summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/.gitignore3
-rw-r--r--arch/x86/boot/compressed/mkpiggy.c2
-rw-r--r--arch/x86/boot/compressed/vmlinux.lds.S4
-rw-r--r--arch/x86/boot/video-vga.c3
-rw-r--r--arch/x86/include/asm/acpi.h2
-rw-r--r--arch/x86/include/asm/cache.h2
-rw-r--r--arch/x86/include/asm/cpufeature.h7
-rw-r--r--arch/x86/include/asm/io_apic.h4
-rw-r--r--arch/x86/include/asm/mce.h8
-rw-r--r--arch/x86/include/asm/msr-index.h1
-rw-r--r--arch/x86/include/asm/pci_x86.h2
-rw-r--r--arch/x86/include/asm/percpu.h2
-rw-r--r--arch/x86/include/asm/pgtable_32_types.h2
-rw-r--r--arch/x86/include/asm/rdc321x_defs.h12
-rw-r--r--arch/x86/include/asm/suspend_32.h2
-rw-r--r--arch/x86/include/asm/suspend_64.h2
-rw-r--r--arch/x86/include/asm/system.h2
-rw-r--r--arch/x86/include/asm/thread_info.h4
-rw-r--r--arch/x86/include/asm/x86_init.h2
-rw-r--r--arch/x86/kernel/acpi/boot.c27
-rw-r--r--arch/x86/kernel/acpi/sleep.c2
-rw-r--r--arch/x86/kernel/acpi/wakeup_32.S2
-rw-r--r--arch/x86/kernel/amd_iommu.c16
-rw-r--r--arch/x86/kernel/amd_iommu_init.c20
-rw-r--r--arch/x86/kernel/apic/apic.c41
-rw-r--r--arch/x86/kernel/apic/io_apic.c12
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.c6
-rw-r--r--arch/x86/kernel/cpu/mcheck/Makefile2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c138
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h23
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c89
-rw-r--r--arch/x86/kernel/cpu/perf_event.c22
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c4
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c1
-rw-r--r--arch/x86/kernel/e820.c2
-rw-r--r--arch/x86/kernel/init_task.c2
-rw-r--r--arch/x86/kernel/mpparse.c2
-rw-r--r--arch/x86/kernel/mrst.c7
-rw-r--r--arch/x86/kernel/pci-calgary_64.c17
-rw-r--r--arch/x86/kernel/reboot.c8
-rw-r--r--arch/x86/kernel/setup.c11
-rw-r--r--arch/x86/kernel/setup_percpu.c8
-rw-r--r--arch/x86/kernel/sfi.c2
-rw-r--r--arch/x86/kernel/smpboot.c28
-rw-r--r--arch/x86/kernel/traps.c11
-rw-r--r--arch/x86/kernel/vmlinux.lds.S4
-rw-r--r--arch/x86/kernel/x86_init.c7
-rw-r--r--arch/x86/kvm/mmu.c7
-rw-r--r--arch/x86/kvm/svm.c96
-rw-r--r--arch/x86/kvm/vmx.c7
-rw-r--r--arch/x86/lguest/boot.c1
-rw-r--r--arch/x86/mm/numa.c23
-rw-r--r--arch/x86/mm/pat.c12
-rw-r--r--arch/x86/mm/pat_internal.h6
-rw-r--r--arch/x86/mm/pat_rbtree.c42
-rw-r--r--arch/x86/mm/pgtable_32.c1
-rw-r--r--arch/x86/pci/acpi.c8
-rw-r--r--arch/x86/pci/i386.c2
-rw-r--r--arch/x86/pci/legacy.c42
-rw-r--r--arch/x86/power/cpu.c4
-rw-r--r--arch/x86/xen/suspend.c4
61 files changed, 629 insertions, 206 deletions
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore
new file mode 100644
index 00000000000..028079065af
--- /dev/null
+++ b/arch/x86/.gitignore
@@ -0,0 +1,3 @@
+boot/compressed/vmlinux
+tools/test_get_len
+
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index bcbd36c4143..5c228129d17 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -77,7 +77,7 @@ int main(int argc, char *argv[])
offs += 32*1024 + 18; /* Add 32K + 18 bytes slack */
offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
- printf(".section \".rodata.compressed\",\"a\",@progbits\n");
+ printf(".section \".rodata..compressed\",\"a\",@progbits\n");
printf(".globl z_input_len\n");
printf("z_input_len = %lu\n", ilen);
printf(".globl z_output_len\n");
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index a6f1a59a5b0..5ddabceee12 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -26,8 +26,8 @@ SECTIONS
HEAD_TEXT
_ehead = . ;
}
- .rodata.compressed : {
- *(.rodata.compressed)
+ .rodata..compressed : {
+ *(.rodata..compressed)
}
.text : {
_text = .; /* Text */
diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c
index ed7aeff786b..45bc9402aa4 100644
--- a/arch/x86/boot/video-vga.c
+++ b/arch/x86/boot/video-vga.c
@@ -41,13 +41,12 @@ static __videocard video_vga;
static u8 vga_set_basic_mode(void)
{
struct biosregs ireg, oreg;
- u16 ax;
u8 mode;
initregs(&ireg);
/* Query current mode */
- ax = 0x0f00;
+ ireg.ax = 0x0f00;
intcall(0x10, &ireg, &oreg);
mode = oreg.al;
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 56f462cf22d..aa2c39d968f 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -85,7 +85,6 @@ extern int acpi_ioapic;
extern int acpi_noirq;
extern int acpi_strict;
extern int acpi_disabled;
-extern int acpi_ht;
extern int acpi_pci_disabled;
extern int acpi_skip_timer_override;
extern int acpi_use_timer_override;
@@ -97,7 +96,6 @@ void acpi_pic_sci_set_trigger(unsigned int, u16);
static inline void disable_acpi(void)
{
acpi_disabled = 1;
- acpi_ht = 0;
acpi_pci_disabled = 1;
acpi_noirq = 1;
}
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index 2f9047cfaac..48f99f15452 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -7,7 +7,7 @@
#define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT)
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
#define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT
#define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT)
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index dca9c545f44..46814591438 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -332,6 +332,7 @@ static __always_inline __pure bool __static_cpu_has(u8 bit)
#endif
}
+#if __GNUC__ >= 4
#define static_cpu_has(bit) \
( \
__builtin_constant_p(boot_cpu_has(bit)) ? \
@@ -340,6 +341,12 @@ static __always_inline __pure bool __static_cpu_has(u8 bit)
__static_cpu_has(bit) : \
boot_cpu_has(bit) \
)
+#else
+/*
+ * gcc 3.x is too stupid to do the static test; fall back to dynamic.
