Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
	net/ipv4/tcp_metrics.c

Overlapping changes between the "don't create two tcp metrics objects
with the same key" race fix in net and the addition of the destination
address in the lookup key in net-next.

Minor overlapping changes in bnx2x driver.

Signed-off-by: David S. Miller <davem@davemloft.net>

22 files changed, 123 insertions, 82 deletions

diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 739c3dfc1da..34d5fd585bb 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -171,7 +171,7 @@ void __init arm_dt_init_cpu_maps(void)
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
-	return (phys_id & MPIDR_HWID_BITMASK) == cpu_logical_map(cpu);
+	return phys_id == cpu_logical_map(cpu);
 }
 
 static const void * __init arch_get_next_mach(const char *const **match)
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index d85055cd24b..20d553c9f5e 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -254,7 +254,7 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
-	int (*init_fn)(struct arm_pmu *);
+	const int (*init_fn)(struct arm_pmu *);
 	struct device_node *node = pdev->dev.of_node;
 	struct arm_pmu *pmu;
 	int ret = -ENODEV;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 6eda3bf85c5..4636d56af2d 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -431,9 +431,10 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 			instr2 = __mem_to_opcode_thumb16(instr2);
 			instr = __opcode_thumb32_compose(instr, instr2);
 		}
-	} else if (get_user(instr, (u32 __user *)pc)) {
+	} else {
+		if (get_user(instr, (u32 __user *)pc))
+			goto die_sig;
 		instr = __mem_to_opcode_arm(instr);
-		goto die_sig;
 	}
 
 	if (call_undef_hook(regs, instr) == 0)
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index bd3bf66ce34..c7de89b263d 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -53,6 +53,7 @@ static void __init highbank_scu_map_io(void)
 
 static void highbank_l2x0_disable(void)
 {
+	outer_flush_all();
 	/* Disable PL310 L2 Cache controller */
 	highbank_smc1(0x102, 0x0);
 }
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index b39efd46abf..c0ab9b26be3 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -162,6 +162,7 @@ void __iomem *omap4_get_l2cache_base(void)
 
 static void omap4_l2x0_disable(void)
 {
+	outer_flush_all();
 	/* Disable PL310 L2 Cache controller */
 	omap_smc1(0x102, 0x0);
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 1f7b19a4706..3e8f106ee5f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -229,7 +229,7 @@ void __init setup_dma_zone(const struct machine_desc *mdesc)
 #ifdef CONFIG_ZONE_DMA
 	if (mdesc->dma_zone_size) {
 		arm_dma_zone_size = mdesc->dma_zone_size;
-		arm_dma_limit = __pv_phys_offset + arm_dma_zone_size - 1;
+		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
 	} else
 		arm_dma_limit = 0xffffffff;
 	arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT;
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 9ed155ad0f9..271b5e97156 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -641,10 +641,10 @@ load_ind:
 			emit(ARM_MUL(r_A, r_A, r_X), ctx);
 			break;
 		case BPF_S_ALU_DIV_K:
-			/* current k == reciprocal_value(userspace k) */
+			if (k == 1)
+				break;
 			emit_mov_i(r_scratch, k, ctx);
-			/* A = top 32 bits of the product */
-			emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+			emit_udiv(r_A, r_A, r_scratch, ctx);
 			break;
 		case BPF_S_ALU_DIV_X:
 			update_on_xread(ctx);
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 57276972722..4cc813eddac 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -229,7 +229,7 @@ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot
 extern void __iounmap(volatile void __iomem *addr);
 extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 
-#define PROT_DEFAULT		(pgprot_default | PTE_DIRTY)
+#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL_NC))
 #define PROT_NORMAL		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
diff --git a/arch/mips/include/asm/cacheops.h b/arch/mips/include/asm/cacheops.h
index c75025f27c2..06b9bc7ea14 100644
--- a/arch/mips/include/asm/cacheops.h
+++ b/arch/mips/include/asm/cacheops.h
@@ -83,6 +83,6 @@
 /*
  * Loongson2-specific cacheops
  */
-#define Hit_Invalidate_I_Loongson23	0x00
+#define Hit_Invalidate_I_Loongson2	0x00
 
