Merge branch 'nfs-rdma'

author: Trond Myklebust <trond.myklebust@primarydata.com> 2016-07-24 23:09:02 +0200
committer: Trond Myklebust <trond.myklebust@primarydata.com> 2016-07-24 23:09:02 +0200
commit: 1592c4d62a89bbca895c568d65ce290dfbc36ecc (patch)
tree: 6b979bc02ded2ea7e644c34e6939ffbbb7ee001d
parent: Merge branch 'pnfs' (diff)
parent: Merge tag 'nfs-rdma-4.8-2' of git://git.linux-nfs.org/projects/anna/nfs-rdma (diff)
download: linux-1592c4d62a89bbca895c568d65ce290dfbc36ecc.tar.xz
linux-1592c4d62a89bbca895c568d65ce290dfbc36ecc.zip
205 files changed, 2417 insertions, 1698 deletions
diff --git a/Documentation/x86/intel_mpx.txt b/Documentation/x86/intel_mpx.txt
index 1a5a12184a35..85d0549ad846 100644
--- a/Documentation/x86/intel_mpx.txt
+++ b/Documentation/x86/intel_mpx.txt
@@ -45,7 +45,7 @@ is how we expect the compiler, application and kernel to work together.
    MPX-instrumented.
 3) The kernel detects that the CPU has MPX, allows the new prctl() to
    succeed, and notes the location of the bounds directory. Userspace is
-   expected to keep the bounds directory at that locationWe note it
+   expected to keep the bounds directory at that location. We note it
    instead of reading it each time because the 'xsave' operation needed
    to access the bounds directory register is an expensive operation.
 4) If the application needs to spill bounds out of the 4 registers, it
@@ -167,7 +167,7 @@ If a #BR is generated due to a bounds violation caused by MPX.
 We need to decode MPX instructions to get violation address and
 set this address into extended struct siginfo.
 
-The _sigfault feild of struct siginfo is extended as follow:
+The _sigfault field of struct siginfo is extended as follow:
 
 87		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 88		struct {
@@ -240,5 +240,5 @@ them at the same bounds table.
 This is allowed architecturally.  See more information "Intel(R) Architecture
 Instruction Set Extensions Programming Reference" (9.3.4).
 
-However, if users did this, the kernel might be fooled in to unmaping an
+However, if users did this, the kernel might be fooled in to unmapping an
 in-use bounds table since it does not recognize sharing.
diff --git a/Documentation/x86/tlb.txt b/Documentation/x86/tlb.txt
index 39d172326703..6a0607b99ed8 100644
--- a/Documentation/x86/tlb.txt
+++ b/Documentation/x86/tlb.txt
@@ -5,7 +5,7 @@ memory, it has two choices:
     from areas other than the one we are trying to flush will be
     destroyed and must be refilled later, at some cost.
  2. Use the invlpg instruction to invalidate a single page at a
-    time.  This could potentialy cost many more instructions, but
+    time.  This could potentially cost many more instructions, but
     it is a much more precise operation, causing no collateral
     damage to other TLB entries.
 
@@ -19,7 +19,7 @@ Which method to do depends on a few things:
     work.
  3. The size of the TLB.  The larger the TLB, the more collateral
     damage we do with a full flush.  So, the larger the TLB, the
-    more attrative an individual flush looks.  Data and
+    more attractive an individual flush looks.  Data and
     instructions have separate TLBs, as do different page sizes.
  4. The microarchitecture.  The TLB has become a multi-level
     cache on modern CPUs, and the global flushes have become more
diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck
index b1fb30273286..d0648a74fceb 100644
--- a/Documentation/x86/x86_64/machinecheck
+++ b/Documentation/x86/x86_64/machinecheck
@@ -36,7 +36,7 @@ between all CPUs.
 
 check_interval
 	How often to poll for corrected machine check errors, in seconds
-	(Note output is hexademical). Default 5 minutes.  When the poller
+	(Note output is hexadecimal). Default 5 minutes.  When the poller
 	finds MCEs it triggers an exponential speedup (poll more often) on
 	the polling interval.  When the poller stops finding MCEs, it
 	triggers an exponential backoff (poll less often) on the polling
diff --git a/Makefile b/Makefile
index 2d24babe6f8b..81b22628025a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc7
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 87e1985f3be8..9d9fd4b9a72e 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -80,12 +80,14 @@
 #define APM_CPU_PART_POTENZA		0x000
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
+#define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
 
 #define BRCM_CPU_PART_VULCAN		0x516
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
+#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index a307eb6e7fa8..7f94755089e2 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -117,6 +117,8 @@ struct pt_regs {
 	};
 	u64 orig_x0;
 	u64 syscallno;
+	u64 orig_addr_limit;
+	u64 unused;	// maintain 16 byte alignment
 };
 
 #define arch_has_single_step()	(1)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index f8e5d47f0880..2f4ba774488a 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -60,6 +60,7 @@ int main(void)
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
+  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index d42789499f17..af716b65110d 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX, 0x00,
 			   (1 << MIDR_VARIANT_SHIFT) | 1),
 	},
+	{
+	/* Cavium ThunderX, T81 pass 1.0 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00),
+	},
 #endif
 	{
 	}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 12e8d2bcb3f9..6c3b7345a6c4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -28,6 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
+#include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -97,7 +98,14 @@
 	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	.endif
+	get_thread_info tsk
+	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	mov	x20, #TASK_SIZE_64
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
 	stp	lr, x21, [sp, #S_LR]
@@ -128,6 +136,14 @@
 	.endm
 
