aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig23
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S5
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c14
-rw-r--r--arch/x86/ia32/ia32_aout.c1
-rw-r--r--arch/x86/ia32/ia32entry.S1
-rw-r--r--arch/x86/include/asm/acpi.h5
-rw-r--r--arch/x86/include/asm/apic.h1
-rw-r--r--arch/x86/include/asm/bitops.h4
-rw-r--r--arch/x86/include/asm/dma.h7
-rw-r--r--arch/x86/include/asm/gart.h24
-rw-r--r--arch/x86/include/asm/i387.h2
-rw-r--r--arch/x86/include/asm/mmu.h6
-rw-r--r--arch/x86/include/asm/msr-index.h4
-rw-r--r--arch/x86/include/asm/numa.h2
-rw-r--r--arch/x86/include/asm/percpu.h10
-rw-r--r--arch/x86/include/asm/thread_info.h10
-rw-r--r--arch/x86/include/asm/types.h16
-rw-r--r--arch/x86/include/asm/unistd_32.h3
-rw-r--r--arch/x86/include/asm/unistd_64.h2
-rw-r--r--arch/x86/kernel/Makefile3
-rw-r--r--arch/x86/kernel/acpi/sleep.c12
-rw-r--r--arch/x86/kernel/acpi/sleep.h2
-rw-r--r--arch/x86/kernel/amd_iommu_init.c26
-rw-r--r--arch/x86/kernel/amd_nb.c2
-rw-r--r--arch/x86/kernel/apb_timer.c2
-rw-r--r--arch/x86/kernel/aperture_64.c2
-rw-r--r--arch/x86/kernel/apic/apic.c33
-rw-r--r--arch/x86/kernel/apic/hw_nmi.c1
-rw-r--r--arch/x86/kernel/apic/io_apic.c97
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c10
-rw-r--r--arch/x86/kernel/apm_32.c5
-rw-r--r--arch/x86/kernel/cpu/amd.c19
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c42
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c23
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c30
-rw-r--r--arch/x86/kernel/cpu/perf_event.c17
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c22
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c9
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c3
-rw-r--r--arch/x86/kernel/crash_dump_32.c3
-rw-r--r--arch/x86/kernel/crash_dump_64.c3
-rw-r--r--arch/x86/kernel/devicetree.c6
-rw-r--r--arch/x86/kernel/dumpstack.c12
-rw-r--r--arch/x86/kernel/e820.c1
-rw-r--r--arch/x86/kernel/head64.c3
-rw-r--r--arch/x86/kernel/i8237.c30
-rw-r--r--arch/x86/kernel/i8259.c33
-rw-r--r--arch/x86/kernel/irq.c1
-rw-r--r--arch/x86/kernel/kgdb.c4
-rw-r--r--arch/x86/kernel/microcode_core.c35
-rw-r--r--arch/x86/kernel/mpparse.c8
-rw-r--r--arch/x86/kernel/pci-gart_64.c41
-rw-r--r--arch/x86/kernel/process_64.c8
-rw-r--r--arch/x86/kernel/reboot.c1
-rw-r--r--arch/x86/kernel/setup.c52
-rw-r--r--arch/x86/kernel/syscall_table_32.S1
-rw-r--r--arch/x86/kvm/x86.c37
-rw-r--r--arch/x86/lib/cmpxchg16b_emu.S14
-rw-r--r--arch/x86/mm/init_64.c27
-rw-r--r--arch/x86/mm/numa.c31
-rw-r--r--arch/x86/mm/numa_emulation.c20
-rw-r--r--arch/x86/mm/srat_32.c4
-rw-r--r--arch/x86/oprofile/nmi_int.c49
-rw-r--r--arch/x86/oprofile/op_counter.h1
-rw-r--r--arch/x86/platform/ce4100/falconfalls.dts2
-rw-r--r--arch/x86/platform/mrst/mrst.c10
-rw-r--r--arch/x86/platform/mrst/vrtc.c4
-rw-r--r--arch/x86/platform/olpc/olpc-xo1.c25
-rw-r--r--arch/x86/platform/uv/tlb_uv.c1
-rw-r--r--arch/x86/platform/visws/visws_quirks.c20
-rw-r--r--arch/x86/vdso/vdso32-setup.c15
-rw-r--r--arch/x86/xen/Kconfig1
-rw-r--r--arch/x86/xen/enlighten.c21
-rw-r--r--arch/x86/xen/mmu.c38
-rw-r--r--arch/x86/xen/p2m.c10
-rw-r--r--arch/x86/xen/setup.c2
76 files changed, 532 insertions, 542 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e1f65c46bc9..cc6c53a95bf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -71,6 +71,7 @@ config X86
select GENERIC_IRQ_SHOW
select IRQ_FORCED_THREADING
select USE_GENERIC_SMP_HELPERS if SMP
+ select ARCH_NO_SYSDEV_OPS
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS)
@@ -123,7 +124,7 @@ config NEED_SG_DMA_LENGTH
def_bool y
config GENERIC_ISA_DMA
- def_bool y
+ def_bool ISA_DMA_API
config GENERIC_IOMAP
def_bool y
@@ -143,7 +144,7 @@ config GENERIC_GPIO
bool
config ARCH_MAY_HAVE_PC_FDC
- def_bool y
+ def_bool ISA_DMA_API
config RWSEM_GENERIC_SPINLOCK
def_bool !X86_XADD
@@ -2002,9 +2003,13 @@ source "drivers/pci/pcie/Kconfig"
source "drivers/pci/Kconfig"
-# x86_64 have no ISA slots, but do have ISA-style DMA.
+# x86_64 have no ISA slots, but can have ISA-style DMA.
config ISA_DMA_API
- def_bool y
+ bool "ISA-style DMA support" if (X86_64 && EXPERT)
+ default y
+ help
+ Enables ISA-style DMA support for devices requiring such controllers.
+ If unsure, say Y.
if X86_32
@@ -2092,6 +2097,16 @@ source "drivers/pcmcia/Kconfig"
source "drivers/pci/hotplug/Kconfig"
+config RAPIDIO
+ bool "RapidIO support"
+ depends on PCI
+ default n
+ help
+ If you say Y here, the kernel will include drivers and
+ infrastructure code to support RapidIO interconnect devices.
+
+source "drivers/rapidio/Kconfig"
+
endmenu
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index adcf794b22e..be6d9e365a8 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -1612,6 +1612,7 @@ _zero_cipher_left_encrypt:
movdqa SHUF_MASK(%rip), %xmm10
PSHUFB_XMM %xmm10, %xmm0
+
ENCRYPT_SINGLE_BLOCK %xmm0, %xmm1 # Encrypt(K, Yn)
sub $16, %r11
add %r13, %r11
@@ -1634,7 +1635,9 @@ _zero_cipher_left_encrypt:
# GHASH computation for the last <16 byte block
sub %r13, %r11
add $16, %r11
- PSHUFB_XMM %xmm10, %xmm1
+
+ movdqa SHUF_MASK(%rip), %xmm10
+ PSHUFB_XMM %xmm10, %xmm0
# shuffle xmm0 back to output as ciphertext
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index e0e6340c8da..2577613fb32 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -828,9 +828,15 @@ static int rfc4106_init(struct crypto_tfm *tfm)
struct cryptd_aead *cryptd_tfm;
struct aesni_rfc4106_gcm_ctx *ctx = (struct aesni_rfc4106_gcm_ctx *)
PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN);
+ struct crypto_aead *cryptd_child;
+ struct aesni_rfc4106_gcm_ctx *child_ctx;
cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni", 0, 0);
if (IS_ERR(cryptd_tfm))
return PTR_ERR(cryptd_tfm);
+
+ cryptd_child = cryptd_aead_child(cryptd_tfm);
+ child_ctx = aesni_rfc4106_gcm_ctx_get(cryptd_child);
+ memcpy(child_ctx, ctx, sizeof(*ctx));
ctx->cryptd_tfm = cryptd_tfm;
tfm->crt_aead.reqsize = sizeof(struct aead_request)
+ crypto_aead_reqsize(&cryptd_tfm->base);
@@ -923,6 +929,9 @@ static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
int ret = 0;
struct crypto_tfm *tfm = crypto_aead_tfm(parent);
struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent);
+ struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm);
+ struct aesni_rfc4106_gcm_ctx *child_ctx =
+ aesni_rfc4106_gcm_ctx_get(cryptd_child);
u8 *new_key_mem = NULL;
if (key_len < 4) {
@@ -966,6 +975,7 @@ static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
goto exit;
}
ret = rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
+ memcpy(child_ctx, ctx, sizeof(*ctx));
exit:
kfree(new_key_mem);
return ret;
@@ -997,7 +1007,6 @@ static int rfc4106_encrypt(struct aead_request *req)
int ret;
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
- struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm);
if (!irq_fpu_usable()) {
struct aead_request *cryptd_req =
@@ -1006,6 +1015,7 @@ static int rfc4106_encrypt(struct aead_request *req)
aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
return crypto_aead_encrypt(cryptd_req);
} else {
+ struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm);
kernel_fpu_begin();
ret = cryptd_child->base.crt_aead.encrypt(req);
kernel_fpu_end();
@@ -1018,7 +1028,6 @@ static int rfc4106_decrypt(struct aead_request *req)
int ret;
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
- struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm);
if (!irq_fpu_usable()) {
struct aead_request *cryptd_req =
@@ -1027,6 +1036,7 @@ static int rfc4106_decrypt(struct aead_request *req)
aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
return crypto_aead_decrypt(cryptd_req);
} else {
+ struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm);
kernel_fpu_begin();
ret = cryptd_child->base.crt_aead.decrypt(req);
kernel_fpu_end();
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 2d93bdbc9ac..fd843877e84 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -298,6 +298,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
/* OK, This is the point of no return */
set_personality(PER_LINUX);
set_thread_flag(TIF_IA32);
+ current->mm->context.ia32_compat = 1;
setup_new_exec(bprm);
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 430312ba6e3..849a9d23c71 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -847,4 +847,5 @@ ia32_sys_call_table:
.quad sys_name_to_handle_at
.quad compat_sys_open_by_handle_at
.quad compat_sys_clock_adjtime
+ .quad sys_syncfs
ia32_syscall_end:
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 448d73a371b..12e0e7dd869 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -114,9 +114,8 @@ static inline void acpi_disable_pci(void)
acpi_noirq_set();
}
-/* routines for saving/restoring kernel state */
-extern int acpi_save_state_mem(void);
-extern void acpi_restore_state_mem(void);
+/* Low-level suspend routine. */
+extern int acpi_suspend_lowlevel(void);
extern const unsigned char acpi_wakeup_code[];
#define acpi_wakeup_address (__pa(TRAMPOLINE_SYM(acpi_wakeup_code)))
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a279d98ea95..2b7d573be54 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -2,7 +2,6 @@
#define _ASM_X86_APIC_H
#include <linux/cpumask.h>
-#include <linux/delay.h>
#include <linux/pm.h>
#include <asm/alternative.h>
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 903683b07e4..69d58131bc8 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -456,14 +456,12 @@ static inline int fls(int x)
#ifdef __KERNEL__
-#include <asm-generic/bitops/ext2-non-atomic.h>
+#include <asm-generic/bitops/le.h>
#define ext2_set_bit_atomic(lock, nr, addr) \
test_and_set_bit((nr), (unsigned long *)(addr))
#define ext2_clear_bit_atomic(lock, nr, addr) \
test_and_clear_bit((nr), (unsigned long *)(addr))
-#include <asm-generic/bitops/minix.h>
-
#endif /* __KERNEL__ */
#endif /* _ASM_X86_BITOPS_H */
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index ca1098a7e58..057099e5fab 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -10,7 +10,6 @@
#include <linux/spinlock.h> /* And spinlocks */
#include <asm/io.h> /* need byte IO */
-#include <linux/delay.h>
#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
#define dma_outb outb_p
@@ -151,6 +150,7 @@
#define DMA_AUTOINIT 0x10
+#ifdef CONFIG_ISA_DMA_API
extern spinlock_t dma_spin_lock;
static inline unsigned long claim_dma_lock(void)
@@ -164,6 +164,7 @@ static inline void release_dma_lock(unsigned long flags)
{
spin_unlock_irqrestore(&dma_spin_lock, flags);
}
+#endif /* CONFIG_ISA_DMA_API */
/* enable/disable a specific DMA channel */
static inline void enable_dma(unsigned int dmanr)
@@ -303,9 +304,11 @@ static inline int get_dma_residue(unsigned int dmanr)
}
-/* These are in kernel/dma.c: */
+/* These are in kernel/dma.c because x86 uses CONFIG_GENERIC_ISA_DMA */
+#ifdef CONFIG_ISA_DMA_API
extern int request_dma(unsigned int dmanr, const char *device_id);
extern void free_dma(unsigned int dmanr);
+#endif
/* From PCI */
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 43085bfc99c..156cd5d18d2 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -66,7 +66,7 @@ static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order)
* Don't enable translation but enable GART IO and CPU accesses.