 #endif	/* __ASM_CACHEOPS_H */
diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index 34d1a191712..c84caddb8bd 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -165,7 +165,7 @@ static inline void flush_icache_line(unsigned long addr)
 	__iflush_prologue
 	switch (boot_cpu_type()) {
 	case CPU_LOONGSON2:
-		cache_op(Hit_Invalidate_I_Loongson23, addr);
+		cache_op(Hit_Invalidate_I_Loongson2, addr);
 		break;
 
 	default:
@@ -219,7 +219,7 @@ static inline void protected_flush_icache_line(unsigned long addr)
 {
 	switch (boot_cpu_type()) {
 	case CPU_LOONGSON2:
-		protected_cache_op(Hit_Invalidate_I_Loongson23, addr);
+		protected_cache_op(Hit_Invalidate_I_Loongson2, addr);
 		break;
 
 	default:
@@ -357,8 +357,8 @@ static inline void invalidate_tcache_page(unsigned long addr)
 		  "i" (op));
 
 /* build blast_xxx, blast_xxx_page, blast_xxx_page_indexed */
-#define __BUILD_BLAST_CACHE(pfx, desc, indexop, hitop, lsize) \
-static inline void blast_##pfx##cache##lsize(void)			\
+#define __BUILD_BLAST_CACHE(pfx, desc, indexop, hitop, lsize, extra)	\
+static inline void extra##blast_##pfx##cache##lsize(void)		\
 {									\
 	unsigned long start = INDEX_BASE;				\
 	unsigned long end = start + current_cpu_data.desc.waysize;	\
@@ -376,7 +376,7 @@ static inline void blast_##pfx##cache##lsize(void)			\
 	__##pfx##flush_epilogue						\
 }									\
 									\
-static inline void blast_##pfx##cache##lsize##_page(unsigned long page) \
+static inline void extra##blast_##pfx##cache##lsize##_page(unsigned long page) \
 {									\
 	unsigned long start = page;					\
 	unsigned long end = page + PAGE_SIZE;				\
@@ -391,7 +391,7 @@ static inline void blast_##pfx##cache##lsize##_page(unsigned long page) \
 	__##pfx##flush_epilogue						\
 }									\
 									\
-static inline void blast_##pfx##cache##lsize##_page_indexed(unsigned long page) \
+static inline void extra##blast_##pfx##cache##lsize##_page_indexed(unsigned long page) \
 {									\
 	unsigned long indexmask = current_cpu_data.desc.waysize - 1;	\
 	unsigned long start = INDEX_BASE + (page & indexmask);		\
@@ -410,23 +410,24 @@ static inline void blast_##pfx##cache##lsize##_page_indexed(unsigned long page)
 	__##pfx##flush_epilogue						\
 }
 
-__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 16)
-__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 16)
-__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16)
-__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 32)
-__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 32)
-__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32)
-__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 64)
-__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 64)
-__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64)
-__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128)
-
-__BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 16)
-__BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 32)
-__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 16)
-__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 32)
-__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 64)
-__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 128)
+__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 16, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 16, )
+__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16, )
+__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 32, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 32, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I_Loongson2, 32, loongson2_)
+__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32, )
+__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 64, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 64, )
+__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64, )
+__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128, )
+
+__BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 16, )
+__BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 32, )
+__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 16, )
+__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 32, )
+__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 64, )
+__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 128, )
 
 /* build blast_xxx_range, protected_blast_xxx_range */
 #define __BUILD_BLAST_CACHE_RANGE(pfx, desc, hitop, prot, extra)	\
@@ -452,8 +453,8 @@ static inline void prot##extra##blast_##pfx##cache##_range(unsigned long start,
 __BUILD_BLAST_CACHE_RANGE(d, dcache, Hit_Writeback_Inv_D, protected_, )
 __BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, protected_, )
 __BUILD_BLAST_CACHE_RANGE(i, icache, Hit_Invalidate_I, protected_, )
-__BUILD_BLAST_CACHE_RANGE(i, icache, Hit_Invalidate_I_Loongson23, \
-	protected_, loongson23_)
+__BUILD_BLAST_CACHE_RANGE(i, icache, Hit_Invalidate_I_Loongson2, \
+	protected_, loongson2_)
 __BUILD_BLAST_CACHE_RANGE(d, dcache, Hit_Writeback_Inv_D, , )
 __BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, , )
 /* blast_inv_dcache_range */
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 62ffd20ea86..49e572d879e 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -237,6 +237,8 @@ static void r4k_blast_icache_page_setup(void)
 		r4k_blast_icache_page = (void *)cache_noop;
 	else if (ic_lsize == 16)
 		r4k_blast_icache_page = blast_icache16_page;
+	else if (ic_lsize == 32 && current_cpu_type() == CPU_LOONGSON2)
+		r4k_blast_icache_page = loongson2_blast_icache32_page;
 	else if (ic_lsize == 32)
 		r4k_blast_icache_page = blast_icache32_page;
 	else if (ic_lsize == 64)
@@ -261,6 +263,9 @@ static void r4k_blast_icache_page_indexed_setup(void)
 		else if (TX49XX_ICACHE_INDEX_INV_WAR)
 			r4k_blast_icache_page_indexed =
 				tx49_blast_icache32_page_indexed;
+		else if (current_cpu_type() == CPU_LOONGSON2)
+			r4k_blast_icache_page_indexed =
+				loongson2_blast_icache32_page_indexed;
 		else
 			r4k_blast_icache_page_indexed =
 				blast_icache32_page_indexed;
@@ -284,6 +289,8 @@ static void r4k_blast_icache_setup(void)
 			r4k_blast_icache = blast_r4600_v1_icache32;
 		else if (TX49XX_ICACHE_INDEX_INV_WAR)
 			r4k_blast_icache = tx49_blast_icache32;
+		else if (current_cpu_type() == CPU_LOONGSON2)
+			r4k_blast_icache = loongson2_blast_icache32;
 		else
 			r4k_blast_icache = blast_icache32;
 	} else if (ic_lsize == 64)
@@ -580,11 +587,11 @@ static inline void local_r4k_flush_icache_range(unsigned long start, unsigned lo
 	else {
 		switch (boot_cpu_type()) {
 		case CPU_LOONGSON2:
-			protected_blast_icache_range(start, end);
+			protected_loongson2_blast_icache_range(start, end);
 			break;
 