 	.macro	kernel_exit, el
+	.if	\el != 0
+	/* Restore the task's original addr_limit. */
+	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+
+	/* No need to restore UAO, it will be restored from SPSR_EL1 */
+	.endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -406,7 +422,6 @@ el1_irq:
 	bl	trace_hardirqs_off
 #endif
 
-	get_thread_info tsk
 	irq_handler
 
 #ifdef CONFIG_PREEMPT
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 013e2cbe7924..b1166d1e5955 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	}
 
 	if (permission_fault(esr) && (addr < USER_DS)) {
-		if (get_fs() == KERNEL_DS)
+		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
+		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
 
 		if (!search_exception_tables(regs->pc))
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index a6b611f1da43..7d44e888134f 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -24,7 +24,7 @@ struct mm_struct;
 struct vm_area_struct;
 
 #define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_NO_READ | \
-				 _CACHE_CACHABLE_NONCOHERENT)
+				 _page_cachable_default)
 #define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_WRITE | \
 				 _page_cachable_default)
 #define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_NO_EXEC | \
@@ -476,7 +476,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	pte.pte_low  &= (_PAGE_MODIFIED | _PAGE_ACCESSED | _PFNX_MASK);
 	pte.pte_high &= (_PFN_MASK | _CACHE_MASK);
 	pte.pte_low  |= pgprot_val(newprot) & ~_PFNX_MASK;
-	pte.pte_high |= pgprot_val(newprot) & ~_PFN_MASK;
+	pte.pte_high |= pgprot_val(newprot) & ~(_PFN_MASK | _CACHE_MASK);
 	return pte;
 }
 #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
@@ -491,7 +491,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #else
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) |
+		     (pgprot_val(newprot) & ~_PAGE_CHG_MASK));
 }
 #endif
 
@@ -632,7 +633,8 @@ static inline struct page *pmd_page(pmd_t pmd)
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | pgprot_val(newprot);
+	pmd_val(pmd) = (pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HUGE)) |
+		       (pgprot_val(newprot) & ~_PAGE_CHG_MASK);
 	return pmd;
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 88a5ecaa157b..ab84c89c9e98 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -230,6 +230,7 @@ extern unsigned long __kernel_virt_size;
 #define KERN_VIRT_SIZE  __kernel_virt_size
 extern struct page *vmemmap;
 extern unsigned long ioremap_bot;
+extern unsigned long pci_io_base;
 #endif /* __ASSEMBLY__ */
 
 #include <asm/book3s/64/hash.h>
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index b5f73cb5eeb6..d70101e1e25c 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -647,7 +647,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 			pci_unlock_rescan_remove();
 		}
 	} else if (frozen_bus) {
-		eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data);
+		eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
 	}
 
 	/*
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 3759df52bd67..a5ae49a2dcc4 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -47,7 +47,6 @@ static int __init pcibios_init(void)
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
 
-	pci_io_base = ISA_IO_BASE;
 	/* For now, override phys_mem_access_prot. If we need it,g
 	 * later, we may move that initialization to each ppc_md
 	 */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e2f12cbcade9..0b93893424f5 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1505,6 +1505,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 		current->thread.regs = regs - 1;
 	}
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * Clear any transactional state, we're exec()ing. The cause is
+	 * not important as there will never be a recheckpoint so it's not
+	 * user visible.
+	 */
+	if (MSR_TM_SUSPENDED(mfmsr()))
+		tm_reclaim_current(0);
+#endif
+
 	memset(regs->gpr, 0, sizeof(regs->gpr));
 	regs->ctr = 0;
 	regs->link = 0;
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index bf8f34a58670..b7019b559ddb 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim)
 	std	r3, STK_PARAM(R3)(r1)
 	SAVE_NVGPRS(r1)
 
-	/* We need to setup MSR for VSX register save instructions.  Here we
-	 * also clear the MSR RI since when we do the treclaim, we won't have a
-	 * valid kernel pointer for a while.  We clear RI here as it avoids
-	 * adding another mtmsr closer to the treclaim.  This makes the region
-	 * maked as non-recoverable wider than it needs to be but it saves on
-	 * inserting another mtmsrd later.
-	 */
+	/* We need to setup MSR for VSX register save instructions. */
 	mfmsr	r14
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
-	li	r16, MSR_RI
+	li	r16, 0
 	ori	r16, r16, MSR_EE /* IRQs hard off */
 	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
@@ -176,7 +170,17 @@ dont_backup_fp:
 1:	tdeqi   r6, 0
 	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
 
-	/* The moment we treclaim, ALL of our GPRs will switch
+	/* Clear MSR RI since we are about to change r1, EE is already off. */
+	li	r4, 0
+	mtmsrd	r4, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 *
+	 * The moment we treclaim, ALL of our GPRs will switch
 	 * to user register state.  (FPRs, CCR etc. also!)
 	 * Use an sprg and a tm_scratch in the PACA to shuffle.
 	 */
@@ -197,6 +201,11 @@ dont_backup_fp:
 
 	/* Store the PPR in r11 and reset to decent value */
 	std	r11, GPR11(r1)			/* Temporary stash */
+
+	/* Reset MSR RI so we can take SLB faults again */
+	li	r11, MSR_RI
+	mtmsrd	r11, 1
+
 	mfspr	r11, SPRN_PPR
 	HMT_MEDIUM
 