+ */
+#define static_cpu_has(bit) boot_cpu_has(bit)
+#endif
#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 63cb4096c3d..9cb2edb87c2 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -183,7 +183,7 @@ struct mp_ioapic_gsi{
u32 gsi_end;
};
extern struct mp_ioapic_gsi mp_gsi_routing[];
-extern u32 gsi_end;
+extern u32 gsi_top;
int mp_find_ioapic(u32 gsi);
int mp_find_ioapic_pin(int ioapic, u32 gsi);
void __init mp_register_ioapic(int id, u32 address, u32 gsi_base);
@@ -197,7 +197,7 @@ static const int timer_through_8259 = 0;
static inline void ioapic_init_mappings(void) { }
static inline void ioapic_insert_resources(void) { }
static inline void probe_nr_irqs_gsi(void) { }
-#define gsi_end (NR_IRQS_LEGACY - 1)
+#define gsi_top (NR_IRQS_LEGACY)
static inline int mp_find_ioapic(u32 gsi) { return 0; }
struct io_apic_irq_attr;
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 6c3fdd631ed..f32a4301c4d 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -225,5 +225,13 @@ extern void mcheck_intel_therm_init(void);
static inline void mcheck_intel_therm_init(void) { }
#endif
+/*
+ * Used by APEI to report memory error via /dev/mcelog
+ */
+
+struct cper_sec_mem_err;
+extern void apei_mce_report_mem_error(int corrected,
+ struct cper_sec_mem_err *mem_err);
+
#endif /* __KERNEL__ */
#endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b49d8ca228f..8c7ae431862 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -110,6 +110,7 @@
#define MSR_AMD64_PATCH_LOADER 0xc0010020
#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
#define MSR_AMD64_OSVW_STATUS 0xc0010141
+#define MSR_AMD64_DC_CFG 0xc0011022
#define MSR_AMD64_IBSFETCHCTL 0xc0011030
#define MSR_AMD64_IBSFETCHLINAD 0xc0011031
#define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 8d8797eae5d..cd2a31dc5fb 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -53,6 +53,8 @@ extern int pcibios_last_bus;
extern struct pci_bus *pci_root_bus;
extern struct pci_ops pci_root_ops;
+void pcibios_scan_specific_bus(int busn);
+
/* pci-irq.c */
struct irq_info {
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0797e748d28..cd28f9ad910 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -77,6 +77,7 @@ do { \
if (0) { \
pto_T__ pto_tmp__; \
pto_tmp__ = (val); \
+ (void)pto_tmp__; \
} \
switch (sizeof(var)) { \
case 1: \
@@ -115,6 +116,7 @@ do { \
if (0) { \
pao_T__ pao_tmp__; \
pao_tmp__ = (val); \
+ (void)pao_tmp__; \
} \
switch (sizeof(var)) { \
case 1: \
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index 5e67c153231..ed5903be26f 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -26,7 +26,7 @@
*/
#define VMALLOC_OFFSET (8 * 1024 * 1024)
-#ifndef __ASSEMBLER__
+#ifndef __ASSEMBLY__
extern bool __vmalloc_start_set; /* set once high_memory is set */
#endif
diff --git a/arch/x86/include/asm/rdc321x_defs.h b/arch/x86/include/asm/rdc321x_defs.h
deleted file mode 100644
index c8e9c8bed3d..00000000000
--- a/arch/x86/include/asm/rdc321x_defs.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#define PFX "rdc321x: "
-
-/* General purpose configuration and data registers */
-#define RDC3210_CFGREG_ADDR 0x0CF8
-#define RDC3210_CFGREG_DATA 0x0CFC
-
-#define RDC321X_GPIO_CTRL_REG1 0x48
-#define RDC321X_GPIO_CTRL_REG2 0x84
-#define RDC321X_GPIO_DATA_REG1 0x4c
-#define RDC321X_GPIO_DATA_REG2 0x88
-
-#define RDC321X_MAX_GPIO 58
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 48dcfa62ea0..fd921c3a684 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -15,6 +15,8 @@ static inline int arch_prepare_suspend(void) { return 0; }
struct saved_context {
u16 es, fs, gs, ss;
unsigned long cr0, cr2, cr3, cr4;
+ u64 misc_enable;
+ bool misc_enable_saved;
struct desc_ptr gdt;
struct desc_ptr idt;
u16 ldt;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 06284f42b75..8d942afae68 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -27,6 +27,8 @@ struct saved_context {
u16 ds, es, fs, gs, ss;
unsigned long gs_base, gs_kernel_base, fs_base;
unsigned long cr0, cr2, cr3, cr4, cr8;
+ u64 misc_enable;
+ bool misc_enable_saved;
unsigned long efer;
u16 gdt_pad;
u16 gdt_limit;
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index b8fe48ee2ed..e7f4d33c55e 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -451,7 +451,7 @@ void stop_this_cpu(void *dummy);
*
* (Could use an alternative three way for this if there was one.)
*/
-static inline void rdtsc_barrier(void)
+static __always_inline void rdtsc_barrier(void)
{
alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 62ba9400cc4..f0b6e5dbc5a 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -239,8 +239,8 @@ static inline struct thread_info *current_thread_info(void)
#define TS_USEDFPU 0x0001 /* FPU was used by this task
this quantum (SMP) */
#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
-#define TS_POLLING 0x0004 /* true if in idle loop
- and not sleeping */
+#define TS_POLLING 0x0004 /* idle task polling need_resched,
+ skip sending interrupt */
#define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */
#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 519b54327d7..baa579c8e03 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -142,6 +142,7 @@ struct x86_cpuinit_ops {
* @set_wallclock: set time back to HW clock
* @is_untracked_pat_range exclude from PAT logic
* @nmi_init enable NMI on cpus
+ * @i8042_detect pre-detect if i8042 controller exists
*/
struct x86_platform_ops {
unsigned long (*calibrate_tsc)(void);
@@ -150,6 +151,7 @@ struct x86_platform_ops {
void (*iommu_shutdown)(void);
bool (*is_untracked_pat_range)(u64 start, u64 end);
void (*nmi_init)(void);
+ int (*i8042_detect)(void);
};
extern struct x86_init_ops x86_init;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 488be461a38..c05872aa3ce 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -63,7 +63,6 @@ EXPORT_SYMBOL(acpi_disabled);
int acpi_noirq; /* skip ACPI IRQ initialization */
int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */
EXPORT_SYMBOL(acpi_pci_disabled);
-int acpi_ht __initdata = 1; /* enable HT */
int acpi_lapic;
int acpi_ioapic;
@@ -119,7 +118,7 @@ static unsigned int gsi_to_irq(unsigned int gsi)
if (gsi >= NR_IRQS_LEGACY)
irq = gsi;
else
- irq = gsi_end + 1 + gsi;
+ irq = gsi_top + gsi;
return irq;
}
@@ -130,10 +129,10 @@ static u32 irq_to_gsi(int irq)
if (irq < NR_IRQS_LEGACY)
gsi = isa_irq_to_gsi[irq];
- else if (irq <= gsi_end)
+ else if (irq < gsi_top)
gsi = irq;
- else if (irq <= (gsi_end + NR_IRQS_LEGACY))
- gsi = irq - gsi_end;
+ else if (irq < (gsi_top + NR_IRQS_LEGACY))
+ gsi = irq - gsi_top;
else
gsi = 0xffffffff;
@@ -1501,9 +1500,8 @@ void __init acpi_boot_table_init(void)
/*
* If acpi_disabled, bail out
- * One exception: acpi=ht continues far enough to enumerate LAPICs
*/
- if (acpi_disabled && !acpi_ht)
+ if (acpi_disabled)
return;
/*
@@ -1534,9 +1532,8 @@ int __init early_acpi_boot_init(void)
{
/*
* If acpi_disabled, bail out
- * One exception: acpi=ht continues far enough to enumerate LAPICs
*/
- if (acpi_disabled && !acpi_ht)
+ if (acpi_disabled)
return 1;
/*
