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

Lots of overlapping changes, mostly trivial in nature.

The mlxsw conflict was resolving using the example
resolution at:

https://github.com/jpirko/linux_mlxsw/blob/combined_queue/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c

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

70 files changed, 539 insertions, 217 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index fbac980d34e1..82f277462349 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5444,6 +5444,7 @@ F:	drivers/iommu/exynos-iommu.c
 
 EZchip NPS platform support
 M:	Vineet Gupta <vgupta@synopsys.com>
+M:	Ofer Levi <oferle@mellanox.com>
 S:	Supported
 F:	arch/arc/plat-eznps
 F:	arch/arc/boot/dts/eznps.dts
diff --git a/Makefile b/Makefile
index 85f3481a56d6..7a3c4548162b 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 18
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
 NAME = Merciless Moray
 
 # *DOCUMENTATION*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 9cf59fc60eab..5151d81476a1 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -50,6 +50,9 @@ config ARC
 	select HAVE_KERNEL_LZMA
 	select ARCH_HAS_PTE_SPECIAL
 
+config ARCH_HAS_CACHE_LINE_SIZE
+	def_bool y
+
 config MIGHT_HAVE_PCI
 	bool
 
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 8486f328cc5d..ff7d3232764a 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -48,7 +48,9 @@
 })
 
 /* Largest line length for either L1 or L2 is 128 bytes */
-#define ARCH_DMA_MINALIGN      128
+#define SMP_CACHE_BYTES		128
+#define cache_line_size()	SMP_CACHE_BYTES
+#define ARCH_DMA_MINALIGN	SMP_CACHE_BYTES
 
 extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index d5da2115d78a..03d6bb0f4e13 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -17,8 +17,11 @@
 #ifndef __ASM_ARC_UDELAY_H
 #define __ASM_ARC_UDELAY_H
 
+#include <asm-generic/types.h>
 #include <asm/param.h>		/* HZ */
 
+extern unsigned long loops_per_jiffy;
+
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 9dbe645ee127..25c631942500 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -1038,7 +1038,7 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
 		      unsigned long pfn)
 {
-	unsigned int paddr = pfn << PAGE_SHIFT;
+	phys_addr_t paddr = pfn << PAGE_SHIFT;
 
 	u_vaddr &= PAGE_MASK;
 
@@ -1058,8 +1058,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page,
 		     unsigned long u_vaddr)
 {
 	/* TBD: do we really need to clear the kernel mapping */
-	__flush_dcache_page(page_address(page), u_vaddr);
-	__flush_dcache_page(page_address(page), page_address(page));
+	__flush_dcache_page((phys_addr_t)page_address(page), u_vaddr);
+	__flush_dcache_page((phys_addr_t)page_address(page),
+			    (phys_addr_t)page_address(page));
 
 }
 
@@ -1246,6 +1247,16 @@ void __init arc_cache_init_master(void)
 		}
 	}
 
+	/*
+	 * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger
+	 * or equal to any cache line length.
+	 */
+	BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES,
+			 "SMP_CACHE_BYTES must be >= any cache line length");
+	if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES))
+		panic("L2 Cache line [%d] > kernel Config [%d]\n",
+		      l2_line_sz, SMP_CACHE_BYTES);
+
 	/* Note that SLC disable not formally supported till HS 3.0 */
 	if (is_isa_arcv2() && l2_line_sz && !slc_enable)
 		arc_slc_disable();
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 8c1071840979..ec47e6079f5d 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -129,14 +129,59 @@ int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
+/*
+ * Cache operations depending on function and direction argument, inspired by
+ * https://lkml.org/lkml/2018/5/18/979
+ * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20]
+ * dma-mapping: provide a generic dma-noncoherent implementation)"
+ *
+ *          |   map          ==  for_device     |   unmap     ==  for_cpu
+ *          |----------------------------------------------------------------
+ * TO_DEV   |   writeback        writeback      |   none          none
+ * FROM_DEV |   invalidate       invalidate     |   invalidate*   invalidate*
+ * BIDIR    |   writeback+inv    writeback+inv  |   invalidate    invalidate
+ *
+ *     [*] needed for CPU speculative prefetches
+ *
+ * NOTE: we don't check the validity of direction argument as it is done in
+ * upper layer functions (in include/linux/dma-mapping.h)
+ */
+
 void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_wback(paddr, size);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback(paddr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv(paddr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
 }
 
 void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_inv(paddr, size);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+
+	/* FROM_DEVICE invalidate needed if speculative CPU prefetch only */
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		dma_cache_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
 }
diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h
index 0c7d11022d0f..4f6a1673b3a6 100644
--- a/arch/arc/plat-eznps/include/plat/ctop.h
+++ b/arch/arc/plat-eznps/include/plat/ctop.h
@@ -21,6 +21,7 @@
 #error "Incorrect ctop.h include"
 #endif
 
+#include <linux/types.h>
 #include <soc/nps/common.h>
 
 /* core auxiliary registers */
@@ -143,6 +144,15 @@ struct nps_host_reg_gim_p_int_dst {
 };
 
 /* AUX registers definition */
+struct nps_host_reg_aux_dpc {
+	union {
+		struct {
+			u32 ien:1, men:1, hen:1, reserved:29;
+		};
+		u32 value;
+	};
+};
+
 struct nps_host_reg_aux_udmc {
 	union {
 		struct {
diff --git a/arch/arc/plat-eznps/mtm.c b/arch/arc/plat-eznps/mtm.c
index 2388de3d09ef..ed0077ef666e 100644
--- a/arch/arc/plat-eznps/mtm.c
+++ b/arch/arc/plat-eznps/mtm.c
@@ -15,6 +15,8 @@
  */
 
 #include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/log2.h>
 #include <asm/arcregs.h>
@@ -157,10 +159,10 @@ void mtm_enable_core(unsigned int cpu)
 /* Verify and set the value of the mtm hs counter */
 static int __init set_mtm_hs_ctr(char *ctr_str)
 {
-	long hs_ctr;
+	int hs_ctr;
 	int ret;
 
-	ret = kstrtol(ctr_str, 0, &hs_ctr);
+	ret = kstrtoint(ctr_str, 0, &hs_ctr);
 
 	if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) {
 		pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n",
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 7cf0b1aa6ea8..8a10f1d7199a 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -488,9 +488,13 @@ static int gcm_decrypt(struct aead_request *req)
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
 		}
-		if (walk.nbytes)
-			pmull_gcm_encrypt_block(iv, iv, NULL,
+		if (walk.nbytes) {
+			kernel_neon_begin();
+			pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc,
 						num_rounds(&ctx->aes_key));
+			kernel_neon_end();
+		}
+
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
 				    num_rounds(&ctx->aes_key));
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 79d570cbf332..b2f89b621b15 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -143,24 +143,33 @@ static inline void mm_context_remove_copro(struct mm_struct *mm)
 {
 	int c;
 