 		default:
-			protected_loongson23_blast_icache_range(start, end);
+			protected_blast_icache_range(start, end);
 			break;
 		}
 	}
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index f33113a6141..70b3674dac4 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -75,6 +75,6 @@
 
 #define SO_BUSY_POLL		0x4027
 
-#define SO_MAX_PACING_RATE	0x4048
+#define SO_MAX_PACING_RATE	0x4028
 
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index cb64a6e1dc5..078145acf7f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1986,19 +1986,23 @@ static void __init prom_init_stdout(void)
 	/* Get the full OF pathname of the stdout device */
 	memset(path, 0, 256);
 	call_prom("instance-to-path", 3, 1, prom.stdout, path, 255);
-	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
-	val = cpu_to_be32(stdout_node);
-	prom_setprop(prom.chosen, "/chosen", "linux,stdout-package",
-		     &val, sizeof(val));
 	prom_printf("OF stdout device is: %s\n", of_stdout_device);
 	prom_setprop(prom.chosen, "/chosen", "linux,stdout-path",
 		     path, strlen(path) + 1);
 
-	/* If it's a display, note it */
-	memset(type, 0, sizeof(type));
-	prom_getprop(stdout_node, "device_type", type, sizeof(type));
-	if (strcmp(type, "display") == 0)
-		prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
+	/* instance-to-package fails on PA-Semi */
+	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
+	if (stdout_node != PROM_ERROR) {
+		val = cpu_to_be32(stdout_node);
+		prom_setprop(prom.chosen, "/chosen", "linux,stdout-package",
+			     &val, sizeof(val));
+
+		/* If it's a display, note it */
+		memset(type, 0, sizeof(type));
+		prom_getprop(stdout_node, "device_type", type, sizeof(type));
+		if (strcmp(type, "display") == 0)
+			prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
+	}
 }
 