@@ -397,11 +406,6 @@ restore_gprs:
 	ld	r5, THREAD_TM_DSCR(r3)
 	ld	r6, THREAD_TM_PPR(r3)
 
-	/* Clear the MSR RI since we are about to change R1.  EE is already off
-	 */
-	li	r4, 0
-	mtmsrd	r4, 1
-
 	REST_GPR(0, r7)				/* GPR0 */
 	REST_2GPRS(2, r7)			/* GPR2-3 */
 	REST_GPR(4, r7)				/* GPR4 */
@@ -439,10 +443,33 @@ restore_gprs:
 	ld	r6, _CCR(r7)
 	mtcr    r6
 
-	REST_GPR(1, r7)				/* GPR1 */
-	REST_GPR(5, r7)				/* GPR5-7 */
 	REST_GPR(6, r7)
-	ld	r7, GPR7(r7)
+
+	/*
+	 * Store r1 and r5 on the stack so that we can access them
+	 * after we clear MSR RI.
+	 */
+
+	REST_GPR(5, r7)
+	std	r5, -8(r1)
+	ld	r5, GPR1(r7)
+	std	r5, -16(r1)
+
+	REST_GPR(7, r7)
+
+	/* Clear MSR RI since we are about to change r1. EE is already off */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/*
+	 * BE CAREFUL HERE:
+	 * At this point we can't take an SLB miss since we have MSR_RI
+	 * off. Load only to/from the stack/paca which are in SLB bolted regions
+	 * until we turn MSR RI back on.
+	 */
+
+	ld	r5, -8(r1)
+	ld	r1, -16(r1)
 
 	/* Commit register state as checkpointed state: */
 	TRECHKPT
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 5b22ba0b58bc..2971ea18c768 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -922,6 +922,10 @@ void __init hash__early_init_mmu(void)
 	vmemmap = (struct page *)H_VMEMMAP_BASE;
 	ioremap_bot = IOREMAP_BASE;
 
+#ifdef CONFIG_PCI
+	pci_io_base = ISA_IO_BASE;
+#endif
+
 	/* Initialize the MMU Hash table and create the linear mapping
 	 * of memory. Has to be done before SLB initialization as this is
 	 * currently where the page size encoding is obtained.
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index e58707deef5c..7931e1496f0d 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -328,6 +328,11 @@ void __init radix__early_init_mmu(void)
 	__vmalloc_end = RADIX_VMALLOC_END;
 	vmemmap = (struct page *)RADIX_VMEMMAP_BASE;
 	ioremap_bot = IOREMAP_BASE;
+
+#ifdef CONFIG_PCI
+	pci_io_base = ISA_IO_BASE;
+#endif
+
 	/*
 	 * For now radix also use the same frag size
 	 */
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 33787ee817f0..26ced536005a 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2319,7 +2319,7 @@ void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
-	const void __user *fp;
+	const unsigned long __user *fp;
 
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
@@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
 		return;
 
-	fp = (void __user *)regs->bp;
+	fp = (unsigned long __user *)regs->bp;
 
 	perf_callchain_store(entry, regs->ip);
 
@@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	pagefault_disable();
 	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
+
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, 16))
+		if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
 			break;
 
-		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+		bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
 		if (bytes != 0)
 			break;
-		bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
+		bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp));
 		if (bytes != 0)
 			break;
 
diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
index 3660b2cf245a..06c2baa51814 100644
--- a/arch/x86/events/intel/Makefile
+++ b/arch/x86/events/intel/Makefile
@@ -1,8 +1,8 @@
 obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o cqm.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl.o
-intel-rapl-objs				:= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl-perf.o
+intel-rapl-perf-objs			:= rapl.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
 intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7c666958a625..9b4f9d3ce465 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
 	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
+
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc6, 0xf),	/* FRONTEND_RETIRED.* */
+
 	EVENT_CONSTRAINT_END
 };
 
@@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index a147e676fc7b..e991d5c8bb3a 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -71,8 +71,8 @@ int amd_cache_northbridges(void)
 	while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
 		i++;
 
-	if (i == 0)
-		return 0;
+	if (!i)
+		return -ENODEV;
 
 	nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
 	if (!nb)
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index b2a4e2a61f6b..3cd69832d7f4 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -396,6 +396,7 @@ int __init pci_acpi_init(void)
 		return -ENODEV;
 
 	printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n");
+	acpi_irq_penalty_init();
 	pcibios_enable_irq = acpi_pci_irq_enable;
 	pcibios_disable_irq = acpi_pci_irq_disable;
 	x86_init.pci.init_irq = x86_init_noop;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 009947d419a6..f2b5e6a5cf95 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -19,6 +19,7 @@
 #include <asm/mtrr.h>
 #include <asm/sections.h>
 #include <asm/suspend.h>
+#include <asm/tlbflush.h>
 
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);
@@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void);
  * kernel's text (this value is passed in the image header).
  */
 unsigned long restore_jump_address __visible;
+unsigned long jump_address_phys;
 
 /*
  * Value of the cr3 register from before the hibernation (this value is passed
@@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible;
 
 pgd_t *temp_level4_pgt __visible;
 
