Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:
	drivers/net/sfc/sfe4001.c
	drivers/net/wireless/libertas/cmd.c
	drivers/staging/Kconfig
	drivers/staging/Makefile
	drivers/staging/rtl8187se/Kconfig
	drivers/staging/rtl8192e/Kconfig

56 files changed, 425 insertions, 190 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8da93745c08..72ace9515a0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -86,10 +86,6 @@ config STACKTRACE_SUPPORT
 config HAVE_LATENCYTOP_SUPPORT
 	def_bool y
 
-config FAST_CMPXCHG_LOCAL
-	bool
-	default y
-
 config MMU
 	def_bool y
 
@@ -495,7 +491,7 @@ if PARAVIRT_GUEST
 source "arch/x86/xen/Kconfig"
 
 config VMI
-	bool "VMI Guest support"
+	bool "VMI Guest support (DEPRECATED)"
 	select PARAVIRT
 	depends on X86_32
 	---help---
@@ -504,6 +500,15 @@ config VMI
 	  at the moment), by linking the kernel to a GPL-ed ROM module
 	  provided by the hypervisor.
 
+	  As of September 2009, VMware has started a phased retirement
+	  of this feature from VMware's products. Please see
+	  feature-removal-schedule.txt for details.  If you are
+	  planning to enable this option, please note that you cannot
+	  live migrate a VMI enabled VM to a future VMware product,
+	  which doesn't support VMI. So if you expect your kernel to
+	  seamlessly migrate to newer VMware products, keep this
+	  disabled.
+
 config KVM_CLOCK
 	bool "KVM paravirtualized clock"
 	select PARAVIRT
@@ -1438,12 +1443,8 @@ config SECCOMP
 
 	  If unsure, say Y. Only embedded should say N here.
 
-config CC_STACKPROTECTOR_ALL
-	bool
-
 config CC_STACKPROTECTOR
 	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	select CC_STACKPROTECTOR_ALL
 	---help---
 	  This option turns on the -fstack-protector GCC feature. This
 	  feature puts, at the beginning of functions, a canary value on
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 527519b8a9f..2649840d888 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -400,7 +400,7 @@ config X86_TSC
 
 config X86_CMPXCHG64
 	def_bool y
-	depends on X86_PAE || X86_64
+	depends on !M386 && !M486
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
@@ -412,6 +412,7 @@ config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
 	default "6" if X86_32 && X86_P6_NOP
+	default "5" if X86_32 && X86_CMPXCHG64
 	default "4" if X86_32 && (X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK)
 	default "3"
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index a012ee8ef80..d2d24c9ee64 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -76,7 +76,6 @@ ifdef CONFIG_CC_STACKPROTECTOR
 	cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
         ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(biarch)),y)
                 stackp-y := -fstack-protector
-                stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += -fstack-protector-all
                 KBUILD_CFLAGS += $(stackp-y)
         else
                 $(warning stack protector enabled but no compiler support)
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 0f6ec455a2b..03c0683636b 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -53,6 +53,9 @@ SECTIONS
 
 	/DISCARD/ : { *(.note*) }
 
+	/*
+	 * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+	 */
 	. = ASSERT(_end <= 0x8000, "Setup too big!");
 	. = ASSERT(hdr == 0x1f1, "The setup header has the wrong offset!");
 	/* Necessary for the very-old-loader check to work... */
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 585edebe12c..49c552c060e 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -82,7 +82,7 @@ static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx,
 		return -EINVAL;
 	}
 
-	if (irq_fpu_usable())
+	if (!irq_fpu_usable())
 		err = crypto_aes_expand_key(ctx, in_key, key_len);
 	else {
 		kernel_fpu_begin();
@@ -103,7 +103,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (irq_fpu_usable())
+	if (!irq_fpu_usable())
 		crypto_aes_encrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -116,7 +116,7 @@ static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (irq_fpu_usable())
+	if (!irq_fpu_usable())
 		crypto_aes_decrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -342,7 +342,7 @@ static int ablk_encrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (irq_fpu_usable()) {
+	if (!irq_fpu_usable()) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 		memcpy(cryptd_req, req, sizeof(*req));
@@ -363,7 +363,7 @@ static int ablk_decrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (irq_fpu_usable()) {
+	if (!irq_fpu_usable()) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 		memcpy(cryptd_req, req, sizeof(*req));
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 11a6c79d5f4..d23b9878265 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -21,8 +21,8 @@
 #define __AUDIT_ARCH_LE	   0x40000000
 
