + if (cr3) + mfn = pfn_to_mfn(PFN_DOWN(cr3)); + else + mfn = 0; + + WARN_ON(mfn == 0 && kernel); + + mcs = __xen_mc_entry(sizeof(*op)); + + op = mcs.args; + op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR; + op->arg1.mfn = mfn; + + MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); + + if (kernel) { + percpu_write(xen_cr3, cr3); + + /* Update xen_current_cr3 once the batch has actually + been submitted. */ + xen_mc_callback(set_current_cr3, (void *)cr3); + } +} + +static void xen_write_cr3(unsigned long cr3) +{ + BUG_ON(preemptible()); + + xen_mc_batch(); /* disables interrupts */ + + /* Update while interrupts are disabled, so its atomic with + respect to ipis */ + percpu_write(xen_cr3, cr3); + + __xen_write_cr3(true, cr3); + +#ifdef CONFIG_X86_64 + { + pgd_t *user_pgd = xen_get_user_pgd(__va(cr3)); + if (user_pgd) + __xen_write_cr3(false, __pa(user_pgd)); + else + __xen_write_cr3(false, 0); + } +#endif + + xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ +} + +static int xen_pgd_alloc(struct mm_struct *mm) +{ + pgd_t *pgd = mm->pgd; + int ret = 0; + + BUG_ON(PagePinned(virt_to_page(pgd))); + +#ifdef CONFIG_X86_64 + { + struct page *page = virt_to_page(pgd); + pgd_t *user_pgd; + + BUG_ON(page->private != 0); + + ret = -ENOMEM; + + user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + page->private = (unsigned long)user_pgd; + + if (user_pgd != NULL) { + user_pgd[pgd_index(VSYSCALL_START)] = + __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); + ret = 0; + } + + BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); + } +#endif + + return ret; +} + +static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ +#ifdef CONFIG_X86_64 + pgd_t *user_pgd = xen_get_user_pgd(pgd); + + if (user_pgd) + free_page((unsigned long)user_pgd); +#endif +} + +#ifdef CONFIG_HIGHPTE +static void *xen_kmap_atomic_pte(struct page *page, enum km_type type) +{ + pgprot_t prot = PAGE_KERNEL; + + if (PagePinned(page)) + prot = PAGE_KERNEL_RO; + + if (0 && PageHighMem(page)) + printk("mapping highpte %lx type %d prot %s\n", + page_to_pfn(page), type, + (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ"); + + return kmap_atomic_prot(page, type, prot); +} +#endif + +#ifdef CONFIG_X86_32 +static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte) +{ + /* If there's an existing pte, then don't allow _PAGE_RW to be set */ + if (pte_val_ma(*ptep) & _PAGE_PRESENT) + pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & + pte_val_ma(pte)); + + return pte; +} + +/* Init-time set_pte while constructing initial pagetables, which + doesn't allow RO pagetable pages to be remapped RW */ +static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) +{ + pte = mask_rw_pte(ptep, pte); + + xen_set_pte(ptep, pte); +} +#endif + +/* Early in boot, while setting up the initial pagetable, assume + everything is pinned. */ +static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) +{ +#ifdef CONFIG_FLATMEM + BUG_ON(mem_map); /* should only be used early */ +#endif + make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); +} + +/* Early release_pte assumes that all pts are pinned, since there's + only init_mm and anything attached to that is pinned. */ +static void xen_release_pte_init(unsigned long pfn) +{ + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); +} + +static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +{ + struct mmuext_op op; + op.cmd = cmd; + op.arg1.mfn = pfn_to_mfn(pfn); + if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) + BUG(); +} + +/* This needs to make sure the new pte page is pinned iff its being + attached to a pinned pagetable. */ +static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level) +{ + struct page *page = pfn_to_page(pfn); + + if (PagePinned(virt_to_page(mm->pgd))) { + SetPagePinned(page); + + vm_unmap_aliases(); + if (!PageHighMem(page)) { + make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn))); + if (level == PT_PTE && USE_SPLIT_PTLOCKS) + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); + } else { + /* make sure there are no stray mappings of + this page */ + kmap_flush_unused(); + } + } +} + +static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn) +{ + xen_alloc_ptpage(mm, pfn, PT_PTE); +} + +static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn) +{ + xen_alloc_ptpage(mm, pfn, PT_PMD); +} + +/* This should never happen until we're OK to use struct page */ +static void xen_release_ptpage(unsigned long pfn, unsigned level) +{ + struct page *page = pfn_to_page(pfn); + + if (PagePinned(page)) { + if (!PageHighMem(page)) { + if (level == PT_PTE && USE_SPLIT_PTLOCKS) + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); + } + ClearPagePinned(page); + } +} + +static void xen_release_pte(unsigned long pfn) +{ + xen_release_ptpage(pfn, PT_PTE); +} + +static void xen_release_pmd(unsigned long pfn) +{ + xen_release_ptpage(pfn, PT_PMD); +} + +#if PAGETABLE_LEVELS == 4 +static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) +{ + xen_alloc_ptpage(mm, pfn, PT_PUD); +} + +static void xen_release_pud(unsigned long pfn) +{ + xen_release_ptpage(pfn, PT_PUD); +} +#endif + +void __init xen_reserve_top(void) +{ +#ifdef CONFIG_X86_32 + unsigned long top = HYPERVISOR_VIRT_START; + struct xen_platform_parameters pp; + + if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0) + top = pp.virt_start; + + reserve_top_address(-top); +#endif /* CONFIG_X86_32 */ +} + +/* + * Like __va(), but returns address in the kernel mapping (which is + * all we have until the physical memory mapping has been set up. + */ +static void *__ka(phys_addr_t paddr) +{ +#ifdef CONFIG_X86_64 + return (void *)(paddr + __START_KERNEL_map); +#else + return __va(paddr); +#endif +} + +/* Convert a machine address to physical address */ +static unsigned long m2p(phys_addr_t maddr) +{ + phys_addr_t paddr; + + maddr &= PTE_PFN_MASK; + paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT; + + return paddr; +} + +/* Convert a machine address to kernel virtual */ +static void *m2v(phys_addr_t maddr) +{ + return __ka(m2p(maddr)); +} + +static void set_page_prot(void *addr, pgprot_t prot) +{ + unsigned long pfn = __pa(addr) >> PAGE_SHIFT; + pte_t pte = pfn_pte(pfn, prot); + + if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0)) + BUG(); +} + +static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) +{ + unsigned pmdidx, pteidx; + unsigned ident_pte; + unsigned long pfn; + + ident_pte = 0; + pfn = 0; + for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) { + pte_t *pte_page; + + /* Reuse or allocate a page of ptes */ + if (pmd_present(pmd[pmdidx])) + pte_page = m2v(pmd[pmdidx].pmd); + else { + /* Check for free pte pages */ + if (ident_pte == ARRAY_SIZE(level1_ident_pgt)) + break; + + pte_page = &level1_ident_pgt[ident_pte]; + ident_pte += PTRS_PER_PTE; + + pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE); + } + + /* Install mappings */ + for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { + pte_t pte; + + if (pfn > max_pfn_mapped) + max_pfn_mapped = pfn; + + if (!pte_none(pte_page[pteidx])) + continue; + + pte = pfn_pte(pfn, PAGE_KERNEL_EXEC); + pte_page[pteidx] = pte; + } + } + + for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE) + set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO); + + set_page_prot(pmd, PAGE_KERNEL_RO); +} + +#ifdef CONFIG_X86_64 +static void convert_pfn_mfn(void *v) +{ + pte_t *pte = v; + int i; + + /* All levels are converted the same way, so just treat them + as ptes. */ + for (i = 0; i < PTRS_PER_PTE; i++) + pte[i] = xen_make_pte(pte[i].pte); +} + +/* + * Set up the inital kernel pagetable. + * + * We can construct this by grafting the Xen provided pagetable into + * head_64.S's preconstructed pagetables. We copy the Xen L2's into + * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This + * means that only the kernel has a physical mapping to start with - + * but that's enough to get __va working. We need to fill in the rest + * of the physical mapping once some sort of allocator has been set + * up. + */ +__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, + unsigned long max_pfn) +{ + pud_t *l3; + pmd_t *l2; + + /* Zap identity mapping */ + init_level4_pgt[0] = __pgd(0); + + /* Pre-constructed entries are in pfn, so convert to mfn */ + convert_pfn_mfn(init_level4_pgt); + convert_pfn_mfn(level3_ident_pgt); + convert_pfn_mfn(level3_kernel_pgt); + + l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); + l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud); + + memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); + memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); + + l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd); + l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud); + memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD); + + /* Set up identity map */ + xen_map_identity_early(level2_ident_pgt, max_pfn); + + /* Make pagetable pieces RO */ + set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); + set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); + set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); + + /* Pin down new L4 */ + pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, + PFN_DOWN(__pa_symbol(init_level4_pgt))); + + /* Unpin Xen-provided one */ + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); + + /* Switch over */ + pgd = init_level4_pgt; + + /* + * At this stage there can be no user pgd, and no page + * structure to attach it to, so make sure we just set kernel + * pgd. + */ + xen_mc_batch(); + __xen_write_cr3(true, __pa(pgd)); + xen_mc_issue(PARAVIRT_LAZY_CPU); + + reserve_early(__pa(xen_start_info->pt_base), + __pa(xen_start_info->pt_base + + xen_start_info->nr_pt_frames * PAGE_SIZE), + "XEN PAGETABLES"); + + return pgd; +} +#else /* !CONFIG_X86_64 */ +static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss; + +__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, + unsigned long max_pfn) +{ + pmd_t *kernel_pmd; + + init_pg_tables_start = __pa(pgd); + init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE; + max_pfn_mapped = PFN_DOWN(init_pg_tables_end + 512*1024); + + kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); + memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); + + xen_map_identity_early(level2_kernel_pgt, max_pfn); + + memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD); + set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY], + __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT)); + + set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); + set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); + set_page_prot(empty_zero_page, PAGE_KERNEL_RO); + + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); + + xen_write_cr3(__pa(swapper_pg_dir)); + + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); + + return swapper_pg_dir; +} +#endif /* CONFIG_X86_64 */ + +static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot) +{ + pte_t pte; + + phys >>= PAGE_SHIFT; + + switch (idx) { + case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: +#ifdef CONFIG_X86_F00F_BUG + case FIX_F00F_IDT: +#endif +#ifdef CONFIG_X86_32 + case FIX_WP_TEST: + case FIX_VDSO: +# ifdef CONFIG_HIGHMEM + case FIX_KMAP_BEGIN ... FIX_KMAP_END: +# endif +#else + case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE: +#endif +#ifdef CONFIG_X86_LOCAL_APIC + case FIX_APIC_BASE: /* maps dummy local APIC */ +#endif + pte = pfn_pte(phys, prot); + break; + + default: + pte = mfn_pte(phys, prot); + break; + } + + __native_set_fixmap(idx, pte); + +#ifdef CONFIG_X86_64 + /* Replicate changes to map the vsyscall page into the user + pagetable vsyscall mapping. */ + if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) { + unsigned long vaddr = __fix_to_virt(idx); + set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); + } +#endif +} + +__init void xen_post_allocator_init(void) +{ + pv_mmu_ops.set_pte = xen_set_pte; + pv_mmu_ops.set_pmd = xen_set_pmd; + pv_mmu_ops.set_pud = xen_set_pud; +#if PAGETABLE_LEVELS == 4 + pv_mmu_ops.set_pgd = xen_set_pgd; +#endif + + /* This will work as long as patching hasn't happened yet + (which it hasn't) */ + pv_mmu_ops.alloc_pte = xen_alloc_pte; + pv_mmu_ops.alloc_pmd = xen_alloc_pmd; + pv_mmu_ops.release_pte = xen_release_pte; + pv_mmu_ops.release_pmd = xen_release_pmd; +#if PAGETABLE_LEVELS == 4 + pv_mmu_ops.alloc_pud = xen_alloc_pud; + pv_mmu_ops.release_pud = xen_release_pud; +#endif + +#ifdef CONFIG_X86_64 + SetPagePinned(virt_to_page(level3_user_vsyscall)); +#endif + xen_mark_init_mm_pinned(); +} + + +const struct pv_mmu_ops xen_mmu_ops __initdata = { + .pagetable_setup_start = xen_pagetable_setup_start, + .pagetable_setup_done = xen_pagetable_setup_done, + + .read_cr2 = xen_read_cr2, + .write_cr2 = xen_write_cr2, + + .read_cr3 = xen_read_cr3, + .write_cr3 = xen_write_cr3, + + .flush_tlb_user = xen_flush_tlb, + .flush_tlb_kernel = xen_flush_tlb, + .flush_tlb_single = xen_flush_tlb_single, + .flush_tlb_others = xen_flush_tlb_others, + + .pte_update = paravirt_nop, + .pte_update_defer = paravirt_nop, + + .pgd_alloc = xen_pgd_alloc, + .pgd_free = xen_pgd_free, + + .alloc_pte = xen_alloc_pte_init, + .release_pte = xen_release_pte_init, + .alloc_pmd = xen_alloc_pte_init, + .alloc_pmd_clone = paravirt_nop, + .release_pmd = xen_release_pte_init, + +#ifdef CONFIG_HIGHPTE + .kmap_atomic_pte = xen_kmap_atomic_pte, +#endif + +#ifdef CONFIG_X86_64 + .set_pte = xen_set_pte, +#else + .set_pte = xen_set_pte_init, +#endif + .set_pte_at = xen_set_pte_at, + .set_pmd = xen_set_pmd_hyper, + + .ptep_modify_prot_start = __ptep_modify_prot_start, + .ptep_modify_prot_commit = __ptep_modify_prot_commit, + + .pte_val = PV_CALLEE_SAVE(xen_pte_val), + .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), + + .make_pte = PV_CALLEE_SAVE(xen_make_pte), + .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), + +#ifdef CONFIG_X86_PAE + .set_pte_atomic = xen_set_pte_atomic, + .set_pte_present = xen_set_pte_at, + .pte_clear = xen_pte_clear, + .pmd_clear = xen_pmd_clear, +#endif /* CONFIG_X86_PAE */ + .set_pud = xen_set_pud_hyper, + + .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), + .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), + +#if PAGETABLE_LEVELS == 4 + .pud_val = PV_CALLEE_SAVE(xen_pud_val), + .make_pud = PV_CALLEE_SAVE(xen_make_pud), + .set_pgd = xen_set_pgd_hyper, + + .alloc_pud = xen_alloc_pte_init, + .release_pud = xen_release_pte_init, +#endif /* PAGETABLE_LEVELS == 4 */ + + .activate_mm = xen_activate_mm, + .dup_mmap = xen_dup_mmap, + .exit_mmap = xen_exit_mmap, + + .lazy_mode = { + .enter = paravirt_enter_lazy_mmu, + .leave = xen_leave_lazy, + }, + + .set_fixmap = xen_set_fixmap, +}; + + #ifdef CONFIG_XEN_DEBUG_FS static struct dentry *d_mmu_debug; diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 98d71659da5..24d1b44a337 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -54,4 +54,7 @@ pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); +unsigned long xen_read_cr2_direct(void); + +extern const struct pv_mmu_ops xen_mmu_ops; #endif /* _XEN_MMU_H */ diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h index fa3e10725d9..9e565da5d1f 100644 --- a/arch/x86/xen/multicalls.h +++ b/arch/x86/xen/multicalls.h @@ -41,7 +41,7 @@ static inline void xen_mc_issue(unsigned mode) xen_mc_flush(); /* restore flags saved in xen_mc_batch */ - local_irq_restore(x86_read_percpu(xen_mc_irq_flags)); + local_irq_restore(percpu_read(xen_mc_irq_flags)); } /* Set up a callback to be called when the current batch is flushed */ diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index c44e2069c7c..035582ae815 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -50,11 +50,7 @@ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); */ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) { -#ifdef CONFIG_X86_32 - __get_cpu_var(irq_stat).irq_resched_count++; -#else - add_pda(irq_resched_count, 1); -#endif + inc_irq_stat(irq_resched_count); return IRQ_HANDLED; } @@ -78,7 +74,7 @@ static __cpuinit void cpu_bringup(void) xen_setup_cpu_clockevents(); cpu_set(cpu, cpu_online_map); - x86_write_percpu(cpu_state, CPU_ONLINE); + percpu_write(cpu_state, CPU_ONLINE); wmb(); /* We can take interrupts now: we're officially "up". */ @@ -174,7 +170,7 @@ static void __init xen_smp_prepare_boot_cpu(void) /* We've switched to the "real" per-cpu gdt, so make sure the old memory can be recycled */ - make_lowmem_page_readwrite(&per_cpu_var(gdt_page)); + make_lowmem_page_readwrite(xen_initial_gdt); xen_setup_vcpu_info_placement(); } @@ -239,6 +235,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) ctxt->user_regs.ss = __KERNEL_DS; #ifdef CONFIG_X86_32 ctxt->user_regs.fs = __KERNEL_PERCPU; +#else + ctxt->gs_base_kernel = per_cpu_offset(cpu); #endif ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle; ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */ @@ -283,23 +281,14 @@ static int __cpuinit xen_cpu_up(unsigned int cpu) struct task_struct *idle = idle_task(cpu); int rc; -#ifdef CONFIG_X86_64 - /* Allocate node local memory for AP pdas */ - WARN_ON(cpu == 0); - if (cpu > 0) { - rc = get_local_pda(cpu); - if (rc) - return rc; - } -#endif - -#ifdef CONFIG_X86_32 - init_gdt(cpu); per_cpu(current_task, cpu) = idle; +#ifdef CONFIG_X86_32 irq_ctx_init(cpu); #else - cpu_pda(cpu)->pcurrent = idle; clear_tsk_thread_flag(idle, TIF_FORK); + per_cpu(kernel_stack, cpu) = + (unsigned long)task_stack_page(idle) - + KERNEL_STACK_OFFSET + THREAD_SIZE; #endif xen_setup_timer(cpu); xen_init_lock_cpu(cpu); @@ -445,11 +434,7 @@ static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id) { irq_enter(); generic_smp_call_function_interrupt(); -#ifdef CONFIG_X86_32 - __get_cpu_var(irq_stat).irq_call_count++; -#else - add_pda(irq_call_count, 1); -#endif + inc_irq_stat(irq_call_count); irq_exit(); return IRQ_HANDLED; @@ -459,11 +444,7 @@ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id) { irq_enter(); generic_smp_call_function_single_interrupt(); -#ifdef CONFIG_X86_32 - __get_cpu_var(irq_stat).irq_call_count++; -#else - add_pda(irq_call_count, 1); -#endif + inc_irq_stat(irq_call_count); irq_exit(); return IRQ_HANDLED; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 212ffe012b7..95be7b43472 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -6,6 +6,7 @@ #include <asm/xen/hypercall.h> #include <asm/xen/page.h> +#include <asm/fixmap.h> #include "xen-ops.h" #include "mmu.h" diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S new file mode 100644 index 00000000000..79d7362ad6d --- /dev/null +++ b/arch/x86/xen/xen-asm.S @@ -0,0 +1,142 @@ +/* + * Asm versions of Xen pv-ops, suitable for either direct use or + * inlining. The inline versions are the same as the direct-use + * versions, with the pre- and post-amble chopped off. + * + * This code is encoded for size rather than absolute efficiency, with + * a view to being able to inline as much as possible. + * + * We only bother with direct forms (ie, vcpu in percpu data) of the + * operations here; the indirect forms are better handled in C, since + * they're generally too large to inline anyway. + */ + +#include <asm/asm-offsets.h> +#include <asm/percpu.h> +#include <asm/processor-flags.h> + +#include "xen-asm.h" + +/* + * Enable events. This clears the event mask and tests the pending + * event status with one and operation. If there are pending events, + * then enter the hypervisor to get them handled. + */ +ENTRY(xen_irq_enable_direct) + /* Unmask events */ + movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + + /* + * Preempt here doesn't matter because that will deal with any + * pending interrupts. The pending check may end up being run + * on the wrong CPU, but that doesn't hurt. + */ + + /* Test for pending */ + testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending + jz 1f + +2: call check_events +1: +ENDPATCH(xen_irq_enable_direct) + ret + ENDPROC(xen_irq_enable_direct) + RELOC(xen_irq_enable_direct, 2b+1) + + +/* + * Disabling events is simply a matter of making the event mask + * non-zero. + */ +ENTRY(xen_irq_disable_direct) + movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask +ENDPATCH(xen_irq_disable_direct) + ret + ENDPROC(xen_irq_disable_direct) + RELOC(xen_irq_disable_direct, 0) + +/* + * (xen_)save_fl is used to get the current interrupt enable status. + * Callers expect the status to be in X86_EFLAGS_IF, and other bits + * may be set in the return value. We take advantage of this by + * making sure that X86_EFLAGS_IF has the right value (and other bits + * in that byte are 0), but other bits in the return value are + * undefined. We need to toggle the state of the bit, because Xen and + * x86 use opposite senses (mask vs enable). + */ +ENTRY(xen_save_fl_direct) + testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + setz %ah + addb %ah, %ah +ENDPATCH(xen_save_fl_direct) + ret + ENDPROC(xen_save_fl_direct) + RELOC(xen_save_fl_direct, 0) + + +/* + * In principle the caller should be passing us a value return from + * xen_save_fl_direct, but for robustness sake we test only the + * X86_EFLAGS_IF flag rather than the whole byte. After setting the + * interrupt mask state, it checks for unmasked pending events and + * enters the hypervisor to get them delivered if so. + */ +ENTRY(xen_restore_fl_direct) +#ifdef CONFIG_X86_64 + testw $X86_EFLAGS_IF, %di +#else + testb $X86_EFLAGS_IF>>8, %ah +#endif + setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + /* + * Preempt here doesn't matter because that will deal with any + * pending interrupts. The pending check may end up being run + * on the wrong CPU, but that doesn't hurt. + */ + + /* check for unmasked and pending */ + cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending + jz 1f +2: call check_events +1: +ENDPATCH(xen_restore_fl_direct) + ret + ENDPROC(xen_restore_fl_direct) + RELOC(xen_restore_fl_direct, 2b+1) + + +/* + * Force an event check by making a hypercall, but preserve regs + * before making the call. + */ +check_events: +#ifdef CONFIG_X86_32 + push %eax + push %ecx + push %edx + call xen_force_evtchn_callback + pop %edx + pop %ecx + pop %eax +#else + push %rax + push %rcx + push %rdx + push %rsi + push %rdi + push %r8 + push %r9 + push %r10 + push %r11 + call xen_force_evtchn_callback + pop %r11 + pop %r10 + pop %r9 + pop %r8 + pop %rdi + pop %rsi + pop %rdx + pop %rcx + pop %rax +#endif + ret diff --git a/arch/x86/xen/xen-asm.h b/arch/x86/xen/xen-asm.h new file mode 100644 index 00000000000..465276467a4 --- /dev/null +++ b/arch/x86/xen/xen-asm.h @@ -0,0 +1,12 @@ +#ifndef _XEN_XEN_ASM_H +#define _XEN_XEN_ASM_H + +#include <linux/linkage.h> + +#define RELOC(x, v) .globl x##_reloc; x##_reloc=v +#define ENDPATCH(x) .globl x##_end; x##_end=. + +/* Pseudo-flag used for virtual NMI, which we don't implement yet */ +#define XEN_EFLAGS_NMI 0x80000000 + +#endif diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index 42786f59d9c..88e15deb8b8 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -1,117 +1,43 @@ /* - Asm versions of Xen pv-ops, suitable for either direct use or inlining. - The inline versions are the same as the direct-use versions, with the - pre- and post-amble chopped off. - - This code is encoded for size rather than absolute efficiency, - with a view to being able to inline as much as possible. - - We only bother with direct forms (ie, vcpu in pda) of the operations - here; the indirect forms are better handled in C, since they're - generally too large to inline anyway. + * Asm versions of Xen pv-ops, suitable for either direct use or + * inlining. The inline versions are the same as the direct-use + * versions, with the pre- and post-amble chopped off. + * + * This code is encoded for size rather than absolute efficiency, with + * a view to being able to inline as much as possible. + * + * We only bother with direct forms (ie, vcpu in pda) of the + * operations here; the indirect forms are better handled in C, since + * they're generally too large to inline anyway. */ -#include <linux/linkage.h> - -#include <asm/asm-offsets.h> #include <asm/thread_info.h> -#include <asm/percpu.h> #include <asm/processor-flags.h> #include <asm/segment.h> #include <xen/interface/xen.h> -#define RELOC(x, v) .globl x##_reloc; x##_reloc=v -#define ENDPATCH(x) .globl x##_end; x##_end=. - -/* Pseudo-flag used for virtual NMI, which we don't implement yet */ -#define XEN_EFLAGS_NMI 0x80000000 - -/* - Enable events. This clears the event mask and tests the pending - event status with one and operation. If there are pending - events, then enter the hypervisor to get them handled. - */ -ENTRY(xen_irq_enable_direct) - /* Unmask events */ - movb $0, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask - - /* Preempt here doesn't matter because that will deal with - any pending interrupts. The pending check may end up being - run on the wrong CPU, but that doesn't hurt. */ - - /* Test for pending */ - testb $0xff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending - jz 1f - -2: call check_events -1: -ENDPATCH(xen_irq_enable_direct) - ret - ENDPROC(xen_irq_enable_direct) - RELOC(xen_irq_enable_direct, 2b+1) - - -/* - Disabling events is simply a matter of making the event mask - non-zero. - */ -ENTRY(xen_irq_disable_direct) - movb $1, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask -ENDPATCH(xen_irq_disable_direct) - ret - ENDPROC(xen_irq_disable_direct) - RELOC(xen_irq_disable_direct, 0) +#include "xen-asm.h" /* - (xen_)save_fl is used to get the current interrupt enable status. - Callers expect the status to be in X86_EFLAGS_IF, and other bits - may be set in the return value. We take advantage of this by - making sure that X86_EFLAGS_IF has the right value (and other bits - in that byte are 0), but other bits in the return value are - undefined. We need to toggle the state of the bit, because - Xen and x86 use opposite senses (mask vs enable). + * Force an event check by making a hypercall, but preserve regs + * before making the call. */ -ENTRY(xen_save_fl_direct) - testb $0xff, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask - setz %ah - addb %ah,%ah -ENDPATCH(xen_save_fl_direct) - ret - ENDPROC(xen_save_fl_direct) - RELOC(xen_save_fl_direct, 0) - - -/* - In principle the caller should be passing us a value return - from xen_save_fl_direct, but for robustness sake we test only - the X86_EFLAGS_IF flag rather than the whole byte. After - setting the interrupt mask state, it checks for unmasked - pending events and enters the hypervisor to get them delivered - if so. - */ -ENTRY(xen_restore_fl_direct) - testb $X86_EFLAGS_IF>>8, %ah - setz PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_mask - /* Preempt here doesn't matter because that will deal with - any pending interrupts. The pending check may end up being - run on the wrong CPU, but that doesn't hurt. */ - - /* check for unmasked and pending */ - cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info)+XEN_vcpu_info_pending - jz 1f -2: call check_events -1: -ENDPATCH(xen_restore_fl_direct) +check_events: + push %eax + push %ecx + push %edx + call xen_force_evtchn_callback + pop %edx + pop %ecx + pop %eax ret - ENDPROC(xen_restore_fl_direct) - RELOC(xen_restore_fl_direct, 2b+1) /* - We can't use sysexit directly, because we're not running in ring0. - But we can easily fake it up using iret. Assuming xen_sysexit - is jumped to with a standard stack frame, we can just strip it - back to a standard iret frame and use iret. + * We can't use sysexit directly, because we're not running in ring0. + * But we can easily fake it up using iret. Assuming xen_sysexit is + * jumped to with a standard stack frame, we can just strip it back to + * a standard iret frame and use iret. */ ENTRY(xen_sysexit) movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */ @@ -122,33 +48,31 @@ ENTRY(xen_sysexit) ENDPROC(xen_sysexit) /* - This is run where a normal iret would be run, with the same stack setup: - 8: eflags - 4: cs - esp-> 0: eip - - This attempts to make sure that any pending events are dealt - with on return to usermode, but there is a small window in - which an event can happen just before entering usermode. If - the nested interrupt ends up setting one of the TIF_WORK_MASK - pending work flags, they will not be tested again before - returning to usermode. This means that a process can end up - with pending work, which will be unprocessed until the process - enters and leaves the kernel again, which could be an - unbounded amount of time. This means that a pending signal or - reschedule event could be indefinitely delayed. - - The fix is to notice a nested interrupt in the critical - window, and if one occurs, then fold the nested interrupt into - the current interrupt stack frame, and re-process it - iteratively rather than recursively. This means that it will - exit via the normal path, and all pending work will be dealt - with appropriately. - - Because the nested interrupt handler needs to deal with the - current stack state in whatever form its in, we keep things - simple by only using a single register which is pushed/popped - on the stack. + * This is run where a normal iret would be run, with the same stack setup: + * 8: eflags + * 4: cs + * esp-> 0: eip + * + * This attempts to make sure that any pending events are dealt with + * on return to usermode, but there is a small window in which an + * event can happen just before entering usermode. If the nested + * interrupt ends up setting one of the TIF_WORK_MASK pending work + * flags, they will not be tested again before returning to + * usermode. This means that a process can end up with pending work, + * which will be unprocessed until the process enters and leaves the + * kernel again, which could be an unbounded amount of time. This + * means that a pending signal or reschedule event could be + * indefinitely delayed. + * + * The fix is to notice a nested interrupt in the critical window, and + * if one occurs, then fold the nested interrupt into the current + * interrupt stack frame, and re-process it iteratively rather than + * recursively. This means that it will exit via the normal path, and + * all pending work will be dealt with appropriately. + * + * Because the nested interrupt handler needs to deal with the current + * stack state in whatever form its in, we keep things simple by only + * using a single register which is pushed/popped on the stack. */ ENTRY(xen_iret) /* test eflags for special cases */ @@ -158,13 +82,15 @@ ENTRY(xen_iret) push %eax ESP_OFFSET=4 # bytes pushed onto stack - /* Store vcpu_info pointer for easy access. Do it this - way to avoid having to reload %fs */ + /* + * Store vcpu_info pointer for easy access. Do it this way to + * avoid having to reload %fs + */ #ifdef CONFIG_SMP GET_THREAD_INFO(%eax) - movl TI_cpu(%eax),%eax - movl __per_cpu_offset(,%eax,4),%eax - mov per_cpu__xen_vcpu(%eax),%eax + movl TI_cpu(%eax), %eax + movl __per_cpu_offset(,%eax,4), %eax + mov per_cpu__xen_vcpu(%eax), %eax #else movl per_cpu__xen_vcpu, %eax #endif @@ -172,37 +98,46 @@ ENTRY(xen_iret) /* check IF state we're restoring */ testb $X86_EFLAGS_IF>>8, 8+1+ESP_OFFSET(%esp) - /* Maybe enable events. Once this happens we could get a - recursive event, so the critical region starts immediately - afterwards. However, if that happens we don't end up - resuming the code, so we don't have to be worried about - being preempted to another CPU. */ + /* + * Maybe enable events. Once this happens we could get a + * recursive event, so the critical region starts immediately + * afterwards. However, if that happens we don't end up + * resuming the code, so we don't have to be worried about + * being preempted to another CPU. + */ setz XEN_vcpu_info_mask(%eax) xen_iret_start_crit: /* check for unmasked and pending */ cmpw $0x0001, XEN_vcpu_info_pending(%eax) - /* If there's something pending, mask events again so we - can jump back into xen_hypervisor_callback */ + /* + * If there's something pending, mask events again so we can + * jump back into xen_hypervisor_callback + */ sete XEN_vcpu_info_mask(%eax) popl %eax - /* From this point on the registers are restored and the stack - updated, so we don't need to worry about it if we're preempted */ + /* + * From this point on the registers are restored and the stack + * updated, so we don't need to worry about it if we're + * preempted + */ iret_restore_end: - /* Jump to hypervisor_callback after fixing up the stack. - Events are masked, so jumping out of the critical - region is OK. */ + /* + * Jump to hypervisor_callback after fixing up the stack. + * Events are masked, so jumping out of the critical region is + * OK. + */ je xen_hypervisor_callback 1: iret xen_iret_end_crit: -.section __ex_table,"a" +.section __ex_table, "a" .align 4 - .long 1b,iret_exc + .long 1b, iret_exc .previous hyper_iret: @@ -212,55 +147,55 @@ hyper_iret: .globl xen_iret_start_crit, xen_iret_end_crit /* - This is called by xen_hypervisor_callback in entry.S when it sees - that the EIP at the time of interrupt was between xen_iret_start_crit - and xen_iret_end_crit. We're passed the EIP in %eax so we can do - a more refined determination of what to do. - - The stack format at this point is: - ---------------- - ss : (ss/esp may be present if we came from usermode) - esp : - eflags } outer exception info - cs } - eip } - ---------------- <- edi (copy dest) - eax : outer eax if it hasn't been restored - ---------------- - eflags } nested exception info - cs } (no ss/esp because we're nested - eip } from the same ring) - orig_eax }<- esi (copy src) - - - - - - - - - - fs } - es } - ds } SAVE_ALL state - eax } - : : - ebx }<- esp - ---------------- - - In order to deliver the nested exception properly, we need to shift - everything from the return addr up to the error code so it - sits just under the outer exception info. This means that when we - handle the exception, we do it in the context of the outer exception - rather than starting a new one. - - The only caveat is that if the outer eax hasn't been - restored yet (ie, it's still on stack), we need to insert - its value into the SAVE_ALL state before going on, since - it's usermode state which we eventually need to restore. + * This is called by xen_hypervisor_callback in entry.S when it sees + * that the EIP at the time of interrupt was between + * xen_iret_start_crit and xen_iret_end_crit. We're passed the EIP in + * %eax so we can do a more refined determination of what to do. + * + * The stack format at this point is: + * ---------------- + * ss : (ss/esp may be present if we came from usermode) + * esp : + * eflags } outer exception info + * cs } + * eip } + * ---------------- <- edi (copy dest) + * eax : outer eax if it hasn't been restored + * ---------------- + * eflags } nested exception info + * cs } (no ss/esp because we're nested + * eip } from the same ring) + * orig_eax }<- esi (copy src) + * - - - - - - - - + * fs } + * es } + * ds } SAVE_ALL state + * eax } + * : : + * ebx }<- esp + * ---------------- + * + * In order to deliver the nested exception properly, we need to shift + * everything from the return addr up to the error code so it sits + * just under the outer exception info. This means that when we + * handle the exception, we do it in the context of the outer + * exception rather than starting a new one. + * + * The only caveat is that if the outer eax hasn't been restored yet + * (ie, it's still on stack), we need to insert its value into the + * SAVE_ALL state before going on, since it's usermode state which we + * eventually need to restore. */ ENTRY(xen_iret_crit_fixup) /* - Paranoia: Make sure we're really coming from kernel space. - One could imagine a case where userspace jumps into the - critical range address, but just before the CPU delivers a GP, - it decides to deliver an interrupt instead. Unlikely? - Definitely. Easy to avoid? Yes. The Intel documents - explicitly say that the reported EIP for a bad jump is the - jump instruction itself, not the destination, but some virtual - environments get this wrong. + * Paranoia: Make sure we're really coming from kernel space. + * One could imagine a case where userspace jumps into the + * critical range address, but just before the CPU delivers a + * GP, it decides to deliver an interrupt instead. Unlikely? + * Definitely. Easy to avoid? Yes. The Intel documents + * explicitly say that the reported EIP for a bad jump is the + * jump instruction itself, not the destination, but some + * virtual environments get this wrong. */ movl PT_CS(%esp), %ecx andl $SEGMENT_RPL_MASK, %ecx @@ -270,15 +205,17 @@ ENTRY(xen_iret_crit_fixup) lea PT_ORIG_EAX(%esp), %esi lea PT_EFLAGS(%esp), %edi - /* If eip is before iret_restore_end then stack - hasn't been restored yet. */ + /* + * If eip is before iret_restore_end then stack + * hasn't been restored yet. + */ cmp $iret_restore_end, %eax jae 1f - movl 0+4(%edi),%eax /* copy EAX (just above top of frame) */ + movl 0+4(%edi), %eax /* copy EAX (just above top of frame) */ movl %eax, PT_EAX(%esp) - lea ESP_OFFSET(%edi),%edi /* move dest up over saved regs */ + lea ESP_OFFSET(%edi), %edi /* move dest up over saved regs */ /* set up the copy */ 1: std @@ -286,20 +223,6 @@ ENTRY(xen_iret_crit_fixup) rep movsl cld - lea 4(%edi),%esp /* point esp to new frame */ + lea 4(%edi), %esp /* point esp to new frame */ 2: jmp xen_do_upcall - -/* - Force an event check by making a hypercall, - but preserve regs before making the call. - */ -check_events: - push %eax - push %ecx - push %edx - call xen_force_evtchn_callback - pop %edx - pop %ecx - pop %eax - ret diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 05794c566e8..02f496a8dba 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -1,174 +1,45 @@ /* - Asm versions of Xen pv-ops, suitable for either direct use or inlining. - The inline versions are the same as the direct-use versions, with the - pre- and post-amble chopped off. - - This code is encoded for size rather than absolute efficiency, - with a view to being able to inline as much as possible. - - We only bother with direct forms (ie, vcpu in pda) of the operations - here; the indirect forms are better handled in C, since they're - generally too large to inline anyway. + * Asm versions of Xen pv-ops, suitable for either direct use or + * inlining. The inline versions are the same as the direct-use + * versions, with the pre- and post-amble chopped off. + * + * This code is encoded for size rather than absolute efficiency, with + * a view to being able to inline as much as possible. + * + * We only bother with direct forms (ie, vcpu in pda) of the + * operations here; the indirect forms are better handled in C, since + * they're generally too large to inline anyway. */ -#include <linux/linkage.h> - -#include <asm/asm-offsets.h> -#include <asm/processor-flags.h> #include <asm/errno.h> +#include <asm/percpu.h> +#include <asm/processor-flags.h> #include <asm/segment.h> #include <xen/interface/xen.h> -#define RELOC(x, v) .globl x##_reloc; x##_reloc=v -#define ENDPATCH(x) .globl x##_end; x##_end=. - -/* Pseudo-flag used for virtual NMI, which we don't implement yet */ -#define XEN_EFLAGS_NMI 0x80000000 - -#if 1 -/* - x86-64 does not yet support direct access to percpu variables - via a segment override, so we just need to make sure this code - never gets used - */ -#define BUG ud2a -#define PER_CPU_VAR(var, off) 0xdeadbeef -#endif - -/* - Enable events. This clears the event mask and tests the pending - event status with one and operation. If there are pending - events, then enter the hypervisor to get them handled. - */ -ENTRY(xen_irq_enable_direct) - BUG - - /* Unmask events */ - movb $0, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask) - - /* Preempt here doesn't matter because that will deal with - any pending interrupts. The pending check may end up being - run on the wrong CPU, but that doesn't hurt. */ - - /* Test for pending */ - testb $0xff, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_pending) - jz 1f - -2: call check_events -1: -ENDPATCH(xen_irq_enable_direct) - ret - ENDPROC(xen_irq_enable_direct) - RELOC(xen_irq_enable_direct, 2b+1) - -/* - Disabling events is simply a matter of making the event mask - non-zero. - */ -ENTRY(xen_irq_disable_direct) - BUG - - movb $1, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask) -ENDPATCH(xen_irq_disable_direct) - ret - ENDPROC(xen_irq_disable_direct) - RELOC(xen_irq_disable_direct, 0) - -/* - (xen_)save_fl is used to get the current interrupt enable status. - Callers expect the status to be in X86_EFLAGS_IF, and other bits - may be set in the return value. We take advantage of this by - making sure that X86_EFLAGS_IF has the right value (and other bits - in that byte are 0), but other bits in the return value are - undefined. We need to toggle the state of the bit, because - Xen and x86 use opposite senses (mask vs enable). - */ -ENTRY(xen_save_fl_direct) - BUG - - testb $0xff, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask) - setz %ah - addb %ah,%ah -ENDPATCH(xen_save_fl_direct) - ret - ENDPROC(xen_save_fl_direct) - RELOC(xen_save_fl_direct, 0) - -/* - In principle the caller should be passing us a value return - from xen_save_fl_direct, but for robustness sake we test only - the X86_EFLAGS_IF flag rather than the whole byte. After - setting the interrupt mask state, it checks for unmasked - pending events and enters the hypervisor to get them delivered - if so. - */ -ENTRY(xen_restore_fl_direct) - BUG - - testb $X86_EFLAGS_IF>>8, %ah - setz PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_mask) - /* Preempt here doesn't matter because that will deal with - any pending interrupts. The pending check may end up being - run on the wrong CPU, but that doesn't hurt. */ - - /* check for unmasked and pending */ - cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info, XEN_vcpu_info_pending) - jz 1f -2: call check_events -1: -ENDPATCH(xen_restore_fl_direct) - ret - ENDPROC(xen_restore_fl_direct) - RELOC(xen_restore_fl_direct, 2b+1) - - -/* - Force an event check by making a hypercall, - but preserve regs before making the call. - */ -check_events: - push %rax - push %rcx - push %rdx - push %rsi - push %rdi - push %r8 - push %r9 - push %r10 - push %r11 - call xen_force_evtchn_callback - pop %r11 - pop %r10 - pop %r9 - pop %r8 - pop %rdi - pop %rsi - pop %rdx - pop %rcx - pop %rax - ret +#include "xen-asm.h" ENTRY(xen_adjust_exception_frame) - mov 8+0(%rsp),%rcx - mov 8+8(%rsp),%r11 + mov 8+0(%rsp), %rcx + mov 8+8(%rsp), %r11 ret $16 hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* - Xen64 iret frame: - - ss - rsp - rflags - cs - rip <-- standard iret frame - - flags - - rcx } - r11 }<-- pushed by hypercall page -rsp -> rax } + * Xen64 iret frame: + * + * ss + * rsp + * rflags + * cs + * rip <-- standard iret frame + * + * flags + * + * rcx } + * r11 }<-- pushed by hypercall page + * rsp->rax } */ ENTRY(xen_iret) pushq $0 @@ -177,8 +48,8 @@ ENDPATCH(xen_iret) RELOC(xen_iret, 1b+1) /* - sysexit is not used for 64-bit processes, so it's - only ever used to return to 32-bit compat userspace. + * sysexit is not used for 64-bit processes, so it's only ever used to + * return to 32-bit compat userspace. */ ENTRY(xen_sysexit) pushq $__USER32_DS @@ -193,13 +64,15 @@ ENDPATCH(xen_sysexit) RELOC(xen_sysexit, 1b+1) ENTRY(xen_sysret64) - /* We're already on the usermode stack at this point, but still - with the kernel gs, so we can easily switch back */ - movq %rsp, %gs:pda_oldrsp - movq %gs:pda_kernelstack,%rsp + /* + * We're already on the usermode stack at this point, but + * still with the kernel gs, so we can easily switch back + */ + movq %rsp, PER_CPU_VAR(old_rsp) + movq PER_CPU_VAR(kernel_stack), %rsp pushq $__USER_DS - pushq %gs:pda_oldrsp + pushq PER_CPU_VAR(old_rsp) pushq %r11 pushq $__USER_CS pushq %rcx @@ -210,13 +83,15 @@ ENDPATCH(xen_sysret64) RELOC(xen_sysret64, 1b+1) ENTRY(xen_sysret32) - /* We're already on the usermode stack at this point, but still - with the kernel gs, so we can easily switch back */ - movq %rsp, %gs:pda_oldrsp - movq %gs:pda_kernelstack, %rsp + /* + * We're already on the usermode stack at this point, but + * still with the kernel gs, so we can easily switch back + */ + movq %rsp, PER_CPU_VAR(old_rsp) + movq PER_CPU_VAR(kernel_stack), %rsp pushq $__USER32_DS - pushq %gs:pda_oldrsp + pushq PER_CPU_VAR(old_rsp) pushq %r11 pushq $__USER32_CS pushq %rcx @@ -227,28 +102,27 @@ ENDPATCH(xen_sysret32) RELOC(xen_sysret32, 1b+1) /* - Xen handles syscall callbacks much like ordinary exceptions, - which means we have: - - kernel gs - - kernel rsp - - an iret-like stack frame on the stack (including rcx and r11): - ss - rsp - rflags - cs - rip - r11 - rsp-> rcx - - In all the entrypoints, we undo all that to make it look - like a CPU-generated syscall/sysenter and jump to the normal - entrypoint. + * Xen handles syscall callbacks much like ordinary exceptions, which + * means we have: + * - kernel gs + * - kernel rsp + * - an iret-like stack frame on the stack (including rcx and r11): + * ss + * rsp + * rflags + * cs + * rip + * r11 + * rsp->rcx + * + * In all the entrypoints, we undo all that to make it look like a + * CPU-generated syscall/sysenter and jump to the normal entrypoint. */ .macro undo_xen_syscall - mov 0*8(%rsp),%rcx - mov 1*8(%rsp),%r11 - mov 5*8(%rsp),%rsp + mov 0*8(%rsp), %rcx + mov 1*8(%rsp), %r11 + mov 5*8(%rsp), %rsp .endm /* Normal 64-bit system call target */ @@ -275,7 +149,7 @@ ENDPROC(xen_sysenter_target) ENTRY(xen_syscall32_target) ENTRY(xen_sysenter_target) - lea 16(%rsp), %rsp /* strip %rcx,%r11 */ + lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $VGCF_in_syscall jmp hypercall_iret diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index c1f8faf0a2c..2f5ef2632ea 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -10,9 +10,12 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; +extern void *xen_initial_gdt; + struct trap_info; void xen_copy_trap_info(struct trap_info *traps); +DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info); DECLARE_PER_CPU(unsigned long, xen_cr3); DECLARE_PER_CPU(unsigned long, xen_current_cr3); @@ -22,6 +25,13 @@ extern struct shared_info *HYPERVISOR_shared_info; void xen_setup_mfn_list_list(void); void xen_setup_shared_info(void); +void xen_setup_machphys_mapping(void); +pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); +void xen_ident_map_ISA(void); +void xen_reserve_top(void); + +void xen_leave_lazy(void); +void xen_post_allocator_init(void); char * __init xen_memory_setup(void); void __init xen_arch_setup(void); diff --git a/crypto/algapi.c b/crypto/algapi.c index 7c41e7405c4..56c62e2858d 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -149,6 +149,9 @@ static struct crypto_larval *__crypto_register_alg(struct crypto_alg *alg) if (q == alg) goto err; + if (crypto_is_moribund(q)) + continue; + if (crypto_is_larval(q)) { if (!strcmp(alg->cra_driver_name, q->cra_driver_name)) goto err; @@ -197,7 +200,7 @@ void crypto_alg_tested(const char *name, int err) down_write(&crypto_alg_sem); list_for_each_entry(q, &crypto_alg_list, cra_list) { - if (!crypto_is_larval(q)) + if (crypto_is_moribund(q) || !crypto_is_larval(q)) continue; test = (struct crypto_larval *)q; @@ -210,6 +213,7 @@ void crypto_alg_tested(const char *name, int err) goto unlock; found: + q->cra_flags |= CRYPTO_ALG_DEAD; alg = test->adult; if (err || list_empty(&alg->cra_list)) goto complete; diff --git a/crypto/api.c b/crypto/api.c index 9975a7bd246..efe77df6863 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -557,34 +557,34 @@ err: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(crypto_alloc_tfm); - + /* - * crypto_free_tfm - Free crypto transform + * crypto_destroy_tfm - Free crypto transform + * @mem: Start of tfm slab * @tfm: Transform to free * - * crypto_free_tfm() frees up the transform and any associated resources, + * This function frees up the transform and any associated resources, * then drops the refcount on the associated algorithm. */ -void crypto_free_tfm(struct crypto_tfm *tfm) +void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm) { struct crypto_alg *alg; int size; - if (unlikely(!tfm)) + if (unlikely(!mem)) return; alg = tfm->__crt_alg; - size = sizeof(*tfm) + alg->cra_ctxsize; + size = ksize(mem); if (!tfm->exit && alg->cra_exit) alg->cra_exit(tfm); crypto_exit_ops(tfm); crypto_mod_put(alg); - memset(tfm, 0, size); - kfree(tfm); + memset(mem, 0, size); + kfree(mem); } - -EXPORT_SYMBOL_GPL(crypto_free_tfm); +EXPORT_SYMBOL_GPL(crypto_destroy_tfm); int crypto_has_alg(const char *name, u32 type, u32 mask) { diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c index 9aeeb52004a..3de89a42440 100644 --- a/crypto/scatterwalk.c +++ b/crypto/scatterwalk.c @@ -54,7 +54,8 @@ static void scatterwalk_pagedone(struct scatter_walk *walk, int out, struct page *page; page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT); - flush_dcache_page(page); + if (!PageSlab(page)) + flush_dcache_page(page); } if (more) { diff --git a/crypto/shash.c b/crypto/shash.c index c9df367332f..d5a2b619c55 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -388,10 +388,15 @@ static int crypto_init_shash_ops_compat(struct crypto_tfm *tfm) struct shash_desc *desc = crypto_tfm_ctx(tfm); struct crypto_shash *shash; + if (!crypto_mod_get(calg)) + return -EAGAIN; + shash = __crypto_shash_cast(crypto_create_tfm( calg, &crypto_shash_type)); - if (IS_ERR(shash)) + if (IS_ERR(shash)) { + crypto_mod_put(calg); return PTR_ERR(shash); + } desc->tfm = shash; tfm->exit = crypto_exit_shash_ops_compat; diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 72fc0f799a6..89d7a6e94c9 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -685,6 +685,7 @@ static int fpga_probe(struct pci_dev *dev, const struct pci_device_id *id) out_release_regions: pci_release_regions(dev); out: + kfree(card); return err; } diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 719ee5c1c8d..5b257a57bc5 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -107,7 +107,7 @@ static SYSDEV_ATTR(crash_notes, 0400, show_crash_notes, NULL); /* * Print cpu online, possible, present, and system maps */ -static ssize_t print_cpus_map(char *buf, cpumask_t *map) +static ssize_t print_cpus_map(char *buf, const struct cpumask *map) { int n = cpulist_scnprintf(buf, PAGE_SIZE-2, map); diff --git a/drivers/base/topology.c b/drivers/base/topology.c index a778fb52b11..bf6b13206d0 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -31,7 +31,10 @@ #include <linux/hardirq.h> #include <linux/topology.h> -#define define_one_ro(_name) \ +#define define_one_ro_named(_name, _func) \ +static SYSDEV_ATTR(_name, 0444, _func, NULL) + +#define define_one_ro(_name) \ static SYSDEV_ATTR(_name, 0444, show_##_name, NULL) #define define_id_show_func(name) \ @@ -42,8 +45,8 @@ static ssize_t show_##name(struct sys_device *dev, \ return sprintf(buf, "%d\n", topology_##name(cpu)); \ } -#if defined(topology_thread_siblings) || defined(topology_core_siblings) -static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf) +#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) +static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf) { ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf; int n = 0; @@ -65,7 +68,7 @@ static ssize_t show_##name(struct sys_device *dev, \ struct sysdev_attribute *attr, char *buf) \ { \ unsigned int cpu = dev->id; \ - return show_cpumap(0, &(topology_##name(cpu)), buf); \ + return show_cpumap(0, topology_##name(cpu), buf); \ } #define define_siblings_show_list(name) \ @@ -74,7 +77,7 @@ static ssize_t show_##name##_list(struct sys_device *dev, \ char *buf) \ { \ unsigned int cpu = dev->id; \ - return show_cpumap(1, &(topology_##name(cpu)), buf); \ + return show_cpumap(1, topology_##name(cpu), buf); \ } #else @@ -82,9 +85,7 @@ static ssize_t show_##name##_list(struct sys_device *dev, \ static ssize_t show_##name(struct sys_device *dev, \ struct sysdev_attribute *attr, char *buf) \ { \ - unsigned int cpu = dev->id; \ - cpumask_t mask = topology_##name(cpu); \ - return show_cpumap(0, &mask, buf); \ + return show_cpumap(0, topology_##name(dev->id), buf); \ } #define define_siblings_show_list(name) \ @@ -92,9 +93,7 @@ static ssize_t show_##name##_list(struct sys_device *dev, \ struct sysdev_attribute *attr, \ char *buf) \ { \ - unsigned int cpu = dev->id; \ - cpumask_t mask = topology_##name(cpu); \ - return show_cpumap(1, &mask, buf); \ + return show_cpumap(1, topology_##name(dev->id), buf); \ } #endif @@ -107,13 +106,13 @@ define_one_ro(physical_package_id); define_id_show_func(core_id); define_one_ro(core_id); -define_siblings_show_func(thread_siblings); -define_one_ro(thread_siblings); -define_one_ro(thread_siblings_list); +define_siblings_show_func(thread_cpumask); +define_one_ro_named(thread_siblings, show_thread_cpumask); +define_one_ro_named(thread_siblings_list, show_thread_cpumask_list); -define_siblings_show_func(core_siblings); -define_one_ro(core_siblings); -define_one_ro(core_siblings_list); +define_siblings_show_func(core_cpumask); +define_one_ro_named(core_siblings, show_core_cpumask); +define_one_ro_named(core_siblings_list, show_core_cpumask_list); static struct attribute *default_attrs[] = { &attr_physical_package_id.attr, diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 34f80fa6fed..8299e2d3b61 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -549,6 +549,15 @@ static void do_nbd_request(struct request_queue * q) BUG_ON(lo->magic != LO_MAGIC); + if (unlikely(!lo->sock)) { + printk(KERN_ERR "%s: Attempted send on closed socket\n", + lo->disk->disk_name); + req->errors++; + nbd_end_request(req); + spin_lock_irq(q->queue_lock); + continue; + } + spin_lock_irq(&lo->queue_lock); list_add_tail(&req->queuelist, &lo->waiting_queue); spin_unlock_irq(&lo->queue_lock); diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c index 726ee8a0277..ecba4942fc8 100644 --- a/drivers/char/tpm/tpm_infineon.c +++ b/drivers/char/tpm/tpm_infineon.c @@ -4,7 +4,7 @@ * SLD 9630 TT 1.1 and SLB 9635 TT 1.2 Trusted Platform Module * Specifications at www.trustedcomputinggroup.org * - * Copyright (C) 2005, Marcel Selhorst <selhorst@crypto.rub.de> + * Copyright (C) 2005, Marcel Selhorst <m.selhorst@sirrix.com> * Sirrix AG - security technologies, http://www.sirrix.com and * Applied Data Security Group, Ruhr-University Bochum, Germany * Project-Homepage: http://www.prosec.rub.de/tpm @@ -636,7 +636,7 @@ static void __exit cleanup_inf(void) module_init(init_inf); module_exit(cleanup_inf); -MODULE_AUTHOR("Marcel Selhorst <selhorst@crypto.rub.de>"); +MODULE_AUTHOR("Marcel Selhorst <m.selhorst@sirrix.com>"); MODULE_DESCRIPTION("Driver for Infineon TPM SLD 9630 TT 1.1 / SLB 9635 TT 1.2"); MODULE_VERSION("1.9"); MODULE_LICENSE("GPL"); diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index e1129fad96d..ee19b6e8fcb 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -143,7 +143,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_LE, #endif #ifndef CONFIG_X86_64 -#include "mach_timer.h" +#include <asm/mach_timer.h> #define PMTMR_EXPECTED_RATE \ ((CALIBRATE_LATCH * (PMTMR_TICKS_PER_SEC >> 10)) / (CLOCK_TICK_RATE>>10)) /* diff --git a/drivers/clocksource/cyclone.c b/drivers/clocksource/cyclone.c index 1bde303b970..8615059a872 100644 --- a/drivers/clocksource/cyclone.c +++ b/drivers/clocksource/cyclone.c @@ -7,7 +7,7 @@ #include <asm/pgtable.h> #include <asm/io.h> -#include "mach_timer.h" +#include <asm/mach_timer.h> #define CYCLONE_CBAR_ADDR 0xFEB00CD0 /* base address ptr */ #define CYCLONE_PMCC_OFFSET 0x51A0 /* offset to control register */ diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index 6a2b036c938..6f45b1658a6 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -117,11 +117,7 @@ static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu, busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.irq); busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.softirq); busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.steal); - - if (!dbs_tuners_ins.ignore_nice) { - busy_time = cputime64_add(busy_time, - kstat_cpu(cpu).cpustat.nice); - } + busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.nice); idle_time = cputime64_sub(cur_wall_time, busy_time); if (wall) @@ -137,23 +133,6 @@ static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall) if (idle_time == -1ULL) return get_cpu_idle_time_jiffy(cpu, wall); - if (dbs_tuners_ins.ignore_nice) { - cputime64_t cur_nice; - unsigned long cur_nice_jiffies; - struct cpu_dbs_info_s *dbs_info; - - dbs_info = &per_cpu(cpu_dbs_info, cpu); - cur_nice = cputime64_sub(kstat_cpu(cpu).cpustat.nice, - dbs_info->prev_cpu_nice); - /* - * Assumption: nice time between sampling periods will be - * less than 2^32 jiffies for 32 bit sys - */ - cur_nice_jiffies = (unsigned long) - cputime64_to_jiffies64(cur_nice); - dbs_info->prev_cpu_nice = kstat_cpu(cpu).cpustat.nice; - return idle_time + jiffies_to_usecs(cur_nice_jiffies); - } return idle_time; } @@ -319,6 +298,9 @@ static ssize_t store_ignore_nice_load(struct cpufreq_policy *policy, dbs_info = &per_cpu(cpu_dbs_info, j); dbs_info->prev_cpu_idle = get_cpu_idle_time(j, &dbs_info->prev_cpu_wall); + if (dbs_tuners_ins.ignore_nice) + dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice; + } mutex_unlock(&dbs_mutex); @@ -419,6 +401,23 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info) j_dbs_info->prev_cpu_idle); j_dbs_info->prev_cpu_idle = cur_idle_time; + if (dbs_tuners_ins.ignore_nice) { + cputime64_t cur_nice; + unsigned long cur_nice_jiffies; + + cur_nice = cputime64_sub(kstat_cpu(j).cpustat.nice, + j_dbs_info->prev_cpu_nice); + /* + * Assumption: nice time between sampling periods will + * be less than 2^32 jiffies for 32 bit sys + */ + cur_nice_jiffies = (unsigned long) + cputime64_to_jiffies64(cur_nice); + + j_dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice; + idle_time += jiffies_to_usecs(cur_nice_jiffies); + } + if (unlikely(!wall_time || wall_time < idle_time)) continue; @@ -575,6 +574,10 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j, &j_dbs_info->prev_cpu_wall); + if (dbs_tuners_ins.ignore_nice) { + j_dbs_info->prev_cpu_nice = + kstat_cpu(j).cpustat.nice; + } } this_dbs_info->cpu = cpu; /* diff --git a/drivers/eisa/Kconfig b/drivers/eisa/Kconfig index c0646576cf4..2705284f622 100644 --- a/drivers/eisa/Kconfig +++ b/drivers/eisa/Kconfig @@ -3,7 +3,7 @@ # config EISA_VLB_PRIMING bool "Vesa Local Bus priming" - depends on X86_PC && EISA + depends on X86 && EISA default n ---help--- Activate this option if your system contains a Vesa Local @@ -24,11 +24,11 @@ config EISA_PCI_EISA When in doubt, say Y. # Using EISA_VIRTUAL_ROOT on something other than an Alpha or -# an X86_PC may lead to crashes... +# an X86 may lead to crashes... config EISA_VIRTUAL_ROOT bool "EISA virtual root device" - depends on EISA && (ALPHA || X86_PC) + depends on EISA && (ALPHA || X86) default y ---help--- Activate this option if your system only have EISA bus diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c index 777fba48d2d..3009e0171e5 100644 --- a/drivers/firmware/dcdbas.c +++ b/drivers/firmware/dcdbas.c @@ -244,7 +244,7 @@ static ssize_t host_control_on_shutdown_store(struct device *dev, */ int dcdbas_smi_request(struct smi_cmd *smi_cmd) { - cpumask_t old_mask; + cpumask_var_t old_mask; int ret = 0; if (smi_cmd->magic != SMI_CMD_MAGIC) { @@ -254,8 +254,11 @@ int dcdbas_smi_request(struct smi_cmd *smi_cmd) } /* SMI requires CPU 0 */ - old_mask = current->cpus_allowed; - set_cpus_allowed_ptr(current, &cpumask_of_cpu(0)); + if (!alloc_cpumask_var(&old_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_copy(old_mask, ¤t->cpus_allowed); + set_cpus_allowed_ptr(current, cpumask_of(0)); if (smp_processor_id() != 0) { dev_dbg(&dcdbas_pdev->dev, "%s: failed to get CPU 0\n", __func__); @@ -275,7 +278,8 @@ int dcdbas_smi_request(struct smi_cmd *smi_cmd) ); out: - set_cpus_allowed_ptr(current, &old_mask); + set_cpus_allowed_ptr(current, old_mask); + free_cpumask_var(old_mask); return ret; } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 5130b72d593..4be3acbaaf9 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -70,7 +70,7 @@ config DRM_I915 select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT - depends on FB + select FB tristate "i915 driver" help Choose this option if you have a system that has Intel 830M, 845G, diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 69aa0ab2840..3795dbc0f50 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -276,6 +276,7 @@ int drm_irq_uninstall(struct drm_device * dev) for (i = 0; i < dev->num_crtcs; i++) { DRM_WAKEUP(&dev->vbl_queue[i]); dev->vblank_enabled[i] = 0; + dev->last_vblank[i] = dev->driver->get_vblank_counter(dev, i); } spin_unlock_irqrestore(&dev->vbl_lock, irqflags); diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c index 803bc9e7ce3..bcc869bc409 100644 --- a/drivers/gpu/drm/drm_memory.c +++ b/drivers/gpu/drm/drm_memory.c @@ -171,9 +171,14 @@ EXPORT_SYMBOL(drm_core_ioremap); void drm_core_ioremap_wc(struct drm_map *map, struct drm_device *dev) { - map->handle = ioremap_wc(map->offset, map->size); + if (drm_core_has_AGP(dev) && + dev->agp && dev->agp->cant_use_aperture && map->type == _DRM_AGP) + map->handle = agp_remap(map->offset, map->size, dev); + else + map->handle = ioremap_wc(map->offset, map->size); } EXPORT_SYMBOL(drm_core_ioremap_wc); + void drm_core_ioremapfree(struct drm_map *map, struct drm_device *dev) { if (!map->handle || !map->size) diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index ee64b7301f6..81f1cff56fd 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -731,8 +731,11 @@ static int i915_getparam(struct drm_device *dev, void *data, case I915_PARAM_HAS_GEM: value = dev_priv->has_gem; break; + case I915_PARAM_NUM_FENCES_AVAIL: + value = dev_priv->num_fence_regs - dev_priv->fence_reg_start; + break; default: - DRM_ERROR("Unknown parameter %d\n", param->param); + DRM_DEBUG("Unknown parameter %d\n", param->param); return -EINVAL; } @@ -764,8 +767,15 @@ static int i915_setparam(struct drm_device *dev, void *data, case I915_SETPARAM_ALLOW_BATCHBUFFER: dev_priv->allow_batchbuffer = param->value; break; + case I915_SETPARAM_NUM_USED_FENCES: + if (param->value > dev_priv->num_fence_regs || + param->value < 0) + return -EINVAL; + /* Userspace can use first N regs */ + dev_priv->fence_reg_start = param->value; + break; default: - DRM_ERROR("unknown parameter %d\n", param->param); + DRM_DEBUG("unknown parameter %d\n", param->param); return -EINVAL; } @@ -966,10 +976,6 @@ static int i915_load_modeset_init(struct drm_device *dev) if (ret) goto kfree_devname; - dev_priv->mm.gtt_mapping = - io_mapping_create_wc(dev->agp->base, - dev->agp->agp_info.aper_size * 1024*1024); - /* Allow hardware batchbuffers unless told otherwise. */ dev_priv->allow_batchbuffer = 1; @@ -1081,6 +1087,23 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto free_priv; } + dev_priv->mm.gtt_mapping = + io_mapping_create_wc(dev->agp->base, + dev->agp->agp_info.aper_size * 1024*1024); + /* Set up a WC MTRR for non-PAT systems. This is more common than + * one would think, because the kernel disables PAT on first + * generation Core chips because WC PAT gets overridden by a UC + * MTRR if present. Even if a UC MTRR isn't present. + */ + dev_priv->mm.gtt_mtrr = mtrr_add(dev->agp->base, + dev->agp->agp_info.aper_size * + 1024 * 1024, + MTRR_TYPE_WRCOMB, 1); + if (dev_priv->mm.gtt_mtrr < 0) { + DRM_INFO("MTRR allocation failed\n. Graphics " + "performance may suffer.