diff options
Diffstat (limited to 'arch/x86/kernel')
45 files changed, 1272 insertions, 1124 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index ef28c210ebf..3d4346a73a8 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -6,11 +6,13 @@ extra-y := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinu CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) -ifdef CONFIG_FTRACE +ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg +CFLAGS_REMOVE_ftrace.o = -pg +CFLAGS_REMOVE_early_printk.o = -pg endif # @@ -40,7 +42,7 @@ obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o obj-y += process.o obj-y += i387.o xsave.o obj-y += ptrace.o -obj-y += ds.o +obj-$(CONFIG_X86_DS) += ds.o obj-$(CONFIG_X86_32) += tls.o obj-$(CONFIG_IA32_EMULATION) += tls.o obj-y += step.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8c1f76abae9..4c51a2f8fd3 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1343,7 +1343,6 @@ static void __init acpi_process_madt(void) error = acpi_parse_madt_ioapic_entries(); if (!error) { acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC; - acpi_irq_balance_set(NULL); acpi_ioapic = 1; smp_found_config = 1; diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index a8fd9ebdc8e..5662e226b0c 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -50,7 +50,7 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom, /* returns !0 if the IOMMU is caching non-present entries in its TLB */ static int iommu_has_npcache(struct amd_iommu *iommu) { - return iommu->cap & IOMMU_CAP_NPCACHE; + return iommu->cap & (1UL << IOMMU_CAP_NPCACHE); } /**************************************************************************** @@ -187,6 +187,8 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) spin_lock_irqsave(&iommu->lock, flags); ret = __iommu_queue_command(iommu, cmd); + if (!ret) + iommu->need_sync = 1; spin_unlock_irqrestore(&iommu->lock, flags); return ret; @@ -210,10 +212,13 @@ static int iommu_completion_wait(struct amd_iommu *iommu) cmd.data[0] = CMD_COMPL_WAIT_INT_MASK; CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT); - iommu->need_sync = 0; - spin_lock_irqsave(&iommu->lock, flags); + if (!iommu->need_sync) + goto out; + + iommu->need_sync = 0; + ret = __iommu_queue_command(iommu, &cmd); if (ret) @@ -254,8 +259,6 @@ static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid) ret = iommu_queue_command(iommu, &cmd); - iommu->need_sync = 1; - return ret; } @@ -281,8 +284,6 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu, ret = iommu_queue_command(iommu, &cmd); - iommu->need_sync = 1; - return ret; } @@ -536,6 +537,9 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom, { address >>= PAGE_SHIFT; iommu_area_free(dom->bitmap, address, pages); + + if (address >= dom->next_bit) + dom->need_flush = true; } /**************************************************************************** @@ -759,8 +763,6 @@ static void set_device_domain(struct amd_iommu *iommu, write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); iommu_queue_inv_dev_entry(iommu, devid); - - iommu->need_sync = 1; } /***************************************************************************** @@ -855,6 +857,9 @@ static int get_device_resources(struct device *dev, print_devid(_bdf, 1); } + if (domain_for_device(_bdf) == NULL) + set_device_domain(*iommu, *domain, _bdf); + return 1; } @@ -992,8 +997,10 @@ static void __unmap_single(struct amd_iommu *iommu, dma_ops_free_addresses(dma_dom, dma_addr, pages); - if (amd_iommu_unmap_flush) + if (amd_iommu_unmap_flush || dma_dom->need_flush) { iommu_flush_pages(iommu, dma_dom->domain.id, dma_addr, size); + dma_dom->need_flush = false; + } } /* @@ -1026,8 +1033,7 @@ static dma_addr_t map_single(struct device *dev, phys_addr_t paddr, if (addr == bad_dma_address) goto out; - if (unlikely(iommu->need_sync)) - iommu_completion_wait(iommu); + iommu_completion_wait(iommu); out: spin_unlock_irqrestore(&domain->lock, flags); @@ -1055,8 +1061,7 @@ static void unmap_single(struct device *dev, dma_addr_t dma_addr, __unmap_single(iommu, domain->priv, dma_addr, size, dir); - if (unlikely(iommu->need_sync)) - iommu_completion_wait(iommu); + iommu_completion_wait(iommu); spin_unlock_irqrestore(&domain->lock, flags); } @@ -1122,8 +1127,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, goto unmap; } - if (unlikely(iommu->need_sync)) - iommu_completion_wait(iommu); + iommu_completion_wait(iommu); out: spin_unlock_irqrestore(&domain->lock, flags); @@ -1168,8 +1172,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist, s->dma_address = s->dma_length = 0; } - if (unlikely(iommu->need_sync)) - iommu_completion_wait(iommu); + iommu_completion_wait(iommu); spin_unlock_irqrestore(&domain->lock, flags); } @@ -1220,8 +1223,7 @@ static void *alloc_coherent(struct device *dev, size_t size, goto out; } - if (unlikely(iommu->need_sync)) - iommu_completion_wait(iommu); + iommu_completion_wait(iommu); out: spin_unlock_irqrestore(&domain->lock, flags); @@ -1252,8 +1254,7 @@ static void free_coherent(struct device *dev, size_t size, __unmap_single(iommu, domain->priv, dma_addr, size, DMA_BIDIRECTIONAL); - if (unlikely(iommu->need_sync)) - iommu_completion_wait(iommu); + iommu_completion_wait(iommu); spin_unlock_irqrestore(&domain->lock, flags); diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 0cdcda35a05..30ae2701b3d 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -121,7 +121,7 @@ u16 amd_iommu_last_bdf; /* largest PCI device id we have LIST_HEAD(amd_iommu_unity_map); /* a list of required unity mappings we find in ACPI */ unsigned amd_iommu_aperture_order = 26; /* size of aperture in power of 2 */ -int amd_iommu_isolate; /* if 1, device isolation is enabled */ +int amd_iommu_isolate = 1; /* if 1, device isolation is enabled */ bool amd_iommu_unmap_flush; /* if true, flush on every unmap */ LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the @@ -1213,7 +1213,9 @@ static int __init parse_amd_iommu_options(char *str) for (; *str; ++str) { if (strncmp(str, "isolate", 7) == 0) amd_iommu_isolate = 1; - if (strncmp(str, "fullflush", 11) == 0) + if (strncmp(str, "share", 5) == 0) + amd_iommu_isolate = 0; + if (strncmp(str, "fullflush", 9) == 0) amd_iommu_unmap_flush = true; } diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c index 04a7f960bbc..16f94879b52 100644 --- a/arch/x86/kernel/apic.c +++ b/arch/x86/kernel/apic.c @@ -1315,7 +1315,7 @@ void enable_x2apic(void) } } -void enable_IR_x2apic(void) +void __init enable_IR_x2apic(void) { #ifdef CONFIG_INTR_REMAP int ret; diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index 0d9c993aa93..ef8f831af82 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -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_SMP +#ifdef CONFIG_X86_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; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 25581dcb280..b9c9ea0217a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -20,6 +20,7 @@ #include <asm/pat.h> #include <asm/asm.h> #include <asm/numa.h> +#include <asm/smp.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/mpspec.h> #include <asm/apic.h> @@ -549,6 +550,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_early_init(c); validate_pat_support(c); + +#ifdef CONFIG_SMP + c->cpu_index = boot_cpu_id; +#endif } void __init early_cpu_init(void) @@ -1134,7 +1139,7 @@ void __cpuinit cpu_init(void) /* * Boot processor to setup the FP and extended state context info. */ - if (!smp_processor_id()) + if (smp_processor_id() == boot_cpu_id) init_thread_xstate(); xsave_init(); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index d3dcd58b87c..7f05f44b97e 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -115,9 +115,20 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data) u32 i = 0; if (cpu_family == CPU_HW_PSTATE) { - rdmsr(MSR_PSTATE_STATUS, lo, hi); - i = lo & HW_PSTATE_MASK; - data->currpstate = i; + if (data->currpstate == HW_PSTATE_INVALID) { + /* read (initial) hw pstate if not yet set */ + rdmsr(MSR_PSTATE_STATUS, lo, hi); + i = lo & HW_PSTATE_MASK; + + /* + * a workaround for family 11h erratum 311 might cause + * an "out-of-range Pstate if the core is in Pstate-0 + */ + if (i >= data->numps) + data->currpstate = HW_PSTATE_0; + else + data->currpstate = i; + } return 0; } do { @@ -1121,6 +1132,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) } data->cpu = pol->cpu; + data->currpstate = HW_PSTATE_INVALID; if (powernow_k8_cpu_init_acpi(data)) { /* diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index ab48cfed4d9..65cfb5d7f77 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -5,6 +5,19 @@ * http://www.gnu.org/licenses/gpl.html */ + +enum pstate { + HW_PSTATE_INVALID = 0xff, + HW_PSTATE_0 = 0, + HW_PSTATE_1 = 1, + HW_PSTATE_2 = 2, + HW_PSTATE_3 = 3, + HW_PSTATE_4 = 4, + HW_PSTATE_5 = 5, + HW_PSTATE_6 = 6, + HW_PSTATE_7 = 7, +}; + struct powernow_k8_data { unsigned int cpu; @@ -23,7 +36,9 @@ struct powernow_k8_data { u32 exttype; /* extended interface = 1 */ /* keep track of the current fid / vid or pstate */ - u32 currvid, currfid, currpstate; + u32 currvid; + u32 currfid; + enum pstate currpstate; /* the powernow_table includes all frequency and vid/fid pairings: * fid are the lower 8 bits of the index, vid are the upper 8 bits. diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c index 2b69994fd3a..a2d1176c38e 100644 --- a/arch/x86/kernel/ds.c +++ b/arch/x86/kernel/ds.c @@ -21,8 +21,6 @@ */ -#ifdef CONFIG_X86_DS - #include <asm/ds.h> #include <linux/errno.h> @@ -211,14 +209,15 @@ static DEFINE_PER_CPU(struct ds_context *, system_context); static inline struct ds_context *ds_get_context(struct task_struct *task) { struct ds_context *context; + unsigned long irq; - spin_lock(&ds_lock); + spin_lock_irqsave(&ds_lock, irq); context = (task ? task->thread.ds_ctx : this_system_context); if (context) context->count++; - spin_unlock(&ds_lock); + spin_unlock_irqrestore(&ds_lock, irq); return context; } @@ -226,18 +225,16 @@ static inline struct ds_context *ds_get_context(struct task_struct *task) /* * Same as ds_get_context, but allocates the context and it's DS * structure, if necessary; returns NULL; if out of memory. - * - * pre: requires ds_lock to be held */ static inline struct ds_context *ds_alloc_context(struct task_struct *task) { struct ds_context **p_context = (task ? &task->thread.ds_ctx : &this_system_context); struct ds_context *context = *p_context; + unsigned long irq; if (!context) { context = kzalloc(sizeof(*context), GFP_KERNEL); - if (!context) return NULL; @@ -247,18 +244,27 @@ static inline struct ds_context *ds_alloc_context(struct task_struct *task) return NULL; } - *p_context = context; + spin_lock_irqsave(&ds_lock, irq); - context->this = p_context; - context->task = task; + if (*p_context) { + kfree(context->ds); + kfree(context); + + context = *p_context; + } else { + *p_context = context; - if (task) - set_tsk_thread_flag(task, TIF_DS_AREA_MSR); + context->this = p_context; + context->task = task; - if (!task || (task == current)) - wrmsr(MSR_IA32_DS_AREA, (unsigned long)context->ds, 0); + if (task) + set_tsk_thread_flag(task, TIF_DS_AREA_MSR); - get_tracer(task); + if (!task || (task == current)) + wrmsrl(MSR_IA32_DS_AREA, + (unsigned long)context->ds); + } + spin_unlock_irqrestore(&ds_lock, irq); } context->count++; @@ -272,10 +278,12 @@ static inline struct ds_context *ds_alloc_context(struct task_struct *task) */ static inline void ds_put_context(struct ds_context *context) { + unsigned long irq; + if (!context) return; - spin_lock(&ds_lock); + spin_lock_irqsave(&ds_lock, irq); if (--context->count) goto out; @@ -297,7 +305,7 @@ static inline void ds_put_context(struct ds_context *context) kfree(context->ds); kfree(context); out: - spin_unlock(&ds_lock); + spin_unlock_irqrestore(&ds_lock, irq); } @@ -368,6 +376,7 @@ static int ds_request(struct task_struct *task, void *base, size_t size, struct ds_context *context; unsigned long buffer, adj; const unsigned long alignment = (1 << 3); + unsigned long irq; int error = 0; if (!ds_cfg.sizeof_ds) @@ -382,25 +391,27 @@ static int ds_request(struct task_struct *task, void *base, size_t size, return -EOPNOTSUPP; - spin_lock(&ds_lock); - - if (!check_tracer(task)) - return -EPERM; - - error = -ENOMEM; context = ds_alloc_context(task); if (!context) + return -ENOMEM; + + spin_lock_irqsave(&ds_lock, irq); + + error = -EPERM; + if (!check_tracer(task)) goto out_unlock; + get_tracer(task); + error = -EALREADY; if (context->owner[qual] == current) - goto out_unlock; + goto out_put_tracer; error = -EPERM; if (context->owner[qual] != NULL) - goto out_unlock; + goto out_put_tracer; context->owner[qual] = current; - spin_unlock(&ds_lock); + spin_unlock_irqrestore(&ds_lock, irq); error = -ENOMEM; @@ -448,10 +459,17 @@ static int ds_request(struct task_struct *task, void *base, size_t size, out_release: context->owner[qual] = NULL; ds_put_context(context); + put_tracer(task); + return error; + + out_put_tracer: + spin_unlock_irqrestore(&ds_lock, irq); + ds_put_context(context); + put_tracer(task); return error; out_unlock: - spin_unlock(&ds_lock); + spin_unlock_irqrestore(&ds_lock, irq); ds_put_context(context); return error; } @@ -801,13 +819,21 @@ static const struct ds_configuration ds_cfg_var = { .sizeof_ds = sizeof(long) * 12, .sizeof_field = sizeof(long), .sizeof_rec[ds_bts] = sizeof(long) * 3, +#ifdef __i386__ .sizeof_rec[ds_pebs] = sizeof(long) * 10 +#else + .sizeof_rec[ds_pebs] = sizeof(long) * 18 +#endif }; static const struct ds_configuration ds_cfg_64 = { .sizeof_ds = 8 * 12, .sizeof_field = 8, .sizeof_rec[ds_bts] = 8 * 3, +#ifdef __i386__ .sizeof_rec[ds_pebs] = 8 * 10 +#else + .sizeof_rec[ds_pebs] = 8 * 18 +#endif }; static inline void @@ -861,4 +887,3 @@ void ds_free(struct ds_context *context) while (leftovers--) ds_put_context(context); } -#endif /* CONFIG_X86_DS */ diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index ce97bf3bed1..7aafeb5263e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1290,15 +1290,17 @@ void __init e820_reserve_resources(void) res->start = e820.map[i].addr; res->end = end; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_MEM; /* * don't register the region that could be conflicted with * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) + if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) { + res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); + } res++; } @@ -1318,7 +1320,7 @@ void __init e820_reserve_resources_late(void) res = e820_res; for (i = 0; i < e820.nr_map; i++) { if (!res->parent && res->end) - reserve_region_with_split(&iomem_resource, res->start, res->end, res->name); + insert_resource_expand_to_fit(&iomem_resource, res); res++; } } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 3ce029ffaa5..1b894b72c0f 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -188,20 +188,6 @@ static void __init ati_bugs_contd(int num, int slot, int func) } #endif -#ifdef CONFIG_DMAR -static void __init intel_g33_dmar(int num, int slot, int func) -{ - struct acpi_table_header *dmar_tbl; - acpi_status status; - - status = acpi_get_table(ACPI_SIG_DMAR, 0, &dmar_tbl); - if (ACPI_SUCCESS(status)) { - printk(KERN_INFO "BIOS BUG: DMAR advertised on Intel G31/G33 chipset -- ignoring\n"); - dmar_disabled = 1; - } -} -#endif - #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 #define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED) @@ -225,10 +211,6 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs }, { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, -#ifdef CONFIG_DMAR - { PCI_VENDOR_ID_INTEL, 0x29c0, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, intel_g33_dmar }, -#endif {} }; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index dd65143941a..fe7014176eb 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -619,28 +619,37 @@ END(syscall_badsys) 27:; /* - * Build the entry stubs and pointer table with - * some assembler magic. + * Build the entry stubs and pointer table with some assembler magic. + * We pack 7 stubs into a single 32-byte chunk, which will fit in a + * single cache line on all modern x86 implementations. */ -.section .rodata,"a" +.section .init.rodata,"a" ENTRY(interrupt) .text - + .p2align 5 + .p2align CONFIG_X86_L1_CACHE_SHIFT ENTRY(irq_entries_start) RING0_INT_FRAME -vector=0 -.rept NR_VECTORS - ALIGN - .if vector +vector=FIRST_EXTERNAL_VECTOR +.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7 + .balign 32 + .rept 7 + .if vector < NR_VECTORS + .if vector <> FIRST_EXTERNAL_VECTOR CFI_ADJUST_CFA_OFFSET -4 - .endif -1: pushl $~(vector) + .endif +1: pushl $(~vector+0x80) /* Note: always in signed byte range */ CFI_ADJUST_CFA_OFFSET 4 - jmp common_interrupt - .previous + .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6 + jmp 2f + .endif + .previous .long 1b - .text + .text vector=vector+1 + .endif + .endr +2: jmp common_interrupt .endr END(irq_entries_start) @@ -652,8 +661,9 @@ END(interrupt) * the CPU automatically disables interrupts when executing an IRQ vector, * so IRQ-flags tracing has to follow that: */ - ALIGN + .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: + addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */ SAVE_ALL TRACE_IRQS_OFF movl %esp,%eax @@ -678,65 +688,6 @@ ENDPROC(name) /* The include is where all of the SMP etc. interrupts come from */ #include "entry_arch.h" -KPROBE_ENTRY(page_fault) - RING0_EC_FRAME - pushl $do_page_fault - CFI_ADJUST_CFA_OFFSET 4 - ALIGN -error_code: - /* the function address is in %fs's slot on the stack */ - 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 - 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 - 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*/ - movl $(__USER_DS), %ecx - movl %ecx, %ds - movl %ecx, %es - TRACE_IRQS_OFF - movl %esp,%eax # pt_regs pointer - call *%edi - jmp ret_from_exception - CFI_ENDPROC -KPROBE_END(page_fault) - ENTRY(coprocessor_error) RING0_INT_FRAME pushl $0 @@ -767,140 +718,6 @@ ENTRY(device_not_available) CFI_ENDPROC END(device_not_available) -/* - * Debug traps and NMI can happen at the one SYSENTER instruction - * that sets up the real kernel stack. Check here, since we can't - * allow the wrong stack to be used. - * - * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have - * already pushed 3 words if it hits on the sysenter instruction: - * eflags, cs and eip. - * - * We just load the right stack, and push the three (known) values - * 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; \ - CFI_REL_OFFSET eip, 0 - -KPROBE_ENTRY(debug) - RING0_INT_FRAME - cmpl $ia32_sysenter_target,(%esp) - jne debug_stack_correct - 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 - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # error code 0 - movl %esp,%eax # pt_regs pointer - call do_debug - jmp ret_from_exception - CFI_ENDPROC -KPROBE_END(debug) - -/* - * NMI is doubly nasty. It can happen _while_ we're handling - * a debug fault, and the debug fault hasn't yet been able to - * clear up the stack. So we first check whether we got an - * NMI on the sysenter entry path, but after that we need to - * check whether we got an NMI on the debug path where the debug - * fault happened on the sysenter path. - */ -KPROBE_ENTRY(nmi) - RING0_INT_FRAME - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 - movl %ss, %eax - cmpw $__ESPFIX_SS, %ax - popl %eax - CFI_ADJUST_CFA_OFFSET -4 - je nmi_espfix_stack - cmpl $ia32_sysenter_target,(%esp) - je nmi_stack_fixup - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 - movl %esp,%eax - /* Do not access memory above the end of our stack page, - * it might not exist. - */ - andl $(THREAD_SIZE-1),%eax - cmpl $(THREAD_SIZE-20),%eax - popl %eax - CFI_ADJUST_CFA_OFFSET -4 - jae nmi_stack_correct - cmpl $ia32_sysenter_target,12(%esp) - je nmi_debug_stack_check -nmi_stack_correct: - /* We have a RING0_INT_FRAME here */ - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_nmi - jmp restore_nocheck_notrace - CFI_ENDPROC - -nmi_stack_fixup: - RING0_INT_FRAME - FIX_STACK(12,nmi_stack_correct, 1) - jmp nmi_stack_correct - -nmi_debug_stack_check: - /* We have a RING0_INT_FRAME here */ - cmpw $__KERNEL_CS,16(%esp) - jne nmi_stack_correct - cmpl $debug,(%esp) - jb nmi_stack_correct - cmpl $debug_esp_fix_insn,(%esp) - ja nmi_stack_correct - FIX_STACK(24,nmi_stack_correct, 1) - jmp nmi_stack_correct - -nmi_espfix_stack: - /* We have a RING0_INT_FRAME here. - * - * create the pointer to lss back - */ - pushl %ss - CFI_ADJUST_CFA_OFFSET 4 - pushl %esp - CFI_ADJUST_CFA_OFFSET 4 - addw $4, (%esp) - /* copy the iret frame of 12 bytes */ - .rept 3 - pushl 16(%esp) - CFI_ADJUST_CFA_OFFSET 4 - .endr - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 - SAVE_ALL - TRACE_IRQS_OFF - FIXUP_ESPFIX_STACK # %eax == %esp - xorl %edx,%edx # zero error code - call do_nmi - RESTORE_REGS - lss 12+4(%esp), %esp # back to espfix stack - CFI_ADJUST_CFA_OFFSET -24 - jmp irq_return - CFI_ENDPROC -KPROBE_END(nmi) - #ifdef CONFIG_PARAVIRT ENTRY(native_iret) iret @@ -916,19 +733,6 @@ ENTRY(native_irq_enable_sysexit) END(native_irq_enable_sysexit) #endif -KPROBE_ENTRY(int3) - RING0_INT_FRAME - pushl $-1 # mark this as an int - CFI_ADJUST_CFA_OFFSET 4 - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_int3 - jmp ret_from_exception - CFI_ENDPROC -KPROBE_END(int3) - ENTRY(overflow) RING0_INT_FRAME pushl $0 @@ -993,14 +797,6 @@ ENTRY(stack_segment) CFI_ENDPROC END(stack_segment) -KPROBE_ENTRY(general_protection) - RING0_EC_FRAME - pushl $do_general_protection - CFI_ADJUST_CFA_OFFSET 4 - jmp error_code - CFI_ENDPROC -KPROBE_END(general_protection) - ENTRY(alignment_check) RING0_EC_FRAME pushl $do_alignment_check @@ -1051,6 +847,7 @@ ENTRY(kernel_thread_helper) push %eax CFI_ADJUST_CFA_OFFSET 4 call do_exit + ud2 # padding for call trace CFI_ENDPROC ENDPROC(kernel_thread_helper) @@ -1149,7 +946,7 @@ ENDPROC(xen_failsafe_callback) #endif /* CONFIG_XEN */ -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(mcount) @@ -1204,9 +1001,233 @@ trace: jmp ftrace_stub END(mcount) #endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ .section .rodata,"a" #include "syscall_table_32.S" syscall_table_size=(.