20 files changed, 294 insertions, 123 deletions

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 968dbe24a255..41a7237606a3 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -129,6 +129,7 @@ KBUILD_CFLAGS += -Wno-sign-compare
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 # prevent gcc from generating any FP code by mistake
 KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
+KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ed3065fd6314..4b4331d71935 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -59,7 +59,8 @@ extern int dma_supported(struct device *hwdev, u64 mask);
 extern int dma_set_mask(struct device *dev, u64 mask);
 
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag);
+					dma_addr_t *dma_addr, gfp_t flag,
+					struct dma_attrs *attrs);
 
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
@@ -111,9 +112,11 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
        return gfp;
 }
 
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
 static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp)
+dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 	void *memory;
@@ -129,18 +132,21 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (!is_device_dma_capable(dev))
 		return NULL;
 
-	if (!ops->alloc_coherent)
+	if (!ops->alloc)
 		return NULL;
 
-	memory = ops->alloc_coherent(dev, size, dma_handle,
-				     dma_alloc_coherent_gfp_flags(dev, gfp));
+	memory = ops->alloc(dev, size, dma_handle,
+			    dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
 	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
 
 	return memory;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t bus)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t bus,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
@@ -150,8 +156,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 		return;
 
 	debug_dma_free_coherent(dev, size, vaddr, bus);
-	if (ops->free_coherent)
-		ops->free_coherent(dev, size, vaddr, bus);
+	if (ops->free)
+		ops->free(dev, size, vaddr, bus, attrs);
 }
 
 #endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7284c9a6a0b5..4fa7dcceb6c0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -974,16 +974,6 @@ extern bool cpu_has_amd_erratum(const int *);
 #define cpu_has_amd_erratum(x)	(false)
 #endif /* CONFIG_CPU_SUP_AMD */
 
-#ifdef CONFIG_X86_32
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-#endif
-
-void disable_hlt(void);
-void enable_hlt(void);
-
 void cpu_idle_wait(void);
 
 extern unsigned long arch_align_stack(unsigned long sp);
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..6fe6767b7124
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,46 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+	return mask*0x0001020304050608ul >> 56;
+}
+
+#else	/* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+#endif
+
+#define REPEAT_BYTE(x)	((~0ul / 0xff) * (x))
+
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+	return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b1e7c7f7a0af..e66311200cbd 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -477,7 +477,7 @@ error:
 /* allocate and map a coherent mapping */
 static void *
 gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
-		    gfp_t flag)
+		    gfp_t flag, struct dma_attrs *attrs)
 {
 	dma_addr_t paddr;
 	unsigned long align_mask;
@@ -500,7 +500,8 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 		}
 		__free_pages(page, get_order(size));
 	} else
-		return dma_generic_alloc_coherent(dev, size, dma_addr, flag);
+		return dma_generic_alloc_coherent(dev, size, dma_addr, flag,
+						  attrs);
 
 	return NULL;
 }
@@ -508,7 +509,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 /* free a coherent mapping */
 static void
 gart_free_coherent(struct device *dev, size_t size, void *vaddr,
-		   dma_addr_t dma_addr)
+		   dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL);
 	free_pages((unsigned long)vaddr, get_order(size));
@@ -700,8 +701,8 @@ static struct dma_map_ops gart_dma_ops = {
 	.unmap_sg			= gart_unmap_sg,
 	.map_page			= gart_map_page,
 	.unmap_page			= gart_unmap_page,
-	.alloc_coherent			= gart_alloc_coherent,
-	.free_coherent			= gart_free_coherent,
+	.alloc				= gart_alloc_coherent,
+	.free				= gart_free_coherent,
 	.mapping_error			= gart_mapping_error,
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ef484d9d0a25..a2dfacfd7103 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1271,6 +1271,17 @@ done:
 	return num ? -EINVAL : 0;
 }
 