\n"); + } + #ifdef CONFIG_HIGHMEM64G /* don't enable GEM on PAE - needs agp + set_memory_* interface fixes */ dev_priv->has_gem = 0; @@ -1089,6 +1112,10 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) dev_priv->has_gem = 1; #endif + dev->driver->get_vblank_counter = i915_get_vblank_counter; + if (IS_GM45(dev)) + dev->driver->get_vblank_counter = gm45_get_vblank_counter; + i915_gem_load(dev); /* Init HWS */ @@ -1145,8 +1172,14 @@ int i915_driver_unload(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + io_mapping_free(dev_priv->mm.gtt_mapping); + if (dev_priv->mm.gtt_mtrr >= 0) { + mtrr_del(dev_priv->mm.gtt_mtrr, dev->agp->base, + dev->agp->agp_info.aper_size * 1024 * 1024); + dev_priv->mm.gtt_mtrr = -1; + } + if (drm_core_check_feature(dev, DRIVER_MODESET)) { - io_mapping_free(dev_priv->mm.gtt_mapping); drm_irq_uninstall(dev); } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f8b3df0926c..aac12ee31a4 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -112,7 +112,6 @@ static struct drm_driver driver = { .suspend = i915_suspend, .resume = i915_resume, .device_is_agp = i915_driver_device_is_agp, - .get_vblank_counter = i915_get_vblank_counter, .enable_vblank = i915_enable_vblank, .disable_vblank = i915_disable_vblank, .irq_preinstall = i915_driver_irq_preinstall, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e1351825200..7325363164f 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -284,6 +284,7 @@ typedef struct drm_i915_private { struct drm_mm gtt_space; struct io_mapping *gtt_mapping; + int gtt_mtrr; /** * List of objects currently involved in rendering from the @@ -534,6 +535,7 @@ extern int i915_vblank_pipe_get(struct drm_device *dev, void *data, extern int i915_enable_vblank(struct drm_device *dev, int crtc); extern void i915_disable_vblank(struct drm_device *dev, int crtc); extern u32 i915_get_vblank_counter(struct drm_device *dev, int crtc); +extern u32 gm45_get_vblank_counter(struct drm_device *dev, int crtc); extern int i915_vblank_swap(struct drm_device *dev, void *data, struct drm_file *file_priv); extern void i915_enable_irq(drm_i915_private_t *dev_priv, u32 mask); @@ -601,6 +603,7 @@ int i915_gem_init_object(struct drm_gem_object *obj); void i915_gem_free_object(struct drm_gem_object *obj); int i915_gem_object_pin(struct drm_gem_object *obj, uint32_t alignment); void i915_gem_object_unpin(struct drm_gem_object *obj); +int i915_gem_object_unbind(struct drm_gem_object *obj); void i915_gem_lastclose(struct drm_device *dev); uint32_t i915_get_gem_seqno(struct drm_device *dev); void i915_gem_retire_requests(struct drm_device *dev); @@ -784,6 +787,11 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller); IS_I945GM(dev) || IS_I965GM(dev) || IS_GM45(dev)) #define I915_NEED_GFX_HWS(dev) (IS_G33(dev) || IS_GM45(dev) || IS_G4X(dev)) +/* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte + * rows, which changed the alignment requirements and fence programming. + */ +#define HAS_128_BYTE_Y_TILING(dev) (IS_I9XX(dev) && !(IS_I915G(dev) || \ + IS_I915GM(dev))) #define SUPPORTS_INTEGRATED_HDMI(dev) (IS_G4X(dev)) #define PRIMARY_RINGBUFFER_SIZE (128*1024) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index debad5c04cc..81857665409 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -52,7 +52,7 @@ static void i915_gem_object_free_page_list(struct drm_gem_object *obj); static int i915_gem_object_wait_rendering(struct drm_gem_object *obj); static int i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment); -static void i915_gem_object_get_fence_reg(struct drm_gem_object *obj); +static int i915_gem_object_get_fence_reg(struct drm_gem_object *obj, bool write); static void i915_gem_clear_fence_reg(struct drm_gem_object *obj); static int i915_gem_evict_something(struct drm_device *dev); static int i915_gem_phys_pwrite(struct drm_device *dev, struct drm_gem_object *obj, @@ -567,6 +567,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) pgoff_t page_offset; unsigned long pfn; int ret = 0; + bool write = !!(vmf->flags & FAULT_FLAG_WRITE); /* We don't use vmf->pgoff since that has the fake offset */ page_offset = ((unsigned long)vmf->virtual_address - vma->vm_start) >> @@ -585,8 +586,13 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) /* Need a new fence register? */ if (obj_priv->fence_reg == I915_FENCE_REG_NONE && - obj_priv->tiling_mode != I915_TILING_NONE) - i915_gem_object_get_fence_reg(obj); + obj_priv->tiling_mode != I915_TILING_NONE) { + ret = i915_gem_object_get_fence_reg(obj, write); + if (ret) { + mutex_unlock(&dev->struct_mutex); + return VM_FAULT_SIGBUS; + } + } pfn = ((dev->agp->base + obj_priv->gtt_offset) >> PAGE_SHIFT) + page_offset; @@ -1211,7 +1217,7 @@ i915_gem_object_wait_rendering(struct drm_gem_object *obj) /** * Unbinds an object from the GTT aperture. */ -static int +int i915_gem_object_unbind(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; @@ -1445,21 +1451,26 @@ static void i915_write_fence_reg(struct drm_i915_fence_reg *reg) drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj_priv = obj->driver_private; int regnum = obj_priv->fence_reg; + int tile_width; uint32_t val; uint32_t pitch_val; if ((obj_priv->gtt_offset & ~I915_FENCE_START_MASK) || (obj_priv->gtt_offset & (obj->size - 1))) { - WARN(1, "%s: object not 1M or size aligned\n", __func__); + WARN(1, "%s: object 0x%08x not 1M or size (0x%zx) aligned\n", + __func__, obj_priv->gtt_offset, obj->size); return; } - if (obj_priv->tiling_mode == I915_TILING_Y && (IS_I945G(dev) || - IS_I945GM(dev) || - IS_G33(dev))) - pitch_val = (obj_priv->stride / 128) - 1; + if (obj_priv->tiling_mode == I915_TILING_Y && + HAS_128_BYTE_Y_TILING(dev)) + tile_width = 128; else - pitch_val = (obj_priv->stride / 512) - 1; + tile_width = 512; + + /* Note: pitch better be a power of two tile widths */ + pitch_val = obj_priv->stride / tile_width; + pitch_val = ffs(pitch_val) - 1; val = obj_priv->gtt_offset; if (obj_priv->tiling_mode == I915_TILING_Y) @@ -1483,7 +1494,8 @@ static void i830_write_fence_reg(struct drm_i915_fence_reg *reg) if ((obj_priv->gtt_offset & ~I915_FENCE_START_MASK) || (obj_priv->gtt_offset & (obj->size - 1))) { - WARN(1, "%s: object not 1M or size aligned\n", __func__); + WARN(1, "%s: object 0x%08x not 1M or size aligned\n", + __func__, obj_priv->gtt_offset); return; } @@ -1503,6 +1515,7 @@ static void i830_write_fence_reg(struct drm_i915_fence_reg *reg) /** * i915_gem_object_get_fence_reg - set up a fence reg for an object * @obj: object to map through a fence reg + * @write: object is about to be written * * When mapping objects through the GTT, userspace wants to be able to write * to them without having to worry about swizzling if the object is tiled. @@ -1513,8 +1526,8 @@ static void i830_write_fence_reg(struct drm_i915_fence_reg *reg) * It then sets up the reg based on the object's properties: address, pitch * and tiling format. */ -static void -i915_gem_object_get_fence_reg(struct drm_gem_object *obj) +static int +i915_gem_object_get_fence_reg(struct drm_gem_object *obj, bool write) { struct drm_device *dev = obj->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1527,12 +1540,18 @@ i915_gem_object_get_fence_reg(struct drm_gem_object *obj) WARN(1, "allocating a fence for non-tiled object?\n"); break; case I915_TILING_X: - WARN(obj_priv->stride & (512 - 1), - "object is X tiled but has non-512B pitch\n"); + if (!obj_priv->stride) + return -EINVAL; + WARN((obj_priv->stride & (512 - 1)), + "object 0x%08x is X tiled but has non-512B pitch\n", + obj_priv->gtt_offset); break; case I915_TILING_Y: - WARN(obj_priv->stride & (128 - 1), - "object is Y tiled but has non-128B pitch\n"); + if (!obj_priv->stride) + return -EINVAL; + WARN((obj_priv->stride & (128 - 1)), + "object 0x%08x is Y tiled but has non-128B pitch\n", + obj_priv->gtt_offset); break; } @@ -1563,10 +1582,11 @@ try_again: * objects to finish before trying again. */ if (i == dev_priv->num_fence_regs) { - ret = i915_gem_object_wait_rendering(reg->obj); + ret = i915_gem_object_set_to_gtt_domain(reg->obj, 0); if (ret) { - WARN(ret, "wait_rendering failed: %d\n", ret); - return; + WARN(ret != -ERESTARTSYS, + "switch to GTT domain failed: %d\n", ret); + return ret; } goto try_again; } @@ -1591,6 +1611,8 @@ try_again: i915_write_fence_reg(reg); else i830_write_fence_reg(reg); + + return 0; } /** @@ -1631,7 +1653,7 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment) if (dev_priv->mm.suspended) return -EBUSY; if (alignment == 0) - alignment = PAGE_SIZE; + alignment = i915_gem_get_gtt_alignment(obj); if (alignment & (PAGE_SIZE - 1)) { DRM_ERROR("Invalid object alignment requested %u\n", alignment); return -EINVAL; @@ -2652,6 +2674,14 @@ i915_gem_object_pin(struct drm_gem_object *obj, uint32_t alignment) DRM_ERROR("Failure to bind: %d", ret); return ret; } + /* + * Pre-965 chips need a fence register set up in order to + * properly handle tiled surfaces. + */ + if (!IS_I965G(dev) && + obj_priv->fence_reg == I915_FENCE_REG_NONE && + obj_priv->tiling_mode != I915_TILING_NONE) + i915_gem_object_get_fence_reg(obj, true); } obj_priv->pin_count++; @@ -3229,10 +3259,6 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, dev_priv->mm.wedged = 0; } - dev_priv->mm.gtt_mapping = io_mapping_create_wc(dev->agp->base, - dev->agp->agp_info.aper_size - * 1024 * 1024); - mutex_lock(&dev->struct_mutex); dev_priv->mm.suspended = 0; @@ -3255,7 +3281,6 @@ int i915_gem_leavevt_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - drm_i915_private_t *dev_priv = dev->dev_private; int ret; if (drm_core_check_feature(dev, DRIVER_MODESET)) @@ -3264,7 +3289,6 @@ i915_gem_leavevt_ioctl(struct drm_device *dev, void *data, ret = i915_gem_idle(dev); drm_irq_uninstall(dev); - io_mapping_free(dev_priv->mm.gtt_mapping); return ret; } @@ -3273,6 +3297,9 @@ i915_gem_lastclose(struct drm_device *dev) { int ret; + if (drm_core_check_feature(dev, DRIVER_MODESET)) + return; + ret = i915_gem_idle(dev); if (ret) DRM_ERROR("failed to idle hardware: %d\n", ret); @@ -3294,7 +3321,7 @@ i915_gem_load(struct drm_device *dev) /* Old X drivers will take 0-2 for front, back, depth buffers */ dev_priv->fence_reg_start = 3; - if (IS_I965G(dev)) + if (IS_I965G(dev) || IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) dev_priv->num_fence_regs = 16; else dev_priv->num_fence_regs = 8; diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 241f39b7f46..fa1685cba84 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -173,6 +173,73 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev) dev_priv->mm.bit_6_swizzle_y = swizzle_y; } + +/** + * Returns the size of the fence for a tiled object of the given size. + */ +static int +i915_get_fence_size(struct drm_device *dev, int size) +{ + int i; + int start; + + if (IS_I965G(dev)) { + /* The 965 can have fences at any page boundary. */ + return ALIGN(size, 4096); + } else { + /* Align the size to a power of two greater than the smallest + * fence size. + */ + if (IS_I9XX(dev)) + start = 1024 * 1024; + else + start = 512 * 1024; + + for (i = start; i < size; i <<= 1) + ; + + return i; + } +} + +/* Check pitch constriants for all chips & tiling formats */ +static bool +i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode) +{ + int tile_width; + + /* Linear is always fine */ + if (tiling_mode == I915_TILING_NONE) + return true; + + if (tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)) + tile_width = 128; + else + tile_width = 512; + + /* 965+ just needs multiples of tile width */ + if (IS_I965G(dev)) { + if (stride & (tile_width - 1)) + return false; + return true; + } + + /* Pre-965 needs power of two tile widths */ + if (stride < tile_width) + return false; + + if (stride & (stride - 1)) + return false; + + /* We don't handle the aperture area covered by the fence being bigger + * than the object size. + */ + if (i915_get_fence_size(dev, size) != size) + return false; + + return true; +} + /** * Sets the tiling mode of an object, returning the required swizzling of * bit 6 of addresses in the object. @@ -191,6 +258,11 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, return -EINVAL; obj_priv = obj->driver_private; + if (!i915_tiling_ok(dev, args->stride, obj->size, args->tiling_mode)) { + drm_gem_object_unreference(obj); + return -EINVAL; + } + mutex_lock(&dev->struct_mutex); if (args->tiling_mode == I915_TILING_NONE) { @@ -207,7 +279,24 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, args->swizzle_mode = I915_BIT_6_SWIZZLE_NONE; } } - obj_priv->tiling_mode = args->tiling_mode; + if (args->tiling_mode != obj_priv->tiling_mode) { + int ret; + + /* Unbind the object, as switching tiling means we're + * switching the cache organization due to fencing, probably. + */ + ret = i915_gem_object_unbind(obj); + if (ret != 0) { + WARN(ret != -ERESTARTSYS, + "failed to unbind object for tiling switch"); + args->tiling_mode = obj_priv->tiling_mode; + mutex_unlock(&dev->struct_mutex); + drm_gem_object_unreference(obj); + + return ret; + } + obj_priv->tiling_mode = args->tiling_mode; + } obj_priv->stride = args->stride; mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 6290219de6c..548ff2c6643 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -174,6 +174,19 @@ u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) return count; } +u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) +{ + drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; + int reg = pipe ? PIPEB_FRMCOUNT_GM45 : PIPEA_FRMCOUNT_GM45; + + if (!i915_pipe_enabled(dev, pipe)) { + DRM_ERROR("trying to get vblank count for disabled pipe %d\n", pipe); + return 0; + } + + return I915_READ(reg); +} + irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) { struct drm_device *dev = (struct drm_device *) arg; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 273162579e1..9d6539a868b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -186,12 +186,12 @@ #define FENCE_REG_830_0 0x2000 #define I830_FENCE_START_MASK 0x07f80000 #define I830_FENCE_TILING_Y_SHIFT 12 -#define I830_FENCE_SIZE_BITS(size) ((get_order(size >> 19) - 1) << 8) +#define I830_FENCE_SIZE_BITS(size) ((ffs((size) >> 19) - 1) << 8) #define I830_FENCE_PITCH_SHIFT 4 #define I830_FENCE_REG_VALID (1<<0) #define I915_FENCE_START_MASK 0x0ff00000 -#define I915_FENCE_SIZE_BITS(size) ((get_order(size >> 20) - 1) << 8) +#define I915_FENCE_SIZE_BITS(size) ((ffs((size) >> 20) - 1) << 8) #define FENCE_REG_965_0 0x03000 #define I965_FENCE_PITCH_SHIFT 2 @@ -1371,6 +1371,9 @@ #define PIPE_FRAME_LOW_SHIFT 24 #define PIPE_PIXEL_MASK 0x00ffffff #define PIPE_PIXEL_SHIFT 0 +/* GM45+ just has to be different */ +#define PIPEA_FRMCOUNT_GM45 0x70040 +#define PIPEA_FLIPCOUNT_GM45 0x70044 /* Cursor A & B regs */ #define CURACNTR 0x70080 @@ -1439,6 +1442,9 @@ #define PIPEBSTAT 0x71024 #define PIPEBFRAMEHIGH 0x71040 #define PIPEBFRAMEPIXEL 0x71044 +#define PIPEB_FRMCOUNT_GM45 0x71040 +#define PIPEB_FLIPCOUNT_GM45 0x71044 + /* Display B control */ #define DSPBCNTR 0x71180 diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 31c3732b7a6..bbdd72909a1 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -755,6 +755,8 @@ static void intel_crtc_mode_set(struct drm_crtc *crtc, case INTEL_OUTPUT_SDVO: case INTEL_OUTPUT_HDMI: is_sdvo = true; + if (intel_output->needs_tv_clock) + is_tv = true; break; case INTEL_OUTPUT_DVO: is_dvo = true; @@ -1452,6 +1454,7 @@ static int intel_connector_clones(struct drm_device *dev, int type_mask) static void intel_setup_outputs(struct drm_device *dev) { + struct drm_i915_private *dev_priv = dev->dev_private; struct drm_connector *connector; intel_crt_init(dev); @@ -1463,13 +1466,16 @@ static void intel_setup_outputs(struct drm_device *dev) if (IS_I9XX(dev)) { int found; - found = intel_sdvo_init(dev, SDVOB); - if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) - intel_hdmi_init(dev, SDVOB); - - found = intel_sdvo_init(dev, SDVOC); - if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) - intel_hdmi_init(dev, SDVOC); + if (I915_READ(SDVOB) & SDVO_DETECTED) { + found = intel_sdvo_init(dev, SDVOB); + if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) + intel_hdmi_init(dev, SDVOB); + } + if (!IS_G4X(dev) || (I915_READ(SDVOB) & SDVO_DETECTED)) { + found = intel_sdvo_init(dev, SDVOC); + if (!found && SUPPORTS_INTEGRATED_HDMI(dev)) + intel_hdmi_init(dev, SDVOC); + } } else intel_dvo_init(dev); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 8a4cc50c5b4..957daef8edf 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -82,6 +82,7 @@ struct intel_output { struct intel_i2c_chan *i2c_bus; /* for control functions */ struct intel_i2c_chan *ddc_bus; /* for DDC only stuff */ bool load_detect_temp; + bool needs_tv_clock; void *dev_priv; }; diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index b36a5214d8d..6d4f9126535 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -27,6 +27,7 @@ * Jesse Barnes <jesse.barnes@intel.com> */ +#include <linux/dmi.h> #include <linux/i2c.h> #include "drmP.h" #include "drm.h" @@ -311,10 +312,8 @@ static int intel_lvds_get_modes(struct drm_connector *connector) if (dev_priv->panel_fixed_mode != NULL) { struct drm_display_mode *mode; - mutex_lock(&dev->mode_config.mutex); mode = drm_mode_duplicate(dev, dev_priv->panel_fixed_mode); drm_mode_probed_add(connector, mode); - mutex_unlock(&dev->mode_config.mutex); return 1; } @@ -405,6 +404,16 @@ void intel_lvds_init(struct drm_device *dev) u32 lvds; int pipe; + /* Blacklist machines that we know falsely report LVDS. */ + /* FIXME: add a check for the Aopen Mini PC */ + + /* Apple Mac Mini Core Duo and Mac Mini Core 2 Duo */ + if(dmi_match(DMI_PRODUCT_NAME, "Macmini1,1") || + dmi_match(DMI_PRODUCT_NAME, "Macmini2,1")) { + DRM_DEBUG("Skipping LVDS initialization for Apple Mac Mini\n"); + return; + } + intel_output = kzalloc(sizeof(struct intel_output), GFP_KERNEL); if (!intel_output) { return; @@ -458,7 +467,7 @@ void intel_lvds_init(struct drm_device *dev) dev_priv->panel_fixed_mode = drm_mode_duplicate(dev, scan); mutex_unlock(&dev->mode_config.mutex); - goto out; /* FIXME: check for quirks */ + goto out; } mutex_unlock(&dev->mode_config.mutex); } @@ -492,7 +501,7 @@ void intel_lvds_init(struct drm_device *dev) if (dev_priv->panel_fixed_mode) { dev_priv->panel_fixed_mode->type |= DRM_MODE_TYPE_PREFERRED; - goto out; /* FIXME: check for quirks */ + goto out; } } @@ -500,38 +509,6 @@ void intel_lvds_init(struct drm_device *dev) if (!dev_priv->panel_fixed_mode) goto failed; - /* FIXME: detect aopen & mac mini type stuff automatically? */ - /* - * Blacklist machines with BIOSes that list an LVDS panel without - * actually having one. - */ - if (IS_I945GM(dev)) { - /* aopen mini pc */ - if (dev->pdev->subsystem_vendor == 0xa0a0) - goto failed; - - if ((dev->pdev->subsystem_vendor == 0x8086) && - (dev->pdev->subsystem_device == 0x7270)) { - /* It's a Mac Mini or Macbook Pro. - * - * Apple hardware is out to get us. The macbook pro - * has a real LVDS panel, but the mac mini does not, - * and they have the same device IDs. We'll - * distinguish by panel size, on the assumption - * that Apple isn't about to make any machines with an - * 800x600 display. - */ - - if (dev_priv->panel_fixed_mode != NULL && - dev_priv->panel_fixed_mode->hdisplay == 800 && - dev_priv->panel_fixed_mode->vdisplay == 600) { - DRM_DEBUG("Suspected Mac Mini, ignoring the LVDS\n"); - goto failed; - } - } - } - - out: drm_sysfs_connector_add(connector); return; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 40721546910..a30508b639b 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -40,13 +40,59 @@ struct intel_sdvo_priv { struct intel_i2c_chan *i2c_bus; int slaveaddr; + + /* Register for the SDVO device: SDVOB or SDVOC */ int output_device; - u16 active_outputs; + /* Active outputs controlled by this SDVO output */ + uint16_t controlled_output; + /* + * Capabilities of the SDVO device returned by + * i830_sdvo_get_capabilities() + */ struct intel_sdvo_caps caps; + + /* Pixel clock limitations reported by the SDVO device, in kHz */ int pixel_clock_min, pixel_clock_max; + /** + * This is set if we're going to treat the device as TV-out. + * + * While we have these nice friendly flags for output types that ought + * to decide this for us, the S-Video output on our HDMI+S-Video card + * shows up as RGB1 (VGA). + */ + bool is_tv; + + /** + * This is set if we treat the device as HDMI, instead of DVI. + */ + bool is_hdmi; + + /** + * Returned SDTV resolutions allowed for the current format, if the + * device reported it. + */ + struct intel_sdvo_sdtv_resolution_reply sdtv_resolutions; + + /** + * Current selected TV format. + * + * This is stored in the same structure that's passed to the device, for + * convenience. + */ + struct intel_sdvo_tv_format tv_format; + + /* + * supported encoding mode, used to determine whether HDMI is + * supported + */ + struct intel_sdvo_encode encode; + + /* DDC bus used by this SDVO output */ + uint8_t ddc_bus; + int save_sdvo_mult; u16 save_active_outputs; struct intel_sdvo_dtd save_input_dtd_1, save_input_dtd_2; @@ -148,8 +194,8 @@ static bool intel_sdvo_write_byte(struct intel_output *intel_output, int addr, #define SDVO_CMD_NAME_ENTRY(cmd) {cmd, #cmd} /** Mapping of command numbers to names, for debug output */ const static struct _sdvo_cmd_name { - u8 cmd; - char *name; + u8 cmd; + char *name; } sdvo_cmd_names[] = { SDVO_CMD_NAME_ENTRY(SDVO_CMD_RESET), SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_DEVICE_CAPS), @@ -186,8 +232,35 @@ const static struct _sdvo_cmd_name { SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_SUPPORTED_TV_FORMATS), SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_TV_FORMAT), SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_TV_FORMAT), - SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_TV_RESOLUTION_SUPPORT), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_SUPPORTED_POWER_STATES), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_POWER_STATE), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_ENCODER_POWER_STATE), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_DISPLAY_POWER_STATE), SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_CONTROL_BUS_SWITCH), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_SDTV_RESOLUTION_SUPPORT), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_SCALED_HDTV_RESOLUTION_SUPPORT), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_SUPPORTED_ENHANCEMENTS), + /* HDMI op code */ + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_SUPP_ENCODE), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_ENCODE), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_ENCODE), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_PIXEL_REPLI), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_PIXEL_REPLI), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_COLORIMETRY_CAP), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_COLORIMETRY), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_COLORIMETRY), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_AUDIO_ENCRYPT_PREFER), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_AUDIO_STAT), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_AUDIO_STAT), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_HBUF_INDEX), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_HBUF_INDEX), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_HBUF_INFO), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_HBUF_AV_SPLIT), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_HBUF_AV_SPLIT), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_HBUF_TXRATE), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_HBUF_TXRATE), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_SET_HBUF_DATA), + SDVO_CMD_NAME_ENTRY(SDVO_CMD_GET_HBUF_DATA), }; #define SDVO_NAME(dev_priv) ((dev_priv)->output_device == SDVOB ? "SDVOB" : "SDVOC") @@ -506,6 +579,50 @@ static bool intel_sdvo_set_output_timing(struct intel_output *intel_output, SDVO_CMD_SET_OUTPUT_TIMINGS_PART1, dtd); } +static bool +intel_sdvo_create_preferred_input_timing(struct intel_output *output, + uint16_t clock, + uint16_t width, + uint16_t height) +{ + struct intel_sdvo_preferred_input_timing_args args; + uint8_t status; + + args.clock = clock; + args.width = width; + args.height = height; + intel_sdvo_write_cmd(output, SDVO_CMD_CREATE_PREFERRED_INPUT_TIMING, + &args, sizeof(args)); + status = intel_sdvo_read_response(output, NULL, 0); + if (status != SDVO_CMD_STATUS_SUCCESS) + return false; + + return true; +} + +static bool intel_sdvo_get_preferred_input_timing(struct intel_output *output, + struct intel_sdvo_dtd *dtd) +{ + bool status; + + intel_sdvo_write_cmd(output, SDVO_CMD_GET_PREFERRED_INPUT_TIMING_PART1, + NULL, 0); + + status = intel_sdvo_read_response(output, &dtd->part1, + sizeof(dtd->part1)); + if (status != SDVO_CMD_STATUS_SUCCESS) + return false; + + intel_sdvo_write_cmd(output, SDVO_CMD_GET_PREFERRED_INPUT_TIMING_PART2, + NULL, 0); + + status = intel_sdvo_read_response(output, &dtd->part2, + sizeof(dtd->part2)); + if (status != SDVO_CMD_STATUS_SUCCESS) + return false; + + return false; +} static int intel_sdvo_get_clock_rate_mult(struct intel_output *intel_output) { @@ -536,36 +653,12 @@ static bool intel_sdvo_set_clock_rate_mult(struct intel_output *intel_output, u8 return true; } -static bool intel_sdvo_mode_fixup(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - /* Make the CRTC code factor in the SDVO pixel multiplier. The SDVO - * device will be told of the multiplier during mode_set. - */ - adjusted_mode->clock *= intel_sdvo_get_pixel_multiplier(mode); - return true; -} - -static void intel_sdvo_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) +static void intel_sdvo_get_dtd_from_mode(struct intel_sdvo_dtd *dtd, + struct drm_display_mode *mode) { - struct drm_device *dev = encoder->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_crtc *crtc = encoder->crtc; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_output *intel_output = enc_to_intel_output(encoder); - struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; - u16 width, height; - u16 h_blank_len, h_sync_len, v_blank_len, v_sync_len; - u16 h_sync_offset, v_sync_offset; - u32 sdvox; - struct intel_sdvo_dtd output_dtd; - int sdvo_pixel_multiply; - - if (!mode) - return; + uint16_t width, height; + uint16_t h_blank_len, h_sync_len, v_blank_len, v_sync_len; + uint16_t h_sync_offset, v_sync_offset; width = mode->crtc_hdisplay; height = mode->crtc_vdisplay; @@ -580,93 +673,423 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder, h_sync_offset = mode->crtc_hsync_start - mode->crtc_hblank_start; v_sync_offset = mode->crtc_vsync_start - mode->crtc_vblank_start; - output_dtd.part1.clock = mode->clock / 10; - output_dtd.part1.h_active = width & 0xff; - output_dtd.part1.h_blank = h_blank_len & 0xff; - output_dtd.part1.h_high = (((width >> 8) & 0xf) << 4) | + dtd->part1.clock = mode->clock / 10; + dtd->part1.h_active = width & 0xff; + dtd->part1.h_blank = h_blank_len & 0xff; + dtd->part1.h_high = (((width >> 8) & 0xf) << 4) | ((h_blank_len >> 8) & 0xf); - output_dtd.part1.v_active = height & 0xff; - output_dtd.part1.v_blank = v_blank_len & 0xff; - output_dtd.part1.v_high = (((height >> 8) & 0xf) << 4) | + dtd->part1.v_active = height & 0xff; + dtd->part1.v_blank = v_blank_len & 0xff; + dtd->part1.v_high = (((height >> 8) & 0xf) << 4) | ((v_blank_len >> 8) & 0xf); - output_dtd.part2.h_sync_off = h_sync_offset; - output_dtd.part2.h_sync_width = h_sync_len & 0xff; - output_dtd.part2.v_sync_off_width = (v_sync_offset & 0xf) << 4 | + dtd->part2.h_sync_off = h_sync_offset; + dtd->part2.h_sync_width = h_sync_len & 0xff; + dtd->part2.v_sync_off_width = (v_sync_offset & 0xf) << 4 | (v_sync_len & 0xf); - output_dtd.part2.sync_off_width_high = ((h_sync_offset & 0x300) >> 2) | + dtd->part2.sync_off_width_high = ((h_sync_offset & 0x300) >> 2) | ((h_sync_len & 0x300) >> 4) | ((v_sync_offset & 0x30) >> 2) | ((v_sync_len & 0x30) >> 4); - output_dtd.part2.dtd_flags = 0x18; + dtd->part2.dtd_flags = 0x18; if (mode->flags & DRM_MODE_FLAG_PHSYNC) - output_dtd.part2.dtd_flags |= 0x2; + dtd->part2.dtd_flags |= 0x2; if (mode->flags & DRM_MODE_FLAG_PVSYNC) - output_dtd.part2.dtd_flags |= 0x4; + dtd->part2.dtd_flags |= 0x4; + + dtd->part2.sdvo_flags = 0; + dtd->part2.v_sync_off_high = v_sync_offset & 0xc0; + dtd->part2.reserved = 0; +} + +static void intel_sdvo_get_mode_from_dtd(struct drm_display_mode * mode, + struct intel_sdvo_dtd *dtd) +{ + uint16_t width, height; + uint16_t h_blank_len, h_sync_len, v_blank_len, v_sync_len; + uint16_t h_sync_offset, v_sync_offset; + + width = mode->crtc_hdisplay; + height = mode->crtc_vdisplay; + + /* do some mode translations */ + h_blank_len = mode->crtc_hblank_end - mode->crtc_hblank_start; + h_sync_len = mode->crtc_hsync_end - mode->crtc_hsync_start; + + v_blank_len = mode->crtc_vblank_end - mode->crtc_vblank_start; + v_sync_len = mode->crtc_vsync_end - mode->crtc_vsync_start; + + h_sync_offset = mode->crtc_hsync_start - mode->crtc_hblank_start; + v_sync_offset = mode->crtc_vsync_start - mode->crtc_vblank_start; + + mode->hdisplay = dtd->part1.h_active; + mode->hdisplay += ((dtd->part1.h_high >> 4) & 0x0f) << 8; + mode->hsync_start = mode->hdisplay + dtd->part2.h_sync_off; + mode->hsync_start += (dtd->part2.sync_off_width_high & 0xa0) << 2; + mode->hsync_end = mode->hsync_start + dtd->part2.h_sync_width; + mode->hsync_end += (dtd->part2.sync_off_width_high & 0x30) << 4; + mode->htotal = mode->hdisplay + dtd->part1.h_blank; + mode->htotal += (dtd->part1.h_high & 0xf) << 8; + + mode->vdisplay = dtd->part1.v_active; + mode->vdisplay += ((dtd->part1.v_high >> 4) & 0x0f) << 8; + mode->vsync_start = mode->vdisplay; + mode->vsync_start += (dtd->part2.v_sync_off_width >> 4) & 0xf; + mode->vsync_start += (dtd->part2.sync_off_width_high & 0x0a) << 2; + mode->vsync_start += dtd->part2.v_sync_off_high & 0xc0; + mode->vsync_end = mode->vsync_start + + (dtd->part2.v_sync_off_width & 0xf); + mode->vsync_end += (dtd->part2.sync_off_width_high & 0x3) << 4; + mode->vtotal = mode->vdisplay + dtd->part1.v_blank; + mode->vtotal += (dtd->part1.v_high & 0xf) << 8; + + mode->clock = dtd->part1.clock * 10; + + mode->flags &= (DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC); + if (dtd->part2.dtd_flags & 0x2) + mode->flags |= DRM_MODE_FLAG_PHSYNC; + if (dtd->part2.dtd_flags & 0x4) + mode->flags |= DRM_MODE_FLAG_PVSYNC; +} + +static bool intel_sdvo_get_supp_encode(struct intel_output *output, + struct intel_sdvo_encode *encode) +{ + uint8_t status; + + intel_sdvo_write_cmd(output, SDVO_CMD_GET_SUPP_ENCODE, NULL, 0); + status = intel_sdvo_read_response(output, encode, sizeof(*encode)); + if (status != SDVO_CMD_STATUS_SUCCESS) { /* non-support means DVI */ + memset(encode, 0, sizeof(*encode)); + return false; + } + + return true; +} + +static bool intel_sdvo_set_encode(struct intel_output *output, uint8_t mode) +{ + uint8_t status; + + intel_sdvo_write_cmd(output, SDVO_CMD_SET_ENCODE, &mode, 1); + status = intel_sdvo_read_response(output, NULL, 0); + + return (status == SDVO_CMD_STATUS_SUCCESS); +} + +static bool intel_sdvo_set_colorimetry(struct intel_output *output, + uint8_t mode) +{ + uint8_t status; + + intel_sdvo_write_cmd(output, SDVO_CMD_SET_COLORIMETRY, &mode, 1); + status = intel_sdvo_read_response(output, NULL, 0); + + return (status == SDVO_CMD_STATUS_SUCCESS); +} + +#if 0 +static void intel_sdvo_dump_hdmi_buf(struct intel_output *output) +{ + int i, j; + uint8_t set_buf_index[2]; + uint8_t av_split; + uint8_t buf_size; + uint8_t buf[48]; + uint8_t *pos; + + intel_sdvo_write_cmd(output, SDVO_CMD_GET_HBUF_AV_SPLIT, NULL, 0); + intel_sdvo_read_response(output, &av_split, 1); + + for (i = 0; i <= av_split; i++) { + set_buf_index[0] = i; set_buf_index[1] = 0; + intel_sdvo_write_cmd(output, SDVO_CMD_SET_HBUF_INDEX, + set_buf_index, 2); + intel_sdvo_write_cmd(output, SDVO_CMD_GET_HBUF_INFO, NULL, 0); + intel_sdvo_read_response(output, &buf_size, 1); + + pos = buf; + for (j = 0; j <= buf_size; j += 8) { + intel_sdvo_write_cmd(output, SDVO_CMD_GET_HBUF_DATA, + NULL, 0); + intel_sdvo_read_response(output, pos, 8); + pos += 8; + } + } +} +#endif + +static void intel_sdvo_set_hdmi_buf(struct intel_output *output, int index, + uint8_t *data, int8_t size, uint8_t tx_rate) +{ + uint8_t set_buf_index[2]; + + set_buf_index[0] = index; + set_buf_index[1] = 0; + + intel_sdvo_write_cmd(output, SDVO_CMD_SET_HBUF_INDEX, set_buf_index, 2); + + for (; size > 0; size -= 8) { + intel_sdvo_write_cmd(output, SDVO_CMD_SET_HBUF_DATA, data, 8); + data += 8; + } + + intel_sdvo_write_cmd(output, SDVO_CMD_SET_HBUF_TXRATE, &tx_rate, 1); +} + +static uint8_t intel_sdvo_calc_hbuf_csum(uint8_t *data, uint8_t size) +{ + uint8_t csum = 0; + int i; + + for (i = 0; i < size; i++) + csum += data[i]; + + return 0x100 - csum; +} + +#define DIP_TYPE_AVI 0x82 +#define DIP_VERSION_AVI 0x2 +#define DIP_LEN_AVI 13 + +struct dip_infoframe { + uint8_t type; + uint8_t version; + uint8_t len; + uint8_t checksum; + union { + struct { + /* Packet Byte #1 */ + uint8_t S:2; + uint8_t B:2; + uint8_t A:1; + uint8_t Y:2; + uint8_t rsvd1:1; + /* Packet Byte #2 */ + uint8_t R:4; + uint8_t M:2; + uint8_t C:2; + /* Packet Byte #3 */ + uint8_t SC:2; + uint8_t Q:2; + uint8_t EC:3; + uint8_t ITC:1; + /* Packet Byte #4 */ + uint8_t VIC:7; + uint8_t rsvd2:1; + /* Packet Byte #5 */ + uint8_t PR:4; + uint8_t rsvd3:4; + /* Packet Byte #6~13 */ + uint16_t top_bar_end; + uint16_t bottom_bar_start; + uint16_t left_bar_end; + uint16_t right_bar_start; + } avi; + struct { + /* Packet Byte #1 */ + uint8_t channel_count:3; + uint8_t rsvd1:1; + uint8_t coding_type:4; + /* Packet Byte #2 */ + uint8_t sample_size:2; /* SS0, SS1 */ + uint8_t sample_frequency:3; + uint8_t rsvd2:3; + /* Packet Byte #3 */ + uint8_t coding_type_private:5; + uint8_t rsvd3:3; + /* Packet Byte #4 */ + uint8_t channel_allocation; + /* Packet Byte #5 */ + uint8_t rsvd4:3; + uint8_t level_shift:4; + uint8_t downmix_inhibit:1; + } audio; + uint8_t payload[28]; + } __attribute__ ((packed)) u; +} __attribute__((packed)); + +static void intel_sdvo_set_avi_infoframe(struct intel_output *output, + struct drm_display_mode * mode) +{ + struct dip_infoframe avi_if = { + .type = DIP_TYPE_AVI, + .version = DIP_VERSION_AVI, + .len = DIP_LEN_AVI, + }; + + avi_if.checksum = intel_sdvo_calc_hbuf_csum((uint8_t *)&avi_if, + 4 + avi_if.len); + intel_sdvo_set_hdmi_buf(output, 1, (uint8_t *)&avi_if, 4 + avi_if.len, + SDVO_HBUF_TX_VSYNC); +} + +static bool intel_sdvo_mode_fixup(struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + struct intel_output *output = enc_to_intel_output(encoder); + struct intel_sdvo_priv *dev_priv = output->dev_priv; - output_dtd.part2.sdvo_flags = 0; - output_dtd.part2.v_sync_off_high = v_sync_offset & 0xc0; - output_dtd.part2.reserved = 0; + if (!dev_priv->is_tv) { + /* Make the CRTC code factor in the SDVO pixel multiplier. The + * SDVO device will be told of the multiplier during mode_set. + */ + adjusted_mode->clock *= intel_sdvo_get_pixel_multiplier(mode); + } else { + struct intel_sdvo_dtd output_dtd; + bool success; + + /* We need to construct preferred input timings based on our + * output timings. To do that, we have to set the output + * timings, even though this isn't really the right place in + * the sequence to do it. Oh well. + */ + + + /* Set output timings */ + intel_sdvo_get_dtd_from_mode(&output_dtd, mode); + intel_sdvo_set_target_output(output, + dev_priv->controlled_output); + intel_sdvo_set_output_timing(output, &output_dtd); + + /* Set the input timing to the screen. Assume always input 0. */ + intel_sdvo_set_target_input(output, true, false); + + + success = intel_sdvo_create_preferred_input_timing(output, + mode->clock / 10, + mode->hdisplay, + mode->vdisplay); + if (success) { + struct intel_sdvo_dtd input_dtd; - /* Set the output timing to the screen */ - intel_sdvo_set_target_output(intel_output, sdvo_priv->active_outputs); - intel_sdvo_set_output_timing(intel_output, &output_dtd); + intel_sdvo_get_preferred_input_timing(output, + &input_dtd); + intel_sdvo_get_mode_from_dtd(adjusted_mode, &input_dtd); + + } else { + return false; + } + } + return true; +} + +static void intel_sdvo_mode_set(struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + struct drm_device *dev = encoder->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_crtc *crtc = encoder->crtc; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_output *output = enc_to_intel_output(encoder); + struct intel_sdvo_priv *sdvo_priv = output->dev_priv; + u32 sdvox = 0; + int sdvo_pixel_multiply; + struct intel_sdvo_in_out_map in_out; + struct intel_sdvo_dtd input_dtd; + u8 status; + + if (!mode) + return; + + /* First, set the input mapping for the first input to our controlled + * output. This is only correct if we're a single-input device, in + * which case the first input is the output from the appropriate SDVO + * channel on the motherboard. In a two-input device, the first input + * will be SDVOB and the second SDVOC. + */ + in_out.in0 = sdvo_priv->controlled_output; + in_out.in1 = 0; + + intel_sdvo_write_cmd(output, SDVO_CMD_SET_IN_OUT_MAP, + &in_out, sizeof(in_out)); + status = intel_sdvo_read_response(output, NULL, 0); + + if (sdvo_priv->is_hdmi) { + intel_sdvo_set_avi_infoframe(output, mode); + sdvox |= SDVO_AUDIO_ENABLE; + } + + intel_sdvo_get_dtd_from_mode(&input_dtd, mode); + + /* If it's a TV, we already set the output timing in mode_fixup. + * Otherwise, the output timing is equal to the input timing. + */ + if (!sdvo_priv->is_tv) { + /* Set the output timing to the screen */ + intel_sdvo_set_target_output(output, + sdvo_priv->controlled_output); + intel_sdvo_set_output_timing(output, &input_dtd); + } /* Set the input timing to the screen. Assume always input 0. */ - intel_sdvo_set_target_input(intel_output, true, false); + intel_sdvo_set_target_input(output, true, false); - /* We would like to use i830_sdvo_create_preferred_input_timing() to + /* We would like to use intel_sdvo_create_preferred_input_timing() to * provide the device with a timing it can support, if it supports that * feature. However, presumably we would need to adjust the CRTC to * output the preferred timing, and we don't support that currently. */ - intel_sdvo_set_input_timing(intel_output, &output_dtd); +#if 0 + success = intel_sdvo_create_preferred_input_timing(output, clock, + width, height); + if (success) { + struct intel_sdvo_dtd *input_dtd; + + intel_sdvo_get_preferred_input_timing(output, &input_dtd); + intel_sdvo_set_input_timing(output, &input_dtd); + } +#else + intel_sdvo_set_input_timing(output, &input_dtd); +#endif switch (intel_sdvo_get_pixel_multiplier(mode)) { case 1: - intel_sdvo_set_clock_rate_mult(intel_output, + intel_sdvo_set_clock_rate_mult(output, SDVO_CLOCK_RATE_MULT_1X); break; case 2: - intel_sdvo_set_clock_rate_mult(intel_output, + intel_sdvo_set_clock_rate_mult(output, SDVO_CLOCK_RATE_MULT_2X); break; case 4: - intel_sdvo_set_clock_rate_mult(intel_output, + intel_sdvo_set_clock_rate_mult(output, SDVO_CLOCK_RATE_MULT_4X); break; } /* Set the SDVO control regs. */ - if (0/*IS_I965GM(dev)*/) { - sdvox = SDVO_BORDER_ENABLE; - } else { - sdvox = I915_READ(sdvo_priv->output_device); - switch (sdvo_priv->output_device) { - case SDVOB: - sdvox &= SDVOB_PRESERVE_MASK; - break; - case SDVOC: - sdvox &= SDVOC_PRESERVE_MASK; - break; - } - sdvox |= (9 << 19) | SDVO_BORDER_ENABLE; - } + if (IS_I965G(dev)) { + sdvox |= SDVO_BORDER_ENABLE | + SDVO_VSYNC_ACTIVE_HIGH | + SDVO_HSYNC_ACTIVE_HIGH; + } else { + sdvox |= I915_READ(sdvo_priv->output_device); + switch (sdvo_priv->output_device) { + case SDVOB: + sdvox &= SDVOB_PRESERVE_MASK; + break; + case SDVOC: + sdvox &= SDVOC_PRESERVE_MASK; + break; + } + sdvox |= (9 << 19) | SDVO_BORDER_ENABLE; + } if (intel_crtc->pipe == 1) sdvox |= SDVO_PIPE_B_SELECT; sdvo_pixel_multiply = intel_sdvo_get_pixel_multiplier(mode); if (IS_I965G(dev)) { - /* done in crtc_mode_set as the dpll_md reg must be written - early */ - } else if (IS_I945G(dev) || IS_I945GM(dev)) { - /* done in crtc_mode_set as it lives inside the - dpll register */ + /* done in crtc_mode_set as the dpll_md reg must be written early */ + } else if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) { + /* done in crtc_mode_set as it lives inside the dpll register */ } else { sdvox |= (sdvo_pixel_multiply - 1) << SDVO_PORT_MULTIPLY_SHIFT; } - intel_sdvo_write_sdvox(intel_output, sdvox); + intel_sdvo_write_sdvox(output, sdvox); } static void intel_sdvo_dpms(struct drm_encoder *encoder, int mode) @@ -714,7 +1137,7 @@ static void intel_sdvo_dpms(struct drm_encoder *encoder, int mode) if (0) intel_sdvo_set_encoder_power_state(intel_output, mode); - intel_sdvo_set_active_outputs(intel_output, sdvo_priv->active_outputs); + intel_sdvo_set_active_outputs(intel_output, sdvo_priv->controlled_output); } return; } @@ -752,6 +1175,9 @@ static void intel_sdvo_save(struct drm_connector *connector) &sdvo_priv->save_output_dtd[o]); } } + if (sdvo_priv->is_tv) { + /* XXX: Save TV format/enhancements. */ + } sdvo_priv->save_SDVOX = I915_READ(sdvo_priv->output_device); } @@ -759,7 +1185,6 @@ static void intel_sdvo_save(struct drm_connector *connector) static void intel_sdvo_restore(struct drm_connector *connector) { struct drm_device *dev = connector->dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_output *intel_output = to_intel_output(connector); struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; int o; @@ -790,7 +1215,11 @@ static void intel_sdvo_restore(struct drm_connector *connector) intel_sdvo_set_clock_rate_mult(intel_output, sdvo_priv->save_sdvo_mult); - I915_WRITE(sdvo_priv->output_device, sdvo_priv->save_SDVOX); + if (sdvo_priv->is_tv) { + /* XXX: Restore TV format/enhancements. */ + } + + intel_sdvo_write_sdvox(intel_output, sdvo_priv->save_SDVOX); if (sdvo_priv->save_SDVOX & SDVO_ENABLE) { @@ -916,20 +1345,173 @@ static enum drm_connector_status intel_sdvo_detect(struct drm_connector *connect status = intel_sdvo_read_response(intel_output, &response, 2); DRM_DEBUG("SDVO response %d %d\n", response[0], response[1]); + + if (status != SDVO_CMD_STATUS_SUCCESS) + return connector_status_unknown; + if ((response[0] != 0) || (response[1] != 0)) return connector_status_connected; else return connector_status_disconnected; } -static int intel_sdvo_get_modes(struct drm_connector *connector) +static void intel_sdvo_get_ddc_modes(struct drm_connector *connector) { struct intel_output *intel_output = to_intel_output(connector); + struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; /* set the bus switch and get the modes */ - intel_sdvo_set_control_bus_switch(intel_output, SDVO_CONTROL_BUS_DDC2); + intel_sdvo_set_control_bus_switch(intel_output, sdvo_priv->ddc_bus); intel_ddc_get_modes(intel_output); +#if 0 + struct drm_device *dev = encoder->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + /* Mac mini hack. On this device, I get DDC through the analog, which + * load-detects as disconnected. I fail to DDC through the SDVO DDC, + * but it does load-detect as connected. So, just steal the DDC bits + * from analog when we fail at finding it the right way. + */ + crt = xf86_config->output[0]; + intel_output = crt->driver_private; + if (intel_output->type == I830_OUTPUT_ANALOG && + crt->funcs->detect(crt) == XF86OutputStatusDisconnected) { + I830I2CInit(pScrn, &intel_output->pDDCBus, GPIOA, "CRTDDC_A"); + edid_mon = xf86OutputGetEDID(crt, intel_output->pDDCBus); + xf86DestroyI2CBusRec(intel_output->pDDCBus, true, true); + } + if (edid_mon) { + xf86OutputSetEDID(output, edid_mon); + modes = xf86OutputGetEDIDModes(output); + } +#endif +} + +/** + * This function checks the current TV format, and chooses a default if + * it hasn't been set. + */ +static void +intel_sdvo_check_tv_format(struct intel_output *output) +{ + struct intel_sdvo_priv *dev_priv = output->dev_priv; + struct intel_sdvo_tv_format format, unset; + uint8_t status; + + intel_sdvo_write_cmd(output, SDVO_CMD_GET_TV_FORMAT, NULL, 0); + status = intel_sdvo_read_response(output, &format, sizeof(format)); + if (status != SDVO_CMD_STATUS_SUCCESS) + return; + + memset(&unset, 0, sizeof(unset)); + if (memcmp(&format, &unset, sizeof(format))) { + DRM_DEBUG("%s: Choosing default TV format of NTSC-M\n", + SDVO_NAME(dev_priv)); + + format.ntsc_m = true; + intel_sdvo_write_cmd(output, SDVO_CMD_SET_TV_FORMAT, NULL, 0); + status = intel_sdvo_read_response(output, NULL, 0); + } +} + +/* + * Set of SDVO TV modes. + * Note! This is in reply order (see loop in get_tv_modes). + * XXX: all 60Hz refresh? + */ +struct drm_display_mode sdvo_tv_modes[] = { + { DRM_MODE("320x200", DRM_MODE_TYPE_DRIVER, 5815680, 321, 384, 416, + 200, 0, 232, 201, 233, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("320x240", DRM_MODE_TYPE_DRIVER, 6814080, 321, 384, 416, + 240, 0, 272, 241, 273, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("400x300", DRM_MODE_TYPE_DRIVER, 9910080, 401, 464, 496, + 300, 0, 332, 301, 333, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("640x350", DRM_MODE_TYPE_DRIVER, 16913280, 641, 704, 736, + 350, 0, 382, 351, 383, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("640x400", DRM_MODE_TYPE_DRIVER, 19121280, 641, 704, 736, + 400, 0, 432, 401, 433, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("640x400", DRM_MODE_TYPE_DRIVER, 19121280, 641, 704, 736, + 400, 0, 432, 401, 433, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("704x480", DRM_MODE_TYPE_DRIVER, 24624000, 705, 768, 800, + 480, 0, 512, 481, 513, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("704x576", DRM_MODE_TYPE_DRIVER, 29232000, 705, 768, 800, + 576, 0, 608, 577, 609, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("720x350", DRM_MODE_TYPE_DRIVER, 18751680, 721, 784, 816, + 350, 0, 382, 351, 383, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("720x400", DRM_MODE_TYPE_DRIVER, 21199680, 721, 784, 816, + 400, 0, 432, 401, 433, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 25116480, 721, 784, 816, + 480, 0, 512, 481, 513, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("720x540", DRM_MODE_TYPE_DRIVER, 28054080, 721, 784, 816, + 540, 0, 572, 541, 573, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 29816640, 721, 784, 816, + 576, 0, 608, 577, 609, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("768x576", DRM_MODE_TYPE_DRIVER, 31570560, 769, 832, 864, + 576, 0, 608, 577, 609, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("800x600", DRM_MODE_TYPE_DRIVER, 34030080, 801, 864, 896, + 600, 0, 632, 601, 633, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("832x624", DRM_MODE_TYPE_DRIVER, 36581760, 833, 896, 928, + 624, 0, 656, 625, 657, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("920x766", DRM_MODE_TYPE_DRIVER, 48707040, 921, 984, 1016, + 766, 0, 798, 767, 799, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("1024x768", DRM_MODE_TYPE_DRIVER, 53827200, 1025, 1088, 1120, + 768, 0, 800, 769, 801, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, + { DRM_MODE("1280x1024", DRM_MODE_TYPE_DRIVER, 87265920, 1281, 1344, 1376, + 1024, 0, 1056, 1025, 1057, 4196112, 0, + DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, +}; + +static void intel_sdvo_get_tv_modes(struct drm_connector *connector) +{ + struct intel_output *output = to_intel_output(connector); + uint32_t reply = 0; + uint8_t status; + int i = 0; + + intel_sdvo_check_tv_format(output); + + /* Read the list of supported input resolutions for the selected TV + * format. + */ + intel_sdvo_write_cmd(output, SDVO_CMD_GET_SDTV_RESOLUTION_SUPPORT, + NULL, 0); + status = intel_sdvo_read_response(output, &reply, 3); + if (status != SDVO_CMD_STATUS_SUCCESS) + return; + + for (i = 0; i < ARRAY_SIZE(sdvo_tv_modes); i++) + if (reply & (1 << i)) + drm_mode_probed_add(connector, &sdvo_tv_modes[i]); +} + +static int intel_sdvo_get_modes(struct drm_connector *connector) +{ + struct intel_output *output = to_intel_output(connector); + struct intel_sdvo_priv *sdvo_priv = output->dev_priv; + + if (sdvo_priv->is_tv) + intel_sdvo_get_tv_modes(connector); + else + intel_sdvo_get_ddc_modes(connector); + if (list_empty(&connector->probed_modes)) return 0; return 1; @@ -978,6 +1560,65 @@ static const struct drm_encoder_funcs intel_sdvo_enc_funcs = { }; +/** + * Choose the appropriate DDC bus for control bus switch command for this + * SDVO output based on the controlled output. + * + * DDC bus number assignment is in a priority order of RGB outputs, then TMDS + * outputs, then LVDS outputs. + */ +static void +intel_sdvo_select_ddc_bus(struct intel_sdvo_priv *dev_priv) +{ + uint16_t mask = 0; + unsigned int num_bits; + + /* Make a mask of outputs less than or equal to our own priority in the + * list. + */ + switch (dev_priv->controlled_output) { + case SDVO_OUTPUT_LVDS1: + mask |= SDVO_OUTPUT_LVDS1; + case SDVO_OUTPUT_LVDS0: + mask |= SDVO_OUTPUT_LVDS0; + case SDVO_OUTPUT_TMDS1: + mask |= SDVO_OUTPUT_TMDS1; + case SDVO_OUTPUT_TMDS0: + mask |= SDVO_OUTPUT_TMDS0; + case SDVO_OUTPUT_RGB1: + mask |= SDVO_OUTPUT_RGB1; + case SDVO_OUTPUT_RGB0: + mask |= SDVO_OUTPUT_RGB0; + break; + } + + /* Count bits to find what number we are in the priority list. */ + mask &= dev_priv->caps.output_flags; + num_bits = hweight16(mask); + if (num_bits > 3) { + /* if more than 3 outputs, default to DDC bus 3 for now */ + num_bits = 3; + } + + /* Corresponds to SDVO_CONTROL_BUS_DDCx */ + dev_priv->ddc_bus = 1 << num_bits; +} + +static bool +intel_sdvo_get_digital_encoding_mode(struct intel_output *output) +{ + struct intel_sdvo_priv *sdvo_priv = output->dev_priv; + uint8_t status; + + intel_sdvo_set_target_output(output, sdvo_priv->controlled_output); + + intel_sdvo_write_cmd(output, SDVO_CMD_GET_ENCODE, NULL, 0); + status = intel_sdvo_read_response(output, &sdvo_priv->is_hdmi, 1); + if (status != SDVO_CMD_STATUS_SUCCESS) + return false; + return true; +} + bool intel_sdvo_init(struct drm_device *dev, int output_device) { struct drm_connector *connector; @@ -1040,45 +1681,76 @@ bool intel_sdvo_init(struct drm_device *dev, int output_device) intel_sdvo_get_capabilities(intel_output, &sdvo_priv->caps); - memset(&sdvo_priv->active_outputs, 0, sizeof(sdvo_priv->active_outputs)); + if (sdvo_priv->caps.output_flags & + (SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_TMDS1)) { + if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_TMDS0) + sdvo_priv->controlled_output = SDVO_OUTPUT_TMDS0; + else + sdvo_priv->controlled_output = SDVO_OUTPUT_TMDS1; + + connector->display_info.subpixel_order = SubPixelHorizontalRGB; + encoder_type = DRM_MODE_ENCODER_TMDS; + connector_type = DRM_MODE_CONNECTOR_DVID; - /* TODO, CVBS, SVID, YPRPB & SCART outputs. */ - if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_RGB0) + if (intel_sdvo_get_supp_encode(intel_output, + &sdvo_priv->encode) && + intel_sdvo_get_digital_encoding_mode(intel_output) && + sdvo_priv->is_hdmi) { + /* enable hdmi encoding mode if supported */ + intel_sdvo_set_encode(intel_output, SDVO_ENCODE_HDMI); + intel_sdvo_set_colorimetry(intel_output, + SDVO_COLORIMETRY_RGB256); + connector_type = DRM_MODE_CONNECTOR_HDMIA; + } + } + else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_SVID0) { - sdvo_priv->active_outputs = SDVO_OUTPUT_RGB0; + sdvo_priv->controlled_output = SDVO_OUTPUT_SVID0; + connector->display_info.subpixel_order = SubPixelHorizontalRGB; + encoder_type = DRM_MODE_ENCODER_TVDAC; + connector_type = DRM_MODE_CONNECTOR_SVIDEO; + sdvo_priv->is_tv = true; + intel_output->needs_tv_clock = true; + } + else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_RGB0) + { + sdvo_priv->controlled_output = SDVO_OUTPUT_RGB0; connector->display_info.subpixel_order = SubPixelHorizontalRGB; encoder_type = DRM_MODE_ENCODER_DAC; connector_type = DRM_MODE_CONNECTOR_VGA; } else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_RGB1) { - sdvo_priv->active_outputs = SDVO_OUTPUT_RGB1; + sdvo_priv->controlled_output = SDVO_OUTPUT_RGB1; connector->display_info.subpixel_order = SubPixelHorizontalRGB; encoder_type = DRM_MODE_ENCODER_DAC; connector_type = DRM_MODE_CONNECTOR_VGA; } - else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_TMDS0) + else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_LVDS0) { - sdvo_priv->active_outputs = SDVO_OUTPUT_TMDS0; + sdvo_priv->controlled_output = SDVO_OUTPUT_LVDS0; connector->display_info.subpixel_order = SubPixelHorizontalRGB; - encoder_type = DRM_MODE_ENCODER_TMDS; - connector_type = DRM_MODE_CONNECTOR_DVID; + encoder_type = DRM_MODE_ENCODER_LVDS; + connector_type = DRM_MODE_CONNECTOR_LVDS; } - else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_TMDS1) + else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_LVDS1) { - sdvo_priv->active_outputs = SDVO_OUTPUT_TMDS1; + sdvo_priv->controlled_output = SDVO_OUTPUT_LVDS1; connector->display_info.subpixel_order = SubPixelHorizontalRGB; - encoder_type = DRM_MODE_ENCODER_TMDS; - connector_type = DRM_MODE_CONNECTOR_DVID; + encoder_type = DRM_MODE_ENCODER_LVDS; + connector_type = DRM_MODE_CONNECTOR_LVDS; } else { unsigned char bytes[2]; + sdvo_priv->controlled_output = 0; memcpy (bytes, &sdvo_priv->caps.output_flags, 2); - DRM_DEBUG("%s: No active RGB or TMDS outputs (0x%02x%02x)\n", + DRM_DEBUG("%s: Unknown SDVO output type (0x%02x%02x)\n", SDVO_NAME(sdvo_priv), bytes[0], bytes[1]); + encoder_type = DRM_MODE_ENCODER_NONE; + connector_type = DRM_MODE_CONNECTOR_Unknown; goto err_i2c; } @@ -1089,6 +1761,8 @@ bool intel_sdvo_init(struct drm_device *dev, int output_device) drm_mode_connector_attach_encoder(&intel_output->base, &intel_output->enc); drm_sysfs_connector_add(connector); + intel_sdvo_select_ddc_bus(sdvo_priv); + /* Set the input timing to the screen. Assume always input 0. */ intel_sdvo_set_target_input(intel_output, true, false); diff --git a/drivers/gpu/drm/i915/intel_sdvo_regs.h b/drivers/gpu/drm/i915/intel_sdvo_regs.h index 861a43f8693..1117b9c151a 100644 --- a/drivers/gpu/drm/i915/intel_sdvo_regs.h +++ b/drivers/gpu/drm/i915/intel_sdvo_regs.h @@ -173,6 +173,9 @@ struct intel_sdvo_get_trained_inputs_response { * Returns two struct intel_sdvo_output_flags structures. */ #define SDVO_CMD_GET_IN_OUT_MAP 0x06 +struct intel_sdvo_in_out_map { + u16 in0, in1; +}; /** * Sets the current mapping of SDVO inputs to outputs on the device. @@ -206,7 +209,8 @@ struct intel_sdvo_get_trained_inputs_response { struct intel_sdvo_get_interrupt_event_source_response { u16 interrupt_status; unsigned int ambient_light_interrupt:1; - unsigned int pad:7; + unsigned int hdmi_audio_encrypt_change:1; + unsigned int pad:6; } __attribute__((packed)); /** @@ -305,23 +309,411 @@ struct intel_sdvo_set_target_input_args { # define SDVO_CLOCK_RATE_MULT_4X (1 << 3) #define SDVO_CMD_GET_SUPPORTED_TV_FORMATS 0x27 +/** 5 bytes of bit flags for TV formats shared by all TV format functions */ +struct intel_sdvo_tv_format { + unsigned int ntsc_m:1; + unsigned int ntsc_j:1; + unsigned int ntsc_443:1; + unsigned int pal_b:1; + unsigned int pal_d:1; + unsigned int pal_g:1; + unsigned int pal_h:1; + unsigned int pal_i:1; + + unsigned int pal_m:1; + unsigned int pal_n:1; + unsigned int pal_nc:1; + unsigned int pal_60:1; + unsigned int secam_b:1; + unsigned int secam_d:1; + unsigned int secam_g:1; + unsigned int secam_k:1; + + unsigned int secam_k1:1; + unsigned int secam_l:1; + unsigned int secam_60:1; + unsigned int hdtv_std_smpte_240m_1080i_59:1; + unsigned int hdtv_std_smpte_240m_1080i_60:1; + unsigned int hdtv_std_smpte_260m_1080i_59:1; + unsigned int hdtv_std_smpte_260m_1080i_60:1; + unsigned int hdtv_std_smpte_274m_1080i_50:1; + + unsigned int hdtv_std_smpte_274m_1080i_59:1; + unsigned int hdtv_std_smpte_274m_1080i_60:1; + unsigned int hdtv_std_smpte_274m_1080p_23:1; + unsigned int hdtv_std_smpte_274m_1080p_24:1; + unsigned int hdtv_std_smpte_274m_1080p_25:1; + unsigned int hdtv_std_smpte_274m_1080p_29:1; + unsigned int hdtv_std_smpte_274m_1080p_30:1; + unsigned int hdtv_std_smpte_274m_1080p_50:1; + + unsigned int hdtv_std_smpte_274m_1080p_59:1; + unsigned int hdtv_std_smpte_274m_1080p_60:1; + unsigned int hdtv_std_smpte_295m_1080i_50:1; + unsigned int hdtv_std_smpte_295m_1080p_50:1; + unsigned int hdtv_std_smpte_296m_720p_59:1; + unsigned int hdtv_std_smpte_296m_720p_60:1; + unsigned int hdtv_std_smpte_296m_720p_50:1; + unsigned int hdtv_std_smpte_293m_480p_59:1; + + unsigned int hdtv_std_smpte_170m_480i_59:1; + unsigned int hdtv_std_iturbt601_576i_50:1; + unsigned int hdtv_std_iturbt601_576p_50:1; + unsigned int hdtv_std_eia_7702a_480i_60:1; + unsigned int hdtv_std_eia_7702a_480p_60:1; + unsigned int pad:3; +} __attribute__((packed)); #define SDVO_CMD_GET_TV_FORMAT 0x28 #define SDVO_CMD_SET_TV_FORMAT 0x29 +/** Returns the resolutiosn that can be used with the given TV format */ +#define SDVO_CMD_GET_SDTV_RESOLUTION_SUPPORT 0x83 +struct intel_sdvo_sdtv_resolution_request { + unsigned int ntsc_m:1; + unsigned int ntsc_j:1; + unsigned int ntsc_443:1; + unsigned int pal_b:1; + unsigned int pal_d:1; + unsigned int pal_g:1; + unsigned int pal_h:1; + unsigned int pal_i:1; + + unsigned int pal_m:1; + unsigned int pal_n:1; + unsigned int pal_nc:1; + unsigned int pal_60:1; + unsigned int secam_b:1; + unsigned int secam_d:1; + unsigned int secam_g:1; + unsigned int secam_k:1; + + unsigned int secam_k1:1; + unsigned int secam_l:1; + unsigned int secam_60:1; + unsigned int pad:5; +} __attribute__((packed)); + +struct intel_sdvo_sdtv_resolution_reply { + unsigned int res_320x200:1; + unsigned int res_320x240:1; + unsigned int res_400x300:1; + unsigned int res_640x350:1; + unsigned int res_640x400:1; + unsigned int res_640x480:1; + unsigned int res_704x480:1; + unsigned int res_704x576:1; + + unsigned int res_720x350:1; + unsigned int res_720x400:1; + unsigned int res_720x480:1; + unsigned int res_720x540:1; + unsigned int res_720x576:1; + unsigned int res_768x576:1; + unsigned int res_800x600:1; + unsigned int res_832x624:1; + + unsigned int res_920x766:1; + unsigned int res_1024x768:1; + unsigned int res_1280x1024:1; + unsigned int pad:5; +} __attribute__((packed)); + +/* Get supported resolution with squire pixel aspect ratio that can be + scaled for the requested HDTV format */ +#define SDVO_CMD_GET_SCALED_HDTV_RESOLUTION_SUPPORT 0x85 + +struct intel_sdvo_hdtv_resolution_request { + unsigned int hdtv_std_smpte_240m_1080i_59:1; + unsigned int hdtv_std_smpte_240m_1080i_60:1; + unsigned int hdtv_std_smpte_260m_1080i_59:1; + unsigned int hdtv_std_smpte_260m_1080i_60:1; + unsigned int hdtv_std_smpte_274m_1080i_50:1; + unsigned int hdtv_std_smpte_274m_1080i_59:1; + unsigned int hdtv_std_smpte_274m_1080i_60:1; + unsigned int hdtv_std_smpte_274m_1080p_23:1; + + unsigned int hdtv_std_smpte_274m_1080p_24:1; + unsigned int hdtv_std_smpte_274m_1080p_25:1; + unsigned int hdtv_std_smpte_274m_1080p_29:1; + unsigned int hdtv_std_smpte_274m_1080p_30:1; + unsigned int hdtv_std_smpte_274m_1080p_50:1; + unsigned int hdtv_std_smpte_274m_1080p_59:1; + unsigned int hdtv_std_smpte_274m_1080p_60:1; + unsigned int hdtv_std_smpte_295m_1080i_50:1; + + unsigned int hdtv_std_smpte_295m_1080p_50:1; + unsigned int hdtv_std_smpte_296m_720p_59:1; + unsigned int hdtv_std_smpte_296m_720p_60:1; + unsigned int hdtv_std_smpte_296m_720p_50:1; + unsigned int hdtv_std_smpte_293m_480p_59:1; + unsigned int hdtv_std_smpte_170m_480i_59:1; + unsigned int hdtv_std_iturbt601_576i_50:1; + unsigned int hdtv_std_iturbt601_576p_50:1; + + unsigned int hdtv_std_eia_7702a_480i_60:1; + unsigned int hdtv_std_eia_7702a_480p_60:1; + unsigned int pad:6; +} __attribute__((packed)); + +struct intel_sdvo_hdtv_resolution_reply { + unsigned int res_640x480:1; + unsigned int res_800x600:1; + unsigned int res_1024x768:1; + unsigned int res_1280x960:1; + unsigned int res_1400x1050:1; + unsigned int res_1600x1200:1; + unsigned int res_1920x1440:1; + unsigned int res_2048x1536:1; + + unsigned int res_2560x1920:1; + unsigned int res_3200x2400:1; + unsigned int res_3840x2880:1; + unsigned int pad1:5; + + unsigned int res_848x480:1; + unsigned int res_1064x600:1; + unsigned int res_1280x720:1; + unsigned int res_1360x768:1; + unsigned int res_1704x960:1; + unsigned int res_1864x1050:1; + unsigned int res_1920x1080:1; + unsigned int res_2128x1200:1; + + unsigned int res_2560x1400:1; + unsigned int res_2728x1536:1; + unsigned int res_3408x1920:1; + unsigned int res_4264x2400:1; + unsigned int res_5120x2880:1; + unsigned int pad2:3; + + unsigned int res_768x480:1; + unsigned int res_960x600:1; + unsigned int res_1152x720:1; + unsigned int res_1124x768:1; + unsigned int res_1536x960:1; + unsigned int res_1680x1050:1; + unsigned int res_1728x1080:1; + unsigned int res_1920x1200:1; + + unsigned int res_2304x1440:1; + unsigned int res_2456x1536:1; + unsigned int res_3072x1920:1; + unsigned int res_3840x2400:1; + unsigned int res_4608x2880:1; + unsigned int pad3:3; + + unsigned int res_1280x1024:1; + unsigned int pad4:7; + + unsigned int res_1280x768:1; + unsigned int pad5:7; +} __attribute__((packed)); + +/* Get supported power state returns info for encoder and monitor, rely on + last SetTargetInput and SetTargetOutput calls */ #define SDVO_CMD_GET_SUPPORTED_POWER_STATES 0x2a +/* Get power state returns info for encoder and monitor, rely on last + SetTargetInput and SetTargetOutput calls */ +#define SDVO_CMD_GET_POWER_STATE 0x2b #define SDVO_CMD_GET_ENCODER_POWER_STATE 0x2b #define SDVO_CMD_SET_ENCODER_POWER_STATE 0x2c # define SDVO_ENCODER_STATE_ON (1 << 0) # define SDVO_ENCODER_STATE_STANDBY (1 << 1) # define SDVO_ENCODER_STATE_SUSPEND (1 << 2) # define SDVO_ENCODER_STATE_OFF (1 << 3) +# define SDVO_MONITOR_STATE_ON (1 << 4) +# define SDVO_MONITOR_STATE_STANDBY (1 << 5) +# define SDVO_MONITOR_STATE_SUSPEND (1 << 6) +# define SDVO_MONITOR_STATE_OFF (1 << 7) + +#define SDVO_CMD_GET_MAX_PANEL_POWER_SEQUENCING 0x2d +#define SDVO_CMD_GET_PANEL_POWER_SEQUENCING 0x2e +#define SDVO_CMD_SET_PANEL_POWER_SEQUENCING 0x2f +/** + * The panel power sequencing parameters are in units of milliseconds. + * The high fields are bits 8:9 of the 10-bit values. + */ +struct sdvo_panel_power_sequencing { + u8 t0; + u8 t1; + u8 t2; + u8 t3; + u8 t4; + + unsigned int t0_high:2; + unsigned int t1_high:2; + unsigned int t2_high:2; + unsigned int t3_high:2; + + unsigned int t4_high:2; + unsigned int pad:6; +} __attribute__((packed)); + +#define SDVO_CMD_GET_MAX_BACKLIGHT_LEVEL 0x30 +struct sdvo_max_backlight_reply { + u8 max_value; + u8 default_value; +} __attribute__((packed)); + +#define SDVO_CMD_GET_BACKLIGHT_LEVEL 0x31 +#define SDVO_CMD_SET_BACKLIGHT_LEVEL 0x32 + +#define SDVO_CMD_GET_AMBIENT_LIGHT 0x33 +struct sdvo_get_ambient_light_reply { + u16 trip_low; + u16 trip_high; + u16 value; +} __attribute__((packed)); +#define SDVO_CMD_SET_AMBIENT_LIGHT 0x34 +struct sdvo_set_ambient_light_reply { + u16 trip_low; + u16 trip_high; + unsigned int enable:1; + unsigned int pad:7; +} __attribute__((packed)); + +/* Set display power state */ +#define SDVO_CMD_SET_DISPLAY_POWER_STATE 0x7d +# define SDVO_DISPLAY_STATE_ON (1 << 0) +# define SDVO_DISPLAY_STATE_STANDBY (1 << 1) +# define SDVO_DISPLAY_STATE_SUSPEND (1 << 2) +# define SDVO_DISPLAY_STATE_OFF (1 << 3) + +#define SDVO_CMD_GET_SUPPORTED_ENHANCEMENTS 0x84 +struct intel_sdvo_enhancements_reply { + unsigned int flicker_filter:1; + unsigned int flicker_filter_adaptive:1; + unsigned int flicker_filter_2d:1; + unsigned int saturation:1; + unsigned int hue:1; + unsigned int brightness:1; + unsigned int contrast:1; + unsigned int overscan_h:1; + + unsigned int overscan_v:1; + unsigned int position_h:1; + unsigned int position_v:1; + unsigned int sharpness:1; + unsigned int dot_crawl:1; + unsigned int dither:1; + unsigned int max_tv_chroma_filter:1; + unsigned int max_tv_luma_filter:1; +} __attribute__((packed)); + +/* Picture enhancement limits below are dependent on the current TV format, + * and thus need to be queried and set after it. + */ +#define SDVO_CMD_GET_MAX_FLICKER_FITER 0x4d +#define SDVO_CMD_GET_MAX_ADAPTIVE_FLICKER_FITER 0x7b +#define SDVO_CMD_GET_MAX_2D_FLICKER_FITER 0x52 +#define SDVO_CMD_GET_MAX_SATURATION 0x55 +#define SDVO_CMD_GET_MAX_HUE 0x58 +#define SDVO_CMD_GET_MAX_BRIGHTNESS 0x5b +#define SDVO_CMD_GET_MAX_CONTRAST 0x5e +#define SDVO_CMD_GET_MAX_OVERSCAN_H 0x61 +#define SDVO_CMD_GET_MAX_OVERSCAN_V 0x64 +#define SDVO_CMD_GET_MAX_POSITION_H 0x67 +#define SDVO_CMD_GET_MAX_POSITION_V 0x6a +#define SDVO_CMD_GET_MAX_SHARPNESS_V 0x6d +#define SDVO_CMD_GET_MAX_TV_CHROMA 0x74 +#define SDVO_CMD_GET_MAX_TV_LUMA 0x77 +struct intel_sdvo_enhancement_limits_reply { + u16 max_value; + u16 default_value; +} __attribute__((packed)); -#define SDVO_CMD_SET_TV_RESOLUTION_SUPPORT 0x93 +#define SDVO_CMD_GET_LVDS_PANEL_INFORMATION 0x7f +#define SDVO_CMD_SET_LVDS_PANEL_INFORMATION 0x80 +# define SDVO_LVDS_COLOR_DEPTH_18 (0 << 0) +# define SDVO_LVDS_COLOR_DEPTH_24 (1 << 0) +# define SDVO_LVDS_CONNECTOR_SPWG (0 << 2) +# define SDVO_LVDS_CONNECTOR_OPENLDI (1 << 2) +# define SDVO_LVDS_SINGLE_CHANNEL (0 << 4) +# define SDVO_LVDS_DUAL_CHANNEL (1 << 4) + +#define SDVO_CMD_GET_FLICKER_FILTER 0x4e +#define SDVO_CMD_SET_FLICKER_FILTER 0x4f +#define SDVO_CMD_GET_ADAPTIVE_FLICKER_FITER 0x50 +#define SDVO_CMD_SET_ADAPTIVE_FLICKER_FITER 0x51 +#define SDVO_CMD_GET_2D_FLICKER_FITER 0x53 +#define SDVO_CMD_SET_2D_FLICKER_FITER 0x54 +#define SDVO_CMD_GET_SATURATION 0x56 +#define SDVO_CMD_SET_SATURATION 0x57 +#define SDVO_CMD_GET_HUE 0x59 +#define SDVO_CMD_SET_HUE 0x5a +#define SDVO_CMD_GET_BRIGHTNESS 0x5c +#define SDVO_CMD_SET_BRIGHTNESS 0x5d +#define SDVO_CMD_GET_CONTRAST 0x5f +#define SDVO_CMD_SET_CONTRAST 0x60 +#define SDVO_CMD_GET_OVERSCAN_H 0x62 +#define SDVO_CMD_SET_OVERSCAN_H 0x63 +#define SDVO_CMD_GET_OVERSCAN_V 0x65 +#define SDVO_CMD_SET_OVERSCAN_V 0x66 +#define SDVO_CMD_GET_POSITION_H 0x68 +#define SDVO_CMD_SET_POSITION_H 0x69 +#define SDVO_CMD_GET_POSITION_V 0x6b +#define SDVO_CMD_SET_POSITION_V 0x6c +#define SDVO_CMD_GET_SHARPNESS 0x6e +#define SDVO_CMD_SET_SHARPNESS 0x6f +#define SDVO_CMD_GET_TV_CHROMA 0x75 +#define SDVO_CMD_SET_TV_CHROMA 0x76 +#define SDVO_CMD_GET_TV_LUMA 0x78 +#define SDVO_CMD_SET_TV_LUMA 0x79 +struct intel_sdvo_enhancements_arg { + u16 value; +}__attribute__((packed)); + +#define SDVO_CMD_GET_DOT_CRAWL 0x70 +#define SDVO_CMD_SET_DOT_CRAWL 0x71 +# define SDVO_DOT_CRAWL_ON (1 << 0) +# define SDVO_DOT_CRAWL_DEFAULT_ON (1 << 1) + +#define SDVO_CMD_GET_DITHER 0x72 +#define SDVO_CMD_SET_DITHER 0x73 +# define SDVO_DITHER_ON (1 << 0) +# define SDVO_DITHER_DEFAULT_ON (1 << 1) #define SDVO_CMD_SET_CONTROL_BUS_SWITCH 0x7a -# define SDVO_CONTROL_BUS_PROM 0x0 -# define SDVO_CONTROL_BUS_DDC1 0x1 -# define SDVO_CONTROL_BUS_DDC2 0x2 -# define SDVO_CONTROL_BUS_DDC3 0x3 +# define SDVO_CONTROL_BUS_PROM (1 << 0) +# define SDVO_CONTROL_BUS_DDC1 (1 << 1) +# define SDVO_CONTROL_BUS_DDC2 (1 << 2) +# define SDVO_CONTROL_BUS_DDC3 (1 << 3) + +/* HDMI op codes */ +#define SDVO_CMD_GET_SUPP_ENCODE 0x9d +#define SDVO_CMD_GET_ENCODE 0x9e +#define SDVO_CMD_SET_ENCODE 0x9f + #define SDVO_ENCODE_DVI 0x0 + #define SDVO_ENCODE_HDMI 0x1 +#define SDVO_CMD_SET_PIXEL_REPLI 0x8b +#define SDVO_CMD_GET_PIXEL_REPLI 0x8c +#define SDVO_CMD_GET_COLORIMETRY_CAP 0x8d +#define SDVO_CMD_SET_COLORIMETRY 0x8e + #define SDVO_COLORIMETRY_RGB256 0x0 + #define SDVO_COLORIMETRY_RGB220 0x1 + #define SDVO_COLORIMETRY_YCrCb422 0x3 + #define SDVO_COLORIMETRY_YCrCb444 0x4 +#define SDVO_CMD_GET_COLORIMETRY 0x8f +#define SDVO_CMD_GET_AUDIO_ENCRYPT_PREFER 0x90 +#define SDVO_CMD_SET_AUDIO_STAT 0x91 +#define SDVO_CMD_GET_AUDIO_STAT 0x92 +#define SDVO_CMD_SET_HBUF_INDEX 0x93 +#define SDVO_CMD_GET_HBUF_INDEX 0x94 +#define SDVO_CMD_GET_HBUF_INFO 0x95 +#define SDVO_CMD_SET_HBUF_AV_SPLIT 0x96 +#define SDVO_CMD_GET_HBUF_AV_SPLIT 0x97 +#define SDVO_CMD_SET_HBUF_DATA 0x98 +#define SDVO_CMD_GET_HBUF_DATA 0x99 +#define SDVO_CMD_SET_HBUF_TXRATE 0x9a +#define SDVO_CMD_GET_HBUF_TXRATE 0x9b + #define SDVO_HBUF_TX_DISABLED (0 << 6) + #define SDVO_HBUF_TX_ONCE (2 << 6) + #define SDVO_HBUF_TX_VSYNC (3 << 6) +#define SDVO_CMD_GET_AUDIO_TX_INFO 0x9c + +struct intel_sdvo_encode{ + u8 dvi_rev; + u8 hdmi_rev; +} __attribute__ ((packed)); diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c index 63212d7bbc2..df4cf97e5d9 100644 --- a/drivers/gpu/drm/radeon/radeon_cp.c +++ b/drivers/gpu/drm/radeon/radeon_cp.c @@ -1039,9 +1039,9 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init, #if __OS_HAS_AGP if (dev_priv->flags & RADEON_IS_AGP) { - drm_core_ioremap(dev_priv->cp_ring, dev); - drm_core_ioremap(dev_priv->ring_rptr, dev); - drm_core_ioremap(dev->agp_buffer_map, dev); + drm_core_ioremap_wc(dev_priv->cp_ring, dev); + drm_core_ioremap_wc(dev_priv->ring_rptr, dev); + drm_core_ioremap_wc(dev->agp_buffer_map, dev); if (!dev_priv->cp_ring->handle || !dev_priv->ring_rptr->handle || !dev->agp_buffer_map->handle) { diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 35561689ff3..ea2638b4198 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -13,11 +13,11 @@ menuconfig INPUT_KEYBOARD if INPUT_KEYBOARD config KEYBOARD_ATKBD - tristate "AT keyboard" if EMBEDDED || !X86_PC + tristate "AT keyboard" if EMBEDDED || !X86 default y select SERIO select SERIO_LIBPS2 - select SERIO_I8042 if X86_PC + select SERIO_I8042 if X86 select SERIO_GSCPS2 if GSC help Say Y here if you want to use a standard AT or PS/2 keyboard. Usually diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig index 093c8c1bca7..9bef935ef19 100644 --- a/drivers/input/mouse/Kconfig +++ b/drivers/input/mouse/Kconfig @@ -17,7 +17,7 @@ config MOUSE_PS2 default y select SERIO select SERIO_LIBPS2 - select SERIO_I8042 if X86_PC + select SERIO_I8042 if X86 select SERIO_GSCPS2 if GSC help Say Y here if you have a PS/2 mouse connected to your system. This diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index 595ba8eb4a0..0b28141e43b 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -4599,6 +4599,7 @@ init_e1_port(struct hfc_multi *hc, struct hm_map *m) printk(KERN_ERR "%s: no memory for coeffs\n", __func__); ret = -ENOMEM; + kfree(bch); goto free_chan; } bch->nr = ch; @@ -4767,6 +4768,7 @@ init_multi_port(struct hfc_multi *hc, int pt) printk(KERN_ERR "%s: no memory for coeffs\n", __func__); ret = -ENOMEM; + kfree(bch); goto free_chan; } bch->nr = ch + 1; diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index c64e6798878..1c484084ed4 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -162,7 +162,7 @@ config ENCLOSURE_SERVICES config SGI_XP tristate "Support communication between SGI SSIs" depends on NET - depends on (IA64_GENERIC || IA64_SGI_SN2 || IA64_SGI_UV || X86_64) && SMP + depends on (IA64_GENERIC || IA64_SGI_SN2 || IA64_SGI_UV || X86_UV) && SMP select IA64_UNCACHED_ALLOCATOR if IA64_GENERIC || IA64_SGI_SN2 select GENERIC_ALLOCATOR if IA64_GENERIC || IA64_SGI_SN2 select SGI_GRU if (IA64_GENERIC || IA64_SGI_UV || X86_64) && SMP @@ -189,7 +189,7 @@ config HP_ILO config SGI_GRU tristate "SGI GRU driver" - depends on (X86_64 || IA64_SGI_UV || IA64_GENERIC) && SMP + depends on (X86_UV || IA64_SGI_UV || IA64_GENERIC) && SMP default n select MMU_NOTIFIER ---help--- diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index 65098380639..c67e4e8bd62 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -36,23 +36,11 @@ #include <linux/interrupt.h> #include <linux/proc_fs.h> #include <linux/uaccess.h> +#include <asm/uv/uv.h> #include "gru.h" #include "grulib.h" #include "grutables.h" -#if defined CONFIG_X86_64 -#include <asm/genapic.h> -#include <asm/irq.h> -#define IS_UV() is_uv_system() -#elif defined CONFIG_IA64 -#include <asm/system.h> -#include <asm/sn/simulator.h> -/* temp support for running on hardware simulator */ -#define IS_UV() IS_MEDUSA() || ia64_platform_is("uv") -#else -#define IS_UV() 0 -#endif - #include <asm/uv/uv_hub.h> #include <asm/uv/uv_mmrs.h> @@ -381,7 +369,7 @@ static int __init gru_init(void) char id[10]; void *gru_start_vaddr; - if (!IS_UV()) + if (!is_uv_system()) return 0; #if defined CONFIG_IA64 @@ -451,7 +439,7 @@ static void __exit gru_exit(void) int order = get_order(sizeof(struct gru_state) * GRU_CHIPLETS_PER_BLADE); - if (!IS_UV()) + if (!is_uv_system()) return; for (i = 0; i < GRU_CHIPLETS_PER_BLADE; i++) diff --git a/drivers/misc/sgi-xp/xp.h b/drivers/misc/sgi-xp/xp.h index 7b4cbd5e03e..2275126cb33 100644 --- a/drivers/misc/sgi-xp/xp.h +++ b/drivers/misc/sgi-xp/xp.h @@ -15,19 +15,19 @@ #include <linux/mutex.h> -#ifdef CONFIG_IA64 +#if defined CONFIG_X86_UV || defined CONFIG_IA64_SGI_UV +#include <asm/uv/uv.h> +#define is_uv() is_uv_system() +#endif + +#ifndef is_uv +#define is_uv() 0 +#endif + +#if defined CONFIG_IA64 #include <asm/system.h> #include <asm/sn/arch.h> /* defines is_shub1() and is_shub2() */ #define is_shub() ia64_platform_is("sn2") -#ifdef CONFIG_IA64_SGI_UV -#define is_uv() ia64_platform_is("uv") -#else -#define is_uv() 0 -#endif -#endif -#ifdef CONFIG_X86_64 -#include <asm/genapic.h> -#define is_uv() is_uv_system() #endif #ifndef is_shub1 @@ -42,10 +42,6 @@ #define is_shub() 0 #endif -#ifndef is_uv -#define is_uv() 0 -#endif - #ifdef USE_DBUG_ON #define DBUG_ON(condition) BUG_ON(condition) #else diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index 89218f7cfaa..6576170de96 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -318,7 +318,7 @@ xpc_hb_checker(void *ignore) /* this thread was marked active by xpc_hb_init() */ - set_cpus_allowed_ptr(current, &cpumask_of_cpu(XPC_HB_CHECK_CPU)); + set_cpus_allowed_ptr(current, cpumask_of(XPC_HB_CHECK_CPU)); /* set our heartbeating to other partitions into motion */ xpc_hb_check_timeout = jiffies + (xpc_hb_check_interval * HZ); diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 8b12e6e109d..2ff88791ceb 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -273,7 +273,7 @@ config MTD_NAND_CAFE config MTD_NAND_CS553X tristate "NAND support for CS5535/CS5536 (AMD Geode companion chip)" - depends on X86_32 && (X86_PC || X86_GENERICARCH) + depends on X86_32 help The CS553x companion chips for the AMD Geode processor include NAND flash controllers with built-in hardware ECC diff --git a/drivers/net/3c509.c b/drivers/net/3c509.c index 535c234286e..8c694213035 100644 --- a/drivers/net/3c509.c +++ b/drivers/net/3c509.c @@ -1475,6 +1475,7 @@ el3_resume(struct device *pdev) spin_lock_irqsave(&lp->lock, flags); outw(PowerUp, ioaddr + EL3_CMD); + EL3WINDOW(0); el3_up(dev); if (netif_running(dev)) diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c index acae2d8cd68..9b12a13a640 100644 --- a/drivers/net/gianfar.c +++ b/drivers/net/gianfar.c @@ -1629,6 +1629,12 @@ static void gfar_schedule_cleanup(struct net_device *dev) if (netif_rx_schedule_prep(&priv->napi)) { gfar_write(&priv->regs->imask, IMASK_RTX_DISABLED); __netif_rx_schedule(&priv->napi); + } else { + /* + * Clear IEVENT, so interrupts aren't called again + * because of the packets that have already arrived. + */ + gfar_write(&priv->regs->ievent, IEVENT_RTX_MASK); } spin_unlock(&priv->rxlock); diff --git a/drivers/net/netxen/netxen_nic.h b/drivers/net/netxen/netxen_nic.h index 9c78c963b72..f4dd9acb687 100644 --- a/drivers/net/netxen/netxen_nic.h +++ b/drivers/net/netxen/netxen_nic.h @@ -1203,7 +1203,7 @@ typedef struct { #define NETXEN_IS_MSI_FAMILY(adapter) \ ((adapter)->flags & (NETXEN_NIC_MSI_ENABLED | NETXEN_NIC_MSIX_ENABLED)) -#define MSIX_ENTRIES_PER_ADAPTER 8 +#define MSIX_ENTRIES_PER_ADAPTER 1 #define NETXEN_MSIX_TBL_SPACE 8192 #define NETXEN_PCI_REG_MSIX_TBL 0x44 diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index 645d384fe87..3b17a793614 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -76,6 +76,7 @@ static void netxen_nic_poll_controller(struct net_device *netdev); #endif static irqreturn_t netxen_intr(int irq, void *data); static irqreturn_t netxen_msi_intr(int irq, void *data); +static irqreturn_t netxen_msix_intr(int irq, void *data); /* PCI Device ID Table */ #define ENTRY(device) \ @@ -1084,7 +1085,9 @@ static int netxen_nic_open(struct net_device *netdev) for (ring = 0; ring < adapter->max_rds_rings; ring++) netxen_post_rx_buffers(adapter, ctx, ring); } - if (NETXEN_IS_MSI_FAMILY(adapter)) + if (adapter->flags & NETXEN_NIC_MSIX_ENABLED) + handler = netxen_msix_intr; + else if (adapter->flags & NETXEN_NIC_MSI_ENABLED) handler = netxen_msi_intr; else { flags |= IRQF_SHARED; @@ -1612,6 +1615,14 @@ static irqreturn_t netxen_msi_intr(int irq, void *data) return IRQ_HANDLED; } +static irqreturn_t netxen_msix_intr(int irq, void *data) +{ + struct netxen_adapter *adapter = data; + + napi_schedule(&adapter->napi); + return IRQ_HANDLED; +} + static int netxen_nic_poll(struct napi_struct *napi, int budget) { struct netxen_adapter *adapter = container_of(napi, struct netxen_adapter, napi); diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 2c73ca606b3..0771eb6fc6e 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -437,6 +437,22 @@ enum features { RTL_FEATURE_GMII = (1 << 2), }; +struct rtl8169_counters { + __le64 tx_packets; + __le64 rx_packets; + __le64 tx_errors; + __le32 rx_errors; + __le16 rx_missed; + __le16 align_errors; + __le32 tx_one_collision; + __le32 tx_multi_collision; + __le64 rx_unicast; + __le64 rx_broadcast; + __le32 rx_multicast; + __le16 tx_aborted; + __le16 tx_underun; +}; + struct rtl8169_private { void __iomem *mmio_addr; /* memory map physical address */ struct pci_dev *pci_dev; /* Index of PCI device */ @@ -480,6 +496,7 @@ struct rtl8169_private { unsigned features; struct mii_if_info mii; + struct rtl8169_counters counters; }; MODULE_AUTHOR("Realtek and the Linux r8169 crew <netdev@vger.kernel.org>"); @@ -1100,22 +1117,6 @@ static const char rtl8169_gstrings[][ETH_GSTRING_LEN] = { "tx_underrun", }; -struct rtl8169_counters { - __le64 tx_packets; - __le64 rx_packets; - __le64 tx_errors; - __le32 rx_errors; - __le16 rx_missed; - __le16 align_errors; - __le32 tx_one_collision; - __le32 tx_multi_collision; - __le64 rx_unicast; - __le64 rx_broadcast; - __le32 rx_multicast; - __le16 tx_aborted; - __le16 tx_underun; -}; - static int rtl8169_get_sset_count(struct net_device *dev, int sset) { switch (sset) { @@ -1126,16 +1127,21 @@ static int rtl8169_get_sset_count(struct net_device *dev, int sset) } } -static void rtl8169_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) +static void rtl8169_update_counters(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; struct rtl8169_counters *counters; dma_addr_t paddr; u32 cmd; + int wait = 1000; - ASSERT_RTNL(); + /* + * Some chips are unable to dump tally counters when the receiver + * is disabled. + */ + if ((RTL_R8(ChipCmd) & CmdRxEnb) == 0) + return; counters = pci_alloc_consistent(tp->pci_dev, sizeof(*counters), &paddr); if (!counters) @@ -1146,31 +1152,45 @@ static void rtl8169_get_ethtool_stats(struct net_device *dev, RTL_W32(CounterAddrLow, cmd); RTL_W32(CounterAddrLow, cmd | CounterDump); - while (RTL_R32(CounterAddrLow) & CounterDump) { - if (msleep_interruptible(1)) + while (wait--) { + if ((RTL_R32(CounterAddrLow) & CounterDump) == 0) { + /* copy updated counters */ + memcpy(&tp->counters, counters, sizeof(*counters)); break; + } + udelay(10); } RTL_W32(CounterAddrLow, 0); RTL_W32(CounterAddrHigh, 0); - data[0] = le64_to_cpu(counters->tx_packets); - data[1] = le64_to_cpu(counters->rx_packets); - data[2] = le64_to_cpu(counters->tx_errors); - data[3] = le32_to_cpu(counters->rx_errors); - data[4] = le16_to_cpu(counters->rx_missed); - data[5] = le16_to_cpu(counters->align_errors); - data[6] = le32_to_cpu(counters->tx_one_collision); - data[7] = le32_to_cpu(counters->tx_multi_collision); - data[8] = le64_to_cpu(counters->rx_unicast); - data[9] = le64_to_cpu(counters->rx_broadcast); - data[10] = le32_to_cpu(counters->rx_multicast); - data[11] = le16_to_cpu(counters->tx_aborted); - data[12] = le16_to_cpu(counters->tx_underun); - pci_free_consistent(tp->pci_dev, sizeof(*counters), counters, paddr); } +static void rtl8169_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct rtl8169_private *tp = netdev_priv(dev); + + ASSERT_RTNL(); + + rtl8169_update_counters(dev); + + data[0] = le64_to_cpu(tp->counters.tx_packets); + data[1] = le64_to_cpu(tp->counters.rx_packets); + data[2] = le64_to_cpu(tp->counters.tx_errors); + data[3] = le32_to_cpu(tp->counters.rx_errors); + data[4] = le16_to_cpu(tp->counters.rx_missed); + data[5] = le16_to_cpu(tp->counters.align_errors); + data[6] = le32_to_cpu(tp->counters.tx_one_collision); + data[7] = le32_to_cpu(tp->counters.tx_multi_collision); + data[8] = le64_to_cpu(tp->counters.rx_unicast); + data[9] = le64_to_cpu(tp->counters.rx_broadcast); + data[10] = le32_to_cpu(tp->counters.rx_multicast); + data[11] = le16_to_cpu(tp->counters.tx_aborted); + data[12] = le16_to_cpu(tp->counters.tx_underun); +} + static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data) { switch(stringset) { @@ -3682,6 +3702,9 @@ static int rtl8169_close(struct net_device *dev) struct rtl8169_private *tp = netdev_priv(dev); struct pci_dev *pdev = tp->pci_dev; + /* update counters before going down */ + rtl8169_update_counters(dev); + rtl8169_down(dev); free_irq(dev->irq, dev); diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index ab0e09bf154..847e9bb0098 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -854,20 +854,27 @@ static void efx_fini_io(struct efx_nic *efx) * interrupts across them. */ static int efx_wanted_rx_queues(void) { - cpumask_t core_mask; + cpumask_var_t core_mask; int count; int cpu; - cpus_clear(core_mask); + if (!alloc_cpumask_var(&core_mask, GFP_KERNEL)) { + printk(KERN_WARNING + "efx.c: allocation failure, irq balancing hobbled\n"); + return 1; + } + + cpumask_clear(core_mask); count = 0; for_each_online_cpu(cpu) { - if (!cpu_isset(cpu, core_mask)) { + if (!cpumask_test_cpu(cpu, core_mask)) { ++count; - cpus_or(core_mask, core_mask, - topology_core_siblings(cpu)); + cpumask_or(core_mask, core_mask, + topology_core_cpumask(cpu)); } } + free_cpumask_var(core_mask); return count; } diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c index b17efa9cc53..49187634106 100644 --- a/drivers/net/sungem.c +++ b/drivers/net/sungem.c @@ -2221,6 +2221,8 @@ static int gem_do_start(struct net_device *dev) gp->running = 1; + napi_enable(&gp->napi); + if (gp->lstate == link_up) { netif_carrier_on(gp->dev); gem_set_link_modes(gp); @@ -2238,6 +2240,8 @@ static int gem_do_start(struct net_device *dev) spin_lock_irqsave(&gp->lock, flags); spin_lock(&gp->tx_lock); + napi_disable(&gp->napi); + gp->running = 0; gem_reset(gp); gem_clean_rings(gp); @@ -2338,8 +2342,6 @@ static int gem_open(struct net_device *dev) if (!gp->asleep) rc = gem_do_start(dev); gp->opened = (rc == 0); - if (gp->opened) - napi_enable(&gp->napi); mutex_unlock(&gp->pm_mutex); @@ -2476,8 +2478,6 @@ static int gem_resume(struct pci_dev *pdev) /* Re-attach net device */ netif_device_attach(dev); - - napi_enable(&gp->napi); } spin_lock_irqsave(&gp->lock, flags); diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c index 7a72a3112f0..cc4013be5e1 100644 --- a/drivers/net/sunhme.c +++ b/drivers/net/sunhme.c @@ -2629,6 +2629,14 @@ static int __devinit happy_meal_sbus_probe_one(struct of_device *op, int is_qfe) int i, qfe_slot = -1; int err = -ENODEV; + sbus_dp = to_of_device(op->dev.parent)->node; + if (is_qfe) + sbus_dp = to_of_device(op->dev.parent->parent)->node; + + /* We can match PCI devices too, do not accept those here. */ + if (strcmp(sbus_dp->name, "sbus")) + return err; + if (is_qfe) { qp = quattro_sbus_find(op); if (qp == NULL) @@ -2734,10 +2742,6 @@ static int __devinit happy_meal_sbus_probe_one(struct of_device *op, int is_qfe) if (qp != NULL) hp->happy_flags |= HFLAG_QUATTRO; - sbus_dp = to_of_device(op->dev.parent)->node; - if (is_qfe) - sbus_dp = to_of_device(op->dev.parent->parent)->node; - /* Get the supported DVMA burst sizes from our Happy SBUS. */ hp->happy_bursts = of_getintprop_default(sbus_dp, "burst-sizes", 0x00); diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c index 0bf2114738b..d4c5ecc51f7 100644 --- a/drivers/net/tulip/de2104x.c +++ b/drivers/net/tulip/de2104x.c @@ -464,13 +464,14 @@ static void de_rx (struct de_private *de) drop = 1; rx_next: - de->rx_ring[rx_tail].opts1 = cpu_to_le32(DescOwn); if (rx_tail == (DE_RX_RING_SIZE - 1)) de->rx_ring[rx_tail].opts2 = cpu_to_le32(RingEnd | de->rx_buf_sz); else de->rx_ring[rx_tail].opts2 = cpu_to_le32(de->rx_buf_sz); de->rx_ring[rx_tail].addr1 = cpu_to_le32(mapping); + wmb(); + de->rx_ring[rx_tail].opts1 = cpu_to_le32(DescOwn); rx_tail = NEXT_RX(rx_tail); } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d7b81e4fdd5..09fea31d3e3 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -157,10 +157,16 @@ static int update_filter(struct tap_filter *filter, void __user *arg) nexact = n; - /* The rest is hashed */ + /* Remaining multicast addresses are hashed, + * unicast will leave the filter disabled. */ memset(filter->mask, 0, sizeof(filter->mask)); - for (; n < uf.count; n++) + for (; n < uf.count; n++) { + if (!is_multicast_ether_addr(addr[n].u)) { + err = 0; /* no filter */ + goto done; + } addr_hash_set(filter->mask, addr[n].u); + } /* For ALLMULTI just set the mask to all ones. * This overrides the mask populated above. */ diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c index 9da5a4b8113..c3ea5fa7d05 100644 --- a/drivers/oprofile/buffer_sync.c +++ b/drivers/oprofile/buffer_sync.c @@ -38,7 +38,7 @@ static LIST_HEAD(dying_tasks); static LIST_HEAD(dead_tasks); -static cpumask_t marked_cpus = CPU_MASK_NONE; +static cpumask_var_t marked_cpus; static DEFINE_SPINLOCK(task_mortuary); static void process_task_mortuary(void); @@ -456,10 +456,10 @@ static void mark_done(int cpu) { int i; - cpu_set(cpu, marked_cpus); + cpumask_set_cpu(cpu, marked_cpus); for_each_online_cpu(i) { - if (!cpu_isset(i, marked_cpus)) + if (!cpumask_test_cpu(i, marked_cpus)) return; } @@ -468,7 +468,7 @@ static void mark_done(int cpu) */ process_task_mortuary(); - cpus_clear(marked_cpus); + cpumask_clear(marked_cpus); } @@ -565,6 +565,20 @@ void sync_buffer(int cpu) mutex_unlock(&buffer_mutex); } +int __init buffer_sync_init(void) +{ + if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL)) + return -ENOMEM; + + cpumask_clear(marked_cpus); + return 0; +} + +void __exit buffer_sync_cleanup(void) +{ + free_cpumask_var(marked_cpus); +} + /* The function can be used to add a buffer worth of data directly to * the kernel buffer. The buffer is assumed to be a circular buffer. * Take the entries from index start and end at index end, wrapping diff --git a/drivers/oprofile/buffer_sync.h b/drivers/oprofile/buffer_sync.h index 3110732c183..0ebf5db6267 100644 --- a/drivers/oprofile/buffer_sync.h +++ b/drivers/oprofile/buffer_sync.h @@ -19,4 +19,8 @@ void sync_stop(void); /* sync the given CPU's buffer */ void sync_buffer(int cpu); +/* initialize/destroy the buffer system. */ +int buffer_sync_init(void); +void buffer_sync_cleanup(void); + #endif /* OPROFILE_BUFFER_SYNC_H */ diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c index 3cffce90f82..ced39f60229 100644 --- a/drivers/oprofile/oprof.c +++ b/drivers/oprofile/oprof.c @@ -183,6 +183,10 @@ static int __init oprofile_init(void) { int err; + err = buffer_sync_init(); + if (err) + return err; + err = oprofile_arch_init(&oprofile_ops); if (err < 0 || timer) { @@ -191,8 +195,10 @@ static int __init oprofile_init(void) } err = oprofilefs_register(); - if (err) + if (err) { oprofile_arch_exit(); + buffer_sync_cleanup(); + } return err; } @@ -202,6 +208,7 @@ static void __exit oprofile_exit(void) { oprofilefs_unregister(); oprofile_arch_exit(); + buffer_sync_cleanup(); } diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c index 101ed49a2d1..032db815b0f 100644 --- a/drivers/parport/parport_serial.c +++ b/drivers/parport/parport_serial.c @@ -64,6 +64,11 @@ struct parport_pc_pci { static int __devinit netmos_parallel_init(struct pci_dev *dev, struct parport_pc_pci *card, int autoirq, int autodma) { + /* the rule described below doesn't hold for this device */ + if (dev->device == PCI_DEVICE_ID_NETMOS_9835 && + dev->subsystem_vendor == PCI_VENDOR_ID_IBM && + dev->subsystem_device == 0x0299) + return -ENODEV; /* * Netmos uses the subdevice ID to indicate the number of parallel * and serial ports. The form is 0x00PS, where <P> is the number of diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 3dfecb20d5e..f4b7c79023f 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -268,7 +268,12 @@ static long list_size; static void domain_remove_dev_info(struct dmar_domain *domain); -int dmar_disabled; +#ifdef CONFIG_DMAR_DEFAULT_ON +int dmar_disabled = 0; +#else +int dmar_disabled = 1; +#endif /*CONFIG_DMAR_DEFAULT_ON*/ + static int __initdata dmar_map_gfx = 1; static int dmar_forcedac; static int intel_iommu_strict; @@ -284,9 +289,12 @@ static int __init intel_iommu_setup(char *str) if (!str) return -EINVAL; while (*str) { - if (!strncmp(str, "off", 3)) { + if (!strncmp(str, "on", 2)) { + dmar_disabled = 0; + printk(KERN_INFO "Intel-IOMMU: enabled\n"); + } else if (!strncmp(str, "off", 3)) { dmar_disabled = 1; - printk(KERN_INFO"Intel-IOMMU: disabled\n"); + printk(KERN_INFO "Intel-IOMMU: disabled\n"); } else if (!strncmp(str, "igfx_off", 8)) { dmar_map_gfx = 0; printk(KERN_INFO diff --git a/drivers/power/pcf50633-charger.c b/drivers/power/pcf50633-charger.c index e988ec130fc..41aec2acbb9 100644 --- a/drivers/power/pcf50633-charger.c +++ b/drivers/power/pcf50633-charger.c @@ -199,7 +199,8 @@ static int adapter_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) { - struct pcf50633_mbc *mbc = container_of(psy, struct pcf50633_mbc, usb); + struct pcf50633_mbc *mbc = container_of(psy, + struct pcf50633_mbc, adapter); int ret = 0; switch (psp) { diff --git a/drivers/rtc/rtc-au1xxx.c b/drivers/rtc/rtc-au1xxx.c index 8906a688e6a..979ed0406ce 100644 --- a/drivers/rtc/rtc-au1xxx.c +++ b/drivers/rtc/rtc-au1xxx.c @@ -81,7 +81,7 @@ static int __devinit au1xtoy_rtc_probe(struct platform_device *pdev) if (au_readl(SYS_TOYTRIM) != 32767) { /* wait until hardware gives access to TRIM register */ t = 0x00100000; - while ((au_readl(SYS_COUNTER_CNTRL) & SYS_CNTRL_T0S) && t--) + while ((au_readl(SYS_COUNTER_CNTRL) & SYS_CNTRL_T0S) && --t) msleep(1); if (!t) { diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c index bd56a033bfd..bb8cc05605a 100644 --- a/drivers/rtc/rtc-pxa.c +++ b/drivers/rtc/rtc-pxa.c @@ -485,7 +485,7 @@ static void __exit pxa_rtc_exit(void) module_init(pxa_rtc_init); module_exit(pxa_rtc_exit); -MODULE_AUTHOR("Robert Jarzmik"); +MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik@free.fr>"); MODULE_DESCRIPTION("PXA27x/PXA3xx Realtime Clock Driver (RTC)"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:pxa-rtc"); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index bd591499414..08c23a92101 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -57,6 +57,8 @@ static void dasd_device_tasklet(struct dasd_device *); static void dasd_block_tasklet(struct dasd_block *); static void do_kick_device(struct work_struct *); static void dasd_return_cqr_cb(struct dasd_ccw_req *, void *); +static void dasd_device_timeout(unsigned long); +static void dasd_block_timeout(unsigned long); /* * SECTION: Operations on the device structure. @@ -99,6 +101,8 @@ struct dasd_device *dasd_alloc_device(void) (unsigned long) device); INIT_LIST_HEAD(&device->ccw_queue); init_timer(&device->timer); + device->timer.function = dasd_device_timeout; + device->timer.data = (unsigned long) device; INIT_WORK(&device->kick_work, do_kick_device); device->state = DASD_STATE_NEW; device->target = DASD_STATE_NEW; @@ -138,6 +142,8 @@ struct dasd_block *dasd_alloc_block(void) INIT_LIST_HEAD(&block->ccw_queue); spin_lock_init(&block->queue_lock); init_timer(&block->timer); + block->timer.function = dasd_block_timeout; + block->timer.data = (unsigned long) block; return block; } @@ -915,19 +921,10 @@ static void dasd_device_timeout(unsigned long ptr) */ void dasd_device_set_timer(struct dasd_device *device, int expires) { - if (expires == 0) { - if (timer_pending(&device->timer)) - del_timer(&device->timer); - return; - } - if (timer_pending(&device->timer)) { - if (mod_timer(&device->timer, jiffies + expires)) - return; - } - device->timer.function = dasd_device_timeout; - device->timer.data = (unsigned long) device; - device->timer.expires = jiffies + expires; - add_timer(&device->timer); + if (expires == 0) + del_timer(&device->timer); + else + mod_timer(&device->timer, jiffies + expires); } /* @@ -935,8 +932,7 @@ void dasd_device_set_timer(struct dasd_device *device, int expires) */ void dasd_device_clear_timer(struct dasd_device *device) { - if (timer_pending(&device->timer)) - del_timer(&device->timer); + del_timer(&device->timer); } static void dasd_handle_killed_request(struct ccw_device *cdev, @@ -1586,19 +1582,10 @@ static void dasd_block_timeout(unsigned long ptr) */ void dasd_block_set_timer(struct dasd_block *block, int expires) { - if (expires == 0) { - if (timer_pending(&block->timer)) - del_timer(&block->timer); - return; - } - if (timer_pending(&block->timer)) { - if (mod_timer(&block->timer, jiffies + expires)) - return; - } - block->timer.function = dasd_block_timeout; - block->timer.data = (unsigned long) block; - block->timer.expires = jiffies + expires; - add_timer(&block->timer); + if (expires == 0) + del_timer(&block->timer); + else + mod_timer(&block->timer, jiffies + expires); } /* @@ -1606,8 +1593,7 @@ void dasd_block_set_timer(struct dasd_block *block, int expires) */ void dasd_block_clear_timer(struct dasd_block *block) { - if (timer_pending(&block->timer)) - del_timer(&block->timer); + del_timer(&block->timer); } /* diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index 300e28a531f..34339902efb 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -677,7 +677,7 @@ static ssize_t dasd_ff_show(struct device *dev, struct device_attribute *attr, struct dasd_devmap *devmap; int ff_flag; - devmap = dasd_find_busid(dev->bus_id); + devmap = dasd_find_busid(dev_name(dev)); if (!IS_ERR(devmap)) ff_flag = (devmap->features & DASD_FEATURE_FAILFAST) != 0; else diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig index 6b996db0dd6..604bd1e0d54 100644 --- a/drivers/staging/android/Kconfig +++ b/drivers/staging/android/Kconfig @@ -27,6 +27,7 @@ menuconfig ANDROID_RAM_CONSOLE_ERROR_CORRECTION bool "Android RAM Console Enable error correction" default n depends on ANDROID_RAM_CONSOLE + depends on !ANDROID_RAM_CONSOLE_EARLY_INIT select REED_SOLOMON select REED_SOLOMON_ENC8 select REED_SOLOMON_DEC8 diff --git a/drivers/staging/android/ram_console.c b/drivers/staging/android/ram_console.c index bf006857a87..643ac5ce381 100644 --- a/drivers/staging/android/ram_console.c +++ b/drivers/staging/android/ram_console.c @@ -224,9 +224,23 @@ static int __init ram_console_init(struct ram_console_buffer *buffer, ram_console_buffer_size = buffer_size - sizeof(struct ram_console_buffer); + if (ram_console_buffer_size > buffer_size) { + pr_err("ram_console: buffer %p, invalid size %d, datasize %d\n", + buffer, buffer_size, ram_console_buffer_size); + return 0; + } + #ifdef CONFIG_ANDROID_RAM_CONSOLE_ERROR_CORRECTION ram_console_buffer_size -= (DIV_ROUND_UP(ram_console_buffer_size, ECC_BLOCK_SIZE) + 1) * ECC_SIZE; + + if (ram_console_buffer_size > buffer_size) { + pr_err("ram_console: buffer %p, invalid size %d, " + "non-ecc datasize %d\n", + buffer, buffer_size, ram_console_buffer_size); + return 0; + } + ram_console_par_buffer = buffer->data + ram_console_buffer_size; diff --git a/drivers/staging/android/timed_gpio.c b/drivers/staging/android/timed_gpio.c index 903270cbbe0..33daff0481d 100644 --- a/drivers/staging/android/timed_gpio.c +++ b/drivers/staging/android/timed_gpio.c @@ -50,7 +50,7 @@ static ssize_t gpio_enable_show(struct device *dev, struct device_attribute *att if (hrtimer_active(&gpio_data->timer)) { ktime_t r = hrtimer_get_remaining(&gpio_data->timer); struct timeval t = ktime_to_timeval(r); - remaining = t.tv_sec * 1000 + t.tv_usec; + remaining = t.tv_sec * 1000 + t.tv_usec / 1000; } else remaining = 0; diff --git a/drivers/staging/at76_usb/Kconfig b/drivers/staging/at76_usb/Kconfig index 4c0e55e1544..8606f962162 100644 --- a/drivers/staging/at76_usb/Kconfig +++ b/drivers/staging/at76_usb/Kconfig @@ -1,6 +1,6 @@ config USB_ATMEL tristate "Atmel at76c503/at76c505/at76c505a USB cards" - depends on MAC80211 && WLAN_80211 && USB + depends on WLAN_80211 && USB default N select FW_LOADER ---help--- diff --git a/drivers/staging/at76_usb/at76_usb.c b/drivers/staging/at76_usb/at76_usb.c index 185533e5476..c8e4d31c7df 100644 --- a/drivers/staging/at76_usb/at76_usb.c +++ b/drivers/staging/at76_usb/at76_usb.c @@ -6,7 +6,6 @@ * Copyright (c) 2004 Nick Jones * Copyright (c) 2004 Balint Seeber <n0_5p4m_p13453@hotmail.com> * Copyright (c) 2007 Guido Guenther <agx@sigxcpu.org> - * Copyright (c) 2007 Kalle Valo <kalle.valo@iki.fi> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as @@ -17,13 +16,6 @@ * Atmel AT76C503A/505/505A. * * Some iw_handler code was taken from airo.c, (C) 1999 Benjamin Reed - * - * TODO for the mac80211 port: - * o adhoc support - * o RTS/CTS support - * o Power Save Mode support - * o support for short/long preambles - * o export variables through debugfs/sysfs */ #include <linux/init.h> @@ -44,7 +36,7 @@ #include <net/ieee80211_radiotap.h> #include <linux/firmware.h> #include <linux/leds.h> -#include <net/mac80211.h> +#include <net/ieee80211.h> #include "at76_usb.h" @@ -84,43 +76,31 @@ #define DBG_WE_EVENTS 0x08000000 /* dump wireless events */ #define DBG_FW 0x10000000 /* firmware download */ #define DBG_DFU 0x20000000 /* device firmware upgrade */ -#define DBG_CMD 0x40000000 -#define DBG_MAC80211 0x80000000 #define DBG_DEFAULTS 0 /* Use our own dbg macro */ #define at76_dbg(bits, format, arg...) \ -do { \ - if (at76_debug & (bits)) \ - printk(KERN_DEBUG DRIVER_NAME ": " format "\n" , ## arg); \ -} while (0) - -#define at76_dbg_dump(bits, buf, len, format, arg...) \ -do { \ - if (at76_debug & (bits)) { \ + do { \ + if (at76_debug & (bits)) \ printk(KERN_DEBUG DRIVER_NAME ": " format "\n" , ## arg); \ - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, buf, len); \ - } \ -} while (0) + } while (0) static int at76_debug = DBG_DEFAULTS; -#define FIRMWARE_IS_WPA(ver) ((ver.major == 1) && (ver.minor == 103)) - /* Protect against concurrent firmware loading and parsing */ static struct mutex fw_mutex; static struct fwentry firmwares[] = { - [0] = { "" }, - [BOARD_503_ISL3861] = { "atmel_at76c503-i3861.bin" }, - [BOARD_503_ISL3863] = { "atmel_at76c503-i3863.bin" }, - [BOARD_503] = { "atmel_at76c503-rfmd.bin" }, - [BOARD_503_ACC] = { "atmel_at76c503-rfmd-acc.bin" }, - [BOARD_505] = { "atmel_at76c505-rfmd.bin" }, - [BOARD_505_2958] = { "atmel_at76c505-rfmd2958.bin" }, - [BOARD_505A] = { "atmel_at76c505a-rfmd2958.bin" }, - [BOARD_505AMX] = { "atmel_at76c505amx-rfmd.bin" }, + [0] = {""}, + [BOARD_503_ISL3861] = {"atmel_at76c503-i3861.bin"}, + [BOARD_503_ISL3863] = {"atmel_at76c503-i3863.bin"}, + [BOARD_503] = {"atmel_at76c503-rfmd.bin"}, + [BOARD_503_ACC] = {"atmel_at76c503-rfmd-acc.bin"}, + [BOARD_505] = {"atmel_at76c505-rfmd.bin"}, + [BOARD_505_2958] = {"atmel_at76c505-rfmd2958.bin"}, + [BOARD_505A] = {"atmel_at76c505a-rfmd2958.bin"}, + [BOARD_505AMX] = {"atmel_at76c505amx-rfmd.bin"}, }; #define USB_DEVICE_DATA(__ops) .driver_info = (kernel_ulong_t)(__ops) @@ -130,133 +110,135 @@ static struct usb_device_id dev_table[] = { * at76c503-i3861 */ /* Generic AT76C503/3861 device */ - { USB_DEVICE(0x03eb, 0x7603), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x03eb, 0x7603), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Linksys WUSB11 v2.1/v2.6 */ - { USB_DEVICE(0x066b, 0x2211), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x066b, 0x2211), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Netgear MA101 rev. A */ - { USB_DEVICE(0x0864, 0x4100), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x0864, 0x4100), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Tekram U300C / Allnet ALL0193 */ - { USB_DEVICE(0x0b3b, 0x1612), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x0b3b, 0x1612), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* HP HN210W J7801A */ - { USB_DEVICE(0x03f0, 0x011c), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x03f0, 0x011c), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Sitecom/Z-Com/Zyxel M4Y-750 */ - { USB_DEVICE(0x0cde, 0x0001), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x0cde, 0x0001), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Dynalink/Askey WLL013 (intersil) */ - { USB_DEVICE(0x069a, 0x0320), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x069a, 0x0320), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* EZ connect 11Mpbs Wireless USB Adapter SMC2662W v1 */ - { USB_DEVICE(0x0d5c, 0xa001), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x0d5c, 0xa001), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* BenQ AWL300 */ - { USB_DEVICE(0x04a5, 0x9000), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x04a5, 0x9000), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Addtron AWU-120, Compex WLU11 */ - { USB_DEVICE(0x05dd, 0xff31), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x05dd, 0xff31), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Intel AP310 AnyPoint II USB */ - { USB_DEVICE(0x8086, 0x0200), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x8086, 0x0200), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Dynalink L11U */ - { USB_DEVICE(0x0d8e, 0x7100), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x0d8e, 0x7100), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* Arescom WL-210, FCC id 07J-GL2411USB */ - { USB_DEVICE(0x0d8e, 0x7110), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x0d8e, 0x7110), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* I-O DATA WN-B11/USB */ - { USB_DEVICE(0x04bb, 0x0919), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x04bb, 0x0919), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* BT Voyager 1010 */ - { USB_DEVICE(0x069a, 0x0821), USB_DEVICE_DATA(BOARD_503_ISL3861) }, + {USB_DEVICE(0x069a, 0x0821), USB_DEVICE_DATA(BOARD_503_ISL3861)}, /* * at76c503-i3863 */ /* Generic AT76C503/3863 device */ - { USB_DEVICE(0x03eb, 0x7604), USB_DEVICE_DATA(BOARD_503_ISL3863) }, + {USB_DEVICE(0x03eb, 0x7604), USB_DEVICE_DATA(BOARD_503_ISL3863)}, /* Samsung SWL-2100U */ - { USB_DEVICE(0x055d, 0xa000), USB_DEVICE_DATA(BOARD_503_ISL3863) }, + {USB_DEVICE(0x055d, 0xa000), USB_DEVICE_DATA(BOARD_503_ISL3863)}, /* * at76c503-rfmd */ /* Generic AT76C503/RFMD device */ - { USB_DEVICE(0x03eb, 0x7605), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x03eb, 0x7605), USB_DEVICE_DATA(BOARD_503)}, /* Dynalink/Askey WLL013 (rfmd) */ - { USB_DEVICE(0x069a, 0x0321), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x069a, 0x0321), USB_DEVICE_DATA(BOARD_503)}, /* Linksys WUSB11 v2.6 */ - { USB_DEVICE(0x077b, 0x2219), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x077b, 0x2219), USB_DEVICE_DATA(BOARD_503)}, /* Network Everywhere NWU11B */ - { USB_DEVICE(0x077b, 0x2227), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x077b, 0x2227), USB_DEVICE_DATA(BOARD_503)}, /* Netgear MA101 rev. B */ - { USB_DEVICE(0x0864, 0x4102), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x0864, 0x4102), USB_DEVICE_DATA(BOARD_503)}, /* D-Link DWL-120 rev. E */ - { USB_DEVICE(0x2001, 0x3200), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x2001, 0x3200), USB_DEVICE_DATA(BOARD_503)}, /* Actiontec 802UAT1, HWU01150-01UK */ - { USB_DEVICE(0x1668, 0x7605), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x1668, 0x7605), USB_DEVICE_DATA(BOARD_503)}, /* AirVast W-Buddie WN210 */ - { USB_DEVICE(0x03eb, 0x4102), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x03eb, 0x4102), USB_DEVICE_DATA(BOARD_503)}, /* Dick Smith Electronics XH1153 802.11b USB adapter */ - { USB_DEVICE(0x1371, 0x5743), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x1371, 0x5743), USB_DEVICE_DATA(BOARD_503)}, /* CNet CNUSB611 */ - { USB_DEVICE(0x1371, 0x0001), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x1371, 0x0001), USB_DEVICE_DATA(BOARD_503)}, /* FiberLine FL-WL200U */ - { USB_DEVICE(0x1371, 0x0002), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x1371, 0x0002), USB_DEVICE_DATA(BOARD_503)}, /* BenQ AWL400 USB stick */ - { USB_DEVICE(0x04a5, 0x9001), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x04a5, 0x9001), USB_DEVICE_DATA(BOARD_503)}, /* 3Com 3CRSHEW696 */ - { USB_DEVICE(0x0506, 0x0a01), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x0506, 0x0a01), USB_DEVICE_DATA(BOARD_503)}, /* Siemens Santis ADSL WLAN USB adapter WLL 013 */ - { USB_DEVICE(0x0681, 0x001b), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x0681, 0x001b), USB_DEVICE_DATA(BOARD_503)}, /* Belkin F5D6050, version 2 */ - { USB_DEVICE(0x050d, 0x0050), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x050d, 0x0050), USB_DEVICE_DATA(BOARD_503)}, /* iBlitzz, BWU613 (not *B or *SB) */ - { USB_DEVICE(0x07b8, 0xb000), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x07b8, 0xb000), USB_DEVICE_DATA(BOARD_503)}, /* Gigabyte GN-WLBM101 */ - { USB_DEVICE(0x1044, 0x8003), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x1044, 0x8003), USB_DEVICE_DATA(BOARD_503)}, /* Planex GW-US11S */ - { USB_DEVICE(0x2019, 0x3220), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x2019, 0x3220), USB_DEVICE_DATA(BOARD_503)}, /* Internal WLAN adapter in h5[4,5]xx series iPAQs */ - { USB_DEVICE(0x049f, 0x0032), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x049f, 0x0032), USB_DEVICE_DATA(BOARD_503)}, /* Corega Wireless LAN USB-11 mini */ - { USB_DEVICE(0x07aa, 0x0011), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x07aa, 0x0011), USB_DEVICE_DATA(BOARD_503)}, /* Corega Wireless LAN USB-11 mini2 */ - { USB_DEVICE(0x07aa, 0x0018), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x07aa, 0x0018), USB_DEVICE_DATA(BOARD_503)}, /* Uniden PCW100 */ - { USB_DEVICE(0x05dd, 0xff35), USB_DEVICE_DATA(BOARD_503) }, + {USB_DEVICE(0x05dd, 0xff35), USB_DEVICE_DATA(BOARD_503)}, /* * at76c503-rfmd-acc */ /* SMC2664W */ - { USB_DEVICE(0x083a, 0x3501), USB_DEVICE_DATA(BOARD_503_ACC) }, + {USB_DEVICE(0x083a, 0x3501), USB_DEVICE_DATA(BOARD_503_ACC)}, /* Belkin F5D6050, SMC2662W v2, SMC2662W-AR */ - { USB_DEVICE(0x0d5c, 0xa002), USB_DEVICE_DATA(BOARD_503_ACC) }, + {USB_DEVICE(0x0d5c, 0xa002), USB_DEVICE_DATA(BOARD_503_ACC)}, /* * at76c505-rfmd */ /* Generic AT76C505/RFMD */ - { USB_DEVICE(0x03eb, 0x7606), USB_DEVICE_DATA(BOARD_505) }, + {USB_DEVICE(0x03eb, 0x7606), USB_DEVICE_DATA(BOARD_505)}, /* * at76c505-rfmd2958 */ /* Generic AT76C505/RFMD, OvisLink WL-1130USB */ - { USB_DEVICE(0x03eb, 0x7613), USB_DEVICE_DATA(BOARD_505_2958) }, + {USB_DEVICE(0x03eb, 0x7613), USB_DEVICE_DATA(BOARD_505_2958)}, /* Fiberline FL-WL240U */ - { USB_DEVICE(0x1371, 0x0014), USB_DEVICE_DATA(BOARD_505_2958) }, + {USB_DEVICE(0x1371, 0x0014), USB_DEVICE_DATA(BOARD_505_2958)}, /* CNet CNUSB-611G */ - { USB_DEVICE(0x1371, 0x0013), USB_DEVICE_DATA(BOARD_505_2958) }, + {USB_DEVICE(0x1371, 0x0013), USB_DEVICE_DATA(BOARD_505_2958)}, /* Linksys WUSB11 v2.8 */ - { USB_DEVICE(0x1915, 0x2233), USB_DEVICE_DATA(BOARD_505_2958) }, + {USB_DEVICE(0x1915, 0x2233), USB_DEVICE_DATA(BOARD_505_2958)}, /* Xterasys XN-2122B, IBlitzz BWU613B/BWU613SB */ - { USB_DEVICE(0x12fd, 0x1001), USB_DEVICE_DATA(BOARD_505_2958) }, + {USB_DEVICE(0x12fd, 0x1001), USB_DEVICE_DATA(BOARD_505_2958)}, /* Corega WLAN USB Stick 11 */ - { USB_DEVICE(0x07aa, 0x7613), USB_DEVICE_DATA(BOARD_505_2958) }, + {USB_DEVICE(0x07aa, 0x7613), USB_DEVICE_DATA(BOARD_505_2958)}, /* Microstar MSI Box MS6978 */ - { USB_DEVICE(0x0db0, 0x1020), USB_DEVICE_DATA(BOARD_505_2958) }, + {USB_DEVICE(0x0db0, 0x1020), USB_DEVICE_DATA(BOARD_505_2958)}, /* * at76c505a-rfmd2958 */ /* Generic AT76C505A device */ - { USB_DEVICE(0x03eb, 0x7614), USB_DEVICE_DATA(BOARD_505A) }, + {USB_DEVICE(0x03eb, 0x7614), USB_DEVICE_DATA(BOARD_505A)}, /* Generic AT76C505AS device */ - { USB_DEVICE(0x03eb, 0x7617), USB_DEVICE_DATA(BOARD_505A) }, + {USB_DEVICE(0x03eb, 0x7617), USB_DEVICE_DATA(BOARD_505A)}, /* Siemens Gigaset USB WLAN Adapter 11 */ - { USB_DEVICE(0x1690, 0x0701), USB_DEVICE_DATA(BOARD_505A) }, + {USB_DEVICE(0x1690, 0x0701), USB_DEVICE_DATA(BOARD_505A)}, + /* OQO Model 01+ Internal Wi-Fi */ + {USB_DEVICE(0x1557, 0x0002), USB_DEVICE_DATA(BOARD_505A)}, /* * at76c505amx-rfmd */ /* Generic AT76C505AMX device */ - { USB_DEVICE(0x03eb, 0x7615), USB_DEVICE_DATA(BOARD_505AMX) }, - { } + {USB_DEVICE(0x03eb, 0x7615), USB_DEVICE_DATA(BOARD_505AMX)}, + {} }; MODULE_DEVICE_TABLE(usb, dev_table); @@ -264,8 +246,26 @@ MODULE_DEVICE_TABLE(usb, dev_table); /* Supported rates of this hardware, bit 7 marks basic rates */ static const u8 hw_rates[] = { 0x82, 0x84, 0x0b, 0x16 }; +/* Frequency of each channel in MHz */ +static const long channel_frequency[] = { + 2412, 2417, 2422, 2427, 2432, 2437, 2442, + 2447, 2452, 2457, 2462, 2467, 2472, 2484 +}; + +#define NUM_CHANNELS ARRAY_SIZE(channel_frequency) + static const char *const preambles[] = { "long", "short", "auto" }; +static const char *const mac_states[] = { + [MAC_INIT] = "INIT", + [MAC_SCANNING] = "SCANNING", + [MAC_AUTH] = "AUTH", + [MAC_ASSOC] = "ASSOC", + [MAC_JOINING] = "JOINING", + [MAC_CONNECTED] = "CONNECTED", + [MAC_OWN_IBSS] = "OWN_IBSS" +}; + /* Firmware download */ /* DFU states */ #define STATE_IDLE 0x00 @@ -300,30 +300,17 @@ struct dfu_status { static inline int at76_is_intersil(enum board_type board) { - if (board == BOARD_503_ISL3861 || board == BOARD_503_ISL3863) - return 1; - return 0; + return (board == BOARD_503_ISL3861 || board == BOARD_503_ISL3863); } static inline int at76_is_503rfmd(enum board_type board) { - if (board == BOARD_503 || board == BOARD_503_ACC) - return 1; - return 0; -} - -static inline int at76_is_505(enum board_type board) -{ - if (board == BOARD_505 || board == BOARD_505_2958) - return 1; - return 0; + return (board == BOARD_503 || board == BOARD_503_ACC); } static inline int at76_is_505a(enum board_type board) { - if (board == BOARD_505A || board == BOARD_505AMX) - return 1; - return 0; + return (board == BOARD_505A || board == BOARD_505AMX); } /* Load a block of the first (internal) part of the firmware */ @@ -504,6 +491,41 @@ exit: return ret; } +/* Report that the scan results are ready */ +static inline void at76_iwevent_scan_complete(struct net_device *netdev) +{ + union iwreq_data wrqu; + wrqu.data.length = 0; + wrqu.data.flags = 0; + wireless_send_event(netdev, SIOCGIWSCAN, &wrqu, NULL); + at76_dbg(DBG_WE_EVENTS, "%s: SIOCGIWSCAN sent", netdev->name); +} + +static inline void at76_iwevent_bss_connect(struct net_device *netdev, + u8 *bssid) +{ + union iwreq_data wrqu; + wrqu.data.length = 0; + wrqu.data.flags = 0; + memcpy(wrqu.ap_addr.sa_data, bssid, ETH_ALEN); + wrqu.ap_addr.sa_family = ARPHRD_ETHER; + wireless_send_event(netdev, SIOCGIWAP, &wrqu, NULL); + at76_dbg(DBG_WE_EVENTS, "%s: %s: SIOCGIWAP sent", netdev->name, + __func__); +} + +static inline void at76_iwevent_bss_disconnect(struct net_device *netdev) +{ + union iwreq_data wrqu; + wrqu.data.length = 0; + wrqu.data.flags = 0; + memset(wrqu.ap_addr.sa_data, 0, ETH_ALEN); + wrqu.ap_addr.sa_family = ARPHRD_ETHER; + wireless_send_event(netdev, SIOCGIWAP, &wrqu, NULL); + at76_dbg(DBG_WE_EVENTS, "%s: %s: SIOCGIWAP sent", netdev->name, + __func__); +} + #define HEX2STR_BUFFERS 4 #define HEX2STR_MAX_LEN 64 #define BIN2HEX(x) ((x) < 10 ? '0' + (x) : (x) + 'A' - 10) @@ -575,6 +597,37 @@ static void at76_ledtrig_tx_activity(void) mod_timer(&ledtrig_tx_timer, jiffies + HZ / 4); } +/* Check if the given ssid is hidden */ +static inline int at76_is_hidden_ssid(u8 *ssid, int length) +{ + static const u8 zeros[32]; + + if (length == 0) + return 1; + + if (length == 1 && ssid[0] == ' ') + return 1; + + return (memcmp(ssid, zeros, length) == 0); +} + +static inline void at76_free_bss_list(struct at76_priv *priv) +{ + struct list_head *next, *ptr; + unsigned long flags; + + spin_lock_irqsave(&priv->bss_list_spinlock, flags); + + priv->curr_bss = NULL; + + list_for_each_safe(ptr, next, &priv->bss_list) { + list_del(ptr); + kfree(list_entry(ptr, struct bss_info, list)); + } + + spin_unlock_irqrestore(&priv->bss_list_spinlock, flags); +} + static int at76_remap(struct usb_device *udev) { int ret; @@ -598,7 +651,7 @@ static int at76_get_op_mode(struct usb_device *udev) return -ENOMEM; ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), 0x33, USB_TYPE_VENDOR | USB_DIR_IN | - USB_RECIP_INTERFACE, 0x01, 0, &op_mode, 1, + USB_RECIP_INTERFACE, 0x01, 0, op_mode, 1, USB_CTRL_GET_TIMEOUT); saved = *op_mode; kfree(op_mode); @@ -676,7 +729,7 @@ exit: kfree(hwcfg); if (ret < 0) printk(KERN_ERR "%s: cannot get HW Config (error %d)\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); return ret; } @@ -685,15 +738,15 @@ static struct reg_domain const *at76_get_reg_domain(u16 code) { int i; static struct reg_domain const fd_tab[] = { - { 0x10, "FCC (USA)", 0x7ff }, /* ch 1-11 */ - { 0x20, "IC (Canada)", 0x7ff }, /* ch 1-11 */ - { 0x30, "ETSI (most of Europe)", 0x1fff }, /* ch 1-13 */ - { 0x31, "Spain", 0x600 }, /* ch 10-11 */ - { 0x32, "France", 0x1e00 }, /* ch 10-13 */ - { 0x40, "MKK (Japan)", 0x2000 }, /* ch 14 */ - { 0x41, "MKK1 (Japan)", 0x3fff }, /* ch 1-14 */ - { 0x50, "Israel", 0x3fc }, /* ch 3-9 */ - { 0x00, "<unknown>", 0xffffffff } /* ch 1-32 */ + {0x10, "FCC (USA)", 0x7ff}, /* ch 1-11 */ + {0x20, "IC (Canada)", 0x7ff}, /* ch 1-11 */ + {0x30, "ETSI (most of Europe)", 0x1fff}, /* ch 1-13 */ + {0x31, "Spain", 0x600}, /* ch 10-11 */ + {0x32, "France", 0x1e00}, /* ch 10-13 */ + {0x40, "MKK (Japan)", 0x2000}, /* ch 14 */ + {0x41, "MKK1 (Japan)", 0x3fff}, /* ch 1-14 */ + {0x50, "Israel", 0x3fc}, /* ch 3-9 */ + {0x00, "<unknown>", 0xffffffff} /* ch 1-32 */ }; /* Last entry is fallback for unknown domain code */ @@ -731,7 +784,7 @@ static inline int at76_get_cmd_status(struct usb_device *udev, u8 cmd) ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), 0x22, USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_INTERFACE, cmd, 0, stat_buf, - sizeof(stat_buf), USB_CTRL_GET_TIMEOUT); + 40, USB_CTRL_GET_TIMEOUT); if (ret >= 0) ret = stat_buf[5]; kfree(stat_buf); @@ -739,24 +792,6 @@ static inline int at76_get_cmd_status(struct usb_device *udev, u8 cmd) return ret; } -#define MAKE_CMD_CASE(c) case (c): return #c - -static const char *at76_get_cmd_string(u8 cmd_status) -{ - switch (cmd_status) { - MAKE_CMD_CASE(CMD_SET_MIB); - MAKE_CMD_CASE(CMD_GET_MIB); - MAKE_CMD_CASE(CMD_SCAN); - MAKE_CMD_CASE(CMD_JOIN); - MAKE_CMD_CASE(CMD_START_IBSS); - MAKE_CMD_CASE(CMD_RADIO_ON); - MAKE_CMD_CASE(CMD_RADIO_OFF); - MAKE_CMD_CASE(CMD_STARTUP); - } - - return "UNKNOWN"; -} - static int at76_set_card_command(struct usb_device *udev, u8 cmd, void *buf, int buf_size) { @@ -772,10 +807,6 @@ static int at76_set_card_command(struct usb_device *udev, u8 cmd, void *buf, cmd_buf->size = cpu_to_le16(buf_size); memcpy(cmd_buf->data, buf, buf_size); - at76_dbg_dump(DBG_CMD, cmd_buf, sizeof(struct at76_command) + buf_size, - "issuing command %s (0x%02x)", - at76_get_cmd_string(cmd), cmd); - ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), 0x0e, USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE, 0, 0, cmd_buf, @@ -813,13 +844,13 @@ static int at76_wait_completion(struct at76_priv *priv, int cmd) status = at76_get_cmd_status(priv->udev, cmd); if (status < 0) { printk(KERN_ERR "%s: at76_get_cmd_status failed: %d\n", - wiphy_name(priv->hw->wiphy), status); + priv->netdev->name, status); break; } at76_dbg(DBG_WAIT_COMPLETE, "%s: Waiting on cmd %d, status = %d (%s)", - wiphy_name(priv->hw->wiphy), cmd, status, + priv->netdev->name, cmd, status, at76_get_cmd_status_string(status)); if (status != CMD_STATUS_IN_PROGRESS @@ -830,7 +861,7 @@ static int at76_wait_completion(struct at76_priv *priv, int cmd) if (time_after(jiffies, timeout)) { printk(KERN_ERR "%s: completion timeout for command %d\n", - wiphy_name(priv->hw->wiphy), cmd); + priv->netdev->name, cmd); status = -ETIMEDOUT; break; } @@ -853,7 +884,7 @@ static int at76_set_mib(struct at76_priv *priv, struct set_mib_buffer *buf) if (ret != CMD_STATUS_COMPLETE) { printk(KERN_INFO "%s: set_mib: at76_wait_completion failed " - "with %d\n", wiphy_name(priv->hw->wiphy), ret); + "with %d\n", priv->netdev->name, ret); ret = -EIO; } @@ -874,7 +905,7 @@ static int at76_set_radio(struct at76_priv *priv, int enable) ret = at76_set_card_command(priv->udev, cmd, NULL, 0); if (ret < 0) printk(KERN_ERR "%s: at76_set_card_command(%d) failed: %d\n", - wiphy_name(priv->hw->wiphy), cmd, ret); + priv->netdev->name, cmd, ret); else ret = 1; @@ -895,7 +926,44 @@ static int at76_set_pm_mode(struct at76_priv *priv) ret = at76_set_mib(priv, &priv->mib_buf); if (ret < 0) printk(KERN_ERR "%s: set_mib (pm_mode) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); + + return ret; +} + +/* Set the association id for power save mode */ +static int at76_set_associd(struct at76_priv *priv, u16 id) +{ + int ret = 0; + + priv->mib_buf.type = MIB_MAC_MGMT; + priv->mib_buf.size = 2; + priv->mib_buf.index = offsetof(struct mib_mac_mgmt, station_id); + priv->mib_buf.data.word = cpu_to_le16(id); + + ret = at76_set_mib(priv, &priv->mib_buf); + if (ret < 0) + printk(KERN_ERR "%s: set_mib (associd) failed: %d\n", + priv->netdev->name, ret); + + return ret; +} + +/* Set the listen interval for power save mode */ +static int at76_set_listen_interval(struct at76_priv *priv, u16 interval) +{ + int ret = 0; + + priv->mib_buf.type = MIB_MAC; + priv->mib_buf.size = 2; + priv->mib_buf.index = offsetof(struct mib_mac, listen_interval); + priv->mib_buf.data.word = cpu_to_le16(interval); + + ret = at76_set_mib(priv, &priv->mib_buf); + if (ret < 0) + printk(KERN_ERR + "%s: set_mib (listen_interval) failed: %d\n", + priv->netdev->name, ret); return ret; } @@ -912,7 +980,7 @@ static int at76_set_preamble(struct at76_priv *priv, u8 type) ret = at76_set_mib(priv, &priv->mib_buf); if (ret < 0) printk(KERN_ERR "%s: set_mib (preamble) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); return ret; } @@ -929,7 +997,7 @@ static int at76_set_frag(struct at76_priv *priv, u16 size) ret = at76_set_mib(priv, &priv->mib_buf); if (ret < 0) printk(KERN_ERR "%s: set_mib (frag threshold) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); return ret; } @@ -946,7 +1014,7 @@ static int at76_set_rts(struct at76_priv *priv, u16 size) ret = at76_set_mib(priv, &priv->mib_buf); if (ret < 0) printk(KERN_ERR "%s: set_mib (rts) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); return ret; } @@ -963,41 +1031,24 @@ static int at76_set_autorate_fallback(struct at76_priv *priv, int onoff) ret = at76_set_mib(priv, &priv->mib_buf); if (ret < 0) printk(KERN_ERR "%s: set_mib (autorate fallback) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); return ret; } -static int at76_set_tkip_bssid(struct at76_priv *priv, const void *addr) +static int at76_add_mac_address(struct at76_priv *priv, void *addr) { int ret = 0; - priv->mib_buf.type = MIB_MAC_ENCRYPTION; + priv->mib_buf.type = MIB_MAC_ADDR; priv->mib_buf.size = ETH_ALEN; - priv->mib_buf.index = offsetof(struct mib_mac_encryption, tkip_bssid); + priv->mib_buf.index = offsetof(struct mib_mac_addr, mac_addr); memcpy(priv->mib_buf.data.addr, addr, ETH_ALEN); ret = at76_set_mib(priv, &priv->mib_buf); if (ret < 0) - printk(KERN_ERR "%s: set_mib (MAC_ENCRYPTION, tkip_bssid) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); - - return ret; -} - -static int at76_reset_rsc(struct at76_priv *priv) -{ - int ret = 0; - - priv->mib_buf.type = MIB_MAC_ENCRYPTION; - priv->mib_buf.size = 4 * 8; - priv->mib_buf.index = offsetof(struct mib_mac_encryption, key_rsc); - memset(priv->mib_buf.data.data, 0 , priv->mib_buf.size); - - ret = at76_set_mib(priv, &priv->mib_buf); - if (ret < 0) - printk(KERN_ERR "%s: set_mib (MAC_ENCRYPTION, key_rsc) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + printk(KERN_ERR "%s: set_mib (MAC_ADDR, mac_addr) failed: %d\n", + priv->netdev->name, ret); return ret; } @@ -1016,16 +1067,16 @@ static void at76_dump_mib_mac_addr(struct at76_priv *priv) sizeof(struct mib_mac_addr)); if (ret < 0) { printk(KERN_ERR "%s: at76_get_mib (MAC_ADDR) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); goto exit; } at76_dbg(DBG_MIB, "%s: MIB MAC_ADDR: mac_addr %s res 0x%x 0x%x", - wiphy_name(priv->hw->wiphy), + priv->netdev->name, mac2str(m->mac_addr), m->res[0], m->res[1]); for (i = 0; i < ARRAY_SIZE(m->group_addr); i++) at76_dbg(DBG_MIB, "%s: MIB MAC_ADDR: group addr %d: %s, " - "status %d", wiphy_name(priv->hw->wiphy), i, + "status %d", priv->netdev->name, i, mac2str(m->group_addr[i]), m->group_addr_status[i]); exit: kfree(m); @@ -1045,13 +1096,13 @@ static void at76_dump_mib_mac_wep(struct at76_priv *priv) sizeof(struct mib_mac_wep)); if (ret < 0) { printk(KERN_ERR "%s: at76_get_mib (MAC_WEP) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); goto exit; } at76_dbg(DBG_MIB, "%s: MIB MAC_WEP: priv_invoked %u def_key_id %u " "key_len %u excl_unencr %u wep_icv_err %u wep_excluded %u " - "encr_level %u key %d", wiphy_name(priv->hw->wiphy), + "encr_level %u key %d", priv->netdev->name, m->privacy_invoked, m->wep_default_key_id, m->wep_key_mapping_len, m->exclude_unencrypted, le32_to_cpu(m->wep_icv_error_count), @@ -1063,55 +1114,12 @@ static void at76_dump_mib_mac_wep(struct at76_priv *priv) for (i = 0; i < WEP_KEYS; i++) at76_dbg(DBG_MIB, "%s: MIB MAC_WEP: key %d: %s", - wiphy_name(priv->hw->wiphy), i, + priv->netdev->name, i, hex2str(m->wep_default_keyvalue[i], key_len)); exit: kfree(m); } -static void at76_dump_mib_mac_encryption(struct at76_priv *priv) -{ - int i; - int ret; - /*int key_len;*/ - struct mib_mac_encryption *m; - - m = kmalloc(sizeof(struct mib_mac_encryption), GFP_KERNEL); - if (!m) - return; - - ret = at76_get_mib(priv->udev, MIB_MAC_ENCRYPTION, m, - sizeof(struct mib_mac_encryption)); - if (ret < 0) { - dev_err(&priv->udev->dev, - "%s: at76_get_mib (MAC_ENCRYPTION) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); - goto exit; - } - - at76_dbg(DBG_MIB, - "%s: MIB MAC_ENCRYPTION: tkip_bssid %s priv_invoked %u " - "ciph_key_id %u grp_key_id %u excl_unencr %u " - "ckip_key_perm %u wep_icv_err %u wep_excluded %u", - wiphy_name(priv->hw->wiphy), mac2str(m->tkip_bssid), - m->privacy_invoked, m->cipher_default_key_id, - m->cipher_default_group_key_id, m->exclude_unencrypted, - m->ckip_key_permutation, - le32_to_cpu(m->wep_icv_error_count), - le32_to_cpu(m->wep_excluded_count)); - - /*key_len = (m->encryption_level == 1) ? - WEP_SMALL_KEY_LEN : WEP_LARGE_KEY_LEN;*/ - - for (i = 0; i < CIPHER_KEYS; i++) - at76_dbg(DBG_MIB, "%s: MIB MAC_ENCRYPTION: key %d: %s", - wiphy_name(priv->hw->wiphy), i, - hex2str(m->cipher_default_keyvalue[i], - CIPHER_KEY_LEN)); -exit: - kfree(m); -} - static void at76_dump_mib_mac_mgmt(struct at76_priv *priv) { int ret; @@ -1125,7 +1133,7 @@ static void at76_dump_mib_mac_mgmt(struct at76_priv *priv) sizeof(struct mib_mac_mgmt)); if (ret < 0) { printk(KERN_ERR "%s: at76_get_mib (MAC_MGMT) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); goto exit; } @@ -1136,7 +1144,7 @@ static void at76_dump_mib_mac_mgmt(struct at76_priv *priv) "pm_mode %d ibss_change %d res %d " "multi_domain_capability_implemented %d " "international_roaming %d country_string %.3s", - wiphy_name(priv->hw->wiphy), le16_to_cpu(m->beacon_period), + priv->netdev->name, le16_to_cpu(m->beacon_period), le16_to_cpu(m->CFP_max_duration), le16_to_cpu(m->medium_occupancy_limit), le16_to_cpu(m->station_id), le16_to_cpu(m->ATIM_window), @@ -1161,7 +1169,7 @@ static void at76_dump_mib_mac(struct at76_priv *priv) ret = at76_get_mib(priv->udev, MIB_MAC, m, sizeof(struct mib_mac)); if (ret < 0) { printk(KERN_ERR "%s: at76_get_mib (MAC) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); goto exit; } @@ -1171,8 +1179,7 @@ static void at76_dump_mib_mac(struct at76_priv *priv) "scan_type %d scan_channel %d probe_delay %u " "min_channel_time %d max_channel_time %d listen_int %d " "desired_ssid %s desired_bssid %s desired_bsstype %d", - wiphy_name(priv->hw->wiphy), - le32_to_cpu(m->max_tx_msdu_lifetime), + priv->netdev->name, le32_to_cpu(m->max_tx_msdu_lifetime), le32_to_cpu(m->max_rx_lifetime), le16_to_cpu(m->frag_threshold), le16_to_cpu(m->rts_threshold), le16_to_cpu(m->cwmin), le16_to_cpu(m->cwmax), @@ -1198,7 +1205,7 @@ static void at76_dump_mib_phy(struct at76_priv *priv) ret = at76_get_mib(priv->udev, MIB_PHY, m, sizeof(struct mib_phy)); if (ret < 0) { printk(KERN_ERR "%s: at76_get_mib (PHY) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); goto exit; } @@ -1207,7 +1214,7 @@ static void at76_dump_mib_phy(struct at76_priv *priv) "mpdu_max_length %d cca_mode_supported %d operation_rate_set " "0x%x 0x%x 0x%x 0x%x channel_id %d current_cca_mode %d " "phy_type %d current_reg_domain %d", - wiphy_name(priv->hw->wiphy), le32_to_cpu(m->ed_threshold), + priv->netdev->name, le32_to_cpu(m->ed_threshold), le16_to_cpu(m->slot_time), le16_to_cpu(m->sifs_time), le16_to_cpu(m->preamble_length), le16_to_cpu(m->plcp_header_length), @@ -1231,14 +1238,13 @@ static void at76_dump_mib_local(struct at76_priv *priv) ret = at76_get_mib(priv->udev, MIB_LOCAL, m, sizeof(struct mib_local)); if (ret < 0) { printk(KERN_ERR "%s: at76_get_mib (LOCAL) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); goto exit; } at76_dbg(DBG_MIB, "%s: MIB LOCAL: beacon_enable %d " "txautorate_fallback %d ssid_size %d promiscuous_mode %d " - "preamble_type %d", wiphy_name(priv->hw->wiphy), - m->beacon_enable, + "preamble_type %d", priv->netdev->name, m->beacon_enable, m->txautorate_fallback, m->ssid_size, m->promiscuous_mode, m->preamble_type); exit: @@ -1257,21 +1263,118 @@ static void at76_dump_mib_mdomain(struct at76_priv *priv) sizeof(struct mib_mdomain)); if (ret < 0) { printk(KERN_ERR "%s: at76_get_mib (MDOMAIN) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); goto exit; } at76_dbg(DBG_MIB, "%s: MIB MDOMAIN: channel_list %s", - wiphy_name(priv->hw->wiphy), + priv->netdev->name, hex2str(m->channel_list, sizeof(m->channel_list))); at76_dbg(DBG_MIB, "%s: MIB MDOMAIN: tx_powerlevel %s", - wiphy_name(priv->hw->wiphy), + priv->netdev->name, hex2str(m->tx_powerlevel, sizeof(m->tx_powerlevel))); exit: kfree(m); } +static int at76_get_current_bssid(struct at76_priv *priv) +{ + int ret = 0; + struct mib_mac_mgmt *mac_mgmt = + kmalloc(sizeof(struct mib_mac_mgmt), GFP_KERNEL); + + if (!mac_mgmt) { + ret = -ENOMEM; + goto exit; + } + + ret = at76_get_mib(priv->udev, MIB_MAC_MGMT, mac_mgmt, + sizeof(struct mib_mac_mgmt)); + if (ret < 0) { + printk(KERN_ERR "%s: at76_get_mib failed: %d\n", + priv->netdev->name, ret); + goto error; + } + memcpy(priv->bssid, mac_mgmt->current_bssid, ETH_ALEN); + printk(KERN_INFO "%s: using BSSID %s\n", priv->netdev->name, + mac2str(priv->bssid)); +error: + kfree(mac_mgmt); +exit: + return ret; +} + +static int at76_get_current_channel(struct at76_priv *priv) +{ + int ret = 0; + struct mib_phy *phy = kmalloc(sizeof(struct mib_phy), GFP_KERNEL); + + if (!phy) { + ret = -ENOMEM; + goto exit; + } + ret = at76_get_mib(priv->udev, MIB_PHY, phy, sizeof(struct mib_phy)); + if (ret < 0) { + printk(KERN_ERR "%s: at76_get_mib(MIB_PHY) failed: %d\n", + priv->netdev->name, ret); + goto error; + } + priv->channel = phy->channel_id; +error: + kfree(phy); +exit: + return ret; +} + +/** + * at76_start_scan - start a scan + * + * @use_essid - use the configured ESSID in non passive mode + */ +static int at76_start_scan(struct at76_priv *priv, int use_essid) +{ + struct at76_req_scan scan; + + memset(&scan, 0, sizeof(struct at76_req_scan)); + memset(scan.bssid, 0xff, ETH_ALEN); + + if (use_essid) { + memcpy(scan.essid, priv->essid, IW_ESSID_MAX_SIZE); + scan.essid_size = priv->essid_size; + } else + scan.essid_size = 0; + + /* jal: why should we start at a certain channel? we do scan the whole + range allowed by reg domain. */ + scan.channel = priv->channel; + + /* atmelwlandriver differs between scan type 0 and 1 (active/passive) + For ad-hoc mode, it uses type 0 only. */ + scan.scan_type = priv->scan_mode; + + /* INFO: For probe_delay, not multiplying by 1024 as this will be + slightly less than min_channel_time + (per spec: probe delay < min. channel time) */ + scan.min_channel_time = cpu_to_le16(priv->scan_min_time); + scan.max_channel_time = cpu_to_le16(priv->scan_max_time); + scan.probe_delay = cpu_to_le16(priv->scan_min_time * 1000); + scan.international_scan = 0; + + /* other values are set to 0 for type 0 */ + + at76_dbg(DBG_PROGRESS, "%s: start_scan (use_essid = %d, intl = %d, " + "channel = %d, probe_delay = %d, scan_min_time = %d, " + "scan_max_time = %d)", + priv->netdev->name, use_essid, + scan.international_scan, scan.channel, + le16_to_cpu(scan.probe_delay), + le16_to_cpu(scan.min_channel_time), + le16_to_cpu(scan.max_channel_time)); + + return at76_set_card_command(priv->udev, CMD_SCAN, &scan, sizeof(scan)); +} + /* Enable monitor mode */ static int at76_start_monitor(struct at76_priv *priv) { @@ -1292,6 +1395,86 @@ static int at76_start_monitor(struct at76_priv *priv) return ret; } +static int at76_start_ibss(struct at76_priv *priv) +{ + struct at76_req_ibss bss; + int ret; + + WARN_ON(priv->mac_state != MAC_OWN_IBSS); + if (priv->mac_state != MAC_OWN_IBSS) + return -EBUSY; + + memset(&bss, 0, sizeof(struct at76_req_ibss)); + memset(bss.bssid, 0xff, ETH_ALEN); + memcpy(bss.essid, priv->essid, IW_ESSID_MAX_SIZE); + bss.essid_size = priv->essid_size; + bss.bss_type = ADHOC_MODE; + bss.channel = priv->channel; + + ret = at76_set_card_command(priv->udev, CMD_START_IBSS, &bss, + sizeof(struct at76_req_ibss)); + if (ret < 0) { + printk(KERN_ERR "%s: start_ibss failed: %d\n", + priv->netdev->name, ret); + return ret; + } + + ret = at76_wait_completion(priv, CMD_START_IBSS); + if (ret != CMD_STATUS_COMPLETE) { + printk(KERN_ERR "%s: start_ibss failed to complete, %d\n", + priv->netdev->name, ret); + return ret; + } + + ret = at76_get_current_bssid(priv); + if (ret < 0) + return ret; + + ret = at76_get_current_channel(priv); + if (ret < 0) + return ret; + + /* not sure what this is good for ??? */ + priv->mib_buf.type = MIB_MAC_MGMT; + priv->mib_buf.size = 1; + priv->mib_buf.index = offsetof(struct mib_mac_mgmt, ibss_change); + priv->mib_buf.data.byte = 0; + + ret = at76_set_mib(priv, &priv->mib_buf); + if (ret < 0) { + printk(KERN_ERR "%s: set_mib (ibss change ok) failed: %d\n", + priv->netdev->name, ret); + return ret; + } + + netif_carrier_on(priv->netdev); + netif_start_queue(priv->netdev); + return 0; +} + +/* Request card to join BSS in managed or ad-hoc mode */ +static int at76_join_bss(struct at76_priv *priv, struct bss_info *ptr) +{ + struct at76_req_join join; + + BUG_ON(!ptr); + + memset(&join, 0, sizeof(struct at76_req_join)); + memcpy(join.bssid, ptr->bssid, ETH_ALEN); + memcpy(join.essid, ptr->ssid, ptr->ssid_len); + join.essid_size = ptr->ssid_len; + join.bss_type = (priv->iw_mode == IW_MODE_ADHOC ? 1 : 2); + join.channel = ptr->channel; + join.timeout = cpu_to_le16(2000); + + at76_dbg(DBG_PROGRESS, + "%s join addr %s ssid %s type %d ch %d timeout %d", + priv->netdev->name, mac2str(join.bssid), join.essid, + join.bss_type, join.channel, le16_to_cpu(join.timeout)); + return at76_set_card_command(priv->udev, CMD_JOIN, &join, + sizeof(struct at76_req_join)); +} + /* Calculate padding from txbuf->wlength (which excludes the USB TX header), likely to compensate a flaw in the AT76C503A USB part ... */ static inline int at76_calc_padding(int wlen) @@ -1310,6 +1493,14 @@ static inline int at76_calc_padding(int wlen) return 0; } +/* We are doing a lot of things here in an interrupt. Need + a bh handler (Watching TV with a TV card is probably + a good test: if you see flickers, we are doing too much. + Currently I do see flickers... even with our tasklet :-( ) + Maybe because the bttv driver and usb-uhci use the same interrupt +*/ +/* Or maybe because our BH handler is preempting bttv's BH handler.. BHs don't + * solve everything.. (alex) */ static void at76_rx_callback(struct urb *urb) { struct at76_priv *priv = urb->context; @@ -1319,6 +1510,1758 @@ static void at76_rx_callback(struct urb *urb) return; } +static void at76_tx_callback(struct urb *urb) +{ + struct at76_priv *priv = urb->context; + struct net_device_stats *stats = &priv->stats; + unsigned long flags; + struct at76_tx_buffer *mgmt_buf; + int ret; + + switch (urb->status) { + case 0: + stats->tx_packets++; + break; + case -ENOENT: + case -ECONNRESET: + /* urb has been unlinked */ + return; + default: + at76_dbg(DBG_URB, "%s - nonzero tx status received: %d", + __func__, urb->status); + stats->tx_errors++; + break; + } + + spin_lock_irqsave(&priv->mgmt_spinlock, flags); + mgmt_buf = priv->next_mgmt_bulk; + priv->next_mgmt_bulk = NULL; + spin_unlock_irqrestore(&priv->mgmt_spinlock, flags); + + if (!mgmt_buf) { + netif_wake_queue(priv->netdev); + return; + } + + /* we don't copy the padding bytes, but add them + to the length */ + memcpy(priv->bulk_out_buffer, mgmt_buf, + le16_to_cpu(mgmt_buf->wlength) + AT76_TX_HDRLEN); + usb_fill_bulk_urb(priv->tx_urb, priv->udev, priv->tx_pipe, + priv->bulk_out_buffer, + le16_to_cpu(mgmt_buf->wlength) + mgmt_buf->padding + + AT76_TX_HDRLEN, at76_tx_callback, priv); + ret = usb_submit_urb(priv->tx_urb, GFP_ATOMIC); + if (ret) + printk(KERN_ERR "%s: error in tx submit urb: %d\n", + priv->netdev->name, ret); + + kfree(mgmt_buf); +} + +/* Send a management frame on bulk-out. txbuf->wlength must be set */ +static int at76_tx_mgmt(struct at76_priv *priv, struct at76_tx_buffer *txbuf) +{ + unsigned long flags; + int ret; + int urb_status; + void *oldbuf = NULL; + + netif_carrier_off(priv->netdev); /* stop netdev watchdog */ + netif_stop_queue(priv->netdev); /* stop tx data packets */ + + spin_lock_irqsave(&priv->mgmt_spinlock, flags); + + urb_status = priv->tx_urb->status; + if (urb_status == -EINPROGRESS) { + /* cannot transmit now, put in the queue */ + oldbuf = priv->next_mgmt_bulk; + priv->next_mgmt_bulk = txbuf; + } + spin_unlock_irqrestore(&priv->mgmt_spinlock, flags); + + if (oldbuf) { + /* a data/mgmt tx is already pending in the URB - + if this is no error in some situations we must + implement a queue or silently modify the old msg */ + printk(KERN_ERR "%s: removed pending mgmt buffer %s\n", + priv->netdev->name, hex2str(oldbuf, 64)); + kfree(oldbuf); + return 0; + } + + txbuf->tx_rate = TX_RATE_1MBIT; + txbuf->padding = at76_calc_padding(le16_to_cpu(txbuf->wlength)); + memset(txbuf->reserved, 0, sizeof(txbuf->reserved)); + + if (priv->next_mgmt_bulk) + printk(KERN_ERR "%s: URB status %d, but mgmt is pending\n", + priv->netdev->name, urb_status); + + at76_dbg(DBG_TX_MGMT, + "%s: tx mgmt: wlen %d tx_rate %d pad %d %s", + priv->netdev->name, le16_to_cpu(txbuf->wlength), + txbuf->tx_rate, txbuf->padding, + hex2str(txbuf->packet, le16_to_cpu(txbuf->wlength))); + + /* txbuf was not consumed above -> send mgmt msg immediately */ + memcpy(priv->bulk_out_buffer, txbuf, + le16_to_cpu(txbuf->wlength) + AT76_TX_HDRLEN); + usb_fill_bulk_urb(priv->tx_urb, priv->udev, priv->tx_pipe, + priv->bulk_out_buffer, + le16_to_cpu(txbuf->wlength) + txbuf->padding + + AT76_TX_HDRLEN, at76_tx_callback, priv); + ret = usb_submit_urb(priv->tx_urb, GFP_ATOMIC); + if (ret) + printk(KERN_ERR "%s: error in tx submit urb: %d\n", + priv->netdev->name, ret); + + kfree(txbuf); + + return ret; +} + +/* Go to the next information element */ +static inline void next_ie(struct ieee80211_info_element **ie) +{ + *ie = (struct ieee80211_info_element *)(&(*ie)->data[(*ie)->len]); +} + +/* Challenge is the challenge string (in TLV format) + we got with seq_nr 2 for shared secret authentication only and + send in seq_nr 3 WEP encrypted to prove we have the correct WEP key; + otherwise it is NULL */ +static int at76_auth_req(struct at76_priv *priv, struct bss_info *bss, + int seq_nr, struct ieee80211_info_element *challenge) +{ + struct at76_tx_buffer *tx_buffer; + struct ieee80211_hdr_3addr *mgmt; + struct ieee80211_auth *req; + int buf_len = (seq_nr != 3 ? AUTH_FRAME_SIZE : + AUTH_FRAME_SIZE + 1 + 1 + challenge->len); + + BUG_ON(!bss); + BUG_ON(seq_nr == 3 && !challenge); + tx_buffer = kmalloc(buf_len + MAX_PADDING_SIZE, GFP_ATOMIC); + if (!tx_buffer) + return -ENOMEM; + + req = (struct ieee80211_auth *)tx_buffer->packet; + mgmt = &req->header; + + /* make wireless header */ + /* first auth msg is not encrypted, only the second (seq_nr == 3) */ + mgmt->frame_ctl = + cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH | + (seq_nr == 3 ? IEEE80211_FCTL_PROTECTED : 0)); + + mgmt->duration_id = cpu_to_le16(0x8000); + memcpy(mgmt->addr1, bss->bssid, ETH_ALEN); + memcpy(mgmt->addr2, priv->netdev->dev_addr, ETH_ALEN); + memcpy(mgmt->addr3, bss->bssid, ETH_ALEN); + mgmt->seq_ctl = cpu_to_le16(0); + + req->algorithm = cpu_to_le16(priv->auth_mode); + req->transaction = cpu_to_le16(seq_nr); + req->status = cpu_to_le16(0); + + if (seq_nr == 3) + memcpy(req->info_element, challenge, 1 + 1 + challenge->len); + + /* init. at76_priv tx header */ + tx_buffer->wlength = cpu_to_le16(buf_len - AT76_TX_HDRLEN); + at76_dbg(DBG_TX_MGMT, "%s: AuthReq bssid %s alg %d seq_nr %d", + priv->netdev->name, mac2str(mgmt->addr3), + le16_to_cpu(req->algorithm), le16_to_cpu(req->transaction)); + if (seq_nr == 3) + at76_dbg(DBG_TX_MGMT, "%s: AuthReq challenge: %s ...", + priv->netdev->name, hex2str(req->info_element, 18)); + + /* either send immediately (if no data tx is pending + or put it in pending list */ + return at76_tx_mgmt(priv, tx_buffer); +} + +static int at76_assoc_req(struct at76_priv *priv, struct bss_info *bss) +{ + struct at76_tx_buffer *tx_buffer; + struct ieee80211_hdr_3addr *mgmt; + struct ieee80211_assoc_request *req; + struct ieee80211_info_element *ie; + char *essid; + int essid_len; + u16 capa; + + BUG_ON(!bss); + + tx_buffer = kmalloc(ASSOCREQ_MAX_SIZE + MAX_PADDING_SIZE, GFP_ATOMIC); + if (!tx_buffer) + return -ENOMEM; + + req = (struct ieee80211_assoc_request *)tx_buffer->packet; + mgmt = &req->header; + ie = req->info_element; + + /* make wireless header */ + mgmt->frame_ctl = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ASSOC_REQ); + + mgmt->duration_id = cpu_to_le16(0x8000); + memcpy(mgmt->addr1, bss->bssid, ETH_ALEN); + memcpy(mgmt->addr2, priv->netdev->dev_addr, ETH_ALEN); + memcpy(mgmt->addr3, bss->bssid, ETH_ALEN); + mgmt->seq_ctl = cpu_to_le16(0); + + /* we must set the Privacy bit in the capabilities to assure an + Agere-based AP with optional WEP transmits encrypted frames + to us. AP only set the Privacy bit in their capabilities + if WEP is mandatory in the BSS! */ + capa = bss->capa; + if (priv->wep_enabled) + capa |= WLAN_CAPABILITY_PRIVACY; + if (priv->preamble_type != PREAMBLE_TYPE_LONG) + capa |= WLAN_CAPABILITY_SHORT_PREAMBLE; + req->capability = cpu_to_le16(capa); + + req->listen_interval = cpu_to_le16(2 * bss->beacon_interval); + + /* write TLV data elements */ + + ie->id = MFIE_TYPE_SSID; + ie->len = bss->ssid_len; + memcpy(ie->data, bss->ssid, bss->ssid_len); + next_ie(&ie); + + ie->id = MFIE_TYPE_RATES; + ie->len = sizeof(hw_rates); + memcpy(ie->data, hw_rates, sizeof(hw_rates)); + next_ie(&ie); /* ie points behind the supp_rates field */ + + /* init. at76_priv tx header */ + tx_buffer->wlength = cpu_to_le16((u8 *)ie - (u8 *)mgmt); + + ie = req->info_element; + essid = ie->data; + essid_len = min_t(int, IW_ESSID_MAX_SIZE, ie->len); + + next_ie(&ie); /* points to IE of rates now */ + at76_dbg(DBG_TX_MGMT, + "%s: AssocReq bssid %s capa 0x%04x ssid %.*s rates %s", + priv->netdev->name, mac2str(mgmt->addr3), + le16_to_cpu(req->capability), essid_len, essid, + hex2str(ie->data, ie->len)); + + /* either send immediately (if no data tx is pending + or put it in pending list */ + return at76_tx_mgmt(priv, tx_buffer); +} + +/* We got to check the bss_list for old entries */ +static void at76_bss_list_timeout(unsigned long par) +{ + struct at76_priv *priv = (struct at76_priv *)par; + unsigned long flags; + struct list_head *lptr, *nptr; + struct bss_info *ptr; + + spin_lock_irqsave(&priv->bss_list_spinlock, flags); + + list_for_each_safe(lptr, nptr, &priv->bss_list) { + + ptr = list_entry(lptr, struct bss_info, list); + + if (ptr != priv->curr_bss + && time_after(jiffies, ptr->last_rx + BSS_LIST_TIMEOUT)) { + at76_dbg(DBG_BSS_TABLE_RM, + "%s: bss_list: removing old BSS %s ch %d", + priv->netdev->name, mac2str(ptr->bssid), + ptr->channel); + list_del(&ptr->list); + kfree(ptr); + } + } + spin_unlock_irqrestore(&priv->bss_list_spinlock, flags); + /* restart the timer */ + mod_timer(&priv->bss_list_timer, jiffies + BSS_LIST_TIMEOUT); +} + +static inline void at76_set_mac_state(struct at76_priv *priv, + enum mac_state mac_state) +{ + at76_dbg(DBG_MAC_STATE, "%s state: %s", priv->netdev->name, + mac_states[mac_state]); + priv->mac_state = mac_state; +} + +static void at76_dump_bss_table(struct at76_priv *priv) +{ + struct bss_info *ptr; + unsigned long flags; + struct list_head *lptr; + + spin_lock_irqsave(&priv->bss_list_spinlock, flags); + + at76_dbg(DBG_BSS_TABLE, "%s BSS table (curr=%p):", priv->netdev->name, + priv->curr_bss); + + list_for_each(lptr, &priv->bss_list) { + ptr = list_entry(lptr, struct bss_info, list); + at76_dbg(DBG_BSS_TABLE, "0x%p: bssid %s channel %d ssid %.*s " + "(%s) capa 0x%04x rates %s rssi %d link %d noise %d", + ptr, mac2str(ptr->bssid), ptr->channel, ptr->ssid_len, + ptr->ssid, hex2str(ptr->ssid, ptr->ssid_len), + ptr->capa, hex2str(ptr->rates, ptr->rates_len), + ptr->rssi, ptr->link_qual, ptr->noise_level); + } + spin_unlock_irqrestore(&priv->bss_list_spinlock, flags); +} + +/* Called upon successful association to mark interface as connected */ +static void at76_work_assoc_done(struct work_struct *work) +{ + struct at76_priv *priv = container_of(work, struct at76_priv, + work_assoc_done); + + mutex_lock(&priv->mtx); + + WARN_ON(priv->mac_state != MAC_ASSOC); + WARN_ON(!priv->curr_bss); + if (priv->mac_state != MAC_ASSOC || !priv->curr_bss) + goto exit; + + if (priv->iw_mode == IW_MODE_INFRA) { + if (priv->pm_mode != AT76_PM_OFF) { + /* calculate the listen interval in units of + beacon intervals of the curr_bss */ + u32 pm_period_beacon = (priv->pm_period >> 10) / + priv->curr_bss->beacon_interval; + + pm_period_beacon = max(pm_period_beacon, 2u); + pm_period_beacon = min(pm_period_beacon, 0xffffu); + + at76_dbg(DBG_PM, + "%s: pm_mode %d assoc id 0x%x listen int %d", + priv->netdev->name, priv->pm_mode, + priv->assoc_id, pm_period_beacon); + + at76_set_associd(priv, priv->assoc_id); + at76_set_listen_interval(priv, (u16)pm_period_beacon); + } + schedule_delayed_work(&priv->dwork_beacon, BEACON_TIMEOUT); + } + at76_set_pm_mode(priv); + + netif_carrier_on(priv->netdev); + netif_wake_queue(priv->netdev); + at76_set_mac_state(priv, MAC_CONNECTED); + at76_iwevent_bss_connect(priv->netdev, priv->curr_bss->bssid); + at76_dbg(DBG_PROGRESS, "%s: connected to BSSID %s", + priv->netdev->name, mac2str(priv->curr_bss->bssid)); + +exit: + mutex_unlock(&priv->mtx); +} + +/* We only store the new mac address in netdev struct, + it gets set when the netdev is opened. */ +static int at76_set_mac_address(struct net_device *netdev, void *addr) +{ + struct sockaddr *mac = addr; + memcpy(netdev->dev_addr, mac->sa_data, ETH_ALEN); + return 1; +} + +static struct net_device_stats *at76_get_stats(struct net_device *netdev) +{ + struct at76_priv *priv = netdev_priv(netdev); + return &priv->stats; +} + +static struct iw_statistics *at76_get_wireless_stats(struct net_device *netdev) +{ + struct at76_priv *priv = netdev_priv(netdev); + + at76_dbg(DBG_IOCTL, "RETURN qual %d level %d noise %d updated %d", + priv->wstats.qual.qual, priv->wstats.qual.level, + priv->wstats.qual.noise, priv->wstats.qual.updated); + + return &priv->wstats; +} + +static void at76_set_multicast(struct net_device *netdev) +{ + struct at76_priv *priv = netdev_priv(netdev); + int promisc; + + promisc = ((netdev->flags & IFF_PROMISC) != 0); + if (promisc != priv->promisc) { + /* This gets called in interrupt, must reschedule */ + priv->promisc = promisc; + schedule_work(&priv->work_set_promisc); + } +} + +/* Stop all network activity, flush all pending tasks */ +static void at76_quiesce(struct at76_priv *priv) +{ + unsigned long flags; + + netif_stop_queue(priv->netdev); + netif_carrier_off(priv->netdev); + + at76_set_mac_state(priv, MAC_INIT); + + cancel_delayed_work(&priv->dwork_get_scan); + cancel_delayed_work(&priv->dwork_beacon); + cancel_delayed_work(&priv->dwork_auth); + cancel_delayed_work(&priv->dwork_assoc); + cancel_delayed_work(&priv->dwork_restart); + + spin_lock_irqsave(&priv->mgmt_spinlock, flags); + kfree(priv->next_mgmt_bulk); + priv->next_mgmt_bulk = NULL; + spin_unlock_irqrestore(&priv->mgmt_spinlock, flags); +} + +/******************************************************************************* + * at76_priv implementations of iw_handler functions: + */ +static int at76_iw_handler_commit(struct net_device *netdev, + struct iw_request_info *info, + void *null, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + at76_dbg(DBG_IOCTL, "%s %s: restarting the device", netdev->name, + __func__); + + if (priv->mac_state != MAC_INIT) + at76_quiesce(priv); + + /* Wait half second before the restart to process subsequent + * requests from the same iwconfig in a single restart */ + schedule_delayed_work(&priv->dwork_restart, HZ / 2); + + return 0; +} + +static int at76_iw_handler_get_name(struct net_device *netdev, + struct iw_request_info *info, + char *name, char *extra) +{ + strcpy(name, "IEEE 802.11b"); + at76_dbg(DBG_IOCTL, "%s: SIOCGIWNAME - name %s", netdev->name, name); + return 0; +} + +static int at76_iw_handler_set_freq(struct net_device *netdev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int chan = -1; + int ret = -EIWCOMMIT; + at76_dbg(DBG_IOCTL, "%s: SIOCSIWFREQ - freq.m %d freq.e %d", + netdev->name, freq->m, freq->e); + + if ((freq->e == 0) && (freq->m <= 1000)) + /* Setting by channel number */ + chan = freq->m; + else { + /* Setting by frequency - search the table */ + int mult = 1; + int i; + + for (i = 0; i < (6 - freq->e); i++) + mult *= 10; + + for (i = 0; i < NUM_CHANNELS; i++) { + if (freq->m == (channel_frequency[i] * mult)) + chan = i + 1; + } + } + + if (chan < 1 || !priv->domain) + /* non-positive channels are invalid + * we need a domain info to set the channel + * either that or an invalid frequency was + * provided by the user */ + ret = -EINVAL; + else if (!(priv->domain->channel_map & (1 << (chan - 1)))) { + printk(KERN_INFO "%s: channel %d not allowed for domain %s\n", + priv->netdev->name, chan, priv->domain->name); + ret = -EINVAL; + } + + if (ret == -EIWCOMMIT) { + priv->channel = chan; + at76_dbg(DBG_IOCTL, "%s: SIOCSIWFREQ - ch %d", netdev->name, + chan); + } + + return ret; +} + +static int at76_iw_handler_get_freq(struct net_device *netdev, + struct iw_request_info *info, + struct iw_freq *freq, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + freq->m = priv->channel; + freq->e = 0; + + if (priv->channel) + at76_dbg(DBG_IOCTL, "%s: SIOCGIWFREQ - freq %ld x 10e%d", + netdev->name, channel_frequency[priv->channel - 1], 6); + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWFREQ - ch %d", netdev->name, + priv->channel); + + return 0; +} + +static int at76_iw_handler_set_mode(struct net_device *netdev, + struct iw_request_info *info, + __u32 *mode, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWMODE - %d", netdev->name, *mode); + + if ((*mode != IW_MODE_ADHOC) && (*mode != IW_MODE_INFRA) && + (*mode != IW_MODE_MONITOR)) + return -EINVAL; + + priv->iw_mode = *mode; + if (priv->iw_mode != IW_MODE_INFRA) + priv->pm_mode = AT76_PM_OFF; + + return -EIWCOMMIT; +} + +static int at76_iw_handler_get_mode(struct net_device *netdev, + struct iw_request_info *info, + __u32 *mode, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + *mode = priv->iw_mode; + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWMODE - %d", netdev->name, *mode); + + return 0; +} + +static int at76_iw_handler_get_range(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + /* inspired by atmel.c */ + struct at76_priv *priv = netdev_priv(netdev); + struct iw_range *range = (struct iw_range *)extra; + int i; + + data->length = sizeof(struct iw_range); + memset(range, 0, sizeof(struct iw_range)); + + /* TODO: range->throughput = xxxxxx; */ + + range->min_nwid = 0x0000; + range->max_nwid = 0x0000; + + /* this driver doesn't maintain sensitivity information */ + range->sensitivity = 0; + + range->max_qual.qual = 100; + range->max_qual.level = 100; + range->max_qual.noise = 0; + range->max_qual.updated = IW_QUAL_NOISE_INVALID; + + range->avg_qual.qual = 50; + range->avg_qual.level = 50; + range->avg_qual.noise = 0; + range->avg_qual.updated = IW_QUAL_NOISE_INVALID; + + range->bitrate[0] = 1000000; + range->bitrate[1] = 2000000; + range->bitrate[2] = 5500000; + range->bitrate[3] = 11000000; + range->num_bitrates = 4; + + range->min_rts = 0; + range->max_rts = MAX_RTS_THRESHOLD; + + range->min_frag = MIN_FRAG_THRESHOLD; + range->max_frag = MAX_FRAG_THRESHOLD; + + range->pmp_flags = IW_POWER_PERIOD; + range->pmt_flags = IW_POWER_ON; + range->pm_capa = IW_POWER_PERIOD | IW_POWER_ALL_R; + + range->encoding_size[0] = WEP_SMALL_KEY_LEN; + range->encoding_size[1] = WEP_LARGE_KEY_LEN; + range->num_encoding_sizes = 2; + range->max_encoding_tokens = WEP_KEYS; + + /* both WL-240U and Linksys WUSB11 v2.6 specify 15 dBm as output power + - take this for all (ignore antenna gains) */ + range->txpower[0] = 15; + range->num_txpower = 1; + range->txpower_capa = IW_TXPOW_DBM; + + range->we_version_source = WIRELESS_EXT; + range->we_version_compiled = WIRELESS_EXT; + + /* same as the values used in atmel.c */ + range->retry_capa = IW_RETRY_LIMIT; + range->retry_flags = IW_RETRY_LIMIT; + range->r_time_flags = 0; + range->min_retry = 1; + range->max_retry = 255; + + range->num_channels = NUM_CHANNELS; + range->num_frequency = 0; + + for (i = 0; i < NUM_CHANNELS; i++) { + /* test if channel map bit is raised */ + if (priv->domain->channel_map & (0x1 << i)) { + range->num_frequency += 1; + + range->freq[i].i = i + 1; + range->freq[i].m = channel_frequency[i] * 100000; + range->freq[i].e = 1; /* freq * 10^1 */ + } + } + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWRANGE", netdev->name); + + return 0; +} + +static int at76_iw_handler_set_spy(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret = 0; + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWSPY - number of addresses %d", + netdev->name, data->length); + + spin_lock_bh(&priv->spy_spinlock); + ret = iw_handler_set_spy(priv->netdev, info, (union iwreq_data *)data, + extra); + spin_unlock_bh(&priv->spy_spinlock); + + return ret; +} + +static int at76_iw_handler_get_spy(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + + struct at76_priv *priv = netdev_priv(netdev); + int ret = 0; + + spin_lock_bh(&priv->spy_spinlock); + ret = iw_handler_get_spy(priv->netdev, info, + (union iwreq_data *)data, extra); + spin_unlock_bh(&priv->spy_spinlock); + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWSPY - number of addresses %d", + netdev->name, data->length); + + return ret; +} + +static int at76_iw_handler_set_thrspy(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret; + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWTHRSPY - number of addresses %d)", + netdev->name, data->length); + + spin_lock_bh(&priv->spy_spinlock); + ret = iw_handler_set_thrspy(netdev, info, (union iwreq_data *)data, + extra); + spin_unlock_bh(&priv->spy_spinlock); + + return ret; +} + +static int at76_iw_handler_get_thrspy(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret; + + spin_lock_bh(&priv->spy_spinlock); + ret = iw_handler_get_thrspy(netdev, info, (union iwreq_data *)data, + extra); + spin_unlock_bh(&priv->spy_spinlock); + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWTHRSPY - number of addresses %d)", + netdev->name, data->length); + + return ret; +} + +static int at76_iw_handler_set_wap(struct net_device *netdev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWAP - wap/bssid %s", netdev->name, + mac2str(ap_addr->sa_data)); + + /* if the incoming address == ff:ff:ff:ff:ff:ff, the user has + chosen any or auto AP preference */ + if (is_broadcast_ether_addr(ap_addr->sa_data) + || is_zero_ether_addr(ap_addr->sa_data)) + priv->wanted_bssid_valid = 0; + else { + /* user wants to set a preferred AP address */ + priv->wanted_bssid_valid = 1; + memcpy(priv->wanted_bssid, ap_addr->sa_data, ETH_ALEN); + } + + return -EIWCOMMIT; +} + +static int at76_iw_handler_get_wap(struct net_device *netdev, + struct iw_request_info *info, + struct sockaddr *ap_addr, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + ap_addr->sa_family = ARPHRD_ETHER; + memcpy(ap_addr->sa_data, priv->bssid, ETH_ALEN); + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWAP - wap/bssid %s", netdev->name, + mac2str(ap_addr->sa_data)); + + return 0; +} + +static int at76_iw_handler_set_scan(struct net_device *netdev, + struct iw_request_info *info, + union iwreq_data *wrqu, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret = 0; + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWSCAN", netdev->name); + + if (mutex_lock_interruptible(&priv->mtx)) + return -EINTR; + + if (!netif_running(netdev)) { + ret = -ENETDOWN; + goto exit; + } + + /* jal: we don't allow "iwlist ethX scan" while we are + in monitor mode */ + if (priv->iw_mode == IW_MODE_MONITOR) { + ret = -EBUSY; + goto exit; + } + + /* Discard old scan results */ + if ((jiffies - priv->last_scan) > (20 * HZ)) + priv->scan_state = SCAN_IDLE; + priv->last_scan = jiffies; + + /* Initiate a scan command */ + if (priv->scan_state == SCAN_IN_PROGRESS) { + ret = -EBUSY; + goto exit; + } + + priv->scan_state = SCAN_IN_PROGRESS; + + at76_quiesce(priv); + + /* Try to do passive or active scan if WE asks as. */ + if (wrqu->data.length + && wrqu->data.length == sizeof(struct iw_scan_req)) { + struct iw_scan_req *req = (struct iw_scan_req *)extra; + + if (req->scan_type == IW_SCAN_TYPE_PASSIVE) + priv->scan_mode = SCAN_TYPE_PASSIVE; + else if (req->scan_type == IW_SCAN_TYPE_ACTIVE) + priv->scan_mode = SCAN_TYPE_ACTIVE; + + /* Sanity check values? */ + if (req->min_channel_time > 0) + priv->scan_min_time = req->min_channel_time; + + if (req->max_channel_time > 0) + priv->scan_max_time = req->max_channel_time; + } + + /* change to scanning state */ + at76_set_mac_state(priv, MAC_SCANNING); + schedule_work(&priv->work_start_scan); + +exit: + mutex_unlock(&priv->mtx); + return ret; +} + +static int at76_iw_handler_get_scan(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + unsigned long flags; + struct list_head *lptr, *nptr; + struct bss_info *curr_bss; + struct iw_event *iwe = kmalloc(sizeof(struct iw_event), GFP_KERNEL); + char *curr_val, *curr_pos = extra; + int i; + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWSCAN", netdev->name); + + if (!iwe) + return -ENOMEM; + + if (priv->scan_state != SCAN_COMPLETED) { + /* scan not yet finished */ + kfree(iwe); + return -EAGAIN; + } + + spin_lock_irqsave(&priv->bss_list_spinlock, flags); + + list_for_each_safe(lptr, nptr, &priv->bss_list) { + curr_bss = list_entry(lptr, struct bss_info, list); + + iwe->cmd = SIOCGIWAP; + iwe->u.ap_addr.sa_family = ARPHRD_ETHER; + memcpy(iwe->u.ap_addr.sa_data, curr_bss->bssid, 6); + curr_pos = iwe_stream_add_event(info, curr_pos, + extra + IW_SCAN_MAX_DATA, iwe, + IW_EV_ADDR_LEN); + + iwe->u.data.length = curr_bss->ssid_len; + iwe->cmd = SIOCGIWESSID; + iwe->u.data.flags = 1; + + curr_pos = iwe_stream_add_point(info, curr_pos, + extra + IW_SCAN_MAX_DATA, iwe, + curr_bss->ssid); + + iwe->cmd = SIOCGIWMODE; + iwe->u.mode = (curr_bss->capa & WLAN_CAPABILITY_IBSS) ? + IW_MODE_ADHOC : + (curr_bss->capa & WLAN_CAPABILITY_ESS) ? + IW_MODE_MASTER : IW_MODE_AUTO; + /* IW_MODE_AUTO = 0 which I thought is + * the most logical value to return in this case */ + curr_pos = iwe_stream_add_event(info, curr_pos, + extra + IW_SCAN_MAX_DATA, iwe, + IW_EV_UINT_LEN); + + iwe->cmd = SIOCGIWFREQ; + iwe->u.freq.m = curr_bss->channel; + iwe->u.freq.e = 0; + curr_pos = iwe_stream_add_event(info, curr_pos, + extra + IW_SCAN_MAX_DATA, iwe, + IW_EV_FREQ_LEN); + + iwe->cmd = SIOCGIWENCODE; + if (curr_bss->capa & WLAN_CAPABILITY_PRIVACY) + iwe->u.data.flags = IW_ENCODE_ENABLED | IW_ENCODE_NOKEY; + else + iwe->u.data.flags = IW_ENCODE_DISABLED; + + iwe->u.data.length = 0; + curr_pos = iwe_stream_add_point(info, curr_pos, + extra + IW_SCAN_MAX_DATA, iwe, + NULL); + + /* Add quality statistics */ + iwe->cmd = IWEVQUAL; + iwe->u.qual.noise = 0; + iwe->u.qual.updated = + IW_QUAL_NOISE_INVALID | IW_QUAL_LEVEL_UPDATED; + iwe->u.qual.level = (curr_bss->rssi * 100 / 42); + if (iwe->u.qual.level > 100) + iwe->u.qual.level = 100; + if (at76_is_intersil(priv->board_type)) + iwe->u.qual.qual = curr_bss->link_qual; + else { + iwe->u.qual.qual = 0; + iwe->u.qual.updated |= IW_QUAL_QUAL_INVALID; + } + /* Add new value to event */ + curr_pos = iwe_stream_add_event(info, curr_pos, + extra + IW_SCAN_MAX_DATA, iwe, + IW_EV_QUAL_LEN); + + /* Rate: stuffing multiple values in a single event requires + * a bit more of magic - Jean II */ + curr_val = curr_pos + IW_EV_LCP_LEN; + + iwe->cmd = SIOCGIWRATE; + /* Those two flags are ignored... */ + iwe->u.bitrate.fixed = 0; + iwe->u.bitrate.disabled = 0; + /* Max 8 values */ + for (i = 0; i < curr_bss->rates_len; i++) { + /* Bit rate given in 500 kb/s units (+ 0x80) */ + iwe->u.bitrate.value = + ((curr_bss->rates[i] & 0x7f) * 500000); + /* Add new value to event */ + curr_val = iwe_stream_add_value(info, curr_pos, + curr_val, + extra + + IW_SCAN_MAX_DATA, iwe, + IW_EV_PARAM_LEN); + } + + /* Check if we added any event */ + if ((curr_val - curr_pos) > IW_EV_LCP_LEN) + curr_pos = curr_val; + + /* more information may be sent back using IWECUSTOM */ + + } + + spin_unlock_irqrestore(&priv->bss_list_spinlock, flags); + + data->length = (curr_pos - extra); + data->flags = 0; + + kfree(iwe); + return 0; +} + +static int at76_iw_handler_set_essid(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWESSID - %s", netdev->name, extra); + + if (data->flags) { + memcpy(priv->essid, extra, data->length); + priv->essid_size = data->length; + } else + priv->essid_size = 0; /* Use any SSID */ + + return -EIWCOMMIT; +} + +static int at76_iw_handler_get_essid(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + if (priv->essid_size) { + /* not the ANY ssid in priv->essid */ + data->flags = 1; + data->length = priv->essid_size; + memcpy(extra, priv->essid, data->length); + } else { + /* the ANY ssid was specified */ + if (priv->mac_state == MAC_CONNECTED && priv->curr_bss) { + /* report the SSID we have found */ + data->flags = 1; + data->length = priv->curr_bss->ssid_len; + memcpy(extra, priv->curr_bss->ssid, data->length); + } else { + /* report ANY back */ + data->flags = 0; + data->length = 0; + } + } + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWESSID - %.*s", netdev->name, + data->length, extra); + + return 0; +} + +static int at76_iw_handler_set_rate(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *bitrate, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret = -EIWCOMMIT; + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWRATE - %d", netdev->name, + bitrate->value); + + switch (bitrate->value) { + case -1: + priv->txrate = TX_RATE_AUTO; + break; /* auto rate */ + case 1000000: + priv->txrate = TX_RATE_1MBIT; + break; + case 2000000: + priv->txrate = TX_RATE_2MBIT; + break; + case 5500000: + priv->txrate = TX_RATE_5_5MBIT; + break; + case 11000000: + priv->txrate = TX_RATE_11MBIT; + break; + default: + ret = -EINVAL; + } + + return ret; +} + +static int at76_iw_handler_get_rate(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *bitrate, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret = 0; + + switch (priv->txrate) { + /* return max rate if RATE_AUTO */ + case TX_RATE_AUTO: + bitrate->value = 11000000; + break; + case TX_RATE_1MBIT: + bitrate->value = 1000000; + break; + case TX_RATE_2MBIT: + bitrate->value = 2000000; + break; + case TX_RATE_5_5MBIT: + bitrate->value = 5500000; + break; + case TX_RATE_11MBIT: + bitrate->value = 11000000; + break; + default: + ret = -EINVAL; + } + + bitrate->fixed = (priv->txrate != TX_RATE_AUTO); + bitrate->disabled = 0; + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWRATE - %d", netdev->name, + bitrate->value); + + return ret; +} + +static int at76_iw_handler_set_rts(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *rts, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret = -EIWCOMMIT; + int rthr = rts->value; + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWRTS - value %d disabled %s", + netdev->name, rts->value, (rts->disabled) ? "true" : "false"); + + if (rts->disabled) + rthr = MAX_RTS_THRESHOLD; + + if ((rthr < 0) || (rthr > MAX_RTS_THRESHOLD)) + ret = -EINVAL; + else + priv->rts_threshold = rthr; + + return ret; +} + +static int at76_iw_handler_get_rts(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *rts, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + rts->value = priv->rts_threshold; + rts->disabled = (rts->value >= MAX_RTS_THRESHOLD); + rts->fixed = 1; + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWRTS - value %d disabled %s", + netdev->name, rts->value, (rts->disabled) ? "true" : "false"); + + return 0; +} + +static int at76_iw_handler_set_frag(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *frag, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret = -EIWCOMMIT; + int fthr = frag->value; + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWFRAG - value %d, disabled %s", + netdev->name, frag->value, + (frag->disabled) ? "true" : "false"); + + if (frag->disabled) + fthr = MAX_FRAG_THRESHOLD; + + if ((fthr < MIN_FRAG_THRESHOLD) || (fthr > MAX_FRAG_THRESHOLD)) + ret = -EINVAL; + else + priv->frag_threshold = fthr & ~0x1; /* get an even value */ + + return ret; +} + +static int at76_iw_handler_get_frag(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *frag, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + frag->value = priv->frag_threshold; + frag->disabled = (frag->value >= MAX_FRAG_THRESHOLD); + frag->fixed = 1; + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWFRAG - value %d, disabled %s", + netdev->name, frag->value, + (frag->disabled) ? "true" : "false"); + + return 0; +} + +static int at76_iw_handler_get_txpow(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *power, char *extra) +{ + power->value = 15; + power->fixed = 1; /* No power control */ + power->disabled = 0; + power->flags = IW_TXPOW_DBM; + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWTXPOW - txpow %d dBm", netdev->name, + power->value); + + return 0; +} + +/* jal: short retry is handled by the firmware (at least 0.90.x), + while long retry is not (?) */ +static int at76_iw_handler_set_retry(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *retry, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret = -EIWCOMMIT; + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWRETRY disabled %d flags 0x%x val %d", + netdev->name, retry->disabled, retry->flags, retry->value); + + if (!retry->disabled && (retry->flags & IW_RETRY_LIMIT)) { + if ((retry->flags & IW_RETRY_MIN) || + !