-void *relocated_restore_code __visible;
+unsigned long relocated_restore_code __visible;
+
+static int set_up_temporary_text_mapping(void)
+{
+	pmd_t *pmd;
+	pud_t *pud;
+
+	/*
+	 * The new mapping only has to cover the page containing the image
+	 * kernel's entry point (jump_address_phys), because the switch over to
+	 * it is carried out by relocated code running from a page allocated
+	 * specifically for this purpose and covered by the identity mapping, so
+	 * the temporary kernel text mapping is only needed for the final jump.
+	 * Moreover, in that mapping the virtual address of the image kernel's
+	 * entry point must be the same as its virtual address in the image
+	 * kernel (restore_jump_address), so the image kernel's
+	 * restore_registers() code doesn't find itself in a different area of
+	 * the virtual address space after switching over to the original page
+	 * tables used by the image kernel.
+	 */
+	pud = (pud_t *)get_safe_page(GFP_ATOMIC);
+	if (!pud)
+		return -ENOMEM;
+
+	pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
+	if (!pmd)
+		return -ENOMEM;
+
+	set_pmd(pmd + pmd_index(restore_jump_address),
+		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
+	set_pud(pud + pud_index(restore_jump_address),
+		__pud(__pa(pmd) | _KERNPG_TABLE));
+	set_pgd(temp_level4_pgt + pgd_index(restore_jump_address),
+		__pgd(__pa(pud) | _KERNPG_TABLE));
+
+	return 0;
+}
 
 static void *alloc_pgt_page(void *context)
 {
@@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void)
 	if (!temp_level4_pgt)
 		return -ENOMEM;
 
-	/* It is safe to reuse the original kernel mapping */
-	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
-		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
+	/* Prepare a temporary mapping for the kernel text */
+	result = set_up_temporary_text_mapping();
+	if (result)
+		return result;
 
 	/* Set up the direct mapping from scratch */
 	for (i = 0; i < nr_pfn_mapped; i++) {
@@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void)
 	return 0;
 }
 
+static int relocate_restore_code(void)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	relocated_restore_code = get_safe_page(GFP_ATOMIC);
+	if (!relocated_restore_code)
+		return -ENOMEM;
+
+	memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE);
+
+	/* Make the page containing the relocated code executable */
+	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code);
+	pud = pud_offset(pgd, relocated_restore_code);
+	if (pud_large(*pud)) {
+		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+	} else {
+		pmd_t *pmd = pmd_offset(pud, relocated_restore_code);
+
+		if (pmd_large(*pmd)) {
+			set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		} else {
+			pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code);
+
+			set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+		}
+	}
+	__flush_tlb_all();
+
+	return 0;
+}
+
 int swsusp_arch_resume(void)
 {
 	int error;
 
 	/* We have got enough memory and from now on we cannot recover */
-	if ((error = set_up_temporary_mappings()))
+	error = set_up_temporary_mappings();
+	if (error)
 		return error;
 
-	relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC);
-	if (!relocated_restore_code)
-		return -ENOMEM;
-	memcpy(relocated_restore_code, &core_restore_code,
-	       &restore_registers - &core_restore_code);
+	error = relocate_restore_code();
+	if (error)
+		return error;
 
 	restore_image();
 	return 0;
@@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn)
 
 struct restore_data_record {
 	unsigned long jump_address;
+	unsigned long jump_address_phys;
 	unsigned long cr3;
 	unsigned long magic;
 };
 
-#define RESTORE_MAGIC	0x0123456789ABCDEFUL
+#define RESTORE_MAGIC	0x123456789ABCDEF0UL
 
 /**
  *	arch_hibernation_header_save - populate the architecture specific part
@@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
 
 	if (max_size < sizeof(struct restore_data_record))
 		return -EOVERFLOW;
-	rdr->jump_address = restore_jump_address;
+	rdr->jump_address = (unsigned long)&restore_registers;
+	rdr->jump_address_phys = __pa_symbol(&restore_registers);
 	rdr->cr3 = restore_cr3;
 	rdr->magic = RESTORE_MAGIC;
 	return 0;
@@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr)
 	struct restore_data_record *rdr = addr;
 
 	restore_jump_address = rdr->jump_address;
+	jump_address_phys = rdr->jump_address_phys;
 	restore_cr3 = rdr->cr3;
 	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
 }
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 4400a43b9e28..3177c2bc26f6 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend)
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	/* save the address of restore_registers */
-	movq	$restore_registers, %rax
-	movq	%rax, restore_jump_address(%rip)
 	/* save cr3 */
 	movq	%cr3, %rax
 	movq	%rax, restore_cr3(%rip)
@@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend)
 ENDPROC(swsusp_arch_suspend)
 
 ENTRY(restore_image)
-	/* switch to temporary page tables */
-	movq	$__PAGE_OFFSET, %rdx
-	movq	temp_level4_pgt(%rip), %rax
-	subq	%rdx, %rax
-	movq	%rax, %cr3
-	/* Flush TLB */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(X86_CR4_PGE), %rdx
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3;
-	movq	%rax, %cr4;  # turn PGE back on
-
 	/* prepare to jump to the image kernel */
-	movq	restore_jump_address(%rip), %rax
-	movq	restore_cr3(%rip), %rbx
+	movq	restore_jump_address(%rip), %r8
+	movq	restore_cr3(%rip), %r9
+
+	/* prepare to switch to temporary page tables */
+	movq	temp_level4_pgt(%rip), %rax
+	movq	mmu_cr4_features(%rip), %rbx
 
 	/* prepare to copy image data to their original locations */
 	movq	restore_pblist(%rip), %rdx
+
+	/* jump to relocated restore code */
 	movq	relocated_restore_code(%rip), %rcx
 	jmpq	*%rcx
 
