diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 363e348..6c72381 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2438,7 +2438,7 @@
 			real-time workloads.  It can also improve energy
 			efficiency for asymmetric multiprocessors.
 
-	rcu_nocbs_poll	[KNL,BOOT]
+	rcu_nocb_poll	[KNL,BOOT]
 			Rather than requiring that offloaded CPUs
 			(specified by rcu_nocbs= above) explicitly
 			awaken the corresponding "rcuoN" kthreads,
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 5658508..7443481 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -115,11 +115,13 @@
 	sldi	r29,r5,SID_SHIFT - VPN_SHIFT
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
-
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-12,48		/* (ea >> 12) & 0xffff */
-	xor	r28,r5,r0
+	/*
+	 * Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
+	 */
+	rldicl	r0,r3,64-12,48
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
@@ -130,11 +132,12 @@
 	/*
 	 * calculate hash value for primary slot and
 	 * store it in r28 for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-12,36		/* (ea >> 12) & 0xfffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 =  (va >> 12) & ((1ul << (40 - 12)) -1) */
+	rldicl	r0,r3,64-12,36
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -407,11 +410,13 @@
 	 */
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
-
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-12,48		/* (ea >> 12) & 0xffff */
-	xor	r28,r5,r0
+	/*
+	 * Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
+	 */
+	rldicl	r0,r3,64-12,48
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
@@ -426,11 +431,12 @@
 	/*
 	 * Calculate hash value for primary slot and
 	 * store it in r28  for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-12,36		/* (ea >> 12) & 0xfffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */
+	rldicl	r0,r3,64-12,36
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -752,25 +758,27 @@
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
 
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-16,52		/* (ea >> 16) & 0xfff */
-	xor	r28,r5,r0
+	/* Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 16) & ((1ul << (28 - 16)) -1)
+	 */
+	rldicl	r0,r3,64-16,52
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
 	sldi	r29,r5,SID_SHIFT_1T - VPN_SHIFT
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
 	or	r29,r28,r29
-
 	/*
 	 * calculate hash value for primary slot and
 	 * store it in r28 for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-16,40		/* (ea >> 16) & 0xffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 = (va >> 16) & ((1ul << (40 - 16)) -1) */
+	rldicl	r0,r3,64-16,40
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 93b9e11..4914e94 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2019,7 +2019,10 @@
 		break;
 
 	case 28: /* Atom */
-	case 54: /* Cedariew */
+	case 38: /* Lincroft */
+	case 39: /* Penwell */
+	case 53: /* Cloverview */
+	case 54: /* Cedarview */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -2084,6 +2087,7 @@
 		pr_cont("SandyBridge events, ");
 		break;
 	case 58: /* IvyBridge */
+	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index f2af39f..4820c23 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -19,7 +19,7 @@
 
 };
 
-static __initconst u64 p6_hw_cache_event_ids
+static u64 p6_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
index cc2f8c1..872eb60 100644
--- a/arch/x86/tools/insn_sanity.c
+++ b/arch/x86/tools/insn_sanity.c
@@ -55,7 +55,7 @@
 static void usage(const char *err)
 {
 	if (err)
-		fprintf(stderr, "Error: %s\n\n", err);
+		fprintf(stderr, "%s: Error: %s\n\n", prog, err);
 	fprintf(stderr, "Usage: %s [-y|-n|-v] [-s seed[,no]] [-m max] [-i input]\n", prog);
 	fprintf(stderr, "\t-y	64bit mode\n");
 	fprintf(stderr, "\t-n	32bit mode\n");
@@ -269,7 +269,13 @@
 		insns++;
 	}
 
-	fprintf(stdout, "%s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n", (errors) ? "Failure" : "Success", insns, (input_file) ? "given" : "random", errors, seed);
+	fprintf(stdout, "%s: %s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n",
+		prog,
+		(errors) ? "Failure" : "Success",
+		insns,
+		(input_file) ? "given" : "random",
+		errors,
+		seed);
 
 	return errors ? 1 : 0;
 }
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 4d0e60a..a2d478e 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1313,14 +1313,18 @@
 				if (!(tmp & EVERGREEN_CRTC_BLANK_DATA_EN)) {
 					radeon_wait_for_vblank(rdev, i);
 					tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
 				if (!(tmp & EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE)) {
 					radeon_wait_for_vblank(rdev, i);
 					tmp |= EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE;
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			}
 			/* wait for the next frame */
@@ -1345,6 +1349,8 @@
 		blackout &= ~BLACKOUT_MODE_MASK;
 		WREG32(MC_SHARED_BLACKOUT_CNTL, blackout | 1);
 	}
+	/* wait for the MC to settle */
+	udelay(100);
 }
 