@@ -1554,9 +1551,8 @@ int __init acpi_boot_init(void)
/*
* If acpi_disabled, bail out
- * One exception: acpi=ht continues far enough to enumerate LAPICs
*/
- if (acpi_disabled && !acpi_ht)
+ if (acpi_disabled)
return 1;
acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
@@ -1591,21 +1587,12 @@ static int __init parse_acpi(char *arg)
/* acpi=force to over-ride black-list */
else if (strcmp(arg, "force") == 0) {
acpi_force = 1;
- acpi_ht = 1;
acpi_disabled = 0;
}
/* acpi=strict disables out-of-spec workarounds */
else if (strcmp(arg, "strict") == 0) {
acpi_strict = 1;
}
- /* Limit ACPI just to boot-time to enable HT */
- else if (strcmp(arg, "ht") == 0) {
- if (!acpi_force) {
- printk(KERN_WARNING "acpi=ht will be removed in Linux-2.6.35\n");
- disable_acpi();
- }
- acpi_ht = 1;
- }
/* acpi=rsdt use RSDT instead of XSDT */
else if (strcmp(arg, "rsdt") == 0) {
acpi_rsdt_forced = 1;
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index f9961034e55..82e508677b9 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -162,8 +162,6 @@ static int __init acpi_sleep_setup(char *str)
#endif
if (strncmp(str, "old_ordering", 12) == 0)
acpi_old_suspend_ordering();
- if (strncmp(str, "sci_force_enable", 16) == 0)
- acpi_set_sci_en_on_resume();
str = strchr(str, ',');
if (str != NULL)
str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 8ded418b059..13ab720573e 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -1,4 +1,4 @@
- .section .text.page_aligned
+ .section .text..page_aligned
#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/page_types.h>
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index fa5a1474cd1..0d20286d78c 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1487,6 +1487,7 @@ static int __attach_device(struct device *dev,
struct protection_domain *domain)
{
struct iommu_dev_data *dev_data, *alias_data;
+ int ret;
dev_data = get_dev_data(dev);
alias_data = get_dev_data(dev_data->alias);
@@ -1498,13 +1499,14 @@ static int __attach_device(struct device *dev,
spin_lock(&domain->lock);
/* Some sanity checks */
+ ret = -EBUSY;
if (alias_data->domain != NULL &&
alias_data->domain != domain)
- return -EBUSY;
+ goto out_unlock;
if (dev_data->domain != NULL &&
dev_data->domain != domain)
- return -EBUSY;
+ goto out_unlock;
/* Do real assignment */
if (dev_data->alias != dev) {
@@ -1520,10 +1522,14 @@ static int __attach_device(struct device *dev,
atomic_inc(&dev_data->bind);
+ ret = 0;
+
+out_unlock:
+
/* ready */
spin_unlock(&domain->lock);
- return 0;
+ return ret;
}
/*
@@ -2324,10 +2330,6 @@ int __init amd_iommu_init_dma_ops(void)
iommu_detected = 1;
swiotlb = 0;
-#ifdef CONFIG_GART_IOMMU
- gart_iommu_aperture_disabled = 1;
- gart_iommu_aperture = 0;
-#endif
/* Make the driver finally visible to the drivers */
dma_ops = &amd_iommu_dma_ops;
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 3bacb4d0844..3cc63e2b8dd 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -287,8 +287,12 @@ static u8 * __init iommu_map_mmio_space(u64 address)
{
u8 *ret;
- if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu"))
+ if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) {
+ pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n",
+ address);
+ pr_err("AMD-Vi: This is a BIOS bug. Please contact your hardware vendor\n");
return NULL;
+ }
ret = ioremap_nocache(address, MMIO_REGION_LENGTH);
if (ret != NULL)
@@ -1314,7 +1318,7 @@ static int __init amd_iommu_init(void)
ret = amd_iommu_init_dma_ops();
if (ret)
- goto free;
+ goto free_disable;
amd_iommu_init_api();
@@ -1332,9 +1336,10 @@ static int __init amd_iommu_init(void)
out:
return ret;
-free:
+free_disable:
disable_iommus();
+free:
amd_iommu_uninit_devices();
free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
@@ -1353,6 +1358,15 @@ free:
free_unity_maps();
+#ifdef CONFIG_GART_IOMMU
+ /*
+ * We failed to initialize the AMD IOMMU - try fallback to GART
+ * if possible.
+ */
+ gart_iommu_init();
+
+#endif
+
goto out;
}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e5a4a1e0161..c02cc692985 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -51,6 +51,7 @@
#include <asm/smp.h>
#include <asm/mce.h>
#include <asm/kvm_para.h>
+#include <asm/tsc.h>
unsigned int num_processors;
@@ -1151,8 +1152,13 @@ static void __cpuinit lapic_setup_esr(void)
*/
void __cpuinit setup_local_APIC(void)
{
- unsigned int value;
- int i, j;
+ unsigned int value, queued;
+ int i, j, acked = 0;
+ unsigned long long tsc = 0, ntsc;
+ long long max_loops = cpu_khz;
+
+ if (cpu_has_tsc)
+ rdtscll(tsc);
if (disable_apic) {
arch_disable_smp_support();
@@ -1204,13 +1210,32 @@ void __cpuinit setup_local_APIC(void)
* the interrupt. Hence a vector might get locked. It was noticed
* for timer irq (vector 0x31). Issue an extra EOI to clear ISR.
*/
- for (i = APIC_ISR_NR - 1; i >= 0; i--) {
- value = apic_read(APIC_ISR + i*0x10);
- for (j = 31; j >= 0; j--) {
- if (value & (1<<j))
- ack_APIC_irq();
+ do {
+ queued = 0;
+ for (i = APIC_ISR_NR - 1; i >= 0; i--)
+ queued |= apic_read(APIC_IRR + i*0x10);
+
+ for (i = APIC_ISR_NR - 1; i >= 0; i--) {
+ value = apic_read(APIC_ISR + i*0x10);
+ for (j = 31; j >= 0; j--) {
+ if (value & (1<<j)) {
+ ack_APIC_irq();
+ acked++;
+ }
+ }
}
- }
+ if (acked > 256) {
+ printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n",
+ acked);
+ break;
+ }
+ if (cpu_has_tsc) {
+ rdtscll(ntsc);
+ max_loops = (cpu_khz << 10) - (ntsc - tsc);
+ } else
+ max_loops--;
+ } while (queued && max_loops > 0);
+ WARN_ON(max_loops <= 0);
/*
* Now that we are all set up, enable the APIC
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 33f3563a2a5..e41ed24ab26 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -89,8 +89,8 @@ int nr_ioapics;
/* IO APIC gsi routing info */
struct mp_ioapic_gsi mp_gsi_routing[MAX_IO_APICS];
-/* The last gsi number used */
-u32 gsi_end;
+/* The one past the highest gsi number used */
+u32 gsi_top;
/* MP IRQ source entries */
struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
@@ -1035,7 +1035,7 @@ static int pin_2_irq(int idx, int apic, int pin)
if (gsi >= NR_IRQS_LEGACY)
irq = gsi;
else
- irq = gsi_end + 1 + gsi;
+ irq = gsi_top + gsi;
}
#ifdef CONFIG_X86_32
@@ -3853,7 +3853,7 @@ void __init probe_nr_irqs_gsi(void)
{
int nr;
- nr = gsi_end + 1 + NR_IRQS_LEGACY;
+ nr = gsi_top + NR_IRQS_LEGACY;
if (nr > nr_irqs_gsi)
nr_irqs_gsi = nr;
@@ -4294,8 +4294,8 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
*/
nr_ioapic_registers[idx] = entries;
- if (mp_gsi_routing[idx].gsi_end > gsi_end)
- gsi_end = mp_gsi_routing[idx].gsi_end;
+ if (mp_gsi_routing[idx].gsi_end >= gsi_top)
+ gsi_top = mp_gsi_routing[idx].gsi_end + 1;
printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
"GSI %d-%d\n", idx, mp_ioapics[idx].apicid,
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 6f3dc8fbbfd..7ec2123838e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1497,8 +1497,8 @@ static struct cpufreq_driver cpufreq_amd64_driver = {
* simply keep the boost-disable flag in sync with the current global
* state.