 static int __init prom_find_machine_type(void)
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index ac3c2a10daf..555034f8505 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -223,10 +223,11 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			}
 			PPC_DIVWU(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
+		case BPF_S_ALU_DIV_K: /* A /= K */
+			if (K == 1)
+				break;
 			PPC_LI32(r_scratch1, K);
-			/* Top 32 bits of 64bit result -> A */
-			PPC_MULHWU(r_A, r_A, r_scratch1);
+			PPC_DIVWU(r_A, r_A, r_scratch1);
 			break;
 		case BPF_S_ALU_AND_X:
 			ctx->seen |= SEEN_XREG;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 16871da3737..708d60e4006 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -368,14 +368,16 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* dr %r4,%r12 */
-		EMIT2(0x1d4c);
+		/* dlr %r4,%r12 */
+		EMIT4(0xb997004c);
 		break;
-	case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K) */
-		/* m %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5c40d000, EMIT_CONST(K));
-		/* lr %r5,%r4 */
-		EMIT2(0x1854);
+	case BPF_S_ALU_DIV_K: /* A /= K */
+		if (K == 1)
+			break;
+		/* lhi %r4,0 */
+		EMIT4(0xa7480000);
+		/* dl %r4,<d(K)>(%r13) */
+		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		break;
 	case BPF_S_ALU_MOD_X: /* A %= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
@@ -385,16 +387,21 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* dr %r4,%r12 */
-		EMIT2(0x1d4c);
+		/* dlr %r4,%r12 */
+		EMIT4(0xb997004c);
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
 	case BPF_S_ALU_MOD_K: /* A %= K */
+		if (K == 1) {
+			/* lhi %r5,0 */
+			EMIT4(0xa7580000);
+			break;
+		}
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* d %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
+		/* dl %r4,<d(K)>(%r13) */
+		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 218b6b23c37..01fe9946d38 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -497,9 +497,20 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ALU_MUL_K:	/* A *= K */
 				emit_alu_K(MUL, K);
 				break;
-			case BPF_S_ALU_DIV_K:	/* A /= K */
-				emit_alu_K(MUL, K);
-				emit_read_y(r_A);
+			case BPF_S_ALU_DIV_K:	/* A /= K with K != 0*/
+				if (K == 1)
+					break;
+				emit_write_y(G0);
+#ifdef CONFIG_SPARC32
+				/* The Sparc v8 architecture requires
+				 * three instructions between a %y
+				 * register write and the first use.
+				 */
+				emit_nop();
+				emit_nop();
+				emit_nop();
+#endif
+				emit_alu_K(DIV, K);
 				break;
 			case BPF_S_ALU_DIV_X:	/* A /= X; */
 				emit_cmpi(r_X, 0);
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index c49a613c645..cea1c76d49b 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -293,12 +293,13 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. "m" is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"		/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (tsk->thread.fpu.has_fpu));
+	if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) {
+		asm volatile(
+			"fnclex\n\t"
+			"emms\n\t"
+			"fildl %P[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (tsk->thread.fpu.has_fpu));
+	}
 
 	return fpu_restore_checking(&tsk->thread.fpu);
 }
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 51e2988c572..a2a4f469788 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1082,7 +1082,7 @@ ENTRY(ftrace_caller)
 	pushl $0	/* Pass NULL as regs pointer */
 	movl 4*4(%esp), %eax
 	movl 0x4(%ebp), %edx
-	leal function_trace_op, %ecx
+	movl function_trace_op, %ecx
 	subl $MCOUNT_INSN_SIZE, %eax
 
 .globl ftrace_call
@@ -1140,7 +1140,7 @@ ENTRY(ftrace_regs_caller)
 	movl 12*4(%esp), %eax	/* Load ip (1st parameter) */
 	subl $MCOUNT_INSN_SIZE, %eax	/* Adjust ip */
 	movl 0x4(%ebp), %edx	/* Load parent ip (2nd parameter) */
-	leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+	movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
 	pushl %esp		/* Save pt_regs as 4th parameter */
 
 GLOBAL(ftrace_regs_call)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e21b0785a85..1e96c3628bf 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -88,7 +88,7 @@ END(function_hook)
 	MCOUNT_SAVE_FRAME \skip
 
 	/* Load the ftrace_ops into the 3rd parameter */
-	leaq function_trace_op, %rdx
+	movq function_trace_op(%rip), %rdx
 
 	/* Load ip into the first parameter */
 	movq RIP(%rsp), %rdi
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 1673940cf9c..775702f649c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1355,7 +1355,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	vcpu->arch.apic_base = value;
 
 	/* update jump label if enable bit changes */
-	if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
+	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
 		if (value & MSR_IA32_APICBASE_ENABLE)
 			static_key_slow_dec_deferred(&apic_hw_disabled);
 		else
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 26328e80086..4ed75dd81d0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -359,15 +359,21 @@ void bpf_jit_compile(struct sk_filter *fp)
 				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
 				break;
 			case BPF_S_ALU_MOD_K: /* A %= K; */
+				if (K == 1) {
+					CLEAR_A();
+					break;
+				}
 				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
 				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
 				EMIT2(0xf7, 0xf1);	/* div %ecx */
 				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
 				break;
-			case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
-				EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */
-				EMIT(K, 4);
-				EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */
+			case BPF_S_ALU_DIV_K: /* A /= K */
+				if (K == 1)
+					break;
+				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
+				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
+				EMIT2(0xf7, 0xf1);	/* div %ecx */
 				break;
 			case BPF_S_ALU_AND_X:
 				seen |= SEEN_XREG;
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 2ada505067c..eb5d7a56f8d 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->wall_time_snsec;
@@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->monotonic_time_sec;
 		ns = gtod->monotonic_time_snsec;
@@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
@@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));