 void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save)
@@ -1378,11 +1384,15 @@
 			if (ASIC_IS_DCE6(rdev)) {
 				tmp = RREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i]);
 				tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 				WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
 				tmp &= ~EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE;
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 				WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp);
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 			}
 			/* wait for the next frame */
 			frame_count = radeon_get_vblank_counter(rdev, i);
@@ -2036,9 +2046,20 @@
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 	WREG32(DMA_TILING_CONFIG, gb_addr_config);
 
-	tmp = gb_addr_config & NUM_PIPES_MASK;
-	tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends,
-					EVERGREEN_MAX_BACKENDS, disabled_rb_mask);
+	if ((rdev->config.evergreen.max_backends == 1) &&
+	    (rdev->flags & RADEON_IS_IGP)) {
+		if ((disabled_rb_mask & 3) == 1) {
+			/* RB0 disabled, RB1 enabled */
+			tmp = 0x11111111;
+		} else {
+			/* RB1 disabled, RB0 enabled */
+			tmp = 0x00000000;
+		}
+	} else {
+		tmp = gb_addr_config & NUM_PIPES_MASK;
+		tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends,
+						EVERGREEN_MAX_BACKENDS, disabled_rb_mask);
+	}
 	WREG32(GB_BACKEND_MAP, tmp);
 
 	WREG32(CGTS_SYS_TCC_DISABLE, 0);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index bc2540b..becb03e 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1462,12 +1462,15 @@
 			      u32 disabled_rb_mask)
 {
 	u32 rendering_pipe_num, rb_num_width, req_rb_num;
-	u32 pipe_rb_ratio, pipe_rb_remain;
+	u32 pipe_rb_ratio, pipe_rb_remain, tmp;
 	u32 data = 0, mask = 1 << (max_rb_num - 1);
 	unsigned i, j;
 
 	/* mask out the RBs that don't exist on that asic */
-	disabled_rb_mask |= (0xff << max_rb_num) & 0xff;
+	tmp = disabled_rb_mask | ((0xff << max_rb_num) & 0xff);
+	/* make sure at least one RB is available */
+	if ((tmp & 0xff) != 0xff)
+		disabled_rb_mask = tmp;
 
 	rendering_pipe_num = 1 << tiling_pipe_num;
 	req_rb_num = total_max_rb_num - r600_count_pipe_bits(disabled_rb_mask);
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 9056faf..0b202c0 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1445,7 +1445,7 @@
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
@@ -1572,7 +1572,7 @@
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
@@ -1699,7 +1699,7 @@
 	.vm = {
 		.init = &si_vm_init,
 		.fini = &si_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &si_vm_set_page,
 	},
 	.ring = {
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 33a56a0..3e403bd 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -2470,6 +2470,14 @@
 								   1),
 								  ATOM_DEVICE_CRT1_SUPPORT);
 				}
+				/* RV100 board with external TDMS bit mis-set.
+				 * Actually uses internal TMDS, clear the bit.
+				 */
+				if (dev->pdev->device == 0x5159 &&
+				    dev->pdev->subsystem_vendor == 0x1014 &&
+				    dev->pdev->subsystem_device == 0x029A) {
+					tmp &= ~(1 << 4);
+				}
 				if ((tmp >> 4) & 0x1) {
 					devices |= ATOM_DEVICE_DFP2_SUPPORT;
 					radeon_add_legacy_encoder(dev,
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index ff3def7..05c96fa 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1115,8 +1115,10 @@
 	}
 
 	radeon_fb = kzalloc(sizeof(*radeon_fb), GFP_KERNEL);
-	if (radeon_fb == NULL)
+	if (radeon_fb == NULL) {
+		drm_gem_object_unreference_unlocked(obj);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	ret = radeon_framebuffer_init(dev, radeon_fb, mode_cmd, obj);
 	if (ret) {
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 2430d80..cd72062 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -377,6 +377,9 @@
 {
 	int r;
 