* Also, set DISTLBWALKPRB since GART tables memory is UC.
*/
- ctl = DISTLBWALKPRB | order << 1;
+ ctl = order << 1;
pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
}
@@ -75,17 +75,17 @@ static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
{
u32 tmp, ctl;
- /* address of the mappings table */
- addr >>= 12;
- tmp = (u32) addr<<4;
- tmp &= ~0xf;
- pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
-
- /* Enable GART translation for this hammer. */
- pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
- ctl |= GARTEN;
- ctl &= ~(DISGARTCPU | DISGARTIO);
- pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+ /* address of the mappings table */
+ addr >>= 12;
+ tmp = (u32) addr<<4;
+ tmp &= ~0xf;
+ pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+
+ /* Enable GART translation for this hammer. */
+ pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+ ctl |= GARTEN | DISTLBWALKPRB;
+ ctl &= ~(DISGARTCPU | DISGARTIO);
+ pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
}
static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index ef328901c80..c9e09ea0564 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -237,7 +237,7 @@ static inline void fpu_save_init(struct fpu *fpu)
} else if (use_fxsr()) {
fpu_fxsave(fpu);
} else {
- asm volatile("fsave %[fx]; fwait"
+ asm volatile("fnsave %[fx]; fwait"
: [fx] "=m" (fpu->state->fsave));
return;
}
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 80a1dee5bea..aeff3e89b22 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -13,6 +13,12 @@ typedef struct {
int size;
struct mutex lock;
void *vdso;
+
+#ifdef CONFIG_X86_64
+ /* True if mm supports a task running in 32 bit compatibility mode. */
+ unsigned short ia32_compat;
+#endif
+
} mm_context_t;
#ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index fd5a1f365c9..3cce71413d0 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -96,11 +96,15 @@
#define MSR_IA32_MC0_ADDR 0x00000402
#define MSR_IA32_MC0_MISC 0x00000403
+#define MSR_AMD64_MC0_MASK 0xc0010044
+
#define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x))
#define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x))
#define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x))
#define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x))
+#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x))
+
/* These are consecutive and not in the normal 4er MCE bank block */
#define MSR_IA32_MC0_CTL2 0x00000280
#define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x))
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 3d4dab43c99..a50fc9f493b 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -51,7 +51,7 @@ static inline void numa_remove_cpu(int cpu) { }
#endif /* CONFIG_NUMA */
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable);
+void debug_cpumask_set_cpu(int cpu, int node, bool enable);
#endif
#endif /* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index a09e1f052d8..d475b4398d8 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -45,7 +45,7 @@
#include <linux/stringify.h>
#ifdef CONFIG_SMP
-#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x
+#define __percpu_prefix "%%"__stringify(__percpu_seg)":"
#define __my_cpu_offset percpu_read(this_cpu_off)
/*
@@ -62,9 +62,11 @@
(typeof(*(ptr)) __kernel __force *)tcp_ptr__; \
})
#else
-#define __percpu_arg(x) "%P" #x
+#define __percpu_prefix ""
#endif
+#define __percpu_arg(x) __percpu_prefix "%P" #x
+
/*
* Initialized pointers to per-cpu variables needed for the boot
* processor need to use these macros to get the proper address
@@ -516,11 +518,11 @@ do { \
typeof(o2) __n2 = n2; \
typeof(o2) __dummy; \
alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4, \
- "cmpxchg16b %%gs:(%%rsi)\n\tsetz %0\n\t", \
+ "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t", \
X86_FEATURE_CX16, \
ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \
"S" (&pcp1), "b"(__n1), "c"(__n2), \
- "a"(__o1), "d"(__o2)); \
+ "a"(__o1), "d"(__o2) : "memory"); \
__ret; \
})
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index f0b6e5dbc5a..1f2e61e2898 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -161,8 +161,14 @@ struct thread_info {
#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
-#define alloc_thread_info(tsk) \
- ((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
+#define alloc_thread_info_node(tsk, node) \
+({ \
+ struct page *page = alloc_pages_node(node, THREAD_FLAGS, \
+ THREAD_ORDER); \
+ struct thread_info *ret = page ? page_address(page) : NULL; \
+ \
+ ret; \
+})
#ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/types.h b/arch/x86/include/asm/types.h
index df1da20f453..8e8c23fef08 100644
--- a/arch/x86/include/asm/types.h
+++ b/arch/x86/include/asm/types.h
@@ -1,22 +1,6 @@
#ifndef _ASM_X86_TYPES_H
#define _ASM_X86_TYPES_H
-#define dma_addr_t dma_addr_t
-
#include <asm-generic/types.h>
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-typedef u64 dma64_addr_t;
-#if defined(CONFIG_X86_64) || defined(CONFIG_HIGHMEM64G)
-/* DMA addresses come in 32-bit and 64-bit flavours. */
-typedef u64 dma_addr_t;
-#else
-typedef u32 dma_addr_t;
-#endif
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
#endif /* _ASM_X86_TYPES_H */
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index ffaf183c619..a755ef5e597 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -349,10 +349,11 @@
#define __NR_name_to_handle_at 341
#define __NR_open_by_handle_at 342
#define __NR_clock_adjtime 343
+#define __NR_syncfs 344
#ifdef __KERNEL__
-#define NR_syscalls 344
+#define NR_syscalls 345
#define __ARCH_WANT_IPC_PARSE_VERSION
#define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 5466bea670e..160fa76bd57 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -675,6 +675,8 @@ __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
#define __NR_clock_adjtime 305
__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
+#define __NR_syncfs 306
+__SYSCALL(__NR_syncfs, sys_syncfs)
#ifndef __NO_STUBS
#define __ARCH_WANT_OLD_READDIR
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 743642f1a36..7338ef2218b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -41,7 +41,7 @@ obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o
obj-y += bootflag.o e820.o
-obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
+obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
obj-y += tsc.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
@@ -55,6 +55,7 @@ obj-$(CONFIG_X86_32) += tls.o
obj-$(CONFIG_IA32_EMULATION) += tls.o
obj-y += step.o
obj-$(CONFIG_INTEL_TXT) += tboot.o
+obj-$(CONFIG_ISA_DMA_API) += i8237.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += cpu/
obj-y += acpi/
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 4572c58e66d..ff93bc1b09c 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -25,12 +25,12 @@ static char temp_stack[4096];
#endif
/**
- * acpi_save_state_mem - save kernel state
+ * acpi_suspend_lowlevel - save kernel state
*
* Create an identity mapped page table and copy the wakeup routine to
* low memory.
*/
-int acpi_save_state_mem(void)
+int acpi_suspend_lowlevel(void)
{
struct wakeup_header *header;
/* address in low memory of the wakeup routine. */
@@ -96,16 +96,10 @@ int acpi_save_state_mem(void)
saved_magic = 0x123456789abcdef0L;
#endif /* CONFIG_64BIT */
+ do_suspend_lowlevel();
return 0;
}
-/*
- * acpi_restore_state - undo effects of acpi_save_state_mem
- */
-void acpi_restore_state_mem(void)
-{
-}
-
static int __init acpi_sleep_setup(char *str)
{
while ((str != NULL) && (*str != '\0')) {
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index 86ba1c87165..416d4be13fe 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -11,3 +11,5 @@ extern int wakeup_pmode_return;
extern unsigned long acpi_copy_wakeup_routine(unsigned long);
extern void wakeup_long64(void);
+
+extern void do_suspend_lowlevel(void);
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 6e11c813415..246d727b65b 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -21,7 +21,7 @@
#include <linux/acpi.h>
#include <linux/list.h>
#include <linux/slab.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/interrupt.h>
#include <linux/msi.h>
#include <asm/pci-direct.h>
@@ -1260,7 +1260,7 @@ static void disable_iommus(void)
* disable suspend until real resume implemented
*/
-static int amd_iommu_resume(struct sys_device *dev)
+static void amd_iommu_resume(void)
{
struct amd_iommu *iommu;
@@ -1276,11 +1276,9 @@ static int amd_iommu_resume(struct sys_device *dev)
*/
amd_iommu_flush_all_devices();
amd_iommu_flush_all_domains();
-
- return 0;
}
-static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
+static int amd_iommu_suspend(void)
{
/* disable IOMMUs to go out of the way for BIOS */
disable_iommus();
@@ -1288,17 +1286,11 @@ static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
return 0;
}
-static struct sysdev_class amd_iommu_sysdev_class = {
- .name = "amd_iommu",
+static struct syscore_ops amd_iommu_syscore_ops = {
.suspend = amd_iommu_suspend,
.resume = amd_iommu_resume,
};
-static struct sys_device device_amd_iommu = {
- .id = 0,
- .cls = &amd_iommu_sysdev_class,
-};
-
/*
* This is the core init function for AMD IOMMU hardware in the system.