(retry->flags & IW_RETRY_MAX)) + priv->short_retry_limit = retry->value; + else + ret = -EINVAL; + } else + ret = -EINVAL; + + return ret; +} + +/* Adapted (ripped) from atmel.c */ +static int at76_iw_handler_get_retry(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *retry, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWRETRY", netdev->name); + + retry->disabled = 0; /* Can't be disabled */ + retry->flags = IW_RETRY_LIMIT; + retry->value = priv->short_retry_limit; + + return 0; +} + +static int at76_iw_handler_set_encode(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *encoding, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int index = (encoding->flags & IW_ENCODE_INDEX) - 1; + int len = encoding->length; + + at76_dbg(DBG_IOCTL, "%s: SIOCSIWENCODE - enc.flags %08x " + "pointer %p len %d", netdev->name, encoding->flags, + encoding->pointer, encoding->length); + at76_dbg(DBG_IOCTL, + "%s: SIOCSIWENCODE - old wepstate: enabled %s key_id %d " + "auth_mode %s", netdev->name, + (priv->wep_enabled) ? "true" : "false", priv->wep_key_id, + (priv->auth_mode == + WLAN_AUTH_SHARED_KEY) ? "restricted" : "open"); + + /* take the old default key if index is invalid */ + if ((index < 0) || (index >= WEP_KEYS)) + index = priv->wep_key_id; + + if (len > 0) { + if (len > WEP_LARGE_KEY_LEN) + len = WEP_LARGE_KEY_LEN; + + memset(priv->wep_keys[index], 0, WEP_KEY_LEN); + memcpy(priv->wep_keys[index], extra, len); + priv->wep_keys_len[index] = (len <= WEP_SMALL_KEY_LEN) ? + WEP_SMALL_KEY_LEN : WEP_LARGE_KEY_LEN; + priv->wep_enabled = 1; + } + + priv->wep_key_id = index; + priv->wep_enabled = ((encoding->flags & IW_ENCODE_DISABLED) == 0); + + if (encoding->flags & IW_ENCODE_RESTRICTED) + priv->auth_mode = WLAN_AUTH_SHARED_KEY; + if (encoding->flags & IW_ENCODE_OPEN) + priv->auth_mode = WLAN_AUTH_OPEN; + + at76_dbg(DBG_IOCTL, + "%s: SIOCSIWENCODE - new wepstate: enabled %s key_id %d " + "key_len %d auth_mode %s", netdev->name, + (priv->wep_enabled) ? "true" : "false", priv->wep_key_id + 1, + priv->wep_keys_len[priv->wep_key_id], + (priv->auth_mode == + WLAN_AUTH_SHARED_KEY) ? "restricted" : "open"); + + return -EIWCOMMIT; +} + +static int at76_iw_handler_get_encode(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *encoding, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int index = (encoding->flags & IW_ENCODE_INDEX) - 1; + + if ((index < 0) || (index >= WEP_KEYS)) + index = priv->wep_key_id; + + encoding->flags = + (priv->auth_mode == WLAN_AUTH_SHARED_KEY) ? + IW_ENCODE_RESTRICTED : IW_ENCODE_OPEN; + + if (!priv->wep_enabled) + encoding->flags |= IW_ENCODE_DISABLED; + + if (encoding->pointer) { + encoding->length = priv->wep_keys_len[index]; + + memcpy(extra, priv->wep_keys[index], priv->wep_keys_len[index]); + + encoding->flags |= (index + 1); + } + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWENCODE - enc.flags %08x " + "pointer %p len %d", netdev->name, encoding->flags, + encoding->pointer, encoding->length); + at76_dbg(DBG_IOCTL, + "%s: SIOCGIWENCODE - wepstate: enabled %s key_id %d " + "key_len %d auth_mode %s", netdev->name, + (priv->wep_enabled) ? "true" : "false", priv->wep_key_id + 1, + priv->wep_keys_len[priv->wep_key_id], + (priv->auth_mode == + WLAN_AUTH_SHARED_KEY) ? "restricted" : "open"); + + return 0; +} + +static int at76_iw_handler_set_power(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *prq, char *extra) +{ + int err = -EIWCOMMIT; + struct at76_priv *priv = netdev_priv(netdev); + + at76_dbg(DBG_IOCTL, + "%s: SIOCSIWPOWER - disabled %s flags 0x%x value 0x%x", + netdev->name, (prq->disabled) ? "true" : "false", prq->flags, + prq->value); + + if (prq->disabled) + priv->pm_mode = AT76_PM_OFF; + else { + switch (prq->flags & IW_POWER_MODE) { + case IW_POWER_ALL_R: + case IW_POWER_ON: + break; + default: + err = -EINVAL; + goto exit; + } + if (prq->flags & IW_POWER_PERIOD) + priv->pm_period = prq->value; + + if (prq->flags & IW_POWER_TIMEOUT) { + err = -EINVAL; + goto exit; + } + priv->pm_mode = AT76_PM_ON; + } +exit: + return err; +} + +static int at76_iw_handler_get_power(struct net_device *netdev, + struct iw_request_info *info, + struct iw_param *power, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + power->disabled = (priv->pm_mode == AT76_PM_OFF); + if (!power->disabled) { + power->flags = IW_POWER_PERIOD | IW_POWER_ALL_R; + power->value = priv->pm_period; + } + + at76_dbg(DBG_IOCTL, "%s: SIOCGIWPOWER - %s flags 0x%x value 0x%x", + netdev->name, power->disabled ? "disabled" : "enabled", + power->flags, power->value); + + return 0; +} + +/******************************************************************************* + * Private IOCTLS + */ +static int at76_iw_set_short_preamble(struct net_device *netdev, + struct iw_request_info *info, char *name, + char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int val = *((int *)name); + int ret = -EIWCOMMIT; + + at76_dbg(DBG_IOCTL, "%s: AT76_SET_SHORT_PREAMBLE, %d", + netdev->name, val); + + if (val < PREAMBLE_TYPE_LONG || val > PREAMBLE_TYPE_AUTO) + ret = -EINVAL; + else + priv->preamble_type = val; + + return ret; +} + +static int at76_iw_get_short_preamble(struct net_device *netdev, + struct iw_request_info *info, + union iwreq_data *wrqu, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + + snprintf(wrqu->name, sizeof(wrqu->name), "%s (%d)", + preambles[priv->preamble_type], priv->preamble_type); + return 0; +} + +static int at76_iw_set_debug(struct net_device *netdev, + struct iw_request_info *info, + struct iw_point *data, char *extra) +{ + char *ptr; + u32 val; + + if (data->length > 0) { + val = simple_strtol(extra, &ptr, 0); + + if (ptr == extra) + val = DBG_DEFAULTS; + + at76_dbg(DBG_IOCTL, "%s: AT76_SET_DEBUG input %d: %s -> 0x%x", + netdev->name, data->length, extra, val); + } else + val = DBG_DEFAULTS; + + at76_dbg(DBG_IOCTL, "%s: AT76_SET_DEBUG, old 0x%x, new 0x%x", + netdev->name, at76_debug, val); + + /* jal: some more output to pin down lockups */ + at76_dbg(DBG_IOCTL, "%s: netif running %d queue_stopped %d " + "carrier_ok %d", netdev->name, netif_running(netdev), + netif_queue_stopped(netdev), netif_carrier_ok(netdev)); + + at76_debug = val; + + return 0; +} + +static int at76_iw_get_debug(struct net_device *netdev, + struct iw_request_info *info, + union iwreq_data *wrqu, char *extra) +{ + snprintf(wrqu->name, sizeof(wrqu->name), "0x%08x", at76_debug); + return 0; +} + +static int at76_iw_set_powersave_mode(struct net_device *netdev, + struct iw_request_info *info, char *name, + char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int val = *((int *)name); + int ret = -EIWCOMMIT; + + at76_dbg(DBG_IOCTL, "%s: AT76_SET_POWERSAVE_MODE, %d (%s)", + netdev->name, val, + val == AT76_PM_OFF ? "active" : val == AT76_PM_ON ? "save" : + val == AT76_PM_SMART ? "smart save" : "<invalid>"); + if (val < AT76_PM_OFF || val > AT76_PM_SMART) + ret = -EINVAL; + else + priv->pm_mode = val; + + return ret; +} + +static int at76_iw_get_powersave_mode(struct net_device *netdev, + struct iw_request_info *info, + union iwreq_data *wrqu, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int *param = (int *)extra; + + param[0] = priv->pm_mode; + return 0; +} + +static int at76_iw_set_scan_times(struct net_device *netdev, + struct iw_request_info *info, char *name, + char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int mint = *((int *)name); + int maxt = *((int *)name + 1); + int ret = -EIWCOMMIT; + + at76_dbg(DBG_IOCTL, "%s: AT76_SET_SCAN_TIMES - min %d max %d", + netdev->name, mint, maxt); + if (mint <= 0 || maxt <= 0 || mint > maxt) + ret = -EINVAL; + else { + priv->scan_min_time = mint; + priv->scan_max_time = maxt; + } + + return ret; +} + +static int at76_iw_get_scan_times(struct net_device *netdev, + struct iw_request_info *info, + union iwreq_data *wrqu, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int *param = (int *)extra; + + param[0] = priv->scan_min_time; + param[1] = priv->scan_max_time; + return 0; +} + +static int at76_iw_set_scan_mode(struct net_device *netdev, + struct iw_request_info *info, char *name, + char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int val = *((int *)name); + int ret = -EIWCOMMIT; + + at76_dbg(DBG_IOCTL, "%s: AT76_SET_SCAN_MODE - mode %s", + netdev->name, (val = SCAN_TYPE_ACTIVE) ? "active" : + (val = SCAN_TYPE_PASSIVE) ? "passive" : "<invalid>"); + + if (val != SCAN_TYPE_ACTIVE && val != SCAN_TYPE_PASSIVE) + ret = -EINVAL; + else + priv->scan_mode = val; + + return ret; +} + +static int at76_iw_get_scan_mode(struct net_device *netdev, + struct iw_request_info *info, + union iwreq_data *wrqu, char *extra) +{ + struct at76_priv *priv = netdev_priv(netdev); + int *param = (int *)extra; + + param[0] = priv->scan_mode; + return 0; +} + +#define AT76_SET_HANDLER(h, f) [h - SIOCIWFIRST] = (iw_handler) f + +/* Standard wireless handlers */ +static const iw_handler at76_handlers[] = { + AT76_SET_HANDLER(SIOCSIWCOMMIT, at76_iw_handler_commit), + AT76_SET_HANDLER(SIOCGIWNAME, at76_iw_handler_get_name), + AT76_SET_HANDLER(SIOCSIWFREQ, at76_iw_handler_set_freq), + AT76_SET_HANDLER(SIOCGIWFREQ, at76_iw_handler_get_freq), + AT76_SET_HANDLER(SIOCSIWMODE, at76_iw_handler_set_mode), + AT76_SET_HANDLER(SIOCGIWMODE, at76_iw_handler_get_mode), + AT76_SET_HANDLER(SIOCGIWRANGE, at76_iw_handler_get_range), + AT76_SET_HANDLER(SIOCSIWSPY, at76_iw_handler_set_spy), + AT76_SET_HANDLER(SIOCGIWSPY, at76_iw_handler_get_spy), + AT76_SET_HANDLER(SIOCSIWTHRSPY, at76_iw_handler_set_thrspy), + AT76_SET_HANDLER(SIOCGIWTHRSPY, at76_iw_handler_get_thrspy), + AT76_SET_HANDLER(SIOCSIWAP, at76_iw_handler_set_wap), + AT76_SET_HANDLER(SIOCGIWAP, at76_iw_handler_get_wap), + AT76_SET_HANDLER(SIOCSIWSCAN, at76_iw_handler_set_scan), + AT76_SET_HANDLER(SIOCGIWSCAN, at76_iw_handler_get_scan), + AT76_SET_HANDLER(SIOCSIWESSID, at76_iw_handler_set_essid), + AT76_SET_HANDLER(SIOCGIWESSID, at76_iw_handler_get_essid), + AT76_SET_HANDLER(SIOCSIWRATE, at76_iw_handler_set_rate), + AT76_SET_HANDLER(SIOCGIWRATE, at76_iw_handler_get_rate), + AT76_SET_HANDLER(SIOCSIWRTS, at76_iw_handler_set_rts), + AT76_SET_HANDLER(SIOCGIWRTS, at76_iw_handler_get_rts), + AT76_SET_HANDLER(SIOCSIWFRAG, at76_iw_handler_set_frag), + AT76_SET_HANDLER(SIOCGIWFRAG, at76_iw_handler_get_frag), + AT76_SET_HANDLER(SIOCGIWTXPOW, at76_iw_handler_get_txpow), + AT76_SET_HANDLER(SIOCSIWRETRY, at76_iw_handler_set_retry), + AT76_SET_HANDLER(SIOCGIWRETRY, at76_iw_handler_get_retry), + AT76_SET_HANDLER(SIOCSIWENCODE, at76_iw_handler_set_encode), + AT76_SET_HANDLER(SIOCGIWENCODE, at76_iw_handler_get_encode), + AT76_SET_HANDLER(SIOCSIWPOWER, at76_iw_handler_set_power), + AT76_SET_HANDLER(SIOCGIWPOWER, at76_iw_handler_get_power) +}; + +#define AT76_SET_PRIV(h, f) [h - SIOCIWFIRSTPRIV] = (iw_handler) f + +/* Private wireless handlers */ +static const iw_handler at76_priv_handlers[] = { + AT76_SET_PRIV(AT76_SET_SHORT_PREAMBLE, at76_iw_set_short_preamble), + AT76_SET_PRIV(AT76_GET_SHORT_PREAMBLE, at76_iw_get_short_preamble), + AT76_SET_PRIV(AT76_SET_DEBUG, at76_iw_set_debug), + AT76_SET_PRIV(AT76_GET_DEBUG, at76_iw_get_debug), + AT76_SET_PRIV(AT76_SET_POWERSAVE_MODE, at76_iw_set_powersave_mode), + AT76_SET_PRIV(AT76_GET_POWERSAVE_MODE, at76_iw_get_powersave_mode), + AT76_SET_PRIV(AT76_SET_SCAN_TIMES, at76_iw_set_scan_times), + AT76_SET_PRIV(AT76_GET_SCAN_TIMES, at76_iw_get_scan_times), + AT76_SET_PRIV(AT76_SET_SCAN_MODE, at76_iw_set_scan_mode), + AT76_SET_PRIV(AT76_GET_SCAN_MODE, at76_iw_get_scan_mode), +}; + +/* Names and arguments of private wireless handlers */ +static const struct iw_priv_args at76_priv_args[] = { + /* 0 - long, 1 - short */ + {AT76_SET_SHORT_PREAMBLE, + IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "set_preamble"}, + + {AT76_GET_SHORT_PREAMBLE, + 0, IW_PRIV_TYPE_CHAR | IW_PRIV_SIZE_FIXED | 10, "get_preamble"}, + + /* we must pass the new debug mask as a string, because iwpriv cannot + * parse hex numbers starting with 0x :-( */ + {AT76_SET_DEBUG, + IW_PRIV_TYPE_CHAR | 10, 0, "set_debug"}, + + {AT76_GET_DEBUG, + 0, IW_PRIV_TYPE_CHAR | IW_PRIV_SIZE_FIXED | 10, "get_debug"}, + + /* 1 - active, 2 - power save, 3 - smart power save */ + {AT76_SET_POWERSAVE_MODE, + IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "set_powersave"}, + + {AT76_GET_POWERSAVE_MODE, + 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "get_powersave"}, + + /* min_channel_time, max_channel_time */ + {AT76_SET_SCAN_TIMES, + IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 2, 0, "set_scan_times"}, + + {AT76_GET_SCAN_TIMES, + 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 2, "get_scan_times"}, + + /* 0 - active, 1 - passive scan */ + {AT76_SET_SCAN_MODE, + IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, 0, "set_scan_mode"}, + + {AT76_GET_SCAN_MODE, + 0, IW_PRIV_TYPE_INT | IW_PRIV_SIZE_FIXED | 1, "get_scan_mode"}, +}; + +static const struct iw_handler_def at76_handler_def = { + .num_standard = ARRAY_SIZE(at76_handlers), + .num_private = ARRAY_SIZE(at76_priv_handlers), + .num_private_args = ARRAY_SIZE(at76_priv_args), + .standard = at76_handlers, + .private = at76_priv_handlers, + .private_args = at76_priv_args, + .get_wireless_stats = at76_get_wireless_stats, +}; + +static const u8 snapsig[] = { 0xaa, 0xaa, 0x03 }; + +/* RFC 1042 encapsulates Ethernet frames in 802.2 SNAP (0xaa, 0xaa, 0x03) with + * a SNAP OID of 0 (0x00, 0x00, 0x00) */ +static const u8 rfc1042sig[] = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; + +static int at76_tx(struct sk_buff *skb, struct net_device *netdev) +{ + struct at76_priv *priv = netdev_priv(netdev); + struct net_device_stats *stats = &priv->stats; + int ret = 0; + int wlen; + int submit_len; + struct at76_tx_buffer *tx_buffer = priv->bulk_out_buffer; + struct ieee80211_hdr_3addr *i802_11_hdr = + (struct ieee80211_hdr_3addr *)tx_buffer->packet; + u8 *payload = i802_11_hdr->payload; + struct ethhdr *eh = (struct ethhdr *)skb->data; + + if (netif_queue_stopped(netdev)) { + printk(KERN_ERR "%s: %s called while netdev is stopped\n", + netdev->name, __func__); + /* skip this packet */ + dev_kfree_skb(skb); + return 0; + } + + if (priv->tx_urb->status == -EINPROGRESS) { + printk(KERN_ERR "%s: %s called while tx urb is pending\n", + netdev->name, __func__); + /* skip this packet */ + dev_kfree_skb(skb); + return 0; + } + + if (skb->len < ETH_HLEN) { + printk(KERN_ERR "%s: %s: skb too short (%d)\n", + netdev->name, __func__, skb->len); + dev_kfree_skb(skb); + return 0; + } + + at76_ledtrig_tx_activity(); /* tell ledtrigger we send a packet */ + + /* we can get rid of memcpy if we set netdev->hard_header_len to + reserve enough space, but we would need to keep the skb around */ + + if (ntohs(eh->h_proto) <= ETH_DATA_LEN) { + /* this is a 802.3 packet */ + if (skb->len >= ETH_HLEN + sizeof(rfc1042sig) + && skb->data[ETH_HLEN] == rfc1042sig[0] + && skb->data[ETH_HLEN + 1] == rfc1042sig[1]) { + /* higher layer delivered SNAP header - keep it */ + memcpy(payload, skb->data + ETH_HLEN, + skb->len - ETH_HLEN); + wlen = IEEE80211_3ADDR_LEN + skb->len - ETH_HLEN; + } else { + printk(KERN_ERR "%s: dropping non-SNAP 802.2 packet " + "(DSAP 0x%02x SSAP 0x%02x cntrl 0x%02x)\n", + priv->netdev->name, skb->data[ETH_HLEN], + skb->data[ETH_HLEN + 1], + skb->data[ETH_HLEN + 2]); + dev_kfree_skb(skb); + return 0; + } + } else { + /* add RFC 1042 header in front */ + memcpy(payload, rfc1042sig, sizeof(rfc1042sig)); + memcpy(payload + sizeof(rfc1042sig), &eh->h_proto, + skb->len - offsetof(struct ethhdr, h_proto)); + wlen = IEEE80211_3ADDR_LEN + sizeof(rfc1042sig) + skb->len - + offsetof(struct ethhdr, h_proto); + } + + /* make wireless header */ + i802_11_hdr->frame_ctl = + cpu_to_le16(IEEE80211_FTYPE_DATA | + (priv->wep_enabled ? IEEE80211_FCTL_PROTECTED : 0) | + (priv->iw_mode == + IW_MODE_INFRA ? IEEE80211_FCTL_TODS : 0)); + + if (priv->iw_mode == IW_MODE_ADHOC) { + memcpy(i802_11_hdr->addr1, eh->h_dest, ETH_ALEN); + memcpy(i802_11_hdr->addr2, eh->h_source, ETH_ALEN); + memcpy(i802_11_hdr->addr3, priv->bssid, ETH_ALEN); + } else if (priv->iw_mode == IW_MODE_INFRA) { + memcpy(i802_11_hdr->addr1, priv->bssid, ETH_ALEN); + memcpy(i802_11_hdr->addr2, eh->h_source, ETH_ALEN); + memcpy(i802_11_hdr->addr3, eh->h_dest, ETH_ALEN); + } + + i802_11_hdr->duration_id = cpu_to_le16(0); + i802_11_hdr->seq_ctl = cpu_to_le16(0); + + /* setup 'Atmel' header */ + tx_buffer->wlength = cpu_to_le16(wlen); + tx_buffer->tx_rate = priv->txrate; + /* for broadcast destination addresses, the firmware 0.100.x + seems to choose the highest rate set with CMD_STARTUP in + basic_rate_set replacing this value */ + + memset(tx_buffer->reserved, 0, sizeof(tx_buffer->reserved)); + + tx_buffer->padding = at76_calc_padding(wlen); + submit_len = wlen + AT76_TX_HDRLEN + tx_buffer->padding; + + at76_dbg(DBG_TX_DATA_CONTENT, "%s skb->data %s", priv->netdev->name, + hex2str(skb->data, 32)); + at76_dbg(DBG_TX_DATA, "%s tx: wlen 0x%x pad 0x%x rate %d hdr %s", + priv->netdev->name, + le16_to_cpu(tx_buffer->wlength), + tx_buffer->padding, tx_buffer->tx_rate, + hex2str(i802_11_hdr, sizeof(*i802_11_hdr))); + at76_dbg(DBG_TX_DATA_CONTENT, "%s payload %s", priv->netdev->name, + hex2str(payload, 48)); + + /* send stuff */ + netif_stop_queue(netdev); + netdev->trans_start = jiffies; + + usb_fill_bulk_urb(priv->tx_urb, priv->udev, priv->tx_pipe, tx_buffer, + submit_len, at76_tx_callback, priv); + ret = usb_submit_urb(priv->tx_urb, GFP_ATOMIC); + if (ret) { + stats->tx_errors++; + printk(KERN_ERR "%s: error in tx submit urb: %d\n", + netdev->name, ret); + if (ret == -EINVAL) + printk(KERN_ERR + "%s: -EINVAL: tx urb %p hcpriv %p complete %p\n", + priv->netdev->name, priv->tx_urb, + priv->tx_urb->hcpriv, priv->tx_urb->complete); + } else { + stats->tx_bytes += skb->len; + dev_kfree_skb(skb); + } + + return ret; +} + +static void at76_tx_timeout(struct net_device *netdev) +{ + struct at76_priv *priv = netdev_priv(netdev); + + if (!priv) + return; + dev_warn(&netdev->dev, "tx timeout."); + + usb_unlink_urb(priv->tx_urb); + priv->stats.tx_errors++; +} + static int at76_submit_rx_urb(struct at76_priv *priv) { int ret; @@ -1327,7 +3270,7 @@ static int at76_submit_rx_urb(struct at76_priv *priv) if (!priv->rx_urb) { printk(KERN_ERR "%s: %s: priv->rx_urb is NULL\n", - wiphy_name(priv->hw->wiphy), __func__); + priv->netdev->name, __func__); return -EFAULT; } @@ -1335,7 +3278,7 @@ static int at76_submit_rx_urb(struct at76_priv *priv) skb = dev_alloc_skb(sizeof(struct at76_rx_buffer)); if (!skb) { printk(KERN_ERR "%s: cannot allocate rx skbuff\n", - wiphy_name(priv->hw->wiphy)); + priv->netdev->name); ret = -ENOMEM; goto exit; } @@ -1355,18 +3298,110 @@ static int at76_submit_rx_urb(struct at76_priv *priv) "usb_submit_urb returned -ENODEV"); else printk(KERN_ERR "%s: rx, usb_submit_urb failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); } exit: if (ret < 0 && ret != -ENODEV) printk(KERN_ERR "%s: cannot submit rx urb - please unload the " "driver and/or power cycle the device\n", - wiphy_name(priv->hw->wiphy)); + priv->netdev->name); return ret; } +static int at76_open(struct net_device *netdev) +{ + struct at76_priv *priv = netdev_priv(netdev); + int ret = 0; + + at76_dbg(DBG_PROC_ENTRY, "%s(): entry", __func__); + + if (mutex_lock_interruptible(&priv->mtx)) + return -EINTR; + + /* if netdev->dev_addr != priv->mac_addr we must + set the mac address in the device ! */ + if (compare_ether_addr(netdev->dev_addr, priv->mac_addr)) { + if (at76_add_mac_address(priv, netdev->dev_addr) >= 0) + at76_dbg(DBG_PROGRESS, "%s: set new MAC addr %s", + netdev->name, mac2str(netdev->dev_addr)); + } + + priv->scan_state = SCAN_IDLE; + priv->last_scan = jiffies; + + ret = at76_submit_rx_urb(priv); + if (ret < 0) { + printk(KERN_ERR "%s: open: submit_rx_urb failed: %d\n", + netdev->name, ret); + goto error; + } + + schedule_delayed_work(&priv->dwork_restart, 0); + + at76_dbg(DBG_PROC_ENTRY, "%s(): end", __func__); +error: + mutex_unlock(&priv->mtx); + return ret < 0 ? ret : 0; +} + +static int at76_stop(struct net_device *netdev) +{ + struct at76_priv *priv = netdev_priv(netdev); + + at76_dbg(DBG_DEVSTART, "%s: ENTER", __func__); + + if (mutex_lock_interruptible(&priv->mtx)) + return -EINTR; + + at76_quiesce(priv); + + if (!priv->device_unplugged) { + /* We are called by "ifconfig ethX down", not because the + * device is not available anymore. */ + at76_set_radio(priv, 0); + + /* We unlink rx_urb because at76_open() re-submits it. + * If unplugged, at76_delete_device() takes care of it. */ + usb_kill_urb(priv->rx_urb); + } + + /* free the bss_list */ + at76_free_bss_list(priv); + + mutex_unlock(&priv->mtx); + at76_dbg(DBG_DEVSTART, "%s: EXIT", __func__); + + return 0; +} + +static void at76_ethtool_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *info) +{ + struct at76_priv *priv = netdev_priv(netdev); + + strncpy(info->driver, DRIVER_NAME, sizeof(info->driver)); + strncpy(info->version, DRIVER_VERSION, sizeof(info->version)); + + usb_make_path(priv->udev, info->bus_info, sizeof(info->bus_info)); + + snprintf(info->fw_version, sizeof(info->fw_version), "%d.%d.%d-%d", + priv->fw_version.major, priv->fw_version.minor, + priv->fw_version.patch, priv->fw_version.build); +} + +static u32 at76_ethtool_get_link(struct net_device *netdev) +{ + struct at76_priv *priv = netdev_priv(netdev); + return priv->mac_state == MAC_CONNECTED; +} + +static struct ethtool_ops at76_ethtool_ops = { + .get_drvinfo = at76_ethtool_get_drvinfo, + .get_link = at76_ethtool_get_link, +}; + /* Download external firmware */ static int at76_load_external_fw(struct usb_device *udev, struct fwentry *fwe) { @@ -1463,6 +3498,406 @@ exit: return ret; } +static int at76_match_essid(struct at76_priv *priv, struct bss_info *ptr) +{ + /* common criteria for both modi */ + + int ret = (priv->essid_size == 0 /* ANY ssid */ || + (priv->essid_size == ptr->ssid_len && + !memcmp(priv->essid, ptr->ssid, ptr->ssid_len))); + if (!ret) + at76_dbg(DBG_BSS_MATCH, + "%s bss table entry %p: essid didn't match", + priv->netdev->name, ptr); + return ret; +} + +static inline int at76_match_mode(struct at76_priv *priv, struct bss_info *ptr) +{ + int ret; + + if (priv->iw_mode == IW_MODE_ADHOC) + ret = ptr->capa & WLAN_CAPABILITY_IBSS; + else + ret = ptr->capa & WLAN_CAPABILITY_ESS; + if (!ret) + at76_dbg(DBG_BSS_MATCH, + "%s bss table entry %p: mode didn't match", + priv->netdev->name, ptr); + return ret; +} + +static int at76_match_rates(struct at76_priv *priv, struct bss_info *ptr) +{ + int i; + + for (i = 0; i < ptr->rates_len; i++) { + u8 rate = ptr->rates[i]; + + if (!(rate & 0x80)) + continue; + + /* this is a basic rate we have to support + (see IEEE802.11, ch. 7.3.2.2) */ + if (rate != (0x80 | hw_rates[0]) + && rate != (0x80 | hw_rates[1]) + && rate != (0x80 | hw_rates[2]) + && rate != (0x80 | hw_rates[3])) { + at76_dbg(DBG_BSS_MATCH, + "%s: bss table entry %p: basic rate %02x not " + "supported", priv->netdev->name, ptr, rate); + return 0; + } + } + + /* if we use short preamble, the bss must support it */ + if (priv->preamble_type == PREAMBLE_TYPE_SHORT && + !(ptr->capa & WLAN_CAPABILITY_SHORT_PREAMBLE)) { + at76_dbg(DBG_BSS_MATCH, + "%s: %p does not support short preamble", + priv->netdev->name, ptr); + return 0; + } else + return 1; +} + +static inline int at76_match_wep(struct at76_priv *priv, struct bss_info *ptr) +{ + if (!priv->wep_enabled && ptr->capa & WLAN_CAPABILITY_PRIVACY) { + /* we have disabled WEP, but the BSS signals privacy */ + at76_dbg(DBG_BSS_MATCH, + "%s: bss table entry %p: requires encryption", + priv->netdev->name, ptr); + return 0; + } + /* otherwise if the BSS does not signal privacy it may well + accept encrypted packets from us ... */ + return 1; +} + +static inline int at76_match_bssid(struct at76_priv *priv, struct bss_info *ptr) +{ + if (!priv->wanted_bssid_valid || + !compare_ether_addr(ptr->bssid, priv->wanted_bssid)) + return 1; + + at76_dbg(DBG_BSS_MATCH, + "%s: requested bssid - %s does not match", + priv->netdev->name, mac2str(priv->wanted_bssid)); + at76_dbg(DBG_BSS_MATCH, + " AP bssid - %s of bss table entry %p", + mac2str(ptr->bssid), ptr); + return 0; +} + +/** + * at76_match_bss - try to find a matching bss in priv->bss + * + * last - last bss tried + * + * last == NULL signals a new round starting with priv->bss_list.next + * this function must be called inside an acquired priv->bss_list_spinlock + * otherwise the timeout on bss may remove the newly chosen entry + */ +static struct bss_info *at76_match_bss(struct at76_priv *priv, + struct bss_info *last) +{ + struct bss_info *ptr = NULL; + struct list_head *curr; + + curr = last ? last->list.next : priv->bss_list.next; + while (curr != &priv->bss_list) { + ptr = list_entry(curr, struct bss_info, list); + if (at76_match_essid(priv, ptr) && at76_match_mode(priv, ptr) + && at76_match_wep(priv, ptr) && at76_match_rates(priv, ptr) + && at76_match_bssid(priv, ptr)) + break; + curr = curr->next; + } + + if (curr == &priv->bss_list) + ptr = NULL; + /* otherwise ptr points to the struct bss_info we have chosen */ + + at76_dbg(DBG_BSS_TABLE, "%s %s: returned %p", priv->netdev->name, + __func__, ptr); + return ptr; +} + +/* Start joining a matching BSS, or create own IBSS */ +static void at76_work_join(struct work_struct *work) +{ + struct at76_priv *priv = container_of(work, struct at76_priv, + work_join); + int ret; + unsigned long flags; + + mutex_lock(&priv->mtx); + + WARN_ON(priv->mac_state != MAC_JOINING); + if (priv->mac_state != MAC_JOINING) + goto exit; + + /* secure the access to priv->curr_bss ! */ + spin_lock_irqsave(&priv->bss_list_spinlock, flags); + priv->curr_bss = at76_match_bss(priv, priv->curr_bss); + spin_unlock_irqrestore(&priv->bss_list_spinlock, flags); + + if (!priv->curr_bss) { + /* here we haven't found a matching (i)bss ... */ + if (priv->iw_mode == IW_MODE_ADHOC) { + at76_set_mac_state(priv, MAC_OWN_IBSS); + at76_start_ibss(priv); + goto exit; + } + /* haven't found a matching BSS in infra mode - try again */ + at76_set_mac_state(priv, MAC_SCANNING); + schedule_work(&priv->work_start_scan); + goto exit; + } + + ret = at76_join_bss(priv, priv->curr_bss); + if (ret < 0) { + printk(KERN_ERR "%s: join_bss failed with %d\n", + priv->netdev->name, ret); + goto exit; + } + + ret = at76_wait_completion(priv, CMD_JOIN); + if (ret != CMD_STATUS_COMPLETE) { + if (ret != CMD_STATUS_TIME_OUT) + printk(KERN_ERR "%s: join_bss completed with %d\n", + priv->netdev->name, ret); + else + printk(KERN_INFO "%s: join_bss ssid %s timed out\n", + priv->netdev->name, + mac2str(priv->curr_bss->bssid)); + + /* retry next BSS immediately */ + schedule_work(&priv->work_join); + goto exit; + } + + /* here we have joined the (I)BSS */ + if (priv->iw_mode == IW_MODE_ADHOC) { + struct bss_info *bptr = priv->curr_bss; + at76_set_mac_state(priv, MAC_CONNECTED); + /* get ESSID, BSSID and channel for priv->curr_bss */ + priv->essid_size = bptr->ssid_len; + memcpy(priv->essid, bptr->ssid, bptr->ssid_len); + memcpy(priv->bssid, bptr->bssid, ETH_ALEN); + priv->channel = bptr->channel; + at76_iwevent_bss_connect(priv->netdev, bptr->bssid); + netif_carrier_on(priv->netdev); + netif_start_queue(priv->netdev); + /* just to be sure */ + cancel_delayed_work(&priv->dwork_get_scan); + cancel_delayed_work(&priv->dwork_auth); + cancel_delayed_work(&priv->dwork_assoc); + } else { + /* send auth req */ + priv->retries = AUTH_RETRIES; + at76_set_mac_state(priv, MAC_AUTH); + at76_auth_req(priv, priv->curr_bss, 1, NULL); + at76_dbg(DBG_MGMT_TIMER, + "%s:%d: starting mgmt_timer + HZ", __func__, __LINE__); + schedule_delayed_work(&priv->dwork_auth, AUTH_TIMEOUT); + } + +exit: + mutex_unlock(&priv->mtx); +} + +/* Reap scan results */ +static void at76_dwork_get_scan(struct work_struct *work) +{ + int status; + int ret; + struct at76_priv *priv = container_of(work, struct at76_priv, + dwork_get_scan.work); + + mutex_lock(&priv->mtx); + WARN_ON(priv->mac_state != MAC_SCANNING); + if (priv->mac_state != MAC_SCANNING) + goto exit; + + status = at76_get_cmd_status(priv->udev, CMD_SCAN); + if (status < 0) { + printk(KERN_ERR "%s: %s: at76_get_cmd_status failed with %d\n", + priv->netdev->name, __func__, status); + status = CMD_STATUS_IN_PROGRESS; + /* INFO: Hope it was a one off error - if not, scanning + further down the line and stop this cycle */ + } + at76_dbg(DBG_PROGRESS, + "%s %s: got cmd_status %d (state %s, need_any %d)", + priv->netdev->name, __func__, status, + mac_states[priv->mac_state], priv->scan_need_any); + + if (status != CMD_STATUS_COMPLETE) { + if ((status != CMD_STATUS_IN_PROGRESS) && + (status != CMD_STATUS_IDLE)) + printk(KERN_ERR "%s: %s: Bad scan status: %s\n", + priv->netdev->name, __func__, + at76_get_cmd_status_string(status)); + + /* the first cmd status after scan start is always a IDLE -> + start the timer to poll again until COMPLETED */ + at76_dbg(DBG_MGMT_TIMER, + "%s:%d: starting mgmt_timer for %d ticks", + __func__, __LINE__, SCAN_POLL_INTERVAL); + schedule_delayed_work(&priv->dwork_get_scan, + SCAN_POLL_INTERVAL); + goto exit; + } + + if (at76_debug & DBG_BSS_TABLE) + at76_dump_bss_table(priv); + + if (priv->scan_need_any) { + ret = at76_start_scan(priv, 0); + if (ret < 0) + printk(KERN_ERR + "%s: %s: start_scan (ANY) failed with %d\n", + priv->netdev->name, __func__, ret); + at76_dbg(DBG_MGMT_TIMER, + "%s:%d: starting mgmt_timer for %d ticks", __func__, + __LINE__, SCAN_POLL_INTERVAL); + schedule_delayed_work(&priv->dwork_get_scan, + SCAN_POLL_INTERVAL); + priv->scan_need_any = 0; + } else { + priv->scan_state = SCAN_COMPLETED; + /* report the end of scan to user space */ + at76_iwevent_scan_complete(priv->netdev); + at76_set_mac_state(priv, MAC_JOINING); + schedule_work(&priv->work_join); + } + +exit: + mutex_unlock(&priv->mtx); +} + +/* Handle loss of beacons from the AP */ +static void at76_dwork_beacon(struct work_struct *work) +{ + struct at76_priv *priv = container_of(work, struct at76_priv, + dwork_beacon.work); + + mutex_lock(&priv->mtx); + if (priv->mac_state != MAC_CONNECTED || priv->iw_mode != IW_MODE_INFRA) + goto exit; + + /* We haven't received any beacons from out AP for BEACON_TIMEOUT */ + printk(KERN_INFO "%s: lost beacon bssid %s\n", + priv->netdev->name, mac2str(priv->curr_bss->bssid)); + + netif_carrier_off(priv->netdev); + netif_stop_queue(priv->netdev); + at76_iwevent_bss_disconnect(priv->netdev); + at76_set_mac_state(priv, MAC_SCANNING); + schedule_work(&priv->work_start_scan); + +exit: + mutex_unlock(&priv->mtx); +} + +/* Handle authentication response timeout */ +static void at76_dwork_auth(struct work_struct *work) +{ + struct at76_priv *priv = container_of(work, struct at76_priv, + dwork_auth.work); + + mutex_lock(&priv->mtx); + WARN_ON(priv->mac_state != MAC_AUTH); + if (priv->mac_state != MAC_AUTH) + goto exit; + + at76_dbg(DBG_PROGRESS, "%s: authentication response timeout", + priv->netdev->name); + + if (priv->retries-- >= 0) { + at76_auth_req(priv, priv->curr_bss, 1, NULL); + at76_dbg(DBG_MGMT_TIMER, "%s:%d: starting mgmt_timer + HZ", + __func__, __LINE__); + schedule_delayed_work(&priv->dwork_auth, AUTH_TIMEOUT); + } else { + /* try to get next matching BSS */ + at76_set_mac_state(priv, MAC_JOINING); + schedule_work(&priv->work_join); + } + +exit: + mutex_unlock(&priv->mtx); +} + +/* Handle association response timeout */ +static void at76_dwork_assoc(struct work_struct *work) +{ + struct at76_priv *priv = container_of(work, struct at76_priv, + dwork_assoc.work); + + mutex_lock(&priv->mtx); + WARN_ON(priv->mac_state != MAC_ASSOC); + if (priv->mac_state != MAC_ASSOC) + goto exit; + + at76_dbg(DBG_PROGRESS, "%s: association response timeout", + priv->netdev->name); + + if (priv->retries-- >= 0) { + at76_assoc_req(priv, priv->curr_bss); + at76_dbg(DBG_MGMT_TIMER, "%s:%d: starting mgmt_timer + HZ", + __func__, __LINE__); + schedule_delayed_work(&priv->dwork_assoc, ASSOC_TIMEOUT); + } else { + /* try to get next matching BSS */ + at76_set_mac_state(priv, MAC_JOINING); + schedule_work(&priv->work_join); + } + +exit: + mutex_unlock(&priv->mtx); +} + +/* Read new bssid in ad-hoc mode */ +static void at76_work_new_bss(struct work_struct *work) +{ + struct at76_priv *priv = container_of(work, struct at76_priv, + work_new_bss); + int ret; + struct mib_mac_mgmt mac_mgmt; + + mutex_lock(&priv->mtx); + + ret = at76_get_mib(priv->udev, MIB_MAC_MGMT, &mac_mgmt, + sizeof(struct mib_mac_mgmt)); + if (ret < 0) { + printk(KERN_ERR "%s: at76_get_mib failed: %d\n", + priv->netdev->name, ret); + goto exit; + } + + at76_dbg(DBG_PROGRESS, "ibss_change = 0x%2x", mac_mgmt.ibss_change); + memcpy(priv->bssid, mac_mgmt.current_bssid, ETH_ALEN); + at76_dbg(DBG_PROGRESS, "using BSSID %s", mac2str(priv->bssid)); + + at76_iwevent_bss_connect(priv->netdev, priv->bssid); + + priv->mib_buf.type = MIB_MAC_MGMT; + priv->mib_buf.size = 1; + priv->mib_buf.index = offsetof(struct mib_mac_mgmt, ibss_change); + priv->mib_buf.data.byte = 0; + + ret = at76_set_mib(priv, &priv->mib_buf); + if (ret < 0) + printk(KERN_ERR "%s: set_mib (ibss change ok) failed: %d\n", + priv->netdev->name, ret); + +exit: + mutex_unlock(&priv->mtx); +} + static int at76_startup_device(struct at76_priv *priv) { struct at76_card_config *ccfg = &priv->card_config; @@ -1470,14 +3905,14 @@ static int at76_startup_device(struct at76_priv *priv) at76_dbg(DBG_PARAMS, "%s param: ssid %.*s (%s) mode %s ch %d wep %s key %d " - "keylen %d", wiphy_name(priv->hw->wiphy), priv->essid_size, - priv->essid, hex2str(priv->essid, IW_ESSID_MAX_SIZE), + "keylen %d", priv->netdev->name, priv->essid_size, priv->essid, + hex2str(priv->essid, IW_ESSID_MAX_SIZE), priv->iw_mode == IW_MODE_ADHOC ? "adhoc" : "infra", priv->channel, priv->wep_enabled ? "enabled" : "disabled", priv->wep_key_id, priv->wep_keys_len[priv->wep_key_id]); at76_dbg(DBG_PARAMS, "%s param: preamble %s rts %d retry %d frag %d " - "txrate %s auth_mode %d", wiphy_name(priv->hw->wiphy), + "txrate %s auth_mode %d", priv->netdev->name, preambles[priv->preamble_type], priv->rts_threshold, priv->short_retry_limit, priv->frag_threshold, priv->txrate == TX_RATE_1MBIT ? "1MBit" : priv->txrate == @@ -1488,7 +3923,7 @@ static int at76_startup_device(struct at76_priv *priv) at76_dbg(DBG_PARAMS, "%s param: pm_mode %d pm_period %d auth_mode %s " "scan_times %d %d scan_mode %s", - wiphy_name(priv->hw->wiphy), priv->pm_mode, priv->pm_period, + priv->netdev->name, priv->pm_mode, priv->pm_period, priv->auth_mode == WLAN_AUTH_OPEN ? "open" : "shared_secret", priv->scan_min_time, priv->scan_max_time, priv->scan_mode == SCAN_TYPE_ACTIVE ? "active" : "passive"); @@ -1522,8 +3957,7 @@ static int at76_startup_device(struct at76_priv *priv) ccfg->ssid_len = priv->essid_size; ccfg->wep_default_key_id = priv->wep_key_id; - memcpy(ccfg->wep_default_key_value, priv->wep_keys, - sizeof(priv->wep_keys)); + memcpy(ccfg->wep_default_key_value, priv->wep_keys, 4 * WEP_KEY_LEN); ccfg->short_preamble = priv->preamble_type; ccfg->beacon_period = cpu_to_le16(priv->beacon_period); @@ -1532,7 +3966,7 @@ static int at76_startup_device(struct at76_priv *priv) sizeof(struct at76_card_config)); if (ret < 0) { printk(KERN_ERR "%s: at76_set_card_command failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); return ret; } @@ -1578,6 +4012,69 @@ static int at76_startup_device(struct at76_priv *priv) return 0; } +/* Restart the interface */ +static void at76_dwork_restart(struct work_struct *work) +{ + struct at76_priv *priv = container_of(work, struct at76_priv, + dwork_restart.work); + + mutex_lock(&priv->mtx); + + netif_carrier_off(priv->netdev); /* stop netdev watchdog */ + netif_stop_queue(priv->netdev); /* stop tx data packets */ + + at76_startup_device(priv); + + if (priv->iw_mode != IW_MODE_MONITOR) { + priv->netdev->type = ARPHRD_ETHER; + at76_set_mac_state(priv, MAC_SCANNING); + schedule_work(&priv->work_start_scan); + } else { + priv->netdev->type = ARPHRD_IEEE80211_RADIOTAP; + at76_start_monitor(priv); + } + + mutex_unlock(&priv->mtx); +} + +/* Initiate scanning */ +static void at76_work_start_scan(struct work_struct *work) +{ + struct at76_priv *priv = container_of(work, struct at76_priv, + work_start_scan); + int ret; + + mutex_lock(&priv->mtx); + + WARN_ON(priv->mac_state != MAC_SCANNING); + if (priv->mac_state != MAC_SCANNING) + goto exit; + + /* only clear the bss list when a scan is actively initiated, + * otherwise simply rely on at76_bss_list_timeout */ + if (priv->scan_state == SCAN_IN_PROGRESS) { + at76_free_bss_list(priv); + priv->scan_need_any = 1; + } else + priv->scan_need_any = 0; + + ret = at76_start_scan(priv, 1); + + if (ret < 0) + printk(KERN_ERR "%s: %s: start_scan failed with %d\n", + priv->netdev->name, __func__, ret); + else { + at76_dbg(DBG_MGMT_TIMER, + "%s:%d: starting mgmt_timer for %d ticks", + __func__, __LINE__, SCAN_POLL_INTERVAL); + schedule_delayed_work(&priv->dwork_get_scan, + SCAN_POLL_INTERVAL); + } + +exit: + mutex_unlock(&priv->mtx); +} + /* Enable or disable promiscuous mode */ static void at76_work_set_promisc(struct work_struct *work) { @@ -1595,7 +4092,7 @@ static void at76_work_set_promisc(struct work_struct *work) ret = at76_set_mib(priv, &priv->mib_buf); if (ret < 0) printk(KERN_ERR "%s: set_mib (promiscuous_mode) failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); + priv->netdev->name, ret); mutex_unlock(&priv->mtx); } @@ -1611,759 +4108,1088 @@ static void at76_work_submit_rx(struct work_struct *work) mutex_unlock(&priv->mtx); } -static void at76_rx_tasklet(unsigned long param) +/* We got an association response */ +static void at76_rx_mgmt_assoc(struct at76_priv *priv, + struct at76_rx_buffer *buf) { - struct urb *urb = (struct urb *)param; - struct at76_priv *priv = urb->context; - struct at76_rx_buffer *buf; - struct ieee80211_rx_status rx_status = { 0 }; - - if (priv->device_unplugged) { - at76_dbg(DBG_DEVSTART, "device unplugged"); - if (urb) - at76_dbg(DBG_DEVSTART, "urb status %d", urb->status); + struct ieee80211_assoc_response *resp = + (struct ieee80211_assoc_response *)buf->packet; + u16 assoc_id = le16_to_cpu(resp->aid); + u16 status = le16_to_cpu(resp->status); + + at76_dbg(DBG_RX_MGMT, "%s: rx AssocResp bssid %s capa 0x%04x status " + "0x%04x assoc_id 0x%04x rates %s", priv->netdev->name, + mac2str(resp->header.addr3), le16_to_cpu(resp->capability), + status, assoc_id, hex2str(resp->info_element->data, + resp->info_element->len)); + + if (priv->mac_state != MAC_ASSOC) { + printk(KERN_INFO "%s: AssocResp in state %s ignored\n", + priv->netdev->name, mac_states[priv->mac_state]); return; } - if (!priv->rx_skb || !priv->rx_skb->data) - return; - - buf = (struct at76_rx_buffer *)priv->rx_skb->data; - - if (urb->status != 0) { - if (urb->status != -ENOENT && urb->status != -ECONNRESET) - at76_dbg(DBG_URB, - "%s %s: - nonzero Rx bulk status received: %d", - __func__, wiphy_name(priv->hw->wiphy), - urb->status); - return; + BUG_ON(!priv->curr_bss); + + cancel_delayed_work(&priv->dwork_assoc); + if (status == WLAN_STATUS_SUCCESS) { + struct bss_info *ptr = priv->curr_bss; + priv->assoc_id = assoc_id & 0x3fff; + /* update iwconfig params */ + memcpy(priv->bssid, ptr->bssid, ETH_ALEN); + memcpy(priv->essid, ptr->ssid, ptr->ssid_len); + priv->essid_size = ptr->ssid_len; + priv->channel = ptr->channel; + schedule_work(&priv->work_assoc_done); + } else { + at76_set_mac_state(priv, MAC_JOINING); + schedule_work(&priv->work_join); } +} - at76_dbg(DBG_RX_ATMEL_HDR, - "%s: rx frame: rate %d rssi %d noise %d link %d", - wiphy_name(priv->hw->wiphy), buf->rx_rate, buf->rssi, - buf->noise_level, buf->link_quality); - - skb_trim(priv->rx_skb, le16_to_cpu(buf->wlength) + AT76_RX_HDRLEN); - at76_dbg_dump(DBG_RX_DATA, &priv->rx_skb->data[AT76_RX_HDRLEN], - priv->rx_skb->len, "RX: len=%d", - (int)(priv->rx_skb->len - AT76_RX_HDRLEN)); +/* Process disassociation request from the AP */ +static void at76_rx_mgmt_disassoc(struct at76_priv *priv, + struct at76_rx_buffer *buf) +{ + struct ieee80211_disassoc *resp = + (struct ieee80211_disassoc *)buf->packet; + struct ieee80211_hdr_3addr *mgmt = &resp->header; + + at76_dbg(DBG_RX_MGMT, + "%s: rx DisAssoc bssid %s reason 0x%04x destination %s", + priv->netdev->name, mac2str(mgmt->addr3), + le16_to_cpu(resp->reason), mac2str(mgmt->addr1)); + + /* We are not connected, ignore */ + if (priv->mac_state == MAC_SCANNING || priv->mac_state == MAC_INIT + || !priv->curr_bss) + return; - rx_status.signal = buf->rssi; - /* FIXME: is rate_idx still present in structure? */ - rx_status.rate_idx = buf->rx_rate; - rx_status.flag |= RX_FLAG_DECRYPTED; - rx_status.flag |= RX_FLAG_IV_STRIPPED; + /* Not our BSSID, ignore */ + if (compare_ether_addr(mgmt->addr3, priv->curr_bss->bssid)) + return; - skb_pull(priv->rx_skb, AT76_RX_HDRLEN); - at76_dbg(DBG_MAC80211, "calling ieee80211_rx_irqsafe(): %d/%d", - priv->rx_skb->len, priv->rx_skb->data_len); - ieee80211_rx_irqsafe(priv->hw, priv->rx_skb, &rx_status); + /* Not for our STA and not broadcast, ignore */ + if (compare_ether_addr(priv->netdev->dev_addr, mgmt->addr1) + && !is_broadcast_ether_addr(mgmt->addr1)) + return; - /* Use a new skb for the next receive */ - priv->rx_skb = NULL; + if (priv->mac_state != MAC_ASSOC && priv->mac_state != MAC_CONNECTED + && priv->mac_state != MAC_JOINING) { + printk(KERN_INFO "%s: DisAssoc in state %s ignored\n", + priv->netdev->name, mac_states[priv->mac_state]); + return; + } - at76_submit_rx_urb(priv); + if (priv->mac_state == MAC_CONNECTED) { + netif_carrier_off(priv->netdev); + netif_stop_queue(priv->netdev); + at76_iwevent_bss_disconnect(priv->netdev); + } + cancel_delayed_work(&priv->dwork_get_scan); + cancel_delayed_work(&priv->dwork_beacon); + cancel_delayed_work(&priv->dwork_auth); + cancel_delayed_work(&priv->dwork_assoc); + at76_set_mac_state(priv, MAC_JOINING); + schedule_work(&priv->work_join); } -/* Load firmware into kernel memory and parse it */ -static struct fwentry *at76_load_firmware(struct usb_device *udev, - enum board_type board_type) +static void at76_rx_mgmt_auth(struct at76_priv *priv, + struct at76_rx_buffer *buf) { - int ret; - char *str; - struct at76_fw_header *fwh; - struct fwentry *fwe = &firmwares[board_type]; - - mutex_lock(&fw_mutex); - - if (fwe->loaded) { - at76_dbg(DBG_FW, "re-using previously loaded fw"); - goto exit; + struct ieee80211_auth *resp = (struct ieee80211_auth *)buf->packet; + struct ieee80211_hdr_3addr *mgmt = &resp->header; + int seq_nr = le16_to_cpu(resp->transaction); + int alg = le16_to_cpu(resp->algorithm); + int status = le16_to_cpu(resp->status); + + at76_dbg(DBG_RX_MGMT, + "%s: rx AuthFrame bssid %s alg %d seq_nr %d status %d " + "destination %s", priv->netdev->name, mac2str(mgmt->addr3), + alg, seq_nr, status, mac2str(mgmt->addr1)); + + if (alg == WLAN_AUTH_SHARED_KEY && seq_nr == 2) + at76_dbg(DBG_RX_MGMT, "%s: AuthFrame challenge %s ...", + priv->netdev->name, hex2str(resp->info_element, 18)); + + if (priv->mac_state != MAC_AUTH) { + printk(KERN_INFO "%s: ignored AuthFrame in state %s\n", + priv->netdev->name, mac_states[priv->mac_state]); + return; } - - at76_dbg(DBG_FW, "downloading firmware %s", fwe->fwname); - ret = request_firmware(&fwe->fw, fwe->fwname, &udev->dev); - if (ret < 0) { - dev_printk(KERN_ERR, &udev->dev, "firmware %s not found!\n", - fwe->fwname); - dev_printk(KERN_ERR, &udev->dev, - "you may need to download the firmware from " - "http://developer.berlios.de/projects/at76c503a/\n"); - goto exit; + if (priv->auth_mode != alg) { + printk(KERN_INFO "%s: ignored AuthFrame for alg %d\n", + priv->netdev->name, alg); + return; } - at76_dbg(DBG_FW, "got it."); - fwh = (struct at76_fw_header *)(fwe->fw->data); + BUG_ON(!priv->curr_bss); - if (fwe->fw->size <= sizeof(*fwh)) { - dev_printk(KERN_ERR, &udev->dev, - "firmware is too short (0x%zx)\n", fwe->fw->size); - goto exit; + /* Not our BSSID or not for our STA, ignore */ + if (compare_ether_addr(mgmt->addr3, priv->curr_bss->bssid) + || compare_ether_addr(priv->netdev->dev_addr, mgmt->addr1)) + return; + + cancel_delayed_work(&priv->dwork_auth); + if (status != WLAN_STATUS_SUCCESS) { + /* try to join next bss */ + at76_set_mac_state(priv, MAC_JOINING); + schedule_work(&priv->work_join); + return; } - /* CRC currently not checked */ - fwe->board_type = le32_to_cpu(fwh->board_type); - if (fwe->board_type != board_type) { - dev_printk(KERN_ERR, &udev->dev, - "board type mismatch, requested %u, got %u\n", - board_type, fwe->board_type); - goto exit; + if (priv->auth_mode == WLAN_AUTH_OPEN || seq_nr == 4) { + priv->retries = ASSOC_RETRIES; + at76_set_mac_state(priv, MAC_ASSOC); + at76_assoc_req(priv, priv->curr_bss); + at76_dbg(DBG_MGMT_TIMER, + "%s:%d: starting mgmt_timer + HZ", __func__, __LINE__); + schedule_delayed_work(&priv->dwork_assoc, ASSOC_TIMEOUT); + return; } - fwe->fw_version.major = fwh->major; - fwe->fw_version.minor = fwh->minor; - fwe->fw_version.patch = fwh->patch; - fwe->fw_version.build = fwh->build; + WARN_ON(seq_nr != 2); + at76_auth_req(priv, priv->curr_bss, seq_nr + 1, resp->info_element); + at76_dbg(DBG_MGMT_TIMER, "%s:%d: starting mgmt_timer + HZ", __func__, + __LINE__); + schedule_delayed_work(&priv->dwork_auth, AUTH_TIMEOUT); +} - str = (char *)fwh + le32_to_cpu(fwh->str_offset); - fwe->intfw = (u8 *)fwh + le32_to_cpu(fwh->int_fw_offset); - fwe->intfw_size = le32_to_cpu(fwh->int_fw_len); - fwe->extfw = (u8 *)fwh + le32_to_cpu(fwh->ext_fw_offset); - fwe->extfw_size = le32_to_cpu(fwh->ext_fw_len); +static void at76_rx_mgmt_deauth(struct at76_priv *priv, + struct at76_rx_buffer *buf) +{ + struct ieee80211_disassoc *resp = + (struct ieee80211_disassoc *)buf->packet; + struct ieee80211_hdr_3addr *mgmt = &resp->header; + + at76_dbg(DBG_RX_MGMT | DBG_PROGRESS, + "%s: rx DeAuth bssid %s reason 0x%04x destination %s", + priv->netdev->name, mac2str(mgmt->addr3), + le16_to_cpu(resp->reason), mac2str(mgmt->addr1)); + + if (priv->mac_state != MAC_AUTH && priv->mac_state != MAC_ASSOC + && priv->mac_state != MAC_CONNECTED) { + printk(KERN_INFO "%s: DeAuth in state %s ignored\n", + priv->netdev->name, mac_states[priv->mac_state]); + return; + } - fwe->loaded = 1; + BUG_ON(!priv->curr_bss); - dev_printk(KERN_DEBUG, &udev->dev, - "using firmware %s (version %d.%d.%d-%d)\n", - fwe->fwname, fwh->major, fwh->minor, fwh->patch, fwh->build); + /* Not our BSSID, ignore */ + if (compare_ether_addr(mgmt->addr3, priv->curr_bss->bssid)) + return; - at76_dbg(DBG_DEVSTART, "board %u, int %d:%d, ext %d:%d", board_type, - le32_to_cpu(fwh->int_fw_offset), le32_to_cpu(fwh->int_fw_len), - le32_to_cpu(fwh->ext_fw_offset), le32_to_cpu(fwh->ext_fw_len)); - at76_dbg(DBG_DEVSTART, "firmware id %s", str); + /* Not for our STA and not broadcast, ignore */ + if (compare_ether_addr(priv->netdev->dev_addr, mgmt->addr1) + && !is_broadcast_ether_addr(mgmt->addr1)) + return; -exit: - mutex_unlock(&fw_mutex); + if (priv->mac_state == MAC_CONNECTED) + at76_iwevent_bss_disconnect(priv->netdev); - if (fwe->loaded) - return fwe; - else - return NULL; + at76_set_mac_state(priv, MAC_JOINING); + schedule_work(&priv->work_join); + cancel_delayed_work(&priv->dwork_get_scan); + cancel_delayed_work(&priv->dwork_beacon); + cancel_delayed_work(&priv->dwork_auth); + cancel_delayed_work(&priv->dwork_assoc); } -static void at76_mac80211_tx_callback(struct urb *urb) +static void at76_rx_mgmt_beacon(struct at76_priv *priv, + struct at76_rx_buffer *buf) { - struct at76_priv *priv = urb->context; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(priv->tx_skb); + int varpar_len; + /* beacon content */ + struct ieee80211_beacon *bdata = (struct ieee80211_beacon *)buf->packet; + struct ieee80211_hdr_3addr *mgmt = &bdata->header; + + struct list_head *lptr; + struct bss_info *match; /* entry matching addr3 with its bssid */ + int new_entry = 0; + int len; + struct ieee80211_info_element *ie; + int have_ssid = 0; + int have_rates = 0; + int have_channel = 0; + int keep_going = 1; + unsigned long flags; + + spin_lock_irqsave(&priv->bss_list_spinlock, flags); + if (priv->mac_state == MAC_CONNECTED) { + /* in state MAC_CONNECTED we use the mgmt_timer to control + the beacon of the BSS */ + BUG_ON(!priv->curr_bss); + + if (!compare_ether_addr(priv->curr_bss->bssid, mgmt->addr3)) { + /* We got our AP's beacon, defer the timeout handler. + Kill pending work first, as schedule_delayed_work() + won't do it. */ + cancel_delayed_work(&priv->dwork_beacon); + schedule_delayed_work(&priv->dwork_beacon, + BEACON_TIMEOUT); + priv->curr_bss->rssi = buf->rssi; + priv->beacons_received++; + goto exit; + } + } - at76_dbg(DBG_MAC80211, "%s()", __func__); + /* look if we have this BSS already in the list */ + match = NULL; - switch (urb->status) { - case 0: - /* success */ - /* FIXME: - * is the frame really ACKed when tx_callback is called ? */ - info->flags |= IEEE80211_TX_STAT_ACK; - break; - case -ENOENT: - case -ECONNRESET: - /* fail, urb has been unlinked */ - /* FIXME: add error message */ - break; - default: - at76_dbg(DBG_URB, "%s - nonzero tx status received: %d", - __func__, urb->status); - break; + if (!list_empty(&priv->bss_list)) { + list_for_each(lptr, &priv->bss_list) { + struct bss_info *bss_ptr = + list_entry(lptr, struct bss_info, list); + if (!compare_ether_addr(bss_ptr->bssid, mgmt->addr3)) { + match = bss_ptr; + break; + } + } } - memset(&info->status, 0, sizeof(info->status)); + if (!match) { + /* BSS not in the list - append it */ + match = kzalloc(sizeof(struct bss_info), GFP_ATOMIC); + if (!match) { + at76_dbg(DBG_BSS_TABLE, + "%s: cannot kmalloc new bss info (%zd byte)", + priv->netdev->name, sizeof(struct bss_info)); + goto exit; + } + new_entry = 1; + list_add_tail(&match->list, &priv->bss_list); + } - ieee80211_tx_status_irqsafe(priv->hw, priv->tx_skb); + match->capa = le16_to_cpu(bdata->capability); + match->beacon_interval = le16_to_cpu(bdata->beacon_interval); + match->rssi = buf->rssi; + match->link_qual = buf->link_quality; + match->noise_level = buf->noise_level; + memcpy(match->bssid, mgmt->addr3, ETH_ALEN); + at76_dbg(DBG_RX_BEACON, "%s: bssid %s", priv->netdev->name, + mac2str(match->bssid)); + + ie = bdata->info_element; + + /* length of var length beacon parameters */ + varpar_len = min_t(int, le16_to_cpu(buf->wlength) - + sizeof(struct ieee80211_beacon), + BEACON_MAX_DATA_LENGTH); + + /* This routine steps through the bdata->data array to get + * some useful information about the access point. + * Currently, this implementation supports receipt of: SSID, + * supported transfer rates and channel, in any order, with some + * tolerance for intermittent unknown codes (although this + * functionality may not be necessary as the useful information will + * usually arrive in consecutively, but there have been some + * reports of some of the useful information fields arriving in a + * different order). + * It does not support any more IE types although MFIE_TYPE_TIM may + * be supported (on my AP at least). + * The bdata->data array is about 1500 bytes long but only ~36 of those + * bytes are useful, hence the have_ssid etc optimizations. */ + + while (keep_going && + ((&ie->data[ie->len] - (u8 *)bdata->info_element) <= + varpar_len)) { + + switch (ie->id) { + + case MFIE_TYPE_SSID: + if (have_ssid) + break; - priv->tx_skb = NULL; + len = min_t(int, IW_ESSID_MAX_SIZE, ie->len); - ieee80211_wake_queues(priv->hw); -} + /* we copy only if this is a new entry, + or the incoming SSID is not a hidden SSID. This + will protect us from overwriting a real SSID read + in a ProbeResponse with a hidden one from a + following beacon. */ + if (!new_entry && at76_is_hidden_ssid(ie->data, len)) { + have_ssid = 1; + break; + } -static int at76_mac80211_tx(struct ieee80211_hw *hw, struct sk_buff *skb) -{ - struct at76_priv *priv = hw->priv; - struct at76_tx_buffer *tx_buffer = priv->bulk_out_buffer; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - int padding, submit_len, ret; + match->ssid_len = len; + memcpy(match->ssid, ie->data, len); + at76_dbg(DBG_RX_BEACON, "%s: SSID - %.*s", + priv->netdev->name, len, match->ssid); + have_ssid = 1; + break; - at76_dbg(DBG_MAC80211, "%s()", __func__); + case MFIE_TYPE_RATES: + if (have_rates) + break; - if (priv->tx_urb->status == -EINPROGRESS) { - printk(KERN_ERR "%s: %s called while tx urb is pending\n", - wiphy_name(priv->hw->wiphy), __func__); - return NETDEV_TX_BUSY; - } + match->rates_len = + min_t(int, sizeof(match->rates), ie->len); + memcpy(match->rates, ie->data, match->rates_len); + have_rates = 1; + at76_dbg(DBG_RX_BEACON, "%s: SUPPORTED RATES %s", + priv->netdev->name, + hex2str(ie->data, ie->len)); + break; - ieee80211_stop_queues(hw); + case MFIE_TYPE_DS_SET: + if (have_channel) + break; - at76_ledtrig_tx_activity(); /* tell ledtrigger we send a packet */ + match->channel = ie->data[0]; + have_channel = 1; + at76_dbg(DBG_RX_BEACON, "%s: CHANNEL - %d", + priv->netdev->name, match->channel); + break; - WARN_ON(priv->tx_skb != NULL); + case MFIE_TYPE_CF_SET: + case MFIE_TYPE_TIM: + case MFIE_TYPE_IBSS_SET: + default: + at76_dbg(DBG_RX_BEACON, "%s: beacon IE id %d len %d %s", + priv->netdev->name, ie->id, ie->len, + hex2str(ie->data, ie->len)); + break; + } - priv->tx_skb = skb; - padding = at76_calc_padding(skb->len); - submit_len = AT76_TX_HDRLEN + skb->len + padding; + /* advance to the next informational element */ + next_ie(&ie); - /* setup 'Atmel' header */ - memset(tx_buffer, 0, sizeof(*tx_buffer)); - tx_buffer->padding = padding; - tx_buffer->wlength = cpu_to_le16(skb->len); - tx_buffer->tx_rate = ieee80211_get_tx_rate(hw, info)->hw_value; - if (FIRMWARE_IS_WPA(priv->fw_version) && info->control.hw_key) { - tx_buffer->key_id = (info->control.hw_key->keyidx); - tx_buffer->cipher_type = - priv->keys[info->control.hw_key->keyidx].cipher; - tx_buffer->cipher_length = - priv->keys[info->control.hw_key->keyidx].keylen; - tx_buffer->reserved = 0; - } else { - tx_buffer->key_id = 0; - tx_buffer->cipher_type = 0; - tx_buffer->cipher_length = 0; - tx_buffer->reserved = 0; - }; - /* memset(tx_buffer->reserved, 0, sizeof(tx_buffer->reserved)); */ - memcpy(tx_buffer->packet, skb->data, skb->len); + /* Optimization: after all, the bdata->data array is + * varpar_len bytes long, whereas we get all of the useful + * information after only ~36 bytes, this saves us a lot of + * time (and trouble as the remaining portion of the array + * could be full of junk) + * Comment this out if you want to see what other information + * comes from the AP - although little of it may be useful */ + } - at76_dbg(DBG_TX_DATA, "%s tx: wlen 0x%x pad 0x%x rate %d hdr", - wiphy_name(priv->hw->wiphy), le16_to_cpu(tx_buffer->wlength), - tx_buffer->padding, tx_buffer->tx_rate); + at76_dbg(DBG_RX_BEACON, "%s: Finished processing beacon data", + priv->netdev->name); - /* send stuff */ - at76_dbg_dump(DBG_TX_DATA_CONTENT, tx_buffer, submit_len, - "%s(): tx_buffer %d bytes:", __func__, submit_len); - usb_fill_bulk_urb(priv->tx_urb, priv->udev, priv->tx_pipe, tx_buffer, - submit_len, at76_mac80211_tx_callback, priv); - ret = usb_submit_urb(priv->tx_urb, GFP_ATOMIC); - if (ret) { - printk(KERN_ERR "%s: error in tx submit urb: %d\n", - wiphy_name(priv->hw->wiphy), ret); - if (ret == -EINVAL) - printk(KERN_ERR - "%s: -EINVAL: tx urb %p hcpriv %p complete %p\n", - wiphy_name(priv->hw->wiphy), priv->tx_urb, - priv->tx_urb->hcpriv, priv->tx_urb->complete); - } + match->last_rx = jiffies; /* record last rx of beacon */ - return 0; +exit: + spin_unlock_irqrestore(&priv->bss_list_spinlock, flags); } -static int at76_mac80211_start(struct ieee80211_hw *hw) +/* Calculate the link level from a given rx_buffer */ +static void at76_calc_level(struct at76_priv *priv, struct at76_rx_buffer *buf, + struct iw_quality *qual) { - struct at76_priv *priv = hw->priv; - int ret; - - at76_dbg(DBG_MAC80211, "%s()", __func__); + /* just a guess for now, might be different for other chips */ + int max_rssi = 42; - mutex_lock(&priv->mtx); - - ret = at76_submit_rx_urb(priv); - if (ret < 0) { - printk(KERN_ERR "%s: open: submit_rx_urb failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); - goto error; - } + qual->level = (buf->rssi * 100 / max_rssi); + if (qual->level > 100) + qual->level = 100; + qual->updated |= IW_QUAL_LEVEL_UPDATED; +} - at76_startup_device(priv); +/* Calculate the link quality from a given rx_buffer */ +static void at76_calc_qual(struct at76_priv *priv, struct at76_rx_buffer *buf, + struct iw_quality *qual) +{ + if (at76_is_intersil(priv->board_type)) + qual->qual = buf->link_quality; + else { + unsigned long elapsed; - at76_start_monitor(priv); + /* Update qual at most once a second */ + elapsed = jiffies - priv->beacons_last_qual; + if (elapsed < 1 * HZ) + return; -error: - mutex_unlock(&priv->mtx); + qual->qual = qual->level * priv->beacons_received * + msecs_to_jiffies(priv->beacon_period) / elapsed; - return 0; + priv->beacons_last_qual = jiffies; + priv->beacons_received = 0; + } + qual->qual = (qual->qual > 100) ? 100 : qual->qual; + qual->updated |= IW_QUAL_QUAL_UPDATED; } -static void at76_mac80211_stop(struct ieee80211_hw *hw) +/* Calculate the noise quality from a given rx_buffer */ +static void at76_calc_noise(struct at76_priv *priv, struct at76_rx_buffer *buf, + struct iw_quality *qual) { - struct at76_priv *priv = hw->priv; - - at76_dbg(DBG_MAC80211, "%s()", __func__); - - mutex_lock(&priv->mtx); + qual->noise = 0; + qual->updated |= IW_QUAL_NOISE_INVALID; +} - if (!priv->device_unplugged) { - /* We are called by "ifconfig ethX down", not because the - * device is not available anymore. */ - if (at76_set_radio(priv, 0) == 1) - at76_wait_completion(priv, CMD_RADIO_ON); +static void at76_update_wstats(struct at76_priv *priv, + struct at76_rx_buffer *buf) +{ + struct iw_quality *qual = &priv->wstats.qual; - /* We unlink rx_urb because at76_open() re-submits it. - * If unplugged, at76_delete_device() takes care of it. */ - usb_kill_urb(priv->rx_urb); + if (buf->rssi && priv->mac_state == MAC_CONNECTED) { + qual->updated = 0; + at76_calc_level(priv, buf, qual); + at76_calc_qual(priv, buf, qual); + at76_calc_noise(priv, buf, qual); + } else { + qual->qual = 0; + qual->level = 0; + qual->noise = 0; + qual->updated = IW_QUAL_ALL_INVALID; } - - mutex_unlock(&priv->mtx); } -static int at76_add_interface(struct ieee80211_hw *hw, - struct ieee80211_if_init_conf *conf) +static void at76_rx_mgmt(struct at76_priv *priv, struct at76_rx_buffer *buf) { - struct at76_priv *priv = hw->priv; - int ret = 0; + struct ieee80211_hdr_3addr *mgmt = + (struct ieee80211_hdr_3addr *)buf->packet; + u16 framectl = le16_to_cpu(mgmt->frame_ctl); + + /* update wstats */ + if (priv->mac_state != MAC_INIT && priv->mac_state != MAC_SCANNING) { + /* jal: this is a dirty hack needed by Tim in ad-hoc mode */ + /* Data packets always seem to have a 0 link level, so we + only read link quality info from management packets. + Atmel driver actually averages the present, and previous + values, we just present the raw value at the moment - TJS */ + if (priv->iw_mode == IW_MODE_ADHOC + || (priv->curr_bss + && !compare_ether_addr(mgmt->addr3, + priv->curr_bss->bssid))) + at76_update_wstats(priv, buf); + } - at76_dbg(DBG_MAC80211, "%s()", __func__); + at76_dbg(DBG_RX_MGMT_CONTENT, "%s rx mgmt framectl 0x%x %s", + priv->netdev->name, framectl, + hex2str(mgmt, le16_to_cpu(buf->wlength))); - mutex_lock(&priv->mtx); + switch (framectl & IEEE80211_FCTL_STYPE) { + case IEEE80211_STYPE_BEACON: + case IEEE80211_STYPE_PROBE_RESP: + at76_rx_mgmt_beacon(priv, buf); + break; + + case IEEE80211_STYPE_ASSOC_RESP: + at76_rx_mgmt_assoc(priv, buf); + break; - switch (conf->type) { - case NL80211_IFTYPE_STATION: - priv->iw_mode = IW_MODE_INFRA; + case IEEE80211_STYPE_DISASSOC: + at76_rx_mgmt_disassoc(priv, buf); break; + + case IEEE80211_STYPE_AUTH: + at76_rx_mgmt_auth(priv, buf); + break; + + case IEEE80211_STYPE_DEAUTH: + at76_rx_mgmt_deauth(priv, buf); + break; + default: - ret = -EOPNOTSUPP; - goto exit; + printk(KERN_DEBUG "%s: ignoring frame with framectl 0x%04x\n", + priv->netdev->name, framectl); } -exit: - mutex_unlock(&priv->mtx); - - return ret; + return; } -static void at76_remove_interface(struct ieee80211_hw *hw, - struct ieee80211_if_init_conf *conf) +/* Convert the 802.11 header into an ethernet-style header, make skb + * ready for consumption by netif_rx() */ +static void at76_ieee80211_to_eth(struct sk_buff *skb, int iw_mode) { - at76_dbg(DBG_MAC80211, "%s()", __func__); -} + struct ieee80211_hdr_3addr *i802_11_hdr; + struct ethhdr *eth_hdr_p; + u8 *src_addr; + u8 *dest_addr; -static int at76_join(struct at76_priv *priv) -{ - struct at76_req_join join; - int ret; + i802_11_hdr = (struct ieee80211_hdr_3addr *)skb->data; - memset(&join, 0, sizeof(struct at76_req_join)); - memcpy(join.essid, priv->essid, priv->essid_size); - join.essid_size = priv->essid_size; - memcpy(join.bssid, priv->bssid, ETH_ALEN); - join.bss_type = INFRASTRUCTURE_MODE; - join.channel = priv->channel; - join.timeout = cpu_to_le16(2000); + /* That would be the ethernet header if the hardware converted + * the frame for us. Make sure the source and the destination + * match the 802.11 header. Which hardware does it? */ + eth_hdr_p = (struct ethhdr *)skb_pull(skb, IEEE80211_3ADDR_LEN); - at76_dbg(DBG_MAC80211, "%s: sending CMD_JOIN", __func__); - ret = at76_set_card_command(priv->udev, CMD_JOIN, &join, - sizeof(struct at76_req_join)); + dest_addr = i802_11_hdr->addr1; + if (iw_mode == IW_MODE_ADHOC) + src_addr = i802_11_hdr->addr2; + else + src_addr = i802_11_hdr->addr3; - if (ret < 0) { - printk(KERN_ERR "%s: at76_set_card_command failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); - return 0; - } + if (!compare_ether_addr(eth_hdr_p->h_source, src_addr) && + !compare_ether_addr(eth_hdr_p->h_dest, dest_addr)) + /* Yes, we already have an ethernet header */ + skb_reset_mac_header(skb); + else { + u16 len; + + /* Need to build an ethernet header */ + if (!memcmp(skb->data, snapsig, sizeof(snapsig))) { + /* SNAP frame - decapsulate, keep proto */ + skb_push(skb, offsetof(struct ethhdr, h_proto) - + sizeof(rfc1042sig)); + len = 0; + } else { + /* 802.3 frame, proto is length */ + len = skb->len; + skb_push(skb, ETH_HLEN); + } - ret = at76_wait_completion(priv, CMD_JOIN); - at76_dbg(DBG_MAC80211, "%s: CMD_JOIN returned: 0x%02x", __func__, ret); - if (ret != CMD_STATUS_COMPLETE) { - printk(KERN_ERR "%s: at76_wait_completion failed: %d\n", - wiphy_name(priv->hw->wiphy), ret); - return 0; + skb_reset_mac_header(skb); + eth_hdr_p = eth_hdr(skb); + /* This needs to be done in this order (eth_hdr_p->h_dest may + * overlap src_addr) */ + memcpy(eth_hdr_p->h_source, src_addr, ETH_ALEN); + memcpy(eth_hdr_p->h_dest, dest_addr, ETH_ALEN); + if (len) + eth_hdr_p->h_proto = htons(len); } - at76_set_tkip_bssid(priv, priv->bssid); - at76_set_pm_mode(priv); - - return 0; + skb->protocol = eth_type_trans(skb, skb->dev); } -static void at76_dwork_hw_scan(struct work_struct *work) +/* Check for fragmented data in priv->rx_skb. If the packet was no fragment + or it was the last of a fragment set a skb containing the whole packet + is returned for further processing. Otherwise we get NULL and are + done and the packet is either stored inside the fragment buffer + or thrown away. Every returned skb starts with the ieee802_11 header + and contains _no_ FCS at the end */ +static struct sk_buff *at76_check_for_rx_frags(struct at76_priv *priv) { - struct at76_priv *priv = container_of(work, struct at76_priv, - dwork_hw_scan.work); - int ret; + struct sk_buff *skb = priv->rx_skb; + struct at76_rx_buffer *buf = (struct at76_rx_buffer *)skb->data; + struct ieee80211_hdr_3addr *i802_11_hdr = + (struct ieee80211_hdr_3addr *)buf->packet; + /* seq_ctrl, fragment_number, sequence number of new packet */ + u16 sctl = le16_to_cpu(i802_11_hdr->seq_ctl); + u16 fragnr = sctl & 0xf; + u16 seqnr = sctl >> 4; + u16 frame_ctl = le16_to_cpu(i802_11_hdr->frame_ctl); - ret = at76_get_cmd_status(priv->udev, CMD_SCAN); - at76_dbg(DBG_MAC80211, "%s: CMD_SCAN status 0x%02x", __func__, ret); + /* Length including the IEEE802.11 header, but without the trailing + * FCS and without the Atmel Rx header */ + int length = le16_to_cpu(buf->wlength) - IEEE80211_FCS_LEN; - /* FIXME: add maximum time for scan to complete */ + /* where does the data payload start in skb->data ? */ + u8 *data = i802_11_hdr->payload; - if (ret != CMD_STATUS_COMPLETE) { - queue_delayed_work(priv->hw->workqueue, &priv->dwork_hw_scan, - SCAN_POLL_INTERVAL); - goto exit; + /* length of payload, excl. the trailing FCS */ + int data_len = length - IEEE80211_3ADDR_LEN; + + int i; + struct rx_data_buf *bptr, *optr; + unsigned long oldest = ~0UL; + + at76_dbg(DBG_RX_FRAGS, + "%s: rx data frame_ctl %04x addr2 %s seq/frag %d/%d " + "length %d data %d: %s ...", priv->netdev->name, frame_ctl, + mac2str(i802_11_hdr->addr2), seqnr, fragnr, length, data_len, + hex2str(data, 32)); + + at76_dbg(DBG_RX_FRAGS_SKB, "%s: incoming skb: head %p data %p " + "tail %p end %p len %d", priv->netdev->name, skb->head, + skb->data, skb_tail_pointer(skb), skb_end_pointer(skb), + skb->len); + + if (data_len < 0) { + /* make sure data starts in the buffer */ + printk(KERN_INFO "%s: data frame too short\n", + priv->netdev->name); + return NULL; } - ieee80211_scan_completed(priv->hw); + WARN_ON(length <= AT76_RX_HDRLEN); + if (length <= AT76_RX_HDRLEN) + return NULL; - if (is_valid_ether_addr(priv->bssid)) { - ieee80211_wake_queues(priv->hw); - at76_join(priv); + /* remove the at76_rx_buffer header - we don't need it anymore */ + /* we need the IEEE802.11 header (for the addresses) if this packet + is the first of a chain */ + skb_pull(skb, AT76_RX_HDRLEN); + + /* remove FCS at end */ + skb_trim(skb, length); + + at76_dbg(DBG_RX_FRAGS_SKB, "%s: trimmed skb: head %p data %p tail %p " + "end %p len %d data %p data_len %d", priv->netdev->name, + skb->head, skb->data, skb_tail_pointer(skb), + skb_end_pointer(skb), skb->len, data, data_len); + + if (fragnr == 0 && !