-sys_call_table) + +/* + * Some functions should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" + +ENTRY(page_fault) + RING0_EC_FRAME + pushl $do_page_fault + CFI_ADJUST_CFA_OFFSET 4 + ALIGN +error_code: + /* the function address is in %fs's slot on the stack */ + 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 + 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 + 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*/ + movl $(__USER_DS), %ecx + movl %ecx, %ds + movl %ecx, %es + TRACE_IRQS_OFF + movl %esp,%eax # pt_regs pointer + call *%edi + jmp ret_from_exception + CFI_ENDPROC +END(page_fault) + +/* + * Debug traps and NMI can happen at the one SYSENTER instruction + * that sets up the real kernel stack. Check here, since we can't + * allow the wrong stack to be used. + * + * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have + * already pushed 3 words if it hits on the sysenter instruction: + * eflags, cs and eip. + * + * We just load the right stack, and push the three (known) values + * 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; \ + CFI_REL_OFFSET eip, 0 + +ENTRY(debug) + RING0_INT_FRAME + cmpl $ia32_sysenter_target,(%esp) + jne debug_stack_correct + 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 + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx,%edx # error code 0 + movl %esp,%eax # pt_regs pointer + call do_debug + jmp ret_from_exception + CFI_ENDPROC +END(debug) + +/* + * NMI is doubly nasty. It can happen _while_ we're handling + * a debug fault, and the debug fault hasn't yet been able to + * clear up the stack. So we first check whether we got an + * NMI on the sysenter entry path, but after that we need to + * check whether we got an NMI on the debug path where the debug + * fault happened on the sysenter path. + */ +ENTRY(nmi) + RING0_INT_FRAME + pushl %eax + CFI_ADJUST_CFA_OFFSET 4 + movl %ss, %eax + cmpw $__ESPFIX_SS, %ax + popl %eax + CFI_ADJUST_CFA_OFFSET -4 + je nmi_espfix_stack + cmpl $ia32_sysenter_target,(%esp) + je nmi_stack_fixup + pushl %eax + CFI_ADJUST_CFA_OFFSET 4 + movl %esp,%eax + /* Do not access memory above the end of our stack page, + * it might not exist. + */ + andl $(THREAD_SIZE-1),%eax + cmpl $(THREAD_SIZE-20),%eax + popl %eax + CFI_ADJUST_CFA_OFFSET -4 + jae nmi_stack_correct + cmpl $ia32_sysenter_target,12(%esp) + je nmi_debug_stack_check +nmi_stack_correct: + /* We have a RING0_INT_FRAME here */ + pushl %eax + CFI_ADJUST_CFA_OFFSET 4 + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_nmi + jmp restore_nocheck_notrace + CFI_ENDPROC + +nmi_stack_fixup: + RING0_INT_FRAME + FIX_STACK(12,nmi_stack_correct, 1) + jmp nmi_stack_correct + +nmi_debug_stack_check: + /* We have a RING0_INT_FRAME here */ + cmpw $__KERNEL_CS,16(%esp) + jne nmi_stack_correct + cmpl $debug,(%esp) + jb nmi_stack_correct + cmpl $debug_esp_fix_insn,(%esp) + ja nmi_stack_correct + FIX_STACK(24,nmi_stack_correct, 1) + jmp nmi_stack_correct + +nmi_espfix_stack: + /* We have a RING0_INT_FRAME here. + * + * create the pointer to lss back + */ + pushl %ss + CFI_ADJUST_CFA_OFFSET 4 + pushl %esp + CFI_ADJUST_CFA_OFFSET 4 + addw $4, (%esp) + /* copy the iret frame of 12 bytes */ + .rept 3 + pushl 16(%esp) + CFI_ADJUST_CFA_OFFSET 4 + .endr + pushl %eax + CFI_ADJUST_CFA_OFFSET 4 + SAVE_ALL + TRACE_IRQS_OFF + FIXUP_ESPFIX_STACK # %eax == %esp + xorl %edx,%edx # zero error code + call do_nmi + RESTORE_REGS + lss 12+4(%esp), %esp # back to espfix stack + CFI_ADJUST_CFA_OFFSET -24 + jmp irq_return + CFI_ENDPROC +END(nmi) + +ENTRY(int3) + RING0_INT_FRAME + pushl $-1 # mark this as an int + CFI_ADJUST_CFA_OFFSET 4 + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_int3 + jmp ret_from_exception + CFI_ENDPROC +END(int3) + +ENTRY(general_protection) + RING0_EC_FRAME + pushl $do_general_protection + CFI_ADJUST_CFA_OFFSET 4 + jmp error_code + CFI_ENDPROC +END(general_protection) + +/* + * End of kprobes section + */ + .popsection diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 09e7145484c..3194636a429 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -11,15 +11,15 @@ * * NOTE: This code handles signal-recognition, which happens every time * after an interrupt and after each system call. - * - * Normal syscalls and interrupts don't save a full stack frame, this is + * + * Normal syscalls and interrupts don't save a full stack frame, this is * only done for syscall tracing, signals or fork/exec et.al. - * - * A note on terminology: - * - top of stack: Architecture defined interrupt frame from SS to RIP - * at the top of the kernel process stack. + * + * A note on terminology: + * - top of stack: Architecture defined interrupt frame from SS to RIP + * at the top of the kernel process stack. * - partial stack frame: partially saved registers upto R11. - * - full stack frame: Like partial stack frame, but all register saved. + * - full stack frame: Like partial stack frame, but all register saved. * * Some macro usage: * - CFI macros are used to generate dwarf2 unwind information for better @@ -60,8 +60,7 @@ #define __AUDIT_ARCH_LE 0x40000000 .code64 - -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(mcount) retq @@ -138,11 +137,11 @@ trace: jmp ftrace_stub END(mcount) #endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args -#endif +#endif #ifdef CONFIG_PARAVIRT ENTRY(native_usergs_sysret64) @@ -161,29 +160,29 @@ ENTRY(native_usergs_sysret64) .endm /* - * C code is not supposed to know about undefined top of stack. Every time - * a C function with an pt_regs argument is called from the SYSCALL based + * C code is not supposed to know about undefined top of stack. Every time + * a C function with an pt_regs argument is called from the SYSCALL based * fast path FIXUP_TOP_OF_STACK is needed. * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs * manipulation. - */ - - /* %rsp:at FRAMEEND */ - .macro FIXUP_TOP_OF_STACK tmp - movq %gs:pda_oldrsp,\tmp - movq \tmp,RSP(%rsp) - movq $__USER_DS,SS(%rsp) - movq $__USER_CS,CS(%rsp) - movq $-1,RCX(%rsp) - movq R11(%rsp),\tmp /* get eflags */ - movq \tmp,EFLAGS(%rsp) + */ + + /* %rsp:at FRAMEEND */ + .macro FIXUP_TOP_OF_STACK tmp offset=0 + movq %gs:pda_oldrsp,\tmp + movq \tmp,RSP+\offset(%rsp) + movq $__USER_DS,SS+\offset(%rsp) + movq $__USER_CS,CS+\offset(%rsp) + movq $-1,RCX+\offset(%rsp) + movq R11+\offset(%rsp),\tmp /* get eflags */ + movq \tmp,EFLAGS+\offset(%rsp) .endm - .macro RESTORE_TOP_OF_STACK tmp,offset=0 - movq RSP-\offset(%rsp),\tmp - movq \tmp,%gs:pda_oldrsp - movq EFLAGS-\offset(%rsp),\tmp - movq \tmp,R11-\offset(%rsp) + .macro RESTORE_TOP_OF_STACK tmp offset=0 + movq RSP+\offset(%rsp),\tmp + movq \tmp,%gs:pda_oldrsp + movq EFLAGS+\offset(%rsp),\tmp + movq \tmp,R11+\offset(%rsp) .endm .macro FAKE_STACK_FRAME child_rip @@ -195,7 +194,7 @@ ENTRY(native_usergs_sysret64) pushq %rax /* rsp */ CFI_ADJUST_CFA_OFFSET 8 CFI_REL_OFFSET rsp,0 - pushq $(1<<9) /* eflags - interrupts on */ + pushq $X86_EFLAGS_IF /* eflags - interrupts on */ CFI_ADJUST_CFA_OFFSET 8 /*CFI_REL_OFFSET rflags,0*/ pushq $__KERNEL_CS /* cs */ @@ -213,62 +212,184 @@ ENTRY(native_usergs_sysret64) CFI_ADJUST_CFA_OFFSET -(6*8) .endm - .macro CFI_DEFAULT_STACK start=1 +/* + * initial frame state for interrupts (and exceptions without error code) + */ + .macro EMPTY_FRAME start=1 offset=0 .if \start - CFI_STARTPROC simple + CFI_STARTPROC simple CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,SS+8 + CFI_DEF_CFA rsp,8+\offset .else - CFI_DEF_CFA_OFFSET SS+8 + CFI_DEF_CFA_OFFSET 8+\offset .endif - CFI_REL_OFFSET r15,R15 - CFI_REL_OFFSET r14,R14 - CFI_REL_OFFSET r13,R13 - CFI_REL_OFFSET r12,R12 - CFI_REL_OFFSET rbp,RBP - CFI_REL_OFFSET rbx,RBX - CFI_REL_OFFSET r11,R11 - CFI_REL_OFFSET r10,R10 - CFI_REL_OFFSET r9,R9 - CFI_REL_OFFSET r8,R8 - CFI_REL_OFFSET rax,RAX - CFI_REL_OFFSET rcx,RCX - CFI_REL_OFFSET rdx,RDX - CFI_REL_OFFSET rsi,RSI - CFI_REL_OFFSET rdi,RDI - CFI_REL_OFFSET rip,RIP - /*CFI_REL_OFFSET cs,CS*/ - /*CFI_REL_OFFSET rflags,EFLAGS*/ - CFI_REL_OFFSET rsp,RSP - /*CFI_REL_OFFSET ss,SS*/ .endm + +/* + * initial frame state for interrupts (and exceptions without error code) + */ + .macro INTR_FRAME start=1 offset=0 + EMPTY_FRAME \start, SS+8+\offset-RIP + /*CFI_REL_OFFSET ss, SS+\offset-RIP*/ + CFI_REL_OFFSET rsp, RSP+\offset-RIP + /*CFI_REL_OFFSET rflags, EFLAGS+\offset-RIP*/ + /*CFI_REL_OFFSET cs, CS+\offset-RIP*/ + CFI_REL_OFFSET rip, RIP+\offset-RIP + .endm + +/* + * initial frame state for exceptions with error code (and interrupts + * with vector already pushed) + */ + .macro XCPT_FRAME start=1 offset=0 + INTR_FRAME \start, RIP+\offset-ORIG_RAX + /*CFI_REL_OFFSET orig_rax, ORIG_RAX-ORIG_RAX*/ + .endm + +/* + * frame that enables calling into C. + */ + .macro PARTIAL_FRAME start=1 offset=0 + XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET + CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET + CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET + CFI_REL_OFFSET rdx, RDX+\offset-ARGOFFSET + CFI_REL_OFFSET rcx, RCX+\offset-ARGOFFSET + CFI_REL_OFFSET rax, RAX+\offset-ARGOFFSET + CFI_REL_OFFSET r8, R8+\offset-ARGOFFSET + CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET + CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET + CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET + .endm + +/* + * frame that enables passing a complete pt_regs to a C function. + */ + .macro DEFAULT_FRAME start=1 offset=0 + PARTIAL_FRAME \start, R11+\offset-R15 + CFI_REL_OFFSET rbx, RBX+\offset + CFI_REL_OFFSET rbp, RBP+\offset + CFI_REL_OFFSET r12, R12+\offset + CFI_REL_OFFSET r13, R13+\offset + CFI_REL_OFFSET r14, R14+\offset + CFI_REL_OFFSET r15, R15+\offset + .endm + +/* save partial stack frame */ +ENTRY(save_args) + XCPT_FRAME + cld + movq_cfi rdi, RDI+16-ARGOFFSET + movq_cfi rsi, RSI+16-ARGOFFSET + movq_cfi rdx, RDX+16-ARGOFFSET + movq_cfi rcx, RCX+16-ARGOFFSET + movq_cfi rax, RAX+16-ARGOFFSET + movq_cfi r8, R8+16-ARGOFFSET + movq_cfi r9, R9+16-ARGOFFSET + movq_cfi r10, R10+16-ARGOFFSET + movq_cfi r11, R11+16-ARGOFFSET + + leaq -ARGOFFSET+16(%rsp),%rdi /* arg1 for handler */ + movq_cfi rbp, 8 /* push %rbp */ + leaq 8(%rsp), %rbp /* mov %rsp, %ebp */ + testl $3, CS(%rdi) + je 1f + SWAPGS + /* + * irqcount 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 + jne 2f + popq_cfi %rax /* move return address... */ + mov %gs:pda_irqstackptr,%rsp + EMPTY_FRAME 0 + pushq_cfi %rax /* ... to the new stack */ + /* + * We entered an interrupt context - irqs are off: + */ +2: TRACE_IRQS_OFF + ret + CFI_ENDPROC +END(save_args) + +ENTRY(save_rest) + PARTIAL_FRAME 1 REST_SKIP+8 + movq 5*8+16(%rsp), %r11 /* save return address */ + movq_cfi rbx, RBX+16 + movq_cfi rbp, RBP+16 + movq_cfi r12, R12+16 + movq_cfi r13, R13+16 + movq_cfi r14, R14+16 + movq_cfi r15, R15+16 + movq %r11, 8(%rsp) /* return address */ + FIXUP_TOP_OF_STACK %r11, 16 + ret + CFI_ENDPROC +END(save_rest) + +/* save complete stack frame */ +ENTRY(save_paranoid) + XCPT_FRAME 1 RDI+8 + cld + movq_cfi rdi, RDI+8 + movq_cfi rsi, RSI+8 + movq_cfi rdx, RDX+8 + movq_cfi rcx, RCX+8 + movq_cfi rax, RAX+8 + movq_cfi r8, R8+8 + movq_cfi r9, R9+8 + movq_cfi r10, R10+8 + movq_cfi r11, R11+8 + movq_cfi rbx, RBX+8 + movq_cfi rbp, RBP+8 + movq_cfi r12, R12+8 + movq_cfi r13, R13+8 + movq_cfi r14, R14+8 + movq_cfi r15, R15+8 + movl $1,%ebx + movl $MSR_GS_BASE,%ecx + rdmsr + testl %edx,%edx + js 1f /* negative -> in kernel */ + SWAPGS + xorl %ebx,%ebx +1: ret + CFI_ENDPROC +END(save_paranoid) + /* - * A newly forked process directly context switches into this. - */ -/* rdi: prev */ + * A newly forked process directly context switches into this address. + * + * rdi: prev task we switched from + */ ENTRY(ret_from_fork) - CFI_DEFAULT_STACK + DEFAULT_FRAME + push kernel_eflags(%rip) CFI_ADJUST_CFA_OFFSET 8 - popf # reset kernel eflags + popf # reset kernel eflags CFI_ADJUST_CFA_OFFSET -8 - call schedule_tail + + call schedule_tail # rdi: 'prev' task parameter + GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx) - jnz rff_trace -rff_action: + + CFI_REMEMBER_STATE RESTORE_REST - testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread? + + testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? je int_ret_from_sys_call - testl $_TIF_IA32,TI_flags(%rcx) + + testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET jnz int_ret_from_sys_call - RESTORE_TOP_OF_STACK %rdi,ARGOFFSET - jmp ret_from_sys_call -rff_trace: - movq %rsp,%rdi - call syscall_trace_leave - GET_THREAD_INFO(%rcx) - jmp rff_action + + RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET + jmp ret_from_sys_call # go to the SYSRET fastpath + + CFI_RESTORE_STATE CFI_ENDPROC END(ret_from_fork) @@ -278,20 +399,20 @@ END(ret_from_fork) * SYSCALL does not save anything on the stack and does not change the * stack pointer. */ - + /* - * Register setup: + * Register setup: * rax system call number * rdi arg0 - * rcx return address for syscall/sysret, C arg3 + * rcx return address for syscall/sysret, C arg3 * rsi arg1 - * rdx arg2 + * rdx arg2 * r10 arg3 (--> moved to rcx for C) * r8 arg4 * r9 arg5 * r11 eflags for syscall/sysret, temporary for C - * r12-r15,rbp,rbx saved by C code, not touched. - * + * r12-r15,rbp,rbx saved by C code, not touched. + * * Interrupts are off on