* This function is called from the generic x86 DMA layer initialization
@@ -1415,14 +1407,6 @@ static int __init amd_iommu_init(void)
goto free;
}
- ret = sysdev_class_register(&amd_iommu_sysdev_class);
- if (ret)
- goto free;
-
- ret = sysdev_register(&device_amd_iommu);
- if (ret)
- goto free;
-
ret = amd_iommu_init_devices();
if (ret)
goto free;
@@ -1441,6 +1425,8 @@ static int __init amd_iommu_init(void)
amd_iommu_init_notifier();
+ register_syscore_ops(&amd_iommu_syscore_ops);
+
if (iommu_pass_through)
goto out;
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 6801959a8b2..4c39baa8fac 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -21,7 +21,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
EXPORT_SYMBOL(amd_nb_misc_ids);
static struct pci_device_id amd_nb_link_ids[] = {
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_LINK) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
{}
};
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 1293c709ee8..cd1ffed4ee2 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -316,7 +316,7 @@ static void apbt_setup_irq(struct apbt_dev *adev)
irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
/* APB timer irqs are set up as mp_irqs, timer is edge type */
- __set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
+ __irq_set_handler(adev->irq, handle_edge_irq, 0, "edge");
if (system_state == SYSTEM_BOOTING) {
if (request_irq(adev->irq, apbt_interrupt_handler,
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 86d1ad4962a..73fb469908c 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -499,7 +499,7 @@ out:
* Don't enable translation yet but enable GART IO and CPU
* accesses and set DISTLBWALKPRB since GART table memory is UC.
*/
- u32 ctl = DISTLBWALKPRB | aper_order << 1;
+ u32 ctl = aper_order << 1;
bus = amd_nb_bus_dev_ranges[i].bus;
dev_base = amd_nb_bus_dev_ranges[i].dev_base;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 966673f4414..fabf01eff77 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -24,7 +24,7 @@
#include <linux/ftrace.h>
#include <linux/ioport.h>
#include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/timex.h>
#include <linux/dmar.h>
@@ -2046,7 +2046,7 @@ static struct {
unsigned int apic_thmr;
} apic_pm_state;
-static int lapic_suspend(struct sys_device *dev, pm_message_t state)
+static int lapic_suspend(void)
{
unsigned long flags;
int maxlvt;
@@ -2084,23 +2084,21 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
return 0;
}
-static int lapic_resume(struct sys_device *dev)
+static void lapic_resume(void)
{
unsigned int l, h;
unsigned long flags;
- int maxlvt;
- int ret = 0;
+ int maxlvt, ret;
struct IO_APIC_route_entry **ioapic_entries = NULL;
if (!apic_pm_state.active)
- return 0;
+ return;
local_irq_save(flags);
if (intr_remapping_enabled) {
ioapic_entries = alloc_ioapic_entries();
if (!ioapic_entries) {
WARN(1, "Alloc ioapic_entries in lapic resume failed.");
- ret = -ENOMEM;
goto restore;
}
@@ -2162,8 +2160,6 @@ static int lapic_resume(struct sys_device *dev)
}
restore:
local_irq_restore(flags);
-
- return ret;
}
/*
@@ -2171,17 +2167,11 @@ restore:
* are needed on every CPU up until machine_halt/restart/poweroff.
*/
-static struct sysdev_class lapic_sysclass = {
- .name = "lapic",
+static struct syscore_ops lapic_syscore_ops = {
.resume = lapic_resume,
.suspend = lapic_suspend,
};
-static struct sys_device device_lapic = {
- .id = 0,
- .cls = &lapic_sysclass,
-};
-
static void __cpuinit apic_pm_activate(void)
{
apic_pm_state.active = 1;
@@ -2189,16 +2179,11 @@ static void __cpuinit apic_pm_activate(void)
static int __init init_lapic_sysfs(void)
{
- int error;
-
- if (!cpu_has_apic)
- return 0;
/* XXX: remove suspend/resume procs if !apic_pm_state.active? */
+ if (cpu_has_apic)
+ register_syscore_ops(&lapic_syscore_ops);
- error = sysdev_class_register(&lapic_sysclass);
- if (!error)
- error = sysdev_register(&device_lapic);
- return error;
+ return 0;
}
/* local apic needs to resume before other devices access its registers. */
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index c4e557a1ebb..5260fe91bcb 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -16,6 +16,7 @@
#include <linux/kprobes.h>
#include <linux/nmi.h>
#include <linux/module.h>
+#include <linux/delay.h>
#ifdef CONFIG_HARDLOCKUP_DETECTOR
u64 hw_nmi_get_sample_period(void)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 180ca240e03..68df09bba92 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -30,7 +30,7 @@
#include <linux/compiler.h>
#include <linux/acpi.h>
#include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/msi.h>
#include <linux/htirq.h>
#include <linux/freezer.h>
@@ -2918,89 +2918,84 @@ static int __init io_apic_bug_finalize(void)
late_initcall(io_apic_bug_finalize);
-struct sysfs_ioapic_data {
- struct sys_device dev;
- struct IO_APIC_route_entry entry[0];
-};
-static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+static struct IO_APIC_route_entry *ioapic_saved_data[MAX_IO_APICS];
-static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
+static void suspend_ioapic(int ioapic_id)
{
- struct IO_APIC_route_entry *entry;
- struct sysfs_ioapic_data *data;
+ struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id];
int i;
- data = container_of(dev, struct sysfs_ioapic_data, dev);
- entry = data->entry;
- for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ )
- *entry = ioapic_read_entry(dev->id, i);
+ if (!saved_data)
+ return;
+
+ for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++)
+ saved_data[i] = ioapic_read_entry(ioapic_id, i);
+}
+
+static int ioapic_suspend(void)
+{
+ int ioapic_id;
+
+ for (ioapic_id = 0; ioapic_id < nr_ioapics; ioapic_id++)
+ suspend_ioapic(ioapic_id);
return 0;
}
-static int ioapic_resume(struct sys_device *dev)
+static void resume_ioapic(int ioapic_id)
{
- struct IO_APIC_route_entry *entry;
- struct sysfs_ioapic_data *data;
+ struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id];
unsigned long flags;
union IO_APIC_reg_00 reg_00;
int i;
- data = container_of(dev, struct sysfs_ioapic_data, dev);
- entry = data->entry;
+ if (!saved_data)
+ return;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].apicid;
- io_apic_write(dev->id, 0, reg_00.raw);
+ reg_00.raw = io_apic_read(ioapic_id, 0);
+ if (reg_00.bits.ID != mp_ioapics[ioapic_id].apicid) {
+ reg_00.bits.ID = mp_ioapics[ioapic_id].apicid;
+ io_apic_write(ioapic_id, 0, reg_00.raw);
}
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
- for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
- ioapic_write_entry(dev->id, i, entry[i]);
+ for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++)
+ ioapic_write_entry(ioapic_id, i, saved_data[i]);
+}
- return 0;
+static void ioapic_resume(void)
+{
+ int ioapic_id;
+
+ for (ioapic_id = nr_ioapics - 1; ioapic_id >= 0; ioapic_id--)
+ resume_ioapic(ioapic_id);
}
-static struct sysdev_class ioapic_sysdev_class = {
- .name = "ioapic",
+static struct syscore_ops ioapic_syscore_ops = {
.suspend = ioapic_suspend,
.resume = ioapic_resume,
};
-static int __init ioapic_init_sysfs(void)
+static int __init ioapic_init_ops(void)
{
- struct sys_device * dev;
- int i, size, error;
+ int i;
- error = sysdev_class_register(&ioapic_sysdev_class);
- if (error)
- return error;
+ for (i = 0; i < nr_ioapics; i++) {
+ unsigned int size;
- for (i = 0; i < nr_ioapics; i++ ) {
- size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+ size = nr_ioapic_registers[i]
* sizeof(struct IO_APIC_route_entry);
- mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
- if (!mp_ioapic_data[i]) {
- printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
- continue;
- }
- dev = &mp_ioapic_data[i]->dev;
- dev->id = i;
- dev->cls = &ioapic_sysdev_class;
- error = sysdev_register(dev);
- if (error) {
- kfree(mp_ioapic_data[i]);
- mp_ioapic_data[i] = NULL;
- printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
- continue;
- }
+ ioapic_saved_data[i] = kzalloc(size, GFP_KERNEL);
+ if (!ioapic_saved_data[i])
+ pr_err("IOAPIC %d: suspend/resume impossible!\n", i);
}
+ register_syscore_ops(&ioapic_syscore_ops);
+
return 0;
}
-device_initcall(ioapic_init_sysfs);
+device_initcall(ioapic_init_ops);
/*
* Dynamic irq allocate and deallocation
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 3c289281394..33b10a0fc09 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -23,6 +23,8 @@
#include <linux/io.h>
#include <linux/pci.h>
#include <linux/kdebug.h>
+#include <linux/delay.h>
+#include <linux/crash_dump.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
@@ -34,6 +36,7 @@
#include <asm/ipi.h>
#include <asm/smp.h>
#include <asm/x86_init.h>
+#include <asm/emergency-restart.h>
DEFINE_PER_CPU(int, x2apic_extra_bits);
@@ -810,4 +813,11 @@ void __init uv_system_init(void)
/* register Legacy VGA I/O redirection handler */
pci_register_set_vga_state(uv_set_vga_state);
+
+ /*
+ * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as
+ * EFI is not enabled in the kdump kernel.
+ */
+ if (is_kdump_kernel())
+ reboot_type = BOOT_ACPI;
}
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 0b4be431c62..adee12e0da1 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,6 +228,7 @@
#include <linux/kthread.h>
#include <linux/jiffies.h>
#include <linux/acpi.h>
+#include <linux/syscore_ops.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -1238,6 +1239,7 @@ static int suspend(int vetoable)
local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
+ syscore_suspend();
local_irq_enable();
@@ -1255,6 +1257,7 @@ static int suspend(int vetoable)
apm_error("suspend", err);
err = (err == APM_SUCCESS) ? 0 : -EIO;
+ syscore_resume();
sysdev_resume();
local_irq_enable();
@@ -1280,6 +1283,7 @@ static void standby(void)
local_irq_disable();
sysdev_suspend(PMSG_SUSPEND);
+ syscore_suspend();
local_irq_enable();
err = set_system_power_state(APM_STATE_STANDBY);
@@ -1287,6 +1291,7 @@ static void standby(void)
apm_error("standby", err);
local_irq_disable();
+ syscore_resume();
sysdev_resume();
local_irq_enable();
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3ecece0217e..3532d3bf810 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -615,6 +615,25 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
/* As a rule processors have APIC timer running in deep C states */
if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400))
set_cpu_cap(c, X86_FEATURE_ARAT);
+
+ /*
+ * Disable GART TLB Walk Errors on Fam10h. We do this here
+ * because this is always needed when GART is enabled, even in a
+ * kernel which has no MCE support built in.