+	/* make sure we aren't trying to allocate more space than there is on the ring */
+	if (ndw > (ring->ring_size / 4))
+		return -ENOMEM;
 	/* Align requested size with padding so unlock_commit can
 	 * pad safely */
 	ndw = (ndw + ring->align_mask) & ~ring->align_mask;
diff --git a/drivers/gpu/drm/radeon/reg_srcs/cayman b/drivers/gpu/drm/radeon/reg_srcs/cayman
index 0f656b1..a072fa8 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/cayman
+++ b/drivers/gpu/drm/radeon/reg_srcs/cayman
@@ -1,5 +1,6 @@
 cayman 0x9400
 0x0000802C GRBM_GFX_INDEX
+0x00008040 WAIT_UNTIL
 0x000084FC CP_STRMOUT_CNTL
 0x000085F0 CP_COHER_CNTL
 0x000085F4 CP_COHER_SIZE
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 2bb6d0e..435ed35 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -336,6 +336,8 @@
 				WREG32(R600_CITF_CNTL, blackout);
 		}
 	}
+	/* wait for the MC to settle */
+	udelay(100);
 }
 
 void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save)
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 27f80cd..46dcb54 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -272,6 +272,7 @@
 	tristate "M-Systems Disk-On-Chip G3"
 	select BCH
 	select BCH_CONST_PARAMS
+	select BITREVERSE
 	---help---
 	  This provides an MTD device driver for the M-Systems DiskOnChip
 	  G3 devices.
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index 67cc73c..7901d72 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -170,7 +170,7 @@
 	resource_size_t res_size;
 	struct mtd_part_parser_data ppdata;
 	bool map_indirect;
-	const char *mtd_name;
+	const char *mtd_name = NULL;
 
 	match = of_match_device(of_flash_match, &dev->dev);
 	if (!match)
diff --git a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
index 86c9a79..595de40 100644
--- a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
+++ b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
@@ -17,8 +17,8 @@
 #include "bcm47xxnflash.h"
 
 /* Broadcom uses 1'000'000 but it seems to be too many. Tests on WNDR4500 has
- * shown 164 retries as maxiumum. */
-#define NFLASH_READY_RETRIES		1000
+ * shown ~1000 retries as maxiumum. */
+#define NFLASH_READY_RETRIES		10000
 
 #define NFLASH_SECTOR_SIZE		512
 
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 3502606..feae55c 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -523,7 +523,7 @@
 static const struct of_device_id davinci_nand_of_match[] = {
 	{.compatible = "ti,davinci-nand", },
 	{},
-}
+};
 MODULE_DEVICE_TABLE(of, davinci_nand_of_match);
 
 static struct davinci_nand_pdata
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 8323ac9..3766682 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2857,8 +2857,11 @@
 	int i;
 	int val;
 
-	/* ONFI need to be probed in 8 bits mode */
-	WARN_ON(chip->options & NAND_BUSWIDTH_16);
+	/* ONFI need to be probed in 8 bits mode, and 16 bits should be selected with NAND_BUSWIDTH_AUTO */
+	if (chip->options & NAND_BUSWIDTH_16) {
+		pr_err("Trying ONFI probe in 16 bits mode, aborting !\n");
+		return 0;
+	}
 	/* Try ONFI for unknown chip or LP */
 	chip->cmdfunc(mtd, NAND_CMD_READID, 0x20, -1);
 	if (chip->read_byte(mtd) != 'O' || chip->read_byte(mtd) != 'N' ||
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index e269510..f2aa754 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -941,6 +941,8 @@
 
 int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
 {
+	int block_size = dev->dev_attrib.block_size;
+
 	if (dev->export_count) {
 		pr_err("dev[%p]: Unable to change SE Device"
 			" fabric_max_sectors while export_count is %d\n",
@@ -978,8 +980,12 @@
 	/*
 	 * Align max_sectors down to PAGE_SIZE to follow transport_allocate_data_tasks()
 	 */
+	if (!block_size) {
+		block_size = 512;
+		pr_warn("Defaulting to 512 for zero block_size\n");
+	}
 	fabric_max_sectors = se_dev_align_max_sectors(fabric_max_sectors,
-						      dev->dev_attrib.block_size);
+						      block_size);
 
 	dev->dev_attrib.fabric_max_sectors = fabric_max_sectors;
 	pr_debug("dev[%p]: SE Device max_sectors changed to %u\n",
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 810263d..c57bbbc 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -754,6 +754,11 @@
 		return -EFAULT;
 	}
 