 	/* code below has been relocated to a safe page */
 ENTRY(core_restore_code)
+	/* switch to temporary page tables */
+	movq	$__PAGE_OFFSET, %rcx
+	subq	%rcx, %rax
+	movq	%rax, %cr3
+	/* flush TLB */
+	movq	%rbx, %rcx
+	andq	$~(X86_CR4_PGE), %rcx
+	movq	%rcx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3;
+	movq	%rbx, %cr4;  # turn PGE back on
 .Lloop:
 	testq	%rdx, %rdx
 	jz	.Ldone
@@ -96,24 +96,17 @@ ENTRY(core_restore_code)
 	/* progress to the next pbe */
 	movq	pbe_next(%rdx), %rdx
 	jmp	.Lloop
+
 .Ldone:
 	/* jump to the restore_registers address from the image header */
-	jmpq	*%rax
-	/*
-	 * NOTE: This assumes that the boot kernel's text mapping covers the
-	 * image kernel's page containing restore_registers and the address of
-	 * this page is the same as in the image kernel's text mapping (it
-	 * should always be true, because the text mapping is linear, starting
-	 * from 0, and is supposed to cover the entire kernel text for every
-	 * kernel).
-	 *
-	 * code below belongs to the image kernel
-	 */
+	jmpq	*%r8
 
+	 /* code below belongs to the image kernel */
+	.align PAGE_SIZE
 ENTRY(restore_registers)
 	FRAME_BEGIN
 	/* go back to the original page tables */
-	movq    %rbx, %cr3
+	movq    %r9, %cr3
 
 	/* Flush TLB, including "global" things (vmalloc) */
 	movq	mmu_cr4_features(%rip), %rax
diff --git a/block/ioprio.c b/block/ioprio.c
index cc7800e9eb44..01b8116298a1 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -150,8 +150,10 @@ static int get_task_ioprio(struct task_struct *p)
 	if (ret)
 		goto out;
 	ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM);
+	task_lock(p);
 	if (p->io_context)
 		ret = p->io_context->ioprio;
+	task_unlock(p);
 out:
 	return ret;
 }
diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c
index 1f4128487dd4..dee86925a9a1 100644
--- a/drivers/acpi/acpi_dbg.c
+++ b/drivers/acpi/acpi_dbg.c
@@ -602,7 +602,7 @@ static int acpi_aml_read_user(char __user *buf, int len)
 	crc->tail = (crc->tail + n) & (ACPI_AML_BUF_SIZE - 1);
 	ret = n;
 out:
-	acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, !ret);
+	acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, ret >= 0);
 	return ret;
 }
 
@@ -672,7 +672,7 @@ static int acpi_aml_write_user(const char __user *buf, int len)
 	crc->head = (crc->head + n) & (ACPI_AML_BUF_SIZE - 1);
 	ret = n;
 out:
-	acpi_aml_unlock_fifo(ACPI_AML_IN_USER, !ret);
+	acpi_aml_unlock_fifo(ACPI_AML_IN_USER, ret >= 0);
 	return n;
 }
 
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index b5e2b0ada0ab..297f6aacd7d4 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -46,6 +46,7 @@
 #include "acnamesp.h"
 #include "acdispat.h"
 #include "actables.h"
+#include "acinterp.h"
 
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsload")
@@ -78,6 +79,8 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 
 	ACPI_FUNCTION_TRACE(ns_load_table);
 
+	acpi_ex_enter_interpreter();
+
 	/*
 	 * Parse the table and load the namespace with all named
 	 * objects found within. Control methods are NOT parsed
@@ -89,7 +92,7 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 	 */
 	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
 	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+		goto unlock_interp;
 	}
 
 	/* If table already loaded into namespace, just return */
@@ -130,6 +133,8 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 
 unlock:
 	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+unlock_interp:
+	(void)acpi_ex_exit_interpreter();
 
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index 1783cd7e1446..f631a47724f0 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -47,7 +47,6 @@
 #include "acparser.h"
 #include "acdispat.h"
 #include "actables.h"
-#include "acinterp.h"
 
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsparse")
@@ -171,8 +170,6 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 
 	ACPI_FUNCTION_TRACE(ns_parse_table);
 
-	acpi_ex_enter_interpreter();
-
 	/*
 	 * AML Parse, pass 1
 	 *
@@ -188,7 +185,7 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 	status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS1,
 					    table_index, start_node);
 	if (ACPI_FAILURE(status)) {
-		goto error_exit;
+		return_ACPI_STATUS(status);
 	}
 
 	/*
@@ -204,10 +201,8 @@ acpi_ns_parse_table(u32 table_index, struct acpi_namespace_node *start_node)
 	status = acpi_ns_one_complete_parse(ACPI_IMODE_LOAD_PASS2,
 					    table_index, start_node);
 	if (ACPI_FAILURE(status)) {
-		goto error_exit;
+		return_ACPI_STATUS(status);
 	}
 
-error_exit:
-	acpi_ex_exit_interpreter();
 	return_ACPI_STATUS(status);
 }
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 2215fc847fa9..ac6ddcc080d4 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -928,7 +928,7 @@ static ssize_t format_show(struct device *dev,
 {
 	struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev);
 
-	return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->code));
+	return sprintf(buf, "0x%04x\n", le16_to_cpu(dcr->code));
 }
 static DEVICE_ATTR_RO(format);
 