+ */
+ if (c->x86 == 0x10) {
+ /*
+ * BIOS should disable GartTlbWlk Errors themself. If
+ * it doesn't do it here as suggested by the BKDG.
+ *
+ * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
+ */
+ u64 mask;
+
+ rdmsrl(MSR_AMD64_MCx_MASK(4), mask);
+ mask |= (1 << 10);
+ wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
+ }
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 8209472b27a..83930deec3c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -106,24 +106,34 @@ int apei_write_mce(struct mce *m)
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;
- }
-
+ int rc, pos;
+
+ rc = erst_get_record_id_begin(&pos);
+ if (rc)
+ return rc;
+retry:
+ rc = erst_get_record_id_next(&pos, record_id);
+ if (rc)
+ goto out;
+ /* no more record */
+ if (*record_id == APEI_ERST_INVALID_RECORD_ID)
+ goto out;
+ rc = erst_read(*record_id, &rcd.hdr, sizeof(rcd));
+ /* someone else has cleared the record, try next one */
+ if (rc == -ENOENT)
+ goto retry;
+ else if (rc < 0)
+ goto out;
+ /* try to skip other type records in storage */
+ else if (rc != sizeof(rcd) ||
+ uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE))
+ goto retry;
memcpy(m, &rcd.mce, sizeof(*m));
- *record_id = rcd.hdr.record_id;
+ rc = sizeof(*m);
+out:
+ erst_get_record_id_end();
- return sizeof(*m);
+ return rc;
}
/* Check whether there is record in ERST */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ab1122998db..3385ea26f68 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -21,6 +21,7 @@
#include <linux/percpu.h>
#include <linux/string.h>
#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/ctype.h>
#include <linux/sched.h>
@@ -1625,7 +1626,7 @@ out:
static unsigned int mce_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &mce_wait, wait);
- if (rcu_dereference_check_mce(mcelog.next))
+ if (rcu_access_index(mcelog.next))
return POLLIN | POLLRDNORM;
if (!mce_apei_read_done && apei_check_mce())
return POLLIN | POLLRDNORM;
@@ -1749,14 +1750,14 @@ static int mce_disable_error_reporting(void)
return 0;
}
-static int mce_suspend(struct sys_device *dev, pm_message_t state)
+static int mce_suspend(void)
{
return mce_disable_error_reporting();
}
-static int mce_shutdown(struct sys_device *dev)
+static void mce_shutdown(void)
{
- return mce_disable_error_reporting();
+ mce_disable_error_reporting();
}
/*
@@ -1764,14 +1765,18 @@ static int mce_shutdown(struct sys_device *dev)
* Only one CPU is active at this time, the others get re-added later using
* CPU hotplug:
*/
-static int mce_resume(struct sys_device *dev)
+static void mce_resume(void)
{
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
-
- return 0;
}
+static struct syscore_ops mce_syscore_ops = {
+ .suspend = mce_suspend,
+ .shutdown = mce_shutdown,
+ .resume = mce_resume,
+};
+
static void mce_cpu_restart(void *data)
{
del_timer_sync(&__get_cpu_var(mce_timer));
@@ -1808,9 +1813,6 @@ static void mce_enable_ce(void *all)
}
static struct sysdev_class mce_sysclass = {
- .suspend = mce_suspend,
- .shutdown = mce_shutdown,
- .resume = mce_resume,
.name = "machinecheck",
};
@@ -2139,6 +2141,7 @@ static __init int mcheck_init_device(void)
return err;
}
+ register_syscore_ops(&mce_syscore_ops);
register_hotcpu_notifier(&mce_cpu_notifier);
misc_register(&mce_log_device);
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index bebabec5b44..929739a653d 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -45,6 +45,7 @@
#include <linux/cpu.h>
#include <linux/pci.h>
#include <linux/smp.h>
+#include <linux/syscore_ops.h>
#include <asm/processor.h>
#include <asm/e820.h>
@@ -292,14 +293,24 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
/*
* HACK!
- * We use this same function to initialize the mtrrs on boot.
- * The state of the boot cpu's mtrrs has been saved, and we want
- * to replicate across all the APs.
- * If we're doing that @reg is set to something special...
+ *
+ * We use this same function to initialize the mtrrs during boot,
+ * resume, runtime cpu online and on an explicit request to set a
+ * specific MTRR.
+ *
+ * During boot or suspend, the state of the boot cpu's mtrrs has been
+ * saved, and we want to replicate that across all the cpus that come
+ * online (either at the end of boot or resume or during a runtime cpu
+ * online). If we're doing that, @reg is set to something special and on
+ * this cpu we still do mtrr_if->set_all(). During boot/resume, this
+ * is unnecessary if at this point we are still on the cpu that started
+ * the boot/resume sequence. But there is no guarantee that we are still
+ * on the same cpu. So we do mtrr_if->set_all() on this cpu aswell to be
+ * sure that we are in sync with everyone else.
*/
if (reg != ~0U)
mtrr_if->set(reg, base, size, type);
- else if (!mtrr_aps_delayed_init)
+ else
mtrr_if->set_all();
/* Wait for the others */
@@ -630,7 +641,7 @@ struct mtrr_value {
static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES];
-static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
+static int mtrr_save(void)
{
int i;
@@ -642,7 +653,7 @@ static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
return 0;
}
-static int mtrr_restore(struct sys_device *sysdev)
+static void mtrr_restore(void)
{
int i;
@@ -653,12 +664,11 @@ static int mtrr_restore(struct sys_device *sysdev)
mtrr_value[i].ltype);
}
}
- return 0;
}
-static struct sysdev_driver mtrr_sysdev_driver = {
+static struct syscore_ops mtrr_syscore_ops = {
.suspend = mtrr_save,
.resume = mtrr_restore,
};
@@ -839,7 +849,7 @@ static int __init mtrr_init_finialize(void)
* TBD: is there any system with such CPU which supports
* suspend/resume? If no, we should remove the code.
*/
- sysdev_driver_register(&cpu_sysdev_class, &mtrr_sysdev_driver);
+ register_syscore_ops(&mtrr_syscore_ops);
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 87eab4a27df..632e5dc9c9c 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -500,12 +500,17 @@ static bool check_hw_exists(void)
return true;
bios_fail:
- printk(KERN_CONT "Broken BIOS detected, using software events only.\n");
+ /*
+ * We still allow the PMU driver to operate:
+ */
+ printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
- return false;
+
+ return true;
msr_fail:
printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+
return false;
}
@@ -581,8 +586,12 @@ static int x86_setup_perfctr(struct perf_event *event)
return -EOPNOTSUPP;
}
+ /*
+ * Do not allow config1 (extended registers) to propagate,
+ * there's no sane user-space generalization yet:
+ */
if (attr->type == PERF_TYPE_RAW)
- return x86_pmu_extra_regs(event->attr.config, event);
+ return 0;
if (attr->type == PERF_TYPE_HW_CACHE)
return set_ext_hw_attr(hwc, event);
@@ -912,7 +921,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
hwc->event_base = 0;
} else if (hwc->idx >= X86_PMC_IDX_FIXED) {
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0;
+ hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED);
} else {
hwc->config_base = x86_pmu_config_addr(hwc->idx);
hwc->event_base = x86_pmu_event_addr(hwc->idx);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 461f62bbd77..cf4e369cea6 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -8,7 +8,7 @@ static __initconst const u64 amd_hw_cache_event_ids
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */
- [ C(RESULT_MISS) ] = 0x0041, /* Data Cache Misses */
+ [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
@@ -427,7 +427,9 @@ static __initconst const struct x86_pmu amd_pmu = {
*
* Exceptions:
*
+ * 0x000 FP PERF_CTL[3], PERF_CTL[5:3] (*)
* 0x003 FP PERF_CTL[3]
+ * 0x004 FP PERF_CTL[3], PERF_CTL[5:3] (*)
* 0x00B FP PERF_CTL[3]
* 0x00D FP PERF_CTL[3]
* 0x023 DE PERF_CTL[2:0]
@@ -448,6 +450,8 @@ static __initconst const struct x86_pmu amd_pmu = {
* 0x0DF LS PERF_CTL[5:0]
* 0x1D6 EX PERF_CTL[5:0]
* 0x1D8 EX PERF_CTL[5:0]
+ *
+ * (*) depending on the umask all FPU counters may be used
*/
static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -460,18 +464,28 @@ static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
static struct event_constraint *
amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
{
- unsigned int event_code = amd_get_event_code(&event->hw);
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned int event_code = amd_get_event_code(hwc);
switch (event_code & AMD_EVENT_TYPE_MASK) {
case AMD_EVENT_FP:
switch (event_code) {
+ case 0x000:
+ if (!(hwc->config & 0x0000F000ULL))
+ break;
+ if (!(hwc->config & 0x00000F00ULL))
+ break;
+ return &amd_f15_PMC3;
+ case 0x004:
+ if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+ break;
+ return &amd_f15_PMC3;
case 0x003:
case 0x00B:
case 0x00D:
return &amd_f15_PMC3;
- default:
- return &amd_f15_PMC53;
}
+ return &amd_f15_PMC53;
case AMD_EVENT_LS:
case AMD_EVENT_DC:
case AMD_EVENT_EX_LS:
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8fc2b2cee1d..43fa20b1381 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -391,12 +391,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids
{
[ C(L1D) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI */
- [ C(RESULT_MISS) ] = 0x0140, /* L1D_CACHE_LD.I_STATE */
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */
},
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI */
- [ C(RESULT_MISS) ] = 0x0141, /* L1D_CACHE_ST.I_STATE */
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */
@@ -1425,6 +1425,7 @@ static __init int intel_pmu_init(void)
case 37: /* 32 nm nehalem, "Clarkdale" */
case 44: /* 32 nm nehalem, "Gulftown" */
+ case 47: /* 32 nm Xeon E7 */
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 0811f5ebfba..d1f77e2934a 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -777,6 +777,7 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
* the counter has reached zero value and continued counting before
* real NMI signal was received:
*/
+ rdmsrl(hwc->event_base, v);
if (!(v & ARCH_P4_UNFLAGGED_BIT))
return 1;
@@ -946,7 +947,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
if (!x86_perf_event_set_period(event))
continue;
if (perf_event_overflow(event, 1, &data, regs))
- p4_pmu_disable_event(event);
+ x86_pmu_stop(event, 0);
}
if (handled) {
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index d5cd13945d5..642f75a68cd 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -14,9 +14,6 @@
static void *kdump_buf_page;
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
static inline bool is_crashed_pfn_valid(unsigned long pfn)
{
#ifndef CONFIG_X86_PAE
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 994828899e0..afa64adb75e 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -10,9 +10,6 @@
#include <linux/uaccess.h>
#include <linux/io.h>
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
/**
* copy_oldmem_page - copy one page from "oldmem"
* @pfn: page frame number to be copied
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 7a8cebc9ff2..706a9fb46a5 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -65,12 +65,10 @@ unsigned int irq_create_of_mapping(struct device_node *controller,
return 0;
ret = ih->xlate(ih, intspec, intsize, &virq, &type);
if (ret)
- return ret;
+ return 0;
if (type == IRQ_TYPE_NONE)
return virq;
- /* set the mask if it is different from current */
- if (type == (irq_to_desc(virq)->status & IRQF_TRIGGER_MASK))
- set_irq_type(virq, type);
+ irq_set_irq_type(virq, type);
return virq;
}
EXPORT_SYMBOL_GPL(irq_create_of_mapping);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 999e2793590..e2a3f0606da 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -27,7 +27,7 @@ static int die_counter;
void printk_address(unsigned long address, int reliable)
{
- printk(" [<%p>] %s%pS\n", (void *) address,
+ printk(" [<%p>] %s%pB\n", (void *) address,
reliable ? "" : "? ", (void *) address);
}
@@ -322,16 +322,6 @@ void die(const char *str, struct pt_regs *regs, long err)
oops_end(flags, regs, sig);
}
-static int __init oops_setup(char *s)
-{
- if (!s)
- return -EINVAL;
- if (!strcmp(s, "panic"))
- panic_on_oops = 1;
- return 0;
-}
-early_param("oops", oops_setup);
-
static int __init kstack_setup(char *s)
{
if (!s)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index cdf5bfd9d4d..3e2ef842531 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
+#include <linux/crash_dump.h>
#include <linux/bootmem.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2d2673c28af..5655c2272ad 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -77,9 +77,6 @@ void __init x86_64_start_kernel(char * real_mode_data)
/* Make NULL pointers segfault */
zap_identity_mappings();
- /* Cleanup the over mapped high alias */
- cleanup_highmap();
-
max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) {
diff --git a/arch/x86/kernel/i8237.c b/arch/x86/kernel/i8237.c
index b42ca694dc6..8eeaa81de06 100644
--- a/arch/x86/kernel/i8237.c
+++ b/arch/x86/kernel/i8237.c
@@ -10,7 +10,7 @@
*/
#include <linux/init.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <asm/dma.h>
@@ -21,7 +21,7 @@
* in asm/dma.h.