(frame_ctl & IEEE80211_FCTL_MOREFRAGS)) { + /* unfragmented packet received */ + /* Use a new skb for the next receive */ + priv->rx_skb = NULL; + at76_dbg(DBG_RX_FRAGS, "%s: unfragmented", priv->netdev->name); + return skb; } - ieee80211_wake_queues(priv->hw); + /* look if we've got a chain for the sender address. + afterwards optr points to first free or the oldest entry, + or, if i < NR_RX_DATA_BUF, bptr points to the entry for the + sender address */ + /* determining the oldest entry doesn't cope with jiffies wrapping + but I don't care to delete a young entry at these rare moments ... */ + + bptr = priv->rx_data; + optr = NULL; + for (i = 0; i < NR_RX_DATA_BUF; i++, bptr++) { + if (!bptr->skb) { + optr = bptr; + oldest = 0UL; + continue; + } -exit: - return; -} + if (!compare_ether_addr(i802_11_hdr->addr2, bptr->sender)) + break; -static int at76_hw_scan(struct ieee80211_hw *hw, u8 *ssid, size_t len) -{ - struct at76_priv *priv = hw->priv; - struct at76_req_scan scan; - int ret; + if (!optr) { + optr = bptr; + oldest = bptr->last_rx; + } else if (bptr->last_rx < oldest) + optr = bptr; + } - at76_dbg(DBG_MAC80211, "%s():", __func__); - at76_dbg_dump(DBG_MAC80211, ssid, len, "ssid %zd bytes:", len); + if (i < NR_RX_DATA_BUF) { + + at76_dbg(DBG_RX_FRAGS, "%s: %d. cacheentry (seq/frag = %d/%d) " + "matched sender addr", + priv->netdev->name, i, bptr->seqnr, bptr->fragnr); + + /* bptr points to an entry for the sender address */ + if (bptr->seqnr == seqnr) { + int left; + /* the fragment has the current sequence number */ + if (((bptr->fragnr + 1) & 0xf) != fragnr) { + /* wrong fragment number -> ignore it */ + /* is & 0xf necessary above ??? */ + at76_dbg(DBG_RX_FRAGS, + "%s: frag nr mismatch: %d + 1 != %d", + priv->netdev->name, bptr->fragnr, + fragnr); + return NULL; + } + bptr->last_rx = jiffies; + /* the next following fragment number -> + add the data at the end */ + + /* for test only ??? */ + left = skb_tailroom(bptr->skb); + if (left < data_len) + printk(KERN_INFO + "%s: only %d byte free (need %d)\n", + priv->netdev->name, left, data_len); + else + memcpy(skb_put(bptr->skb, data_len), data, + data_len); + + bptr->fragnr = fragnr; + if (frame_ctl & IEEE80211_FCTL_MOREFRAGS) + return NULL; + + /* this was the last fragment - send it */ + skb = bptr->skb; + bptr->skb = NULL; /* free the entry */ + at76_dbg(DBG_RX_FRAGS, "%s: last frag of seq %d", + priv->netdev->name, seqnr); + return skb; + } - mutex_lock(&priv->mtx); + /* got another sequence number */ + if (fragnr == 0) { + /* it's the start of a new chain - replace the + old one by this */ + /* bptr->sender has the correct value already */ + at76_dbg(DBG_RX_FRAGS, + "%s: start of new seq %d, removing old seq %d", + priv->netdev->name, seqnr, bptr->seqnr); + bptr->seqnr = seqnr; + bptr->fragnr = 0; + bptr->last_rx = jiffies; + /* swap bptr->skb and priv->rx_skb */ + skb = bptr->skb; + bptr->skb = priv->rx_skb; + priv->rx_skb = skb; + } else { + /* it from the middle of a new chain -> + delete the old entry and skip the new one */ + at76_dbg(DBG_RX_FRAGS, + "%s: middle of new seq %d (%d) " + "removing old seq %d", + priv->netdev->name, seqnr, fragnr, + bptr->seqnr); + dev_kfree_skb(bptr->skb); + bptr->skb = NULL; + } + return NULL; + } - ieee80211_stop_queues(hw); + /* if we didn't find a chain for the sender address, optr + points either to the first free or the oldest entry */ - memset(&scan, 0, sizeof(struct at76_req_scan)); - memset(scan.bssid, 0xFF, ETH_ALEN); - scan.scan_type = SCAN_TYPE_ACTIVE; - if (priv->essid_size > 0) { - memcpy(scan.essid, ssid, len); - scan.essid_size = len; + if (fragnr != 0) { + /* this is not the begin of a fragment chain ... */ + at76_dbg(DBG_RX_FRAGS, + "%s: no chain for non-first fragment (%d)", + priv->netdev->name, fragnr); + return NULL; } - scan.min_channel_time = cpu_to_le16(priv->scan_min_time); - scan.max_channel_time = cpu_to_le16(priv->scan_max_time); - scan.probe_delay = cpu_to_le16(priv->scan_min_time * 1000); - scan.international_scan = 0; - at76_dbg(DBG_MAC80211, "%s: sending CMD_SCAN", __func__); - ret = at76_set_card_command(priv->udev, CMD_SCAN, &scan, sizeof(scan)); + BUG_ON(!optr); + if (optr->skb) { + /* swap the skb's */ + skb = optr->skb; + optr->skb = priv->rx_skb; + priv->rx_skb = skb; - if (ret < 0) { - err("CMD_SCAN failed: %d", ret); - goto exit; - } + at76_dbg(DBG_RX_FRAGS, + "%s: free old contents: sender %s seq/frag %d/%d", + priv->netdev->name, mac2str(optr->sender), + optr->seqnr, optr->fragnr); - queue_delayed_work(priv->hw->workqueue, &priv->dwork_hw_scan, - SCAN_POLL_INTERVAL); + } else { + /* take the skb from priv->rx_skb */ + optr->skb = priv->rx_skb; + /* let at76_submit_rx_urb() allocate a new skb */ + priv->rx_skb = NULL; -exit: - mutex_unlock(&priv->mtx); + at76_dbg(DBG_RX_FRAGS, "%s: use a free entry", + priv->netdev->name); + } + memcpy(optr->sender, i802_11_hdr->addr2, ETH_ALEN); + optr->seqnr = seqnr; + optr->fragnr = 0; + optr->last_rx = jiffies; - return 0; + return NULL; } -static int at76_config(struct ieee80211_hw *hw, u32 changed) +/* Rx interrupt: we expect the complete data buffer in priv->rx_skb */ +static void at76_rx_data(struct at76_priv *priv) { - struct at76_priv *priv = hw->priv; - struct ieee80211_conf *conf = &hw->conf; + struct net_device *netdev = priv->netdev; + struct net_device_stats *stats = &priv->stats; + struct sk_buff *skb = priv->rx_skb; + struct at76_rx_buffer *buf = (struct at76_rx_buffer *)skb->data; + struct ieee80211_hdr_3addr *i802_11_hdr; + int length = le16_to_cpu(buf->wlength); - at76_dbg(DBG_MAC80211, "%s(): channel %d radio %d", - __func__, conf->channel->hw_value, conf->radio_enabled); - at76_dbg_dump(DBG_MAC80211, priv->essid, priv->essid_size, "ssid:"); - at76_dbg_dump(DBG_MAC80211, priv->bssid, ETH_ALEN, "bssid:"); + at76_dbg(DBG_RX_DATA, "%s received data packet: %s", netdev->name, + hex2str(skb->data, AT76_RX_HDRLEN)); - mutex_lock(&priv->mtx); + at76_dbg(DBG_RX_DATA_CONTENT, "rx packet: %s", + hex2str(skb->data + AT76_RX_HDRLEN, length)); - priv->channel = conf->channel->hw_value; + skb = at76_check_for_rx_frags(priv); + if (!skb) + return; - if (is_valid_ether_addr(priv->bssid)) { - at76_join(priv); - ieee80211_wake_queues(priv->hw); - } else { - ieee80211_stop_queues(priv->hw); - at76_start_monitor(priv); - }; + /* Atmel header and the FCS are already removed */ + i802_11_hdr = (struct ieee80211_hdr_3addr *)skb->data; - mutex_unlock(&priv->mtx); + skb->dev = netdev; + skb->ip_summed = CHECKSUM_NONE; /* TODO: should check CRC */ - return 0; -} + if (is_broadcast_ether_addr(i802_11_hdr->addr1)) { + if (!compare_ether_addr(i802_11_hdr->addr1, netdev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else if (compare_ether_addr(i802_11_hdr->addr1, netdev->dev_addr)) + skb->pkt_type = PACKET_OTHERHOST; -static int at76_config_interface(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct ieee80211_if_conf *conf) -{ - struct at76_priv *priv = hw->priv; + at76_ieee80211_to_eth(skb, priv->iw_mode); - at76_dbg_dump(DBG_MAC80211, conf->bssid, ETH_ALEN, "bssid:"); + netdev->last_rx = jiffies; + netif_rx(skb); + stats->rx_packets++; + stats->rx_bytes += length; - mutex_lock(&priv->mtx); + return; +} - memcpy(priv->bssid, conf->bssid, ETH_ALEN); -// memcpy(priv->essid, conf->ssid, conf->ssid_len); -// priv->essid_size = conf->ssid_len; +static void at76_rx_monitor_mode(struct at76_priv *priv) +{ + struct at76_rx_radiotap *rt; + u8 *payload; + int skblen; + struct net_device *netdev = priv->netdev; + struct at76_rx_buffer *buf = + (struct at76_rx_buffer *)priv->rx_skb->data; + /* length including the IEEE802.11 header and the trailing FCS, + but not at76_rx_buffer */ + int length = le16_to_cpu(buf->wlength); + struct sk_buff *skb = priv->rx_skb; + struct net_device_stats *stats = &priv->stats; - if (is_valid_ether_addr(priv->bssid)) { - /* mac80211 is joining a bss */ - ieee80211_wake_queues(priv->hw); - at76_join(priv); - } else - ieee80211_stop_queues(priv->hw); + if (length < IEEE80211_FCS_LEN) { + /* buffer contains no data */ + at76_dbg(DBG_MONITOR_MODE, + "%s: MONITOR MODE: rx skb without data", + priv->netdev->name); + return; + } - mutex_unlock(&priv->mtx); + skblen = sizeof(struct at76_rx_radiotap) + length; - return 0; + skb = dev_alloc_skb(skblen); + if (!skb) { + printk(KERN_ERR "%s: MONITOR MODE: dev_alloc_skb for radiotap " + "header returned NULL\n", priv->netdev->name); + return; + } + + skb_put(skb, skblen); + + rt = (struct at76_rx_radiotap *)skb->data; + payload = skb->data + sizeof(struct at76_rx_radiotap); + + rt->rt_hdr.it_version = 0; + rt->rt_hdr.it_pad = 0; + rt->rt_hdr.it_len = cpu_to_le16(sizeof(struct at76_rx_radiotap)); + rt->rt_hdr.it_present = cpu_to_le32(AT76_RX_RADIOTAP_PRESENT); + + rt->rt_tsft = cpu_to_le64(le32_to_cpu(buf->rx_time)); + rt->rt_rate = hw_rates[buf->rx_rate] & (~0x80); + rt->rt_signal = buf->rssi; + rt->rt_noise = buf->noise_level; + rt->rt_flags = IEEE80211_RADIOTAP_F_FCS; + if (buf->fragmentation) + rt->rt_flags |= IEEE80211_RADIOTAP_F_FRAG; + + memcpy(payload, buf->packet, length); + skb->dev = netdev; + skb->ip_summed = CHECKSUM_NONE; + skb_reset_mac_header(skb); + skb->pkt_type = PACKET_OTHERHOST; + skb->protocol = htons(ETH_P_802_2); + + netdev->last_rx = jiffies; + netif_rx(skb); + stats->rx_packets++; + stats->rx_bytes += length; } -/* must be atomic */ -static void at76_configure_filter(struct ieee80211_hw *hw, - unsigned int changed_flags, - unsigned int *total_flags, int mc_count, - struct dev_addr_list *mc_list) +/* Check if we spy on the sender address in buf and update stats */ +static void at76_iwspy_update(struct at76_priv *priv, + struct at76_rx_buffer *buf) { - struct at76_priv *priv = hw->priv; - int flags; - - at76_dbg(DBG_MAC80211, "%s(): changed_flags=0x%08x " - "total_flags=0x%08x mc_count=%d", - __func__, changed_flags, *total_flags, mc_count); + struct ieee80211_hdr_3addr *hdr = + (struct ieee80211_hdr_3addr *)buf->packet; + struct iw_quality qual; - flags = changed_flags & AT76_SUPPORTED_FILTERS; - *total_flags = AT76_SUPPORTED_FILTERS; + /* We can only set the level here */ + qual.updated = IW_QUAL_QUAL_INVALID | IW_QUAL_NOISE_INVALID; + qual.level = 0; + qual.noise = 0; + at76_calc_level(priv, buf, &qual); - /* FIXME: access to priv->promisc should be protected with - * priv->mtx, but it's impossible because this function needs to be - * atomic */ + spin_lock_bh(&priv->spy_spinlock); - if (flags && !priv->promisc) { - /* mac80211 wants us to enable promiscuous mode */ - priv->promisc = 1; - } else if (!flags && priv->promisc) { - /* we need to disable promiscuous mode */ - priv->promisc = 0; - } else - return; + if (priv->spy_data.spy_number > 0) + wireless_spy_update(priv->netdev, hdr->addr2, &qual); - queue_work(hw->workqueue, &priv->work_set_promisc); + spin_unlock_bh(&priv->spy_spinlock); } -static int at76_set_key_oldfw(struct ieee80211_hw *hw, enum set_key_cmd cmd, - const u8 *local_address, const u8 *address, - struct ieee80211_key_conf *key) +static void at76_rx_tasklet(unsigned long param) { - struct at76_priv *priv = hw->priv; - - int i; - - at76_dbg(DBG_MAC80211, "%s(): cmd %d key->alg %d key->keyidx %d " - "key->keylen %d", - __func__, cmd, key->alg, key->keyidx, key->keylen); + struct urb *urb = (struct urb *)param; + struct at76_priv *priv = urb->context; + struct net_device *netdev = priv->netdev; + struct at76_rx_buffer *buf; + struct ieee80211_hdr_3addr *i802_11_hdr; + u16 frame_ctl; - if (key->alg != ALG_WEP) - return -EOPNOTSUPP; + if (priv->device_unplugged) { + at76_dbg(DBG_DEVSTART, "device unplugged"); + if (urb) + at76_dbg(DBG_DEVSTART, "urb status %d", urb->status); + return; + } - key->hw_key_idx = key->keyidx; + if (!priv->rx_skb || !netdev || !priv->rx_skb->data) + return; - mutex_lock(&priv->mtx); + buf = (struct at76_rx_buffer *)priv->rx_skb->data; - switch (cmd) { - case SET_KEY: - memcpy(priv->wep_keys[key->keyidx], key->key, key->keylen); - priv->wep_keys_len[key->keyidx] = key->keylen; + i802_11_hdr = (struct ieee80211_hdr_3addr *)buf->packet; - /* FIXME: find out how to do this properly */ - priv->wep_key_id = key->keyidx; + frame_ctl = le16_to_cpu(i802_11_hdr->frame_ctl); - break; - case DISABLE_KEY: - default: - priv->wep_keys_len[key->keyidx] = 0; - break; + if (urb->status != 0) { + if (urb->status != -ENOENT && urb->status != -ECONNRESET) + at76_dbg(DBG_URB, + "%s %s: - nonzero Rx bulk status received: %d", + __func__, netdev->name, urb->status); + return; } - priv->wep_enabled = 0; + at76_dbg(DBG_RX_ATMEL_HDR, + "%s: rx frame: rate %d rssi %d noise %d link %d %s", + priv->netdev->name, buf->rx_rate, buf->rssi, buf->noise_level, + buf->link_quality, hex2str(i802_11_hdr, 48)); + if (priv->iw_mode == IW_MODE_MONITOR) { + at76_rx_monitor_mode(priv); + goto exit; + } - for (i = 0; i < WEP_KEYS; i++) { - if (priv->wep_keys_len[i] != 0) - priv->wep_enabled = 1; + /* there is a new bssid around, accept it: */ + if (buf->newbss && priv->iw_mode == IW_MODE_ADHOC) { + at76_dbg(DBG_PROGRESS, "%s: rx newbss", netdev->name); + schedule_work(&priv->work_new_bss); } - at76_startup_device(priv); + switch (frame_ctl & IEEE80211_FCTL_FTYPE) { + case IEEE80211_FTYPE_DATA: + at76_rx_data(priv); + break; - mutex_unlock(&priv->mtx); + case IEEE80211_FTYPE_MGMT: + /* jal: TODO: find out if we can update iwspy also on + other frames than management (might depend on the + radio chip / firmware version !) */ - return 0; -} + at76_iwspy_update(priv, buf); -static int at76_set_key_newfw(struct ieee80211_hw *hw, enum set_key_cmd cmd, - const u8 *local_address, const u8 *address, - struct ieee80211_key_conf *key) -{ - struct at76_priv *priv = hw->priv; - int ret = -EOPNOTSUPP; - - at76_dbg(DBG_MAC80211, "%s(): cmd %d key->alg %d key->keyidx %d " - "key->keylen %d", - __func__, cmd, key->alg, key->keyidx, key->keylen); + at76_rx_mgmt(priv, buf); + break; - mutex_lock(&priv->mtx); + case IEEE80211_FTYPE_CTL: + at76_dbg(DBG_RX_CTRL, "%s: ignored ctrl frame: %04x", + priv->netdev->name, frame_ctl); + break; - priv->mib_buf.type = MIB_MAC_ENCRYPTION; + default: + printk(KERN_DEBUG "%s: ignoring frame with framectl 0x%04x\n", + priv->netdev->name, frame_ctl); + } +exit: + at76_submit_rx_urb(priv); +} - if (cmd == DISABLE_KEY) { - priv->mib_buf.size = CIPHER_KEY_LEN; - priv->mib_buf.index = offsetof(struct mib_mac_encryption, - cipher_default_keyvalue[key->keyidx]); - memset(priv->mib_buf.data.data, 0, CIPHER_KEY_LEN); - if (at76_set_mib(priv, &priv->mib_buf) != CMD_STATUS_COMPLETE) - ret = -EOPNOTSUPP; /* -EIO would be probably better */ - else { +/* Load firmware into kernel memory and parse it */ +static struct fwentry *at76_load_firmware(struct usb_device *udev, + enum board_type board_type) +{ + int ret; + char *str; + struct at76_fw_header *fwh; + struct fwentry *fwe = &firmwares[board_type]; - priv->keys[key->keyidx].cipher = CIPHER_NONE; - priv->keys[key->keyidx].keylen = 0; - }; - if (priv->default_group_key == key->keyidx) - priv->default_group_key = 0xff; + mutex_lock(&fw_mutex); - if (priv->default_pairwise_key == key->keyidx) - priv->default_pairwise_key = 0xff; - /* If default pairwise key is removed, fall back to - * group key? */ - ret = 0; + if (fwe->loaded) { + at76_dbg(DBG_FW, "re-using previously loaded fw"); goto exit; - }; - - if (cmd == SET_KEY) { - /* store key into MIB */ - priv->mib_buf.size = CIPHER_KEY_LEN; - priv->mib_buf.index = offsetof(struct mib_mac_encryption, - cipher_default_keyvalue[key->keyidx]); - memset(priv->mib_buf.data.data, 0, CIPHER_KEY_LEN); - memcpy(priv->mib_buf.data.data, key->key, key->keylen); - - switch (key->alg) { - case ALG_WEP: - if (key->keylen == 5) { - priv->keys[key->keyidx].cipher = - CIPHER_WEP64; - priv->keys[key->keyidx].keylen = 8; - } else if (key->keylen == 13) { - priv->keys[key->keyidx].cipher = - CIPHER_WEP128; - /* Firmware needs this */ - priv->keys[key->keyidx].keylen = 8; - } else { - ret = -EOPNOTSUPP; - goto exit; - }; - break; - case ALG_TKIP: - key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC; - priv->keys[key->keyidx].cipher = CIPHER_TKIP; - priv->keys[key->keyidx].keylen = 12; - break; + } - case ALG_CCMP: - if (!at76_is_505a(priv->board_type)) { - ret = -EOPNOTSUPP; - goto exit; - }; - key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC; - priv->keys[key->keyidx].cipher = CIPHER_CCMP; - priv->keys[key->keyidx].keylen = 16; - break; + at76_dbg(DBG_FW, "downloading firmware %s", fwe->fwname); + ret = request_firmware(&fwe->fw, fwe->fwname, &udev->dev); + if (ret < 0) { + dev_printk(KERN_ERR, &udev->dev, "firmware %s not found!\n", + fwe->fwname); + dev_printk(KERN_ERR, &udev->dev, + "you may need to download the firmware from " + "http://developer.berlios.de/projects/at76c503a/"); + goto exit; + } - default: - ret = -EOPNOTSUPP; - goto exit; - }; - - priv->mib_buf.data.data[38] = priv->keys[key->keyidx].cipher; - priv->mib_buf.data.data[39] = 1; /* Taken from atmelwlandriver, - not documented */ - - if (is_valid_ether_addr(address)) - /* Pairwise key */ - priv->mib_buf.data.data[39] |= (KEY_PAIRWISE | KEY_TX); - else if (is_broadcast_ether_addr(address)) - /* Group key */ - priv->mib_buf.data.data[39] |= (KEY_TX); - else /* Key used only for transmission ??? */ - priv->mib_buf.data.data[39] |= (KEY_TX); - - if (at76_set_mib(priv, &priv->mib_buf) != - CMD_STATUS_COMPLETE) { - ret = -EOPNOTSUPP; /* -EIO would be probably better */ - goto exit; - }; + at76_dbg(DBG_FW, "got it."); + fwh = (struct at76_fw_header *)(fwe->fw->data); - if ((key->alg == ALG_TKIP) || (key->alg == ALG_CCMP)) - at76_reset_rsc(priv); + if (fwe->fw->size <= sizeof(*fwh)) { + dev_printk(KERN_ERR, &udev->dev, + "firmware is too short (0x%zx)\n", fwe->fw->size); + goto exit; + } - key->hw_key_idx = key->keyidx; + /* CRC currently not checked */ + fwe->board_type = le32_to_cpu(fwh->board_type); + if (fwe->board_type != board_type) { + dev_printk(KERN_ERR, &udev->dev, + "board type mismatch, requested %u, got %u\n", + board_type, fwe->board_type); + goto exit; + } - /* Set up default keys */ - if (is_broadcast_ether_addr(address)) - priv->default_group_key = key->keyidx; - if (is_valid_ether_addr(address)) - priv->default_pairwise_key = key->keyidx; + fwe->fw_version.major = fwh->major; + fwe->fw_version.minor = fwh->minor; + fwe->fw_version.patch = fwh->patch; + fwe->fw_version.build = fwh->build; - /* Set up encryption MIBs */ + str = (char *)fwh + le32_to_cpu(fwh->str_offset); + fwe->intfw = (u8 *)fwh + le32_to_cpu(fwh->int_fw_offset); + fwe->intfw_size = le32_to_cpu(fwh->int_fw_len); + fwe->extfw = (u8 *)fwh + le32_to_cpu(fwh->ext_fw_offset); + fwe->extfw_size = le32_to_cpu(fwh->ext_fw_len); - /* first block of settings */ - priv->mib_buf.size = 3; - priv->mib_buf.index = offsetof(struct mib_mac_encryption, - privacy_invoked); - priv->mib_buf.data.data[0] = 1; /* privacy_invoked */ - priv->mib_buf.data.data[1] = priv->default_pairwise_key; - priv->mib_buf.data.data[2] = priv->default_group_key; + fwe->loaded = 1; - ret = at76_set_mib(priv, &priv->mib_buf); - if (ret != CMD_STATUS_COMPLETE) - goto exit; + dev_printk(KERN_DEBUG, &udev->dev, + "using firmware %s (version %d.%d.%d-%d)\n", + fwe->fwname, fwh->major, fwh->minor, fwh->patch, fwh->build); - /* second block of settings */ - priv->mib_buf.size = 3; - priv->mib_buf.index = offsetof(struct mib_mac_encryption, - exclude_unencrypted); - priv->mib_buf.data.data[0] = 1; /* exclude_unencrypted */ - priv->mib_buf.data.data[1] = 0; /* wep_encryption_type */ - priv->mib_buf.data.data[2] = 0; /* ckip_key_permutation */ + at76_dbg(DBG_DEVSTART, "board %u, int %d:%d, ext %d:%d", board_type, + le32_to_cpu(fwh->int_fw_offset), le32_to_cpu(fwh->int_fw_len), + le32_to_cpu(fwh->ext_fw_offset), le32_to_cpu(fwh->ext_fw_len)); + at76_dbg(DBG_DEVSTART, "firmware id %s", str); - ret = at76_set_mib(priv, &priv->mib_buf); - if (ret != CMD_STATUS_COMPLETE) - goto exit; - ret = 0; - }; exit: - at76_dump_mib_mac_encryption(priv); - mutex_unlock(&priv->mtx); - return ret; -} - -static int at76_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, - const u8 *local_address, const u8 *address, - struct ieee80211_key_conf *key) -{ - struct at76_priv *priv = hw->priv; - - at76_dbg(DBG_MAC80211, "%s(): cmd %d key->alg %d key->keyidx %d " - "key->keylen %d", - __func__, cmd, key->alg, key->keyidx, key->keylen); + mutex_unlock(&fw_mutex); - if (FIRMWARE_IS_WPA(priv->fw_version)) - return at76_set_key_newfw(hw, cmd, local_address, address, key); + if (fwe->loaded) + return fwe; else - return at76_set_key_oldfw(hw, cmd, local_address, address, key); - + return NULL; } -static const struct ieee80211_ops at76_ops = { - .tx = at76_mac80211_tx, - .add_interface = at76_add_interface, - .remove_interface = at76_remove_interface, - .config = at76_config, - .config_interface = at76_config_interface, - .configure_filter = at76_configure_filter, - .start = at76_mac80211_start, - .stop = at76_mac80211_stop, - .hw_scan = at76_hw_scan, - .set_key = at76_set_key, -}; - /* Allocate network device and initialize private data */ static struct at76_priv *at76_alloc_new_device(struct usb_device *udev) { - struct ieee80211_hw *hw; + struct net_device *netdev; struct at76_priv *priv; + int i; - hw = ieee80211_alloc_hw(sizeof(struct at76_priv), &at76_ops); - if (!hw) { - printk(KERN_ERR DRIVER_NAME ": could not register" - " ieee80211_hw\n"); + /* allocate memory for our device state and initialize it */ + netdev = alloc_etherdev(sizeof(struct at76_priv)); + if (!netdev) { + dev_printk(KERN_ERR, &udev->dev, "out of memory\n"); return NULL; } - priv = hw->priv; - priv->hw = hw; + priv = netdev_priv(netdev); priv->udev = udev; + priv->netdev = netdev; mutex_init(&priv->mtx); + INIT_WORK(&priv->work_assoc_done, at76_work_assoc_done); + INIT_WORK(&priv->work_join, at76_work_join); + INIT_WORK(&priv->work_new_bss, at76_work_new_bss); + INIT_WORK(&priv->work_start_scan, at76_work_start_scan); INIT_WORK(&priv->work_set_promisc, at76_work_set_promisc); INIT_WORK(&priv->work_submit_rx, at76_work_submit_rx); - INIT_DELAYED_WORK(&priv->dwork_hw_scan, at76_dwork_hw_scan); + INIT_DELAYED_WORK(&priv->dwork_restart, at76_dwork_restart); + INIT_DELAYED_WORK(&priv->dwork_get_scan, at76_dwork_get_scan); + INIT_DELAYED_WORK(&priv->dwork_beacon, at76_dwork_beacon); + INIT_DELAYED_WORK(&priv->dwork_auth, at76_dwork_auth); + INIT_DELAYED_WORK(&priv->dwork_assoc, at76_dwork_assoc); + + spin_lock_init(&priv->mgmt_spinlock); + priv->next_mgmt_bulk = NULL; + priv->mac_state = MAC_INIT; + + /* initialize empty BSS list */ + priv->curr_bss = NULL; + INIT_LIST_HEAD(&priv->bss_list); + spin_lock_init(&priv->bss_list_spinlock); + + init_timer(&priv->bss_list_timer); + priv->bss_list_timer.data = (unsigned long)priv; + priv->bss_list_timer.function = at76_bss_list_timeout; + + spin_lock_init(&priv->spy_spinlock); + + /* mark all rx data entries as unused */ + for (i = 0; i < NR_RX_DATA_BUF; i++) + priv->rx_data[i].skb = NULL; priv->rx_tasklet.func = at76_rx_tasklet; priv->rx_tasklet.data = 0; @@ -2371,9 +5197,6 @@ static struct at76_priv *at76_alloc_new_device(struct usb_device *udev) priv->pm_mode = AT76_PM_OFF; priv->pm_period = 0; - /* unit us */ - priv->hw->channel_change_time = 100000; - return priv; } @@ -2436,42 +5259,11 @@ static int at76_alloc_urbs(struct at76_priv *priv, return 0; } -static struct ieee80211_rate at76_rates[] = { - { .bitrate = 10, .hw_value = TX_RATE_1MBIT, }, - { .bitrate = 20, .hw_value = TX_RATE_2MBIT, }, - { .bitrate = 55, .hw_value = TX_RATE_5_5MBIT, }, - { .bitrate = 110, .hw_value = TX_RATE_11MBIT, }, -}; - -static struct ieee80211_channel at76_channels[] = { - { .center_freq = 2412, .hw_value = 1 }, - { .center_freq = 2417, .hw_value = 2 }, - { .center_freq = 2422, .hw_value = 3 }, - { .center_freq = 2427, .hw_value = 4 }, - { .center_freq = 2432, .hw_value = 5 }, - { .center_freq = 2437, .hw_value = 6 }, - { .center_freq = 2442, .hw_value = 7 }, - { .center_freq = 2447, .hw_value = 8 }, - { .center_freq = 2452, .hw_value = 9 }, - { .center_freq = 2457, .hw_value = 10 }, - { .center_freq = 2462, .hw_value = 11 }, - { .center_freq = 2467, .hw_value = 12 }, - { .center_freq = 2472, .hw_value = 13 }, - { .center_freq = 2484, .hw_value = 14 } -}; - -static struct ieee80211_supported_band at76_supported_band = { - .channels = at76_channels, - .n_channels = ARRAY_SIZE(at76_channels), - .bitrates = at76_rates, - .n_bitrates = ARRAY_SIZE(at76_rates), -}; - /* Register network device and initialize the hardware */ static int at76_init_new_device(struct at76_priv *priv, struct usb_interface *interface) { - struct device *dev = &interface->dev; + struct net_device *netdev = priv->netdev; int ret; /* set up the endpoint information */ @@ -2487,11 +5279,14 @@ static int at76_init_new_device(struct at76_priv *priv, /* MAC address */ ret = at76_get_hw_config(priv); if (ret < 0) { - dev_err(dev, "cannot get MAC address\n"); + dev_printk(KERN_ERR, &interface->dev, + "cannot get MAC address\n"); goto exit; } priv->domain = at76_get_reg_domain(priv->regulatory_domain); + /* init. netdev->dev_addr */ + memcpy(netdev->dev_addr, priv->mac_addr, ETH_ALEN); priv->channel = DEF_CHANNEL; priv->iw_mode = IW_MODE_INFRA; @@ -2501,54 +5296,47 @@ static int at76_init_new_device(struct at76_priv *priv, priv->txrate = TX_RATE_AUTO; priv->preamble_type = PREAMBLE_TYPE_LONG; priv->beacon_period = 100; + priv->beacons_last_qual = jiffies; priv->auth_mode = WLAN_AUTH_OPEN; priv->scan_min_time = DEF_SCAN_MIN_TIME; priv->scan_max_time = DEF_SCAN_MAX_TIME; priv->scan_mode = SCAN_TYPE_ACTIVE; - priv->default_pairwise_key = 0xff; - priv->default_group_key = 0xff; - - /* mac80211 initialisation */ - priv->hw->wiphy->bands[IEEE80211_BAND_2GHZ] = &at76_supported_band; - if (FIRMWARE_IS_WPA(priv->fw_version) && - (at76_is_503rfmd(priv->board_type) || - at76_is_505(priv->board_type))) - priv->hw->flags = IEEE80211_HW_SIGNAL_UNSPEC; - else - priv->hw->flags = IEEE80211_HW_RX_INCLUDES_FCS | - IEEE80211_HW_SIGNAL_UNSPEC; - - priv->hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION); - - SET_IEEE80211_DEV(priv->hw, &interface->dev); - SET_IEEE80211_PERM_ADDR(priv->hw, priv->mac_addr); - - ret = ieee80211_register_hw(priv->hw); + netdev->flags &= ~IFF_MULTICAST; /* not yet or never */ + netdev->open = at76_open; + netdev->stop = at76_stop; + netdev->get_stats = at76_get_stats; + netdev->ethtool_ops = &at76_ethtool_ops; + + /* Add pointers to enable iwspy support. */ + priv->wireless_data.spy_data = &priv->spy_data; + netdev->wireless_data = &priv->wireless_data; + + netdev->hard_start_xmit = at76_tx; + netdev->tx_timeout = at76_tx_timeout; + netdev->watchdog_timeo = 2 * HZ; + netdev->wireless_handlers = &at76_handler_def; + netdev->set_multicast_list = at76_set_multicast; + netdev->set_mac_address = at76_set_mac_address; + dev_alloc_name(netdev, "wlan%d"); + + ret = register_netdev(priv->netdev); if (ret) { - dev_err(dev, "cannot register mac80211 hw (status %d)!\n", ret); + dev_printk(KERN_ERR, &interface->dev, + "cannot register netdevice (status %d)!\n", ret); goto exit; } + priv->netdev_registered = 1; - priv->mac80211_registered = 1; + printk(KERN_INFO "%s: USB %s, MAC %s, firmware %d.%d.%d-%d\n", + netdev->name, dev_name(&interface->dev), mac2str(priv->mac_addr), + priv->fw_version.major, priv->fw_version.minor, + priv->fw_version.patch, priv->fw_version.build); + printk(KERN_INFO "%s: regulatory domain 0x%02x: %s\n", netdev->name, + priv->regulatory_domain, priv->domain->name); - dev_info(dev, "%s: USB %s, MAC %s, firmware %d.%d.%d-%d\n", - wiphy_name(priv->hw->wiphy), - dev_name(&interface->dev), mac2str(priv->mac_addr), - priv->fw_version.major, priv->fw_version.minor, - priv->fw_version.patch, priv->fw_version.build); - dev_info(dev, "%s: regulatory domain 0x%02x: %s\n", - wiphy_name(priv->hw->wiphy), - priv->regulatory_domain, priv->domain->name); - dev_info(dev, "%s: WPA support: ", wiphy_name(priv->hw->wiphy)); - if (!FIRMWARE_IS_WPA(priv->fw_version)) - printk("none\n"); - else { - if (!at76_is_505a(priv->board_type)) - printk("TKIP\n"); - else - printk("TKIP, AES/CCMP\n"); - }; + /* we let this timer run the whole time this driver instance lives */ + mod_timer(&priv->bss_list_timer, jiffies + BSS_LIST_TIMEOUT); exit: return ret; @@ -2556,13 +5344,15 @@ exit: static void at76_delete_device(struct at76_priv *priv) { + int i; + at76_dbg(DBG_PROC_ENTRY, "%s: ENTER", __func__); /* The device is gone, don't bother turning it off */ priv->device_unplugged = 1; - if (priv->mac80211_registered) - ieee80211_unregister_hw(priv->hw); + if (priv->netdev_registered) + unregister_netdev(priv->netdev); /* assuming we used keventd, it must quiesce too */ flush_scheduled_work(); @@ -2583,11 +5373,25 @@ static void at76_delete_device(struct at76_priv *priv) if (priv->rx_skb) kfree_skb(priv->rx_skb); + at76_free_bss_list(priv); + del_timer_sync(&priv->bss_list_timer); + cancel_delayed_work(&priv->dwork_get_scan); + cancel_delayed_work(&priv->dwork_beacon); + cancel_delayed_work(&priv->dwork_auth); + cancel_delayed_work(&priv->dwork_assoc); + + if (priv->mac_state == MAC_CONNECTED) + at76_iwevent_bss_disconnect(priv->netdev); + + for (i = 0; i < NR_RX_DATA_BUF; i++) + if (priv->rx_data[i].skb) { + dev_kfree_skb(priv->rx_data[i].skb); + priv->rx_data[i].skb = NULL; + } usb_put_dev(priv->udev); - at76_dbg(DBG_PROC_ENTRY, "%s: before freeing priv/ieee80211_hw", - __func__); - ieee80211_free_hw(priv->hw); + at76_dbg(DBG_PROC_ENTRY, "%s: before freeing priv/netdev", __func__); + free_netdev(priv->netdev); /* priv is in netdev */ at76_dbg(DBG_PROC_ENTRY, "%s: EXIT", __func__); } @@ -2621,8 +5425,8 @@ static int at76_probe(struct usb_interface *interface, we get 204 with 2.4.23, Fiberline FL-WL240u (505A+RFMD2958) ??? */ if (op_mode == OPMODE_HW_CONFIG_MODE) { - dev_err(&interface->dev, - "cannot handle a device in HW_CONFIG_MODE\n"); + dev_printk(KERN_ERR, &interface->dev, + "cannot handle a device in HW_CONFIG_MODE\n"); ret = -EBUSY; goto error; } @@ -2630,12 +5434,13 @@ static int at76_probe(struct usb_interface *interface, if (op_mode != OPMODE_NORMAL_NIC_WITH_FLASH && op_mode != OPMODE_NORMAL_NIC_WITHOUT_FLASH) { /* download internal firmware part */ - dev_dbg(&interface->dev, "downloading internal firmware\n"); + dev_printk(KERN_DEBUG, &interface->dev, + "downloading internal firmware\n"); ret = at76_load_internal_fw(udev, fwe); if (ret < 0) { - dev_err(&interface->dev, - "error %d downloading internal firmware\n", - ret); + dev_printk(KERN_ERR, &interface->dev, + "error %d downloading internal firmware\n", + ret); goto error; } usb_put_dev(udev); @@ -2660,7 +5465,8 @@ static int at76_probe(struct usb_interface *interface, need_ext_fw = 1; if (need_ext_fw) { - dev_dbg(&interface->dev, "downloading external firmware\n"); + dev_printk(KERN_DEBUG, &interface->dev, + "downloading external firmware\n"); ret = at76_load_external_fw(udev, fwe); if (ret) @@ -2669,8 +5475,8 @@ static int at76_probe(struct usb_interface *interface, /* Re-check firmware version */ ret = at76_get_mib(udev, MIB_FW_VERSION, &fwv, sizeof(fwv)); if (ret < 0) { - dev_err(&interface->dev, - "error %d getting firmware version\n", ret); + dev_printk(KERN_ERR, &interface->dev, + "error %d getting firmware version\n", ret); goto error; } } @@ -2681,6 +5487,7 @@ static int at76_probe(struct usb_interface *interface, goto error; } + SET_NETDEV_DEV(priv->netdev, &interface->dev); usb_set_intfdata(interface, priv); memcpy(&priv->fw_version, &fwv, sizeof(struct mib_fw_version)); @@ -2708,7 +5515,7 @@ static void at76_disconnect(struct usb_interface *interface) if (!priv) return; - printk(KERN_INFO "%s: disconnecting\n", wiphy_name(priv->hw->wiphy)); + printk(KERN_INFO "%s: disconnecting\n", priv->netdev->name); at76_delete_device(priv); dev_printk(KERN_INFO, &interface->dev, "disconnected\n"); } @@ -2764,8 +5571,5 @@ MODULE_AUTHOR("Alex <alex@foogod.com>"); MODULE_AUTHOR("Nick Jones"); MODULE_AUTHOR("Balint Seeber <n0_5p4m_p13453@hotmail.com>"); MODULE_AUTHOR("Pavel Roskin <proski@gnu.org>"); -MODULE_AUTHOR("Guido Guenther <agx@sigxcpu.org>"); -MODULE_AUTHOR("Kalle Valo <kalle.valo@iki.fi>"); -MODULE_AUTHOR("Milan Plzik <milan.plzik@gmail.com>"); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); diff --git a/drivers/staging/at76_usb/at76_usb.h b/drivers/staging/at76_usb/at76_usb.h index 8bb352f16d4..b20be9da1fa 100644 --- a/drivers/staging/at76_usb/at76_usb.h +++ b/drivers/staging/at76_usb/at76_usb.h @@ -34,6 +34,23 @@ enum board_type { BOARD_505AMX = 8 }; +/* our private ioctl's */ +/* preamble length (0 - long, 1 - short, 2 - auto) */ +#define AT76_SET_SHORT_PREAMBLE (SIOCIWFIRSTPRIV + 0) +#define AT76_GET_SHORT_PREAMBLE (SIOCIWFIRSTPRIV + 1) +/* which debug channels are enabled */ +#define AT76_SET_DEBUG (SIOCIWFIRSTPRIV + 2) +#define AT76_GET_DEBUG (SIOCIWFIRSTPRIV + 3) +/* power save mode (incl. the Atmel proprietary smart save mode) */ +#define AT76_SET_POWERSAVE_MODE (SIOCIWFIRSTPRIV + 4) +#define AT76_GET_POWERSAVE_MODE (SIOCIWFIRSTPRIV + 5) +/* min and max channel times for scan */ +#define AT76_SET_SCAN_TIMES (SIOCIWFIRSTPRIV + 6) +#define AT76_GET_SCAN_TIMES (SIOCIWFIRSTPRIV + 7) +/* scan mode (0 - active, 1 - passive) */ +#define AT76_SET_SCAN_MODE (SIOCIWFIRSTPRIV + 8) +#define AT76_GET_SCAN_MODE (SIOCIWFIRSTPRIV + 9) + #define CMD_STATUS_IDLE 0x00 #define CMD_STATUS_COMPLETE 0x01 #define CMD_STATUS_UNKNOWN 0x02 @@ -65,7 +82,6 @@ enum board_type { #define MIB_MAC 0x03 #define MIB_MAC_MGMT 0x05 #define MIB_MAC_WEP 0x06 -#define MIB_MAC_ENCRYPTION 0x06 #define MIB_PHY 0x07 #define MIB_FW_VERSION 0x08 #define MIB_MDOMAIN 0x09 @@ -90,26 +106,6 @@ enum board_type { #define AT76_PM_ON 2 #define AT76_PM_SMART 3 -/* cipher values for encryption keys */ -#define CIPHER_NONE 0 /* this value is only guessed */ -#define CIPHER_WEP64 1 -#define CIPHER_TKIP 2 -#define CIPHER_CCMP 3 -#define CIPHER_CCX 4 /* for consistency sake only */ -#define CIPHER_WEP128 5 - -/* bit flags key types for encryption keys */ -#define KEY_PAIRWISE 2 -#define KEY_TX 4 - -#define CIPHER_KEYS (4) -#define CIPHER_KEY_LEN (40) - -struct key_config { - u8 cipher; - u8 keylen; -}; - struct hwcfg_r505 { u8 cr39_values[14]; u8 reserved1[14]; @@ -151,9 +147,6 @@ union at76_hwcfg { #define WEP_SMALL_KEY_LEN (40 / 8) #define WEP_LARGE_KEY_LEN (104 / 8) -#define WEP_KEYS (4) - - struct at76_card_config { u8 exclude_unencrypted; @@ -168,7 +161,7 @@ struct at76_card_config { u8 privacy_invoked; u8 wep_default_key_id; /* 0..3 */ u8 current_ssid[32]; - u8 wep_default_key_value[4][WEP_LARGE_KEY_LEN]; + u8 wep_default_key_value[4][WEP_KEY_LEN]; u8 ssid_len; u8 short_preamble; __le16 beacon_period; @@ -193,7 +186,7 @@ struct at76_rx_buffer { u8 link_quality; u8 noise_level; __le32 rx_time; - u8 packet[IEEE80211_MAX_FRAG_THRESHOLD]; + u8 packet[IEEE80211_FRAME_LEN + IEEE80211_FCS_LEN]; } __attribute__((packed)); /* Length of Atmel-specific Tx header before 802.11 frame */ @@ -203,11 +196,8 @@ struct at76_tx_buffer { __le16 wlength; u8 tx_rate; u8 padding; - u8 key_id; - u8 cipher_type; - u8 cipher_length; - u8 reserved; - u8 packet[IEEE80211_MAX_FRAG_THRESHOLD]; + u8 reserved[4]; + u8 packet[IEEE80211_FRAME_LEN + IEEE80211_FCS_LEN]; } __attribute__((packed)); /* defines for scan_type below */ @@ -254,7 +244,6 @@ struct set_mib_buffer { u8 byte; __le16 word; u8 addr[ETH_ALEN]; - u8 data[256]; /* we need more space for mib_mac_encryption */ } data; } __attribute__((packed)); @@ -328,24 +317,10 @@ struct mib_mac_wep { u8 exclude_unencrypted; __le32 wep_icv_error_count; __le32 wep_excluded_count; - u8 wep_default_keyvalue[WEP_KEYS][WEP_LARGE_KEY_LEN]; + u8 wep_default_keyvalue[WEP_KEYS][WEP_KEY_LEN]; u8 encryption_level; /* 1 for 40bit, 2 for 104bit encryption */ } __attribute__((packed)); -struct mib_mac_encryption { - u8 cipher_default_keyvalue[CIPHER_KEYS][CIPHER_KEY_LEN]; - u8 tkip_bssid[6]; - u8 privacy_invoked; - u8 cipher_default_key_id; - u8 cipher_default_group_key_id; - u8 exclude_unencrypted; - u8 wep_encryption_type; - u8 ckip_key_permutation; /* bool */ - __le32 wep_icv_error_count; - __le32 wep_excluded_count; - u8 key_rsc[CIPHER_KEYS][8]; -} __attribute__((packed)); - struct mib_phy { __le32 ed_threshold; @@ -389,6 +364,16 @@ struct at76_fw_header { __le32 ext_fw_len; /* external firmware image length */ } __attribute__((packed)); +enum mac_state { + MAC_INIT, + MAC_SCANNING, + MAC_AUTH, + MAC_ASSOC, + MAC_JOINING, + MAC_CONNECTED, + MAC_OWN_IBSS +}; + /* a description of a regulatory domain and the allowed channels */ struct reg_domain { u16 code; @@ -396,6 +381,47 @@ struct reg_domain { u32 channel_map; /* if bit N is set, channel (N+1) is allowed */ }; +/* how long do we keep a (I)BSS in the bss_list in jiffies + this should be long enough for the user to retrieve the table + (by iwlist ?) after the device started, because all entries from + other channels than the one the device locks on get removed, too */ +#define BSS_LIST_TIMEOUT (120 * HZ) +/* struct to store BSS info found during scan */ +#define BSS_LIST_MAX_RATE_LEN 32 /* 32 rates should be enough ... */ + +struct bss_info { + struct list_head list; + + u8 bssid[ETH_ALEN]; /* bssid */ + u8 ssid[IW_ESSID_MAX_SIZE]; /* essid */ + u8 ssid_len; /* length of ssid above */ + u8 channel; + u16 capa; /* BSS capabilities */ + u16 beacon_interval; /* beacon interval, Kus (1024 microseconds) */ + u8 rates[BSS_LIST_MAX_RATE_LEN]; /* supported rates in units of + 500 kbps, ORed with 0x80 for + basic rates */ + u8 rates_len; + + /* quality of received beacon */ + u8 rssi; + u8 link_qual; + u8 noise_level; + + unsigned long last_rx; /* time (jiffies) of last beacon received */ +}; + +/* a rx data buffer to collect rx fragments */ +struct rx_data_buf { + u8 sender[ETH_ALEN]; /* sender address */ + u16 seqnr; /* sequence number */ + u16 fragnr; /* last fragment received */ + unsigned long last_rx; /* jiffies of last rx */ + struct sk_buff *skb; /* == NULL if entry is free */ +}; + +#define NR_RX_DATA_BUF 8 + /* Data for one loaded firmware file */ struct fwentry { const char *const fwname; @@ -412,9 +438,11 @@ struct fwentry { struct at76_priv { struct usb_device *udev; /* USB device pointer */ + struct net_device *netdev; /* net device pointer */ + struct net_device_stats stats; /* net device stats */ + struct iw_statistics wstats; /* wireless stats */ struct sk_buff *rx_skb; /* skbuff for receiving data */ - struct sk_buff *tx_skb; /* skbuff for transmitting data */ void *bulk_out_buffer; /* buffer for sending data */ struct urb *tx_urb; /* URB for sending data */ @@ -426,17 +454,26 @@ struct at76_priv { struct mutex mtx; /* locks this structure */ /* work queues */ + struct work_struct work_assoc_done; + struct work_struct work_join; + struct work_struct work_new_bss; + struct work_struct work_start_scan; struct work_struct work_set_promisc; struct work_struct work_submit_rx; - struct delayed_work dwork_hw_scan; + struct delayed_work dwork_restart; + struct delayed_work dwork_get_scan; + struct delayed_work dwork_beacon; + struct delayed_work dwork_auth; + struct delayed_work dwork_assoc; struct tasklet_struct rx_tasklet; /* the WEP stuff */ int wep_enabled; /* 1 if WEP is enabled */ int wep_key_id; /* key id to be used */ - u8 wep_keys[WEP_KEYS][WEP_LARGE_KEY_LEN]; /* WEP keys */ - u8 wep_keys_len[WEP_KEYS]; /* length of WEP keys */ + u8 wep_keys[WEP_KEYS][WEP_KEY_LEN]; /* the four WEP keys, + 5 or 13 bytes are used */ + u8 wep_keys_len[WEP_KEYS]; /* the length of the above keys */ int channel; int iw_mode; @@ -458,13 +495,44 @@ struct at76_priv { int scan_mode; /* SCAN_TYPE_ACTIVE, SCAN_TYPE_PASSIVE */ int scan_need_any; /* if set, need to scan for any ESSID */ + /* the list we got from scanning */ + spinlock_t bss_list_spinlock; /* protects bss_list operations */ + struct list_head bss_list; /* list of BSS we got beacons from */ + struct timer_list bss_list_timer; /* timer to purge old entries + from bss_list */ + struct bss_info *curr_bss; /* current BSS */ u16 assoc_id; /* current association ID, if associated */ + u8 wanted_bssid[ETH_ALEN]; + int wanted_bssid_valid; /* != 0 if wanted_bssid is to be used */ + + /* some data for infrastructure mode only */ + spinlock_t mgmt_spinlock; /* this spinlock protects access to + next_mgmt_bulk */ + + struct at76_tx_buffer *next_mgmt_bulk; /* pending management msg to + send via bulk out */ + enum mac_state mac_state; + enum { + SCAN_IDLE, + SCAN_IN_PROGRESS, + SCAN_COMPLETED + } scan_state; + time_t last_scan; + + int retries; /* remaining retries in case of timeout when + * sending AuthReq or AssocReq */ u8 pm_mode; /* power management mode */ u32 pm_period; /* power management period in microseconds */ struct reg_domain const *domain; /* reg domain description */ + /* iwspy support */ + spinlock_t spy_spinlock; + struct iw_spy_data spy_data; + + struct iw_public_data wireless_data; + /* These fields contain HW config provided by the device (not all of * these fields are used by all board types) */ u8 mac_addr[ETH_ALEN]; @@ -472,6 +540,9 @@ struct at76_priv { struct at76_card_config card_config; + /* store rx fragments until complete */ + struct rx_data_buf rx_data[NR_RX_DATA_BUF]; + enum board_type board_type; struct mib_fw_version fw_version; @@ -479,20 +550,58 @@ struct at76_priv { unsigned int netdev_registered:1; struct set_mib_buffer mib_buf; /* global buffer for set_mib calls */ + /* beacon counting */ int beacon_period; /* period of mgmt beacons, Kus */ + int beacons_received; + unsigned long beacons_last_qual; /* time we restarted counting + beacons */ +}; - struct ieee80211_hw *hw; - int mac80211_registered; - - struct key_config keys[4]; /* installed key types */ - u8 default_pairwise_key; - u8 default_group_key; +struct at76_rx_radiotap { + struct ieee80211_radiotap_header rt_hdr; + __le64 rt_tsft; + u8 rt_flags; + u8 rt_rate; + s8 rt_signal; + s8 rt_noise; }; -#define AT76_SUPPORTED_FILTERS FIF_PROMISC_IN_BSS +#define AT76_RX_RADIOTAP_PRESENT \ + ((1 << IEEE80211_RADIOTAP_TSFT) | \ + (1 << IEEE80211_RADIOTAP_FLAGS) | \ + (1 << IEEE80211_RADIOTAP_RATE) | \ + (1 << IEEE80211_RADIOTAP_DB_ANTSIGNAL) | \ + (1 << IEEE80211_RADIOTAP_DB_ANTNOISE)) + +#define BEACON_MAX_DATA_LENGTH 1500 + +/* the maximum size of an AssocReq packet */ +#define ASSOCREQ_MAX_SIZE \ + (AT76_TX_HDRLEN + sizeof(struct ieee80211_assoc_request) + \ + 1 + 1 + IW_ESSID_MAX_SIZE + 1 + 1 + 4) + +/* for shared secret auth, add the challenge text size */ +#define AUTH_FRAME_SIZE (AT76_TX_HDRLEN + sizeof(struct ieee80211_auth)) + +/* Maximal number of AuthReq retries */ +#define AUTH_RETRIES 3 +/* Maximal number of AssocReq retries */ +#define ASSOC_RETRIES 3 + +/* Beacon timeout in managed mode when we are connected */ +#define BEACON_TIMEOUT (10 * HZ) + +/* Timeout for authentication response */ +#define AUTH_TIMEOUT (1 * HZ) + +/* Timeout for association response */ +#define ASSOC_TIMEOUT (1 * HZ) + +/* Polling interval when scan is running */ #define SCAN_POLL_INTERVAL (HZ / 4) +/* Command completion timeout */ #define CMD_COMPLETION_TIMEOUT (5 * HZ) #define DEF_RTS_THRESHOLD 1536 @@ -502,6 +611,8 @@ struct at76_priv { #define DEF_SCAN_MIN_TIME 10 #define DEF_SCAN_MAX_TIME 120 +#define MAX_RTS_THRESHOLD (MAX_FRAG_THRESHOLD + 1) + /* the max padding size for tx in bytes (see calc_padding) */ #define MAX_PADDING_SIZE 53 diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c index 5ffe269c238..ab69c1bf36a 100644 --- a/drivers/staging/panel/panel.c +++ b/drivers/staging/panel/panel.c @@ -622,7 +622,7 @@ static int set_ctrl_bits(void) } /* sets ctrl & data port bits according to current signals values */ -static void set_bits(void) +static void panel_set_bits(void) { set_data_bits(); set_ctrl_bits(); @@ -707,12 +707,12 @@ static void lcd_send_serial(int byte) */ for (bit = 0; bit < 8; bit++) { bits.cl = BIT_CLR; /* CLK low */ - set_bits(); + panel_set_bits(); bits.da = byte & 1; - set_bits(); + panel_set_bits(); udelay(2); /* maintain the data during 2 us before CLK up */ bits.cl = BIT_SET; /* CLK high */ - set_bits(); + panel_set_bits(); udelay(1); /* maintain the strobe during 1 us */ byte >>= 1; } @@ -727,7 +727,7 @@ static void lcd_backlight(int on) /* The backlight is activated by seting the AUTOFEED line to +5V */ spin_lock(&pprt_lock); bits.bl = on; - set_bits(); + panel_set_bits(); spin_unlock(&pprt_lock); } diff --git a/drivers/usb/Makefile b/drivers/usb/Makefile index 8bcde8cde55..b2ceb4aff23 100644 --- a/drivers/usb/Makefile +++ b/drivers/usb/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_USB_MON) += mon/ obj-$(CONFIG_PCI) += host/ obj-$(CONFIG_USB_EHCI_HCD) += host/ obj-$(CONFIG_USB_ISP116X_HCD) += host/ +obj-$(CONFIG_USB_ISP1760_HCD) += host/ obj-$(CONFIG_USB_OHCI_HCD) += host/ obj-$(CONFIG_USB_UHCI_HCD) += host/ obj-$(CONFIG_USB_FHCI_HCD) += host/ diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 97ba4a985ed..326dd7f65ee 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1349,9 +1349,6 @@ static struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, - { USB_DEVICE(0x0e8d, 0x3329), /* i-blue 747, Qstarz BT-Q1000, Holux M-241 */ - .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ - }, { USB_DEVICE(0x0e8d, 0x3329), /* MediaTek Inc GPS */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, diff --git a/drivers/usb/gadget/fsl_qe_udc.c b/drivers/usb/gadget/fsl_qe_udc.c index d6c5bcd4006..d701bf4698d 100644 --- a/drivers/usb/gadget/fsl_qe_udc.c +++ b/drivers/usb/gadget/fsl_qe_udc.c @@ -1622,6 +1622,8 @@ static int qe_ep_disable(struct usb_ep *_ep) nuke(ep, -ESHUTDOWN); ep->desc = NULL; ep->stopped = 1; + ep->tx_req = NULL; + qe_ep_reset(udc, ep->epnum); spin_unlock_irqrestore(&udc->lock, flags); cpm_muram_free(cpm_muram_offset(ep->rxbase)); @@ -1681,14 +1683,11 @@ static void qe_free_request(struct usb_ep *_ep, struct usb_request *_req) kfree(req); } -/* queues (submits) an I/O request to an endpoint */ -static int qe_ep_queue(struct usb_ep *_ep, struct usb_request *_req, - gfp_t gfp_flags) +static int __qe_ep_queue(struct usb_ep *_ep, struct usb_request *_req) { struct qe_ep *ep = container_of(_ep, struct qe_ep, ep); struct qe_req *req = container_of(_req, struct qe_req, req); struct qe_udc *udc; - unsigned long flags; int reval; udc = ep->udc; @@ -1732,7 +1731,7 @@ static int qe_ep_queue(struct usb_ep *_ep, struct usb_request *_req, list_add_tail(&req->queue, &ep->queue); dev_vdbg(udc->dev, "gadget have request in %s! %d\n", ep->name, req->req.length); - spin_lock_irqsave(&udc->lock, flags); + /* push the request to device */ if (ep_is_in(ep)) reval = ep_req_send(ep, req); @@ -1748,11 +1747,24 @@ static int qe_ep_queue(struct usb_ep *_ep, struct usb_request *_req, if (ep->dir == USB_DIR_OUT) reval = ep_req_receive(ep, req); - spin_unlock_irqrestore(&udc->lock, flags); - return 0; } +/* queues (submits) an I/O request to an endpoint */ +static int qe_ep_queue(struct usb_ep *_ep, struct usb_request *_req, + gfp_t gfp_flags) +{ + struct qe_ep *ep = container_of(_ep, struct qe_ep, ep); + struct qe_udc *udc = ep->udc; + unsigned long flags; + int ret; + + spin_lock_irqsave(&udc->lock, flags); + ret = __qe_ep_queue(_ep, _req); + spin_unlock_irqrestore(&udc->lock, flags); + return ret; +} + /* dequeues (cancels, unlinks) an I/O request from an endpoint */ static int qe_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req) { @@ -2008,7 +2020,7 @@ static void ch9getstatus(struct qe_udc *udc, u8 request_type, u16 value, udc->ep0_dir = USB_DIR_IN; /* data phase */ - status = qe_ep_queue(&ep->ep, &req->req, GFP_ATOMIC); + status = __qe_ep_queue(&ep->ep, &req->req); if (status == 0) return; @@ -2151,6 +2163,9 @@ static int reset_irq(struct qe_udc *udc) { unsigned char i; + if (udc->usb_state == USB_STATE_DEFAULT) + return 0; + qe_usb_disable(); out_8(&udc->usb_regs->usb_usadr, 0); @@ -2442,8 +2457,12 @@ static int __devinit qe_udc_reg_init(struct qe_udc *udc) struct usb_ctlr __iomem *qe_usbregs; qe_usbregs = udc->usb_regs; - /* Init the usb register */ + /* Spec says that we must enable the USB controller to change mode. */ out_8(&qe_usbregs->usb_usmod, 0x01); + /* Mode changed, now disable it, since muram isn't initialized yet. */ + out_8(&qe_usbregs->usb_usmod, 0x00); + + /* Initialize the rest. */ out_be16(&qe_usbregs->usb_usbmr, 0); out_8(&qe_usbregs->usb_uscom, 0); out_be16(&qe_usbregs->usb_usber, USBER_ALL_CLEAR); @@ -2604,6 +2623,10 @@ static int __devinit qe_udc_probe(struct of_device *ofdev, (unsigned long)udc_controller); /* request irq and disable DR */ udc_controller->usb_irq = irq_of_parse_and_map(np, 0); + if (!udc_controller->usb_irq) { + ret = -EINVAL; + goto err_noirq; + } ret = request_irq(udc_controller->usb_irq, qe_udc_irq, 0, driver_name, udc_controller); @@ -2625,6 +2648,8 @@ static int __devinit qe_udc_probe(struct of_device *ofdev, err6: free_irq(udc_controller->usb_irq, udc_controller); err5: + irq_dispose_mapping(udc_controller->usb_irq); +err_noirq: if (udc_controller->nullmap) { dma_unmap_single(udc_controller->gadget.dev.parent, udc_controller->nullp, 256, @@ -2648,7 +2673,7 @@ err2: iounmap(udc_controller->usb_regs); err1: kfree(udc_controller); - + udc_controller = NULL; return ret; } @@ -2710,6 +2735,7 @@ static int __devexit qe_udc_remove(struct of_device *ofdev) kfree(ep->txframe); free_irq(udc_controller->usb_irq, udc_controller); + irq_dispose_mapping(udc_controller->usb_irq); tasklet_kill(&udc_controller->rx_tasklet); diff --git a/drivers/usb/serial/aircable.c b/drivers/usb/serial/aircable.c index 537f953bd7f..6d106e74265 100644 --- a/drivers/usb/serial/aircable.c +++ b/drivers/usb/serial/aircable.c @@ -621,9 +621,9 @@ static int __init aircable_init(void) goto failed_usb_register; return 0; -failed_serial_register: - usb_serial_deregister(&aircable_device); failed_usb_register: + usb_serial_deregister(&aircable_device); +failed_serial_register: return retval; } diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 75597337583..f92f4d77337 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -662,6 +662,7 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(FTDI_VID, FTDI_DOMINTELL_DUSB_PID) }, { USB_DEVICE(ALTI2_VID, ALTI2_N3_PID) }, { USB_DEVICE(FTDI_VID, DIEBOLD_BCS_SE923_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_NDI_HUC_PID) }, { }, /* Optional parameter entry */ { } /* Terminating entry */ }; @@ -1064,8 +1065,10 @@ static int set_serial_info(struct tty_struct *tty, if (!capable(CAP_SYS_ADMIN)) { if (((new_serial.flags & ~ASYNC_USR_MASK) != - (priv->flags & ~ASYNC_USR_MASK))) + (priv->flags & ~ASYNC_USR_MASK))) { + unlock_kernel(); return -EPERM; + } priv->flags = ((priv->flags & ~ASYNC_USR_MASK) | (new_serial.flags & ASYNC_USR_MASK)); priv->custom_divisor = new_serial.custom_divisor; diff --git a/drivers/usb/serial/ftdi_sio.h b/drivers/usb/serial/ftdi_sio.h index 1b62eff475d..e300c840f8c 100644 --- a/drivers/usb/serial/ftdi_sio.h +++ b/drivers/usb/serial/ftdi_sio.h @@ -844,6 +844,9 @@ #define TML_VID 0x1B91 /* Vendor ID */ #define TML_USB_SERIAL_PID 0x0064 /* USB - Serial Converter */ +/* NDI Polaris System */ +#define FTDI_NDI_HUC_PID 0xDA70 + /* Propox devices */ #define FTDI_PROPOX_JTAGCABLEII_PID 0xD738 diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 6c89da9c6fe..bfd0b68cecc 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -199,14 +199,15 @@ static int option_send_setup(struct tty_struct *tty, struct usb_serial_port *po #define NOVATELWIRELESS_PRODUCT_MC950D 0x4400 /* FUTURE NOVATEL PRODUCTS */ -#define NOVATELWIRELESS_PRODUCT_EVDO_1 0x6000 -#define NOVATELWIRELESS_PRODUCT_HSPA_1 0x7000 -#define NOVATELWIRELESS_PRODUCT_EMBEDDED_1 0x8000 -#define NOVATELWIRELESS_PRODUCT_GLOBAL_1 0x9000 -#define NOVATELWIRELESS_PRODUCT_EVDO_2 0x6001 -#define NOVATELWIRELESS_PRODUCT_HSPA_2 0x7001 -#define NOVATELWIRELESS_PRODUCT_EMBEDDED_2 0x8001 -#define NOVATELWIRELESS_PRODUCT_GLOBAL_2 0x9001 +#define NOVATELWIRELESS_PRODUCT_EVDO_FULLSPEED 0X6000 +#define NOVATELWIRELESS_PRODUCT_EVDO_HIGHSPEED 0X6001 +#define NOVATELWIRELESS_PRODUCT_HSPA_FULLSPEED 0X7000 +#define NOVATELWIRELESS_PRODUCT_HSPA_HIGHSPEED 0X7001 +#define NOVATELWIRELESS_PRODUCT_EVDO_EMBEDDED_FULLSPEED 0X8000 +#define NOVATELWIRELESS_PRODUCT_EVDO_EMBEDDED_HIGHSPEED 0X8001 +#define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_FULLSPEED 0X9000 +#define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED 0X9001 +#define NOVATELWIRELESS_PRODUCT_GLOBAL 0XA001 /* AMOI PRODUCTS */ #define AMOI_VENDOR_ID 0x1614 @@ -216,6 +217,27 @@ static int option_send_setup(struct tty_struct *tty, struct usb_serial_port *po #define DELL_VENDOR_ID 0x413C +/* Dell modems */ +#define DELL_PRODUCT_5700_MINICARD 0x8114 +#define DELL_PRODUCT_5500_MINICARD 0x8115 +#define DELL_PRODUCT_5505_MINICARD 0x8116 +#define DELL_PRODUCT_5700_EXPRESSCARD 0x8117 +#define DELL_PRODUCT_5510_EXPRESSCARD 0x8118 + +#define DELL_PRODUCT_5700_MINICARD_SPRINT 0x8128 +#define DELL_PRODUCT_5700_MINICARD_TELUS 0x8129 + +#define DELL_PRODUCT_5720_MINICARD_VZW 0x8133 +#define DELL_PRODUCT_5720_MINICARD_SPRINT 0x8134 +#define DELL_PRODUCT_5720_MINICARD_TELUS 0x8135 +#define DELL_PRODUCT_5520_MINICARD_CINGULAR 0x8136 +#define DELL_PRODUCT_5520_MINICARD_GENERIC_L 0x8137 +#define DELL_PRODUCT_5520_MINICARD_GENERIC_I 0x8138 + +#define DELL_PRODUCT_5730_MINICARD_SPRINT 0x8180 +#define DELL_PRODUCT_5730_MINICARD_TELUS 0x8181 +#define DELL_PRODUCT_5730_MINICARD_VZW 0x8182 + #define KYOCERA_VENDOR_ID 0x0c88 #define KYOCERA_PRODUCT_KPC650 0x17da #define KYOCERA_PRODUCT_KPC680 0x180a @@ -274,12 +296,6 @@ static int option_send_setup(struct tty_struct *tty, struct usb_serial_port *po #define ERICSSON_VENDOR_ID 0x0bdb #define ERICSSON_PRODUCT_F3507G 0x1900 -/* Pantech products */ -#define PANTECH_VENDOR_ID 0x106c -#define PANTECH_PRODUCT_PC5740 0x3701 -#define PANTECH_PRODUCT_PC5750 0x3702 /* PX-500 */ -#define PANTECH_PRODUCT_UM150 0x3711 - static struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -395,31 +411,37 @@ static struct usb_device_id option_ids[] = { { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EU870D) }, /* Novatel EU850D/EU860D/EU870D */ { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC950D) }, /* Novatel MC930D/MC950D */ { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC727) }, /* Novatel MC727/U727/USB727 */ - { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EVDO_1) }, /* Novatel EVDO product */ - { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_HSPA_1) }, /* Novatel HSPA product */ - { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EMBEDDED_1) }, /* Novatel Embedded product */ - { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_GLOBAL_1) }, /* Novatel Global product */ - { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EVDO_2) }, /* Novatel EVDO product */ - { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_HSPA_2) }, /* Novatel HSPA product */ - { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EMBEDDED_2) }, /* Novatel Embedded product */ - { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_GLOBAL_2) }, /* Novatel Global product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EVDO_FULLSPEED) }, /* Novatel EVDO product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_HSPA_FULLSPEED) }, /* Novatel HSPA product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EVDO_EMBEDDED_FULLSPEED) }, /* Novatel EVDO Embedded product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_FULLSPEED) }, /* Novatel HSPA Embedded product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EVDO_HIGHSPEED) }, /* Novatel EVDO product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_HSPA_HIGHSPEED) }, /* Novatel HSPA product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EVDO_EMBEDDED_HIGHSPEED) }, /* Novatel EVDO Embedded product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED) }, /* Novatel HSPA Embedded product */ + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_GLOBAL) }, /* Novatel Global product */ { USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01) }, { USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01A) }, { USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H02) }, - { USB_DEVICE(DELL_VENDOR_ID, 0x8114) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO Mini-Card == Novatel Expedite EV620 CDMA/EV-DO */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8115) }, /* Dell Wireless 5500 Mobile Broadband HSDPA Mini-Card == Novatel Expedite EU740 HSDPA/3G */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8116) }, /* Dell Wireless 5505 Mobile Broadband HSDPA Mini-Card == Novatel Expedite EU740 HSDPA/3G */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8117) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO ExpressCard == Novatel Merlin XV620 CDMA/EV-DO */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8118) }, /* Dell Wireless 5510 Mobile Broadband HSDPA ExpressCard == Novatel Merlin XU870 HSDPA/3G */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8128) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO Mini-Card == Novatel Expedite E720 CDMA/EV-DO */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8129) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO Mini-Card == Novatel Expedite ET620 CDMA/EV-DO */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8133) }, /* Dell Wireless 5720 == Novatel EV620 CDMA/EV-DO */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8136) }, /* Dell Wireless HSDPA 5520 == Novatel Expedite EU860D */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8137) }, /* Dell Wireless HSDPA 5520 */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8138) }, /* Dell Wireless 5520 Voda I Mobile Broadband (3G HSDPA) Minicard */ - { USB_DEVICE(DELL_VENDOR_ID, 0x8147) }, /* Dell Wireless 5530 Mobile Broadband (3G HSPA) Mini-Card */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5700_MINICARD) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO Mini-Card == Novatel Expedite EV620 CDMA/EV-DO */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5500_MINICARD) }, /* Dell Wireless 5500 Mobile Broadband HSDPA Mini-Card == Novatel Expedite EU740 HSDPA/3G */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5505_MINICARD) }, /* Dell Wireless 5505 Mobile Broadband HSDPA Mini-Card == Novatel Expedite EU740 HSDPA/3G */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5700_EXPRESSCARD) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO ExpressCard == Novatel Merlin XV620 CDMA/EV-DO */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5510_EXPRESSCARD) }, /* Dell Wireless 5510 Mobile Broadband HSDPA ExpressCard == Novatel Merlin XU870 HSDPA/3G */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5700_MINICARD_SPRINT) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO Mini-Card == Novatel Expedite E720 CDMA/EV-DO */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5700_MINICARD_TELUS) }, /* Dell Wireless 5700 Mobile Broadband CDMA/EVDO Mini-Card == Novatel Expedite ET620 CDMA/EV-DO */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5720_MINICARD_VZW) }, /* Dell Wireless 5720 == Novatel EV620 CDMA/EV-DO */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5720_MINICARD_SPRINT) }, /* Dell Wireless 5720 == Novatel EV620 CDMA/EV-DO */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5720_MINICARD_TELUS) }, /* Dell Wireless 5720 == Novatel EV620 CDMA/EV-DO */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5520_MINICARD_CINGULAR) }, /* Dell Wireless HSDPA 5520 == Novatel Expedite EU860D */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5520_MINICARD_GENERIC_L) }, /* Dell Wireless HSDPA 5520 */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5520_MINICARD_GENERIC_I) }, /* Dell Wireless 5520 Voda I Mobile Broadband (3G HSDPA) Minicard */ + { USB_DEVICE(DELL_VENDOR_ID, 0x8147) }, /* Dell Wireless 5530 Mobile Broadband (3G HSPA) Mini-Card */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5730_MINICARD_SPRINT) }, /* Dell Wireless 5730 Mobile Broadband EVDO/HSPA Mini-Card */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5730_MINICARD_TELUS) }, /* Dell Wireless 5730 Mobile Broadband EVDO/HSPA Mini-Card */ + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5730_MINICARD_VZW) }, /* Dell Wireless 5730 Mobile Broadband EVDO/HSPA Mini-Card */ { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_E100A) }, /* ADU-E100, ADU-310 */ { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_500A) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_620UW) }, @@ -488,9 +510,6 @@ static struct usb_device_id option_ids[] = { { USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_MF628) }, { USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH) }, { USB_DEVICE(ERICSSON_VENDOR_ID, ERICSSON_PRODUCT_F3507G) }, - { USB_DEVICE(PANTECH_VENDOR_ID, PANTECH_PRODUCT_PC5740) }, - { USB_DEVICE(PANTECH_VENDOR_ID, PANTECH_PRODUCT_PC5750) }, - { USB_DEVICE(PANTECH_VENDOR_ID, PANTECH_PRODUCT_UM150) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index baf591137b8..2620bf6fe5e 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -176,7 +176,7 @@ static unsigned int product_5052_count; /* the array dimension is the number of default entries plus */ /* TI_EXTRA_VID_PID_COUNT user defined entries plus 1 terminating */ /* null entry */ -static struct usb_device_id ti_id_table_3410[7+TI_EXTRA_VID_PID_COUNT+1] = { +static struct usb_device_id ti_id_table_3410[10+TI_EXTRA_VID_PID_COUNT+1] = { { USB_DEVICE(TI_VENDOR_ID, TI_3410_PRODUCT_ID) }, { USB_DEVICE(TI_VENDOR_ID, TI_3410_EZ430_ID) }, { USB_DEVICE(MTS_VENDOR_ID, MTS_GSM_NO_FW_PRODUCT_ID) }, @@ -185,9 +185,11 @@ static struct usb_device_id ti_id_table_3410[7+TI_EXTRA_VID_PID_COUNT+1] = { { USB_DEVICE(MTS_VENDOR_ID, MTS_GSM_PRODUCT_ID) }, { USB_DEVICE(MTS_VENDOR_ID, MTS_EDGE_PRODUCT_ID) }, { USB_DEVICE(IBM_VENDOR_ID, IBM_4543_PRODUCT_ID) }, + { USB_DEVICE(IBM_VENDOR_ID, IBM_454B_PRODUCT_ID) }, + { USB_DEVICE(IBM_VENDOR_ID, IBM_454C_PRODUCT_ID) }, }; -static struct usb_device_id ti_id_table_5052[4+TI_EXTRA_VID_PID_COUNT+1] = { +static struct usb_device_id ti_id_table_5052[5+TI_EXTRA_VID_PID_COUNT+1] = { { USB_DEVICE(TI_VENDOR_ID, TI_5052_BOOT_PRODUCT_ID) }, { USB_DEVICE(TI_VENDOR_ID, TI_5152_BOOT_PRODUCT_ID) }, { USB_DEVICE(TI_VENDOR_ID, TI_5052_EEPROM_PRODUCT_ID) }, @@ -195,7 +197,7 @@ static struct usb_device_id ti_id_table_5052[4+TI_EXTRA_VID_PID_COUNT+1] = { { USB_DEVICE(IBM_VENDOR_ID, IBM_4543_PRODUCT_ID) }, }; -static struct usb_device_id ti_id_table_combined[6+2*TI_EXTRA_VID_PID_COUNT+1] = { +static struct usb_device_id ti_id_table_combined[14+2*TI_EXTRA_VID_PID_COUNT+1] = { { USB_DEVICE(TI_VENDOR_ID, TI_3410_PRODUCT_ID) }, { USB_DEVICE(TI_VENDOR_ID, TI_3410_EZ430_ID) }, { USB_DEVICE(MTS_VENDOR_ID, MTS_GSM_NO_FW_PRODUCT_ID) }, @@ -208,6 +210,8 @@ static struct usb_device_id ti_id_table_combined[6+2*TI_EXTRA_VID_PID_COUNT+1] = { USB_DEVICE(TI_VENDOR_ID, TI_5052_EEPROM_PRODUCT_ID) }, { USB_DEVICE(TI_VENDOR_ID, TI_5052_FIRMWARE_PRODUCT_ID) }, { USB_DEVICE(IBM_VENDOR_ID, IBM_4543_PRODUCT_ID) }, + { USB_DEVICE(IBM_VENDOR_ID, IBM_454B_PRODUCT_ID) }, + { USB_DEVICE(IBM_VENDOR_ID, IBM_454C_PRODUCT_ID) }, { } }; diff --git a/drivers/usb/serial/ti_usb_3410_5052.h b/drivers/usb/serial/ti_usb_3410_5052.h index b7ea5dbadee..f323c602585 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.h +++ b/drivers/usb/serial/ti_usb_3410_5052.h @@ -30,6 +30,8 @@ #define IBM_VENDOR_ID 0x04b3 #define TI_3410_PRODUCT_ID 0x3410 #define IBM_4543_PRODUCT_ID 0x4543 +#define IBM_454B_PRODUCT_ID 0x454b +#define IBM_454C_PRODUCT_ID 0x454c #define TI_3410_EZ430_ID 0xF430 /* TI ez430 development tool */ #define TI_5052_BOOT_PRODUCT_ID 0x5052 /* no EEPROM, no firmware */ #define TI_5152_BOOT_PRODUCT_ID 0x5152 /* no EEPROM, no firmware */ diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 2a42b862aa9..727c506417c 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -64,6 +64,7 @@ */ #define VENDOR_ID_NOKIA 0x0421 #define VENDOR_ID_NIKON 0x04b0 +#define VENDOR_ID_PENTAX 0x0a17 #define VENDOR_ID_MOTOROLA 0x22b8 /*********************************************************************** @@ -158,6 +159,7 @@ static int slave_configure(struct scsi_device *sdev) switch (le16_to_cpu(us->pusb_dev->descriptor.idVendor)) { case VENDOR_ID_NOKIA: case VENDOR_ID_NIKON: + case VENDOR_ID_PENTAX: case VENDOR_ID_MOTOROLA: if (!