-	c = atomic_dec_if_positive(&mm->context.copros);
-
-	/* Detect imbalance between add and remove */
-	WARN_ON(c < 0);
-
 	/*
-	 * Need to broadcast a global flush of the full mm before
-	 * decrementing active_cpus count, as the next TLBI may be
-	 * local and the nMMU and/or PSL need to be cleaned up.
-	 * Should be rare enough so that it's acceptable.
+	 * When removing the last copro, we need to broadcast a global
+	 * flush of the full mm, as the next TLBI may be local and the
+	 * nMMU and/or PSL need to be cleaned up.
+	 *
+	 * Both the 'copros' and 'active_cpus' counts are looked at in
+	 * flush_all_mm() to determine the scope (local/global) of the
+	 * TLBIs, so we need to flush first before decrementing
+	 * 'copros'. If this API is used by several callers for the
+	 * same context, it can lead to over-flushing. It's hopefully
+	 * not common enough to be a problem.
 	 *
 	 * Skip on hash, as we don't know how to do the proper flush
 	 * for the time being. Invalidations will remain global if
-	 * used on hash.
+	 * used on hash. Note that we can't drop 'copros' either, as
+	 * it could make some invalidations local with no flush
+	 * in-between.
 	 */
-	if (c == 0 && radix_enabled()) {
+	if (radix_enabled()) {
 		flush_all_mm(mm);
-		dec_mm_active_cpus(mm);
+
+		c = atomic_dec_if_positive(&mm->context.copros);
+		/* Detect imbalance between add and remove */
+		WARN_ON(c < 0);
+
+		if (c == 0)
+			dec_mm_active_cpus(mm);
 	}
 }
 #else
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index fe9733ffffaa..471aac313b89 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -42,6 +42,8 @@
 #include <asm/ppc-pci.h>
 #include <asm/eeh.h>
 
+#include "../../../drivers/pci/pci.h"
+
 /* hose_spinlock protects accesses to the the phb_bitmap. */
 static DEFINE_SPINLOCK(hose_spinlock);
 LIST_HEAD(hose_list);
@@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus)
 		/* Cardbus can call us to add new devices to a bus, so ignore
 		 * those who are already fully discovered
 		 */
-		if (dev->is_added)
+		if (pci_dev_is_added(dev))
 			continue;
 
 		pcibios_setup_device(dev);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5bd0eb6681bc..70b2e1e0f23c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -46,6 +46,7 @@
 
 #include "powernv.h"
 #include "pci.h"
+#include "../../../../drivers/pci/pci.h"
 
 #define PNV_IODA1_M64_NUM	16	/* Number of M64 BARs	*/
 #define PNV_IODA1_M64_SEGS	8	/* Segments per M64 BAR	*/
@@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	struct pci_dn *pdn;
 	int mul, total_vfs;
 
-	if (!pdev->is_physfn || pdev->is_added)
+	if (!pdev->is_physfn || pci_dev_is_added(pdev))
 		return;
 
 	pdn = pci_get_pdn(pdev);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 139f0af6c3d9..8a4868a3964b 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -71,6 +71,7 @@
 #include <asm/security_features.h>
 
 #include "pseries.h"
+#include "../../../../drivers/pci/pci.h"
 
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
@@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev)
 	const int *indexes;
 	struct device_node *dn = pci_device_to_OF_node(pdev);
 
-	if (!pdev->is_physfn || pdev->is_added)
+	if (!pdev->is_physfn || pci_dev_is_added(pdev))
 		return;
 	/*Firmware must support open sriov otherwise dont configure*/
 	indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 8c5107545251..9e2157371491 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,3 +1,4 @@
+#include <asm/e820/types.h>
 #include <asm/processor.h>
 #include "pgtable.h"
 #include "../string.h"
@@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data);
 extern struct boot_params *boot_params;
 int cmdline_find_option_bool(const char *option);
 
+static unsigned long find_trampoline_placement(void)
+{
+	unsigned long bios_start, ebda_start;
+	unsigned long trampoline_start;
+	struct boot_e820_entry *entry;
+	int i;
+
+	/*
+	 * Find a suitable spot for the trampoline.
+	 * This code is based on reserve_bios_regions().
+	 */
+
+	ebda_start = *(unsigned short *)0x40e << 4;
+	bios_start = *(unsigned short *)0x413 << 10;
+
+	if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
+		bios_start = BIOS_START_MAX;
+
+	if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
+		bios_start = ebda_start;
+
+	bios_start = round_down(bios_start, PAGE_SIZE);
+
+	/* Find the first usable memory region under bios_start. */
+	for (i = boot_params->e820_entries - 1; i >= 0; i--) {
+		entry = &boot_params->e820_table[i];
+
+		/* Skip all entries above bios_start. */
+		if (bios_start <= entry->addr)
+			continue;
+
+		/* Skip non-RAM entries. */
+		if (entry->type != E820_TYPE_RAM)
+			continue;
+
+		/* Adjust bios_start to the end of the entry if needed. */
+		if (bios_start > entry->addr + entry->size)
+			bios_start = entry->addr + entry->size;
+
+		/* Keep bios_start page-aligned. */
+		bios_start = round_down(bios_start, PAGE_SIZE);
+
+		/* Skip the entry if it's too small. */
+		if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr)
+			continue;
+
+		break;
+	}
+
+	/* Place the trampoline just below the end of low memory */
+	return bios_start - TRAMPOLINE_32BIT_SIZE;
+}
+
 struct paging_config paging_prepare(void *rmode)
 {
 	struct paging_config paging_config = {};
-	unsigned long bios_start, ebda_start;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
 	boot_params = rmode;
@@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode)
 		paging_config.l5_required = 1;
 	}
 
-	/*
-	 * Find a suitable spot for the trampoline.
-	 * This code is based on reserve_bios_regions().
-	 */
-
-	ebda_start = *(unsigned short *)0x40e << 4;
-	bios_start = *(unsigned short *)0x413 << 10;
-
-	if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
-		bios_start = BIOS_START_MAX;
-
-	if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
-		bios_start = ebda_start;
-
-	/* Place the trampoline just below the end of low memory, aligned to 4k */
-	paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE;
-	paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE);
+	paging_config.trampoline_start = find_trampoline_placement();
 
 	trampoline_32bit = (unsigned long *)paging_config.trampoline_start;
 
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index c9e1e0bef3c3..e17ab885b1e9 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -28,7 +28,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	3
+#define UNCORE_EXTRA_PCI_DEV_MAX	4
 
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 87dc0263a2e1..51d7c117e3c7 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	BDX_PCI_QPI_PORT2_FILTER,
 	HSWEP_PCI_PCU_3,
 };
 
@@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
 	},
 	{ /* QPI Port 0 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
 	},
 	{ /* QPI Port 1 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
 	{ /* QPI Port 2 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   BDX_PCI_QPI_PORT2_FILTER),
 	},
 	{ /* PCU.3 (for Capability registers) */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e30da9a2430c..5d8e317c2b04 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7893,6 +7893,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 		     HRTIMER_MODE_REL_PINNED);
 	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
 
+	vmx->nested.vpid02 = allocate_vpid();
+
 	vmx->nested.vmxon = true;
 	return 0;
 