*/
-static int i8237A_resume(struct sys_device *dev)
+static void i8237A_resume(void)
{
unsigned long flags;
int i;
@@ -41,31 +41,15 @@ static int i8237A_resume(struct sys_device *dev)
enable_dma(4);
release_dma_lock(flags);
-
- return 0;
}
-static int i8237A_suspend(struct sys_device *dev, pm_message_t state)
-{
- return 0;
-}
-
-static struct sysdev_class i8237_sysdev_class = {
- .name = "i8237",
- .suspend = i8237A_suspend,
+static struct syscore_ops i8237_syscore_ops = {
.resume = i8237A_resume,
};
-static struct sys_device device_i8237A = {
- .id = 0,
- .cls = &i8237_sysdev_class,
-};
-
-static int __init i8237A_init_sysfs(void)
+static int __init i8237A_init_ops(void)
{
- int error = sysdev_class_register(&i8237_sysdev_class);
- if (!error)
- error = sysdev_register(&device_i8237A);
- return error;
+ register_syscore_ops(&i8237_syscore_ops);
+ return 0;
}
-device_initcall(i8237A_init_sysfs);
+device_initcall(i8237A_init_ops);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index d9ca749c123..65b8f5c2eeb 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -8,7 +8,7 @@
#include <linux/random.h>
#include <linux/init.h>
#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/bitops.h>
#include <linux/acpi.h>
#include <linux/io.h>
@@ -245,20 +245,19 @@ static void save_ELCR(char *trigger)
trigger[1] = inb(0x4d1) & 0xDE;
}
-static int i8259A_resume(struct sys_device *dev)
+static void i8259A_resume(void)
{
init_8259A(i8259A_auto_eoi);
restore_ELCR(irq_trigger);
- return 0;
}
-static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
+static int i8259A_suspend(void)
{
save_ELCR(irq_trigger);
return 0;
}
-static int i8259A_shutdown(struct sys_device *dev)
+static void i8259A_shutdown(void)
{
/* Put the i8259A into a quiescent state that
* the kernel initialization code can get it
@@ -266,21 +265,14 @@ static int i8259A_shutdown(struct sys_device *dev)
*/
outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */
outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */
- return 0;
}
-static struct sysdev_class i8259_sysdev_class = {
- .name = "i8259",
+static struct syscore_ops i8259_syscore_ops = {
.suspend = i8259A_suspend,
.resume = i8259A_resume,
.shutdown = i8259A_shutdown,
};
-static struct sys_device device_i8259A = {
- .id = 0,
- .cls = &i8259_sysdev_class,
-};
-
static void mask_8259A(void)
{
unsigned long flags;
@@ -399,17 +391,12 @@ struct legacy_pic default_legacy_pic = {
struct legacy_pic *legacy_pic = &default_legacy_pic;
-static int __init i8259A_init_sysfs(void)
+static int __init i8259A_init_ops(void)
{
- int error;
-
- if (legacy_pic != &default_legacy_pic)
- return 0;
+ if (legacy_pic == &default_legacy_pic)
+ register_syscore_ops(&i8259_syscore_ops);
- error = sysdev_class_register(&i8259_sysdev_class);
- if (!error)
- error = sysdev_register(&device_i8259A);
- return error;
+ return 0;
}
-device_initcall(i8259A_init_sysfs);
+device_initcall(i8259A_init_ops);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 948a31eae75..1cb0b9fc78d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -8,6 +8,7 @@
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/ftrace.h>
+#include <linux/delay.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index dba0b36941a..5f9ecff328b 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -121,8 +121,8 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
dbg_reg_def[regno].size);
- switch (regno) {
#ifdef CONFIG_X86_32
+ switch (regno) {
case GDB_SS:
if (!user_mode_vm(regs))
*(unsigned long *)mem = __KERNEL_DS;
@@ -135,8 +135,8 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
case GDB_FS:
*(unsigned long *)mem = 0xFFFF;
break;
-#endif
}
+#endif
return dbg_reg_def[regno].name;
}
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 87af68e0e1e..f9242800bc8 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -82,6 +82,7 @@
#include <linux/cpu.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/syscore_ops.h>
#include <asm/microcode.h>
#include <asm/processor.h>
@@ -438,33 +439,25 @@ static int mc_sysdev_remove(struct sys_device *sys_dev)
return 0;
}
-static int mc_sysdev_resume(struct sys_device *dev)
+static struct sysdev_driver mc_sysdev_driver = {
+ .add = mc_sysdev_add,
+ .remove = mc_sysdev_remove,
+};
+
+/**
+ * mc_bp_resume - Update boot CPU microcode during resume.
+ */
+static void mc_bp_resume(void)
{
- int cpu = dev->id;
+ int cpu = smp_processor_id();
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- if (!cpu_online(cpu))
- return 0;
-
- /*
- * All non-bootup cpus are still disabled,
- * so only CPU 0 will apply ucode here.
- *
- * Moreover, there can be no concurrent
- * updates from any other places at this point.
- */
- WARN_ON(cpu != 0);
-
if (uci->valid && uci->mc)
microcode_ops->apply_microcode(cpu);
-
- return 0;
}
-static struct sysdev_driver mc_sysdev_driver = {
- .add = mc_sysdev_add,
- .remove = mc_sysdev_remove,
- .resume = mc_sysdev_resume,
+static struct syscore_ops mc_syscore_ops = {
+ .resume = mc_bp_resume,
};
static __cpuinit int
@@ -542,6 +535,7 @@ static int __init microcode_init(void)
if (error)
return error;
+ register_syscore_ops(&mc_syscore_ops);
register_hotcpu_notifier(&mc_cpu_notifier);
pr_info("Microcode Update Driver: v" MICROCODE_VERSION
@@ -556,6 +550,7 @@ static void __exit microcode_exit(void)
microcode_dev_exit();
unregister_hotcpu_notifier(&mc_cpu_notifier);
+ unregister_syscore_ops(&mc_syscore_ops);
get_online_cpus();
mutex_lock(&microcode_mutex);
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 6f789a887c0..5a532ce646b 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -714,10 +714,6 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
*nr_m_spare += 1;
}
}
-#else /* CONFIG_X86_IO_APIC */
-static
-inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
-#endif /* CONFIG_X86_IO_APIC */
static int
check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
@@ -731,6 +727,10 @@ check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count)
return ret;
}
+#else /* CONFIG_X86_IO_APIC */
+static
+inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
+#endif /* CONFIG_X86_IO_APIC */
static int __init replace_intsrc_all(struct mpc_table *mpc,
unsigned long mpc_new_phys,
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c01ffa5b9b8..b117efd24f7 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -27,7 +27,7 @@
#include <linux/kdebug.h>
#include <linux/scatterlist.h>
#include <linux/iommu-helper.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/io.h>
#include <linux/gfp.h>
#include <asm/atomic.h>
@@ -81,6 +81,9 @@ static u32 gart_unmapped_entry;
#define AGPEXTERN
#endif
+/* GART can only remap to physical addresses < 1TB */
+#define GART_MAX_PHYS_ADDR (1ULL << 40)
+
/* backdoor interface to AGP driver */
AGPEXTERN int agp_memory_reserved;
AGPEXTERN __u32 *agp_gatt_table;
@@ -212,9 +215,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
size_t size, int dir, unsigned long align_mask)
{
unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE);
- unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
+ unsigned long iommu_page;
int i;
+ if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
+ return bad_dma_addr;
+
+ iommu_page = alloc_iommu(dev, npages, align_mask);
if (iommu_page == -1) {
if (!nonforced_iommu(dev, phys_mem, size))
return phys_mem;
@@ -589,7 +596,7 @@ void set_up_gart_resume(u32 aper_order, u32 aper_alloc)
aperture_alloc = aper_alloc;
}
-static void gart_fixup_northbridges(struct sys_device *dev)
+static void gart_fixup_northbridges(void)
{
int i;
@@ -613,33 +620,20 @@ static void gart_fixup_northbridges(struct sys_device *dev)
}
}
-static int gart_resume(struct sys_device *dev)
+static void gart_resume(void)
{
pr_info("PCI-DMA: Resuming GART IOMMU\n");
- gart_fixup_northbridges(dev);
+ gart_fixup_northbridges();
enable_gart_translations();
-
- return 0;
}
-static int gart_suspend(struct sys_device *dev, pm_message_t state)
-{
- return 0;
-}
-
-static struct sysdev_class gart_sysdev_class = {
- .name = "gart",
- .suspend = gart_suspend,
+static struct syscore_ops gart_syscore_ops = {
.resume = gart_resume,
};
-static struct sys_device device_gart = {
- .cls = &gart_sysdev_class,
-};
-
/*
* Private Northbridge GATT initialization in case we cannot use the
* AGP driver for some reason.