+PMU_FORMAT_ATTR(cccr, "config:0-31" );
+PMU_FORMAT_ATTR(escr, "config:32-62");
+PMU_FORMAT_ATTR(ht,   "config:63"   );
+
+static struct attribute *intel_p4_formats_attr[] = {
+	&format_attr_cccr.attr,
+	&format_attr_escr.attr,
+	&format_attr_ht.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu p4_pmu = {
 	.name			= "Netburst P4/Xeon",
 	.handle_irq		= p4_pmu_handle_irq,
@@ -1305,6 +1316,8 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 * the former idea is taken from OProfile code
 	 */
 	.perfctr_second_write	= 1,
+
+	.format_attrs		= intel_p4_formats_attr,
 };
 
 __init int p4_pmu_init(void)
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7943e0c21bde..3dafc6003b7c 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -282,8 +282,13 @@ void fixup_irqs(void)
 		else if (!(warned++))
 			set_affinity = 0;
 
+		/*
+		 * We unmask if the irq was not marked masked by the
+		 * core code. That respects the lazy irq disable
+		 * behaviour.
+		 */
 		if (!irqd_can_move_in_process_context(data) &&
-		    !irqd_irq_disabled(data) && chip->irq_unmask)
+		    !irqd_irq_masked(data) && chip->irq_unmask)
 			chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 90fcf62854bb..1d5d31ea686b 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -68,16 +68,9 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
 	return count;
 }
 
-static int setup_data_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-
-	return 0;
-}
-
 static const struct file_operations fops_setup_data = {
 	.read		= setup_data_read,
-	.open		= setup_data_open,
+	.open		= simple_open,
 	.llseek		= default_llseek,
 };
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index db6720edfdd0..8bfb6146f753 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -43,6 +43,8 @@
 #include <linux/smp.h>
 #include <linux/nmi.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/uaccess.h>
+#include <linux/memory.h>
 
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
@@ -741,6 +743,64 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+	int err;
+	char opc[BREAK_INSTR_SIZE];
+
+	bpt->type = BP_BREAKPOINT;
+	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+				BREAK_INSTR_SIZE);
+	if (err)
+		return err;
+	err = probe_kernel_write((char *)bpt->bpt_addr,
+				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
+#ifdef CONFIG_DEBUG_RODATA
+	if (!err)
+		return err;
+	/*
+	 * It is safe to call text_poke() because normal kernel execution
+	 * is stopped on all cores, so long as the text_mutex is not locked.
+	 */
+	if (mutex_is_locked(&text_mutex))
+		return -EBUSY;
+	text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+		  BREAK_INSTR_SIZE);
+	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+	if (err)
+		return err;
+	if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
+		return -EINVAL;
+	bpt->type = BP_POKE_BREAKPOINT;
+#endif /* CONFIG_DEBUG_RODATA */
+	return err;
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+#ifdef CONFIG_DEBUG_RODATA
+	int err;
+	char opc[BREAK_INSTR_SIZE];
+
+	if (bpt->type != BP_POKE_BREAKPOINT)
+		goto knl_write;
+	/*
+	 * It is safe to call text_poke() because normal kernel execution
+	 * is stopped on all cores, so long as the text_mutex is not locked.
+	 */
+	if (mutex_is_locked(&text_mutex))
+		goto knl_write;
+	text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
+	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+	if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
+		goto knl_write;
+	return err;
+knl_write:
+#endif /* CONFIG_DEBUG_RODATA */
+	return probe_kernel_write((char *)bpt->bpt_addr,
+				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
+}
+
 struct kgdb_arch arch_kgdb_ops = {
 	/* Breakpoint instruction: */
 	.gdb_bpt_instr		= { 0xcc },
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 6ac5782f4d6b..d0b2fb9ccbb1 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -430,7 +430,7 @@ static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr,
 }
 
 static void* calgary_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t flag)
+	dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs)
 {
 	void *ret = NULL;
 	dma_addr_t mapping;
@@ -463,7 +463,8 @@ error:
 }
 
 static void calgary_free_coherent(struct device *dev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle)
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	unsigned int npages;
 	struct iommu_table *tbl = find_iommu_table(dev);
@@ -476,8 +477,8 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 }
 