*/
-static int __cpuinit cpb_notify(struct notifier_block *nb, unsigned long action,
- void *hcpu)
+static int cpb_notify(struct notifier_block *nb, unsigned long action,
+ void *hcpu)
{
unsigned cpu = (long)hcpu;
u32 lo, hi;
@@ -1528,7 +1528,7 @@ static int __cpuinit cpb_notify(struct notifier_block *nb, unsigned long action,
return NOTIFY_OK;
}
-static struct notifier_block __cpuinitdata cpb_nb = {
+static struct notifier_block cpb_nb = {
.notifier_call = cpb_notify,
};
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index 4ac6d48fe11..bb34b03af25 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -7,3 +7,5 @@ obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o
obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
+
+obj-$(CONFIG_ACPI_APEI) += mce-apei.o
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
new file mode 100644
index 00000000000..745b54f9be8
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -0,0 +1,138 @@
+/*
+ * Bridge between MCE and APEI
+ *
+ * On some machine, corrected memory errors are reported via APEI
+ * generic hardware error source (GHES) instead of corrected Machine
+ * Check. These corrected memory errors can be reported to user space
+ * through /dev/mcelog via faking a corrected Machine Check, so that
+ * the error memory page can be offlined by /sbin/mcelog if the error
+ * count for one page is beyond the threshold.
+ *
+ * For fatal MCE, save MCE record into persistent storage via ERST, so
+ * that the MCE record can be logged after reboot via ERST.
+ *
+ * Copyright 2010 Intel Corp.
+ * Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/acpi.h>
+#include <linux/cper.h>
+#include <acpi/apei.h>
+#include <asm/mce.h>
+
+#include "mce-internal.h"
+
+void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
+{
+ struct mce m;
+
+ /* Only corrected MC is reported */
+ if (!corrected)
+ return;
+
+ mce_setup(&m);
+ m.bank = 1;
+ /* Fake a memory read corrected error with unknown channel */
+ m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | 0x9f;
+ m.addr = mem_err->physical_addr;
+ mce_log(&m);
+ mce_notify_irq();
+}
+EXPORT_SYMBOL_GPL(apei_mce_report_mem_error);
+
+#define CPER_CREATOR_MCE \
+ UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \
+ 0x64, 0x90, 0xb8, 0x9d)
+#define CPER_SECTION_TYPE_MCE \
+ UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96, \
+ 0x04, 0x4a, 0x38, 0xfc)
+
+/*
+ * CPER specification (in UEFI specification 2.3 appendix N) requires
+ * byte-packed.
+ */
+struct cper_mce_record {
+ struct cper_record_header hdr;
+ struct cper_section_descriptor sec_hdr;
+ struct mce mce;
+} __packed;
+
+int apei_write_mce(struct mce *m)
+{
+ struct cper_mce_record rcd;
+
+ memset(&rcd, 0, sizeof(rcd));
+ memcpy(rcd.hdr.signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
+ rcd.hdr.revision = CPER_RECORD_REV;
+ rcd.hdr.signature_end = CPER_SIG_END;
+ rcd.hdr.section_count = 1;
+ rcd.hdr.error_severity = CPER_SER_FATAL;
+ /* timestamp, platform_id, partition_id are all invalid */
+ rcd.hdr.validation_bits = 0;
+ rcd.hdr.record_length = sizeof(rcd);
+ rcd.hdr.creator_id = CPER_CREATOR_MCE;
+ rcd.hdr.notification_type = CPER_NOTIFY_MCE;
+ rcd.hdr.record_id = cper_next_record_id();
+ rcd.hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR;
+
+ rcd.sec_hdr.section_offset = (void *)&rcd.mce - (void *)&rcd;
+ rcd.sec_hdr.section_length = sizeof(rcd.mce);
+ rcd.sec_hdr.revision = CPER_SEC_REV;
+ /* fru_id and fru_text is invalid */
+ rcd.sec_hdr.validation_bits = 0;
+ rcd.sec_hdr.flags = CPER_SEC_PRIMARY;
+ rcd.sec_hdr.section_type = CPER_SECTION_TYPE_MCE;
+ rcd.sec_hdr.section_severity = CPER_SER_FATAL;
+
+ memcpy(&rcd.mce, m, sizeof(*m));
+
+ return erst_write(&rcd.hdr);
+}
+
+ssize_t apei_read_mce(struct mce *m, u64 *record_id)
+{
+ struct cper_mce_record rcd;
+ ssize_t len;
+
+ len = erst_read_next(&rcd.hdr, sizeof(rcd));
+ if (len <= 0)
+ return len;
+ /* Can not skip other records in storage via ERST unless clear them */
+ else if (len != sizeof(rcd) ||
+ uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) {
+ if (printk_ratelimit())
+ pr_warning(
+ "MCE-APEI: Can not skip the unknown record in ERST");
+ return -EIO;
+ }
+
+ memcpy(m, &rcd.mce, sizeof(*m));
+ *record_id = rcd.hdr.record_id;
+
+ return sizeof(*m);
+}
+
+/* Check whether there is record in ERST */
+int apei_check_mce(void)
+{
+ return erst_get_record_count();
+}
+
+int apei_clear_mce(u64 record_id)
+{
+ return erst_clear(record_id);
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 32996f9fab6..fefcc69ee8b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -28,3 +28,26 @@ extern int mce_ser;
extern struct mce_bank *mce_banks;
+#ifdef CONFIG_ACPI_APEI
+int apei_write_mce(struct mce *m);
+ssize_t apei_read_mce(struct mce *m, u64 *record_id);
+int apei_check_mce(void);
+int apei_clear_mce(u64 record_id);
+#else
+static inline int apei_write_mce(struct mce *m)
+{
+ return -EINVAL;
+}
+static inline ssize_t apei_read_mce(struct mce *m, u64 *record_id)
+{
+ return 0;
+}
+static inline int apei_check_mce(void)
+{
+ return 0;
+}
+static inline int apei_clear_mce(u64 record_id)
+{
+ return -EINVAL;
+}
+#endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7a355ddcc64..18cc4256225 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -36,6 +36,7 @@
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/debugfs.h>
+#include <linux/edac_mce.h>
#include <asm/processor.h>
#include <asm/hw_irq.h>
@@ -169,6 +170,15 @@ void mce_log(struct mce *mce)
entry = rcu_dereference_check_mce(mcelog.next);
for (;;) {
/*
+ * If edac_mce is enabled, it will check the error type
+ * and will process it, if it is a known error.
+ * Otherwise, the error will be sent through mcelog
+ * interface
+ */
+ if (edac_mce_parse(mce))
+ return;
+
+ /*
* When the buffer fills up discard new entries.
* Assume that the earlier errors are the more
* interesting ones:
@@ -264,7 +274,7 @@ static void wait_for_panic(void)
static void mce_panic(char *msg, struct mce *final, char *exp)
{
- int i;
+ int i, apei_err = 0;
if (!fake_panic) {
/*
@@ -287,8 +297,11 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
struct mce *m = &mcelog.entry[i];
if (!(m->status & MCI_STATUS_VAL))
continue;
- if (!(m->status & MCI_STATUS_UC))
+ if (!(m->status & MCI_STATUS_UC)) {
print_mce(m);
+ if (!apei_err)
+ apei_err = apei_write_mce(m);
+ }
}
/* Now print uncorrected but with the final one last */
for (i = 0; i < MCE_LOG_LEN; i++) {
@@ -297,11 +310,17 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
continue;
if (!(m->status & MCI_STATUS_UC))
continue;
- if (!final || memcmp(m, final, sizeof(struct mce)))
+ if (!final || memcmp(m, final, sizeof(struct mce))) {
print_mce(m);
+ if (!apei_err)
+ apei_err = apei_write_mce(m);
+ }
}
- if (final)
+ if (final) {
print_mce(final);
+ if (!apei_err)
+ apei_err = apei_write_mce(final);
+ }
if (cpu_missing)
printk(KERN_EMERG "Some CPUs didn't answer in synchronization\n");
print_mce_tail();
@@ -1493,6 +1512,43 @@ static void collect_tscs(void *data)
rdtscll(cpu_tsc[smp_processor_id()]);
}
+static int mce_apei_read_done;
+
+/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
+static int __mce_read_apei(char __user **ubuf, size_t usize)
+{
+ int rc;
+ u64 record_id;
+ struct mce m;
+
+ if (usize < sizeof(struct mce))
+ return -EINVAL;
+
+ rc = apei_read_mce(&m, &record_id);
+ /* Error or no more MCE record */
+ if (rc <= 0) {
+ mce_apei_read_done = 1;
+ return rc;
+ }
+ rc = -EFAULT;
+ if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
+ return rc;
+ /*
+ * In fact, we should have cleared the record after that has
+ * been flushed to the disk or sent to network in
+ * /sbin/mcelog, but we have no interface to support that now,
+ * so just clear it to avoid duplication.