@@ -650,7 +644,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
unsigned aper_base, new_aper_base;
struct pci_dev *dev;
void *gatt;
- int i, error;
+ int i;
pr_info("PCI-DMA: Disabling AGP.\n");
@@ -685,12 +679,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
agp_gatt_table = gatt;
- error = sysdev_class_register(&gart_sysdev_class);
- if (!error)
- error = sysdev_register(&device_gart);
- if (error)
- panic("Could not register gart_sysdev -- "
- "would corrupt data on next suspend");
+ register_syscore_ops(&gart_syscore_ops);
flush_gart();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index bd387e8f73b..6c9dd922ac0 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -501,6 +501,10 @@ void set_personality_64bit(void)
/* Make sure to be in 64bit mode */
clear_thread_flag(TIF_IA32);
+ /* Ensure the corresponding mm is not marked. */
+ if (current->mm)
+ current->mm->context.ia32_compat = 0;
+
/* TBD: overwrites user setup. Should have two bits.
But 64bit processes have always behaved this way,
so it's not too bad. The main problem is just that
@@ -516,6 +520,10 @@ void set_personality_ia32(void)
set_thread_flag(TIF_IA32);
current->personality |= force_personality32;
+ /* Mark the associated mm as containing 32-bit tasks. */
+ if (current->mm)
+ current->mm->context.ia32_compat = 1;
+
/* Prepare the first "return" to user space */
current_thread_info()->status |= TS_COMPAT;
}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index d3ce37edb54..08c44b08bf5 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -6,6 +6,7 @@
#include <linux/dmi.h>
#include <linux/sched.h>
#include <linux/tboot.h>
+#include <linux/delay.h>
#include <acpi/reboot.h>
#include <asm/io.h>
#include <asm/apic.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9d43b28e072..4be9b398470 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -294,30 +294,11 @@ static void __init init_gbpages(void)
else
direct_gbpages = 0;
}
-
-static void __init cleanup_highmap_brk_end(void)
-{
- pud_t *pud;
- pmd_t *pmd;
-
- mmu_cr4_features = read_cr4();
-
- /*
- * _brk_end cannot change anymore, but it and _end may be
- * located on different 2M pages. cleanup_highmap(), however,
- * can only consider _end when it runs, so destroy any
- * mappings beyond _brk_end here.
- */
- pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
- pmd = pmd_offset(pud, _brk_end - 1);
- while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
- pmd_clear(pmd);
-}
#else
static inline void init_gbpages(void)
{
}
-static inline void cleanup_highmap_brk_end(void)
+static void __init cleanup_highmap(void)
{
}
#endif
@@ -330,8 +311,6 @@ static void __init reserve_brk(void)
/* Mark brk area as locked down and no longer taking any
new allocations */
_brk_start = 0;
-
- cleanup_highmap_brk_end();
}
#ifdef CONFIG_BLK_DEV_INITRD
@@ -640,28 +619,6 @@ void __init reserve_standard_io_resources(void)
}
-/*
- * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
- * is_kdump_kernel() to determine if we are booting after a panic. Hence
- * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
- */
-
-#ifdef CONFIG_CRASH_DUMP
-/* elfcorehdr= specifies the location of elf core header
- * stored by the crashed kernel. This option will be passed
- * by kexec loader to the capture kernel.
- */
-static int __init setup_elfcorehdr(char *arg)
-{
- char *end;
- if (!arg)
- return -EINVAL;
- elfcorehdr_addr = memparse(arg, &end);
- return end > arg ? 0 : -EINVAL;
-}
-early_param("elfcorehdr", setup_elfcorehdr);
-#endif
-
static __init void reserve_ibft_region(void)
{
unsigned long addr, size = 0;
@@ -950,6 +907,8 @@ void __init setup_arch(char **cmdline_p)
*/
reserve_brk();
+ cleanup_highmap();
+
memblock.current_limit = get_max_mapped();
memblock_x86_fill();
@@ -1017,6 +976,11 @@ void __init setup_arch(char **cmdline_p)
paging_init();
x86_init.paging.pagetable_setup_done(swapper_pg_dir);
+ if (boot_cpu_data.cpuid_level >= 0) {
+ /* A CPU has %cr4 if and only if it has CPUID */
+ mmu_cr4_features = read_cr4();
+ }
+
#ifdef CONFIG_X86_32
/* sync back kernel address range */
clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 5f181742e8f..abce34d5c79 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -343,3 +343,4 @@ ENTRY(sys_call_table)
.long sys_name_to_handle_at
.long sys_open_by_handle_at
.long sys_clock_adjtime
+ .long sys_syncfs
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 58f517b5964..934b4c6b0bf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2395,9 +2395,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
int i;
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- for (i = 1; *nent < maxnent; ++i) {
- if (entry[i - 1].eax == 0 && i != 2)
- break;
+ for (i = 1; *nent < maxnent && i < 64; ++i) {
+ if (entry[i].eax == 0)
+ continue;
do_cpuid_1_ent(&entry[i], function, i);
entry[i].flags |=
KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
@@ -4958,12 +4958,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
best = e;
break;
}
- /*
- * Both basic or both extended?
- */
- if (((e->function ^ function) & 0x80000000) == 0)
- if (!best || e->function > best->function)
- best = e;
}
return best;
}
@@ -4983,6 +4977,27 @@ not_found:
return 36;
}
+/*
+ * If no match is found, check whether we exceed the vCPU's limit
+ * and return the content of the highest valid _standard_ leaf instead.
+ * This is to satisfy the CPUID specification.
+ */
+static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
+ u32 function, u32 index)
+{
+ struct kvm_cpuid_entry2 *maxlevel;
+
+ maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
+ if (!maxlevel || maxlevel->eax >= function)
+ return NULL;
+ if (function & 0x80000000) {
+ maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
+ if (!maxlevel)
+ return NULL;
+ }
+ return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
+}
+
void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
u32 function, index;
@@ -4995,6 +5010,10 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
kvm_register_write(vcpu, VCPU_REGS_RCX, 0);
kvm_register_write(vcpu, VCPU_REGS_RDX, 0);
best = kvm_find_cpuid_entry(vcpu, function, index);
+
+ if (!best)
+ best = check_cpuid_limit(vcpu, function, index);
+
if (best) {
kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax);
kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx);
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 3e8b08a6de2..1e572c507d0 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -10,6 +10,12 @@
#include <asm/frame.h>
#include <asm/dwarf2.h>
+#ifdef CONFIG_SMP
+#define SEG_PREFIX %gs:
+#else
+#define SEG_PREFIX
+#endif
+
.text
/*
@@ -37,13 +43,13 @@ this_cpu_cmpxchg16b_emu:
pushf
cli
- cmpq %gs:(%rsi), %rax
+ cmpq SEG_PREFIX(%rsi), %rax
jne not_same
- cmpq %gs:8(%rsi), %rdx
+ cmpq SEG_PREFIX 8(%rsi), %rdx
jne not_same
- movq %rbx, %gs:(%rsi)
- movq %rcx, %gs:8(%rsi)
+ movq %rbx, SEG_PREFIX(%rsi)
+ movq %rcx, SEG_PREFIX 8(%rsi)
popf
mov $1, %al
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0aa34669ed3..79423358728 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -52,6 +52,7 @@
#include <asm/cacheflush.h>
#include <asm/init.h>
#include <asm/uv/uv.h>
+#include <asm/setup.h>
static int __init parse_direct_gbpages_off(char *arg)
{
@@ -294,18 +295,18 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
* to the compile time generated pmds. This results in invalid pmds up
* to the point where we hit the physaddr 0 mapping.
*
- * We limit the mappings to the region from _text to _end. _end is
- * rounded up to the 2MB boundary. This catches the invalid pmds as
+ * We limit the mappings to the region from _text to _brk_end. _brk_end
+ * is rounded up to the 2MB boundary. This catches the invalid pmds as
* well, as they are located before _text:
*/
void __init cleanup_highmap(void)
{
unsigned long vaddr = __START_KERNEL_map;
- unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
+ unsigned long vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
+ unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
pmd_t *pmd = level2_kernel_pgt;
- pmd_t *last_pmd = pmd + PTRS_PER_PMD;
- for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
+ for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
if (pmd_none(*pmd))
continue;
if (vaddr < (unsigned long) _text || vaddr > end)
@@ -861,18 +862,18 @@ static struct vm_area_struct gate_vma = {
.vm_flags = VM_READ | VM_EXEC
};
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
#ifdef CONFIG_IA32_EMULATION
- if (test_tsk_thread_flag(tsk, TIF_IA32))
+ if (!mm || mm->context.ia32_compat)
return NULL;
#endif
return &gate_vma;
}
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
{
- struct vm_area_struct *vma = get_gate_vma(task);
+ struct vm_area_struct *vma = get_gate_vma(mm);
if (!vma)
return 0;
@@ -881,11 +882,11 @@ int in_gate_area(struct task_struct *task, unsigned long addr)
}
/*
- * Use this when you have no reliable task/vma, typically from interrupt
- * context. It is less reliable than using the task's vma and may give
- * false positives:
+ * Use this when you have no reliable mm, typically from interrupt
+ * context. It is less reliable than using a task's mm and may give
+ * false positives.