 static struct dma_map_ops calgary_dma_ops = {
-	.alloc_coherent = calgary_alloc_coherent,
-	.free_coherent = calgary_free_coherent,
+	.alloc = calgary_alloc_coherent,
+	.free = calgary_free_coherent,
 	.map_sg = calgary_map_sg,
 	.unmap_sg = calgary_unmap_sg,
 	.map_page = calgary_map_page,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 28e5e06fcba4..3003250ac51d 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -96,7 +96,8 @@ void __init pci_iommu_alloc(void)
 	}
 }
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_addr, gfp_t flag)
+				 dma_addr_t *dma_addr, gfp_t flag,
+				 struct dma_attrs *attrs)
 {
 	unsigned long dma_mask;
 	struct page *page;
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 3af4af810c07..f96050685b46 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -75,7 +75,7 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 }
 
 static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
-				dma_addr_t dma_addr)
+				dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
 	free_pages((unsigned long)vaddr, get_order(size));
 }
@@ -96,8 +96,8 @@ static void nommu_sync_sg_for_device(struct device *dev,
 }
 
 struct dma_map_ops nommu_dma_ops = {
-	.alloc_coherent		= dma_generic_alloc_coherent,
-	.free_coherent		= nommu_free_coherent,
+	.alloc			= dma_generic_alloc_coherent,
+	.free			= nommu_free_coherent,
 	.map_sg			= nommu_map_sg,
 	.map_page		= nommu_map_page,
 	.sync_single_for_device = nommu_sync_single_for_device,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 8f972cbddef0..6c483ba98b9c 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -15,21 +15,30 @@
 int swiotlb __read_mostly;
 
 static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-					dma_addr_t *dma_handle, gfp_t flags)
+					dma_addr_t *dma_handle, gfp_t flags,
+					struct dma_attrs *attrs)
 {
 	void *vaddr;
 
-	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags);
+	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
+					   attrs);
 	if (vaddr)
 		return vaddr;
 
 	return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
 }
 
+static void x86_swiotlb_free_coherent(struct device *dev, size_t size,
+				      void *vaddr, dma_addr_t dma_addr,
+				      struct dma_attrs *attrs)
+{
+	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
+
 static struct dma_map_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
-	.alloc_coherent = x86_swiotlb_alloc_coherent,
-	.free_coherent = swiotlb_free_coherent,
+	.alloc = x86_swiotlb_alloc_coherent,
+	.free = x86_swiotlb_free_coherent,
 	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index a33afaa5ddb7..1d92a5ab6e8b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -362,34 +362,10 @@ void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
 #endif
 
-#ifdef CONFIG_X86_32
-/*
- * This halt magic was a workaround for ancient floppy DMA
- * wreckage. It should be safe to remove.
- */
-static int hlt_counter;
-void disable_hlt(void)
-{
-	hlt_counter++;
-}
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
-	hlt_counter--;
-}
-EXPORT_SYMBOL(enable_hlt);
-
-static inline int hlt_use_halt(void)
-{
-	return (!hlt_counter && boot_cpu_data.hlt_works_ok);
-}
-#else
 static inline int hlt_use_halt(void)
 {
 	return 1;
 }
-#endif
 
 #ifndef CONFIG_SMP
 static inline void play_dead(void)
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 66870223f8c5..877b9a1b2152 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -18,17 +18,17 @@
  * r9d : hlen = skb->len - skb->data_len
  */
 #define SKBDATA	%r8
-
-sk_load_word_ind:
-	.globl	sk_load_word_ind
-
-	add	%ebx,%esi	/* offset += X */
-#	test    %esi,%esi	/* if (offset < 0) goto bpf_error; */
-	js	bpf_error
+#define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
 
 sk_load_word:
 	.globl	sk_load_word
 
+	test	%esi,%esi
+	js	bpf_slow_path_word_neg
+
+sk_load_word_positive_offset:
+	.globl	sk_load_word_positive_offset
+
 	mov	%r9d,%eax		# hlen
 	sub	%esi,%eax		# hlen - offset
 	cmp	$3,%eax
@@ -37,16 +37,15 @@ sk_load_word:
 	bswap   %eax  			/* ntohl() */
 	ret
 
-
-sk_load_half_ind:
-	.globl sk_load_half_ind
-
-	add	%ebx,%esi	/* offset += X */
-	js	bpf_error
-
 sk_load_half:
 	.globl	sk_load_half
 
