Linux 3.14.1

commit 8ceee72808 upstream.

The GHASH setkey() function uses SSE registers but fails to call
kernel_fpu_begin()/kernel_fpu_end(). Instead of adding these calls, and
then having to deal with the restriction that they cannot be called from
interrupt context, move the setkey() implementation to the C domain.

Note that setkey() does not use any particular SSE features and is not
expected to become a performance bottleneck.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Fixes: 0e1227d356 (crypto: ghash - Add PCLMULQDQ accelerated implementation)
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 14
-SUBLEVEL = 0
+SUBLEVEL = 1
 EXTRAVERSION =
 NAME = Shuffling Zombie Juror
 

arch/arc/boot/dts/nsimosci.dts

@@ -11,13 +11,16 @@
 
 / {
 	compatible = "snps,nsimosci";
-	clock-frequency = <80000000>;	/* 80 MHZ */
+	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&intc>;
 
 	chosen {
-		bootargs = "console=tty0 consoleblank=0";
+		/* this is for console on PGU */
+		/* bootargs = "console=tty0 consoleblank=0"; */
+		/* this is for console on serial */
+		bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=ttyS0,115200n8 consoleblank=0 debug";
 	};
 
 	aliases {
@@ -44,15 +47,14 @@
 		};
 
 		uart0: serial@c0000000 {
-			compatible = "snps,dw-apb-uart";
+			compatible = "ns8250";
 			reg = <0xc0000000 0x2000>;
 			interrupts = <11>;
-			#clock-frequency = <80000000>;
 			clock-frequency = <3686400>;
 			baud = <115200>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
-			status = "okay";
+			no-loopback-test = <1>;
 		};
 
 		pgu0: pgu@c9000000 {

arch/arc/configs/nsimosci_defconfig

@@ -54,6 +54,7 @@ CONFIG_SERIO_ARC_PS2=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set

arch/m68k/Kconfig

@@ -17,6 +17,7 @@ config M68K
 	select FPU if MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
+	select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_REL
 	select MODULES_USE_ELF_RELA

arch/s390/Kconfig

@@ -117,6 +117,7 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4

arch/x86/crypto/ghash-clmulni-intel_asm.S

@@ -24,10 +24,6 @@
 .align 16
 .Lbswap_mask:
 	.octa 0x000102030405060708090a0b0c0d0e0f
-.Lpoly:
-	.octa 0xc2000000000000000000000000000001
-.Ltwo_one:
-	.octa 0x00000001000000000000000000000001
 
 #define DATA	%xmm0
 #define SHASH	%xmm1
@@ -134,28 +130,3 @@ ENTRY(clmul_ghash_update)
 .Lupdate_just_ret:
 	ret
 ENDPROC(clmul_ghash_update)
-
-/*
- * void clmul_ghash_setkey(be128 *shash, const u8 *key);
- *
- * Calculate hash_key << 1 mod poly
- */
-ENTRY(clmul_ghash_setkey)
-	movaps .Lbswap_mask, BSWAP
-	movups (%rsi), %xmm0
-	PSHUFB_XMM BSWAP %xmm0
-	movaps %xmm0, %xmm1
-	psllq $1, %xmm0
-	psrlq $63, %xmm1
-	movaps %xmm1, %xmm2
-	pslldq $8, %xmm1
-	psrldq $8, %xmm2
-	por %xmm1, %xmm0
-	# reduction
-	pshufd $0b00100100, %xmm2, %xmm1
-	pcmpeqd .Ltwo_one, %xmm1
-	pand .Lpoly, %xmm1
-	pxor %xmm1, %xmm0
-	movups %xmm0, (%rdi)
-	ret
-ENDPROC(clmul_ghash_setkey)

arch/x86/crypto/ghash-clmulni-intel_glue.c

@@ -30,8 +30,6 @@ void clmul_ghash_mul(char *dst, const be128 *shash);
 void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
 			const be128 *shash);
 