@@ -961,8 +961,8 @@ static ssize_t format1_show(struct device *dev,
 				continue;
 			if (nfit_dcr->dcr->code == dcr->code)
 				continue;
-			rc = sprintf(buf, "%#x\n",
-					be16_to_cpu(nfit_dcr->dcr->code));
+			rc = sprintf(buf, "0x%04x\n",
+					le16_to_cpu(nfit_dcr->dcr->code));
 			break;
 		}
 		if (rc != ENXIO)
@@ -1131,11 +1131,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 
 	/*
 	 * Until standardization materializes we need to consider up to 3
-	 * different command sets.  Note, that checking for function0 (bit0)
-	 * tells us if any commands are reachable through this uuid.
+	 * different command sets.  Note, that checking for zero functions
+	 * tells us if any commands might be reachable through this uuid.
 	 */
 	for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_HPE2; i++)
-		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
+		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 0))
 			break;
 
 	/* limit the supported commands to those that are publicly documented */
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 11cb38348aef..02b9ea1e8d2e 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -53,12 +53,12 @@ enum nfit_uuids {
 };
 
 /*
- * Region format interface codes are stored as an array of bytes in the
- * NFIT DIMM Control Region structure
+ * Region format interface codes are stored with the interface as the
+ * LSB and the function as the MSB.
  */
-#define NFIT_FIC_BYTE cpu_to_be16(0x101) /* byte-addressable energy backed */
-#define NFIT_FIC_BLK cpu_to_be16(0x201) /* block-addressable non-energy backed */
-#define NFIT_FIC_BYTEN cpu_to_be16(0x301) /* byte-addressable non-energy backed */
+#define NFIT_FIC_BYTE cpu_to_le16(0x101) /* byte-addressable energy backed */
+#define NFIT_FIC_BLK cpu_to_le16(0x201) /* block-addressable non-energy backed */
+#define NFIT_FIC_BYTEN cpu_to_le16(0x301) /* byte-addressable non-energy backed */
 
 enum {
 	NFIT_BLK_READ_FLUSH = 1,
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 8fc7323ed3e8..c983bf733ad3 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -470,6 +470,7 @@ static int acpi_irq_pci_sharing_penalty(int irq)
 {
 	struct acpi_pci_link *link;
 	int penalty = 0;
+	int i;
 
 	list_for_each_entry(link, &acpi_link_list, list) {
 		/*
@@ -478,18 +479,14 @@ static int acpi_irq_pci_sharing_penalty(int irq)
 		 */
 		if (link->irq.active && link->irq.active == irq)
 			penalty += PIRQ_PENALTY_PCI_USING;
-		else {
-			int i;
-
-			/*
-			 * If a link is inactive, penalize the IRQs it
-			 * might use, but not as severely.
-			 */
-			for (i = 0; i < link->irq.possible_count; i++)
-				if (link->irq.possible[i] == irq)
-					penalty += PIRQ_PENALTY_PCI_POSSIBLE /
-						link->irq.possible_count;
-		}
+
+		/*
+		 * penalize the IRQs PCI might use, but not as severely.
+		 */
+		for (i = 0; i < link->irq.possible_count; i++)
+			if (link->irq.possible[i] == irq)
+				penalty += PIRQ_PENALTY_PCI_POSSIBLE /
+					link->irq.possible_count;
 	}
 
 	return penalty;
@@ -499,9 +496,6 @@ static int acpi_irq_get_penalty(int irq)
 {
 	int penalty = 0;
 
-	if (irq < ACPI_MAX_ISA_IRQS)
-		penalty += acpi_isa_irq_penalty[irq];
-
 	/*
 	* Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict
 	* with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be
@@ -516,10 +510,49 @@ static int acpi_irq_get_penalty(int irq)
 			penalty += PIRQ_PENALTY_PCI_USING;
 	}
 
+	if (irq < ACPI_MAX_ISA_IRQS)
+		return penalty + acpi_isa_irq_penalty[irq];
+
 	penalty += acpi_irq_pci_sharing_penalty(irq);
 	return penalty;
 }
 
+int __init acpi_irq_penalty_init(void)
+{
+	struct acpi_pci_link *link;
+	int i;
+
+	/*
+	 * Update penalties to facilitate IRQ balancing.
+	 */
+	list_for_each_entry(link, &acpi_link_list, list) {
+
+		/*
+		 * reflect the possible and active irqs in the penalty table --
+		 * useful for breaking ties.
+		 */
+		if (link->irq.possible_count) {
+			int penalty =
+			    PIRQ_PENALTY_PCI_POSSIBLE /
+			    link->irq.possible_count;
+
+			for (i = 0; i < link->irq.possible_count; i++) {
+				if (link->irq.possible[i] < ACPI_MAX_ISA_IRQS)
+					acpi_isa_irq_penalty[link->irq.
+							 possible[i]] +=
+					    penalty;
+			}
+
+		} else if (link->irq.active &&
+				(link->irq.active < ACPI_MAX_ISA_IRQS)) {
+			acpi_isa_irq_penalty[link->irq.active] +=
+			    PIRQ_PENALTY_PCI_POSSIBLE;
+		}
+	}
+
+	return 0;
+}
+
 static int acpi_irq_balance = -1;	/* 0: static, 1: balance */
 
 static int acpi_pci_link_allocate(struct acpi_pci_link *link)
@@ -839,7 +872,7 @@ void acpi_penalize_isa_irq(int irq, int active)
 {
 	if ((irq >= 0) && (irq < ARRAY_SIZE(acpi_isa_irq_penalty)))
 		acpi_isa_irq_penalty[irq] = acpi_irq_get_penalty(irq) +
-			active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING;
+		  (active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING);
 }
 
 bool acpi_isa_irq_available(int irq)
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 22c09952e177..b4de130f2d57 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -680,9 +680,6 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs)
 	u64 mask = 0;
 	union acpi_object *obj;
 