@@ -8480,21 +8482,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 /* Emulate the VMPTRST instruction */
 static int handle_vmptrst(struct kvm_vcpu *vcpu)
 {
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	gva_t vmcs_gva;
+	unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION);
+	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
 	struct x86_exception e;
+	gva_t gva;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, exit_qualification,
-			vmx_instruction_info, true, &vmcs_gva))
+	if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva))
 		return 1;
 	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
-	if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
-					(void *)&to_vmx(vcpu)->nested.current_vmptr,
-					sizeof(u64), &e)) {
+	if (kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
+					sizeof(gpa_t), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -10370,11 +10371,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 			goto free_vmcs;
 	}
 
-	if (nested) {
+	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
 					   kvm_vcpu_apicv_active(&vmx->vcpu));
-		vmx->nested.vpid02 = allocate_vpid();
-	}
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
@@ -10391,7 +10390,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	return &vmx->vcpu;
 
 free_vmcs:
-	free_vpid(vmx->nested.vpid02);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
diff --git a/block/blk-core.c b/block/blk-core.c
index f84a9b7b6f5a..ee33590f54eb 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2155,11 +2155,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 	if (part->policy && op_is_write(bio_op(bio))) {
 		char b[BDEVNAME_SIZE];
 
-		printk(KERN_ERR
+		WARN_ONCE(1,
 		       "generic_make_request: Trying to write "
 			"to read-only block-device %s (partno %d)\n",
 			bio_devname(bio, b), part->partno);
-		return true;
+		/* Older lvm-tools actually trigger this */
+		return false;
 	}
 
 	return false;
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 09b2ee6694fb..3de0836163c2 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -271,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * test and set the bit before assining ->rqs[].
 	 */
 	rq = tags->rqs[bitnr];
-	if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
+	if (rq && blk_mq_request_started(rq))
 		iter_data->fn(rq, iter_data->data, reserved);
 
 	return true;
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 1c6cbda56afe..09d823d36d3a 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -266,6 +266,8 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key,
 		return;
 	}
 
+	count -= initial;
+
 	if (initial)
 		asm volatile (".byte 0xf3,0x0f,0xa7,0xc8"	/* rep xcryptecb */
 			      : "+S"(input), "+D"(output)
@@ -273,7 +275,7 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key,
 
 	asm volatile (".byte 0xf3,0x0f,0xa7,0xc8"	/* rep xcryptecb */
 		      : "+S"(input), "+D"(output)
-		      : "d"(control_word), "b"(key), "c"(count - initial));
+		      : "d"(control_word), "b"(key), "c"(count));
 }
 
 static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
@@ -284,6 +286,8 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
 	if (count < cbc_fetch_blocks)
 		return cbc_crypt(input, output, key, iv, control_word, count);
 
+	count -= initial;
+
 	if (initial)
 		asm volatile (".byte 0xf3,0x0f,0xa7,0xd0"	/* rep xcryptcbc */
 			      : "+S" (input), "+D" (output), "+a" (iv)
@@ -291,7 +295,7 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
 
 	asm volatile (".byte 0xf3,0x0f,0xa7,0xd0"	/* rep xcryptcbc */
 		      : "+S" (input), "+D" (output), "+a" (iv)
-		      : "d" (control_word), "b" (key), "c" (count-initial));
+		      : "d" (control_word), "b" (key), "c" (count));
 	return iv;
 }
 
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 73021b388e12..dd3ff2f2cdce 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -429,6 +429,18 @@ static void adv7511_hpd_work(struct work_struct *work)
 	else
 		status = connector_status_disconnected;
 
+	/*
+	 * The bridge resets its registers on unplug. So when we get a plug
+	 * event and we're already supposed to be powered, cycle the bridge to
+	 * restore its state.
+	 */
+	if (status == connector_status_connected &&
+	    adv7511->connector.status == connector_status_disconnected &&
+	    adv7511->powered) {
+		regcache_mark_dirty(adv7511->regmap);
+		adv7511_power_on(adv7511);
+	}
+
 	if (adv7511->connector.status != status) {
 		adv7511->connector.status = status;
 		if (status == connector_status_disconnected)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 130da5195f3b..81e32199d3ef 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1510,8 +1510,9 @@ int drm_atomic_helper_async_check(struct drm_device *dev,
 {
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
-	struct drm_plane *plane;
-	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane *plane = NULL;
+	struct drm_plane_state *old_plane_state = NULL;
+	struct drm_plane_state *new_plane_state = NULL;
 	const struct drm_plane_helper_funcs *funcs;
 	int i, n_planes = 0;
 
@@ -1527,7 +1528,8 @@ int drm_atomic_helper_async_check(struct drm_device *dev,
 	if (n_planes != 1)
 		return -EINVAL;
 
-	if (!new_plane_state->crtc)
+	if (!new_plane_state->crtc ||
+	    old_plane_state->crtc != new_plane_state->crtc)
 		return -EINVAL;
 
 	funcs = plane->helper_private;
diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c
index 3c4000facb36..f973d287696a 100644
--- a/drivers/gpu/drm/drm_context.c
+++ b/drivers/gpu/drm/drm_context.c
@@ -372,7 +372,7 @@ int drm_legacy_addctx(struct drm_device *dev, void *data,
 		ctx->handle = drm_legacy_ctxbitmap_next(dev);
 	}
 	DRM_DEBUG("%d\n", ctx->handle);
-	if (ctx->handle == -1) {
+	if (ctx->handle < 0) {
 		DRM_DEBUG("Not enough free contexts.\n");
 		/* Should this return -EBUSY instead? */
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 1d34619eb3fe..a951ec75d01f 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -320,6 +320,9 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state)
 			vc4_state->x_scaling[0] = VC4_SCALING_TPZ;
 		if (vc4_state->y_scaling[0] == VC4_SCALING_NONE)
 			vc4_state->y_scaling[0] = VC4_SCALING_TPZ;
+	} else {
+		vc4_state->x_scaling[1] = VC4_SCALING_NONE;
+		vc4_state->y_scaling[1] = VC4_SCALING_NONE;
 	}
 
 	vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE &&
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index cc06e8404e9b..583d3a10b940 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1984,15 +1984,64 @@ static int modify_qp(struct ib_uverbs_file *file,
 		goto release_qp;
 	}
 