+	if (!(dev->dev_flags & DF_CONFIGURED)) {
+		pr_err("se_device not configured yet, cannot port link\n");
+		return -ENODEV;
+	}
+
 	tpg_ci = &lun_ci->ci_parent->ci_group->cg_item;
 	se_tpg = container_of(to_config_group(tpg_ci),
 				struct se_portal_group, tpg_group);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 26a6d18..a664c66 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -58,11 +58,10 @@
 	buf[7] = dev->dev_attrib.block_size & 0xff;
 
 	rbuf = transport_kmap_data_sg(cmd);
-	if (!rbuf)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-
-	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-	transport_kunmap_data_sg(cmd);
+	if (rbuf) {
+		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+		transport_kunmap_data_sg(cmd);
+	}
 
 	target_complete_cmd(cmd, GOOD);
 	return 0;
@@ -97,11 +96,10 @@
 		buf[14] = 0x80;
 
 	rbuf = transport_kmap_data_sg(cmd);
-	if (!rbuf)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-
-	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-	transport_kunmap_data_sg(cmd);
+	if (rbuf) {
+		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+		transport_kunmap_data_sg(cmd);
+	}
 
 	target_complete_cmd(cmd, GOOD);
 	return 0;
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 84f9e96..2d88f08 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -641,11 +641,10 @@
 
 out:
 	rbuf = transport_kmap_data_sg(cmd);
-	if (!rbuf)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-
-	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-	transport_kunmap_data_sg(cmd);
+	if (rbuf) {
+		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+		transport_kunmap_data_sg(cmd);
+	}
 
 	if (!ret)
 		target_complete_cmd(cmd, GOOD);
@@ -851,7 +850,7 @@
 {
 	struct se_device *dev = cmd->se_dev;
 	char *cdb = cmd->t_task_cdb;
-	unsigned char *buf, *map_buf;
+	unsigned char buf[SE_MODE_PAGE_BUF], *rbuf;
 	int type = dev->transport->get_device_type(dev);
 	int ten = (cmd->t_task_cdb[0] == MODE_SENSE_10);
 	bool dbd = !!(cdb[1] & 0x08);
@@ -863,26 +862,8 @@
 	int ret;
 	int i;
 
-	map_buf = transport_kmap_data_sg(cmd);
-	if (!map_buf)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	/*
-	 * If SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC is not set, then we
-	 * know we actually allocated a full page.  Otherwise, if the
-	 * data buffer is too small, allocate a temporary buffer so we
-	 * don't have to worry about overruns in all our INQUIRY
-	 * emulation handling.
-	 */
-	if (cmd->data_length < SE_MODE_PAGE_BUF &&
-	    (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC)) {
-		buf = kzalloc(SE_MODE_PAGE_BUF, GFP_KERNEL);
-		if (!buf) {
-			transport_kunmap_data_sg(cmd);
-			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		}
-	} else {
-		buf = map_buf;
-	}
+	memset(buf, 0, SE_MODE_PAGE_BUF);
+
 	/*
 	 * Skip over MODE DATA LENGTH + MEDIUM TYPE fields to byte 3 for
 	 * MODE_SENSE_10 and byte 2 for MODE_SENSE (6).
@@ -934,8 +915,6 @@
 	if (page == 0x3f) {
 		if (subpage != 0x00 && subpage != 0xff) {
 			pr_warn("MODE_SENSE: Invalid subpage code: 0x%02x\n", subpage);
-			kfree(buf);
-			transport_kunmap_data_sg(cmd);
 			return TCM_INVALID_CDB_FIELD;
 		}
 
@@ -972,7 +951,6 @@
 		pr_err("MODE SENSE: unimplemented page/subpage: 0x%02x/0x%02x\n",
 		       page, subpage);
 
-	transport_kunmap_data_sg(cmd);
 	return TCM_UNKNOWN_MODE_PAGE;
 
 set_length:
@@ -981,12 +959,12 @@
 	else
 		buf[0] = length - 1;
 
-	if (buf != map_buf) {
-		memcpy(map_buf, buf, cmd->data_length);
-		kfree(buf);
+	rbuf = transport_kmap_data_sg(cmd);
+	if (rbuf) {
+		memcpy(rbuf, buf, min_t(u32, SE_MODE_PAGE_BUF, cmd->data_length));
+		transport_kunmap_data_sg(cmd);
 	}
 
-	transport_kunmap_data_sg(cmd);
 	target_complete_cmd(cmd, GOOD);
 	return 0;
 }
diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c
index b20df5c..22321cf 100644
--- a/drivers/vhost/tcm_vhost.c
+++ b/drivers/vhost/tcm_vhost.c
@@ -575,10 +575,8 @@
 