-	if (funcs == 0)
-		return false;
-
 	obj = acpi_evaluate_dsm(handle, uuid, rev, 0, NULL);
 	if (!obj)
 		return false;
@@ -695,6 +692,9 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, u64 rev, u64 funcs)
 			mask |= (((u64)obj->buffer.pointer[i]) << (i * 8));
 	ACPI_FREE(obj);
 
+	if (funcs == 0)
+		return true;
+
 	/*
 	 * Bit 0 indicates whether there's support for any functions other than
 	 * function 0 for the specified UUID and revision.
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 2e6d1e9c3345..fcc5b4e0aef2 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -207,6 +207,9 @@ struct blkfront_info
 	struct blk_mq_tag_set tag_set;
 	struct blkfront_ring_info *rinfo;
 	unsigned int nr_rings;
+	/* Save uncomplete reqs and bios for migration. */
+	struct list_head requests;
+	struct bio_list bio_list;
 };
 
 static unsigned int nr_minors;
@@ -2002,69 +2005,22 @@ static int blkif_recover(struct blkfront_info *info)
 {
 	unsigned int i, r_index;
 	struct request *req, *n;
-	struct blk_shadow *copy;
 	int rc;
 	struct bio *bio, *cloned_bio;
-	struct bio_list bio_list, merge_bio;
 	unsigned int segs, offset;
 	int pending, size;
 	struct split_bio *split_bio;
-	struct list_head requests;
 
 	blkfront_gather_backend_features(info);
 	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
 	blk_queue_max_segments(info->rq, segs);
-	bio_list_init(&bio_list);
-	INIT_LIST_HEAD(&requests);
 
 	for (r_index = 0; r_index < info->nr_rings; r_index++) {
-		struct blkfront_ring_info *rinfo;
-
-		rinfo = &info->rinfo[r_index];
-		/* Stage 1: Make a safe copy of the shadow state. */
-		copy = kmemdup(rinfo->shadow, sizeof(rinfo->shadow),
-			       GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
-		if (!copy)
-			return -ENOMEM;
-
-		/* Stage 2: Set up free list. */
-		memset(&rinfo->shadow, 0, sizeof(rinfo->shadow));
-		for (i = 0; i < BLK_RING_SIZE(info); i++)
-			rinfo->shadow[i].req.u.rw.id = i+1;
-		rinfo->shadow_free = rinfo->ring.req_prod_pvt;
-		rinfo->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
+		struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
 
 		rc = blkfront_setup_indirect(rinfo);
-		if (rc) {
-			kfree(copy);
+		if (rc)
 			return rc;
-		}
-
-		for (i = 0; i < BLK_RING_SIZE(info); i++) {
-			/* Not in use? */
-			if (!copy[i].request)
-				continue;
-
-			/*
-			 * Get the bios in the request so we can re-queue them.
-			 */
-			if (copy[i].request->cmd_flags &
-			    (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
-				/*
-				 * Flush operations don't contain bios, so
-				 * we need to requeue the whole request
-				 */
-				list_add(&copy[i].request->queuelist, &requests);
-				continue;
-			}
-			merge_bio.head = copy[i].request->bio;
-			merge_bio.tail = copy[i].request->biotail;
-			bio_list_merge(&bio_list, &merge_bio);
-			copy[i].request->bio = NULL;
-			blk_end_request_all(copy[i].request, 0);
-		}
-
-		kfree(copy);
 	}
 	xenbus_switch_state(info->xbdev, XenbusStateConnected);
 
@@ -2079,7 +2035,7 @@ static int blkif_recover(struct blkfront_info *info)
 		kick_pending_request_queues(rinfo);
 	}
 
-	list_for_each_entry_safe(req, n, &requests, queuelist) {
+	list_for_each_entry_safe(req, n, &info->requests, queuelist) {
 		/* Requeue pending requests (flush or discard) */
 		list_del_init(&req->queuelist);
 		BUG_ON(req->nr_phys_segments > segs);
@@ -2087,7 +2043,7 @@ static int blkif_recover(struct blkfront_info *info)
 	}
 	blk_mq_kick_requeue_list(info->rq);
 
-	while ((bio = bio_list_pop(&bio_list)) != NULL) {
+	while ((bio = bio_list_pop(&info->bio_list)) != NULL) {
 		/* Traverse the list of pending bios and re-queue them */
 		if (bio_segments(bio) > segs) {
 			/*
@@ -2133,9 +2089,42 @@ static int blkfront_resume(struct xenbus_device *dev)
 {
 	struct blkfront_info *info = dev_get_drvdata(&dev->dev);
 	int err = 0;
+	unsigned int i, j;
 
 	dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename);
 