+	test	%esi,%esi
+	js	bpf_slow_path_half_neg
+
+sk_load_half_positive_offset:
+	.globl	sk_load_half_positive_offset
+
 	mov	%r9d,%eax
 	sub	%esi,%eax		#	hlen - offset
 	cmp	$1,%eax
@@ -55,14 +54,15 @@ sk_load_half:
 	rol	$8,%ax			# ntohs()
 	ret
 
-sk_load_byte_ind:
-	.globl sk_load_byte_ind
-	add	%ebx,%esi	/* offset += X */
-	js	bpf_error
-
 sk_load_byte:
 	.globl	sk_load_byte
 
+	test	%esi,%esi
+	js	bpf_slow_path_byte_neg
+
+sk_load_byte_positive_offset:
+	.globl	sk_load_byte_positive_offset
+
 	cmp	%esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
 	jle	bpf_slow_path_byte
 	movzbl	(SKBDATA,%rsi),%eax
@@ -73,25 +73,21 @@ sk_load_byte:
  *
  * Implements BPF_S_LDX_B_MSH : ldxb  4*([offset]&0xf)
  * Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value, already known positive
+ * Inputs : %esi is the offset value
  */
-ENTRY(sk_load_byte_msh)
-	CFI_STARTPROC
+sk_load_byte_msh:
+	.globl	sk_load_byte_msh
+	test	%esi,%esi
+	js	bpf_slow_path_byte_msh_neg
+
+sk_load_byte_msh_positive_offset:
+	.globl	sk_load_byte_msh_positive_offset
 	cmp	%esi,%r9d      /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
 	jle	bpf_slow_path_byte_msh
 	movzbl	(SKBDATA,%rsi),%ebx
 	and	$15,%bl
 	shl	$2,%bl
 	ret
-	CFI_ENDPROC
-ENDPROC(sk_load_byte_msh)
-
-bpf_error:
-# force a return 0 from jit handler
-	xor		%eax,%eax
-	mov		-8(%rbp),%rbx
-	leaveq
-	ret
 
 /* rsi contains offset and can be scratched */
 #define bpf_slow_path_common(LEN)		\
@@ -138,3 +134,67 @@ bpf_slow_path_byte_msh:
 	shl	$2,%al
 	xchg	%eax,%ebx
 	ret
+
+#define sk_negative_common(SIZE)				\
+	push	%rdi;	/* save skb */				\
+	push	%r9;						\
+	push	SKBDATA;					\
+/* rsi already has offset */					\
+	mov	$SIZE,%ecx;	/* size */			\
+	call	bpf_internal_load_pointer_neg_helper;		\
+	test	%rax,%rax;					\
+	pop	SKBDATA;					\
+	pop	%r9;						\
+	pop	%rdi;						\
+	jz	bpf_error
+
+
+bpf_slow_path_word_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
+	jl	bpf_error	/* offset lower -> error  */
+sk_load_word_negative_offset:
+	.globl	sk_load_word_negative_offset
+	sk_negative_common(4)
+	mov	(%rax), %eax
+	bswap	%eax
+	ret
+
+bpf_slow_path_half_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_half_negative_offset:
+	.globl	sk_load_half_negative_offset
+	sk_negative_common(2)
+	mov	(%rax),%ax
+	rol	$8,%ax
+	movzwl	%ax,%eax
+	ret
+
+bpf_slow_path_byte_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_byte_negative_offset:
+	.globl	sk_load_byte_negative_offset
+	sk_negative_common(1)
+	movzbl	(%rax), %eax
+	ret
+
+bpf_slow_path_byte_msh_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_byte_msh_negative_offset:
+	.globl	sk_load_byte_msh_negative_offset
+	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
+	sk_negative_common(1)
+	movzbl	(%rax),%eax
+	and	$15,%al
+	shl	$2,%al
+	xchg	%eax,%ebx
+	ret
+
+bpf_error:
+# force a return 0 from jit handler
+	xor		%eax,%eax
+	mov		-8(%rbp),%rbx
+	leaveq
+	ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5a5b6e4dd738..0597f95b6da6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -30,7 +30,10 @@ int bpf_jit_enable __read_mostly;
  * assembly code in arch/x86/net/bpf_jit.S
  */
 extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
-extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[];
+extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
+extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
+extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
 
 static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -117,6 +120,8 @@ static inline void bpf_flush_icache(void *start, void *end)
 	set_fs(old_fs);
 }
 
