Merge commit 'v2.6.39-rc6' into x86/cleanups

Merge reason: move to a (much) newer upstream base.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

73 files changed, 677 insertions, 506 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d57ddd7573c..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)
@@ -2096,6 +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/boot/memory.c b/arch/x86/boot/memory.c
index cae3feb1035..db75d07c364 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -91,7 +91,7 @@ static int detect_memory_e801(void)
 	if (oreg.ax > 15*1024) {
 		return -1;	/* Bogus! */
 	} else if (oreg.ax == 15*1024) {
-		boot_params.alt_mem_k = (oreg.dx << 6) + oreg.ax;
+		boot_params.alt_mem_k = (oreg.bx << 6) + oreg.ax;
 	} else {
 		/*
 		 * This ignores memory above 16MB if we have a memory
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/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 97b6d8114a4..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
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/io_apic.h b/arch/x86/include/asm/io_apic.h
index c4bd267dfc5..a97a240f67f 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -150,7 +150,7 @@ void setup_IO_APIC_irq_extra(u32 gsi);
 extern void ioapic_and_gsi_init(void);
 extern void ioapic_insert_resources(void);
 
-int io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr);
+int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr);
 
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
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/types.h b/arch/x86/include/asm/types.h
index 88102055a4b..8e8c23fef08 100644
--- a/arch/x86/include/asm/types.h
+++ b/arch/x86/include/asm/types.h
@@ -3,12 +3,4 @@
 
 #include <asm-generic/types.h>
 
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-typedef u64 dma64_addr_t;
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
 #endif /* _ASM_X86_TYPES_H */
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 = {