+ */
+ rc = apei_clear_mce(record_id);
+ if (rc) {
+ mce_apei_read_done = 1;
+ return rc;
+ }
+ *ubuf += sizeof(struct mce);
+
+ return 0;
+}
+
static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
loff_t *off)
{
@@ -1506,15 +1562,19 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
return -ENOMEM;
mutex_lock(&mce_read_mutex);
+
+ if (!mce_apei_read_done) {
+ err = __mce_read_apei(&buf, usize);
+ if (err || buf != ubuf)
+ goto out;
+ }
+
next = rcu_dereference_check_mce(mcelog.next);
/* Only supports full reads right now */
- if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
- mutex_unlock(&mce_read_mutex);
- kfree(cpu_tsc);
-
- return -EINVAL;
- }
+ err = -EINVAL;
+ if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
+ goto out;
err = 0;
prev = 0;
@@ -1562,10 +1622,15 @@ timeout:
memset(&mcelog.entry[i], 0, sizeof(struct mce));
}
}
+
+ if (err)
+ err = -EFAULT;
+
+out:
mutex_unlock(&mce_read_mutex);
kfree(cpu_tsc);
- return err ? -EFAULT : buf - ubuf;
+ return err ? err : buf - ubuf;
}
static unsigned int mce_poll(struct file *file, poll_table *wait)
@@ -1573,6 +1638,8 @@ static unsigned int mce_poll(struct file *file, poll_table *wait)
poll_wait(file, &mce_wait, wait);
if (rcu_dereference_check_mce(mcelog.next))
return POLLIN | POLLRDNORM;
+ if (!mce_apei_read_done && apei_check_mce())
+ return POLLIN | POLLRDNORM;
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c77586061bc..5db5b7d65a1 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -106,6 +106,7 @@ struct cpu_hw_events {
int n_events;
int n_added;
+ int n_txn;
int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
u64 tags[X86_PMC_IDX_MAX];
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
@@ -983,6 +984,7 @@ static int x86_pmu_enable(struct perf_event *event)
out:
cpuc->n_events = n;
cpuc->n_added += n - n0;
+ cpuc->n_txn += n - n0;
return 0;
}
@@ -1089,6 +1091,14 @@ static void x86_pmu_disable(struct perf_event *event)
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
int i;
+ /*
+ * If we're called during a txn, we don't need to do anything.
+ * The events never got scheduled and ->cancel_txn will truncate
+ * the event_list.
+ */
+ if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+ return;
+
x86_pmu_stop(event);
for (i = 0; i < cpuc->n_events; i++) {
@@ -1379,6 +1389,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
cpuc->group_flag |= PERF_EVENT_TXN_STARTED;
+ cpuc->n_txn = 0;
}
/*
@@ -1391,6 +1402,11 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED;
+ /*
+ * Truncate the collected events.
+ */
+ cpuc->n_added -= cpuc->n_txn;
+ cpuc->n_events -= cpuc->n_txn;
}
/*
@@ -1419,6 +1435,12 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
*/
memcpy(cpuc->assign, assign, n*sizeof(int));
+ /*
+ * Clear out the txn count so that ->cancel_txn() which gets
+ * run after ->commit_txn() doesn't undo things.
+ */
+ cpuc->n_txn = 0;
+
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 611df11ba15..c2897b7b4a3 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -102,8 +102,8 @@ static const u64 amd_perfmon_event_map[] =
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
[PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
[PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
};
static u64 amd_pmu_event_map(int hw_event)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index fdbc652d3fe..214ac860ebe 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -72,6 +72,7 @@ static struct event_constraint intel_westmere_event_constraints[] =
INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
+ INTEL_EVENT_CONSTRAINT(0xb3, 0x1), /* SNOOPQ_REQUEST_OUTSTANDING */
EVENT_CONSTRAINT_END
};
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7bca3c6a02f..0d6fc71bedb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -729,7 +729,7 @@ static int __init e820_mark_nvs_memory(void)
struct e820entry *ei = &e820.map[i];
if (ei->type == E820_NVS)
- hibernate_nvs_register(ei->addr, ei->size);
+ suspend_nvs_register(ei->addr, ei->size);
}
return 0;
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
index 3a54dcb9cd0..43e9ccf4494 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -34,7 +34,7 @@ EXPORT_SYMBOL(init_task);
/*
* per-CPU TSS segments. Threads are completely 'soft' on Linux,
* no more per-task TSS's. The TSS size is kept cacheline-aligned
- * so they are allowed to end up in the .data.cacheline_aligned
+ * so they are allowed to end up in the .data..cacheline_aligned
* section. Since TSS's are completely CPU-local, we want them
* on exact cacheline boundaries, to eliminate cacheline ping-pong.
*/
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 5ae5d2426ed..d86dbf7e54b 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -123,7 +123,7 @@ static void __init MP_ioapic_info(struct mpc_ioapic *m)
printk(KERN_INFO "I/O APIC #%d Version %d at 0x%X.\n",
m->apicid, m->apicver, m->apicaddr);
- mp_register_ioapic(m->apicid, m->apicaddr, gsi_end + 1);
+ mp_register_ioapic(m->apicid, m->apicaddr, gsi_top);
}
static void print_MP_intsrc_info(struct mpc_intsrc *m)
diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c
index e796448f0eb..5915e0b3330 100644
--- a/arch/x86/kernel/mrst.c
+++ b/arch/x86/kernel/mrst.c
@@ -216,6 +216,12 @@ static void __init mrst_setup_boot_clock(void)
setup_boot_APIC_clock();
};
+/* MID systems don't have i8042 controller */
+static int mrst_i8042_detect(void)
+{
+ return 0;
+}
+
/*
* Moorestown specific x86_init function overrides and early setup
* calls.
@@ -233,6 +239,7 @@ void __init x86_mrst_early_setup(void)
x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock;
x86_platform.calibrate_tsc = mrst_calibrate_tsc;
+ x86_platform.i8042_detect = mrst_i8042_detect;
x86_init.pci.init = pci_mrst_init;
x86_init.pci.fixup_irqs = x86_init_noop;
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index fb99f7edb34..078d4ec1a9d 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -103,11 +103,16 @@ int use_calgary __read_mostly = 0;
#define PMR_SOFTSTOPFAULT 0x40000000
#define PMR_HARDSTOP 0x20000000
-#define MAX_NUM_OF_PHBS 8 /* how many PHBs in total? */
-#define MAX_NUM_CHASSIS 8 /* max number of chassis */
-/* MAX_PHB_BUS_NUM is the maximal possible dev->bus->number */
-#define MAX_PHB_BUS_NUM (MAX_NUM_OF_PHBS * MAX_NUM_CHASSIS * 2)
-#define PHBS_PER_CALGARY 4
+/*
+ * The maximum PHB bus number.