-void clmul_ghash_setkey(be128 *shash, const u8 *key);
-
 struct ghash_async_ctx {
 	struct cryptd_ahash *cryptd_tfm;
 };
@@ -58,13 +56,23 @@ static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
 	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	be128 *x = (be128 *)key;
+	u64 a, b;
 
 	if (keylen != GHASH_BLOCK_SIZE) {
 		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
-	clmul_ghash_setkey(&ctx->shash, key);
+	/* perform multiplication by 'x' in GF(2^128) */
+	a = be64_to_cpu(x->a);
+	b = be64_to_cpu(x->b);
+
+	ctx->shash.a = (__be64)((b << 1) | (a >> 63));
+	ctx->shash.b = (__be64)((a << 1) | (b >> 63));
+
+	if (a >> 63)
+		ctx->shash.b ^= cpu_to_be64(0xc2);
 
 	return 0;
 }

arch/x86/include/asm/efi.h

@@ -130,7 +130,8 @@ extern void efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
 extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
-extern void efi_setup_page_tables(void);
+extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
+extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init old_map_region(efi_memory_desc_t *md);
 extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_mkexec(void);

arch/x86/include/asm/pgtable_types.h

@@ -385,6 +385,8 @@ extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags);
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+			       unsigned numpages);
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */

arch/x86/mm/pageattr.c

@@ -692,6 +692,18 @@ static bool try_to_free_pmd_page(pmd_t *pmd)
 	return true;
 }
 
+static bool try_to_free_pud_page(pud_t *pud)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		if (!pud_none(pud[i]))
+			return false;
+
+	free_page((unsigned long)pud);
+	return true;
+}
+
 static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
 {
 	pte_t *pte = pte_offset_kernel(pmd, start);
@@ -805,6 +817,16 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 	 */
 }
 
+static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
+{
+	pgd_t *pgd_entry = root + pgd_index(addr);
+
+	unmap_pud_range(pgd_entry, addr, end);
+
+	if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
+		pgd_clear(pgd_entry);
+}
+
 static int alloc_pte_page(pmd_t *pmd)
 {
 	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
@@ -999,9 +1021,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 {
 	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
-	bool allocd_pgd = false;
-	pgd_t *pgd_entry;
 	pud_t *pud = NULL;	/* shut up gcc */
+	pgd_t *pgd_entry;
 	int ret;
 
 	pgd_entry = cpa->pgd + pgd_index(addr);
@@ -1015,7 +1036,6 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 			return -1;
 
 		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
-		allocd_pgd = true;
 	}
 
 	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
@@ -1023,19 +1043,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 
 	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
 	if (ret < 0) {
-		unmap_pud_range(pgd_entry, addr,
+		unmap_pgd_range(cpa->pgd, addr,
 				addr + (cpa->numpages << PAGE_SHIFT));
-
-		if (allocd_pgd) {
-			/*
-			 * If I allocated this PUD page, I can just as well
-			 * free it in this error path.
-			 */
-			pgd_clear(pgd_entry);
-			free_page((unsigned long)pud);
-		}
 		return ret;
 	}
+
 	cpa->numpages = ret;
 	return 0;
 }
@@ -1861,6 +1873,12 @@ out:
 	return retval;
 }
 
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+			       unsigned numpages)
+{
+	unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.

arch/x86/platform/efi/efi.c

@@ -939,14 +939,36 @@ static void __init efi_map_regions_fixed(void)
 
 }
 
-/*
- * Map efi memory ranges for runtime serivce and update new_memmap with virtual
- * addresses.
- */
-static void * __init efi_map_regions(int *count)
+static void *realloc_pages(void *old_memmap, int old_shift)
 {
+	void *ret;
+
+	ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1);
+	if (!ret)
+		goto out;
+
+	/*
+	 * A first-time allocation doesn't have anything to copy.
+	 */
+	if (!old_memmap)
+		return ret;
+
+	memcpy(ret, old_memmap, PAGE_SIZE << old_shift);
+
+out:
+	free_pages((unsigned long)old_memmap, old_shift);
+	return ret;
+}
+
+/*
+ * Map the efi memory ranges of the runtime services and update new_mmap with
+ * virtual addresses.
+ */
+static void * __init efi_map_regions(int *count, int *pg_shift)
+{
+	void *p, *new_memmap = NULL;
+	unsigned long left = 0;
 	efi_memory_desc_t *md;
-	void *p, *tmp, *new_memmap = NULL;
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
@@ -961,20 +983,23 @@ static void * __init efi_map_regions(int *count)
 		efi_map_region(md);
 		get_systab_virt_addr(md);
 