(us->fflags & (US_FL_FIX_CAPACITY | US_FL_CAPACITY_OK))) diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 1d5438e6363..fb65d221ced 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -558,32 +558,10 @@ static void last_sector_hacks(struct us_data *us, struct scsi_cmnd *srb) if (srb->result == SAM_STAT_GOOD && scsi_get_resid(srb) == 0) { - /* The command succeeded. If the capacity is odd - * (i.e., if the sector number is even) then the - * "always-even" heuristic would be wrong for this - * device. Issue a WARN() so that the kerneloops.org - * project will be notified and we will then know to - * mark the device with a CAPACITY_OK flag. Hopefully - * this will occur for only a few devices. - * - * Use the sign of us->last_sector_hacks to tell whether - * the warning has already been issued; we don't need - * more than one warning per device. + /* The command succeeded. We know this device doesn't + * have the last-sector bug, so stop checking it. */ - if (!(sector & 1) && us->use_last_sector_hacks > 0) { - unsigned vid = le16_to_cpu( - us->pusb_dev->descriptor.idVendor); - unsigned pid = le16_to_cpu( - us->pusb_dev->descriptor.idProduct); - unsigned rev = le16_to_cpu( - us->pusb_dev->descriptor.bcdDevice); - - WARN(1, "%s: Successful last sector success at %u, " - "device %04x:%04x:%04x\n", - sdkp->disk->disk_name, sector, - vid, pid, rev); - us->use_last_sector_hacks = -1; - } + us->use_last_sector_hacks = 0; } else { /* The command failed. Allow up to 3 retries in case this @@ -599,14 +577,6 @@ static void last_sector_hacks(struct us_data *us, struct scsi_cmnd *srb) srb->result = SAM_STAT_CHECK_CONDITION; memcpy(srb->sense_buffer, record_not_found, sizeof(record_not_found)); - - /* In theory we might want to issue a WARN() here if the - * capacity is even, since it could indicate the device - * has the READ CAPACITY bug _and_ the real capacity is - * odd. But it could also indicate that the device - * simply can't access its last sector, a failure mode - * which is surprisingly common. So no warning. - */ } done: diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 69269f73956..50dc33a6065 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1214,7 +1214,7 @@ UNUSUAL_DEV( 0x07c4, 0xa400, 0x0000, 0xffff, "Datafab", "KECF-USB", US_SC_DEVICE, US_PR_DEVICE, NULL, - US_FL_FIX_INQUIRY ), + US_FL_FIX_INQUIRY | US_FL_FIX_CAPACITY ), /* Reported by Rauch Wolke <rauchwolke@gmx.net> */ UNUSUAL_DEV( 0x07c4, 0xa4a5, 0x0000, 0xffff, @@ -1354,21 +1354,6 @@ UNUSUAL_DEV( 0x0a17, 0x0004, 0x1000, 0x1000, US_SC_DEVICE, US_PR_DEVICE, NULL, US_FL_FIX_INQUIRY ), - -/* Submitted by Per Winkvist <per.winkvist@uk.com> */ -UNUSUAL_DEV( 0x0a17, 0x006, 0x0000, 0xffff, - "Pentax", - "Optio S/S4", - US_SC_DEVICE, US_PR_DEVICE, NULL, - US_FL_FIX_INQUIRY ), - -/* Reported by Jaak Ristioja <Ristioja@gmail.com> */ -UNUSUAL_DEV( 0x0a17, 0x006e, 0x0100, 0x0100, - "Pentax", - "K10D", - US_SC_DEVICE, US_PR_DEVICE, NULL, - US_FL_FIX_CAPACITY ), - /* These are virtual windows driver CDs, which the zd1211rw driver * automatically converts into WLAN devices. */ UNUSUAL_DEV( 0x0ace, 0x2011, 0x0101, 0x0101, diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index f0267706cb4..bf0af660df8 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -1054,9 +1054,10 @@ config FB_RIVA_BACKLIGHT config FB_I810 tristate "Intel 810/815 support (EXPERIMENTAL)" - depends on FB && EXPERIMENTAL && PCI && X86_32 + depends on EXPERIMENTAL && PCI && X86_32 select AGP select AGP_INTEL + select FB select FB_MODE_HELPERS select FB_CFB_FILLRECT select FB_CFB_COPYAREA @@ -1119,7 +1120,8 @@ config FB_CARILLO_RANCH config FB_INTEL tristate "Intel 830M/845G/852GM/855GM/865G/915G/945G/945GM/965G/965GM support (EXPERIMENTAL)" - depends on FB && EXPERIMENTAL && PCI && X86 + depends on EXPERIMENTAL && PCI && X86 + select FB select AGP select AGP_INTEL select FB_MODE_HELPERS diff --git a/drivers/video/bfin-t350mcqb-fb.c b/drivers/video/bfin-t350mcqb-fb.c index 2a423d3a2a8..90cfddabf1f 100644 --- a/drivers/video/bfin-t350mcqb-fb.c +++ b/drivers/video/bfin-t350mcqb-fb.c @@ -447,7 +447,7 @@ static irqreturn_t bfin_t350mcqb_irq_error(int irq, void *dev_id) return IRQ_HANDLED; } -static int __init bfin_t350mcqb_probe(struct platform_device *pdev) +static int __devinit bfin_t350mcqb_probe(struct platform_device *pdev) { struct bfin_t350mcqbfb_info *info; struct fb_info *fbinfo; diff --git a/drivers/video/geode/gx1fb_core.c b/drivers/video/geode/gx1fb_core.c index 751e491ca8c..f20eff8c4a8 100644 --- a/drivers/video/geode/gx1fb_core.c +++ b/drivers/video/geode/gx1fb_core.c @@ -136,13 +136,10 @@ static int gx1fb_set_par(struct fb_info *info) { struct geodefb_par *par = info->par; - if (info->var.bits_per_pixel == 16) { + if (info->var.bits_per_pixel == 16) info->fix.visual = FB_VISUAL_TRUECOLOR; - fb_dealloc_cmap(&info->cmap); - } else { + else info->fix.visual = FB_VISUAL_PSEUDOCOLOR; - fb_alloc_cmap(&info->cmap, 1<<info->var.bits_per_pixel, 0); - } info->fix.line_length = gx1_line_delta(info->var.xres, info->var.bits_per_pixel); @@ -315,6 +312,10 @@ static struct fb_info * __init gx1fb_init_fbinfo(struct device *dev) if (!par->panel_x) par->enable_crt = 1; /* fall back to CRT if no panel is specified */ + if (fb_alloc_cmap(&info->cmap, 256, 0) < 0) { + framebuffer_release(info); + return NULL; + } return info; } @@ -374,8 +375,11 @@ static int __init gx1fb_probe(struct pci_dev *pdev, const struct pci_device_id * release_mem_region(gx1_gx_base() + 0x8300, 0x100); } - if (info) + if (info) { + fb_dealloc_cmap(&info->cmap); framebuffer_release(info); + } + return ret; } @@ -395,6 +399,7 @@ static void gx1fb_remove(struct pci_dev *pdev) iounmap(par->dc_regs); release_mem_region(gx1_gx_base() + 0x8300, 0x100); + fb_dealloc_cmap(&info->cmap); pci_set_drvdata(pdev, NULL); framebuffer_release(info); diff --git a/drivers/video/geode/gxfb_core.c b/drivers/video/geode/gxfb_core.c index 48411892631..2552cac39e1 100644 --- a/drivers/video/geode/gxfb_core.c +++ b/drivers/video/geode/gxfb_core.c @@ -171,13 +171,10 @@ static int gxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) static int gxfb_set_par(struct fb_info *info) { - if (info->var.bits_per_pixel > 8) { + if (info->var.bits_per_pixel > 8) info->fix.visual = FB_VISUAL_TRUECOLOR; - fb_dealloc_cmap(&info->cmap); - } else { + else info->fix.visual = FB_VISUAL_PSEUDOCOLOR; - fb_alloc_cmap(&info->cmap, 1<<info->var.bits_per_pixel, 0); - } info->fix.line_length = gx_line_delta(info->var.xres, info->var.bits_per_pixel); @@ -331,6 +328,11 @@ static struct fb_info * __init gxfb_init_fbinfo(struct device *dev) info->var.grayscale = 0; + if (fb_alloc_cmap(&info->cmap, 256, 0) < 0) { + framebuffer_release(info); + return NULL; + } + return info; } @@ -443,8 +445,10 @@ static int __init gxfb_probe(struct pci_dev *pdev, const struct pci_device_id *i pci_release_region(pdev, 1); } - if (info) + if (info) { + fb_dealloc_cmap(&info->cmap); framebuffer_release(info); + } return ret; } @@ -467,6 +471,7 @@ static void gxfb_remove(struct pci_dev *pdev) iounmap(par->gp_regs); pci_release_region(pdev, 1); + fb_dealloc_cmap(&info->cmap); pci_set_drvdata(pdev, NULL); framebuffer_release(info); diff --git a/drivers/video/geode/lxfb_core.c b/drivers/video/geode/lxfb_core.c index b965ecdbc60..889cbe39e58 100644 --- a/drivers/video/geode/lxfb_core.c +++ b/drivers/video/geode/lxfb_core.c @@ -278,13 +278,10 @@ static int lxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) static int lxfb_set_par(struct fb_info *info) { - if (info->var.bits_per_pixel > 8) { + if (info->var.bits_per_pixel > 8) info->fix.visual = FB_VISUAL_TRUECOLOR; - fb_dealloc_cmap(&info->cmap); - } else { + else info->fix.visual = FB_VISUAL_PSEUDOCOLOR; - fb_alloc_cmap(&info->cmap, 1<<info->var.bits_per_pixel, 0); - } info->fix.line_length = lx_get_pitch(info->var.xres, info->var.bits_per_pixel); @@ -451,6 +448,11 @@ static struct fb_info * __init lxfb_init_fbinfo(struct device *dev) info->pseudo_palette = (void *)par + sizeof(struct lxfb_par); + if (fb_alloc_cmap(&info->cmap, 256, 0) < 0) { + framebuffer_release(info); + return NULL; + } + info->var.grayscale = 0; return info; @@ -579,8 +581,10 @@ err: pci_release_region(pdev, 3); } - if (info) + if (info) { + fb_dealloc_cmap(&info->cmap); framebuffer_release(info); + } return ret; } @@ -604,6 +608,7 @@ static void lxfb_remove(struct pci_dev *pdev) iounmap(par->vp_regs); pci_release_region(pdev, 3); + fb_dealloc_cmap(&info->cmap); pci_set_drvdata(pdev, NULL); framebuffer_release(info); } diff --git a/drivers/w1/slaves/w1_therm.c b/drivers/w1/slaves/w1_therm.c index 2c8dff9f77d..1ed3d554e37 100644 --- a/drivers/w1/slaves/w1_therm.c +++ b/drivers/w1/slaves/w1_therm.c @@ -115,7 +115,7 @@ static struct w1_therm_family_converter w1_therm_families[] = { static inline int w1_DS18B20_convert_temp(u8 rom[9]) { - s16 t = (rom[1] << 8) | rom[0]; + int t = ((s16)rom[1] << 8) | rom[0]; t = t*1000/16; return t; } diff --git a/drivers/watchdog/rdc321x_wdt.c b/drivers/watchdog/rdc321x_wdt.c index bf92802f2bb..36e221beedc 100644 --- a/drivers/watchdog/rdc321x_wdt.c +++ b/drivers/watchdog/rdc321x_wdt.c @@ -37,7 +37,7 @@ #include <linux/io.h> #include <linux/uaccess.h> -#include <asm/mach-rdc321x/rdc321x_defs.h> +#include <asm/rdc321x_defs.h> #define RDC_WDT_MASK 0x80000000 /* Mask */ #define RDC_WDT_EN 0x00800000 /* Enable bit */ diff --git a/drivers/xen/events.c b/drivers/xen/events.c index eb0dfdeaa94..30963af5dba 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -26,9 +26,11 @@ #include <linux/irq.h> #include <linux/module.h> #include <linux/string.h> +#include <linux/bootmem.h> #include <asm/ptrace.h> #include <asm/irq.h> +#include <asm/idle.h> #include <asm/sync_bitops.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -50,36 +52,55 @@ static DEFINE_PER_CPU(int, virq_to_irq[NR_VIRQS]) = {[0 ... NR_VIRQS-1] = -1}; /* IRQ <-> IPI mapping */ static DEFINE_PER_CPU(int, ipi_to_irq[XEN_NR_IPIS]) = {[0 ... XEN_NR_IPIS-1] = -1}; -/* Packed IRQ information: binding type, sub-type index, and event channel. */ -struct packed_irq -{ - unsigned short evtchn; - unsigned char index; - unsigned char type; -}; - -static struct packed_irq irq_info[NR_IRQS]; - -/* Binding types. */ -enum { - IRQT_UNBOUND, +/* Interrupt types. */ +enum xen_irq_type { + IRQT_UNBOUND = 0, IRQT_PIRQ, IRQT_VIRQ, IRQT_IPI, IRQT_EVTCHN }; -/* Convenient shorthand for packed representation of an unbound IRQ. */ -#define IRQ_UNBOUND mk_irq_info(IRQT_UNBOUND, 0, 0) +/* + * Packed IRQ information: + * type - enum xen_irq_type + * event channel - irq->event channel mapping + * cpu - cpu this event channel is bound to + * index - type-specific information: + * PIRQ - vector, with MSB being "needs EIO" + * VIRQ - virq number + * IPI - IPI vector + * EVTCHN - + */ +struct irq_info +{ + enum xen_irq_type type; /* type */ + unsigned short evtchn; /* event channel */ + unsigned short cpu; /* cpu bound */ + + union { + unsigned short virq; + enum ipi_vector ipi; + struct { + unsigned short gsi; + unsigned short vector; + } pirq; + } u; +}; + +static struct irq_info irq_info[NR_IRQS]; static int evtchn_to_irq[NR_EVENT_CHANNELS] = { [0 ... NR_EVENT_CHANNELS-1] = -1 }; -static unsigned long cpu_evtchn_mask[NR_CPUS][NR_EVENT_CHANNELS/BITS_PER_LONG]; -static u8 cpu_evtchn[NR_EVENT_CHANNELS]; - -/* Reference counts for bindings to IRQs. */ -static int irq_bindcount[NR_IRQS]; +struct cpu_evtchn_s { + unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG]; +}; +static struct cpu_evtchn_s *cpu_evtchn_mask_p; +static inline unsigned long *cpu_evtchn_mask(int cpu) +{ + return cpu_evtchn_mask_p[cpu].bits; +} /* Xen will never allocate port zero for any purpose. */ #define VALID_EVTCHN(chn) ((chn) != 0) @@ -87,27 +108,108 @@ static int irq_bindcount[NR_IRQS]; static struct irq_chip xen_dynamic_chip; /* Constructor for packed IRQ information. */ -static inline struct packed_irq mk_irq_info(u32 type, u32 index, u32 evtchn) +static struct irq_info mk_unbound_info(void) +{ + return (struct irq_info) { .type = IRQT_UNBOUND }; +} + +static struct irq_info mk_evtchn_info(unsigned short evtchn) +{ + return (struct irq_info) { .type = IRQT_EVTCHN, .evtchn = evtchn, + .cpu = 0 }; +} + +static struct irq_info mk_ipi_info(unsigned short evtchn, enum ipi_vector ipi) { - return (struct packed_irq) { evtchn, index, type }; + return (struct irq_info) { .type = IRQT_IPI, .evtchn = evtchn, + .cpu = 0, .u.ipi = ipi }; +} + +static struct irq_info mk_virq_info(unsigned short evtchn, unsigned short virq) +{ + return (struct irq_info) { .type = IRQT_VIRQ, .evtchn = evtchn, + .cpu = 0, .u.virq = virq }; +} + +static struct irq_info mk_pirq_info(unsigned short evtchn, + unsigned short gsi, unsigned short vector) +{ + return (struct irq_info) { .type = IRQT_PIRQ, .evtchn = evtchn, + .cpu = 0, .u.pirq = { .gsi = gsi, .vector = vector } }; } /* * Accessors for packed IRQ information. */ -static inline unsigned int evtchn_from_irq(int irq) +static struct irq_info *info_for_irq(unsigned irq) +{ + return &irq_info[irq]; +} + +static unsigned int evtchn_from_irq(unsigned irq) { - return irq_info[irq].evtchn; + return info_for_irq(irq)->evtchn; } -static inline unsigned int index_from_irq(int irq) +static enum ipi_vector ipi_from_irq(unsigned irq) { - return irq_info[irq].index; + struct irq_info *info = info_for_irq(irq); + + BUG_ON(info == NULL); + BUG_ON(info->type != IRQT_IPI); + + return info->u.ipi; } -static inline unsigned int type_from_irq(int irq) +static unsigned virq_from_irq(unsigned irq) { - return irq_info[irq].type; + struct irq_info *info = info_for_irq(irq); + + BUG_ON(info == NULL); + BUG_ON(info->type != IRQT_VIRQ); + + return info->u.virq; +} + +static unsigned gsi_from_irq(unsigned irq) +{ + struct irq_info *info = info_for_irq(irq); + + BUG_ON(info == NULL); + BUG_ON(info->type != IRQT_PIRQ); + + return info->u.pirq.gsi; +} + +static unsigned vector_from_irq(unsigned irq) +{ + struct irq_info *info = info_for_irq(irq); + + BUG_ON(info == NULL); + BUG_ON(info->type != IRQT_PIRQ); + + return info->u.pirq.vector; +} + +static enum xen_irq_type type_from_irq(unsigned irq) +{ + return info_for_irq(irq)->type; +} + +static unsigned cpu_from_irq(unsigned irq) +{ + return info_for_irq(irq)->cpu; +} + +static unsigned int cpu_from_evtchn(unsigned int evtchn) +{ + int irq = evtchn_to_irq[evtchn]; + unsigned ret = 0; + + if (irq != -1) + ret = cpu_from_irq(irq); + + return ret; } static inline unsigned long active_evtchns(unsigned int cpu, @@ -115,7 +217,7 @@ static inline unsigned long active_evtchns(unsigned int cpu, unsigned int idx) { return (sh->evtchn_pending[idx] & - cpu_evtchn_mask[cpu][idx] & + cpu_evtchn_mask(cpu)[idx] & ~sh->evtchn_mask[idx]); } @@ -125,13 +227,13 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) BUG_ON(irq == -1); #ifdef CONFIG_SMP - irq_to_desc(irq)->affinity = cpumask_of_cpu(cpu); + cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu)); #endif - __clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]); - __set_bit(chn, cpu_evtchn_mask[cpu]); + __clear_bit(chn, cpu_evtchn_mask(cpu_from_irq(irq))); + __set_bit(chn, cpu_evtchn_mask(cpu)); - cpu_evtchn[chn] = cpu; + irq_info[irq].cpu = cpu; } static void init_evtchn_cpu_bindings(void) @@ -142,17 +244,11 @@ static void init_evtchn_cpu_bindings(void) /* By default all event channels notify CPU#0. */ for_each_irq_desc(i, desc) { - desc->affinity = cpumask_of_cpu(0); + cpumask_copy(desc->affinity, cpumask_of(0)); } #endif - memset(cpu_evtchn, 0, sizeof(cpu_evtchn)); - memset(cpu_evtchn_mask[0], ~0, sizeof(cpu_evtchn_mask[0])); -} - -static inline unsigned int cpu_from_evtchn(unsigned int evtchn) -{ - return cpu_evtchn[evtchn]; + memset(cpu_evtchn_mask(0), ~0, sizeof(cpu_evtchn_mask(0))); } static inline void clear_evtchn(int port) @@ -232,9 +328,8 @@ static int find_unbound_irq(void) int irq; struct irq_desc *desc; - /* Only allocate from dynirq range */ for (irq = 0; irq < nr_irqs; irq++) - if (irq_bindcount[irq] == 0) + if (irq_info[irq].type == IRQT_UNBOUND) break; if (irq == nr_irqs) @@ -244,6 +339,8 @@ static int find_unbound_irq(void) if (WARN_ON(desc == NULL)) return -1; + dynamic_irq_init(irq); + return irq; } @@ -258,16 +355,13 @@ int bind_evtchn_to_irq(unsigned int evtchn) if (irq == -1) { irq = find_unbound_irq(); - dynamic_irq_init(irq); set_irq_chip_and_handler_name(irq, &xen_dynamic_chip, handle_level_irq, "event"); evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_EVTCHN, 0, evtchn); + irq_info[irq] = mk_evtchn_info(evtchn); } - irq_bindcount[irq]++; - spin_unlock(&irq_mapping_update_lock); return irq; @@ -282,12 +376,12 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) spin_lock(&irq_mapping_update_lock); irq = per_cpu(ipi_to_irq, cpu)[ipi]; + if (irq == -1) { irq = find_unbound_irq(); if (irq < 0) goto out; - dynamic_irq_init(irq); set_irq_chip_and_handler_name(irq, &xen_dynamic_chip, handle_level_irq, "ipi"); @@ -298,15 +392,12 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) evtchn = bind_ipi.port; evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn); - + irq_info[irq] = mk_ipi_info(evtchn, ipi); per_cpu(ipi_to_irq, cpu)[ipi] = irq; bind_evtchn_to_cpu(evtchn, cpu); } - irq_bindcount[irq]++; - out: spin_unlock(&irq_mapping_update_lock); return irq; @@ -332,20 +423,17 @@ static int bind_virq_to_irq(unsigned int virq, unsigned int cpu) irq = find_unbound_irq(); - dynamic_irq_init(irq); set_irq_chip_and_handler_name(irq, &xen_dynamic_chip, handle_level_irq, "virq"); evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn); + irq_info[irq] = mk_virq_info(evtchn, virq); per_cpu(virq_to_irq, cpu)[virq] = irq; bind_evtchn_to_cpu(evtchn, cpu); } - irq_bindcount[irq]++; - spin_unlock(&irq_mapping_update_lock); return irq; @@ -358,7 +446,7 @@ static void unbind_from_irq(unsigned int irq) spin_lock(&irq_mapping_update_lock); - if ((--irq_bindcount[irq] == 0) && VALID_EVTCHN(evtchn)) { + if (VALID_EVTCHN(evtchn)) { close.port = evtchn; if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) BUG(); @@ -366,11 +454,11 @@ static void unbind_from_irq(unsigned int irq) switch (type_from_irq(irq)) { case IRQT_VIRQ: per_cpu(virq_to_irq, cpu_from_evtchn(evtchn)) - [index_from_irq(irq)] = -1; + [virq_from_irq(irq)] = -1; break; case IRQT_IPI: per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn)) - [index_from_irq(irq)] = -1; + [ipi_from_irq(irq)] = -1; break; default: break; @@ -380,7 +468,7 @@ static void unbind_from_irq(unsigned int irq) bind_evtchn_to_cpu(evtchn, 0); evtchn_to_irq[evtchn] = -1; - irq_info[irq] = IRQ_UNBOUND; + irq_info[irq] = mk_unbound_info(); dynamic_irq_cleanup(irq); } @@ -498,8 +586,8 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id) for(i = 0; i < NR_EVENT_CHANNELS; i++) { if (sync_test_bit(i, sh->evtchn_pending)) { printk(" %d: event %d -> irq %d\n", - cpu_evtchn[i], i, - evtchn_to_irq[i]); + cpu_from_evtchn(i), i, + evtchn_to_irq[i]); } } @@ -508,7 +596,6 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } - /* * Search the CPUs pending events bitmasks. For each one found, map * the event number to an irq, and feed it into do_IRQ() for @@ -521,11 +608,15 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id) void xen_evtchn_do_upcall(struct pt_regs *regs) { int cpu = get_cpu(); + struct pt_regs *old_regs = set_irq_regs(regs); struct shared_info *s = HYPERVISOR_shared_info; struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu); static DEFINE_PER_CPU(unsigned, nesting_count); unsigned count; + exit_idle(); + irq_enter(); + do { unsigned long pending_words; @@ -550,7 +641,7 @@ void xen_evtchn_do_upcall(struct pt_regs *regs) int irq = evtchn_to_irq[port]; if (irq != -1) - xen_do_IRQ(irq, regs); + handle_irq(irq, regs); } } @@ -561,12 +652,17 @@ void xen_evtchn_do_upcall(struct pt_regs *regs) } while(count != 1); out: + irq_exit(); + set_irq_regs(old_regs); + put_cpu(); } /* Rebind a new event channel to an existing irq. */ void rebind_evtchn_irq(int evtchn, int irq) { + struct irq_info *info = info_for_irq(irq); + /* Make sure the irq is masked, since the new event channel will also be masked. */ disable_irq(irq); @@ -576,11 +672,11 @@ void rebind_evtchn_irq(int evtchn, int irq) /* After resume the irq<->evtchn mappings are all cleared out */ BUG_ON(evtchn_to_irq[evtchn] != -1); /* Expect irq to have been bound before, - so the bindcount should be non-0 */ - BUG_ON(irq_bindcount[irq] == 0); + so there should be a proper type */ + BUG_ON(info->type == IRQT_UNBOUND); evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_EVTCHN, 0, evtchn); + irq_info[irq] = mk_evtchn_info(evtchn); spin_unlock(&irq_mapping_update_lock); @@ -690,8 +786,7 @@ static void restore_cpu_virqs(unsigned int cpu) if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1) continue; - BUG_ON(irq_info[irq].type != IRQT_VIRQ); - BUG_ON(irq_info[irq].index != virq); + BUG_ON(virq_from_irq(irq) != virq); /* Get a new binding from Xen. */ bind_virq.virq = virq; @@ -703,7 +798,7 @@ static void restore_cpu_virqs(unsigned int cpu) /* Record the new mapping. */ evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn); + irq_info[irq] = mk_virq_info(evtchn, virq); bind_evtchn_to_cpu(evtchn, cpu); /* Ready for use. */ @@ -720,8 +815,7 @@ static void restore_cpu_ipis(unsigned int cpu) if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1) continue; - BUG_ON(irq_info[irq].type != IRQT_IPI); - BUG_ON(irq_info[irq].index != ipi); + BUG_ON(ipi_from_irq(irq) != ipi); /* Get a new binding from Xen. */ bind_ipi.vcpu = cpu; @@ -732,7 +826,7 @@ static void restore_cpu_ipis(unsigned int cpu) /* Record the new mapping. */ evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn); + irq_info[irq] = mk_ipi_info(evtchn, ipi); bind_evtchn_to_cpu(evtchn, cpu); /* Ready for use. */ @@ -812,8 +906,11 @@ void xen_irq_resume(void) static struct irq_chip xen_dynamic_chip __read_mostly = { .name = "xen-dyn", + + .disable = disable_dynirq, .mask = disable_dynirq, .unmask = enable_dynirq, + .ack = ack_dynirq, .set_affinity = set_affinity_irq, .retrigger = retrigger_dynirq, @@ -822,6 +919,10 @@ static struct irq_chip xen_dynamic_chip __read_mostly = { void __init xen_init_IRQ(void) { int i; + size_t size = nr_cpu_ids * sizeof(struct cpu_evtchn_s); + + cpu_evtchn_mask_p = alloc_bootmem(size); + BUG_ON(cpu_evtchn_mask_p == NULL); init_evtchn_cpu_bindings(); @@ -829,9 +930,5 @@ void __init xen_init_IRQ(void) for (i = 0; i < NR_EVENT_CHANNELS; i++) mask_evtchn(i); - /* Dynamic IRQ space is currently unbound. Zero the refcnts. */ - for (i = 0; i < nr_irqs; i++) - irq_bindcount[i] = 0; - irq_ctx_init(smp_processor_id()); } diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 9b91617b958..e7e83b65c18 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -100,7 +100,7 @@ static void do_suspend(void) /* XXX use normal device tree? */ xenbus_suspend(); - err = stop_machine(xen_suspend, &cancelled, &cpumask_of_cpu(0)); + err = stop_machine(xen_suspend, &cancelled, cpumask_of(0)); if (err) { printk(KERN_ERR "failed to start xen_suspend: %d\n", err); goto out; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 551177c0011..35443cc4b9a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1530,8 +1530,7 @@ again: * for higher level blocks, try not to allocate blocks * with the block and the parent locks held. */ - if (level > 0 && !prealloc_block.objectid && - btrfs_path_lock_waiting(p, level)) { + if (level > 0 && !prealloc_block.objectid) { u32 size = b->len; u64 hint = b->start; diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 68fd9ccf180..9ebe9385129 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -236,25 +236,3 @@ int btrfs_tree_locked(struct extent_buffer *eb) return test_bit(EXTENT_BUFFER_BLOCKING, &eb->bflags) || spin_is_locked(&eb->lock); } - -/* - * btrfs_search_slot uses this to decide if it should drop its locks - * before doing something expensive like allocating free blocks for cow. - */ -int btrfs_path_lock_waiting(struct btrfs_path *path, int level) -{ - int i; - struct extent_buffer *eb; - - for (i = level; i <= level + 1 && i < BTRFS_MAX_LEVEL; i++) { - eb = path->nodes[i]; - if (!eb) - break; - smp_mb(); - if (spin_is_contended(&eb->lock) || - waitqueue_active(&eb->lock_wq)) - return 1; - } - return 0; -} - diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index d92e707f587..6bb0afbff92 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -26,8 +26,6 @@ int btrfs_tree_locked(struct extent_buffer *eb); int btrfs_try_tree_lock(struct extent_buffer *eb); int btrfs_try_spin_lock(struct extent_buffer *eb); -int btrfs_path_lock_waiting(struct btrfs_path *path, int level); - void btrfs_set_lock_blocking(struct extent_buffer *eb); void btrfs_clear_lock_blocking(struct extent_buffer *eb); #endif diff --git a/fs/ext2/super.c b/fs/ext2/super.c index da8bdeaa2e6..7c6e3606f0e 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1185,9 +1185,12 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data) es = sbi->s_es; if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) != (old_mount_opt & EXT2_MOUNT_XIP)) && - invalidate_inodes(sb)) - ext2_warning(sb, __func__, "busy inodes while remounting "\ - "xip remain in cache (no functional problem)"); + invalidate_inodes(sb)) { + ext2_warning(sb, __func__, "refusing change of xip flag " + "with busy inodes while remounting"); + sbi->s_mount_opt &= ~EXT2_MOUNT_XIP; + sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP; + } if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) return 0; if (*flags & MS_RDONLY) { diff --git a/fs/ext3/super.c b/fs/ext3/super.c index b70d90e08a3..4a970411a45 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2428,12 +2428,13 @@ static void ext3_write_super (struct super_block * sb) static int ext3_sync_fs(struct super_block *sb, int wait) { - sb->s_dirt = 0; - if (wait) - ext3_force_commit(sb); - else - journal_start_commit(EXT3_SB(sb)->s_journal, NULL); + tid_t target; + sb->s_dirt = 0; + if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) { + if (wait) + log_wait_commit(EXT3_SB(sb)->s_journal, target); + } return 0; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 6903d37af03..9b800d97a68 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -108,7 +108,8 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) if (hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), - len >> huge_page_shift(h), vma)) + len >> huge_page_shift(h), vma, + vma->vm_flags)) goto out; ret = 0; @@ -947,7 +948,7 @@ static int can_do_hugetlb_shm(void) can_do_mlock()); } -struct file *hugetlb_file_setup(const char *name, size_t size) +struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag) { int error = -ENOMEM; struct file *file; @@ -981,7 +982,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size) error = -ENOMEM; if (hugetlb_reserve_pages(inode, 0, - size >> huge_page_shift(hstate_inode(inode)), NULL)) + size >> huge_page_shift(hstate_inode(inode)), NULL, + acctflag)) goto out_inode; d_instantiate(dentry, inode); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 9e4fa52d7dc..e79c07812af 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -427,7 +427,7 @@ int __log_space_left(journal_t *journal) } /* - * Called under j_state_lock. Returns true if a transaction was started. + * Called under j_state_lock. Returns true if a transaction commit was started. */ int __log_start_commit(journal_t *journal, tid_t target) { @@ -495,7 +495,8 @@ int journal_force_commit_nested(journal_t *journal) /* * Start a commit of the current running transaction (if any). Returns true - * if a transaction was started, and fills its tid in at *ptid + * if a transaction is going to be committed (or is currently already + * committing), and fills its tid in at *ptid */ int journal_start_commit(journal_t *journal, tid_t *ptid) { @@ -505,15 +506,19 @@ int journal_start_commit(journal_t *journal, tid_t *ptid) if (journal->j_running_transaction) { tid_t tid = journal->j_running_transaction->t_tid; - ret = __log_start_commit(journal, tid); - if (ret && ptid) + __log_start_commit(journal, tid); + /* There's a running transaction and we've just made sure + * it's commit has been scheduled. */ + if (ptid) *ptid = tid; - } else if (journal->j_committing_transaction && ptid) { + ret = 1; + } else if (journal->j_committing_transaction) { /* * If ext3_write_super() recently started a commit, then we * have to wait for completion of that transaction */ - *ptid = journal->j_committing_transaction->t_tid; + if (ptid) + *ptid = journal->j_committing_transaction->t_tid; ret = 1; } spin_unlock(&journal->j_state_lock); diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 6063a8e4b9f..763b78a6e9d 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -427,7 +427,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; case -EAGAIN: ret = nlm_lck_denied; - goto out; + break; case FILE_LOCK_DEFERRED: if (wait) break; @@ -443,6 +443,10 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } + ret = nlm_lck_denied; + if (!wait) + goto out; + ret = nlm_lck_blocked; /* Append to list of blocked */ diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index b0e63c672eb..00f45ff081a 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -80,4 +80,56 @@ extern void setup_per_cpu_areas(void); #define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \ __typeof__(type) per_cpu_var(name) +/* + * Optional methods for optimized non-lvalue per-cpu variable access. + * + * @var can be a percpu variable or a field of it and its size should + * equal char, int or long. percpu_read() evaluates to a lvalue and + * all others to void. + * + * These operations are guaranteed to be atomic w.r.t. preemption. + * The generic versions use plain get/put_cpu_var(). Archs are + * encouraged to implement single-instruction alternatives which don't + * require preemption protection. + */ +#ifndef percpu_read +# define percpu_read(var) \ + ({ \ + typeof(per_cpu_var(var)) __tmp_var__; \ + __tmp_var__ = get_cpu_var(var); \ + put_cpu_var(var); \ + __tmp_var__; \ + }) +#endif + +#define __percpu_generic_to_op(var, val, op) \ +do { \ + get_cpu_var(var) op val; \ + put_cpu_var(var); \ +} while (0) + +#ifndef percpu_write +# define percpu_write(var, val) __percpu_generic_to_op(var, (val), =) +#endif + +#ifndef percpu_add +# define percpu_add(var, val) __percpu_generic_to_op(var, (val), +=) +#endif + +#ifndef percpu_sub +# define percpu_sub(var, val) __percpu_generic_to_op(var, (val), -=) +#endif + +#ifndef percpu_and +# define percpu_and(var, val) __percpu_generic_to_op(var, (val), &=) +#endif + +#ifndef percpu_or +# define percpu_or(var, val) __percpu_generic_to_op(var, (val), |=) +#endif + +#ifndef percpu_xor +# define percpu_xor(var, val) __percpu_generic_to_op(var, (val), ^=) +#endif + #endif /* _ASM_GENERIC_PERCPU_H_ */ diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 79a7ff925bf..4ce48e87853 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -9,7 +9,7 @@ extern char __bss_start[], __bss_stop[]; extern char __init_begin[], __init_end[]; extern char _sinittext[], _einittext[]; extern char _end[]; -extern char __per_cpu_start[], __per_cpu_end[]; +extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[]; extern char __kprobes_text_start[], __kprobes_text_end[]; extern char __initdata_begin[], __initdata_end[]; extern char __start_rodata[], __end_rodata[]; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c61fab1dd2f..5406e70aba8 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -430,12 +430,59 @@ *(.initcall7.init) \ *(.initcall7s.init) +/** + * PERCPU_VADDR - define output section for percpu area + * @vaddr: explicit base address (optional) + * @phdr: destination PHDR (optional) + * + * Macro which expands to output section for percpu area. If @vaddr + * is not blank, it specifies explicit base address and all percpu + * symbols will be offset from the given address. If blank, @vaddr + * always equals @laddr + LOAD_OFFSET. + * + * @phdr defines the output PHDR to use if not blank. Be warned that + * output PHDR is sticky. If @phdr is specified, the next output + * section in the linker script will go there too. @phdr should have + * a leading colon. + * + * Note that this macros defines __per_cpu_load as an absolute symbol. + * If there is no need to put the percpu section at a predetermined + * address, use PERCPU(). + */ +#define PERCPU_VADDR(vaddr, phdr) \ + VMLINUX_SYMBOL(__per_cpu_load) = .; \ + .data.percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load) \ + - LOAD_OFFSET) { \ + VMLINUX_SYMBOL(__per_cpu_start) = .; \ + *(.data.percpu.first) \ + *(.data.percpu.page_aligned) \ + *(.data.percpu) \ + *(.data.percpu.shared_aligned) \ + VMLINUX_SYMBOL(__per_cpu_end) = .; \ + } phdr \ + . = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data.percpu); + +/** + * PERCPU - define output section for percpu area, simple version + * @align: required alignment + * + * Align to @align and outputs output section for percpu area. This + * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and + * __per_cpu_start will be identical. + * + * This macro is equivalent to ALIGN(align); PERCPU_VADDR( , ) except + * that __per_cpu_load is defined as a relative symbol against + * .data.percpu which is required for relocatable x86_32 + * configuration. + */ #define PERCPU(align) \ . = ALIGN(align); \ - VMLINUX_SYMBOL(__per_cpu_start) = .; \ - .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { \ + .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { \ + VMLINUX_SYMBOL(__per_cpu_load) = .; \ + VMLINUX_SYMBOL(__per_cpu_start) = .; \ + *(.data.percpu.first) \ *(.data.percpu.page_aligned) \ *(.data.percpu) \ *(.data.percpu.shared_aligned) \ - } \ - VMLINUX_SYMBOL(__per_cpu_end) = .; + VMLINUX_SYMBOL(__per_cpu_end) = .; \ + } diff --git a/include/crypto/hash.h b/include/crypto/hash.h index cd16d6e668c..d797e119e3d 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -222,7 +222,7 @@ static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm) static inline void crypto_free_shash(struct crypto_shash *tfm) { - crypto_free_tfm(crypto_shash_tfm(tfm)); + crypto_destroy_tfm(tfm, crypto_shash_tfm(tfm)); } static inline unsigned int crypto_shash_alignmask( diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index b3bcf72dc65..912cd52db96 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -261,6 +261,7 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_LAST_DISPATCH 3 #define I915_PARAM_CHIPSET_ID 4 #define I915_PARAM_HAS_GEM 5 +#define I915_PARAM_NUM_FENCES_AVAIL 6 typedef struct drm_i915_getparam { int param; @@ -272,6 +273,7 @@ typedef struct drm_i915_getparam { #define I915_SETPARAM_USE_MI_BATCHBUFFER_START 1 #define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY 2 #define I915_SETPARAM_ALLOW_BATCHBUFFER 3 +#define I915_SETPARAM_NUM_USED_FENCES 4 typedef struct drm_i915_setparam { int param; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e4e8e117d27..499900d0cee 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -378,6 +378,7 @@ struct cgroup_subsys { * - initiating hotplug events */ struct mutex hierarchy_mutex; + struct lock_class_key subsys_key; /* * Link to parent, and list entry in parent's children. diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 3bacd71509f..1f2e9020acc 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -552,7 +552,12 @@ struct crypto_tfm *crypto_alloc_tfm(const char *alg_name, const struct crypto_type *frontend, u32 type, u32 mask); struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask); -void crypto_free_tfm(struct crypto_tfm *tfm); +void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm); + +static inline void crypto_free_tfm(struct crypto_tfm *tfm) +{ + return crypto_destroy_tfm(tfm, tfm); +} int alg_test(const char *driver, const char *alg, u32 type, u32 mask); diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 3e0f64c335c..3e68469c188 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -282,6 +282,18 @@ static inline void dmaengine_put(void) } #endif +#ifdef CONFIG_NET_DMA +#define net_dmaengine_get() dmaengine_get() +#define net_dmaengine_put() dmaengine_put() +#else +static inline void net_dmaengine_get(void) +{ +} +static inline void net_dmaengine_put(void) +{ +} +#endif + dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest, void *src, size_t len); dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan, diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 5ca54d77079..7605c5e9589 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -111,6 +111,15 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re #endif } +static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs) +{ +#ifdef ELF_CORE_COPY_KERNEL_REGS + ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs); +#else + elf_core_copy_regs(elfregs, regs); +#endif +} + static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs) { #ifdef ELF_CORE_COPY_TASK_REGS diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f1d2fba19ea..03be7f29ca0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -33,7 +33,8 @@ unsigned long hugetlb_total_pages(void); int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access); int hugetlb_reserve_pages(struct inode *inode, long from, long to, - struct vm_area_struct *vma); + struct vm_area_struct *vma, + int acctflags); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long hugepages_treat_as_movable; @@ -138,7 +139,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern const struct file_operations hugetlbfs_file_operations; extern struct vm_operations_struct hugetlb_vm_ops; -struct file *hugetlb_file_setup(const char *name, size_t); +struct file *hugetlb_file_setup(const char *name, size_t, int); int hugetlb_get_quota(struct address_space *mapping, long delta); void hugetlb_put_quota(struct address_space *mapping, long delta); @@ -158,9 +159,9 @@ static inline void set_file_hugepages(struct file *file) } #else /* !CONFIG_HUGETLBFS */ -#define is_file_hugepages(file) 0 -#define set_file_hugepages(file) BUG() -#define hugetlb_file_setup(name,size) ERR_PTR(-ENOSYS) +#define is_file_hugepages(file) 0 +#define set_file_hugepages(file) BUG() +#define hugetlb_file_setup(name,size,acctflag) ERR_PTR(-ENOSYS) #endif /* !CONFIG_HUGETLBFS */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index ea0ea1a4c36..e752d973fa2 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -48,12 +48,11 @@ extern struct fs_struct init_fs; .posix_timers = LIST_HEAD_INIT(sig.posix_timers), \ .cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \ .rlim = INIT_RLIMITS, \ - .cputime = { .totals = { \ - .utime = cputime_zero, \ - .stime = cputime_zero, \ - .sum_exec_runtime = 0, \ - .lock = __SPIN_LOCK_UNLOCKED(sig.cputime.totals.lock), \ - }, }, \ + .cputimer = { \ + .cputime = INIT_CPUTIME, \ + .running = 0, \ + .lock = __SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \ + }, \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9127f6b51a3..472f11765f6 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -467,6 +467,7 @@ int show_interrupts(struct seq_file *p, void *v); struct irq_desc; extern int early_irq_init(void); +extern int arch_probe_nr_irqs(void); extern int arch_early_irq_init(void); extern int arch_init_chip_data(struct irq_desc *desc, int cpu); diff --git a/include/linux/irq.h b/include/linux/irq.h index f899b502f18..27a67536511 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -182,11 +182,11 @@ struct irq_desc { unsigned int irqs_unhandled; spinlock_t lock; #ifdef CONFIG_SMP - cpumask_t affinity; + cpumask_var_t affinity; unsigned int cpu; -#endif #ifdef CONFIG_GENERIC_PENDING_IRQ - cpumask_t pending_mask; + cpumask_var_t pending_mask; +#endif #endif #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; @@ -422,4 +422,84 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry); #endif /* !CONFIG_S390 */ +#ifdef CONFIG_SMP +/** + * init_alloc_desc_masks - allocate cpumasks for irq_desc + * @desc: pointer to irq_desc struct + * @cpu: cpu which will be handling the cpumasks + * @boot: true if need bootmem + * + * Allocates affinity and pending_mask cpumask if required. + * Returns true if successful (or not required). + * Side effect: affinity has all bits set, pending_mask has all bits clear. + */ +static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu, + bool boot) +{ + int node; + + if (boot) { + alloc_bootmem_cpumask_var(&desc->affinity); + cpumask_setall(desc->affinity); + +#ifdef CONFIG_GENERIC_PENDING_IRQ + alloc_bootmem_cpumask_var(&desc->pending_mask); + cpumask_clear(desc->pending_mask); +#endif + return true; + } + + node = cpu_to_node(cpu); + + if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node)) + return false; + cpumask_setall(desc->affinity); + +#ifdef CONFIG_GENERIC_PENDING_IRQ + if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) { + free_cpumask_var(desc->affinity); + return false; + } + cpumask_clear(desc->pending_mask); +#endif + return true; +} + +/** + * init_copy_desc_masks - copy cpumasks for irq_desc + * @old_desc: pointer to old irq_desc struct + * @new_desc: pointer to new irq_desc struct + * + * Insures affinity and pending_masks are copied to new irq_desc. + * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the + * irq_desc struct so the copy is redundant. + */ + +static inline void init_copy_desc_masks(struct irq_desc *old_desc, + struct irq_desc *new_desc) +{ +#ifdef CONFIG_CPUMASKS_OFFSTACK + cpumask_copy(new_desc->affinity, old_desc->affinity); + +#ifdef CONFIG_GENERIC_PENDING_IRQ + cpumask_copy(new_desc->pending_mask, old_desc->pending_mask); +#endif +#endif +} + +#else /* !CONFIG_SMP */ + +static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu, + bool boot) +{ + return true; +} + +static inline void init_copy_desc_masks(struct irq_desc *old_desc, + struct irq_desc *new_desc) +{ +} + +#endif /* CONFIG_SMP */ + #endif /* _LINUX_IRQ_H */ diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h index 86af92e9e84..887477bc2ab 100644 --- a/include/linux/irqnr.h +++ b/include/linux/irqnr.h @@ -20,6 +20,7 @@ # define for_each_irq_desc_reverse(irq, desc) \ for (irq = nr_irqs - 1; irq >= 0; irq--) + #else /* CONFIG_GENERIC_HARDIRQS */ extern int nr_irqs; diff --git a/include/linux/magic.h b/include/linux/magic.h index 0b4df7eba85..5b4e28bcb78 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -49,4 +49,5 @@ #define FUTEXFS_SUPER_MAGIC 0xBAD1DEA #define INOTIFYFS_SUPER_MAGIC 0x2BAD1DEA +#define STACK_END_MAGIC 0x57AC6E9D #endif /* __LINUX_MAGIC_H__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index e8ddc98b840..323561582c1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1129,8 +1129,7 @@ extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long flag, unsigned long pgoff); extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, - unsigned int vm_flags, unsigned long pgoff, - int accountable); + unsigned int vm_flags, unsigned long pgoff); static inline unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 9f2a3751873..3577ffd90d4 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -8,35 +8,46 @@ #include <asm/percpu.h> +#ifndef PER_CPU_BASE_SECTION +#ifdef CONFIG_SMP +#define PER_CPU_BASE_SECTION ".data.percpu" +#else +#define PER_CPU_BASE_SECTION ".data" +#endif +#endif + #ifdef CONFIG_SMP -#define DEFINE_PER_CPU(type, name) \ - __attribute__((__section__(".data.percpu"))) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name #ifdef MODULE -#define SHARED_ALIGNED_SECTION ".data.percpu" +#define PER_CPU_SHARED_ALIGNED_SECTION "" #else -#define SHARED_ALIGNED_SECTION ".data.percpu.shared_aligned" +#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned" #endif +#define PER_CPU_FIRST_SECTION ".first" -#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ - __attribute__((__section__(SHARED_ALIGNED_SECTION))) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name \ - ____cacheline_aligned_in_smp +#else -#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \ - __attribute__((__section__(".data.percpu.page_aligned"))) \ +#define PER_CPU_SHARED_ALIGNED_SECTION "" +#define PER_CPU_FIRST_SECTION "" + +#endif + +#define DEFINE_PER_CPU_SECTION(type, name, section) \ + __attribute__((__section__(PER_CPU_BASE_SECTION section))) \ PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name -#else + #define DEFINE_PER_CPU(type, name) \ - PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name + DEFINE_PER_CPU_SECTION(type, name, "") -#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ - DEFINE_PER_CPU(type, name) +#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \ + ____cacheline_aligned_in_smp -#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \ - DEFINE_PER_CPU(type, name) -#endif +#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, ".page_aligned") + +#define DEFINE_PER_CPU_FIRST(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION) #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var) #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var) diff --git a/include/linux/sched.h b/include/linux/sched.h index 2127e959e0f..f0a50b20e8a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -443,7 +443,6 @@ struct pacct_struct { * @utime: time spent in user mode, in &cputime_t units * @stime: time spent in kernel mode, in &cputime_t units * @sum_exec_runtime: total time spent on the CPU, in nanoseconds - * @lock: lock for fields in this struct * * This structure groups together three kinds of CPU time that are * tracked for threads and thread groups. Most things considering @@ -454,23 +453,33 @@ struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; - spinlock_t lock; }; /* Alternate field names when used to cache expirations. */ #define prof_exp stime #define virt_exp utime #define sched_exp sum_exec_runtime +#define INIT_CPUTIME \ + (struct task_cputime) { \ + .utime = cputime_zero, \ + .stime = cputime_zero, \ + .sum_exec_runtime = 0, \ + } + /** - * struct thread_group_cputime - thread group interval timer counts - * @totals: thread group interval timers; substructure for - * uniprocessor kernel, per-cpu for SMP kernel. + * struct thread_group_cputimer - thread group interval timer counts + * @cputime: thread group interval timers. + * @running: non-zero when there are timers running and + * @cputime receives updates. + * @lock: lock for fields in this struct. * * This structure contains the version of task_cputime, above, that is - * used for thread group CPU clock calculations. + * used for thread group CPU timer calculations. */ -struct thread_group_cputime { - struct task_cputime totals; +struct thread_group_cputimer { + struct task_cputime cputime; + int running; + spinlock_t lock; }; /* @@ -519,10 +528,10 @@ struct signal_struct { cputime_t it_prof_incr, it_virt_incr; /* - * Thread group totals for process CPU clocks. - * See thread_group_cputime(), et al, for details. + * Thread group totals for process CPU timers. + * See thread_group_cputimer(), et al, for details. */ - struct thread_group_cputime cputime; + struct thread_group_cputimer cputimer; /* Earliest-expiration cache. */ struct task_cputime cputime_expires; @@ -559,7 +568,7 @@ struct signal_struct { * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ - cputime_t cutime, cstime; + cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -568,6 +577,14 @@ struct signal_struct { struct task_io_accounting ioac; /* + * Cumulative ns of schedule CPU time fo dead threads in the + * group, not including a zombie group leader, (This only differs + * from jiffies_to_ns(utime + stime) if sched_clock uses something + * other than jiffies.) + */ + unsigned long long sum_sched_runtime; + + /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one @@ -1161,10 +1178,9 @@ struct task_struct { pid_t pid; pid_t tgid; -#ifdef CONFIG_CC_STACKPROTECTOR /* Canary value for the -fstack-protector gcc feature */ unsigned long stack_canary; -#endif + /* * pointers to (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with @@ -2070,6 +2086,19 @@ static inline int object_is_on_stack(void *obj) extern void thread_info_cache_init(void); +#ifdef CONFIG_DEBUG_STACK_USAGE +static inline unsigned long stack_not_used(struct task_struct *p) +{ + unsigned long *n = end_of_stack(p); + + do { /* Skip over canary */ + n++; + } while (!