+ * x3950M2 (rare): 8 chassis, 48 PHBs per chassis = 384
+ * x3950M2: 4 chassis, 48 PHBs per chassis = 192
+ * x3950 (PCIE): 8 chassis, 32 PHBs per chassis = 256
+ * x3950 (PCIX): 8 chassis, 16 PHBs per chassis = 128
+ */
+#define MAX_PHB_BUS_NUM 256
+
+#define PHBS_PER_CALGARY 4
/* register offsets in Calgary's internal register space */
static const unsigned long tar_offsets[] = {
@@ -1051,8 +1056,6 @@ static int __init calgary_init_one(struct pci_dev *dev)
struct iommu_table *tbl;
int ret;
- BUG_ON(dev->bus->number >= MAX_PHB_BUS_NUM);
-
bbar = busno_to_bbar(dev->bus->number);
ret = calgary_setup_tar(dev, bbar);
if (ret)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 8e1aac86b50..e3af342fe83 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -228,6 +228,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T5400"),
},
},
+ { /* Handle problems with rebooting on Dell T7400's */
+ .callback = set_bios_reboot,
+ .ident = "Dell Precision T7400",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T7400"),
+ },
+ },
{ /* Handle problems with rebooting on HP laptops */
.callback = set_bios_reboot,
.ident = "HP Compaq Laptop",
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index e8029896309..b4ae4acbd03 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -676,6 +676,17 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
},
},
+ /*
+ * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so
+ * match on the product name.
+ */
+ {
+ .callback = dmi_low_memory_corruption,
+ .ident = "Phoenix BIOS",
+ .matches = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"),
+ },
+ },
#endif
{}
};
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index a867940a6df..de3b63ae3da 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -21,12 +21,6 @@
#include <asm/cpu.h>
#include <asm/stackprotector.h>
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(fmt, ...) pr_dbg(fmt, ##__VA_ARGS__)
-#else
-# define DBG(fmt, ...) do { if (0) pr_dbg(fmt, ##__VA_ARGS__); } while (0)
-#endif
-
DEFINE_PER_CPU(int, cpu_number);
EXPORT_PER_CPU_SYMBOL(cpu_number);
@@ -247,7 +241,7 @@ void __init setup_per_cpu_areas(void)
#endif
#endif
/*
- * Up to this point, the boot CPU has been using .data.init
+ * Up to this point, the boot CPU has been using .init.data
* area. Reload any changed state for the boot CPU.
*/
if (cpu == boot_cpu_id)
diff --git a/arch/x86/kernel/sfi.c b/arch/x86/kernel/sfi.c
index 7ded57896c0..cb22acf3ed0 100644
--- a/arch/x86/kernel/sfi.c
+++ b/arch/x86/kernel/sfi.c
@@ -93,7 +93,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table)
pentry = (struct sfi_apic_table_entry *)sb->pentry;
for (i = 0; i < num; i++) {
- mp_register_ioapic(i, pentry->phys_addr, gsi_end + 1);
+ mp_register_ioapic(i, pentry->phys_addr, gsi_top);
pentry++;
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 763d815e27a..c4f33b2e77d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -686,7 +686,7 @@ static void __cpuinit do_fork_idle(struct work_struct *work)
static void __cpuinit announce_cpu(int cpu, int apicid)
{
static int current_node = -1;
- int node = cpu_to_node(cpu);
+ int node = early_cpu_to_node(cpu);
if (system_state == SYSTEM_BOOTING) {
if (node != current_node) {
@@ -1215,9 +1215,17 @@ __init void prefill_possible_map(void)
if (!num_processors)
num_processors = 1;
- if (setup_possible_cpus == -1)
- possible = num_processors + disabled_cpus;
- else
+ i = setup_max_cpus ?: 1;
+ if (setup_possible_cpus == -1) {
+ possible = num_processors;
+#ifdef CONFIG_HOTPLUG_CPU
+ if (setup_max_cpus)
+ possible += disabled_cpus;
+#else
+ if (possible > i)
+ possible = i;
+#endif
+ } else
possible = setup_possible_cpus;
total_cpus = max_t(int, possible, num_processors + disabled_cpus);
@@ -1230,11 +1238,23 @@ __init void prefill_possible_map(void)
possible = nr_cpu_ids;
}
+#ifdef CONFIG_HOTPLUG_CPU
+ if (!setup_max_cpus)
+#endif
+ if (possible > i) {
+ printk(KERN_WARNING
+ "%d Processors exceeds max_cpus limit of %u\n",
+ possible, setup_max_cpus);
+ possible = i;
+ }
+
printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n",
possible, max_t(int, possible - num_processors, 0));
for (i = 0; i < possible; i++)
set_cpu_possible(i, true);
+ for (; i < NR_CPUS; i++)
+ set_cpu_possible(i, false);
nr_cpu_ids = possible;
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 142d70c74b0..725ef4d17cd 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -526,6 +526,7 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk = current;
+ int user_icebp = 0;
unsigned long dr6;
int si_code;
@@ -534,6 +535,14 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
/* Filter out all the reserved bits which are preset to 1 */
dr6 &= ~DR6_RESERVED;
+ /*
+ * If dr6 has no reason to give us about the origin of this trap,
+ * then it's very likely the result of an icebp/int01 trap.
+ * User wants a sigtrap for that.
+ */
+ if (!dr6 && user_mode(regs))
+ user_icebp = 1;
+
/* Catch kmemcheck conditions first of all! */
if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
return;
@@ -575,7 +584,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
regs->flags &= ~X86_EFLAGS_TF;
}
si_code = get_si_code(tsk->thread.debugreg6);
- if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS))
+ if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
send_sigtrap(tsk, regs, error_code, si_code);
preempt_conditional_cli(regs);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 2cc249718c4..d0bb52296fa 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -97,7 +97,7 @@ SECTIONS
HEAD_TEXT
#ifdef CONFIG_X86_32
. = ALIGN(PAGE_SIZE);
- *(.text.page_aligned)
+ *(.text..page_aligned)
#endif
. = ALIGN(8);
_stext = .;
@@ -305,7 +305,7 @@ SECTIONS
. = ALIGN(PAGE_SIZE);
.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
__bss_start = .;
- *(.bss.page_aligned)
+ *(.bss..page_aligned)
*(.bss)
. = ALIGN(4);
__bss_stop = .;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 61a1e8c7e19..cd6da6bf3ec 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -5,6 +5,7 @@
*/
#include <linux/init.h>
#include <linux/ioport.h>
+#include <linux/module.h>
#include <asm/bios_ebda.h>
#include <asm/paravirt.h>
@@ -85,6 +86,7 @@ struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
};
static void default_nmi_init(void) { };
+static int default_i8042_detect(void) { return 1; };
struct x86_platform_ops x86_platform = {
.calibrate_tsc = native_calibrate_tsc,
@@ -92,5 +94,8 @@ struct x86_platform_ops x86_platform = {
.set_wallclock = mach_set_rtc_mmss,
.iommu_shutdown = iommu_shutdown_noop,
.is_untracked_pat_range = is_ISA_range,
- .nmi_init = default_nmi_init
+ .nmi_init = default_nmi_init,
+ .i8042_detect = default_i8042_detect
};
+
+EXPORT_SYMBOL_GPL(x86_platform);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 81563e76e28..3699613e883 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1815,6 +1815,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
spte |= PT_WRITABLE_MASK;
+ if (!tdp_enabled && !(pte_access & ACC_WRITE_MASK))
+ spte &= ~PT_USER_MASK;
+
/*
* Optimization: for pte sync, if spte was writable the hash
* lookup is unnecessary (and expensive). Write protection
@@ -1870,10 +1873,14 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
child = page_header(pte & PT64_BASE_ADDR_MASK);
mmu_page_remove_parent_pte(child, sptep);
+ __set_spte(sptep, shadow_trap_nonpresent_pte);