-	if ((cmd->base.attr_mask & IB_QP_AV) &&
-	    !rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) {
-		ret = -EINVAL;
-		goto release_qp;
+	if ((cmd->base.attr_mask & IB_QP_AV)) {
+		if (!rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) {
+			ret = -EINVAL;
+			goto release_qp;
+		}
+
+		if (cmd->base.attr_mask & IB_QP_STATE &&
+		    cmd->base.qp_state == IB_QPS_RTR) {
+		/* We are in INIT->RTR TRANSITION (if we are not,
+		 * this transition will be rejected in subsequent checks).
+		 * In the INIT->RTR transition, we cannot have IB_QP_PORT set,
+		 * but the IB_QP_STATE flag is required.
+		 *
+		 * Since kernel 3.14 (commit dbf727de7440), the uverbs driver,
+		 * when IB_QP_AV is set, has required inclusion of a valid
+		 * port number in the primary AV. (AVs are created and handled
+		 * differently for infiniband and ethernet (RoCE) ports).
+		 *
+		 * Check the port number included in the primary AV against
+		 * the port number in the qp struct, which was set (and saved)
+		 * in the RST->INIT transition.
+		 */
+			if (cmd->base.dest.port_num != qp->real_qp->port) {
+				ret = -EINVAL;
+				goto release_qp;
+			}
+		} else {
+		/* We are in SQD->SQD. (If we are not, this transition will
+		 * be rejected later in the verbs layer checks).
+		 * Check for both IB_QP_PORT and IB_QP_AV, these can be set
+		 * together in the SQD->SQD transition.
+		 *
+		 * If only IP_QP_AV was set, add in IB_QP_PORT as well (the
+		 * verbs layer driver does not track primary port changes
+		 * resulting from path migration. Thus, in SQD, if the primary
+		 * AV is modified, the primary port should also be modified).
+		 *
+		 * Note that in this transition, the IB_QP_STATE flag
+		 * is not allowed.
+		 */
+			if (((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT))
+			     == (IB_QP_AV | IB_QP_PORT)) &&
+			    cmd->base.port_num != cmd->base.dest.port_num) {
+				ret = -EINVAL;
+				goto release_qp;
+			}
+			if ((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT))
+			    == IB_QP_AV) {
+				cmd->base.attr_mask |= IB_QP_PORT;
+				cmd->base.port_num = cmd->base.dest.port_num;
+			}
+		}
 	}
 
 	if ((cmd->base.attr_mask & IB_QP_ALT_PATH) &&
 	    (!rdma_is_port_valid(qp->device, cmd->base.alt_port_num) ||
-	    !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num))) {
+	    !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num) ||
+	    cmd->base.alt_port_num != cmd->base.alt_dest.port_num)) {
 		ret = -EINVAL;
 		goto release_qp;
 	}
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index edb35a5c57ea..a99fc0ced7a7 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -728,9 +728,6 @@ EXPORT_SYMBOL_GPL(vsp1_du_setup_lif);
  */
 void vsp1_du_atomic_begin(struct device *dev, unsigned int pipe_index)
 {
-	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
-
-	mutex_lock(&vsp1->drm->lock);
 }
 EXPORT_SYMBOL_GPL(vsp1_du_atomic_begin);
 
@@ -846,6 +843,7 @@ void vsp1_du_atomic_flush(struct device *dev, unsigned int pipe_index,
 
 	drm_pipe->crc = cfg->crc;
 
+	mutex_lock(&vsp1->drm->lock);
 	vsp1_du_pipeline_setup_inputs(vsp1, pipe);
 	vsp1_du_pipeline_configure(pipe);
 	mutex_unlock(&vsp1->drm->lock);
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index fcfab6635f9c..81b150e5dfdb 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -174,6 +174,7 @@ static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog)
 
 	rcu_assign_pointer(raw->progs, new_array);
 	bpf_prog_array_free(old_array);
+	bpf_prog_put(prog);
 unlock:
 	mutex_unlock(&ir_raw_handler_lock);
 	return ret;
diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c
index 2e0066b1a31c..e7948908e78c 100644
--- a/drivers/media/rc/rc-ir-raw.c
+++ b/drivers/media/rc/rc-ir-raw.c
@@ -30,13 +30,13 @@ static int ir_raw_event_thread(void *data)
 		while (kfifo_out(&raw->kfifo, &ev, 1)) {
 			if (is_timing_event(ev)) {
 				if (ev.duration == 0)
-					dev_err(&dev->dev, "nonsensical timing event of duration 0");
+					dev_warn_once(&dev->dev, "nonsensical timing event of duration 0");
 				if (is_timing_event(raw->prev_ev) &&
 				    !is_transition(&ev, &raw->prev_ev))
-					dev_err(&dev->dev, "two consecutive events of type %s",
-						TO_STR(ev.pulse));
+					dev_warn_once(&dev->dev, "two consecutive events of type %s",
+						      TO_STR(ev.pulse));
 				if (raw->prev_ev.reset && ev.pulse == 0)
-					dev_err(&dev->dev, "timing event after reset should be pulse");
+					dev_warn_once(&dev->dev, "timing event after reset should be pulse");
 			}
 			list_for_each_entry(handler, &ir_raw_handler_list, list)
 				if (dev->enabled_protocols &
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 2e222d9ee01f..ca68e1d2b2f9 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -679,6 +679,14 @@ static void ir_timer_repeat(struct timer_list *t)
 	spin_unlock_irqrestore(&dev->keylock, flags);
 }
 
+static unsigned int repeat_period(int protocol)
+{
+	if (protocol >= ARRAY_SIZE(protocols))
+		return 100;
+
+	return protocols[protocol].repeat_period;
+}
+
 /**
  * rc_repeat() - signals that a key is still pressed
  * @dev:	the struct rc_dev descriptor of the device
@@ -691,7 +699,7 @@ void rc_repeat(struct rc_dev *dev)
 {
 	unsigned long flags;
 	unsigned int timeout = nsecs_to_jiffies(dev->timeout) +
-		msecs_to_jiffies(protocols[dev->last_protocol].repeat_period);
+		msecs_to_jiffies(repeat_period(dev->last_protocol));
 	struct lirc_scancode sc = {
 		.scancode = dev->last_scancode, .rc_proto = dev->last_protocol,
 		.keycode = dev->keypressed ? dev->last_keycode : KEY_RESERVED,
@@ -803,7 +811,7 @@ void rc_keydown(struct rc_dev *dev, enum rc_proto protocol, u32 scancode,
 
 	if (dev->keypressed) {
 		dev->keyup_jiffies = jiffies + nsecs_to_jiffies(dev->timeout) +
-			msecs_to_jiffies(protocols[protocol].repeat_period);
+			msecs_to_jiffies(repeat_period(protocol));
 		mod_timer(&dev->timer_keyup, dev->keyup_jiffies);
 	}
 	spin_unlock_irqrestore(&dev->keylock, flags);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index a4669e79fdf9..66ea256fe560 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -327,12 +327,16 @@ static void mlxsw_afa_resource_add(struct mlxsw_afa_block *block,
 	list_add(&resource->list, &block->resource_list);
 }
 