-		tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
-			       GFP_KERNEL);
-		if (!tmp)
-			goto out;
-		new_memmap = tmp;
+		if (left < memmap.desc_size) {
+			new_memmap = realloc_pages(new_memmap, *pg_shift);
+			if (!new_memmap)
+				return NULL;
+
+			left += PAGE_SIZE << *pg_shift;
+			(*pg_shift)++;
+		}
+
 		memcpy(new_memmap + (*count * memmap.desc_size), md,
 		       memmap.desc_size);
+
+		left -= memmap.desc_size;
 		(*count)++;
 	}
 
 	return new_memmap;
-out:
-	kfree(new_memmap);
-	return NULL;
 }
 
 /*
@@ -1000,9 +1025,9 @@ out:
  */
 void __init efi_enter_virtual_mode(void)
 {
-	efi_status_t status;
+	int err, count = 0, pg_shift = 0;
 	void *new_memmap = NULL;
-	int err, count = 0;
+	efi_status_t status;
 
 	efi.systab = NULL;
 
@@ -1019,20 +1044,24 @@ void __init efi_enter_virtual_mode(void)
 		efi_map_regions_fixed();
 	} else {
 		efi_merge_regions();
-		new_memmap = efi_map_regions(&count);
+		new_memmap = efi_map_regions(&count, &pg_shift);
 		if (!new_memmap) {
 			pr_err("Error reallocating memory, EFI runtime non-functional!\n");
 			return;
 		}
-	}
 
-	err = save_runtime_map();
-	if (err)
-		pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+		err = save_runtime_map();
+		if (err)
+			pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+	}
 
 	BUG_ON(!efi.systab);
 
-	efi_setup_page_tables();
+	if (!efi_setup) {
+		if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift))
+			return;
+	}
+
 	efi_sync_low_kernel_mappings();
 
 	if (!efi_setup) {
@@ -1072,7 +1101,35 @@ void __init efi_enter_virtual_mode(void)
 
 	efi_runtime_mkexec();
 
-	kfree(new_memmap);
+
+	/*
+	 * We mapped the descriptor array into the EFI pagetable above but we're
+	 * not unmapping it here. Here's why:
+	 *
+	 * We're copying select PGDs from the kernel page table to the EFI page
+	 * table and when we do so and make changes to those PGDs like unmapping
+	 * stuff from them, those changes appear in the kernel page table and we
+	 * go boom.
+	 *
+	 * From setup_real_mode():
+	 *
+	 * ...
+	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
+	 *
+	 * In this particular case, our allocation is in PGD 0 of the EFI page
+	 * table but we've copied that PGD from PGD[272] of the EFI page table:
+	 *
+	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
+	 *
+	 * where the direct memory mapping in kernel space is.
+	 *
+	 * new_memmap's VA comes from that direct mapping and thus clearing it,
+	 * it would get cleared in the kernel page table too.
+	 *
+	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
+	 */
+	if (!efi_setup)
+		free_pages((unsigned long)new_memmap, pg_shift);
 
 	/* clean DUMMY object */
 	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,

arch/x86/platform/efi/efi_32.c

@@ -40,7 +40,12 @@
 static unsigned long efi_rt_eflags;
 
 void efi_sync_low_kernel_mappings(void) {}
-void efi_setup_page_tables(void) {}
+void __init efi_dump_pagetable(void) {}
+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	return 0;
+}
+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {}
 
 void __init efi_map_region(efi_memory_desc_t *md)
 {

arch/x86/platform/efi/efi_64.c

@@ -137,12 +137,38 @@ void efi_sync_low_kernel_mappings(void)
 		sizeof(pgd_t) * num_pgds);
 }
 
-void efi_setup_page_tables(void)
+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+	pgd_t *pgd;
 