*/
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
{
return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 9559d360fde..745258dfc4d 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -213,53 +213,48 @@ int early_cpu_to_node(int cpu)
return per_cpu(x86_cpu_to_node_map, cpu);
}
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+void debug_cpumask_set_cpu(int cpu, int node, bool enable)
{
- int node = early_cpu_to_node(cpu);
struct cpumask *mask;
char buf[64];
if (node == NUMA_NO_NODE) {
/* early_cpu_to_node() already emits a warning and trace */
- return NULL;
+ return;
}
mask = node_to_cpumask_map[node];
if (!mask) {
pr_err("node_to_cpumask_map[%i] NULL\n", node);
dump_stack();
- return NULL;
+ return;
}
+ if (enable)
+ cpumask_set_cpu(cpu, mask);
+ else
+ cpumask_clear_cpu(cpu, mask);
+
cpulist_scnprintf(buf, sizeof(buf), mask);
printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
enable ? "numa_add_cpu" : "numa_remove_cpu",
cpu, node, buf);
- return mask;
+ return;
}
# ifndef CONFIG_NUMA_EMU
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
{
- struct cpumask *mask;
-
- mask = debug_cpumask_set_cpu(cpu, enable);
- if (!mask)
- return;
-
- if (enable)
- cpumask_set_cpu(cpu, mask);
- else
- cpumask_clear_cpu(cpu, mask);
+ debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
}
void __cpuinit numa_add_cpu(int cpu)
{
- numa_set_cpumask(cpu, 1);
+ numa_set_cpumask(cpu, true);
}
void __cpuinit numa_remove_cpu(int cpu)
{
- numa_set_cpumask(cpu, 0);
+ numa_set_cpumask(cpu, false);
}
# endif /* !CONFIG_NUMA_EMU */
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index ad091e4cff1..de84cc14037 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -454,10 +454,9 @@ void __cpuinit numa_remove_cpu(int cpu)
cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
}
#else /* !CONFIG_DEBUG_PER_CPU_MAPS */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
{
- struct cpumask *mask;
- int nid, physnid, i;
+ int nid, physnid;
nid = early_cpu_to_node(cpu);
if (nid == NUMA_NO_NODE) {
@@ -467,28 +466,21 @@ static void __cpuinit numa_set_cpumask(int cpu, int enable)
physnid = emu_nid_to_phys[nid];
- for_each_online_node(i) {
+ for_each_online_node(nid) {
if (emu_nid_to_phys[nid] != physnid)
continue;
- mask = debug_cpumask_set_cpu(cpu, enable);
- if (!mask)
- return;
-
- if (enable)
- cpumask_set_cpu(cpu, mask);
- else
- cpumask_clear_cpu(cpu, mask);
+ debug_cpumask_set_cpu(cpu, nid, enable);
}
}
void __cpuinit numa_add_cpu(int cpu)
{
- numa_set_cpumask(cpu, 1);
+ numa_set_cpumask(cpu, true);
}
void __cpuinit numa_remove_cpu(int cpu)
{
- numa_set_cpumask(cpu, 0);
+ numa_set_cpumask(cpu, false);
}
#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 48651c6f657..364f36bdfad 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -211,10 +211,12 @@ int __init get_memcfg_from_srat(void)
{
int i, j, nid;
-
if (srat_disabled())
goto out_fail;
+ if (acpi_numa_init() < 0)
+ goto out_fail;
+
if (num_memory_chunks == 0) {
printk(KERN_DEBUG
"could not find any ACPI SRAT memory areas.\n");
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index e2b7b0c06cd..cf9750004a0 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -15,7 +15,7 @@
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/oprofile.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
#include <linux/slab.h>
#include <linux/moduleparam.h>
#include <linux/kdebug.h>
@@ -49,6 +49,10 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
val |= counter_config->user ? ARCH_PERFMON_EVENTSEL_USR : 0;
val |= counter_config->kernel ? ARCH_PERFMON_EVENTSEL_OS : 0;
val |= (counter_config->unit_mask & 0xFF) << 8;
+ counter_config->extra &= (ARCH_PERFMON_EVENTSEL_INV |
+ ARCH_PERFMON_EVENTSEL_EDGE |
+ ARCH_PERFMON_EVENTSEL_CMASK);
+ val |= counter_config->extra;
event &= model->event_mask ? model->event_mask : 0xFF;
val |= event & 0xFF;
val |= (event & 0x0F00) << 24;
@@ -440,6 +444,7 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root)
oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+ oprofilefs_create_ulong(sb, dir, "extra", &counter_config[i].extra);
}
return 0;
@@ -536,7 +541,7 @@ static void nmi_shutdown(void)
#ifdef CONFIG_PM
-static int nmi_suspend(struct sys_device *dev, pm_message_t state)
+static int nmi_suspend(void)
{
/* Only one CPU left, just stop that one */
if (nmi_enabled == 1)
@@ -544,49 +549,31 @@ static int nmi_suspend(struct sys_device *dev, pm_message_t state)
return 0;
}
-static int nmi_resume(struct sys_device *dev)
+static void nmi_resume(void)
{
if (nmi_enabled == 1)
nmi_cpu_start(NULL);
- return 0;
}
-static struct sysdev_class oprofile_sysclass = {
- .name = "oprofile",
+static struct syscore_ops oprofile_syscore_ops = {
.resume = nmi_resume,
.suspend = nmi_suspend,
};
-static struct sys_device device_oprofile = {
- .id = 0,
- .cls = &oprofile_sysclass,
-};
-
-static int __init init_sysfs(void)
+static void __init init_suspend_resume(void)
{
- int error;
-
- error = sysdev_class_register(&oprofile_sysclass);
- if (error)
- return error;
-
- error = sysdev_register(&device_oprofile);
- if (error)
- sysdev_class_unregister(&oprofile_sysclass);
-
- return error;
+ register_syscore_ops(&oprofile_syscore_ops);
}
-static void exit_sysfs(void)
+static void exit_suspend_resume(void)
{
- sysdev_unregister(&device_oprofile);
- sysdev_class_unregister(&oprofile_sysclass);
+ unregister_syscore_ops(&oprofile_syscore_ops);
}
#else
-static inline int init_sysfs(void) { return 0; }
-static inline void exit_sysfs(void) { }
+static inline void init_suspend_resume(void) { }
+static inline void exit_suspend_resume(void) { }
#endif /* CONFIG_PM */
@@ -789,9 +776,7 @@ int __init op_nmi_init(struct oprofile_operations *ops)
mux_init(ops);
- ret = init_sysfs();
- if (ret)
- return ret;
+ init_suspend_resume();
printk(KERN_INFO "oprofile: using NMI interrupt.\n");
return 0;
@@ -799,5 +784,5 @@ int __init op_nmi_init(struct oprofile_operations *ops)
void op_nmi_exit(void)
{
- exit_sysfs();
+ exit_suspend_resume();
}
diff --git a/arch/x86/oprofile/op_counter.h b/arch/x86/oprofile/op_counter.h
index e28398df0df..0b7b7b179cb 100644
--- a/arch/x86/oprofile/op_counter.h
+++ b/arch/x86/oprofile/op_counter.h
@@ -22,6 +22,7 @@ struct op_counter_config {
unsigned long kernel;
unsigned long user;
unsigned long unit_mask;
+ unsigned long extra;
};
extern struct op_counter_config counter_config[];
diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts
index dc701ea5854..2d6d226f2b1 100644
--- a/arch/x86/platform/ce4100/falconfalls.dts
+++ b/arch/x86/platform/ce4100/falconfalls.dts
@@ -74,6 +74,7 @@
compatible = "intel,ce4100-pci", "pci";
device_type = "pci";
bus-range = <1 1>;
+ reg = <0x0800 0x0 0x0 0x0 0x0>;
ranges = <0x2000000 0 0xdffe0000 0x2000000 0 0xdffe0000 0 0x1000>;
interrupt-parent = <&ioapic2>;
@@ -412,6 +413,7 @@
#address-cells = <2>;
#size-cells = <1>;
compatible = "isa";
+ reg = <0xf800 0x0 0x0 0x0 0x0>;
ranges = <1 0 0 0 0 0x100>;
rtc@70 {
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 5c0207bf959..275dbc19e2c 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -97,11 +97,11 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table)
pentry->freq_hz, pentry->irq);
if (!pentry->irq)
continue;
- mp_irq.type = MP_IOAPIC;
+ mp_irq.type = MP_INTSRC;
mp_irq.irqtype = mp_INT;
/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
mp_irq.irqflag = 5;
- mp_irq.srcbus = 0;
+ mp_irq.srcbus = MP_BUS_ISA;
mp_irq.srcbusirq = pentry->irq; /* IRQ */
mp_irq.dstapic = MP_APIC_ALL;
mp_irq.dstirq = pentry->irq;
@@ -168,10 +168,10 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) {
pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n",
totallen, (u32)pentry->phys_addr, pentry->irq);
- mp_irq.type = MP_IOAPIC;
+ mp_irq.type = MP_INTSRC;
mp_irq.irqtype = mp_INT;
mp_irq.irqflag = 0xf; /* level trigger and active low */
- mp_irq.srcbus = 0;
+ mp_irq.srcbus = MP_BUS_ISA;
mp_irq.srcbusirq = pentry->irq; /* IRQ */
mp_irq.dstapic = MP_APIC_ALL;
mp_irq.dstirq = pentry->irq;
@@ -282,7 +282,7 @@ void __init x86_mrst_early_setup(void)
/* Avoid searching for BIOS MP tables */
x86_init.mpparse.find_smp_config = x86_init_noop;
x86_init.mpparse.get_smp_config = x86_init_uint_noop;
-
+ set_bit(MP_BUS_ISA, mp_bus_not_pci);
}
/*
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 04cf645feb9..73d70d65e76 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -100,9 +100,11 @@ int vrtc_set_mmss(unsigned long nowtime)
void __init mrst_rtc_init(void)
{
- unsigned long vrtc_paddr = sfi_mrtc_array[0].phys_addr;
+ unsigned long vrtc_paddr;
sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
+
+ vrtc_paddr = sfi_mrtc_array[0].phys_addr;
if (!sfi_mrtc_num || !vrtc_paddr)
return;
diff --git a/arch/x86/platform/olpc/olpc-xo1.c b/arch/x86/platform/olpc/olpc-xo1.c
index 127775696d6..ab81fb27176 100644
--- a/arch/x86/platform/olpc/olpc-xo1.c
+++ b/arch/x86/platform/olpc/olpc-xo1.c
@@ -15,6 +15,7 @@
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/pm.h>
+#include <linux/mfd/core.h>
#include <asm/io.h>
#include <asm/olpc.h>
@@ -56,25 +57,24 @@ static void xo1_power_off(void)
static int __devinit olpc_xo1_probe(struct platform_device *pdev)
{
struct resource *res;
+ int err;
/* don't run on non-XOs */
if (!machine_is_olpc())
return -ENODEV;
+ err = mfd_cell_enable(pdev);
+ if (err)
+ return err;
+
res = platform_get_resource(pdev, IORESOURCE_IO, 0);
if (!res) {
dev_err(&pdev->dev, "can't fetch device resource info\n");
return -EIO;
}
-
- if (!request_region(res->start, resource_size(res), DRV_NAME)) {
- dev_err(&pdev->dev, "can't request region\n");
- return -EIO;
- }
-
if (strcmp(pdev->name, "cs5535-pms") == 0)
pms_base = res->start;
- else if (strcmp(pdev->name, "cs5535-acpi") == 0)
+ else if (strcmp(pdev->name, "olpc-xo1-pm-acpi") == 0)
acpi_base = res->start;
/* If we have both addresses, we can override the poweroff hook */