+static void mlxsw_afa_resource_del(struct mlxsw_afa_resource *resource)
+{
+	list_del(&resource->list);
+}
+
 static void mlxsw_afa_resources_destroy(struct mlxsw_afa_block *block)
 {
 	struct mlxsw_afa_resource *resource, *tmp;
 
 	list_for_each_entry_safe(resource, tmp, &block->resource_list, list) {
-		list_del(&resource->list);
 		resource->destructor(block, resource);
 	}
 }
@@ -565,6 +569,7 @@ static void
 mlxsw_afa_fwd_entry_ref_destroy(struct mlxsw_afa_block *block,
 				struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref)
 {
+	mlxsw_afa_resource_del(&fwd_entry_ref->resource);
 	mlxsw_afa_fwd_entry_put(block->afa, fwd_entry_ref->fwd_entry);
 	kfree(fwd_entry_ref);
 }
@@ -614,6 +619,7 @@ static void
 mlxsw_afa_counter_destroy(struct mlxsw_afa_block *block,
 			  struct mlxsw_afa_counter *counter)
 {
+	mlxsw_afa_resource_del(&counter->resource);
 	block->afa->ops->counter_index_put(block->afa->ops_priv,
 					   counter->counter_index);
 	kfree(counter);
@@ -661,8 +667,8 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
 	char *oneact;
 	char *actions;
 
-	if (WARN_ON(block->finished))
-		return NULL;
+	if (block->finished)
+		return ERR_PTR(-EINVAL);
 	if (block->cur_act_index + action_size >
 	    block->afa->max_acts_per_set) {
 		struct mlxsw_afa_set *set;
@@ -672,7 +678,7 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
 		 */
 		set = mlxsw_afa_set_create(false);
 		if (!set)
-			return NULL;
+			return ERR_PTR(-ENOBUFS);
 		set->prev = block->cur_set;
 		block->cur_act_index = 0;
 		block->cur_set->next = set;
@@ -760,9 +766,9 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
 						  MLXSW_AFA_VLAN_CODE,
 						  MLXSW_AFA_VLAN_SIZE);
 
-	if (!act) {
+	if (IS_ERR(act)) {
 		NL_SET_ERR_MSG_MOD(extack, "Cannot append vlan_modify action");
-		return -ENOBUFS;
+		return PTR_ERR(act);
 	}
 	mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
@@ -844,8 +850,8 @@ int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block)
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0);
 	return 0;
@@ -858,8 +864,8 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id)
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD,
 				trap_id);
@@ -874,8 +880,8 @@ int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD,
 				trap_id);
@@ -894,6 +900,7 @@ static void
 mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block,
 			 struct mlxsw_afa_mirror *mirror)
 {
+	mlxsw_afa_resource_del(&mirror->resource);
 	block->afa->ops->mirror_del(block->afa->ops_priv,
 				    mirror->local_in_port,
 				    mirror->span_id,
@@ -946,8 +953,8 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block,
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0);
 	mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent);
@@ -1043,9 +1050,9 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
 
 	act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE,
 					    MLXSW_AFA_FORWARD_SIZE);
-	if (!act) {
-		err = -ENOBUFS;
+	if (IS_ERR(act)) {
 		NL_SET_ERR_MSG_MOD(extack, "Cannot append forward action");
+		err = PTR_ERR(act);
 		goto err_append_action;
 	}
 	mlxsw_afa_forward_pack(act, MLXSW_AFA_FORWARD_TYPE_PBS,
@@ -1100,8 +1107,8 @@ int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block,
 {
 	char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_POLCNT_CODE,
 						  MLXSW_AFA_POLCNT_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES,
 			      counter_index);
 	return 0;
@@ -1176,9 +1183,9 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid,
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_VIRFWD_CODE,
 						  MLXSW_AFA_VIRFWD_SIZE);
-	if (!act) {
+	if (IS_ERR(act)) {
 		NL_SET_ERR_MSG_MOD(extack, "Cannot append fid_set action");
-		return -ENOBUFS;
+		return PTR_ERR(act);
 	}
 	mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid);
 	return 0;
@@ -1248,8 +1255,8 @@ int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_MCROUTER_CODE,
 						  MLXSW_AFA_MCROUTER_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP,
 				expected_irif, min_mtu, rmid_valid, kvdl_index);
 	return 0;
diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index 093bd21f574d..4907453f17f5 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -1362,7 +1362,7 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/
             case 0x001:
                 printk(KERN_WARNING "%s: Master Abort (naughty)\n", dev->name);
                 break;
-            case 0x010:
+            case 0x002:
                 printk(KERN_WARNING "%s: Target Abort (not so naughty)\n", dev->name);
                 break;
             default:
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 35b7fc87eac5..5cb40b2518f9 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -330,7 +330,7 @@ void pci_bus_add_device(struct pci_dev *dev)
 		return;
 	}
 
-	dev->is_added = 1;
+	pci_dev_assign_added(dev, true);
 }
 EXPORT_SYMBOL_GPL(pci_bus_add_device);
 
@@ -347,14 +347,14 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Skip already-added devices */
-		if (dev->is_added)
+		if (pci_dev_is_added(dev))
 			continue;
 		pci_bus_add_device(dev);
 	}
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Skip if device attach failed */
-		if (!dev->is_added)
+		if (!pci_dev_is_added(dev))
 			continue;
 		child = dev->subordinate;
 		if (child)
diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c
index 4d6c20e47bed..cf0aa7cee5b0 100644
--- a/drivers/pci/controller/pcie-mobiveil.c
+++ b/drivers/pci/controller/pcie-mobiveil.c
@@ -107,7 +107,7 @@
 #define CFG_WINDOW_TYPE	0
 #define IO_WINDOW_TYPE		1
 #define MEM_WINDOW_TYPE	2
-#define IB_WIN_SIZE		(256 * 1024 * 1024 * 1024)
+#define IB_WIN_SIZE		((u64)256 * 1024 * 1024 * 1024)
 #define MAX_PIO_WINDOWS	8
 
 /* Parameters for the waiting for link up routine */
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 3a17b290df5d..ef0b1b6ba86f 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -509,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot)
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		/* Assume that newly added devices are powered on already. */
-		if (!dev->is_added)
+		if (!pci_dev_is_added(dev))
 			dev->current_state = PCI_D0;
 	}
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 882f1f9596df..08817253c8a2 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -288,6 +288,7 @@ struct pci_sriov {
 
 /* pci_dev priv_flags */
 #define PCI_DEV_DISCONNECTED 0
+#define PCI_DEV_ADDED 1
 
 static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused)
 {
@@ -300,6 +301,16 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev)
 	return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags);
 }
 
+static inline void pci_dev_assign_added(struct pci_dev *dev, bool added)
+{
+	assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added);
+}
+
+static inline bool pci_dev_is_added(const struct pci_dev *dev)
+{
+	return test_bit(PCI_DEV_ADDED, &dev->priv_flags);
+}
+
 #ifdef CONFIG_PCI_ATS
 void pci_restore_ats_state(struct pci_dev *dev);
 #else
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ac876e32de4b..611adcd9c169 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2433,13 +2433,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn)
 	dev = pci_scan_single_device(bus, devfn);
 	if (!dev)
 		return 0;
-	if (!dev->is_added)
+	if (!pci_dev_is_added(dev))
 		nr++;
 
 	for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) {
 		dev = pci_scan_single_device(bus, devfn + fn);
 		if (dev) {
-			if (!dev->is_added)
+			if (!pci_dev_is_added(dev))
 				nr++;
 			dev->multifunction = 1;
 		}
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 6f072eae4f7a..5e3d0dced2b8 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -19,11 +19,12 @@ static void pci_stop_dev(struct pci_dev *dev)
 {
 	pci_pme_active(dev, false);
 