-	if (!efi_enabled(EFI_OLD_MEMMAP))
-		efi_scratch.use_pgd = true;
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return 0;
+
+	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+	pgd = __va(efi_scratch.efi_pgt);
+
+	/*
+	 * It can happen that the physical address of new_memmap lands in memory
+	 * which is not mapped in the EFI page table. Therefore we need to go
+	 * and ident-map those pages containing the map before calling
+	 * phys_efi_set_virtual_address_map().
+	 */
+	if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
+		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
+		return 1;
+	}
+
+	efi_scratch.use_pgd = true;
+
+
+	return 0;
+}
+
+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
 }
 
 static void __init __map_region(efi_memory_desc_t *md, u64 va)

drivers/isdn/isdnloop/isdnloop.c

@@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[] =
 static void
 isdnloop_fake_err(isdnloop_card *card)
 {
-	char buf[60];
+	char buf[64];
 
-	sprintf(buf, "E%s", card->omsg);
+	snprintf(buf, sizeof(buf), "E%s", card->omsg);
 	isdnloop_fake(card, buf, -1);
 	isdnloop_fake(card, "NAK", -1);
 }
@@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card *card)
 	case 7:
 		/* 0x;EAZ */
 		p += 3;
+		if (strlen(p) >= sizeof(card->eazlist[0]))
+			break;
 		strcpy(card->eazlist[ch - 1], p);
 		break;
 	case 8:
@@ -1070,6 +1072,12 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
 		return -EBUSY;
 	if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
 		return -EFAULT;
+
+	for (i = 0; i < 3; i++) {
+		if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
+			return -EINVAL;
+	}
+
 	spin_lock_irqsave(&card->isdnloop_lock, flags);
 	switch (sdef.ptype) {
 	case ISDN_PTYPE_EURO:
@@ -1127,7 +1135,7 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 {
 	ulong a;
 	int i;
-	char cbuf[60];
+	char cbuf[80];
 	isdn_ctrl cmd;
 	isdnloop_cdef cdef;
 
@@ -1192,7 +1200,6 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			break;
 		if ((c->arg & 255) < ISDNLOOP_BCH) {
 			char *p;
-			char dial[50];
 			char dcode[4];
 
 			a = c->arg;
@@ -1204,10 +1211,10 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			} else
 				/* Normal Dial */
 				strcpy(dcode, "CAL");
-			strcpy(dial, p);
-			sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
-				dcode, dial, c->parm.setup.si1,
-				c->parm.setup.si2, c->parm.setup.eazmsn);
+			snprintf(cbuf, sizeof(cbuf),
+				 "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
+				 dcode, p, c->parm.setup.si1,
+				 c->parm.setup.si2, c->parm.setup.eazmsn);
 			i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
 		}
 		break;

drivers/net/ethernet/cadence/at91_ether.c

@@ -342,6 +342,9 @@ static int __init at91ether_probe(struct platform_device *pdev)
 	}
 	clk_enable(lp->pclk);
 
+	lp->hclk = ERR_PTR(-ENOENT);
+	lp->tx_clk = ERR_PTR(-ENOENT);
+
 	/* Install the interrupt handler */
 	dev->irq = platform_get_irq(pdev, 0);
 	res = devm_request_irq(&pdev->dev, dev->irq, at91ether_interrupt, 0, dev->name, dev);

drivers/net/ethernet/sfc/ef10.c

@@ -565,10 +565,17 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx)
 	 * several of each (in fact that's the only option if host
 	 * page size is >4K).  So we may allocate some extra VIs just
 	 * for writing PIO buffers through.
+	 *
+	 * The UC mapping contains (min_vis - 1) complete VIs and the
+	 * first half of the next VI.  Then the WC mapping begins with
+	 * the second half of this last VI.
 	 */
 	uc_mem_map_size = PAGE_ALIGN((min_vis - 1) * EFX_VI_PAGE_SIZE +
 				     ER_DZ_TX_PIOBUF);
 	if (nic_data->n_piobufs) {
+		/* pio_write_vi_base rounds down to give the number of complete
+		 * VIs inside the UC mapping.
+		 */
 		pio_write_vi_base = uc_mem_map_size / EFX_VI_PAGE_SIZE;
 		wc_mem_map_size = (PAGE_ALIGN((pio_write_vi_base +
 					       nic_data->n_piobufs) *

drivers/net/ethernet/sfc/efx.c

@@ -1603,6 +1603,8 @@ static int efx_probe_nic(struct efx_nic *efx)
 	if (rc)
 		goto fail1;
 