+ kvm_flush_remote_tlbs(vcpu->kvm);
} else if (pfn != spte_to_pfn(*sptep)) {
pgprintk("hfn old %lx new %lx\n",
spte_to_pfn(*sptep), pfn);
rmap_remove(vcpu->kvm, sptep);
+ __set_spte(sptep, shadow_trap_nonpresent_pte);
+ kvm_flush_remote_tlbs(vcpu->kvm);
} else
was_rmapped = 1;
}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 96dc232bfc5..ce438e0fdd2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -28,6 +28,7 @@
#include <linux/ftrace_event.h>
#include <linux/slab.h>
+#include <asm/tlbflush.h>
#include <asm/desc.h>
#include <asm/virtext.h>
@@ -56,6 +57,8 @@ MODULE_LICENSE("GPL");
#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+static bool erratum_383_found __read_mostly;
+
static const u32 host_save_user_msrs[] = {
#ifdef CONFIG_X86_64
MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
@@ -374,6 +377,31 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
svm->vmcb->control.event_inj_err = error_code;
}
+static void svm_init_erratum_383(void)
+{
+ u32 low, high;
+ int err;
+ u64 val;
+
+ /* Only Fam10h is affected */
+ if (boot_cpu_data.x86 != 0x10)
+ return;
+
+ /* Use _safe variants to not break nested virtualization */
+ val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
+ if (err)
+ return;
+
+ val |= (1ULL << 47);
+
+ low = lower_32_bits(val);
+ high = upper_32_bits(val);
+
+ native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
+
+ erratum_383_found = true;
+}
+
static int has_svm(void)
{
const char *msg;
@@ -429,6 +457,8 @@ static int svm_hardware_enable(void *garbage)
wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
+ svm_init_erratum_383();
+
return 0;
}
@@ -1410,8 +1440,59 @@ static int nm_interception(struct vcpu_svm *svm)
return 1;
}
-static int mc_interception(struct vcpu_svm *svm)
+static bool is_erratum_383(void)
{
+ int err, i;
+ u64 value;
+
+ if (!erratum_383_found)
+ return false;
+
+ value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
+ if (err)
+ return false;
+
+ /* Bit 62 may or may not be set for this mce */
+ value &= ~(1ULL << 62);
+
+ if (value != 0xb600000000010015ULL)
+ return false;
+
+ /* Clear MCi_STATUS registers */
+ for (i = 0; i < 6; ++i)
+ native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
+
+ value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
+ if (!err) {
+ u32 low, high;
+
+ value &= ~(1ULL << 2);
+ low = lower_32_bits(value);
+ high = upper_32_bits(value);
+
+ native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
+ }
+
+ /* Flush tlb to evict multi-match entries */
+ __flush_tlb_all();
+
+ return true;
+}
+
+static void svm_handle_mce(struct vcpu_svm *svm)
+{
+ if (is_erratum_383()) {
+ /*
+ * Erratum 383 triggered. Guest state is corrupt so kill the
+ * guest.
+ */
+ pr_err("KVM: Guest triggered AMD Erratum 383\n");
+
+ set_bit(KVM_REQ_TRIPLE_FAULT, &svm->vcpu.requests);
+
+ return;
+ }
+
/*
* On an #MC intercept the MCE handler is not called automatically in
* the host. So do it by hand here.
@@ -1420,6 +1501,11 @@ static int mc_interception(struct vcpu_svm *svm)
"int $0x12\n");
/* not sure if we ever come back to this point */
+ return;
+}
+
+static int mc_interception(struct vcpu_svm *svm)
+{
return 1;
}
@@ -3088,6 +3174,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);
vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR);
}
+
+ /*
+ * We need to handle MC intercepts here before the vcpu has a chance to
+ * change the physical cpu
+ */
+ if (unlikely(svm->vmcb->control.exit_code ==
+ SVM_EXIT_EXCP_BASE + MC_VECTOR))
+ svm_handle_mce(svm);
}
#undef R
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 859a01a07db..ee03679efe7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1744,18 +1744,15 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
(guest_tr_ar & ~AR_TYPE_MASK)
| AR_TYPE_BUSY_64_TSS);
}
- vcpu->arch.efer |= EFER_LMA;
- vmx_set_efer(vcpu, vcpu->arch.efer);
+ vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA);
}
static void exit_lmode(struct kvm_vcpu *vcpu)
{
- vcpu->arch.efer &= ~EFER_LMA;
-
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS)
& ~VM_ENTRY_IA32E_MODE);
- vmx_set_efer(vcpu, vcpu->arch.efer);
+ vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA);
}
#endif
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 2bdf628066b..9257510b483 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1390,7 +1390,6 @@ __init void lguest_init(void)
#endif
#ifdef CONFIG_ACPI
acpi_disabled = 1;
- acpi_ht = 0;
#endif
/*
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 10c27bb1e95..787c52ca49c 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -2,13 +2,6 @@
#include <linux/topology.h>
#include <linux/module.h>
#include <linux/bootmem.h>
-#include <linux/random.h>
-
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(x...) printk(KERN_DEBUG x)
-#else
-# define DBG(x...)
-#endif
/*
* Which logical CPUs are on which nodes
@@ -66,19 +59,3 @@ const struct cpumask *cpumask_of_node(int node)
}
EXPORT_SYMBOL(cpumask_of_node);
#endif
-
-/*
- * Return the bit number of a random bit set in the nodemask.
- * (returns -1 if nodemask is empty)
- */
-int __node_random(const nodemask_t *maskp)
-{
- int w, bit = -1;
-
- w = nodes_weight(*maskp);
- if (w)
- bit = bitmap_ord_to_pos(maskp->bits,
- get_random_int() % w, MAX_NUMNODES);
- return bit;
-}
-EXPORT_SYMBOL(__node_random);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index bbe5502ee1c..64121a18b8c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -302,7 +302,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
return -EINVAL;
}
- new = kmalloc(sizeof(struct memtype), GFP_KERNEL);
+ new = kzalloc(sizeof(struct memtype), GFP_KERNEL);
if (!new)
return -ENOMEM;
@@ -336,6 +336,7 @@ int free_memtype(u64 start, u64 end)
{
int err = -EINVAL;
int is_range_ram;
+ struct memtype *entry;
if (!pat_enabled)
return 0;
@@ -355,17 +356,20 @@ int free_memtype(u64 start, u64 end)
}
spin_lock(&memtype_lock);
- err = rbt_memtype_erase(start, end);
+ entry = rbt_memtype_erase(start, end);
spin_unlock(&memtype_lock);
- if (err) {
+ if (!entry) {
printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n",
current->comm, current->pid, start, end);
+ return -EINVAL;
}
+ kfree(entry);
+
dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end);
- return err;
+ return 0;
}
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index 4f39eefa3e6..77e5ba153fa 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -28,15 +28,15 @@ static inline char *cattr_name(unsigned long flags)
#ifdef CONFIG_X86_PAT
extern int rbt_memtype_check_insert(struct memtype *new,
unsigned long *new_type);
-extern int rbt_memtype_erase(u64 start, u64 end);
+extern struct memtype *rbt_memtype_erase(u64 start, u64 end);
extern struct memtype *rbt_memtype_lookup(u64 addr);
extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos);
#else
static inline int rbt_memtype_check_insert(struct memtype *new,
unsigned long *new_type)
{ return 0; }
-static inline int rbt_memtype_erase(u64 start, u64 end)
-{ return 0; }
+static inline struct memtype *rbt_memtype_erase(u64 start, u64 end)
+{ return NULL; }
static inline struct memtype *rbt_memtype_lookup(u64 addr)
{ return NULL; }
static inline int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 07de4cb8cc3..8acaddd0fb2 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -34,8 +34,7 @@
* memtype_lock protects the rbtree.