-	if (dev->is_added) {
+	if (pci_dev_is_added(dev)) {
 		device_release_driver(&dev->dev);
 		pci_proc_detach_device(dev);
 		pci_remove_sysfs_dev_files(dev);
-		dev->is_added = 0;
+
+		pci_dev_assign_added(dev, false);
 	}
 
 	if (dev->bus->self)
diff --git a/fs/iomap.c b/fs/iomap.c
index 77397b5a96ef..0d0bd8845586 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1443,7 +1443,7 @@ iomap_bmap(struct address_space *mapping, sector_t bno,
 		const struct iomap_ops *ops)
 {
 	struct inode *inode = mapping->host;
-	loff_t pos = bno >> inode->i_blkbits;
+	loff_t pos = bno << inode->i_blkbits;
 	unsigned blocksize = i_blocksize(inode);
 
 	if (filemap_write_and_wait(mapping))
diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h
index 395c4c0d0f06..1682a87c00b2 100644
--- a/fs/jfs/jfs_dinode.h
+++ b/fs/jfs/jfs_dinode.h
@@ -115,6 +115,13 @@ struct dinode {
 					dxd_t _dxd;	/* 16: */
 					union {
 						__le32 _rdev;	/* 4: */
+						/*
+						 * The fast symlink area
+						 * is expected to overflow
+						 * into _inlineea when
+						 * needed (which will clear
+						 * INLINEEA).
+						 */
 						u8 _fastsymlink[128];
 					} _u;
 					u8 _inlineea[128];
diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h
index 1f26d1910409..9940a1e04cbf 100644
--- a/fs/jfs/jfs_incore.h
+++ b/fs/jfs/jfs_incore.h
@@ -87,6 +87,7 @@ struct jfs_inode_info {
 		struct {
 			unchar _unused[16];	/* 16: */
 			dxd_t _dxd;		/* 16: */
+			/* _inline may overflow into _inline_ea when needed */
 			unchar _inline[128];	/* 128: inline symlink */
 			/* _inline_ea may overlay the last part of
 			 * file._xtroot if maxentry = XTROOTINITSLOT
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 1b9264fd54b6..f08571433aba 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -967,8 +967,7 @@ static int __init init_jfs_fs(void)
 	jfs_inode_cachep =
 	    kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info),
 			0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
-			offsetof(struct jfs_inode_info, i_inline),
-			sizeof_field(struct jfs_inode_info, i_inline),
+			offsetof(struct jfs_inode_info, i_inline), IDATASIZE,
 			init_once);
 	if (jfs_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6dd146885da9..f6c4ccd693f4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6466,34 +6466,34 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 		if (data->arg.new_lock && !data->cancelled) {
 			data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
 			if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0)
-				break;
+				goto out_restart;
 		}
-
 		if (data->arg.new_lock_owner != 0) {
 			nfs_confirm_seqid(&lsp->ls_seqid, 0);
 			nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid);
 			set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags);
-			goto out_done;
-		} else if (nfs4_update_lock_stateid(lsp, &data->res.stateid))
-			goto out_done;
-
+		} else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid))
+			goto out_restart;
 		break;
 	case -NFS4ERR_BAD_STATEID:
 	case -NFS4ERR_OLD_STATEID:
 	case -NFS4ERR_STALE_STATEID:
 	case -NFS4ERR_EXPIRED:
 		if (data->arg.new_lock_owner != 0) {
-			if (nfs4_stateid_match(&data->arg.open_stateid,
+			if (!nfs4_stateid_match(&data->arg.open_stateid,
 						&lsp->ls_state->open_stateid))
-				goto out_done;
-		} else if (nfs4_stateid_match(&data->arg.lock_stateid,
+				goto out_restart;
+		} else if (!nfs4_stateid_match(&data->arg.lock_stateid,
 						&lsp->ls_stateid))
-				goto out_done;
+				goto out_restart;
 	}
-	if (!data->cancelled)
-		rpc_restart_call_prepare(task);
 out_done:
 	dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status);
+	return;
+out_restart:
+	if (!data->cancelled)
+		rpc_restart_call_prepare(task);
+	goto out_done;
 }
 
 static void nfs4_lock_release(void *calldata)
@@ -6502,7 +6502,7 @@ static void nfs4_lock_release(void *calldata)
 
 	dprintk("%s: begin!\n", __func__);
 	nfs_free_seqid(data->arg.open_seqid);
-	if (data->cancelled) {
+	if (data->cancelled && data->rpc_status == 0) {
 		struct rpc_task *task;
 		task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp,
 				data->arg.lock_seqid);
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 594d192b2331..bad9cea37f12 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -633,8 +633,10 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 		/* the various vma->vm_userfaultfd_ctx still points to it */
 		down_write(&mm->mmap_sem);
 		for (vma = mm->mmap; vma; vma = vma->vm_next)
-			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx)
+			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+				vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+			}
 		up_write(&mm->mmap_sem);
 
 		userfaultfd_ctx_put(release_new_ctx);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index abd5d5e17aee..c133ccfa002e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -368,7 +368,6 @@ struct pci_dev {
 	unsigned int	transparent:1;		/* Subtractive decode bridge */
 	unsigned int	multifunction:1;	/* Multi-function device */
 
-	unsigned int	is_added:1;
 	unsigned int	is_busmaster:1;		/* Is busmaster */
 	unsigned int	no_msi:1;		/* May not use MSI */
 	unsigned int	no_64bit_msi:1; 	/* May only use 32-bit MSIs */
diff --git a/ipc/shm.c b/ipc/shm.c
index d4daf78df6da..fa1d322daa27 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -428,6 +428,17 @@ static int shm_split(struct vm_area_struct *vma, unsigned long addr)
 	return 0;
 }
 
+static unsigned long shm_pagesize(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	if (sfd->vm_ops->pagesize)
+		return sfd->vm_ops->pagesize(vma);
+
+	return PAGE_SIZE;
+}
+
 #ifdef CONFIG_NUMA
 static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
 {
@@ -555,6 +566,7 @@ static const struct vm_operations_struct shm_vm_ops = {
 	.close	= shm_close,	/* callback for when the vm-area is released */
 	.fault	= shm_fault,
 	.split	= shm_split,
+	.pagesize = shm_pagesize,
 #if defined(CONFIG_NUMA)
 	.set_policy = shm_set_policy,
 	.get_policy = shm_get_policy,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index daeabd791d58..9a8b7ba9aa88 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1068,6 +1068,13 @@ static int irq_setup_forced_threading(struct irqaction *new)
 	if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
 		return 0;
 
+	/*
+	 * No further action required for interrupts which are requested as
+	 * threaded interrupts already
+	 */
+	if (new->handler == irq_default_primary_handler)
+		return 0;
+
 	new->flags |= IRQF_ONESHOT;
 