entry. * Only called from user space. * @@ -301,7 +422,7 @@ END(ret_from_fork) * When user can change the frames always force IRET. That is because * it deals with uncanonical addresses better. SYSRET has trouble * with them due to bugs in both AMD and Intel CPUs. - */ + */ ENTRY(system_call) CFI_STARTPROC simple @@ -317,7 +438,7 @@ ENTRY(system_call) */ ENTRY(system_call_after_swapgs) - movq %rsp,%gs:pda_oldrsp + movq %rsp,%gs:pda_oldrsp movq %gs:pda_kernelstack,%rsp /* * No need to follow this irqs off/on section - it's straight @@ -325,7 +446,7 @@ ENTRY(system_call_after_swapgs) */ ENABLE_INTERRUPTS(CLBR_NONE) SAVE_ARGS 8,1 - movq %rax,ORIG_RAX-ARGOFFSET(%rsp) + movq %rax,ORIG_RAX-ARGOFFSET(%rsp) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET GET_THREAD_INFO(%rcx) @@ -339,19 +460,19 @@ system_call_fastpath: movq %rax,RAX-ARGOFFSET(%rsp) /* * Syscall return path ending with SYSRET (fast path) - * Has incomplete stack frame and undefined top of stack. - */ + * Has incomplete stack frame and undefined top of stack. + */ ret_from_sys_call: movl $_TIF_ALLWORK_MASK,%edi /* edi: flagmask */ -sysret_check: +sysret_check: LOCKDEP_SYS_EXIT GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF movl TI_flags(%rcx),%edx andl %edi,%edx - jnz sysret_careful + jnz sysret_careful CFI_REMEMBER_STATE /* * sysretq will re-enable interrupts: @@ -366,7 +487,7 @@ sysret_check: CFI_RESTORE_STATE /* Handle reschedules */ - /* edx: work, edi: workmask */ + /* edx: work, edi: workmask */ sysret_careful: bt $TIF_NEED_RESCHED,%edx jnc sysret_signal @@ -379,7 +500,7 @@ sysret_careful: CFI_ADJUST_CFA_OFFSET -8 jmp sysret_check - /* Handle a signal */ + /* Handle a signal */ sysret_signal: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) @@ -388,17 +509,20 @@ sysret_signal: jc sysret_audit #endif /* edx: work flags (arg3) */ - leaq do_notify_resume(%rip),%rax leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1 xorl %esi,%esi # oldset -> arg2 - call ptregscall_common + SAVE_REST + FIXUP_TOP_OF_STACK %r11 + call do_notify_resume + RESTORE_TOP_OF_STACK %r11 + RESTORE_REST movl $_TIF_WORK_MASK,%edi /* Use IRET because user could have changed frame. This works because ptregscall_common has called FIXUP_TOP_OF_STACK. */ DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF jmp int_with_check - + badsys: movq $-ENOSYS,RAX-ARGOFFSET(%rsp) jmp ret_from_sys_call @@ -437,7 +561,7 @@ sysret_audit: #endif /* CONFIG_AUDITSYSCALL */ /* Do syscall tracing */ -tracesys: +tracesys: #ifdef CONFIG_AUDITSYSCALL testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%rcx) jz auditsys @@ -460,8 +584,8 @@ tracesys: call *sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) /* Use IRET because user could have changed frame */ - -/* + +/* * Syscall return path ending with IRET. * Has correct top of stack, but partial stack frame. */ @@ -505,18 +629,18 @@ int_very_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) SAVE_REST - /* Check for syscall exit trace */ + /* Check for syscall exit trace */ testl $_TIF_WORK_SYSCALL_EXIT,%edx jz int_signal pushq %rdi CFI_ADJUST_CFA_OFFSET 8 - leaq 8(%rsp),%rdi # &ptregs -> arg1 + leaq 8(%rsp),%rdi # &ptregs -> arg1 call syscall_trace_leave popq %rdi CFI_ADJUST_CFA_OFFSET -8 andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi jmp int_restore_rest - + int_signal: testl $_TIF_DO_NOTIFY_MASK,%edx jz 1f @@ -531,22 +655,24 @@ int_restore_rest: jmp int_with_check CFI_ENDPROC END(system_call) - -/* + +/* * Certain special system calls that need to save a complete full stack frame. - */ - + */ .macro PTREGSCALL label,func,arg - .globl \label -\label: - leaq \func(%rip),%rax - leaq -ARGOFFSET+8(%rsp),\arg /* 8 for return address */ - jmp ptregscall_common +ENTRY(\label) + PARTIAL_FRAME 1 8 /* offset 8: return address */ + subq $REST_SKIP, %rsp + CFI_ADJUST_CFA_OFFSET REST_SKIP + call save_rest + DEFAULT_FRAME 0 8 /* offset 8: return address */ + leaq 8(%rsp), \arg /* pt_regs pointer */ + call \func + jmp ptregscall_common + CFI_ENDPROC END(\label) .endm - CFI_STARTPROC - PTREGSCALL stub_clone, sys_clone, %r8 PTREGSCALL stub_fork, sys_fork, %rdi PTREGSCALL stub_vfork, sys_vfork, %rdi @@ -554,25 +680,18 @@ END(\label) PTREGSCALL stub_iopl, sys_iopl, %rsi ENTRY(ptregscall_common) - popq %r11 - CFI_ADJUST_CFA_OFFSET -8 - CFI_REGISTER rip, r11 - SAVE_REST - movq %r11, %r15 - CFI_REGISTER rip, r15 - FIXUP_TOP_OF_STACK %r11 - call *%rax - RESTORE_TOP_OF_STACK %r11 - movq %r15, %r11 - CFI_REGISTER rip, r11 - RESTORE_REST - pushq %r11 - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rip, 0 - ret + DEFAULT_FRAME 1 8 /* offset 8: return address */ + RESTORE_TOP_OF_STACK %r11, 8 + movq_cfi_restore R15+8, r15 + movq_cfi_restore R14+8, r14 + movq_cfi_restore R13+8, r13 + movq_cfi_restore R12+8, r12 + movq_cfi_restore RBP+8, rbp + movq_cfi_restore RBX+8, rbx + ret $REST_SKIP /* pop extended registers */ CFI_ENDPROC END(ptregscall_common) - + ENTRY(stub_execve) CFI_STARTPROC popq %r11 @@ -588,11 +707,11 @@ ENTRY(stub_execve) jmp int_ret_from_sys_call CFI_ENDPROC END(stub_execve) - + /* * sigreturn is special because it needs to restore all registers on return. * This cannot be done with SYSRET, so use the IRET return path instead. - */ + */ ENTRY(stub_rt_sigreturn) CFI_STARTPROC addq $8, %rsp @@ -608,70 +727,70 @@ ENTRY(stub_rt_sigreturn) END(stub_rt_sigreturn) /* - * initial frame state for interrupts and exceptions + * Build the entry stubs and pointer table with some assembler magic. + * We pack 7 stubs into a single 32-byte chunk, which will fit in a + * single cache line on all modern x86 implementations. */ - .macro _frame ref - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,SS+8-\ref - /*CFI_REL_OFFSET ss,SS-\ref*/ - CFI_REL_OFFSET rsp,RSP-\ref - /*CFI_REL_OFFSET rflags,EFLAGS-\ref*/ - /*CFI_REL_OFFSET cs,CS-\ref*/ - CFI_REL_OFFSET rip,RIP-\ref - .endm + .section .init.rodata,"a" +ENTRY(interrupt) + .text + .p2align 5 + .p2align CONFIG_X86_L1_CACHE_SHIFT +ENTRY(irq_entries_start) + INTR_FRAME +vector=FIRST_EXTERNAL_VECTOR +.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7 + .balign 32 + .rept 7 + .if vector < NR_VECTORS + .if vector <> FIRST_EXTERNAL_VECTOR + CFI_ADJUST_CFA_OFFSET -8 + .endif +1: pushq $(~vector+0x80) /* Note: always in signed byte range */ + CFI_ADJUST_CFA_OFFSET 8 + .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6 + jmp 2f + .endif + .previous + .quad 1b + .text +vector=vector+1 + .endif + .endr +2: jmp common_interrupt +.endr + CFI_ENDPROC +END(irq_entries_start) -/* initial frame state for interrupts (and exceptions without error code) */ -#define INTR_FRAME _frame RIP -/* initial frame state for exceptions with error code (and interrupts with - vector already pushed) */ -#define XCPT_FRAME _frame ORIG_RAX +.previous +END(interrupt) +.previous -/* +/* * Interrupt entry/exit. * * Interrupt entry points save only callee clobbered registers in fast path. - * - * Entry runs with interrupts off. - */ + * + * Entry runs with interrupts off. + */ -/* 0(%rsp): interrupt number */ +/* 0(%rsp): ~(interrupt number) */ .macro interrupt func - cld - SAVE_ARGS - leaq -ARGOFFSET(%rsp),%rdi # arg1 for handler - pushq %rbp - /* - * Save rbp twice: One is for marking the stack frame, as usual, and the - * other, to fill pt_regs properly. This is because bx comes right - * before the last saved register in that structure, and not bp. If the - * base pointer were in the place bx is today, this would not be needed. - */ - movq %rbp, -8(%rsp) - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rbp, 0 - movq %rsp,%rbp - CFI_DEF_CFA_REGISTER rbp - testl $3,CS(%rdi) - je 1f - SWAPGS - /* irqcount 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 - cmoveq %gs:pda_irqstackptr,%rsp - push %rbp # backlink for old unwinder - /* - * We entered an interrupt context - irqs are off: - */ - TRACE_IRQS_OFF + subq $10*8, %rsp + CFI_ADJUST_CFA_OFFSET 10*8 + call save_args + PARTIAL_FRAME 0 call \func .endm -ENTRY(common_interrupt) + /* + * The interrupt stubs push (~vector+0x80) onto the stack and + * then jump to common_interrupt. + */ + .p2align CONFIG_X86_L1_CACHE_SHIFT +common_interrupt: XCPT_FRAME + addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ interrupt do_IRQ /* 0(%rsp): oldrsp-ARGOFFSET */ ret_from_intr: @@ -685,12 +804,12 @@ exit_intr: GET_THREAD_INFO(%rcx) testl $3,CS-ARGOFFSET(%rsp) je retint_kernel - + /* Interrupt came from user space */ /* * Has a correct top of stack, but a partial stack frame * %rcx: thread info. Interrupts off. - */ + */ retint_with_reschedule: movl $_TIF_WORK_MASK,%edi retint_check: @@ -763,20 +882,20 @@ retint_careful: pushq %rdi CFI_ADJUST_CFA_OFFSET 8 call schedule - popq %rdi + popq %rdi CFI_ADJUST_CFA_OFFSET -8 GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF jmp retint_check - + retint_signal: testl $_TIF_DO_NOTIFY_MASK,%edx jz retint_swapgs TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) SAVE_REST - movq $-1,ORIG_RAX(%rsp) + movq $-1,ORIG_RAX(%rsp) xorl %esi,%esi # oldset movq %rsp,%rdi # &pt_regs call do_notify_resume @@ -798,324 +917,211 @@ ENTRY(retint_kernel) jnc retint_restore_args call preempt_schedule_irq jmp exit_intr -#endif +#endif CFI_ENDPROC END(common_interrupt) - + /* * APIC interrupts. - */ - .macro apicinterrupt num,func + */ +.macro apicinterrupt num sym do_sym +ENTRY(\sym) INTR_FRAME pushq $~(\num) CFI_ADJUST_CFA_OFFSET 8 - interrupt \func + interrupt \do_sym jmp ret_from_intr CFI_ENDPROC - .endm - -ENTRY(thermal_interrupt) - apicinterrupt THERMAL_APIC_VECTOR,smp_thermal_interrupt -END(thermal_interrupt) - -ENTRY(threshold_interrupt) - apicinterrupt THRESHOLD_APIC_VECTOR,mce_threshold_interrupt -END(threshold_interrupt) - -#ifdef CONFIG_SMP -ENTRY(reschedule_interrupt) - apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt -END(reschedule_interrupt) - - .macro INVALIDATE_ENTRY num -ENTRY(invalidate_interrupt\num) - apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt -END(invalidate_interrupt\num) - .endm +END(\sym) +.endm - INVALIDATE_ENTRY 0 - INVALIDATE_ENTRY 1 - INVALIDATE_ENTRY 2 - INVALIDATE_ENTRY 3 - INVALIDATE_ENTRY 4 - INVALIDATE_ENTRY 5 - INVALIDATE_ENTRY 6 - INVALIDATE_ENTRY 7 - -ENTRY(call_function_interrupt) - apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt -END(call_function_interrupt) -ENTRY(call_function_single_interrupt) - apicinterrupt CALL_FUNCTION_SINGLE_VECTOR,smp_call_function_single_interrupt -END(call_function_single_interrupt) -ENTRY(irq_move_cleanup_interrupt) - apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt -END(irq_move_cleanup_interrupt) +#ifdef CONFIG_SMP +apicinterrupt IRQ_MOVE_CLEANUP_VECTOR \ + irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt #endif -ENTRY(apic_timer_interrupt) - apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt -END(apic_timer_interrupt) +apicinterrupt UV_BAU_MESSAGE \ + uv_bau_message_intr1 uv_bau_message_interrupt +apicinterrupt LOCAL_TIMER_VECTOR \ + apic_timer_interrupt smp_apic_timer_interrupt + +#ifdef CONFIG_SMP +apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \ + invalidate_interrupt0 smp_invalidate_interrupt +apicinterrupt INVALIDATE_TLB_VECTOR_START+1 \ + invalidate_interrupt1 smp_invalidate_interrupt +apicinterrupt INVALIDATE_TLB_VECTOR_START+2 \ + invalidate_interrupt2 smp_invalidate_interrupt +apicinterrupt INVALIDATE_TLB_VECTOR_START+3 \ + invalidate_interrupt3 smp_invalidate_interrupt +apicinterrupt INVALIDATE_TLB_VECTOR_START+4 \ + invalidate_interrupt4 smp_invalidate_interrupt +apicinterrupt INVALIDATE_TLB_VECTOR_START+5 \ + invalidate_interrupt5 smp_invalidate_interrupt +apicinterrupt INVALIDATE_TLB_VECTOR_START+6 \ + invalidate_interrupt6 smp_invalidate_interrupt +apicinterrupt INVALIDATE_TLB_VECTOR_START+7 \ + invalidate_interrupt7 smp_invalidate_interrupt +#endif -ENTRY(uv_bau_message_intr1) - apicinterrupt 220,uv_bau_message_interrupt -END(uv_bau_message_intr1) +apicinterrupt THRESHOLD_APIC_VECTOR \ + threshold_interrupt mce_threshold_interrupt +apicinterrupt THERMAL_APIC_VECTOR \ + thermal_interrupt smp_thermal_interrupt + +#ifdef CONFIG_SMP +apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \ + call_function_single_interrupt smp_call_function_single_interrupt +apicinterrupt CALL_FUNCTION_VECTOR \ + call_function_interrupt smp_call_function_interrupt +apicinterrupt RESCHEDULE_VECTOR \ + reschedule_interrupt smp_reschedule_interrupt +#endif -ENTRY(error_interrupt) - apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt -END(error_interrupt) +apicinterrupt ERROR_APIC_VECTOR \ + error_interrupt smp_error_interrupt +apicinterrupt SPURIOUS_APIC_VECTOR \ + spurious_interrupt smp_spurious_interrupt -ENTRY(spurious_interrupt) - apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt -END(spurious_interrupt) - /* * Exception entry points. - */ - .macro zeroentry sym + */ +.macro zeroentry sym do_sym +ENTRY(\sym) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq $0 /* push error code/oldrax */ - CFI_ADJUST_CFA_OFFSET 8 - pushq %rax /* push real oldrax to the rdi slot */ - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rax,0 - leaq \sym(%rip),%rax - jmp error_entry + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + subq $15*8,%rsp + CFI_ADJUST_CFA_OFFSET 15*8 + call error_entry + DEFAULT_FRAME 0 + movq %rsp,%rdi /* pt_regs pointer */ + xorl %esi,%esi /* no error code */ + call \do_sym + jmp error_exit /* %ebx: no swapgs flag */ CFI_ENDPROC - .endm +END(\sym) +.endm - .macro errorentry sym - XCPT_FRAME +.macro paranoidzeroentry sym do_sym +ENTRY(\sym) + INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq %rax + pushq $-1 /* ORIG_RAX: no syscall to restart */ CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rax,0 - leaq \sym(%rip),%rax - jmp error_entry + subq $15*8, %rsp + call save_paranoid + TRACE_IRQS_OFF + movq %rsp,%rdi /* pt_regs pointer */ + xorl %esi,%esi /* no error code */ + call \do_sym + jmp paranoid_exit /* %ebx: no swapgs flag */ CFI_ENDPROC - .endm +END(\sym) +.endm - /* error code is on the stack already */ - /* handle NMI like exceptions that can happen everywhere */ - .macro paranoidentry sym, ist=0, irqtrace=1 - SAVE_ALL - cld - movl $1,%ebx - movl $MSR_GS_BASE,%ecx - rdmsr - testl %edx,%edx - js 1f - SWAPGS - xorl %ebx,%ebx -1: - .if \ist - movq %gs:pda_data_offset, %rbp - .endif - .if \irqtrace - TRACE_IRQS_OFF - .endif - movq %rsp,%rdi - movq ORIG_RAX(%rsp),%rsi - movq $-1,ORIG_RAX(%rsp) - .if \ist - subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp) - .endif - call \sym - .if \ist - addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp) - .endif - DISABLE_INTERRUPTS(CLBR_NONE) - .if \irqtrace +.macro paranoidzeroentry_ist sym do_sym ist +ENTRY(\sym) + INTR_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME + pushq $-1 /* ORIG_RAX: no syscall to restart */ + CFI_ADJUST_CFA_OFFSET 8 + subq $15*8, %rsp + call save_paranoid TRACE_IRQS_OFF - .endif - .endm + 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) + call \do_sym + addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp) + jmp paranoid_exit /* %ebx: no swapgs flag */ + CFI_ENDPROC +END(\sym) +.endm - /* - * "Paranoid" exit path from exception stack. - * Paranoid because this is used by NMIs and cannot take - * any kernel state for granted. - * We don't do kernel preemption checks here, because only - * NMI should be common and it does not enable IRQs and - * cannot get reschedule ticks. - * - * "trace" is 0 for the NMI handler only, because irq-tracing - * is fundamentally NMI-unsafe. (we cannot change the soft and - * hard flags at once, atomically) - */ - .macro paranoidexit trace=1 - /* ebx: no swapgs flag */ -paranoid_exit\trace: - testl %ebx,%ebx /* swapgs needed? */ - jnz paranoid_restore\trace - testl $3,CS(%rsp) - jnz paranoid_userspace\trace -paranoid_swapgs\trace: - .if \trace - TRACE_IRQS_IRETQ 0 - .endif - SWAPGS_UNSAFE_STACK -paranoid_restore\trace: - RESTORE_ALL 8 - jmp irq_return -paranoid_userspace\trace: - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%ebx - andl $_TIF_WORK_MASK,%ebx - jz paranoid_swapgs\trace - movq %rsp,%rdi /* &pt_regs */ - call sync_regs - movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx - jnz paranoid_schedule\trace - movl %ebx,%edx /* arg3: thread flags */ - .if \trace - TRACE_IRQS_ON - .endif - ENABLE_INTERRUPTS(CLBR_NONE) - xorl %esi,%esi /* arg2: oldset */ - movq %rsp,%rdi /* arg1: &pt_regs */ - call do_notify_resume - DISABLE_INTERRUPTS(CLBR_NONE) - .if \trace - TRACE_IRQS_OFF - .endif - jmp paranoid_userspace\trace -paranoid_schedule\trace: - .if \trace - TRACE_IRQS_ON - .endif - ENABLE_INTERRUPTS(CLBR_ANY) - call schedule - DISABLE_INTERRUPTS(CLBR_ANY) - .if \trace - TRACE_IRQS_OFF - .endif - jmp paranoid_userspace\trace +.macro errorentry sym do_sym +ENTRY(\sym) + XCPT_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME + subq $15*8,%rsp + CFI_ADJUST_CFA_OFFSET 15*8 + call error_entry + DEFAULT_FRAME 0 + movq %rsp,%rdi /* pt_regs pointer */ + movq ORIG_RAX(%rsp),%rsi /* get error code */ + movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + call \do_sym + jmp error_exit /* %ebx: no swapgs flag */ CFI_ENDPROC - .endm +END(\sym) +.endm -/* - * Exception entry point. This expects an error code/orig_rax on the stack - * and the exception handler in %rax. - */ -KPROBE_ENTRY(error_entry) - _frame RDI - CFI_REL_OFFSET rax,0 - /* rdi slot contains rax, oldrax contains error code */ - cld - subq $14*8,%rsp - CFI_ADJUST_CFA_OFFSET (14*8) - movq %rsi,13*8(%rsp) - CFI_REL_OFFSET rsi,RSI - movq 14*8(%rsp),%rsi /* load rax from rdi slot */ - CFI_REGISTER rax,rsi - movq %rdx,12*8(%rsp) - CFI_REL_OFFSET rdx,RDX - movq %rcx,11*8(%rsp) - CFI_REL_OFFSET rcx,RCX - movq %rsi,10*8(%rsp) /* store rax */ - CFI_REL_OFFSET rax,RAX - movq %r8, 9*8(%rsp) - CFI_REL_OFFSET r8,R8 - movq %r9, 8*8(%rsp) - CFI_REL_OFFSET r9,R9 - movq %r10,7*8(%rsp) - CFI_REL_OFFSET r10,R10 - movq %r11,6*8(%rsp) - CFI_REL_OFFSET r11,R11 - movq %rbx,5*8(%rsp) - CFI_REL_OFFSET rbx,RBX - movq %rbp,4*8(%rsp) - CFI_REL_OFFSET rbp,RBP - movq %r12,3*8(%rsp) - CFI_REL_OFFSET r12,R12 - movq %r13,2*8(%rsp) - CFI_REL_OFFSET r13,R13 - movq %r14,1*8(%rsp) - CFI_REL_OFFSET r14,R14 - movq %r15,(%rsp) - CFI_REL_OFFSET r15,R15 - xorl %ebx,%ebx - testl $3,CS(%rsp) - je error_kernelspace -error_swapgs: - SWAPGS -error_sti: - TRACE_IRQS_OFF - movq %rdi,RDI(%rsp) - CFI_REL_OFFSET rdi,RDI - movq %rsp,%rdi - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) - call *%rax - /* ebx: no swapgs flag (1: don't need swapgs, 0: need it) */ -error_exit: - movl %ebx,%eax - RESTORE_REST - DISABLE_INTERRUPTS(CLBR_NONE) + /* error code is on the stack already */ +.macro paranoiderrorentry sym do_sym +ENTRY(\sym) + XCPT_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME + subq $15*8,%rsp + CFI_ADJUST_CFA_OFFSET 15*8 + call save_paranoid + DEFAULT_FRAME 0 TRACE_IRQS_OFF - GET_THREAD_INFO(%rcx) - testl %eax,%eax - jne retint_kernel - LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx),%edx - movl $_TIF_WORK_MASK,%edi - andl %edi,%edx - jnz retint_careful - jmp retint_swapgs + movq %rsp,%rdi /* pt_regs pointer */ + movq ORIG_RAX(%rsp),%rsi /* get error code */ + movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + call \do_sym + jmp paranoid_exit /* %ebx: no swapgs flag */ CFI_ENDPROC +END(\sym) +.endm -error_kernelspace: - incl %ebx - /* There are two places in the kernel that can potentially fault with - usergs. Handle them here. The exception handlers after - iret run with kernel gs again, so don't set the user space flag. - B stepping K8s sometimes report an truncated RIP for IRET - exceptions returning to compat mode. Check for these here too. */ - leaq irq_return(%rip),%rcx - cmpq %rcx,RIP(%rsp) - je error_swapgs - movl %ecx,%ecx /* zero extend */ - cmpq %rcx,RIP(%rsp) - je error_swapgs - cmpq $gs_change,RIP(%rsp) - je error_swapgs - jmp error_sti -KPROBE_END(error_entry) - - /* Reload gs selector with exception handling */ - /* edi: new selector */ +zeroentry divide_error do_divide_error +zeroentry overflow do_overflow +zeroentry bounds do_bounds +zeroentry invalid_op do_invalid_op +zeroentry device_not_available do_device_not_available +paranoiderrorentry double_fault do_double_fault +zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun +errorentry invalid_TSS do_invalid_TSS +errorentry segment_not_present do_segment_not_present +zeroentry spurious_interrupt_bug do_spurious_interrupt_bug +zeroentry coprocessor_error do_coprocessor_error +errorentry alignment_check do_alignment_check +zeroentry simd_coprocessor_error do_simd_coprocessor_error + + /* Reload gs selector with exception handling */ + /* edi: new selector */ ENTRY(native_load_gs_index) CFI_STARTPROC pushf CFI_ADJUST_CFA_OFFSET 8 DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI)) - SWAPGS -gs_change: - movl %edi,%gs + SWAPGS +gs_change: + movl %edi,%gs 2: mfence /* workaround */ SWAPGS - popf + popf CFI_ADJUST_CFA_OFFSET -8 - ret + ret CFI_ENDPROC -ENDPROC(native_load_gs_index) - - .section __ex_table,"a" - .align 8 - .quad gs_change,bad_gs - .previous - .section .fixup,"ax" +END(native_load_gs_index) + + .section __ex_table,"a" + .align 8 + .quad gs_change,bad_gs + .previous + .section .fixup,"ax" /* running with kernelgs */ -bad_gs: +bad_gs: SWAPGS /* switch back to user gs */ xorl %eax,%eax - movl %eax,%gs - jmp 2b - .previous - + movl %eax,%gs + jmp 2b + .previous + /* * Create a kernel thread. * @@ -1138,7 +1144,7 @@ ENTRY(kernel_thread) xorl %r8d,%r8d xorl %r9d,%r9d - + # clone now call do_fork movq %rax,RAX(%rsp) @@ -1149,15 +1155,15 @@ ENTRY(kernel_thread) * so internally to the x86_64 port you can rely on kernel_thread() * not to reschedule the child before returning, this avoids the need * of hacks for example to fork off the per-CPU idle tasks. - * [Hopefully no generic code relies on the reschedule -AK] + * [Hopefully no generic code relies on the reschedule -AK] */ RESTORE_ALL UNFAKE_STACK_FRAME ret CFI_ENDPROC -ENDPROC(kernel_thread) - -child_rip: +END(kernel_thread) + +ENTRY(child_rip) pushq $0 # fake return address CFI_STARTPROC /* @@ -1170,8 +1176,9 @@ child_rip: # exit mov %eax, %edi call do_exit + ud2 # padding for call trace CFI_ENDPROC -ENDPROC(child_rip) +END(child_rip) /* * execve(). This function needs to use IRET, not SYSRET, to set up all state properly. @@ -1191,10 +1198,10 @@ ENDPROC(child_rip) ENTRY(kernel_execve) CFI_STARTPROC FAKE_STACK_FRAME $0 - SAVE_ALL + SAVE_ALL movq %rsp,%rcx call sys_execve - movq %rax, RAX(%rsp) + movq %rax, RAX(%rsp) RESTORE_REST testq %rax,%rax je int_ret_from_sys_call @@ -1202,129 +1209,7 @@ ENTRY(kernel_execve) UNFAKE_STACK_FRAME ret CFI_ENDPROC -ENDPROC(kernel_execve) - -KPROBE_ENTRY(page_fault) - errorentry do_page_fault -KPROBE_END(page_fault) - -ENTRY(coprocessor_error) - zeroentry do_coprocessor_error -END(coprocessor_error) - -ENTRY(simd_coprocessor_error) - zeroentry do_simd_coprocessor_error -END(simd_coprocessor_error) - -ENTRY(device_not_available) - zeroentry do_device_not_available -END(device_not_available) - - /* runs on exception stack */ -KPROBE_ENTRY(debug) - INTR_FRAME - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq $0 - CFI_ADJUST_CFA_OFFSET 8 - paranoidentry do_debug, DEBUG_STACK - paranoidexit -KPROBE_END(debug) - - /* runs on exception stack */ -KPROBE_ENTRY(nmi) - INTR_FRAME - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq $-1 - CFI_ADJUST_CFA_OFFSET 8 - paranoidentry do_nmi, 0, 0 -#ifdef CONFIG_TRACE_IRQFLAGS - paranoidexit 0 -#else - jmp paranoid_exit1 - CFI_ENDPROC -#endif -KPROBE_END(nmi) - -KPROBE_ENTRY(int3) - INTR_FRAME - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq $0 - CFI_ADJUST_CFA_OFFSET 8 - paranoidentry do_int3, DEBUG_STACK - jmp paranoid_exit1 - CFI_ENDPROC -KPROBE_END(int3) - -ENTRY(overflow) - zeroentry do_overflow -END(overflow) - -ENTRY(bounds) - zeroentry do_bounds -END(bounds) - -ENTRY(invalid_op) - zeroentry do_invalid_op -END(invalid_op) - -ENTRY(coprocessor_segment_overrun) - zeroentry do_coprocessor_segment_overrun -END(coprocessor_segment_overrun) - - /* runs on exception stack */ -ENTRY(double_fault) - XCPT_FRAME - PARAVIRT_ADJUST_EXCEPTION_FRAME - paranoidentry do_double_fault - jmp paranoid_exit1 - CFI_ENDPROC -END(double_fault) - -ENTRY(invalid_TSS) - errorentry do_invalid_TSS -END(invalid_TSS) - -ENTRY(segment_not_present) - errorentry do_segment_not_present -END(segment_not_present) - - /* runs on exception stack */ -ENTRY(stack_segment) - XCPT_FRAME - PARAVIRT_ADJUST_EXCEPTION_FRAME - paranoidentry do_stack_segment - jmp paranoid_exit1 - CFI_ENDPROC -END(stack_segment) - -KPROBE_ENTRY(general_protection) - errorentry do_general_protection -KPROBE_END(general_protection) - -ENTRY(alignment_check) - errorentry do_alignment_check -END(alignment_check) - -ENTRY(divide_error) - zeroentry do_divide_error -END(divide_error) - -ENTRY(spurious_interrupt_bug) - zeroentry do_spurious_interrupt_bug -END(spurious_interrupt_bug) - -#ifdef CONFIG_X86_MCE - /* runs on exception stack */ -ENTRY(machine_check) - INTR_FRAME - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq $0 - CFI_ADJUST_CFA_OFFSET 8 - paranoidentry do_machine_check - jmp paranoid_exit1 - CFI_ENDPROC -END(machine_check) -#endif +END(kernel_execve) /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(call_softirq) @@ -1344,40 +1229,33 @@ ENTRY(call_softirq) decl %gs:pda_irqcount ret CFI_ENDPROC -ENDPROC(call_softirq) - -KPROBE_ENTRY(ignore_sysret) - CFI_STARTPROC - mov $-ENOSYS,%eax - sysret - CFI_ENDPROC -ENDPROC(ignore_sysret) +END(call_softirq) #ifdef CONFIG_XEN -ENTRY(xen_hypervisor_callback) - zeroentry xen_do_hypervisor_callback -END(xen_hypervisor_callback) +zeroentry xen_hypervisor_callback xen_do_hypervisor_callback /* -# A note on the "critical region" in our callback handler. -# We want to avoid stacking callback handlers due to events occurring -# during handling of the last event. To do this, we keep events disabled -# until we've done all processing. HOWEVER, we must enable events before -# popping the stack frame (can't be done atomically) and so it would still -# be possible to get enough handler activations to overflow the stack. -# Although unlikely, bugs of that kind are hard to track down, so we'd -# like to avoid the possibility. -# So, on entry to the handler we detect whether we interrupted an -# existing activation in its critical region -- if so, we pop the current -# activation and restart the handler using the previous one. -*/ + * A note on the "critical region" in our callback handler. + * We want to avoid stacking callback handlers due to events occurring + * during handling of the last event. To do this, we keep events disabled + * until we've done all processing. HOWEVER, we must enable events before + * popping the stack frame (can't be done atomically) and so it would still + * be possible to get enough handler activations to overflow the stack. + * Although unlikely, bugs of that kind are hard to track down, so we'd + * like to avoid the possibility. + * So, on entry to the handler we detect whether we interrupted an + * existing activation in its critical region -- if so, we pop the current + * activation and restart the handler using the previous one. + */ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) CFI_STARTPROC -/* Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will - see the correct pointer to the pt_regs */ +/* + * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will + * see the correct pointer to the pt_regs + */ movq %rdi, %rsp # we don't return, adjust the stack frame CFI_ENDPROC - CFI_DEFAULT_STACK + DEFAULT_FRAME 11: incl %gs:pda_irqcount movq %rsp,%rbp CFI_DEF_CFA_REGISTER rbp @@ -1392,23 +1270,26 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) END(do_hypervisor_callback) /* -# Hypervisor uses this for application faults while it executes. -# We get here for two reasons: -# 1. Fault while reloading DS, ES, FS or GS -# 2. Fault while executing IRET -# Category 1 we do not need to fix up as Xen has already reloaded all segment -# registers that could be reloaded and zeroed the others. -# Category 2 we fix up by killing the current process. We cannot use the -# normal Linux return path in this case because if we use the IRET hypercall -# to pop the stack frame we end up in an infinite loop of failsafe callbacks. -# We distinguish between categories by comparing each saved segment register -# with its current contents: any discrepancy means we in category 1. -*/ + * Hypervisor uses this for application faults while it executes. + * We get here for two reasons: + * 1. Fault while reloading DS, ES, FS or GS + * 2. Fault while executing IRET + * Category 1 we do not need to fix up as Xen has already reloaded all segment + * registers that could be reloaded and zeroed the others. + * Category 2 we fix up by killing the current process. We cannot use the + * normal Linux return path in this case because if we use the IRET hypercall + * to pop the stack frame we end up in an infinite loop of failsafe callbacks. + * We distinguish between categories by comparing each saved segment register + * with its current contents: any discrepancy means we in category 1. + */ ENTRY(xen_failsafe_callback) - framesz = (RIP-0x30) /* workaround buggy gas */ - _frame framesz - CFI_REL_OFFSET rcx, 0 - CFI_REL_OFFSET r11, 8 + INTR_FRAME 1 (6*8) + /*CFI_REL_OFFSET gs,GS*/ + /*CFI_REL_OFFSET fs,FS*/ + /*CFI_REL_OFFSET es,ES*/ + /*CFI_REL_OFFSET ds,DS*/ + CFI_REL_OFFSET r11,8 + CFI_REL_OFFSET rcx,0 movw %ds,%cx cmpw %cx,0x10(%rsp) CFI_REMEMBER_STATE @@ -1429,12 +1310,9 @@ ENTRY(xen_failsafe_callback) CFI_RESTORE r11 addq $0x30,%rsp CFI_ADJUST_CFA_OFFSET -0x30 - pushq $0 - CFI_ADJUST_CFA_OFFSET 8 - pushq %r11 - CFI_ADJUST_CFA_OFFSET 8 - pushq %rcx - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $0 /* RIP */ + pushq_cfi %r11 + pushq_cfi %rcx jmp general_protection CFI_RESTORE_STATE 1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ @@ -1444,11 +1322,223 @@ ENTRY(xen_failsafe_callback) CFI_RESTORE r11 addq $0x30,%rsp CFI_ADJUST_CFA_OFFSET -0x30 - pushq $0 - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $0 SAVE_ALL jmp error_exit CFI_ENDPROC END(xen_failsafe_callback) #endif /* CONFIG_XEN */ + +/* + * Some functions should be protected against kprobes + */ + .pushsection .kprobes.text, "ax" + +paranoidzeroentry_ist debug do_debug DEBUG_STACK +paranoidzeroentry_ist int3 do_int3 DEBUG_STACK +paranoiderrorentry stack_segment do_stack_segment +errorentry general_protection do_general_protection +errorentry page_fault do_page_fault +#ifdef CONFIG_X86_MCE +paranoidzeroentry machine_check do_machine_check +#endif + + /* + * "Paranoid" exit path from exception stack. + * Paranoid because this is used by NMIs and cannot take + * any kernel state for granted. + * We don't do kernel preemption checks here, because only + * NMI should be common and it does not enable IRQs and + * cannot get reschedule ticks. + * + * "trace" is 0 for the NMI handler only, because irq-tracing + * is fundamentally NMI-unsafe. (we cannot change the soft and + * hard flags at once, atomically) + */ + + /* ebx: no swapgs flag */ +ENTRY(paranoid_exit) + INTR_FRAME + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + testl %ebx,%ebx /* swapgs needed? */ + jnz paranoid_restore + testl $3,CS(%rsp) + jnz paranoid_userspace +paranoid_swapgs: + TRACE_IRQS_IRETQ 0 + SWAPGS_UNSAFE_STACK +paranoid_restore: + RESTORE_ALL 8 + jmp irq_return +paranoid_userspace: + GET_THREAD_INFO(%rcx) + movl TI_flags(%rcx),%ebx + andl $_TIF_WORK_MASK,%ebx + jz paranoid_swapgs + movq %rsp,%rdi /* &pt_regs */ + call sync_regs + movq %rax,%rsp /* switch stack for scheduling */ + testl $_TIF_NEED_RESCHED,%ebx + jnz paranoid_schedule + movl %ebx,%edx /* arg3: thread flags */ + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + xorl %esi,%esi /* arg2: oldset */ + movq %rsp,%rdi /* arg1: &pt_regs */ + call do_notify_resume + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + jmp paranoid_userspace +paranoid_schedule: + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_ANY) + call schedule + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF + jmp paranoid_userspace + CFI_ENDPROC +END(paranoid_exit) + +/* + * Exception entry point. This expects an error code/orig_rax on the stack. + * returns in "no swapgs flag" in %ebx. + */ +ENTRY(error_entry) + XCPT_FRAME + CFI_ADJUST_CFA_OFFSET 15*8 + /* oldrax contains error code */ + cld + movq_cfi rdi, RDI+8 + movq_cfi rsi, RSI+8 + movq_cfi rdx, RDX+8 + movq_cfi rcx, RCX+8 + movq_cfi rax, RAX+8 + movq_cfi r8, R8+8 + movq_cfi r9, R9+8 + movq_cfi r10, R10+8 + movq_cfi r11, R11+8 + movq_cfi rbx, RBX+8 + movq_cfi rbp, RBP+8 + movq_cfi r12, R12+8 + movq_cfi r13, R13+8 + movq_cfi r14, R14+8 + movq_cfi r15, R15+8 + xorl %ebx,%ebx + testl $3,CS+8(%rsp) + je error_kernelspace +error_swapgs: + SWAPGS +error_sti: + TRACE_IRQS_OFF + ret + CFI_ENDPROC + +/* + * There are two places in the kernel that can potentially fault with + * usergs. Handle them here. The exception handlers after iret run with + * kernel gs again, so don't set the user space flag. B stepping K8s + * sometimes report an truncated RIP for IRET exceptions returning to + * compat mode. Check for these here too. + */ +error_kernelspace: + incl %ebx + leaq irq_return(%rip),%rcx + cmpq %rcx,RIP+8(%rsp) + je error_swapgs + movl %ecx,%ecx /* zero extend */ + cmpq %rcx,RIP+8(%rsp) + je error_swapgs + cmpq $gs_change,RIP+8(%rsp) + je error_swapgs + jmp error_sti +END(error_entry) + + +/* ebx: no swapgs flag (1: don't need swapgs, 0: need it) */ +ENTRY(error_exit) + DEFAULT_FRAME + movl %ebx,%eax + RESTORE_REST + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + GET_THREAD_INFO(%rcx) + testl %eax,%eax + jne retint_kernel + LOCKDEP_SYS_EXIT_IRQ + movl TI_flags(%rcx),%edx + movl $_TIF_WORK_MASK,%edi + andl %edi,%edx + jnz retint_careful + jmp retint_swapgs + CFI_ENDPROC +END(error_exit) + + + /* runs on exception stack */ +ENTRY(nmi) + INTR_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME + pushq_cfi $-1 + subq $15*8, %rsp + CFI_ADJUST_CFA_OFFSET 15*8 + call save_paranoid + DEFAULT_FRAME 0 + /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ + movq %rsp,%rdi + movq $-1,%rsi + call do_nmi +#ifdef CONFIG_TRACE_IRQFLAGS + /* paranoidexit; without TRACE_IRQS_OFF */ + /* ebx: no swapgs flag */ + DISABLE_INTERRUPTS(CLBR_NONE) + testl %ebx,%ebx /* swapgs needed? */ + jnz nmi_restore + testl $3,CS(%rsp) + jnz nmi_userspace +nmi_swapgs: + SWAPGS_UNSAFE_STACK +nmi_restore: + RESTORE_ALL 8 + jmp irq_return +nmi_userspace: + GET_THREAD_INFO(%rcx) + movl TI_flags(%rcx),%ebx + andl $_TIF_WORK_MASK,%ebx + jz nmi_swapgs + movq %rsp,%rdi /* &pt_regs */ + call sync_regs + movq %rax,%rsp /* switch stack for scheduling */ + testl $_TIF_NEED_RESCHED,%ebx + jnz nmi_schedule + movl %ebx,%edx /* arg3: thread flags */ + ENABLE_INTERRUPTS(CLBR_NONE) + xorl %esi,%esi /* arg2: oldset */ + movq %rsp,%rdi /* arg1: &pt_regs */ + call do_notify_resume + DISABLE_INTERRUPTS(CLBR_NONE) + jmp nmi_userspace +nmi_schedule: + ENABLE_INTERRUPTS(CLBR_ANY) + call schedule + DISABLE_INTERRUPTS(CLBR_ANY) + jmp nmi_userspace + CFI_ENDPROC +#else + jmp paranoid_exit + CFI_ENDPROC +#endif +END(nmi) + +ENTRY(ignore_sysret) + CFI_STARTPROC + mov $-ENOSYS,%eax + sysret + CFI_ENDPROC +END(ignore_sysret) + +/* + * End of kprobes section + */ + .popsection diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c index f454c78fcef..0aa2c443d60 100644 --- a/arch/x86/kernel/es7000_32.c +++ b/arch/x86/kernel/es7000_32.c @@ -250,31 +250,24 @@ int __init find_unisys_acpi_oem_table(unsigned long *oem_addr) { struct acpi_table_header *header = NULL; int i = 0; - acpi_size tbl_size; - while (ACPI_SUCCESS(acpi_get_table_with_size("OEM1", i++, &header, &tbl_size))) { + while (ACPI_SUCCESS(acpi_get_table("OEM1", i++, &header))) { if (!memcmp((char *) &header->oem_id, "UNISYS", 6)) { struct oem_table *t = (struct oem_table *)header; oem_addrX = t->OEMTableAddr; oem_size = t->OEMTableSize; - early_acpi_os_unmap_memory(header, tbl_size); *oem_addr = (unsigned long)__acpi_map_table(oem_addrX, oem_size); return 0; } - early_acpi_os_unmap_memory(header, tbl_size); } return -1; } void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr) { - if (!oem_addr) - return; - - __acpi_unmap_table((char *)oem_addr, oem_size); } #endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d073d981a73..50ea0ac8c9b 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -21,8 +21,7 @@ #include <asm/nops.h> -/* Long is fine, even if it is only 4 bytes ;-) */ -static unsigned long *ftrace_nop; +static unsigned char ftrace_nop[MCOUNT_INSN_SIZE]; union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; @@ -33,17 +32,17 @@ union ftrace_code_union { }; -static int notrace ftrace_calc_offset(long ip, long addr) +static int ftrace_calc_offset(long ip, long addr) { return (int)(addr - ip); } -notrace unsigned char *ftrace_nop_replace(void) +unsigned char *ftrace_nop_replace(void) { - return (char *)ftrace_nop; + return ftrace_nop; } -notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) { static union ftrace_code_union calc; @@ -57,7 +56,7 @@ notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) return calc.code; } -notrace int +int ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code) { @@ -66,26 +65,31 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, /* * Note: Due to modules and __init, code can * disappear and change, we need to protect against faulting - * as well as code changing. + * as well as code changing. We do this by using the + * probe_kernel_* functions. * * No real locking needed, this code is run through * kstop_machine, or before SMP starts. */ - if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE)) - return 1; + /* read the text we want to modify */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) - return 2; + return -EINVAL; - WARN_ON_ONCE(__copy_to_user_inatomic((char __user *)ip, new_code, - MCOUNT_INSN_SIZE)); + /* replace the text with the new text */ + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) + return -EPERM; sync_core(); return 0; } -notrace int ftrace_update_ftrace_func(ftrace_func_t func) +int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); unsigned char old[MCOUNT_INSN_SIZE], *new; @@ -98,13 +102,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } -notrace int ftrace_mcount_set(unsigned long *data) -{ - /* mcount is initialized as a nop */ - *data = 0; - return 0; -} - int __init ftrace_dyn_arch_init(void *data) { extern const unsigned char ftrace_test_p6nop[]; @@ -127,9 +124,6 @@ int __init ftrace_dyn_arch_init(void *data) * TODO: check the cpuid to determine the best nop. */ asm volatile ( - "jmp ftrace_test_jmp\n" - /* This code needs to stay around */ - ".section .text, \"ax\"\n" "ftrace_test_jmp:" "jmp ftrace_test_p6nop\n" "nop\n" @@ -140,8 +134,6 @@ int __init ftrace_dyn_arch_init(void *data) "jmp 1f\n" "ftrace_test_nop5:" ".byte 0x66,0x66,0x66,0x66,0x90\n" - "jmp 1f\n" - ".previous\n" "1:" ".section .fixup, \"ax\"\n" "2: movl $1, %0\n" @@ -156,15 +148,15 @@ int __init ftrace_dyn_arch_init(void *data) switch (faulted) { case 0: pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n"); - ftrace_nop = (unsigned long *)ftrace_test_p6nop; + memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE); break; case 1: pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n"); - ftrace_nop = (unsigned long *)ftrace_test_nop5; + memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE); break; case 2: pr_info("ftrace: converting mcount calls to jmp . + 5\n"); - ftrace_nop = (unsigned long *)ftrace_test_jmp; + memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE); break; } diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c index 680a06557c5..2c7dbdb9827 100644 --- a/arch/x86/kernel/genx2apic_uv_x.c +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -15,7 +15,6 @@ #include <linux/ctype.h> #include <linux/init.h> #include <linux/sched.h> -#include <linux/bootmem.h> #include <linux/module.h> #include <linux/hardirq.h> #include <asm/smp.h> @@ -398,16 +397,16 @@ void __init uv_system_init(void) printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades()); bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades(); - uv_blade_info = alloc_bootmem_pages(bytes); + uv_blade_info = kmalloc(bytes, GFP_KERNEL); get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size); bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes(); - uv_node_to_blade = alloc_bootmem_pages(bytes); + uv_node_to_blade = kmalloc(bytes, GFP_KERNEL); memset(uv_node_to_blade, 255, bytes); bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus(); - uv_cpu_to_blade = alloc_bootmem_pages(bytes); + uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL); memset(uv_cpu_to_blade, 255, bytes); blade = 0; diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 77017e834cf..067d8de913f 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -322,7 +322,7 @@ static int hpet_next_event(unsigned long delta, * what we wrote hit the chip before we compare it to the * counter. */ - WARN_ON((u32)hpet_readl(HPET_T0_CMP) != cnt); + WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt); return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; } @@ -445,7 +445,7 @@ static int hpet_setup_irq(struct hpet_dev *dev) { if (request_irq(dev->irq, hpet_interrupt_handler, - IRQF_SHARED|IRQF_NOBALANCING, dev->name, dev)) + IRQF_DISABLED|IRQF_NOBALANCING, dev->name, dev)) return -1; disable_irq(dev->irq); diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index dd7ebee446a..43cec6bdda6 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -5,7 +5,7 @@ #include <asm/desc.h> #include <asm/ftrace.h> -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER /* mcount is defined in assembly */ EXPORT_SYMBOL(mcount); #endif diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 1f20608d4ca..b0f61f0dcd0 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -58,7 +58,7 @@ void __cpuinit mxcsr_feature_mask_init(void) stts(); } -void __init init_thread_xstate(void) +void __cpuinit init_thread_xstate(void) { if (!HAVE_HWFP) { xstate_size = sizeof(struct i387_soft_struct); diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index b764d7429c6..9043251210f 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -1140,6 +1140,20 @@ static void __clear_irq_vector(int irq) cfg->vector = 0; cpus_clear(cfg->domain); + + if (likely(!cfg->move_in_progress)) + return; + cpus_and(mask, cfg->old_domain, cpu_online_map); + for_each_cpu_mask_nr(cpu, mask) { + for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; + vector++) { + if (per_cpu(vector_irq, cpu)[vector] != irq) + continue; + per_cpu(vector_irq, cpu)[vector] = -1; + break; + } + } + cfg->move_in_progress = 0; } void __setup_vector_irq(int cpu) @@ -3594,25 +3608,7 @@ int __init io_apic_get_redir_entries (int ioapic) int __init probe_nr_irqs(void) { - int idx; - int nr = 0; -#ifndef CONFIG_XEN - int nr_min = 32; -#else - int nr_min = NR_IRQS; -#endif - - for (idx = 0; idx < nr_ioapics; idx++) - nr += io_apic_get_redir_entries(idx) + 1; - - /* double it for hotplug and msi and nmi */ - nr <<= 1; - - /* something wrong ? */ - if (nr < nr_min) - nr = nr_min; - - return nr; + return NR_IRQS; } /* -------------------------------------------------------------------------- @@ -3759,7 +3755,9 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity) void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; + struct irq_desc *desc; struct irq_cfg *cfg; + cpumask_t mask; if (skip_ioapic_setup == 1) return; @@ -3776,16 +3774,30 @@ void __init setup_ioapic_dest(void) * cpu is online. */ cfg = irq_cfg(irq); - if (!cfg->vector) + if (!cfg->vector) { setup_IO_APIC_irq(ioapic, pin, irq, irq_trigger(irq_entry), irq_polarity(irq_entry)); + continue; + + } + + /* + * Honour affinities which have been set in early boot + */ + desc = irq_to_desc(irq); + if (desc->status & + (IRQ_NO_BALANCING | IRQ_AFFINITY_SET)) + mask = desc->affinity; + else + mask = TARGET_CPUS; + #ifdef CONFIG_INTR_REMAP - else if (intr_remapping_enabled) - set_ir_ioapic_affinity_irq(irq, TARGET_CPUS); -#endif + if (intr_remapping_enabled) + set_ir_ioapic_affinity_irq(irq, mask); else - set_ioapic_affinity_irq(irq, TARGET_CPUS); +#endif + set_ioapic_affinity_irq(irq, mask); } } diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 60eb84eb77a..1d3d0e71b04 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -18,7 +18,6 @@ #include <asm/idle.h> #include <asm/smp.h> -#ifdef CONFIG_DEBUG_STACKOVERFLOW /* * Probabilistic stack overflow check: * @@ -28,19 +27,18 @@ */ static inline void stack_overflow_check(struct pt_regs *regs) { +#ifdef CONFIG_DEBUG_STACKOVERFLOW u64 curbase = (u64)task_stack_page(current); - static unsigned long warned = -60*HZ; - - if (regs->sp >= curbase && regs->sp <= curbase + THREAD_SIZE && - regs->sp < curbase + sizeof(struct thread_info) + 128 && - time_after(jiffies, warned + 60*HZ)) { - printk("do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n", - current->comm, curbase, regs->sp); - show_stack(NULL,NULL); - warned = jiffies; - } -} + + WARN_ONCE(regs->sp >= curbase && + regs->sp <= curbase + THREAD_SIZE && + regs->sp < curbase + sizeof(struct thread_info) + + sizeof(struct pt_regs) + 128, + + "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n", + current->comm, curbase, regs->sp); #endif +} /* * do_IRQ handles all normal device IRQ's (the special @@ -60,9 +58,7 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs) irq_enter(); irq = __get_cpu_var(vector_irq)[vector]; -#ifdef CONFIG_DEBUG_STACKOVERFLOW stack_overflow_check(regs); -#endif desc = irq_to_desc(irq); if (likely(desc)) diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c index 845aa9803e8..607db63044a 100644 --- a/arch/x86/kernel/irqinit_32.c +++ b/arch/x86/kernel/irqinit_32.c @@ -129,7 +129,7 @@ void __init native_init_IRQ(void) for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) { /* SYSCALL_VECTOR was reserved in trap_init. */ if (i != SYSCALL_VECTOR) - set_intr_gate(i, interrupt[i]); + set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]); } diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index ff023539128..8670b3ce626 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -24,41 +24,6 @@ #include <asm/i8259.h> /* - * Common place to define all x86 IRQ vectors - * - * This builds up the IRQ handler stubs using some ugly macros in irq.h - * - * These macros create the low-level assembly IRQ routines that save - * register context and call do_IRQ(). do_IRQ() then does all the - * operations that are needed to keep the AT (or SMP IOAPIC) - * interrupt-controller happy. - */ - -#define IRQ_NAME2(nr) nr##_interrupt(void) -#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr) - -/* - * SMP has a few special interrupts for IPI messages - */ - -#define BUILD_IRQ(nr) \ - asmlinkage void IRQ_NAME(nr); \ - asm("\n.text\n.p2align\n" \ - "IRQ" #nr "_interrupt:\n\t" \ - "push $~(" #nr ") ; " \ - "jmp common_interrupt\n" \ - ".previous"); - -#define BI(x,y) \ - BUILD_IRQ(x##y) - -#define BUILD_16_IRQS(x) \ - BI(x,0) BI(x,1) BI(x,2) BI(x,3) \ - BI(x,4) BI(x,5) BI(x,6) BI(x,7) \ - BI(x,8) BI(x,9) BI(x,a) BI(x,b) \ - BI(x,c) BI(x,d) BI(x,e) BI(x,f) - -/* * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts: * (these are usually mapped to vectors 0x30-0x3f) */ @@ -73,37 +38,6 @@ * * (these are usually mapped into the 0x30-0xff vector range) */ - BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3) -BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7) -BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb) -BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf) - -#undef BUILD_16_IRQS -#undef BI - - -#define IRQ(x,y) \ - IRQ##x##y##_interrupt - -#define IRQLIST_16(x) \ - IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \ - IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \ - IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \ - IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f) - -/* for the irq vectors */ -static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = { - IRQLIST_16(0x2), IRQLIST_16(0x3), - IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7), - IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb), - IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf) -}; - -#undef IRQ -#undef IRQLIST_16 - - - /* * IRQ2 is cascade interrupt to second interrupt controller diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c index 304d8bad655..cbc4332a77b 100644 --- a/arch/x86/kernel/k8.c +++ b/arch/x86/kernel/k8.c @@ -18,7 +18,6 @@ static u32 *flush_words; struct pci_device_id k8_nb_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) }, {} }; EXPORT_SYMBOL(k8_nb_ids); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 774ac499156..e169ae9b6a6 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -128,7 +128,7 @@ static int kvm_register_clock(char *txt) } #ifdef CONFIG_X86_LOCAL_APIC -static void kvm_setup_secondary_clock(void) +static void __cpuinit kvm_setup_secondary_clock(void) { /* * Now that the first cpu already had this clocksource initialized, diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 0732adba05c..7a385746509 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -162,7 +162,10 @@ void machine_kexec(struct kimage *image) page_list[VA_PTE_0] = (unsigned long)kexec_pte0; page_list[PA_PTE_1] = __pa(kexec_pte1); page_list[VA_PTE_1] = (unsigned long)kexec_pte1; - page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT); + + if (image->type == KEXEC_TYPE_DEFAULT) + page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) + << PAGE_SHIFT); /* The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7a1f8eeac2c..5f8e5d75a25 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -39,7 +39,7 @@ #include <asm/microcode.h> MODULE_DESCRIPTION("AMD Microcode Update Driver"); -MODULE_AUTHOR("Peter Oruba <peter.oruba@amd.com>"); +MODULE_AUTHOR("Peter Oruba"); MODULE_LICENSE("GPL v2"); #define UCODE_MAGIC 0x00414d44 diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 936d8d55f23..82fb2809ce3 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -480,8 +480,8 @@ static int __init microcode_init(void) printk(KERN_INFO "Microcode Update Driver: v" MICROCODE_VERSION - " <tigran@aivazian.fsnet.co.uk>" - " <peter.oruba@amd.com>\n"); + " <tigran@aivazian.fsnet.co.uk>," + " Peter Oruba\n"); return 0; } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index f98f4e1dba0..0f4c1fd5a1f 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -604,6 +604,9 @@ static void __init __get_smp_config(unsigned int early) printk(KERN_INFO "Using ACPI for processor (LAPIC) " "configuration information\n"); + if (!mpf) + return; + printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index e1e731d78f3..d28bbdc35e4 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -1567,7 +1567,7 @@ static int __init calgary_parse_options(char *p) ++p; if (*p == '\0') break; - bridge = simple_strtol(p, &endp, 0); + bridge = simple_strtoul(p, &endp, 0); if (p == endp) break; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 1972266e8ba..19262482021 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -9,6 +9,8 @@ #include <asm/calgary.h> #include <asm/amd_iommu.h> +static int forbid_dac __read_mostly; + struct dma_mapping_ops *dma_ops; EXPORT_SYMBOL(dma_ops); @@ -291,3 +293,17 @@ void pci_iommu_shutdown(void) } /* Must execute after PCI subsystem */ fs_initcall(pci_iommu_init); + +#ifdef CONFIG_PCI +/* Many VIA bridges seem to corrupt data for DAC. Disable it here */ + +static __devinit void via_no_dac(struct pci_dev *dev) +{ + if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { + printk(KERN_INFO "PCI: VIA PCI bridge detected." + "Disabling DAC.\n"); + forbid_dac = 1; + } +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac); +#endif diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index e3f75bbcede..ba7ad83e20a 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -123,6 +123,8 @@ static void free_iommu(unsigned long offset, int size) spin_lock_irqsave(&iommu_bitmap_lock, flags); iommu_area_free(iommu_gart_bitmap, offset, size); + if (offset >= next_bit) + next_bit = offset + size; spin_unlock_irqrestore(&iommu_bitmap_lock, flags); } @@ -744,7 +746,7 @@ void __init gart_iommu_init(void) long i; if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) { - printk(KERN_INFO "PCI-GART: No AMD northbridge found.\n"); + printk(KERN_INFO "PCI-GART: No AMD GART found.\n"); return; } diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index c4ce0332759..3c539d111ab 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -18,9 +18,21 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); } +static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags) +{ + void *vaddr; + + vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags); + if (vaddr) + return vaddr; + + return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); +} + struct dma_mapping_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, - .alloc_coherent = swiotlb_alloc_coherent, + .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, .map_single = swiotlb_map_single_phys, .unmap_single = swiotlb_unmap_single, diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f4c93f1cfc1..cc5a2545dd4 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -29,11 +29,7 @@ EXPORT_SYMBOL(pm_power_off); static const struct desc_ptr no_idt = {}; static int reboot_mode; -/* - * Keyboard reset and triple fault may result in INIT, not RESET, which - * doesn't work when we're in vmx root mode. Try ACPI first. - */ -enum reboot_type reboot_type = BOOT_ACPI; +enum reboot_type reboot_type = BOOT_KBD; int reboot_force; #if defined(CONFIG_X86_32) && defined(CONFIG_SMP) @@ -173,6 +169,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "0KW626"), }, }, + { /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */ + .callback = set_bios_reboot, + .ident = "Dell OptiPlex 330", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"), + DMI_MATCH(DMI_BOARD_NAME, "0KP561"), + }, + }, { /* Handle problems with rebooting on Dell 2400's */ .callback = set_bios_reboot, .ident = "Dell PowerEdge 2400", diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0fa6790c1dd..9d5674f7b6c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -764,7 +764,7 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = { .callback = dmi_low_memory_corruption, .ident = "Phoenix BIOS", .matches = { - DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"), + DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"), }, }, #endif diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index cb19d650c21..418a095c579 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -80,6 +80,8 @@ unsigned long __init calibrate_cpu(void) break; no_ctr_free = (i == 4); if (no_ctr_free) { + WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... " + "cpu_khz value may be incorrect.\n"); i = 3; rdmsrl(MSR_K7_EVNTSEL3, evntsel3); wrmsrl(MSR_K7_EVNTSEL3, 0); diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c index e00534b3353..f4049f3513b 100644 --- a/arch/x86/kernel/tlb_32.c +++ b/arch/x86/kernel/tlb_32.c @@ -154,6 +154,12 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, 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. diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c index dcbf7a1159e..8f919ca6949 100644 --- a/arch/x86/kernel/tlb_64.c +++ b/arch/x86/kernel/tlb_64.c @@ -183,6 +183,11 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, cpus_or(f->flush_cpumask, cpumask, f->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. */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 161bb850fc4..424093b157d 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -55,7 +55,7 @@ u64 native_sched_clock(void) rdtscll(this_offset); /* return the value in ns */ - return cycles_2_ns(this_offset); + return __cycles_2_ns(this_offset); } /* We need to define a real function for sched_clock, to override the @@ -759,7 +759,7 @@ __cpuinit int unsynchronized_tsc(void) if (!cpu_has_tsc || tsc_unstable) return 1; -#ifdef CONFIG_SMP +#ifdef CONFIG_X86_SMP if (apic_is_clustered_box()) return 1; #endif @@ -813,10 +813,6 @@ void __init tsc_init(void) cpu_khz = calibrate_cpu(); #endif - lpj = ((u64)tsc_khz * 1000); - do_div(lpj, HZ); - lpj_fine = lpj; - printk("Detected %lu.%03lu MHz processor.\n", (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); @@ -836,6 +832,10 @@ void __init tsc_init(void) /* now allow native_sched_clock() to use rdtsc */ tsc_disabled = 0; + lpj = ((u64)tsc_khz * 1000); + do_div(lpj, HZ); + lpj_fine = lpj; + use_tsc_delay(); /* Check and install the TSC clocksource */ dmi_check_system(bad_tsc_dmi_table); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 9ffb01c31c4..1c0dfbca87c 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -46,7 +46,9 @@ static __cpuinit void check_tsc_warp(void) cycles_t start, now, prev, end; int i; + rdtsc_barrier(); start = get_cycles(); + rdtsc_barrier(); /* * The measurement runs for 20 msecs: */ @@ -61,7 +63,9 @@ static __cpuinit void check_tsc_warp(void) */ __raw_spin_lock(&sync_lock); prev = last_tsc; + rdtsc_barrier(); now = get_cycles(); + rdtsc_barrier(); last_tsc = now; __raw_spin_unlock(&sync_lock); diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 7766d36983f..a688f3bfaec 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -78,7 +78,7 @@ static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf, static void __init set_vsmp_pv_ops(void) { - void *address; + void __iomem *address; unsigned int cap, ctl, cfg; /* set vSMP magic bits to indicate vSMP capable kernel */ diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 0b8b6690a86..ebf2f12900f 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -128,7 +128,16 @@ static __always_inline void do_vgettimeofday(struct timeval * tv) gettimeofday(tv,NULL); return; } + + /* + * Surround the RDTSC by barriers, to make sure it's not + * speculated to outside the seqlock critical section and + * does not cause time warps: + */ + rdtsc_barrier(); now = vread(); + rdtsc_barrier(); + base = __vsyscall_gtod_data.clock.cycle_last; mask = __vsyscall_gtod_data.clock.mask; mult = __vsyscall_gtod_data.clock.mult; diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index b545f371b5f..695e426aa35 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -12,7 +12,7 @@ #include <asm/desc.h> #include <asm/ftrace.h> -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER /* mcount is defined in assembly */ EXPORT_SYMBOL(mcount); #endif diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index b13acb75e82..15c3e699918 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -310,7 +310,7 @@ static void __init setup_xstate_init(void) /* * Enable and initialize the xsave feature. */ -void __init xsave_cntxt_init(void) +void __ref xsave_cntxt_init(void) { unsigned int eax, ebx, ecx, edx; |