+	efx_set_channels(efx);
+
 	rc = efx->type->dimension_resources(efx);
 	if (rc)
 		goto fail2;
@@ -1613,7 +1615,6 @@ static int efx_probe_nic(struct efx_nic *efx)
 		efx->rx_indir_table[i] =
 			ethtool_rxfh_indir_default(i, efx->rss_spread);
 
-	efx_set_channels(efx);
 	netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
 	netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels);
 

drivers/net/vxlan.c

@@ -871,6 +871,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	if (err)
 		return err;
 
+	if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
+		return -EAFNOSUPPORT;
+
 	spin_lock_bh(&vxlan->hash_lock);
 	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, vni, ifindex, ndm->ndm_flags);
@@ -2612,9 +2615,10 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
 	dst->remote_vni = vni;
 
+	/* Unless IPv6 is explicitly requested, assume IPv4 */
+	dst->remote_ip.sa.sa_family = AF_INET;
 	if (data[IFLA_VXLAN_GROUP]) {
 		dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
-		dst->remote_ip.sa.sa_family = AF_INET;
 	} else if (data[IFLA_VXLAN_GROUP6]) {
 		if (!IS_ENABLED(CONFIG_IPV6))
 			return -EPFNOSUPPORT;

drivers/net/wireless/iwlwifi/mvm/rs.c

@@ -211,9 +211,9 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.next_columns = {
 			RS_COLUMN_LEGACY_ANT_B,
 			RS_COLUMN_SISO_ANT_A,
+			RS_COLUMN_SISO_ANT_B,
 			RS_COLUMN_MIMO2,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_MIMO2_SGI,
 		},
 	},
 	[RS_COLUMN_LEGACY_ANT_B] = {
@@ -221,10 +221,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.ant = ANT_B,
 		.next_columns = {
 			RS_COLUMN_LEGACY_ANT_A,
+			RS_COLUMN_SISO_ANT_A,
 			RS_COLUMN_SISO_ANT_B,
 			RS_COLUMN_MIMO2,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_MIMO2_SGI,
 		},
 	},
 	[RS_COLUMN_SISO_ANT_A] = {
@@ -234,8 +234,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_B,
 			RS_COLUMN_MIMO2,
 			RS_COLUMN_SISO_ANT_A_SGI,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_SISO_ANT_B_SGI,
+			RS_COLUMN_MIMO2_SGI,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -248,8 +248,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_A,
 			RS_COLUMN_MIMO2,
 			RS_COLUMN_SISO_ANT_B_SGI,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_SISO_ANT_A_SGI,
+			RS_COLUMN_MIMO2_SGI,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -263,8 +263,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_B_SGI,
 			RS_COLUMN_MIMO2_SGI,
 			RS_COLUMN_SISO_ANT_A,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_SISO_ANT_B,
+			RS_COLUMN_MIMO2,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -279,8 +279,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_A_SGI,
 			RS_COLUMN_MIMO2_SGI,
 			RS_COLUMN_SISO_ANT_B,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_SISO_ANT_A,
+			RS_COLUMN_MIMO2,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -292,10 +292,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.ant = ANT_AB,
 		.next_columns = {
 			RS_COLUMN_SISO_ANT_A,
+			RS_COLUMN_SISO_ANT_B,
+			RS_COLUMN_SISO_ANT_A_SGI,
+			RS_COLUMN_SISO_ANT_B_SGI,
 			RS_COLUMN_MIMO2_SGI,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
 		},
 		.checks = {
 			rs_mimo_allow,
@@ -307,10 +307,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.sgi = true,
 		.next_columns = {
 			RS_COLUMN_SISO_ANT_A_SGI,
+			RS_COLUMN_SISO_ANT_B_SGI,
+			RS_COLUMN_SISO_ANT_A,
+			RS_COLUMN_SISO_ANT_B,
 			RS_COLUMN_MIMO2,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
 		},
 		.checks = {
 			rs_mimo_allow,

drivers/net/xen-netback/common.h

@@ -113,6 +113,11 @@ struct xenvif {
 	domid_t          domid;
 	unsigned int     handle;
 