 	/*
@@ -1075,7 +1082,7 @@ static int irq_setup_forced_threading(struct irqaction *new)
 	 * thread handler. We force thread them as well by creating a
 	 * secondary action.
 	 */
-	if (new->handler != irq_default_primary_handler && new->thread_fn) {
+	if (new->handler && new->thread_fn) {
 		/* Allocate the secondary action */
 		new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
 		if (!new->secondary)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 75ffc1d1a2e0..6f584861d329 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -390,7 +390,7 @@ static inline void tick_irq_exit(void)
 
 	/* Make sure that timer wheel updates are propagated */
 	if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
-		if (!in_interrupt())
+		if (!in_irq())
 			tick_nohz_irq_exit();
 	}
 #endif
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index da9455a6b42b..5b33e2f5c0ed 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -642,7 +642,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 
 static inline bool local_timer_softirq_pending(void)
 {
-	return local_softirq_pending() & TIMER_SOFTIRQ;
+	return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
 }
 
 static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 039ddbc574e9..3103099f64fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3167,6 +3167,13 @@ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf)
 	return 0;
 }
 
+/*
+ * When a new function is introduced to vm_operations_struct and added
+ * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops.
+ * This is because under System V memory model, mappings created via
+ * shmget/shmat with "huge page" specified are backed by hugetlbfs files,
+ * their original vm_ops are overwritten with shm_vm_ops.
+ */
 const struct vm_operations_struct hugetlb_vm_ops = {
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8c0280b3143e..b2173f7e5164 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4037,6 +4037,14 @@ static struct cftype mem_cgroup_legacy_files[] = {
 
 static DEFINE_IDR(mem_cgroup_idr);
 
+static void mem_cgroup_id_remove(struct mem_cgroup *memcg)
+{
+	if (memcg->id.id > 0) {
+		idr_remove(&mem_cgroup_idr, memcg->id.id);
+		memcg->id.id = 0;
+	}
+}
+
 static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
 {
 	VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0);
@@ -4047,8 +4055,7 @@ static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
 {
 	VM_BUG_ON(atomic_read(&memcg->id.ref) < n);
 	if (atomic_sub_and_test(n, &memcg->id.ref)) {
-		idr_remove(&mem_cgroup_idr, memcg->id.id);
-		memcg->id.id = 0;
+		mem_cgroup_id_remove(memcg);
 
 		/* Memcg ID pins CSS */
 		css_put(&memcg->css);
@@ -4185,8 +4192,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	return memcg;
 fail:
-	if (memcg->id.id > 0)
-		idr_remove(&mem_cgroup_idr, memcg->id.id);
+	mem_cgroup_id_remove(memcg);
 	__mem_cgroup_free(memcg);
 	return NULL;
 }
@@ -4245,6 +4251,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	return &memcg->css;
 fail:
+	mem_cgroup_id_remove(memcg);
 	mem_cgroup_free(memcg);
 	return ERR_PTR(-ENOMEM);
 }
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index b403728e2757..6e2c8e7595e0 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1139,13 +1139,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
 				l2tp_session_get(sock_net(sk), tunnel,
 						 stats.session_id);
 
-			if (session && session->pwtype == L2TP_PWTYPE_PPP) {
-				err = pppol2tp_session_ioctl(session, cmd,
-							     arg);
+			if (!session) {
+				err = -EBADR;
+				break;
+			}
+			if (session->pwtype != L2TP_PWTYPE_PPP) {
 				l2tp_session_dec_refcount(session);
-			} else {
 				err = -EBADR;
+				break;
 			}
+
+			err = pppol2tp_session_ioctl(session, cmd, arg);
+			l2tp_session_dec_refcount(session);
 			break;
 		}
 #ifdef CONFIG_XFRM
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 505bf36474ba..930d17fa906c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1013,8 +1013,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 
 	if (nlk->ngroups == 0)
 		groups = 0;
-	else
-		groups &= (1ULL << nlk->ngroups) - 1;
+	else if (nlk->ngroups < 8*sizeof(groups))
+		groups &= (1UL << nlk->ngroups) - 1;
 
 	bound = nlk->bound;
 	if (bound) {
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index a7af2289cdff..ed5dcf03fe0b 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -278,7 +278,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 			/* force immediate tx of current consumer cursor, but
 			 * under send_lock to guarantee arrival in seqno-order
 			 */
-			smc_tx_sndbuf_nonempty(conn);
+			if (smc->sk.sk_state != SMC_INIT)
+				smc_tx_sndbuf_nonempty(conn);
 		}
 	}
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 72335c2e8108..4e937cd7c17d 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -84,10 +84,8 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
 	int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len);
 
-	if (err) {
-		xdp_return_buff(xdp);
+	if (err)
 		xs->rx_dropped++;
-	}
 
 	return err;
 }
diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
index ac5ba55066dd..985534d0b448 100644
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -399,5 +399,6 @@
 #define __NR_pkey_free		385
 #define __NR_pkey_mprotect	386
 #define __NR_rseq		387
+#define __NR_io_pgetevents	388
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h
new file mode 100644
index 000000000000..2ccd588fbad4
--- /dev/null
+++ b/tools/arch/x86/include/asm/mcsafe_test.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MCSAFE_TEST_H_
+#define _MCSAFE_TEST_H_
+
+.macro MCSAFE_TEST_CTL
+.endm
+
+.macro MCSAFE_TEST_SRC reg count target
+.endm
+
+.macro MCSAFE_TEST_DST reg count target
+.endm
+#endif /* _MCSAFE_TEST_H_ */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 9a53a06e5a3e..298ef1479240 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -3,6 +3,7 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
+#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -183,12 +184,15 @@ ENTRY(memcpy_orig)
 ENDPROC(memcpy_orig)
 
 #ifndef CONFIG_UML
+
+MCSAFE_TEST_CTL
+
 /*
- * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
+ * __memcpy_mcsafe - memory copy with machine check exception handling
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(memcpy_mcsafe_unrolled)
+ENTRY(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -204,58 +208,33 @@ ENTRY(memcpy_mcsafe_unrolled)
 	subl $8, %ecx
 	negl %ecx
 	subl %ecx, %edx
-.L_copy_leading_bytes:
+.L_read_leading_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
+.L_write_leading_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_leading_bytes
+	jnz .L_read_leading_bytes
 