 #ifndef CONFIG_AUDITSYSCALL
-#define sysexit_audit int_ret_from_sys_call
-#define sysretl_audit int_ret_from_sys_call
+#define sysexit_audit ia32_ret_from_sys_call
+#define sysretl_audit ia32_ret_from_sys_call
 #endif
 
 #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
@@ -39,12 +39,12 @@
 	.endm 
 
 	/* clobbers %eax */	
-	.macro  CLEAR_RREGS _r9=rax
+	.macro  CLEAR_RREGS offset=0, _r9=rax
 	xorl 	%eax,%eax
-	movq	%rax,R11(%rsp)
-	movq	%rax,R10(%rsp)
-	movq	%\_r9,R9(%rsp)
-	movq	%rax,R8(%rsp)
+	movq	%rax,\offset+R11(%rsp)
+	movq	%rax,\offset+R10(%rsp)
+	movq	%\_r9,\offset+R9(%rsp)
+	movq	%rax,\offset+R8(%rsp)
 	.endm
 
 	/*
@@ -172,6 +172,10 @@ sysexit_from_sys_call:
 	movl	RIP-R11(%rsp),%edx		/* User %eip */
 	CFI_REGISTER rip,rdx
 	RESTORE_ARGS 1,24,1,1,1,1
+	xorq	%r8,%r8
+	xorq	%r9,%r9
+	xorq	%r10,%r10
+	xorq	%r11,%r11
 	popfq
 	CFI_ADJUST_CFA_OFFSET -8
 	/*CFI_RESTORE rflags*/
@@ -200,9 +204,9 @@ sysexit_from_sys_call:
 	movl RDI-ARGOFFSET(%rsp),%r8d	/* reload 5th syscall arg */
 	.endm
 
-	.macro auditsys_exit exit,ebpsave=RBP
+	.macro auditsys_exit exit
 	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10)
-	jnz int_ret_from_sys_call
+	jnz ia32_ret_from_sys_call
 	TRACE_IRQS_ON
 	sti
 	movl %eax,%esi		/* second arg, syscall return value */
@@ -213,13 +217,13 @@ sysexit_from_sys_call:
 	call audit_syscall_exit
 	GET_THREAD_INFO(%r10)
 	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall return value */
-	movl \ebpsave-ARGOFFSET(%rsp),%ebp /* reload user register value */
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
 	cli
 	TRACE_IRQS_OFF
 	testl %edi,TI_flags(%r10)
-	jnz int_with_check
-	jmp \exit
+	jz \exit
+	CLEAR_RREGS -ARGOFFSET
+	jmp int_with_check
 	.endm
 
 sysenter_auditsys:
@@ -329,6 +333,9 @@ sysretl_from_sys_call:
 	CFI_REGISTER rip,rcx
 	movl EFLAGS-ARGOFFSET(%rsp),%r11d	
 	/*CFI_REGISTER rflags,r11*/
+	xorq	%r10,%r10
+	xorq	%r9,%r9
+	xorq	%r8,%r8
 	TRACE_IRQS_ON
 	movl RSP-ARGOFFSET(%rsp),%esp
 	CFI_RESTORE rsp
@@ -343,7 +350,7 @@ cstar_auditsys:
 	jmp cstar_dispatch
 
 sysretl_audit:
-	auditsys_exit sysretl_from_sys_call, RCX /* user %ebp in RCX slot */
+	auditsys_exit sysretl_from_sys_call
 #endif
 
 cstar_tracesys:
@@ -353,7 +360,7 @@ cstar_tracesys:
 #endif
 	xchgl %r9d,%ebp
 	SAVE_REST
-	CLEAR_RREGS r9
+	CLEAR_RREGS 0, r9
 	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
 	movq %rsp,%rdi        /* &pt_regs -> arg1 */
 	call syscall_trace_enter
@@ -425,6 +432,8 @@ ia32_do_call:
 	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
 ia32_sysret:
 	movq %rax,RAX-ARGOFFSET(%rsp)
+ia32_ret_from_sys_call:
+	CLEAR_RREGS -ARGOFFSET
 	jmp int_ret_from_sys_call 
 