+	/* Is this interface disabled? True when backend discovers
+	 * frontend is rogue.
+	 */
+	bool disabled;
+
 	/* Use NAPI for guest TX */
 	struct napi_struct napi;
 	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */

drivers/net/xen-netback/interface.c

@@ -62,6 +62,15 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
 	struct xenvif *vif = container_of(napi, struct xenvif, napi);
 	int work_done;
 
+	/* This vif is rogue, we pretend we've there is nothing to do
+	 * for this vif to deschedule it from NAPI. But this interface
+	 * will be turned off in thread context later.
+	 */
+	if (unlikely(vif->disabled)) {
+		napi_complete(napi);
+		return 0;
+	}
+
 	work_done = xenvif_tx_action(vif, budget);
 
 	if (work_done < budget) {
@@ -321,6 +330,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->ip_csum = 1;
 	vif->dev = dev;
 
+	vif->disabled = false;
+
 	vif->credit_bytes = vif->remaining_credit = ~0UL;
 	vif->credit_usec  = 0UL;
 	init_timer(&vif->credit_timeout);

drivers/net/xen-netback/netback.c

@@ -192,8 +192,8 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 * into multiple copies tend to give large frags their
 	 * own buffers as before.
 	 */
-	if ((offset + size > MAX_BUFFER_OFFSET) &&
-	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+	BUG_ON(size > MAX_BUFFER_OFFSET);
+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
 		return true;
 
 	return false;
@@ -482,6 +482,8 @@ static void xenvif_rx_action(struct xenvif *vif)
 
 	while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
 		RING_IDX max_slots_needed;
+		RING_IDX old_req_cons;
+		RING_IDX ring_slots_used;
 		int i;
 
 		/* We need a cheap worse case estimate for the number of
@@ -493,9 +495,28 @@ static void xenvif_rx_action(struct xenvif *vif)
 						PAGE_SIZE);
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 			unsigned int size;
+			unsigned int offset;
+
 			size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
-			max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE);
+			offset = skb_shinfo(skb)->frags[i].page_offset;
+
+			/* For a worse-case estimate we need to factor in
+			 * the fragment page offset as this will affect the
+			 * number of times xenvif_gop_frag_copy() will
+			 * call start_new_rx_buffer().
+			 */
+			max_slots_needed += DIV_ROUND_UP(offset + size,
+							 PAGE_SIZE);
 		}
+
+		/* To avoid the estimate becoming too pessimal for some
+		 * frontends that limit posted rx requests, cap the estimate
+		 * at MAX_SKB_FRAGS.
+		 */
+		if (max_slots_needed > MAX_SKB_FRAGS)
+			max_slots_needed = MAX_SKB_FRAGS;
+
+		/* We may need one more slot for GSO metadata */
 		if (skb_is_gso(skb) &&
 		   (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
 		    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
@@ -511,8 +532,12 @@ static void xenvif_rx_action(struct xenvif *vif)
 			vif->rx_last_skb_slots = 0;
 
 		sco = (struct skb_cb_overlay *)skb->cb;
+
+		old_req_cons = vif->rx.req_cons;
 		sco->meta_slots_used = xenvif_gop_skb(skb, &npo);
-		BUG_ON(sco->meta_slots_used > max_slots_needed);
+		ring_slots_used = vif->rx.req_cons - old_req_cons;
+
+		BUG_ON(ring_slots_used > max_slots_needed);
 
 		__skb_queue_tail(&rxq, skb);
 	}
@@ -655,7 +680,8 @@ static void xenvif_tx_err(struct xenvif *vif,
 static void xenvif_fatal_tx_err(struct xenvif *vif)
 {
 	netdev_err(vif->dev, "fatal error; disabling device\n");
-	xenvif_carrier_off(vif);
+	vif->disabled = true;
+	xenvif_kick_thread(vif);
 }
 
 static int xenvif_count_requests(struct xenvif *vif,
@@ -1126,7 +1152,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
 				   vif->tx.sring->req_prod, vif->tx.req_cons,
 				   XEN_NETIF_TX_RING_SIZE);
 			xenvif_fatal_tx_err(vif);
-			continue;
+			break;
 		}
 