 .L_8byte_aligned:
-	/* Figure out how many whole cache lines (64-bytes) to copy */
-	movl %edx, %ecx
-	andl $63, %edx
-	shrl $6, %ecx
-	jz .L_no_whole_cache_lines
-
-	/* Loop copying whole cache lines */
-.L_cache_w0: movq (%rsi), %r8
-.L_cache_w1: movq 1*8(%rsi), %r9
-.L_cache_w2: movq 2*8(%rsi), %r10
-.L_cache_w3: movq 3*8(%rsi), %r11
-	movq %r8, (%rdi)
-	movq %r9, 1*8(%rdi)
-	movq %r10, 2*8(%rdi)
-	movq %r11, 3*8(%rdi)
-.L_cache_w4: movq 4*8(%rsi), %r8
-.L_cache_w5: movq 5*8(%rsi), %r9
-.L_cache_w6: movq 6*8(%rsi), %r10
-.L_cache_w7: movq 7*8(%rsi), %r11
-	movq %r8, 4*8(%rdi)
-	movq %r9, 5*8(%rdi)
-	movq %r10, 6*8(%rdi)
-	movq %r11, 7*8(%rdi)
-	leaq 64(%rsi), %rsi
-	leaq 64(%rdi), %rdi
-	decl %ecx
-	jnz .L_cache_w0
-
-	/* Are there any trailing 8-byte words? */
-.L_no_whole_cache_lines:
 	movl %edx, %ecx
 	andl $7, %edx
 	shrl $3, %ecx
 	jz .L_no_whole_words
 
-	/* Copy trailing words */
-.L_copy_trailing_words:
+.L_read_words:
 	movq (%rsi), %r8
-	mov %r8, (%rdi)
-	leaq 8(%rsi), %rsi
-	leaq 8(%rdi), %rdi
+	MCSAFE_TEST_SRC %rsi 8 .E_read_words
+	MCSAFE_TEST_DST %rdi 8 .E_write_words
+.L_write_words:
+	movq %r8, (%rdi)
+	addq $8, %rsi
+	addq $8, %rdi
 	decl %ecx
-	jnz .L_copy_trailing_words
+	jnz .L_read_words
 
 	/* Any trailing bytes? */
 .L_no_whole_words:
@@ -264,38 +243,55 @@ ENTRY(memcpy_mcsafe_unrolled)
 
 	/* Copy trailing bytes */
 	movl %edx, %ecx
-.L_copy_trailing_bytes:
+.L_read_trailing_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
+.L_write_trailing_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_trailing_bytes
+	jnz .L_read_trailing_bytes
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorq %rax, %rax
 	ret
-ENDPROC(memcpy_mcsafe_unrolled)
-EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
+ENDPROC(__memcpy_mcsafe)
+EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"
-	/* Return -EFAULT for any failure */
-.L_memcpy_mcsafe_fail:
-	mov	$-EFAULT, %rax
+	/*
+	 * Return number of bytes not copied for any failure. Note that
+	 * there is no "tail" handling since the source buffer is 8-byte
+	 * aligned and poison is cacheline aligned.
+	 */
+.E_read_words:
+	shll	$3, %ecx
+.E_leading_bytes:
+	addl	%edx, %ecx
+.E_trailing_bytes:
+	mov	%ecx, %eax
 	ret
 
+	/*
+	 * For write fault handling, given the destination is unaligned,
+	 * we handle faults on multi-byte writes with a byte-by-byte
+	 * copy up to the write-protected page.
+	 */
+.E_write_words:
+	shll	$3, %ecx
+	addl	%edx, %ecx
+	movl	%ecx, %edx
+	jmp mcsafe_handle_tail
+
 	.previous
 
-	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE(.L_write_words, .E_write_words)
+	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
 #endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 9c8191845585..e860ca859b28 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -35,6 +35,7 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -91,7 +92,8 @@ static bool map_is_map_of_progs(__u32 type)
 static void *alloc_value(struct bpf_map_info *info)
 {
 	if (map_is_per_cpu(info->type))
-		return malloc(info->value_size * get_possible_cpus());
+		return malloc(round_up(info->value_size, 8) *
+			      get_possible_cpus());
 	else
 		return malloc(info->value_size);
 }
@@ -273,9 +275,10 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 			do_dump_btf(&d, info, key, value);
 		}
 	} else {
-		unsigned int i, n;
+		unsigned int i, n, step;
 
 		n = get_possible_cpus();
+		step = round_up(info->value_size, 8);
 
 		jsonw_name(json_wtr, "key");
 		print_hex_data_json(key, info->key_size);
@@ -288,7 +291,7 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 			jsonw_int_field(json_wtr, "cpu", i);
 
 			jsonw_name(json_wtr, "value");
-			print_hex_data_json(value + i * info->value_size,
+			print_hex_data_json(value + i * step,
 					    info->value_size);
 
 			jsonw_end_object(json_wtr);
@@ -319,9 +322,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 
 		printf("\n");
 	} else {
-		unsigned int i, n;
+		unsigned int i, n, step;
 
 		n = get_possible_cpus();
+		step = round_up(info->value_size, 8);
 
 		printf("key:\n");
 		fprint_hex(stdout, key, info->key_size, " ");
@@ -329,7 +333,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 		for (i = 0; i < n; i++) {
 			printf("value (CPU %02d):%c",
 			       i, info->value_size > 16 ? '\n' : ' ');
-			fprint_hex(stdout, value + i * info->value_size,
+			fprint_hex(stdout, value + i * step,
 				   info->value_size, " ");
 			printf("\n");
 		}
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index b8e288a1f740..eeb787b1c53c 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -143,6 +143,8 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
 	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
+
+	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63,
 };
 
 /*
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index 63a74c32ddc5..e33ef5bc31c5 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 #include "../../util/intel-pt.h"
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 06bae7023a51..950539f9a4f7 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -2,6 +2,7 @@
 #include <stdbool.h>
 #include <errno.h>
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 #include "../../perf.h"
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 60bf11943047..eafce1a130a1 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
 
+perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index b43f8d2a34ec..9ad015a1e202 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,6 +6,7 @@
 #define altinstr_replacement text
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
+#define _ASM_EXTABLE(x, y)
 
 #include "../../arch/x86/lib/memcpy_64.S"
 /*
diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c
new file mode 100644
index 000000000000..4130734dde84
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c
@@ -0,0 +1,24 @@
+/*
+ * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
+ * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
+ * happy.
+ */
+#include <linux/types.h>
+
+unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
+
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++) {
+		/*
+		 * Call the assembly routine back directly since
+		 * memcpy_mcsafe() may silently fallback to memcpy.
+		 */
+		unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+		if (rem)
+			break;
+	}
+	return len;
+}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index a1a97956136f..d215714f48df 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -5,6 +5,7 @@
 #include <time.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 
 extern bool test_attr__enabled;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 90d4577a92dc..6d7fe44aadc0 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -2,6 +2,7 @@
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <sys/types.h>
 #include <stdbool.h>
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 760558dcfd18..cae1a9a39722 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -10,6 +10,7 @@
 #define __PERF_NAMESPACES_H
 
 #include <sys/types.h>
+#include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
index 270fa8f49573..785eabf2a593 100755
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
@@ -115,14 +115,14 @@ ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o
 ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link
 
 ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65
-ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4
+ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4
 
-ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6
+ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6
 ip netns exec ns4 ip -6 addr add fc42::1 dev lo
 ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87
 
 ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109
-ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8
+ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8
 
 ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo
 ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 77f762780199..e8c5dff448eb 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -402,7 +402,7 @@ int main(int argc, char *argv[])
 		exit(1);
 	}
 
-	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	fd = socket(cfg_family, SOCK_STREAM, 0);
 	if (fd == -1) {
 		perror("socket");
 		exit(1);