 ia32_tracesys:			 
@@ -442,8 +451,8 @@ END(ia32_syscall)
 
 ia32_badsys:
 	movq $0,ORIG_RAX-ARGOFFSET(%rsp)
-	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
-	jmp int_ret_from_sys_call
+	movq $-ENOSYS,%rax
+	jmp ia32_sysret
 
 quiet_ni_syscall:
 	movq $-ENOSYS,%rax
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index ac95995b7ba..4b180897e6b 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -31,6 +31,7 @@ extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
 extern void amd_iommu_flush_all_domains(void);
 extern void amd_iommu_flush_all_devices(void);
 extern void amd_iommu_shutdown(void);
+extern void amd_iommu_apply_erratum_63(u16 devid);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index e8de2f6f5ca..617bd56b307 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -288,7 +288,7 @@ static inline void load_LDT(mm_context_t *pc)
 
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
-	return desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24);
+	return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
 }
 
 static inline void set_desc_base(struct desc_struct *desc, unsigned long base)
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 0ee770d23d0..6a25d5d4283 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -14,6 +14,12 @@
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
 
+#ifdef CONFIG_ISA
+# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
+#else
+# define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
+#endif
+
 extern dma_addr_t bad_dma_address;
 extern int iommu_merge;
 extern struct device x86_dma_fallback_dev;
@@ -124,10 +130,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
 		return memory;
 
-	if (!dev) {
+	if (!dev)
 		dev = &x86_dma_fallback_dev;
-		gfp |= GFP_DMA;
-	}
 
 	if (!is_device_dma_capable(dev))
 		return NULL;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3be000435fa..d83892226f7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -796,6 +796,7 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index b608a64c581..f1363b72364 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -133,6 +133,8 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
 static inline void enable_p5_mce(void) {}
 #endif
 
+extern void (*x86_mce_decode_callback)(struct mce *m);
+
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, mce_dev);
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8aebcc41041..efb38994859 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -840,42 +840,22 @@ static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
 
 static inline unsigned long __raw_local_save_flags(void)
 {
-	unsigned long f;
-
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     : "=a"(f)
-		     : paravirt_type(pv_irq_ops.save_fl),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc");
-	return f;
+	return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
 }
 
 static inline void raw_local_irq_restore(unsigned long f)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     : "=a"(f)
-		     : PV_FLAGS_ARG(f),
-		       paravirt_type(pv_irq_ops.restore_fl),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc");
+	PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
 }
 
 static inline void raw_local_irq_disable(void)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     :
-		     : paravirt_type(pv_irq_ops.irq_disable),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc");
+	PVOP_VCALLEE0(pv_irq_ops.irq_disable);
 }
 
 static inline void raw_local_irq_enable(void)
 {
-	asm volatile(paravirt_alt(PARAVIRT_CALL)
-		     :
-		     : paravirt_type(pv_irq_ops.irq_enable),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc");
+	PVOP_VCALLEE0(pv_irq_ops.irq_enable);
 }
 
 static inline unsigned long __raw_local_irq_save(void)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index dd0f5b32489..9357473c8da 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -494,10 +494,11 @@ int paravirt_disable_iospace(void);
 #define EXTRA_CLOBBERS
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
+/* [re]ax isn't an arg, but the return val */
 #define PVOP_VCALL_ARGS					\
 	unsigned long __edi = __edi, __esi = __esi,	\
-		__edx = __edx, __ecx = __ecx
-#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS, __eax
+		__edx = __edx, __ecx = __ecx, __eax = __eax
+#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)		"D" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)		"S" ((unsigned long)(x))
@@ -509,6 +510,7 @@ int paravirt_disable_iospace(void);
 				"=c" (__ecx)
 #define PVOP_CALL_CLOBBERS	PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
+/* void functions are still allowed [re]ax for scratch */
 #define PVOP_VCALLEE_CLOBBERS	"=a" (__eax)
 #define PVOP_CALLEE_CLOBBERS	PVOP_VCALLEE_CLOBBERS
 
@@ -583,8 +585,8 @@ int paravirt_disable_iospace(void);
 		       VEXTRA_CLOBBERS,					\
 		       pre, post, ##__VA_ARGS__)
 