 		work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx);
@@ -1548,7 +1574,18 @@ int xenvif_kthread(void *data)
 	while (!kthread_should_stop()) {
 		wait_event_interruptible(vif->wq,
 					 rx_work_todo(vif) ||
+					 vif->disabled ||
 					 kthread_should_stop());
+
+		/* This frontend is found to be rogue, disable it in
+		 * kthread context. Currently this is only set when
+		 * netback finds out frontend sends malformed packet,
+		 * but we cannot disable the interface in softirq
+		 * context so we defer it here.
+		 */
+		if (unlikely(vif->disabled && netif_carrier_ok(vif->dev)))
+			xenvif_carrier_off(vif);
+
 		if (kthread_should_stop())
 			break;
 

include/linux/futex.h

@@ -55,7 +55,11 @@ union futex_key {
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
 extern void exit_pi_state_list(struct task_struct *curr);
+#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
+#define futex_cmpxchg_enabled 1
+#else
 extern int futex_cmpxchg_enabled;
+#endif
 #else
 static inline void exit_robust_list(struct task_struct *curr)
 {

init/Kconfig

@@ -1387,6 +1387,13 @@ config FUTEX
 	  support for "fast userspace mutexes".  The resulting kernel may not
 	  run glibc-based applications correctly.
 
+config HAVE_FUTEX_CMPXCHG
+	bool
+	help
+	  Architectures should select this if futex_atomic_cmpxchg_inatomic()
+	  is implemented and always working. This removes a couple of runtime
+	  checks.
+
 config EPOLL
 	bool "Enable eventpoll support" if EXPERT
 	default y

kernel/futex.c

@@ -157,7 +157,9 @@
  * enqueue.
  */
 
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
 int __read_mostly futex_cmpxchg_enabled;
+#endif
 
 /*
  * Futex flags used to encode options to functions and preserve them across
@@ -1450,6 +1452,7 @@ retry:
 	hb2 = hash_futex(&key2);
 
 retry_private:
+	hb_waiters_inc(hb2);
 	double_lock_hb(hb1, hb2);
 
 	if (likely(cmpval != NULL)) {
@@ -1459,6 +1462,7 @@ retry_private:
 
 		if (unlikely(ret)) {
 			double_unlock_hb(hb1, hb2);
+			hb_waiters_dec(hb2);
 
 			ret = get_user(curval, uaddr1);
 			if (ret)
@@ -1508,6 +1512,7 @@ retry_private:
 			break;
 		case -EFAULT:
 			double_unlock_hb(hb1, hb2);
+			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
 			ret = fault_in_user_writeable(uaddr2);
@@ -1517,6 +1522,7 @@ retry_private:
 		case -EAGAIN:
 			/* The owner was exiting, try again. */
 			double_unlock_hb(hb1, hb2);
+			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
 			cond_resched();
@@ -1592,6 +1598,7 @@ retry_private:
 
 out_unlock:
 	double_unlock_hb(hb1, hb2);
+	hb_waiters_dec(hb2);
 
 	/*
 	 * drop_futex_key_refs() must be called outside the spinlocks. During
@@ -2875,9 +2882,28 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
 }
 
+static void __init futex_detect_cmpxchg(void)
+{
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
+	u32 curval;
+
+	/*
+	 * This will fail and we want it. Some arch implementations do
+	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
+	 * functionality. We want to know that before we call in any
+	 * of the complex code paths. Also we want to prevent
+	 * registration of robust lists in that case. NULL is
+	 * guaranteed to fault and we get -EFAULT on functional
+	 * implementation, the non-functional ones will return
+	 * -ENOSYS.
+	 */
+	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
+		futex_cmpxchg_enabled = 1;
+#endif
+}
+
 static int __init futex_init(void)
 {
-	u32 curval;
 	unsigned int futex_shift;
 	unsigned long i;
 