 	/* Must use ioctl VHOST_SCSI_SET_ENDPOINT */
 	tv_tpg = vs->vs_tpg;
-	if (unlikely(!tv_tpg)) {
-		pr_err("%s endpoint not set\n", __func__);
+	if (unlikely(!tv_tpg))
 		return;
-	}
 
 	mutex_lock(&vq->mutex);
 	vhost_disable_notify(&vs->dev, vq);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 301079d..7b6646a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -908,6 +908,15 @@
 }
 
 /*
+ * Initialize event state based on the perf_event_attr::disabled.
+ */
+static inline void perf_event__state_init(struct perf_event *event)
+{
+	event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF :
+					      PERF_EVENT_STATE_INACTIVE;
+}
+
+/*
  * Called at perf_event creation and when events are attached/detached from a
  * group.
  */
@@ -6179,8 +6188,7 @@
 	event->overflow_handler	= overflow_handler;
 	event->overflow_handler_context = context;
 
-	if (attr->disabled)
-		event->state = PERF_EVENT_STATE_OFF;
+	perf_event__state_init(event);
 
 	pmu = NULL;
 
@@ -6609,9 +6617,17 @@
 
 		mutex_lock(&gctx->mutex);
 		perf_remove_from_context(group_leader);
+
+		/*
+		 * Removing from the context ends up with disabled
+		 * event. What we want here is event in the initial
+		 * startup state, ready to be add into new context.
+		 */
+		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
 			perf_remove_from_context(sibling);
+			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
 		mutex_unlock(&gctx->mutex);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index f6e5ec2..c1cc7e1 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -40,8 +40,7 @@
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
 static bool have_rcu_nocb_mask;	    /* Was rcu_nocb_mask allocated? */
-static bool rcu_nocb_poll;	    /* Offload kthread are to poll. */
-module_param(rcu_nocb_poll, bool, 0444);
+static bool __read_mostly rcu_nocb_poll;    /* Offload kthread are to poll. */
 static char __initdata nocb_buf[NR_CPUS * 5];
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
@@ -2159,6 +2158,13 @@
 }
 __setup("rcu_nocbs=", rcu_nocb_setup);
 
+static int __init parse_rcu_nocb_poll(char *arg)
+{
+	rcu_nocb_poll = 1;
+	return 0;
+}
+early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
+
 /* Is the specified CPU a no-CPUs CPU? */
 static bool is_nocb_cpu(int cpu)
 {
@@ -2366,10 +2372,11 @@
 	for (;;) {
 		/* If not polling, wait for next batch of callbacks. */
 		if (!rcu_nocb_poll)
-			wait_event(rdp->nocb_wq, rdp->nocb_head);
+			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
 		list = ACCESS_ONCE(rdp->nocb_head);
 		if (!list) {
 			schedule_timeout_interruptible(1);
+			flush_signals(current);
 			continue;
 		}
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2cd3c1b..7ae4c4c 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -222,8 +222,8 @@
 			cfs_rq->runnable_load_avg);
 	SEQ_printf(m, "  .%-30s: %lld\n", "blocked_load_avg",
 			cfs_rq->blocked_load_avg);
-	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
-			atomic64_read(&cfs_rq->tg->load_avg));
+	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_avg",
+			(unsigned long long)atomic64_read(&cfs_rq->tg->load_avg));
 	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_contrib",
 			cfs_rq->tg_load_contrib);
 	SEQ_printf(m, "  .%-30s: %d\n", "tg_runnable_contrib",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5eea870..81fa536 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2663,7 +2663,7 @@
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
-static void unthrottle_offline_cfs_rqs(struct rq *rq)
+static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
 	struct cfs_rq *cfs_rq;
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 418feb0..4f02b28 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -566,7 +566,7 @@
 static int do_balance_runtime(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
-	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+	struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd;
 	int i, weight, more = 0;
 	u64 rt_period;
 
diff --git a/lib/digsig.c b/lib/digsig.c
index 8c0e629..dc2be7e 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -162,6 +162,8 @@
 	memset(out1, 0, head);
 	memcpy(out1 + head, p, l);
 
+	kfree(p);
+
 	err = pkcs_1_v1_5_decode_emsa(out1, len, mblen, out2, &len);
 	if (err)
 		goto err;