@@ -88,14 +88,11 @@ static int __devinit olpc_xo1_probe(struct platform_device *pdev)
static int __devexit olpc_xo1_remove(struct platform_device *pdev)
{
- struct resource *r;
-
- r = platform_get_resource(pdev, IORESOURCE_IO, 0);
- release_region(r->start, resource_size(r));
+ mfd_cell_disable(pdev);
if (strcmp(pdev->name, "cs5535-pms") == 0)
pms_base = 0;
- else if (strcmp(pdev->name, "cs5535-acpi") == 0)
+ else if (strcmp(pdev->name, "olpc-xo1-pm-acpi") == 0)
acpi_base = 0;
pm_power_off = NULL;
@@ -113,7 +110,7 @@ static struct platform_driver cs5535_pms_drv = {
static struct platform_driver cs5535_acpi_drv = {
.driver = {
- .name = "cs5535-acpi",
+ .name = "olpc-xo1-pm-acpi",
.owner = THIS_MODULE,
},
.probe = olpc_xo1_probe,
@@ -143,7 +140,7 @@ static void __exit olpc_xo1_exit(void)
MODULE_AUTHOR("Daniel Drake <dsd@laptop.org>");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:olpc-xo1");
+MODULE_ALIAS("platform:cs5535-pms");
module_init(olpc_xo1_init);
module_exit(olpc_xo1_exit);
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index a7b38d35c29..7cb6424317f 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -11,6 +11,7 @@
#include <linux/debugfs.h>
#include <linux/kernel.h>
#include <linux/slab.h>
+#include <linux/delay.h>
#include <asm/mmu_context.h>
#include <asm/uv/uv.h>
diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c
index fe4cf829487..c7abf13a213 100644
--- a/arch/x86/platform/visws/visws_quirks.c
+++ b/arch/x86/platform/visws/visws_quirks.c
@@ -471,15 +471,7 @@ static unsigned int startup_piix4_master_irq(struct irq_data *data)
{
legacy_pic->init(0);
enable_cobalt_irq(data);
-}
-
-static void end_piix4_master_irq(struct irq_data *data)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&cobalt_lock, flags);
- enable_cobalt_irq(data);
- spin_unlock_irqrestore(&cobalt_lock, flags);
+ return 0;
}
static struct irq_chip piix4_master_irq_type = {
@@ -492,7 +484,7 @@ static void pii4_mask(struct irq_data *data) { }
static struct irq_chip piix4_virtual_irq_type = {
.name = "PIIX4-virtual",
- .mask = pii4_mask,
+ .irq_mask = pii4_mask,
};
/*
@@ -580,9 +572,9 @@ static struct irqaction cascade_action = {
static inline void set_piix4_virtual_irq_type(void)
{
- piix4_virtual_irq_type.enable = i8259A_chip.unmask;
- piix4_virtual_irq_type.disable = i8259A_chip.mask;
- piix4_virtual_irq_type.unmask = i8259A_chip.unmask;
+ piix4_virtual_irq_type.irq_enable = i8259A_chip.irq_unmask;
+ piix4_virtual_irq_type.irq_disable = i8259A_chip.irq_mask;
+ piix4_virtual_irq_type.irq_unmask = i8259A_chip.irq_unmask;
}
static void __init visws_pre_intr_init(void)
@@ -599,7 +591,7 @@ static void __init visws_pre_intr_init(void)
else if (i == CO_IRQ_IDE0)
chip = &cobalt_irq_type;
else if (i == CO_IRQ_IDE1)
- >chip = &cobalt_irq_type;
+ chip = &cobalt_irq_type;
else if (i == CO_IRQ_8259)
chip = &piix4_master_irq_type;
else if (i < CO_IRQ_APIC0)
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 36df991985b..468d591dde3 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -417,24 +417,25 @@ const char *arch_vma_name(struct vm_area_struct *vma)
return NULL;
}
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
- struct mm_struct *mm = tsk->mm;
-
- /* Check to see if this task was created in compat vdso mode */
+ /*
+ * Check to see if the corresponding task was created in compat vdso
+ * mode.
+ */
if (mm && mm->context.vdso == (void *)VDSO_HIGH_BASE)
return &gate_vma;
return NULL;
}
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
{
- const struct vm_area_struct *vma = get_gate_vma(task);
+ const struct vm_area_struct *vma = get_gate_vma(mm);
return vma && addr >= vma->vm_start && addr < vma->vm_end;
}
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
{
return 0;
}
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 1c7121ba18f..5cc821cb2e0 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -39,6 +39,7 @@ config XEN_MAX_DOMAIN_MEMORY
config XEN_SAVE_RESTORE
bool
depends on XEN
+ select HIBERNATE_CALLBACKS
default y
config XEN_DEBUG_FS
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 49dbd78ec3c..e3c6a06cf72 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -238,6 +238,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
static __init void xen_init_cpuid_mask(void)
{
unsigned int ax, bx, cx, dx;
+ unsigned int xsave_mask;
cpuid_leaf1_edx_mask =
~((1 << X86_FEATURE_MCE) | /* disable MCE */
@@ -249,24 +250,16 @@ static __init void xen_init_cpuid_mask(void)
cpuid_leaf1_edx_mask &=
~((1 << X86_FEATURE_APIC) | /* disable local APIC */
(1 << X86_FEATURE_ACPI)); /* disable ACPI */
-
ax = 1;
- cx = 0;
xen_cpuid(&ax, &bx, &cx, &dx);
- /* cpuid claims we support xsave; try enabling it to see what happens */
- if (cx & (1 << (X86_FEATURE_XSAVE % 32))) {
- unsigned long cr4;
-
- set_in_cr4(X86_CR4_OSXSAVE);
-
- cr4 = read_cr4();
+ xsave_mask =
+ (1 << (X86_FEATURE_XSAVE % 32)) |
+ (1 << (X86_FEATURE_OSXSAVE % 32));
- if ((cr4 & X86_CR4_OSXSAVE) == 0)
- cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32));
-
- clear_in_cr4(X86_CR4_OSXSAVE);
- }
+ /* Xen will set CR4.OSXSAVE if supported and not disabled by force */
+ if ((cx & xsave_mask) != xsave_mask)
+ cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
}
static void xen_set_debugreg(int reg, unsigned long val)
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 39ee7182fd1..aef7af92b28 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -565,13 +565,13 @@ pte_t xen_make_pte_debug(pteval_t pte)
if (io_page &&
(xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
- WARN(addr != other_addr,
+ WARN_ONCE(addr != other_addr,
"0x%lx is using VM_IO, but it is 0x%lx!\n",
(unsigned long)addr, (unsigned long)other_addr);
} else {
pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
other_addr = (_pte.pte & PTE_PFN_MASK);
- WARN((addr == other_addr) && (!io_page) && (!iomap_set),
+ WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
"0x%lx is missing VM_IO (and wasn't fixed)!\n",
(unsigned long)addr);
}
@@ -1473,28 +1473,35 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
#endif
}
+#ifdef CONFIG_X86_32
static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
{
- unsigned long pfn = pte_pfn(pte);
-
-#ifdef CONFIG_X86_32
/* If there's an existing pte, then don't allow _PAGE_RW to be set */
if (pte_val_ma(*ptep) & _PAGE_PRESENT)
pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
pte_val_ma(pte));
-#endif
+
+ return pte;
+}
+#else /* CONFIG_X86_64 */
+static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
+{
+ unsigned long pfn = pte_pfn(pte);
/*
* If the new pfn is within the range of the newly allocated
* kernel pagetable, and it isn't being mapped into an
- * early_ioremap fixmap slot, make sure it is RO.
+ * early_ioremap fixmap slot as a freshly allocated page, make sure
+ * it is RO.
*/
- if (!is_early_ioremap_ptep(ptep) &&
- pfn >= pgt_buf_start && pfn < pgt_buf_end)
+ if (((!is_early_ioremap_ptep(ptep) &&
+ pfn >= pgt_buf_start && pfn < pgt_buf_end)) ||
+ (is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
pte = pte_wrprotect(pte);
return pte;
}
+#endif /* CONFIG_X86_64 */
/* Init-time set_pte while constructing initial pagetables, which
doesn't allow RO pagetable pages to be remapped RW */
@@ -1700,9 +1707,6 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
pte_t pte;
- if (pfn > max_pfn_mapped)
- max_pfn_mapped = pfn;
-
if (!pte_none(pte_page[pteidx]))
continue;
@@ -1760,6 +1764,12 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
pud_t *l3;
pmd_t *l2;
+ /* max_pfn_mapped is the last pfn mapped in the initial memory
+ * mappings. Considering that on Xen after the kernel mappings we
+ * have the mappings of some pages that don't exist in pfn space, we
+ * set max_pfn_mapped to the last real pfn mapped. */
+ max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+
/* Zap identity mapping */
init_level4_pgt[0] = __pgd(0);
@@ -1864,9 +1874,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
initial_kernel_pmd =
extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
- max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
- xen_start_info->nr_pt_frames * PAGE_SIZE +
- 512*1024);
+ max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 215a3ce6106..141eb0de8b0 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -497,7 +497,7 @@ static bool alloc_p2m(unsigned long pfn)
return true;
}
-bool __early_alloc_p2m(unsigned long pfn)
+static bool __init __early_alloc_p2m(unsigned long pfn)
{
unsigned topidx, mididx, idx;
@@ -530,7 +530,7 @@ bool __early_alloc_p2m(unsigned long pfn)
}
return idx != 0;
}
-unsigned long set_phys_range_identity(unsigned long pfn_s,
+unsigned long __init set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e)
{
unsigned long pfn;
@@ -671,7 +671,9 @@ int m2p_add_override(unsigned long mfn, struct page *page)
page->private = mfn;
page->index = pfn_to_mfn(pfn);
- __set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
+ if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
+ return -ENOMEM;
+
if (!PageHighMem(page))
/* Just zap old mapping for now */
pte_clear(&init_mm, address, ptep);
@@ -709,7 +711,7 @@ int m2p_remove_override(struct page *page)
spin_lock_irqsave(&m2p_override_lock, flags);
list_del(&page->lru);
spin_unlock_irqrestore(&m2p_override_lock, flags);
- __set_phys_to_machine(pfn, page->index);
+ set_phys_to_machine(pfn, page->index);
if (!PageHighMem(page))
set_pte_at(&init_mm, address, ptep,
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index fa0269a9937..90bac0aac3a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -227,7 +227,7 @@ char * __init xen_memory_setup(void)
memcpy(map_raw, map, sizeof(map));
e820.nr_map = 0;
- xen_extra_mem_start = mem_end;
+ xen_extra_mem_start = max((1ULL << 32), mem_end);
for (i = 0; i < memmap.nr_entries; i++) {
unsigned long long end;