@@ -2893,18 +2919,8 @@ static int __init futex_init(void)
 					       &futex_shift, NULL,
 					       futex_hashsize, futex_hashsize);
 	futex_hashsize = 1UL << futex_shift;
-	/*
-	 * This will fail and we want it. Some arch implementations do
-	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
-	 * functionality. We want to know that before we call in any
-	 * of the complex code paths. Also we want to prevent
-	 * registration of robust lists in that case. NULL is
-	 * guaranteed to fault and we get -EFAULT on functional
-	 * implementation, the non-functional ones will return
-	 * -ENOSYS.
-	 */
-	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
-		futex_cmpxchg_enabled = 1;
+
+	futex_detect_cmpxchg();
 
 	for (i = 0; i < futex_hashsize; i++) {
 		atomic_set(&futex_queues[i].waiters, 0);

lib/nlattr.c

@@ -303,9 +303,15 @@ int nla_memcmp(const struct nlattr *nla, const void *data,
  */
 int nla_strcmp(const struct nlattr *nla, const char *str)
 {
-	int len = strlen(str) + 1;
-	int d = nla_len(nla) - len;
+	int len = strlen(str);
+	char *buf = nla_data(nla);
+	int attrlen = nla_len(nla);
+	int d;
 
+	if (attrlen > 0 && buf[attrlen - 1] == '\0')
+		attrlen--;
+
+	d = attrlen - len;
 	if (d == 0)
 		d = memcmp(nla_data(nla), str, len);
 

net/ipv6/icmp.c

@@ -520,7 +520,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 			      np->tclass, NULL, &fl6, (struct rt6_info *)dst,
 			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,

net/ipv6/ip6_output.c

@@ -1566,8 +1566,8 @@ int ip6_push_pending_frames(struct sock *sk)
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
 	err = ip6_local_out(skb);

net/ipv6/mcast.c

@@ -1620,11 +1620,12 @@ static void mld_sendpack(struct sk_buff *skb)
 		      dst_output);
 out:
 	if (!err) {
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
-	} else
-		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
+		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+	} else {
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+	}
 
 	rcu_read_unlock();
 	return;

net/ipv6/ping.c

@@ -182,8 +182,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			      MSG_DONTWAIT, np->dontfrag);
 
 	if (err) {
-		ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
-				   ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev,
+				ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6,

net/rds/iw.c

@@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support IB devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_RNIC)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",

security/selinux/hooks.c

@@ -1418,15 +1418,33 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 		isec->sid = sbsec->sid;
 
 		if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
-			if (opt_dentry) {
-				isec->sclass = inode_mode_to_security_class(inode->i_mode);
-				rc = selinux_proc_get_sid(opt_dentry,
-							  isec->sclass,
-							  &sid);
-				if (rc)
-					goto out_unlock;
-				isec->sid = sid;
-			}
+			/* We must have a dentry to determine the label on
+			 * procfs inodes */
+			if (opt_dentry)
+				/* Called from d_instantiate or
+				 * d_splice_alias. */
+				dentry = dget(opt_dentry);
+			else
+				/* Called from selinux_complete_init, try to
+				 * find a dentry. */
+				dentry = d_find_alias(inode);
+			/*
+			 * This can be hit on boot when a file is accessed
+			 * before the policy is loaded.  When we load policy we
+			 * may find inodes that have no dentry on the
+			 * sbsec->isec_head list.  No reason to complain as
+			 * these will get fixed up the next time we go through
+			 * inode_doinit() with a dentry, before these inodes
+			 * could be used again by userspace.
+			 */
+			if (!dentry)
+				goto out_unlock;
+			isec->sclass = inode_mode_to_security_class(inode->i_mode);
+			rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
+			dput(dentry);
+			if (rc)
+				goto out_unlock;
+			isec->sid = sid;
 		}
 		break;
 	}

sound/pci/hda/hda_intel.c

@@ -297,9 +297,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define ULI_NUM_CAPTURE		5
 #define ULI_NUM_PLAYBACK	6
 
-/* ATI HDMI may have up to 8 playbacks and 0 capture */
+/* ATI HDMI has 1 playback and 0 capture */
 #define ATIHDMI_NUM_CAPTURE	0
-#define ATIHDMI_NUM_PLAYBACK	8
+#define ATIHDMI_NUM_PLAYBACK	1
 
 /* TERA has 4 playback and 3 capture */
 #define TERA_NUM_CAPTURE	3