-#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...)			\
-	____PVOP_CALL(rettype, op.func, CLBR_RET_REG,			\
+#define __PVOP_VCALLEESAVE(op, pre, post, ...)				\
+	____PVOP_VCALL(op.func, CLBR_RET_REG,				\
 		      PVOP_VCALLEE_CLOBBERS, ,				\
 		      pre, post, ##__VA_ARGS__)
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c3429e8b242..c9786480f0f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -1000,7 +1000,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
-#define KSTK_ESP(tsk)		-1 /* sorry. doesn't work for syscall. */
+extern unsigned long KSTK_ESP(struct task_struct *task);
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 25a92842dd9..40e37b10c6c 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,6 +143,7 @@ extern unsigned long node_remap_size[];
 				| 1*SD_BALANCE_FORK			\
 				| 0*SD_BALANCE_WAKE			\
 				| 1*SD_WAKE_AFFINE			\
+				| 0*SD_PREFER_LOCAL			\
 				| 0*SD_SHARE_CPUPOWER			\
 				| 0*SD_POWERSAVINGS_BALANCE		\
 				| 0*SD_SHARE_PKG_RESOURCES		\
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 04eb6c958b9..d1414af9855 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -19,6 +19,8 @@
 #include <asm/types.h>
 #include <asm/percpu.h>
 #include <asm/uv/uv_mmrs.h>
+#include <asm/irq_vectors.h>
+#include <asm/io_apic.h>
 
 
 /*
@@ -114,7 +116,7 @@
 /*
  * The largest possible NASID of a C or M brick (+ 2)
  */
-#define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_NODES * 2)
+#define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_BLADES * 2)
 
 struct uv_scir_s {
 	struct timer_list timer;
@@ -230,6 +232,20 @@ static inline unsigned long uv_gpa(void *v)
 	return uv_soc_phys_ram_to_gpa(__pa(v));
 }
 
+/* gnode -> pnode */
+static inline unsigned long uv_gpa_to_gnode(unsigned long gpa)
+{
+	return gpa >> uv_hub_info->m_val;
+}
+
+/* gpa -> pnode */
+static inline int uv_gpa_to_pnode(unsigned long gpa)
+{
+	unsigned long n_mask = (1UL << uv_hub_info->n_val) - 1;
+
+	return uv_gpa_to_gnode(gpa) & n_mask;
+}
+
 /* pnode, offset --> socket virtual */
 static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
 {
@@ -421,9 +437,14 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 {
 	unsigned long val;
+	unsigned long dmode = dest_Fixed;
+
+	if (vector == NMI_VECTOR)
+		dmode = dest_NMI;
 
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 			((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
+			(dmode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
 			(vector << UVH_IPI_INT_VECTOR_SHFT);
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 }
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
index 7da00b799cd..060fff8f5c5 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
@@ -57,5 +57,8 @@ SECTIONS
 		*(.note*)
 	}
 
+	/*
+	 * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+	 */
 	. = ASSERT(_end <= WAKEUP_SIZE, "Wakeup too big!");
 }
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 98f230f6a28..0285521e0a9 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1220,6 +1220,8 @@ static void __detach_device(struct protection_domain *domain, u16 devid)
 	amd_iommu_dev_table[devid].data[1] = 0;
 	amd_iommu_dev_table[devid].data[2] = 0;
 
+	amd_iommu_apply_erratum_63(devid);
+
 	/* decrease reference counter */
 	domain->dev_cnt -= 1;
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index b4b61d462dc..c20001e4f55 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -240,7 +240,7 @@ static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
 	writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
 }
 
-static void __init iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
+static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
 {
 	u32 ctrl;
 
@@ -519,6 +519,26 @@ static void set_dev_entry_bit(u16 devid, u8 bit)
 	amd_iommu_dev_table[devid].data[i] |= (1 << _bit);
 }
 
+static int get_dev_entry_bit(u16 devid, u8 bit)
+{
+	int i = (bit >> 5) & 0x07;
+	int _bit = bit & 0x1f;
+
+	return (amd_iommu_dev_table[devid].data[i] & (1 << _bit)) >> _bit;
+}
+
+
+void amd_iommu_apply_erratum_63(u16 devid)
+{
+	int sysmgt;
+
+	sysmgt = get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1) |
+		 (get_dev_