*n); + + return (unsigned long)n - (unsigned long)end_of_stack(p); +} +#endif + /* set thread flags in other task's structures * - see asm/thread_info.h for TIF_xxxx flags available */ @@ -2183,27 +2212,14 @@ static inline int spin_needbreak(spinlock_t *lock) /* * Thread group CPU time accounting. */ - -static inline -void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) -{ - struct task_cputime *totals = &tsk->signal->cputime.totals; - unsigned long flags; - - spin_lock_irqsave(&totals->lock, flags); - *times = *totals; - spin_unlock_irqrestore(&totals->lock, flags); -} +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); +void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); static inline void thread_group_cputime_init(struct signal_struct *sig) { - sig->cputime.totals = (struct task_cputime){ - .utime = cputime_zero, - .stime = cputime_zero, - .sum_exec_runtime = 0, - }; - - spin_lock_init(&sig->cputime.totals.lock); + sig->cputimer.cputime = INIT_CPUTIME; + spin_lock_init(&sig->cputimer.lock); + sig->cputimer.running = 0; } static inline void thread_group_cputime_free(struct signal_struct *sig) diff --git a/include/linux/smp.h b/include/linux/smp.h index 715196b09d6..bbacb7baa44 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -176,6 +176,12 @@ static inline void init_call_single_data(void) #define put_cpu() preempt_enable() #define put_cpu_no_resched() preempt_enable_no_resched() +/* + * Callback to arch code if there's nosmp or maxcpus=0 on the + * boot command line: + */ +extern void arch_disable_smp_support(void); + void smp_setup_processor_id(void); #endif /* __LINUX_SMP_H */ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index e0c0fccced4..a0c66a2e00a 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -124,7 +124,12 @@ do { \ #ifdef CONFIG_GENERIC_LOCKBREAK #define spin_is_contended(lock) ((lock)->break_lock) #else + +#ifdef __raw_spin_is_contended #define spin_is_contended(lock) __raw_spin_is_contended(&(lock)->raw_lock) +#else +#define spin_is_contended(lock) (((void)(lock), 0)) +#endif /*__raw_spin_is_contended*/ #endif /** diff --git a/include/linux/stackprotector.h b/include/linux/stackprotector.h new file mode 100644 index 00000000000..6f3e54c704c --- /dev/null +++ b/include/linux/stackprotector.h @@ -0,0 +1,16 @@ +#ifndef _LINUX_STACKPROTECTOR_H +#define _LINUX_STACKPROTECTOR_H 1 + +#include <linux/compiler.h> +#include <linux/sched.h> +#include <linux/random.h> + +#ifdef CONFIG_CC_STACKPROTECTOR +# include <asm/stackprotector.h> +#else +static inline void boot_init_stack_canary(void) +{ +} +#endif + +#endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0eda02ff241..f9f900cfd06 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -95,13 +95,13 @@ struct old_linux_dirent; #define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__) #define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) -#define SYSCALL_DEFINE0(name) asmlinkage long sys_##name(void) -#define SYSCALL_DEFINE1(...) SYSCALL_DEFINEx(1, __VA_ARGS__) -#define SYSCALL_DEFINE2(...) SYSCALL_DEFINEx(2, __VA_ARGS__) -#define SYSCALL_DEFINE3(...) SYSCALL_DEFINEx(3, __VA_ARGS__) -#define SYSCALL_DEFINE4(...) SYSCALL_DEFINEx(4, __VA_ARGS__) -#define SYSCALL_DEFINE5(...) SYSCALL_DEFINEx(5, __VA_ARGS__) -#define SYSCALL_DEFINE6(...) SYSCALL_DEFINEx(6, __VA_ARGS__) +#define SYSCALL_DEFINE0(name) asmlinkage long sys_##name(void) +#define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) +#define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) +#define SYSCALL_DEFINE3(name, ...) SYSCALL_DEFINEx(3, _##name, __VA_ARGS__) +#define SYSCALL_DEFINE4(name, ...) SYSCALL_DEFINEx(4, _##name, __VA_ARGS__) +#define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) +#define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) #ifdef CONFIG_PPC64 #define SYSCALL_ALIAS(alias, name) \ @@ -121,21 +121,21 @@ struct old_linux_dirent; #define SYSCALL_DEFINE(name) static inline long SYSC_##name #define SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long sys_##name(__SC_DECL##x(__VA_ARGS__)); \ - static inline long SYSC_##name(__SC_DECL##x(__VA_ARGS__)); \ - asmlinkage long SyS_##name(__SC_LONG##x(__VA_ARGS__)) \ + asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__)); \ + static inline long SYSC##name(__SC_DECL##x(__VA_ARGS__)); \ + asmlinkage long SyS##name(__SC_LONG##x(__VA_ARGS__)) \ { \ __SC_TEST##x(__VA_ARGS__); \ - return (long) SYSC_##name(__SC_CAST##x(__VA_ARGS__)); \ + return (long) SYSC##name(__SC_CAST##x(__VA_ARGS__)); \ } \ - SYSCALL_ALIAS(sys_##name, SyS_##name); \ - static inline long SYSC_##name(__SC_DECL##x(__VA_ARGS__)) + SYSCALL_ALIAS(sys##name, SyS##name); \ + static inline long SYSC##name(__SC_DECL##x(__VA_ARGS__)) #else /* CONFIG_HAVE_SYSCALL_WRAPPERS */ #define SYSCALL_DEFINE(name) asmlinkage long sys_##name #define SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long sys_##name(__SC_DECL##x(__VA_ARGS__)) + asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__)) #endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */ diff --git a/include/linux/topology.h b/include/linux/topology.h index e632d29f054..a16b9e06f2e 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -193,5 +193,11 @@ int arch_update_cpu_topology(void); #ifndef topology_core_siblings #define topology_core_siblings(cpu) cpumask_of_cpu(cpu) #endif +#ifndef topology_thread_cpumask +#define topology_thread_cpumask(cpu) cpumask_of(cpu) +#endif +#ifndef topology_core_cpumask +#define topology_core_cpumask(cpu) cpumask_of(cpu) +#endif #endif /* _LINUX_TOPOLOGY_H */ diff --git a/init/main.c b/init/main.c index 844209453c0..6441083f827 100644 --- a/init/main.c +++ b/init/main.c @@ -14,6 +14,7 @@ #include <linux/proc_fs.h> #include <linux/kernel.h> #include <linux/syscalls.h> +#include <linux/stackprotector.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/delay.h> @@ -135,14 +136,14 @@ unsigned int __initdata setup_max_cpus = NR_CPUS; * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ -#ifndef CONFIG_X86_IO_APIC -static inline void disable_ioapic_setup(void) {}; -#endif + +void __weak arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; - disable_ioapic_setup(); + arch_disable_smp_support(); + return 0; } @@ -152,14 +153,14 @@ static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) - disable_ioapic_setup(); + arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); #else -#define setup_max_cpus NR_CPUS +const unsigned int setup_max_cpus = NR_CPUS; #endif /* @@ -539,6 +540,12 @@ asmlinkage void __init start_kernel(void) */ lockdep_init(); debug_objects_early_init(); + + /* + * Set up the the initial canary ASAP: + */ + boot_init_stack_canary(); + cgroup_init_early(); local_irq_disable(); diff --git a/ipc/shm.c b/ipc/shm.c index f8f69fad3a2..05d51d2a792 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -340,6 +340,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) struct file * file; char name[13]; int id; + int acctflag = 0; if (size < SHMMIN || size > ns->shm_ctlmax) return -EINVAL; @@ -364,11 +365,12 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) sprintf (name, "SYSV%08x", key); if (shmflg & SHM_HUGETLB) { - /* hugetlb_file_setup takes care of mlock user accounting */ - file = hugetlb_file_setup(name, size); + /* hugetlb_file_setup applies strict accounting */ + if (shmflg & SHM_NORESERVE) + acctflag = VM_NORESERVE; + file = hugetlb_file_setup(name, size, acctflag); shp->mlock_user = current_user(); } else { - int acctflag = 0; /* * Do not allow no accounting for OVERCOMMIT_NEVER, even * if it's asked for. diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5a54ff42874..e14db9c089b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2351,7 +2351,7 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root) for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; if (ss->root == root) - mutex_lock_nested(&ss->hierarchy_mutex, i); + mutex_lock(&ss->hierarchy_mutex); } } @@ -2637,6 +2637,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) BUG_ON(!list_empty(&init_task.tasks)); mutex_init(&ss->hierarchy_mutex); + lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key); ss->active = 1; } diff --git a/kernel/exit.c b/kernel/exit.c index f80dec3f187..167e1e3ad7c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -118,6 +118,8 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ + sig->utime = cputime_add(sig->utime, task_utime(tsk)); + sig->stime = cputime_add(sig->stime, task_stime(tsk)); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -126,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); + sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -977,12 +980,9 @@ static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); static int lowest_to_date = THREAD_SIZE; - unsigned long *n = end_of_stack(current); unsigned long free; - while (*n == 0) - n++; - free = (unsigned long)n - (unsigned long)end_of_stack(current); + free = stack_not_used(current); if (free >= lowest_to_date) return; diff --git a/kernel/fork.c b/kernel/fork.c index 6d5dbb7a13e..8de303bdd4e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -61,6 +61,7 @@ #include <linux/proc_fs.h> #include <linux/blkdev.h> #include <trace/sched.h> +#include <linux/magic.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -212,6 +213,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) { struct task_struct *tsk; struct thread_info *ti; + unsigned long *stackend; + int err; prepare_to_copy(orig); @@ -237,6 +240,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) goto out; setup_thread_stack(tsk, orig); + stackend = end_of_stack(tsk); + *stackend = STACK_END_MAGIC; /* for overflow detection */ #ifdef CONFIG_CC_STACKPROTECTOR tsk->stack_canary = get_random_int(); @@ -851,13 +856,14 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->tty_old_pgrp = NULL; sig->tty = NULL; - sig->cutime = sig->cstime = cputime_zero; + sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; task_io_accounting_init(&sig->ioac); + sig->sum_sched_runtime = 0; taskstats_tgid_init(sig); task_lock(current->group_leader); @@ -1094,7 +1100,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif - if (unlikely(ptrace_reparented(current))) + if (unlikely(current->ptrace)) ptrace_fork(p, clone_flags); /* Perform scheduler related setup. Assign this task to a CPU. */ diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 7de11bd64df..122fef4b0bd 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -46,7 +46,10 @@ void dynamic_irq_init(unsigned int irq) desc->irq_count = 0; desc->irqs_unhandled = 0; #ifdef CONFIG_SMP - cpumask_setall(&desc->affinity); + cpumask_setall(desc->affinity); +#ifdef CONFIG_GENERIC_PENDING_IRQ + cpumask_clear(desc->pending_mask); +#endif #endif spin_unlock_irqrestore(&desc->lock, flags); } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 3aba8d12f32..f51eaee921b 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -17,6 +17,7 @@ #include <linux/kernel_stat.h> #include <linux/rculist.h> #include <linux/hash.h> +#include <linux/bootmem.h> #include "internals.h" @@ -69,6 +70,7 @@ int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); #ifdef CONFIG_SPARSE_IRQ + static struct irq_desc irq_desc_init = { .irq = -1, .status = IRQ_DISABLED, @@ -76,9 +78,6 @@ static struct irq_desc irq_desc_init = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif }; void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) @@ -113,6 +112,10 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) printk(KERN_ERR "can not alloc kstat_irqs\n"); BUG_ON(1); } + if (!init_alloc_desc_masks(desc, cpu, false)) { + printk(KERN_ERR "can not alloc irq_desc cpumasks\n"); + BUG_ON(1); + } arch_init_chip_data(desc, cpu); } @@ -121,7 +124,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) */ DEFINE_SPINLOCK(sparse_irq_lock); -struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly; +struct irq_desc **irq_desc_ptrs __read_mostly; static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = { [0 ... NR_IRQS_LEGACY-1] = { @@ -131,14 +134,10 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif } }; -/* FIXME: use bootmem alloc ...*/ -static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS]; +static unsigned int *kstat_irqs_legacy; int __init early_irq_init(void) { @@ -148,18 +147,30 @@ int __init early_irq_init(void) init_irq_default_affinity(); + /* initialize nr_irqs based on nr_cpu_ids */ + arch_probe_nr_irqs(); + printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs); + desc = irq_desc_legacy; legacy_count = ARRAY_SIZE(irq_desc_legacy); + /* allocate irq_desc_ptrs array based on nr_irqs */ + irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *)); + + /* allocate based on nr_cpu_ids */ + /* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */ + kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids * + sizeof(int)); + for (i = 0; i < legacy_count; i++) { desc[i].irq = i; - desc[i].kstat_irqs = kstat_irqs_legacy[i]; + desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids; lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); - + init_alloc_desc_masks(&desc[i], 0, true); irq_desc_ptrs[i] = desc + i; } - for (i = legacy_count; i < NR_IRQS; i++) + for (i = legacy_count; i < nr_irqs; i++) irq_desc_ptrs[i] = NULL; return arch_early_irq_init(); @@ -167,7 +178,10 @@ int __init early_irq_init(void) struct irq_desc *irq_to_desc(unsigned int irq) { - return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL; + if (irq_desc_ptrs && irq < nr_irqs) + return irq_desc_ptrs[irq]; + + return NULL; } struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) @@ -176,10 +190,9 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) unsigned long flags; int node; - if (irq >= NR_IRQS) { - printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n", - irq, NR_IRQS); - WARN_ON(1); + if (irq >= nr_irqs) { + WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n", + irq, nr_irqs); return NULL; } @@ -221,9 +234,6 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif } }; @@ -235,12 +245,15 @@ int __init early_irq_init(void) init_irq_default_affinity(); + printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS); + desc = irq_desc; count = ARRAY_SIZE(irq_desc); - for (i = 0; i < count; i++) + for (i = 0; i < count; i++) { desc[i].irq = i; - + init_alloc_desc_masks(&desc[i], 0, true); + } return arch_early_irq_init(); } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index e6d0a43cc12..40416a81a0f 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -16,7 +16,14 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, extern struct lock_class_key irq_desc_lock_class; extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr); extern spinlock_t sparse_irq_lock; + +#ifdef CONFIG_SPARSE_IRQ +/* irq_desc_ptrs allocated at boot time */ +extern struct irq_desc **irq_desc_ptrs; +#else +/* irq_desc_ptrs is a fixed size array */ extern struct irq_desc *irq_desc_ptrs[NR_IRQS]; +#endif #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 291f0366455..a3a5dc9ef34 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -90,14 +90,14 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { - cpumask_copy(&desc->affinity, cpumask); + cpumask_copy(desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); } else { desc->status |= IRQ_MOVE_PENDING; - cpumask_copy(&desc->pending_mask, cpumask); + cpumask_copy(desc->pending_mask, cpumask); } #else - cpumask_copy(&desc->affinity, cpumask); + cpumask_copy(desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); #endif desc->status |= IRQ_AFFINITY_SET; @@ -119,16 +119,16 @@ int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc) * one of the targets is online. */ if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) { - if (cpumask_any_and(&desc->affinity, cpu_online_mask) + if (cpumask_any_and(desc->affinity, cpu_online_mask) < nr_cpu_ids) goto set_affinity; else desc->status &= ~IRQ_AFFINITY_SET; } - cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity); + cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity); set_affinity: - desc->chip->set_affinity(irq, &desc->affinity); + desc->chip->set_affinity(irq, desc->affinity); return 0; } diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index bd72329e630..e05ad9be43b 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -18,7 +18,7 @@ void move_masked_irq(int irq) desc->status &= ~IRQ_MOVE_PENDING; - if (unlikely(cpumask_empty(&desc->pending_mask))) + if (unlikely(cpumask_empty(desc->pending_mask))) return; if (!desc->chip->set_affinity) @@ -38,13 +38,13 @@ void move_masked_irq(int irq) * For correct operation this depends on the caller * masking the irqs. */ - if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask) + if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)) { - cpumask_and(&desc->affinity, - &desc->pending_mask, cpu_online_mask); - desc->chip->set_affinity(irq, &desc->affinity); + cpumask_and(desc->affinity, + desc->pending_mask, cpu_online_mask); + desc->chip->set_affinity(irq, desc->affinity); } - cpumask_clear(&desc->pending_mask); + cpumask_clear(desc->pending_mask); } void move_native_irq(int irq) diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index acd88356ac7..7f9b80434e3 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -38,15 +38,22 @@ static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc) old_desc->kstat_irqs = NULL; } -static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, +static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, struct irq_desc *desc, int cpu) { memcpy(desc, old_desc, sizeof(struct irq_desc)); + if (!init_alloc_desc_masks(desc, cpu, false)) { + printk(KERN_ERR "irq %d: can not get new irq_desc cpumask " + "for migration.\n", irq); + return false; + } spin_lock_init(&desc->lock); desc->cpu = cpu; lockdep_set_class(&desc->lock, &irq_desc_lock_class); init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids); + init_copy_desc_masks(old_desc, desc); arch_init_copy_chip_data(old_desc, desc, cpu); + return true; } static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc) @@ -76,12 +83,18 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, node = cpu_to_node(cpu); desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); if (!desc) { - printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq); + printk(KERN_ERR "irq %d: can not get new irq_desc " + "for migration.\n", irq); + /* still use old one */ + desc = old_desc; + goto out_unlock; + } + if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) { /* still use old one */ + kfree(desc); desc = old_desc; goto out_unlock; } - init_copy_one_irq_desc(irq, old_desc, desc, cpu); irq_desc_ptrs[irq] = desc; spin_unlock_irqrestore(&sparse_irq_lock, flags); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index aae3f742bce..692363dd591 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -20,11 +20,11 @@ static struct proc_dir_entry *root_irq_dir; static int irq_affinity_proc_show(struct seq_file *m, void *v) { struct irq_desc *desc = irq_to_desc((long)m->private); - const struct cpumask *mask = &desc->affinity; + const struct cpumask *mask = desc->affinity; #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PENDING) - mask = &desc->pending_mask; + mask = desc->pending_mask; #endif seq_cpumask(m, mask); seq_putc(m, '\n'); diff --git a/kernel/itimer.c b/kernel/itimer.c index 6a5fe93dd8b..58762f7077e 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -62,7 +62,7 @@ int do_getitimer(int which, struct itimerval *value) struct task_cputime cputime; cputime_t utime; - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); utime = cputime.utime; if (cputime_le(cval, utime)) { /* about to fire */ cval = jiffies_to_cputime(1); @@ -82,7 +82,7 @@ int do_getitimer(int which, struct itimerval *value) struct task_cputime times; cputime_t ptime; - thread_group_cputime(tsk, ×); + thread_group_cputimer(tsk, ×); ptime = cputime_add(times.utime, times.stime); if (cputime_le(cval, ptime)) { /* about to fire */ cval = jiffies_to_cputime(1); diff --git a/kernel/kexec.c b/kernel/kexec.c index 8a6d7b08864..795e7b67a22 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1130,7 +1130,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu) return; memset(&prstatus, 0, sizeof(prstatus)); prstatus.pr_pid = current->pid; - elf_core_copy_regs(&prstatus.pr_reg, regs); + elf_core_copy_kernel_regs(&prstatus.pr_reg, regs); buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, &prstatus, sizeof(prstatus)); final_note(buf); diff --git a/kernel/panic.c b/kernel/panic.c index 2a2ff36ff44..32fe4eff1b8 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -74,6 +74,9 @@ NORET_TYPE void panic(const char * fmt, ...) vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf); +#ifdef CONFIG_DEBUG_BUGVERBOSE + dump_stack(); +#endif bust_spinlocks(0); /* @@ -355,15 +358,18 @@ EXPORT_SYMBOL(warn_slowpath); #endif #ifdef CONFIG_CC_STACKPROTECTOR + /* * Called when gcc's -fstack-protector feature is used, and * gcc detects corruption of the on-stack canary value */ void __stack_chk_fail(void) { - panic("stack-protector: Kernel stack is corrupted"); + panic("stack-protector: Kernel stack is corrupted in: %p\n", + __builtin_return_address(0)); } EXPORT_SYMBOL(__stack_chk_fail); + #endif core_param(panic, panic_timeout, int, 0644); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index fa07da94d7b..2313a4cc14e 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -230,6 +230,71 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, return 0; } +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) +{ + struct sighand_struct *sighand; + struct signal_struct *sig; + struct task_struct *t; + + *times = INIT_CPUTIME; + + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + if (!sighand) + goto out; + + sig = tsk->signal; + + t = tsk; + do { + times->utime = cputime_add(times->utime, t->utime); + times->stime = cputime_add(times->stime, t->stime); + times->sum_exec_runtime += t->se.sum_exec_runtime; + + t = next_thread(t); + } while (t != tsk); + + times->utime = cputime_add(times->utime, sig->utime); + times->stime = cputime_add(times->stime, sig->stime); + times->sum_exec_runtime += sig->sum_sched_runtime; +out: + rcu_read_unlock(); +} + +static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b) +{ + if (cputime_gt(b->utime, a->utime)) + a->utime = b->utime; + + if (cputime_gt(b->stime, a->stime)) + a->stime = b->stime; + + if (b->sum_exec_runtime > a->sum_exec_runtime) + a->sum_exec_runtime = b->sum_exec_runtime; +} + +void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + struct task_cputime sum; + unsigned long flags; + + spin_lock_irqsave(&cputimer->lock, flags); + if (!cputimer->running) { + cputimer->running = 1; + /* + * The POSIX timer interface allows for absolute time expiry + * values through the TIMER_ABSTIME flag, therefore we have + * to synchronize the timer to the clock every time we start + * it. + */ + thread_group_cputime(tsk, &sum); + update_gt_cputime(&cputimer->cputime, &sum); + } + *times = cputimer->cputime; + spin_unlock_irqrestore(&cputimer->lock, flags); +} + /* * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. @@ -457,7 +522,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk) { struct task_cputime cputime; - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); cleanup_timers(tsk->signal->cpu_timers, cputime.utime, cputime.stime, cputime.sum_exec_runtime); } @@ -964,6 +1029,19 @@ static void check_thread_timers(struct task_struct *tsk, } } +static void stop_process_timers(struct task_struct *tsk) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + unsigned long flags; + + if (!cputimer->running) + return; + + spin_lock_irqsave(&cputimer->lock, flags); + cputimer->running = 0; + spin_unlock_irqrestore(&cputimer->lock, flags); +} + /* * Check for any per-thread CPU timers that have fired and move them * off the tsk->*_timers list onto the firing list. Per-thread timers @@ -987,13 +1065,15 @@ static void check_process_timers(struct task_struct *tsk, sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY && list_empty(&timers[CPUCLOCK_VIRT]) && cputime_eq(sig->it_virt_expires, cputime_zero) && - list_empty(&timers[CPUCLOCK_SCHED])) + list_empty(&timers[CPUCLOCK_SCHED])) { + stop_process_timers(tsk); return; + } /* * Collect the current process totals. */ - thread_group_cputime(tsk, &cputime); + thread_group_cputimer(tsk, &cputime); utime = cputime.utime; ptime = cputime_add(utime, cputime.stime); sum_sched_runtime = cputime.sum_exec_runtime; @@ -1259,7 +1339,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (!task_cputime_zero(&sig->cputime_expires)) { struct task_cputime group_sample; - thread_group_cputime(tsk, &group_sample); + thread_group_cputimer(tsk, &group_sample); if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; } @@ -1329,6 +1409,33 @@ void run_posix_cpu_timers(struct task_struct *tsk) } /* + * Sample a process (thread group) timer for the given group_leader task. + * Must be called with tasklist_lock held for reading. + */ +static int cpu_timer_sample_group(const clockid_t which_clock, + struct task_struct *p, + union cpu_time_count *cpu) +{ + struct task_cputime cputime; + + thread_group_cputimer(p, &cputime); + switch (CPUCLOCK_WHICH(which_clock)) { + default: + return -EINVAL; + case CPUCLOCK_PROF: + cpu->cpu = cputime_add(cputime.utime, cputime.stime); + break; + case CPUCLOCK_VIRT: + cpu->cpu = cputime.utime; + break; + case CPUCLOCK_SCHED: + cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); + break; + } + return 0; +} + +/* * Set one of the process-wide special case CPU timers. * The tsk->sighand->siglock must be held by the caller. * The *newval argument is relative and we update it to be absolute, *oldval @@ -1341,7 +1448,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); - cpu_clock_sample_group(clock_idx, tsk, &now); + cpu_timer_sample_group(clock_idx, tsk, &now); if (oldval) { if (!cputime_eq(*oldval, cputime_zero)) { diff --git a/kernel/profile.c b/kernel/profile.c index 784933acf5b..7724e0409ba 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -114,12 +114,15 @@ int __ref profile_init(void) if (!slab_is_available()) { prof_buffer = alloc_bootmem(buffer_bytes); alloc_bootmem_cpumask_var(&prof_cpu_mask); + cpumask_copy(prof_cpu_mask, cpu_possible_mask); return 0; } if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) return -ENOMEM; + cpumask_copy(prof_cpu_mask, cpu_possible_mask); + prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL); if (prof_buffer) return 0; diff --git a/kernel/sched.c b/kernel/sched.c index 8ee437a5ec1..61245b8d0f1 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2266,16 +2266,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) if (!sched_feat(SYNC_WAKEUPS)) sync = 0; - if (!sync) { - if (current->se.avg_overlap < sysctl_sched_migration_cost && - p->se.avg_overlap < sysctl_sched_migration_cost) - sync = 1; - } else { - if (current->se.avg_overlap >= sysctl_sched_migration_cost || - p->se.avg_overlap >= sysctl_sched_migration_cost) - sync = 0; - } - #ifdef CONFIG_SMP if (sched_feat(LB_WAKEUP_UPDATE)) { struct sched_domain *sd; @@ -3890,19 +3880,24 @@ int select_nohz_load_balancer(int stop_tick) int cpu = smp_processor_id(); if (stop_tick) { - cpumask_set_cpu(cpu, nohz.cpu_mask); cpu_rq(cpu)->in_nohz_recently = 1; - /* - * If we are going offline and still the leader, give up! - */ - if (!cpu_active(cpu) && - atomic_read(&nohz.load_balancer) == cpu) { + if (!cpu_active(cpu)) { + if (atomic_read(&nohz.load_balancer) != cpu) + return 0; + + /* + * If we are going offline and still the leader, + * give up! + */ if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) BUG(); + return 0; } + cpumask_set_cpu(cpu, nohz.cpu_mask); + /* time for ilb owner also to sleep */ if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { if (atomic_read(&nohz.load_balancer) == cpu) @@ -5949,12 +5944,7 @@ void sched_show_task(struct task_struct *p) printk(KERN_CONT " %016lx ", thread_saved_pc(p)); #endif #ifdef CONFIG_DEBUG_STACK_USAGE - { - unsigned long *n = end_of_stack(p); - while (!*n) - n++; - free = (unsigned long)n - (unsigned long)end_of_stack(p); - } + free = stack_not_used(p); #endif printk(KERN_CONT "%5lu %5d %6d\n", free, task_pid_nr(p), task_pid_nr(p->real_parent)); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a7e50ba185a..0566f2a03c4 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1191,15 +1191,20 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq, int idx, unsigned long load, unsigned long this_load, unsigned int imbalance) { + struct task_struct *curr = this_rq->curr; + struct task_group *tg; unsigned long tl = this_load; unsigned long tl_per_task; - struct task_group *tg; unsigned long weight; int balanced; if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) return 0; + if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost || + p->se.avg_overlap > sysctl_sched_migration_cost)) + sync = 0; + /* * If sync wakeup then subtract the (maximum possible) * effect of the currently running task from the load @@ -1426,7 +1431,9 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) if (!sched_feat(WAKEUP_PREEMPT)) return; - if (sched_feat(WAKEUP_OVERLAP) && sync) { + if (sched_feat(WAKEUP_OVERLAP) && (sync || + (se->avg_overlap < sysctl_sched_migration_cost && + pse->avg_overlap < sysctl_sched_migration_cost))) { resched_task(curr); return; } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index bac1061cea2..da932f4c852 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -960,12 +960,13 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu) static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); -static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask) +static inline int pick_optimal_cpu(int this_cpu, + const struct cpumask *mask) { int first; /* "this_cpu" is cheaper to preempt than a remote processor */ - if ((this_cpu != -1) && cpu_isset(this_cpu, *mask)) + if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask)) return this_cpu; first = cpumask_first(mask); @@ -981,6 +982,7 @@ static int find_lowest_rq(struct task_struct *task) struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask); int this_cpu = smp_processor_id(); int cpu = task_cpu(task); + cpumask_var_t domain_mask; if (task->rt.nr_cpus_allowed == 1) return -1; /* No other targets possible */ @@ -1013,19 +1015,25 @@ static int find_lowest_rq(struct task_struct *task) if (this_cpu == cpu) this_cpu = -1; /* Skip this_cpu opt if the same */ - for_each_domain(cpu, sd) { - if (sd->flags & SD_WAKE_AFFINE) { - cpumask_t domain_mask; - int best_cpu; + if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) { + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_AFFINE) { + int best_cpu; - cpumask_and(&domain_mask, sched_domain_span(sd), - lowest_mask); + cpumask_and(domain_mask, + sched_domain_span(sd), + lowest_mask); - best_cpu = pick_optimal_cpu(this_cpu, - &domain_mask); - if (best_cpu != -1) - return best_cpu; + best_cpu = pick_optimal_cpu(this_cpu, + domain_mask); + + if (best_cpu != -1) { + free_cpumask_var(domain_mask); + return best_cpu; + } + } } + free_cpumask_var(domain_mask); } /* diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 8ab0cef8eca..a8f93dd374e 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -296,19 +296,21 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) static inline void account_group_user_time(struct task_struct *tsk, cputime_t cputime) { - struct task_cputime *times; - struct signal_struct *sig; + struct thread_group_cputimer *cputimer; /* tsk == current, ensure it is safe to use ->signal */ if (unlikely(tsk->exit_state)) return; - sig = tsk->signal; - times = &sig->cputime.totals; + cputimer = &tsk->signal->cputimer; - spin_lock(×->lock); - times->utime = cputime_add(times->utime, cputime); - spin_unlock(×->lock); + if (!cputimer->running) + return; + + spin_lock(&cputimer->lock); + cputimer->cputime.utime = + cputime_add(cputimer->cputime.utime, cputime); + spin_unlock(&cputimer->lock); } /** @@ -324,19 +326,21 @@ static inline void account_group_user_time(struct task_struct *tsk, static inline void account_group_system_time(struct task_struct *tsk, cputime_t cputime) { - struct task_cputime *times; - struct signal_struct *sig; + struct thread_group_cputimer *cputimer; /* tsk == current, ensure it is safe to use ->signal */ if (unlikely(tsk->exit_state)) return; - sig = tsk->signal; - times = &sig->cputime.totals; + cputimer = &tsk->signal->cputimer; + + if (!cputimer->running) + return; - spin_lock(×->lock); - times->stime = cputime_add(times->stime, cputime); - spin_unlock(×->lock); + spin_lock(&cputimer->lock); + cputimer->cputime.stime = + cputime_add(cputimer->cputime.stime, cputime); + spin_unlock(&cputimer->lock); } /** @@ -352,7 +356,7 @@ static inline void account_group_system_time(struct task_struct *tsk, static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { - struct task_cputime *times; + struct thread_group_cputimer *cputimer; struct signal_struct *sig; sig = tsk->signal; @@ -361,9 +365,12 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, if (unlikely(!sig)) return; - times = &sig->cputime.totals; + cputimer = &sig->cputimer; + + if (!cputimer->running) + return; - spin_lock(×->lock); - times->sum_exec_runtime += ns; - spin_unlock(×->lock); + spin_lock(&cputimer->lock); + cputimer->cputime.sum_exec_runtime += ns; + spin_unlock(&cputimer->lock); } diff --git a/kernel/signal.c b/kernel/signal.c index b6b36768b75..2a74fe87c0d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1367,7 +1367,6 @@ int do_notify_parent(struct task_struct *tsk, int sig) struct siginfo info; unsigned long flags; struct sighand_struct *psig; - struct task_cputime cputime; int ret = sig; BUG_ON(sig == -1); @@ -1397,9 +1396,10 @@ int do_notify_parent(struct task_struct *tsk, int sig) info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); - thread_group_cputime(tsk, &cputime); - info.si_utime = cputime_to_jiffies(cputime.utime); - info.si_stime = cputime_to_jiffies(cputime.stime); + info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime, + tsk->signal->utime)); + info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime, + tsk->signal->stime)); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) diff --git a/kernel/softirq.c b/kernel/softirq.c index bdbe9de9cd8..0365b4899a3 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -795,6 +795,11 @@ int __init __weak early_irq_init(void) return 0; } +int __init __weak arch_probe_nr_irqs(void) +{ + return 0; +} + int __init __weak arch_early_irq_init(void) { return 0; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 790f9d78566..c5ef44ff850 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -101,6 +101,7 @@ static int two = 2; static int zero; static int one = 1; +static unsigned long one_ul = 1; static int one_hundred = 100; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ @@ -974,7 +975,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &dirty_background_bytes_handler, .strategy = &sysctl_intvec, - .extra1 = &one, + .extra1 = &one_ul, }, { .ctl_name = VM_DIRTY_RATIO, @@ -995,7 +996,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &dirty_bytes_handler, .strategy = &sysctl_intvec, - .extra1 = &one, + .extra1 = &one_ul, }, { .procname = "dirty_writeback_centisecs", diff --git a/mm/fremap.c b/mm/fremap.c index 736ba7f3306..b6ec85abbb3 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -198,7 +198,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; get_file(file); addr = mmap_region(file, start, size, - flags, vma->vm_flags, pgoff, 1); + flags, vma->vm_flags, pgoff); fput(file); if (IS_ERR_VALUE(addr)) { err = addr; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 618e9830408..107da3d809a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2269,12 +2269,18 @@ void hugetlb_change_protection(struct vm_area_struct *vma, int hugetlb_reserve_pages(struct inode *inode, long from, long to, - struct vm_area_struct *vma) + struct vm_area_struct *vma, + int acctflag) { long ret, chg; struct hstate *h = hstate_inode(inode); - if (vma && vma->vm_flags & VM_NORESERVE) + /* + * Only apply hugepage reservation if asked. At fault time, an + * attempt will be made for VM_NORESERVE to allocate a page + * and filesystem quota without using reserves + */ + if (acctflag & VM_NORESERVE) return 0; /* @@ -2299,13 +2305,31 @@ int hugetlb_reserve_pages(struct inode *inode, if (chg < 0) return chg; + /* There must be enough filesystem quota for the mapping */ if (hugetlb_get_quota(inode->i_mapping, chg)) return -ENOSPC; + + /* + * Check enough hugepages are available for the reservation. + * Hand back the quota if there are not + */ ret = hugetlb_acct_memory(h, chg); if (ret < 0) { hugetlb_put_quota(inode->i_mapping, chg); return ret; } + + /* + * Account for the reservations made. Shared mappings record regions + * that have reservations as they are shared by multiple VMAs. + * When the last VMA disappears, the region map says how much + * the reservation was and the page cache tells how much of + * the reservation was consumed. Private mappings are per-VMA and + * only the consumed reservations are tracked. When the VMA + * disappears, the original reservation is the VMA size and the + * consumed reservations are stored in the map. Hence, nothing + * else has to be done for private mappings here + */ if (!vma || vma->vm_flags & VM_SHARED) region_add(&inode->i_mapping->private_list, from, to); return 0; diff --git a/mm/migrate.c b/mm/migrate.c index 2bb4e1d6352..a9eff3f092f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1129,7 +1129,7 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, struct vm_area_struct *vma; int err = 0; - for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) { + for (vma = mm->mmap; vma && !err; vma = vma->vm_next) { if (vma->vm_ops && vma->vm_ops->migrate) { err = vma->vm_ops->migrate(vma, to, from, flags); if (err) diff --git a/mm/mlock.c b/mm/mlock.c index 028ec482fdd..037161d61b4 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -311,7 +311,10 @@ long mlock_vma_pages_range(struct vm_area_struct *vma, is_vm_hugetlb_page(vma) || vma == get_gate_vma(current))) { - return __mlock_vma_pages_range(vma, start, end, 1); + __mlock_vma_pages_range(vma, start, end, 1); + + /* Hide errors from mmap() and other callers */ + return 0; } /* diff --git a/mm/mmap.c b/mm/mmap.c index 214b6a258ee..00ced3ee49a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -918,7 +918,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, struct inode *inode; unsigned int vm_flags; int error; - int accountable = 1; unsigned long reqprot = prot; /* @@ -1019,8 +1018,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, return -EPERM; vm_flags &= ~VM_MAYEXEC; } - if (is_file_hugepages(file)) - accountable = 0; if (!file->f_op || !file->f_op->mmap) return -ENODEV; @@ -1053,8 +1050,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (error) return error; - return mmap_region(file, addr, len, flags, vm_flags, pgoff, - accountable); + return mmap_region(file, addr, len, flags, vm_flags, pgoff); } EXPORT_SYMBOL(do_mmap_pgoff); @@ -1092,17 +1088,23 @@ int vma_wants_writenotify(struct vm_area_struct *vma) /* * We account for memory if it's a private writeable mapping, - * and VM_NORESERVE wasn't set. + * not hugepages and VM_NORESERVE wasn't set. */ -static inline int accountable_mapping(unsigned int vm_flags) +static inline int accountable_mapping(struct file *file, unsigned int vm_flags) { + /* + * hugetlb has its own accounting separate from the core VM + * VM_HUGETLB may not be set yet so we cannot check for that flag. + */ + if (file && is_file_hugepages(file)) + return 0; + return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, - unsigned int vm_flags, unsigned long pgoff, - int accountable) + unsigned int vm_flags, unsigned long pgoff) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; @@ -1128,18 +1130,22 @@ munmap_back: /* * Set 'VM_NORESERVE' if we should not account for the - * memory use of this mapping. We only honor MAP_NORESERVE - * if we're allowed to overcommit memory. + * memory use of this mapping. */ - if ((flags & MAP_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) - vm_flags |= VM_NORESERVE; - if (!accountable) - vm_flags |= VM_NORESERVE; + if ((flags & MAP_NORESERVE)) { + /* We honor MAP_NORESERVE if allowed to overcommit */ + if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) + vm_flags |= VM_NORESERVE; + + /* hugetlb applies strict overcommit unless MAP_NORESERVE */ + if (file && is_file_hugepages(file)) + vm_flags |= VM_NORESERVE; + } /* * Private writable mapping: check memory availability */ - if (accountable_mapping(vm_flags)) { + if (accountable_mapping(file, vm_flags)) { charged = len >> PAGE_SHIFT; if (security_vm_enough_memory(charged)) return -ENOMEM; @@ -2078,12 +2084,8 @@ void exit_mmap(struct mm_struct *mm) unsigned long end; /* mm's last user has gone, and its about to be pulled down */ - arch_exit_mmap(mm); mmu_notifier_release(mm); - if (!mm->mmap) /* Can happen if dup_mmap() received an OOM */ - return; - if (mm->locked_vm) { vma = mm->mmap; while (vma) { @@ -2092,7 +2094,13 @@ void exit_mmap(struct mm_struct *mm) vma = vma->vm_next; } } + + arch_exit_mmap(mm); + vma = mm->mmap; + if (!vma) /* Can happen if dup_mmap() received an OOM */ + return; + lru_add_drain(); flush_cache_mm(mm); tlb = tlb_gather_mmu(mm, 1); diff --git a/mm/mprotect.c b/mm/mprotect.c index abe2694e13f..258197b76fb 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -151,10 +151,11 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, /* * If we make a private mapping writable we increase our commit; * but (without finer accounting) cannot reduce our commit if we - * make it unwritable again. + * make it unwritable again. hugetlb mapping were accounted for + * even if read-only so there is no need to account for them here */ if (newflags & VM_WRITE) { - if (!(oldflags & (VM_ACCOUNT|VM_WRITE| + if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB| VM_SHARED|VM_NORESERVE))) { charged = nrpages; if (security_vm_enough_memory(charged)) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index dc32dae01e5..3c84128596b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -209,7 +209,7 @@ int dirty_bytes_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { - int old_bytes = vm_dirty_bytes; + unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos); @@ -1051,20 +1051,23 @@ continue_unlock: } } - if (nr_to_write > 0) + if (nr_to_write > 0) { nr_to_write--; - else if (wbc->sync_mode == WB_SYNC_NONE) { - /* - * We stop writing back only if we are not - * doing integrity sync. In case of integrity - * sync we have to keep going because someone - * may be concurrently dirtying pages, and we - * might have synced a lot of newly appeared - * dirty pages, but have not synced all of the - * old dirty pages. - */ - done = 1; - break; + if (nr_to_write == 0 && + wbc->sync_mode == WB_SYNC_NONE) { + /* + * We stop writing back only if we are + * not doing integrity sync. In case of + * integrity sync we have to keep going + * because someone may be concurrently + * dirtying pages, and we might have + * synced a lot of newly appeared dirty + * pages, but have not synced all of the + * old dirty pages. + */ + done = 1; + break; + } } if (wbc->nonblocking && bdi_write_congested(bdi)) { @@ -1076,7 +1079,7 @@ continue_unlock: pagevec_release(&pvec); cond_resched(); } - if (!cycled) { + if (!cycled && !done) { /* * range_cyclic: * We hit the last page and there is more work to be done: wrap diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 7006a11350c..ceecfbb143f 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -114,7 +114,8 @@ static int __init_refok init_section_page_cgroup(unsigned long pfn) nid = page_to_nid(pfn_to_page(pfn)); table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION; if (slab_is_available()) { - base = kmalloc_node(table_size, GFP_KERNEL, nid); + base = kmalloc_node(table_size, + GFP_KERNEL | __GFP_NOWARN, nid); if (!base) base = vmalloc_node(table_size, nid); } else { diff --git a/mm/rmap.c b/mm/rmap.c index ac4af8cffbf..16521664010 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1072,7 +1072,8 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration) spin_lock(&mapping->i_mmap_lock); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { if (MLOCK_PAGES && unlikely(unlock)) { - if (!(vma->vm_flags & VM_LOCKED)) + if (!((vma->vm_flags & VM_LOCKED) && + page_mapped_in_vma(page, vma))) continue; /* must visit all vmas */ ret = SWAP_MLOCK; } else { diff --git a/mm/slab.c b/mm/slab.c index ddc41f337d5..4d00855629c 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4457,3 +4457,4 @@ size_t ksize(const void *objp) return obj_size(virt_to_cache(objp)); } +EXPORT_SYMBOL(ksize); diff --git a/mm/slob.c b/mm/slob.c index bf7e8fc3aed..52bc8a2bd9e 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -521,6 +521,7 @@ size_t ksize(const void *block) } else return sp->page.private; } +EXPORT_SYMBOL(ksize); struct kmem_cache { unsigned int size, align; diff --git a/mm/slub.c b/mm/slub.c index bdc9abb08a2..0280eee6cf3 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2736,6 +2736,7 @@ size_t ksize(const void *object) */ return s->size; } +EXPORT_SYMBOL(ksize); void kfree(const void *x) { diff --git a/net/9p/protocol.c b/net/9p/protocol.c index dcd7666824b..fc70147c771 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -29,6 +29,7 @@ #include <linux/errno.h> #include <linux/uaccess.h> #include <linux/sched.h> +#include <linux/types.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include "protocol.h" @@ -160,29 +161,32 @@ p9pdu_vreadf(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap) break; case 'w':{ int16_t *val = va_arg(ap, int16_t *); - if (pdu_read(pdu, val, sizeof(*val))) { + __le16 le_val; + if (pdu_read(pdu, &le_val, sizeof(le_val))) { errcode = -EFAULT; break; } - *val = cpu_to_le16(*val); + *val = le16_to_cpu(le_val); } break; case 'd':{ int32_t *val = va_arg(ap, int32_t *); - if (pdu_read(pdu, val, sizeof(*val))) { + __le32 le_val; + if (pdu_read(pdu, &le_val, sizeof(le_val))) { errcode = -EFAULT; break; } - *val = cpu_to_le32(*val); + *val = le32_to_cpu(le_val); } break; case 'q':{ int64_t *val = va_arg(ap, int64_t *); - if (pdu_read(pdu, val, sizeof(*val))) { + __le64 le_val; + if (pdu_read(pdu, &le_val, sizeof(le_val))) { errcode = -EFAULT; break; } - *val = cpu_to_le64(*val); + *val = le64_to_cpu(le_val); } break; case 's':{ @@ -362,19 +366,19 @@ p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap) } break; case 'w':{ - int16_t val = va_arg(ap, int); + __le16 val = cpu_to_le16(va_arg(ap, int)); if (pdu_write(pdu, &val, sizeof(val))) errcode = -EFAULT; } break; case 'd':{ - int32_t val = va_arg(ap, int32_t); + __le32 val = cpu_to_le32(va_arg(ap, int32_t)); if (pdu_write(pdu, &val, sizeof(val))) errcode = -EFAULT; } break; case 'q':{ - int64_t val = va_arg(ap, int64_t); + __le64 val = cpu_to_le64(va_arg(ap, int64_t)); if (pdu_write(pdu, &val, sizeof(val))) errcode = -EFAULT; } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index bdd9ccea17c..d2c27c808d3 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -67,6 +67,11 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) { struct net_device *indev; + if (skb_warn_if_lro(skb)) { + kfree_skb(skb); + return; + } + indev = skb->dev; skb->dev = to->dev; skb_forward_csum(skb); @@ -89,7 +94,7 @@ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) /* called with rcu_read_lock */ void br_forward(const struct net_bridge_port *to, struct sk_buff *skb) { - if (!skb_warn_if_lro(skb) && should_deliver(to, skb)) { + if (should_deliver(to, skb)) { __br_forward(to, skb); return; } diff --git a/net/core/dev.c b/net/core/dev.c index 5379b0c1190..a17e0066236 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1090,7 +1090,7 @@ int dev_open(struct net_device *dev) /* * Enable NET_DMA */ - dmaengine_get(); + net_dmaengine_get(); /* * Initialize multicasting status @@ -1172,7 +1172,7 @@ int dev_close(struct net_device *dev) /* * Shutdown NET_DMA */ - dmaengine_put(); + net_dmaengine_put(); return 0; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f66c58df895..278a142d104 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1994,8 +1994,8 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) if (!net_eq(neigh_parms_net(p), net)) continue; - if (nidx++ < neigh_skip) - continue; + if (nidx < neigh_skip) + goto next; if (neightbl_fill_param_info(skb, tbl, p, NETLINK_CB(cb->skb).pid, @@ -2003,6 +2003,8 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) goto out; + next: + nidx++; } neigh_skip = 0; @@ -2082,12 +2084,10 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (h > s_h) s_idx = 0; for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { - int lidx; if (dev_net(n->dev) != net) continue; - lidx = idx++; - if (lidx < s_idx) - continue; + if (idx < s_idx) + goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, @@ -2096,6 +2096,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, rc = -1; goto out; } + next: + idx++; } } read_unlock_bh(&tbl->lock); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cc3a0a06c00..c47c989cb1f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1234,8 +1234,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct udphdr *uh; unsigned short ulen; struct rtable *rt = (struct rtable*)skb->dst; - __be32 saddr = ip_hdr(skb)->saddr; - __be32 daddr = ip_hdr(skb)->daddr; + __be32 saddr, daddr; struct net *net = dev_net(skb->dev); /* @@ -1259,6 +1258,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; + saddr = ip_hdr(skb)->saddr; + daddr = ip_hdr(skb)->daddr; + if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) return __udp4_lib_mcast_deliver(net, skb, uh, saddr, daddr, udptable); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index c62dd247774..7712578bdc6 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -323,17 +323,21 @@ static struct ip6_flowlabel * fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, int optlen, int *err_p) { - struct ip6_flowlabel *fl; + struct ip6_flowlabel *fl = NULL; int olen; int addr_type; int err; + olen = optlen - CMSG_ALIGN(sizeof(*freq)); + err = -EINVAL; + if (olen > 64 * 1024) + goto done; + err = -ENOMEM; fl = kzalloc(sizeof(*fl), GFP_KERNEL); if (fl == NULL) goto done; - olen = optlen - CMSG_ALIGN(sizeof(*freq)); if (olen > 0) { struct msghdr msg; struct flowi flowi; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 58e2b0d9375..d994c55a5b1 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -249,8 +249,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) } t = netdev_priv(dev); - ip6_tnl_dev_init(dev); t->parms = *p; + ip6_tnl_dev_init(dev); if ((err = register_netdevice(dev)) < 0) goto failed_free; diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index c455cf4ee75..c323643ffcf 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -49,8 +49,19 @@ static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, static const u_int8_t invmap[] = { [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, - [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_QUERY + 1, - [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_REPLY +1 + [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, + [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY +1 +}; + +static const u_int8_t noct_valid_new[] = { + [ICMPV6_MGM_QUERY - 130] = 1, + [ICMPV6_MGM_REPORT -130] = 1, + [ICMPV6_MGM_REDUCTION - 130] = 1, + [NDISC_ROUTER_SOLICITATION - 130] = 1, + [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, + [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, + [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, + [ICMPV6_MLD2_REPORT - 130] = 1 }; static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, @@ -178,6 +189,7 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, { const struct icmp6hdr *icmp6h; struct icmp6hdr _ih; + int type; icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmp6h == NULL) { @@ -194,6 +206,15 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, return -NF_ACCEPT; } + type = icmp6h->icmp6_type - 130; + if (type >= 0 && type < sizeof(noct_valid_new) && + noct_valid_new[type]) { + skb->nfct = &nf_conntrack_untracked.ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); + return NF_ACCEPT; + } + /* is not error message ? */ if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c32a7e8e3a1..cb78aa00399 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -434,7 +434,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, } else return NOTIFY_DONE; - if (!nfnetlink_has_listeners(group)) + if (!item->report && !nfnetlink_has_listeners(group)) return NOTIFY_DONE; skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); @@ -1215,6 +1215,16 @@ ctnetlink_create_conntrack(struct nlattr *cda[], } } +#ifdef CONFIG_NF_NAT_NEEDED + if (cda[CTA_NAT_SEQ_ADJ_ORIG] || cda[CTA_NAT_SEQ_ADJ_REPLY]) { + err = ctnetlink_change_nat_seq_adj(ct, cda); + if (err < 0) { + rcu_read_unlock(); + goto err; + } + } +#endif + if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) { @@ -1492,7 +1502,8 @@ static int ctnetlink_expect_event(struct notifier_block *this, } else return NOTIFY_DONE; - if (!nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW)) + if (!item->report && + !nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW)) return NOTIFY_DONE; skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index e223cb43ae8..a189ada9128 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -105,7 +105,7 @@ match_packet(const struct sk_buff *skb, switch (chunk_match_type) { case SCTP_CHUNK_MATCH_ALL: - return SCTP_CHUNKMAP_IS_CLEAR(info->chunkmap); + return SCTP_CHUNKMAP_IS_CLEAR(chunkmapcopy); case SCTP_CHUNK_MATCH_ANY: return false; case SCTP_CHUNK_MATCH_ONLY: diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d7d2bed7a69..eac5e7bb736 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -284,13 +284,13 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, if (IS_ERR(trans)) { call = ERR_CAST(trans); trans = NULL; - goto out; + goto out_notrans; } } else { trans = rx->trans; if (!trans) { call = ERR_PTR(-ENOTCONN); - goto out; + goto out_notrans; } atomic_inc(&trans->usage); } @@ -315,6 +315,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, rxrpc_put_bundle(trans, bundle); out: rxrpc_put_transport(trans); +out_notrans: release_sock(&rx->sk); _leave(" = %p", call); return call; diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh new file mode 100644 index 00000000000..29493dc4528 --- /dev/null +++ b/scripts/gcc-x86_32-has-stack-protector.sh @@ -0,0 +1,8 @@ +#!/bin/sh + +echo "int foo(void) { char X[200]; return 3; }" | $* -S -xc -c -O0 -fstack-protector - -o - 2> /dev/null | grep -q "%gs" +if [ "$?" -eq "0" ] ; then + echo y +else + echo n +fi diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh index 325c0a1b03b..afaec618b39 100644 --- a/scripts/gcc-x86_64-has-stack-protector.sh +++ b/scripts/gcc-x86_64-has-stack-protector.sh @@ -1,6 +1,8 @@ #!/bin/sh -echo "int foo(void) { char X[200]; return 3; }" | $1 -S -xc -c -O0 -mcmodel=kernel -fstack-protector - -o - 2> /dev/null | grep -q "%gs" +echo "int foo(void) { char X[200]; return 3; }" | $* -S -xc -c -O0 -mcmodel=kernel -fstack-protector - -o - 2> /dev/null | grep -q "%gs" if [ "$?" -eq "0" ] ; then - echo $2 + echo y +else + echo n fi diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 8bb83a100ed..0f11870116d 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1827,6 +1827,40 @@ sub reset_state { $state = 0; } +sub syscall_munge() { + my $void = 0; + + $prototype =~ s@[\r\n\t]+@ @gos; # strip newlines/CR's/tabs +## if ($prototype =~ m/SYSCALL_DEFINE0\s*\(\s*(a-zA-Z0-9_)*\s*\)/) { + if ($prototype =~ m/SYSCALL_DEFINE0/) { + $void = 1; +## $prototype = "long sys_$1(void)"; + } + + $prototype =~ s/SYSCALL_DEFINE.*\(/long sys_/; # fix return type & func name + if ($prototype =~ m/long (sys_.*?),/) { + $prototype =~ s/,/\(/; + } elsif ($void) { + $prototype =~ s/\)/\(void\)/; + } + + # now delete all of the odd-number commas in $prototype + # so that arg types & arg names don't have a comma between them + my $count = 0; + my $len = length($prototype); + if ($void) { + $len = 0; # skip the for-loop + } + for (my $ix = 0; $ix < $len; $ix++) { + if (substr($prototype, $ix, 1) eq ',') { + $count++; + if ($count % 2 == 1) { + substr($prototype, $ix, 1) = ' '; + } + } + } +} + sub process_state3_function($$) { my $x = shift; my $file = shift; @@ -1839,11 +1873,15 @@ sub process_state3_function($$) { elsif ($x =~ /([^\{]*)/) { $prototype .= $1; } + if (($x =~ /\{/) || ($x =~ /\#\s*define/) || ($x =~ /;/)) { $prototype =~ s@/\*.*?\*/@@gos; # strip comments. $prototype =~ s@[\r\n]+@ @gos; # strip newlines/cr's. $prototype =~ s@^\s+@@gos; # strip leading spaces - dump_function($prototype,$file); + if ($prototype =~ /SYSCALL_DEFINE/) { + syscall_munge(); + } + dump_function($prototype, $file); reset_state(); } } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 88921611b22..7e62303133d 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -415,8 +415,9 @@ static int parse_elf(struct elf_info *info, const char *filename) const char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; const char *secname; + int nobits = sechdrs[i].sh_type == SHT_NOBITS; - if (sechdrs[i].sh_offset > info->size) { + if (!nobits && sechdrs[i].sh_offset > info->size) { fatal("%s is truncated. sechdrs[i].sh_offset=%lu > " "sizeof(*hrd)=%zu\n", filename, (unsigned long)sechdrs[i].sh_offset, @@ -425,6 +426,8 @@ static int parse_elf(struct elf_info *info, const char *filename) } secname = secstrings + sechdrs[i].sh_name; if (strcmp(secname, ".modinfo") == 0) { + if (nobits) + fatal("%s has NOBITS .modinfo\n", filename); info->modinfo = (void *)hdr + sechdrs[i].sh_offset; info->modinfo_len = sechdrs[i].sh_size; } else if (strcmp(secname, "__ksymtab") == 0) diff --git a/sound/arm/aaci.c b/sound/arm/aaci.c index 89096e811a4..772901e41ec 100644 --- a/sound/arm/aaci.c +++ b/sound/arm/aaci.c @@ -90,7 +90,7 @@ static void aaci_ac97_write(struct snd_ac97 *ac97, unsigned short reg, */ do { v = readl(aaci->base + AACI_SLFR); - } while ((v & (SLFR_1TXB|SLFR_2TXB)) && timeout--); + } while ((v & (SLFR_1TXB|SLFR_2TXB)) && --timeout); if (!timeout) dev_err(&aaci->dev->dev, @@ -126,7 +126,7 @@ static unsigned short aaci_ac97_read(struct snd_ac97 *ac97, unsigned short reg) */ do { v = readl(aaci->base + AACI_SLFR); - } while ((v & SLFR_1TXB) && timeout--); + } while ((v & SLFR_1TXB) && --timeout); if (!timeout) { dev_err(&aaci->dev->dev, "timeout on slot 1 TX busy\n"); @@ -147,7 +147,7 @@ static unsigned short aaci_ac97_read(struct snd_ac97 *ac97, unsigned short reg) do { cond_resched(); v = readl(aaci->base + AACI_SLFR) & (SLFR_1RXV|SLFR_2RXV); - } while ((v != (SLFR_1RXV|SLFR_2RXV)) && timeout--); + } while ((v != (SLFR_1RXV|SLFR_2RXV)) && --timeout); if (!timeout) { dev_err(&aaci->dev->dev, "timeout on RX valid\n"); diff --git a/sound/drivers/Kconfig b/sound/drivers/Kconfig index 0bcf14640fd..84714a65e5c 100644 --- a/sound/drivers/Kconfig +++ b/sound/drivers/Kconfig @@ -33,7 +33,7 @@ if SND_DRIVERS config SND_PCSP tristate "PC-Speaker support (READ HELP!)" - depends on PCSPKR_PLATFORM && X86_PC && HIGH_RES_TIMERS + depends on PCSPKR_PLATFORM && X86 && HIGH_RES_TIMERS depends on INPUT depends on EXPERIMENTAL select SND_PCM |