+#define CHOOSE_LOAD_FUNC(K, func) \
+	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
 void bpf_jit_compile(struct sk_filter *fp)
 {
@@ -473,44 +478,46 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
 				break;
 			case BPF_S_LD_W_ABS:
-				func = sk_load_word;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 common_load:			seen |= SEEN_DATAREF;
-				if ((int)K < 0) {
-					/* Abort the JIT because __load_pointer() is needed. */
-					goto out;
-				}
 				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K); /* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call */
 				break;
 			case BPF_S_LD_H_ABS:
-				func = sk_load_half;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_half);
 				goto common_load;
 			case BPF_S_LD_B_ABS:
-				func = sk_load_byte;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
 				goto common_load;
 			case BPF_S_LDX_B_MSH:
-				if ((int)K < 0) {
-					/* Abort the JIT because __load_pointer() is needed. */
-					goto out;
-				}
+				func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 				seen |= SEEN_DATAREF | SEEN_XREG;
-				t_offset = sk_load_byte_msh - (image + addrs[i]);
+				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K);	/* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
 				break;
 			case BPF_S_LD_W_IND:
-				func = sk_load_word_ind;
+				func = sk_load_word;
 common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 				t_offset = func - (image + addrs[i]);
-				EMIT1_off32(0xbe, K);	/* mov imm32,%esi   */
+				if (K) {
+					if (is_imm8(K)) {
+						EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */
+					} else {
+						EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
+						EMIT(K, 4);
+					}
+				} else {
+					EMIT2(0x89,0xde); /* mov %ebx,%esi */
+				}
 				EMIT1_off32(0xe8, t_offset);	/* call sk_load_xxx_ind */
 				break;
 			case BPF_S_LD_H_IND:
-				func = sk_load_half_ind;
+				func = sk_load_half;
 				goto common_load_ind;
 			case BPF_S_LD_B_IND:
-				func = sk_load_byte_ind;
+				func = sk_load_byte;
 				goto common_load_ind;
 			case BPF_S_JMP_JA:
 				t_offset = addrs[i + K] - addrs[i];
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 47936830968c..218cdb16163c 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -225,13 +225,13 @@ static void __restore_processor_state(struct saved_context *ctxt)
 	fix_processor_context();
 
 	do_fpu_end();
+	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
 }
 
 /* Needed by apm.c */
 void restore_processor_state(void)
 {
-	x86_platform.restore_sched_clock_state();
 	__restore_processor_state(&saved_context);
 }
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 988828b479ed..b8e279479a6b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1859,6 +1859,7 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 #endif	/* CONFIG_X86_64 */
 
 static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
+static unsigned char fake_ioapic_mapping[PAGE_SIZE] __page_aligned_bss;
 
 static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 {
@@ -1899,7 +1900,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 		 * We just don't map the IO APIC - all access is via
 		 * hypercalls.  Keep the address in the pte for reference.
 		 */
-		pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
+		pte = pfn_pte(PFN_DOWN(__pa(fake_ioapic_mapping)), PAGE_KERNEL);
 		break;
 #endif
 
@@ -2064,6 +2065,7 @@ void __init xen_init_mmu_ops(void)
 	pv_mmu_ops = xen_mmu_ops;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
+	memset(fake_ioapic_mapping, 0xfd, PAGE_SIZE);
 }
 
 /* Protected by xen_reservation_lock. */
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index b480d4207a4c..967633ad98c4 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -12,8 +12,8 @@ int xen_swiotlb __read_mostly;
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
 	.mapping_error = xen_swiotlb_dma_mapping_error,
-	.alloc_coherent = xen_swiotlb_alloc_coherent,
-	.free_coherent = xen_swiotlb_free_coherent,
+	.alloc = xen_swiotlb_alloc_coherent,
+	.free = xen_swiotlb_free_coherent,
 	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 02900e8ce26c..5fac6919b957 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -59,7 +59,7 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 
 static void __cpuinit cpu_bringup(void)
 {
-	int cpu = smp_processor_id();
+	int cpu;
 
 	cpu_init();
 	touch_softlockup_watchdog();