*/
-static void memtype_rb_augment_cb(struct rb_node *node);
-static struct rb_root memtype_rbroot = RB_AUGMENT_ROOT(&memtype_rb_augment_cb);
+static struct rb_root memtype_rbroot = RB_ROOT;
static int is_node_overlap(struct memtype *node, u64 start, u64 end)
{
@@ -56,7 +55,7 @@ static u64 get_subtree_max_end(struct rb_node *node)
}
/* Update 'subtree_max_end' for a node, based on node and its children */
-static void update_node_max_end(struct rb_node *node)
+static void memtype_rb_augment_cb(struct rb_node *node, void *__unused)
{
struct memtype *data;
u64 max_end, child_max_end;
@@ -78,25 +77,6 @@ static void update_node_max_end(struct rb_node *node)
data->subtree_max_end = max_end;
}
-/* Update 'subtree_max_end' for a node and all its ancestors */
-static void update_path_max_end(struct rb_node *node)
-{
- u64 old_max_end, new_max_end;
-
- while (node) {
- struct memtype *data = container_of(node, struct memtype, rb);
-
- old_max_end = data->subtree_max_end;
- update_node_max_end(node);
- new_max_end = data->subtree_max_end;
-
- if (new_max_end == old_max_end)
- break;
-
- node = rb_parent(node);
- }
-}
-
/* Find the first (lowest start addr) overlapping range from rb tree */
static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
u64 start, u64 end)
@@ -190,12 +170,6 @@ failure:
return -EBUSY;
}
-static void memtype_rb_augment_cb(struct rb_node *node)
-{
- if (node)
- update_path_max_end(node);
-}
-
static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
{
struct rb_node **node = &(root->rb_node);
@@ -213,6 +187,7 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
rb_link_node(&newdata->rb, parent, node);
rb_insert_color(&newdata->rb, root);
+ rb_augment_insert(&newdata->rb, memtype_rb_augment_cb, NULL);
}
int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type)
@@ -226,21 +201,26 @@ int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type)
if (ret_type)
new->type = *ret_type;
+ new->subtree_max_end = new->end;
memtype_rb_insert(&memtype_rbroot, new);
}
return err;
}
-int rbt_memtype_erase(u64 start, u64 end)
+struct memtype *rbt_memtype_erase(u64 start, u64 end)
{
+ struct rb_node *deepest;
struct memtype *data;
data = memtype_rb_exact_match(&memtype_rbroot, start, end);
if (!data)
- return -EINVAL;
+ goto out;
+ deepest = rb_augment_erase_begin(&data->rb);
rb_erase(&data->rb, &memtype_rbroot);
- return 0;
+ rb_augment_erase_end(deepest, memtype_rb_augment_cb, NULL);
+out:
+ return data;
}
struct memtype *rbt_memtype_lookup(u64 addr)
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 792854003ed..cac71849925 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -9,7 +9,6 @@
#include <linux/pagemap.h>
#include <linux/spinlock.h>
#include <linux/module.h>
-#include <linux/quicklist.h>
#include <asm/system.h>
#include <asm/pgtable.h>
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 31930fd30ea..2ec04c424a6 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -207,10 +207,9 @@ get_current_resources(struct acpi_device *device, int busnum,
if (!info.res)
goto res_alloc_fail;
- info.name = kmalloc(16, GFP_KERNEL);
+ info.name = kasprintf(GFP_KERNEL, "PCI Bus %04x:%02x", domain, busnum);
if (!info.name)
goto name_alloc_fail;
- sprintf(info.name, "PCI Bus %04x:%02x", domain, busnum);
info.res_num = 0;
acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
@@ -224,8 +223,11 @@ res_alloc_fail:
return;
}
-struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int domain, int busnum)
+struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
{
+ struct acpi_device *device = root->device;
+ int domain = root->segment;
+ int busnum = root->secondary.start;
struct pci_bus *bus;
struct pci_sysdata *sd;
int node;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 97da2ba9344..6fdb3ec30c3 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -96,6 +96,7 @@ EXPORT_SYMBOL(pcibios_align_resource);
* the fact the PCI specs explicitly allow address decoders to be
* shared between expansion ROMs and other resource regions, it's
* at least dangerous)
+ * - bad resource sizes or overlaps with other regions
*
* Our solution:
* (1) Allocate resources for all buses behind PCI-to-PCI bridges.
@@ -136,6 +137,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
* child resource allocations in this
* range.
*/
+ r->start = r->end = 0;
r->flags = 0;
}
}
diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c
index 0db5eaf5456..8d460eaf524 100644
--- a/arch/x86/pci/legacy.c
+++ b/arch/x86/pci/legacy.c
@@ -11,28 +11,14 @@
*/
static void __devinit pcibios_fixup_peer_bridges(void)
{
- int n, devfn;
- long node;
+ int n;
if (pcibios_last_bus <= 0 || pcibios_last_bus > 0xff)
return;
DBG("PCI: Peer bridge fixup\n");
- for (n=0; n <= pcibios_last_bus; n++) {
- u32 l;
- if (pci_find_bus(0, n))
- continue;
- node = get_mp_bus_to_node(n);
- for (devfn = 0; devfn < 256; devfn += 8) {
- if (!raw_pci_read(0, n, devfn, PCI_VENDOR_ID, 2, &l) &&
- l != 0x0000 && l != 0xffff) {
- DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l);
- printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n);
- pci_scan_bus_on_node(n, &pci_root_ops, node);
- break;
- }
- }
- }
+ for (n=0; n <= pcibios_last_bus; n++)
+ pcibios_scan_specific_bus(n);
}
int __init pci_legacy_init(void)
@@ -50,6 +36,28 @@ int __init pci_legacy_init(void)
return 0;
}
+void pcibios_scan_specific_bus(int busn)
+{
+ int devfn;
+ long node;
+ u32 l;
+
+ if (pci_find_bus(0, busn))
+ return;
+
+ node = get_mp_bus_to_node(busn);
+ for (devfn = 0; devfn < 256; devfn += 8) {
+ if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) &&
+ l != 0x0000 && l != 0xffff) {
+ DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l);
+ printk(KERN_INFO "PCI: Discovered peer bus %02x\n", busn);
+ pci_scan_bus_on_node(busn, &pci_root_ops, node);
+ return;
+ }
+ }
+}
+EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus);
+
int __init pci_subsys_init(void)
{
/*
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 0a979f3e5b8..1290ba54b35 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -105,6 +105,8 @@ static void __save_processor_state(struct saved_context *ctxt)
ctxt->cr4 = read_cr4();
ctxt->cr8 = read_cr8();
#endif
+ ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
+ &ctxt->misc_enable);
}
/* Needed by apm.c */
@@ -152,6 +154,8 @@ static void fix_processor_context(void)
*/
static void __restore_processor_state(struct saved_context *ctxt)
{
+ if (ctxt->misc_enable_saved)
+ wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
/*
* control registers
*/
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 987267f79bf..a9c66110803 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -60,6 +60,6 @@ static void xen_vcpu_notify_restore(void *data)
void xen_arch_resume(void)
{
- smp_call_function(xen_vcpu_notify_restore,
- (void *)CLOCK_EVT_NOTIFY_RESUME, 1);
+ on_each_cpu(xen_vcpu_notify_restore,
+ (void *)CLOCK_EVT_NOTIFY_RESUME, 1);
}