+	bio_list_init(&info->bio_list);
+	INIT_LIST_HEAD(&info->requests);
+	for (i = 0; i < info->nr_rings; i++) {
+		struct blkfront_ring_info *rinfo = &info->rinfo[i];
+		struct bio_list merge_bio;
+		struct blk_shadow *shadow = rinfo->shadow;
+
+		for (j = 0; j < BLK_RING_SIZE(info); j++) {
+			/* Not in use? */
+			if (!shadow[j].request)
+				continue;
+
+			/*
+			 * Get the bios in the request so we can re-queue them.
+			 */
+			if (shadow[j].request->cmd_flags &
+					(REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+				/*
+				 * Flush operations don't contain bios, so
+				 * we need to requeue the whole request
+				 */
+				list_add(&shadow[j].request->queuelist, &info->requests);
+				continue;
+			}
+			merge_bio.head = shadow[j].request->bio;
+			merge_bio.tail = shadow[j].request->biotail;
+			bio_list_merge(&info->bio_list, &merge_bio);
+			shadow[j].request->bio = NULL;
+			blk_mq_end_request(shadow[j].request, 0);
+		}
+	}
+
 	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
 
 	err = negotiate_mq(info);
diff --git a/drivers/clk/clk-oxnas.c b/drivers/clk/clk-oxnas.c
index efba7d4dbcfc..79bcb2e42060 100644
--- a/drivers/clk/clk-oxnas.c
+++ b/drivers/clk/clk-oxnas.c
@@ -144,9 +144,9 @@ static int oxnas_stdclk_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	regmap = syscon_node_to_regmap(of_get_parent(np));
-	if (!regmap) {
+	if (IS_ERR(regmap)) {
 		dev_err(&pdev->dev, "failed to have parent regmap\n");
-		return -EINVAL;
+		return PTR_ERR(regmap);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(clk_oxnas_init); i++) {
diff --git a/drivers/clk/rockchip/clk-cpu.c b/drivers/clk/rockchip/clk-cpu.c
index 4bb130cd0062..05b3d73bfefa 100644
--- a/drivers/clk/rockchip/clk-cpu.c
+++ b/drivers/clk/rockchip/clk-cpu.c
@@ -321,9 +321,9 @@ struct clk *rockchip_clk_register_cpuclk(const char *name,
 	}
 
 	cclk = clk_register(NULL, &cpuclk->hw);
-	if (IS_ERR(clk)) {
+	if (IS_ERR(cclk)) {
 		pr_err("%s: could not register cpuclk %s\n", __func__,	name);
-		ret = PTR_ERR(clk);
+		ret = PTR_ERR(cclk);
 		goto free_rate_table;
 	}
 
diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c
index bc856f21f6b2..077fcdc7908b 100644
--- a/drivers/clk/rockchip/clk-mmc-phase.c
+++ b/drivers/clk/rockchip/clk-mmc-phase.c
@@ -41,8 +41,6 @@ static unsigned long rockchip_mmc_recalc(struct clk_hw *hw,
 #define ROCKCHIP_MMC_DEGREE_MASK 0x3
 #define ROCKCHIP_MMC_DELAYNUM_OFFSET 2
 #define ROCKCHIP_MMC_DELAYNUM_MASK (0xff << ROCKCHIP_MMC_DELAYNUM_OFFSET)
-#define ROCKCHIP_MMC_INIT_STATE_RESET 0x1
-#define ROCKCHIP_MMC_INIT_STATE_SHIFT 1
 
 #define PSECS_PER_SEC 1000000000000LL
 
@@ -154,6 +152,7 @@ struct clk *rockchip_clk_register_mmc(const char *name,
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
+	init.flags = 0;
 	init.num_parents = num_parents;
 	init.parent_names = parent_names;
 	init.ops = &rockchip_mmc_clk_ops;
@@ -162,15 +161,6 @@ struct clk *rockchip_clk_register_mmc(const char *name,
 	mmc_clock->reg = reg;
 	mmc_clock->shift = shift;
 
-	/*
-	 * Assert init_state to soft reset the CLKGEN
-	 * for mmc tuning phase and degree
-	 */
-	if (mmc_clock->shift == ROCKCHIP_MMC_INIT_STATE_SHIFT)
-		writel(HIWORD_UPDATE(ROCKCHIP_MMC_INIT_STATE_RESET,
-				     ROCKCHIP_MMC_INIT_STATE_RESET,
-				     mmc_clock->shift), mmc_clock->reg);
-
 	clk = clk_register(NULL, &mmc_clock->hw);
 	if (IS_ERR(clk))
 		kfree(mmc_clock);
diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c
index 291543f52caa..8059a8d3ea36 100644
--- a/drivers/clk/rockchip/clk-rk3399.c
+++ b/drivers/clk/rockchip/clk-rk3399.c
@@ -832,9 +832,9 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = {
 			RK3399_CLKGATE_CON(13), 1, GFLAGS),
 
 	/* perihp */
-	GATE(0, "cpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED,
+	GATE(0, "cpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED,
 			RK3399_CLKGATE_CON(5), 0, GFLAGS),
-	GATE(0, "gpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED,
+	GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED,
 			RK3399_CLKGATE_CON(5), 1, GFLAGS),
 	COMPOSITE(ACLK_PERIHP, "aclk_perihp", mux_aclk_perihp_p, CLK_IGNORE_UNUSED,
 			RK3399_CLKSEL_CON(14), 7, 1, MFLAGS, 0, 5, DFLAGS,
@@ -1466,6 +1466,8 @@ static struct rockchip_clk_branch rk3399_clk_pmu_branches[] __initdata = {
 
 static const char *const rk3399_cru_critical_clocks[] __initconst = {
 	"aclk_cci_pre",
+	"aclk_gic",
+	"aclk_gic_noc",
 	"pclk_perilp0",
 	"pclk_perilp0",
 	"hclk_perilp0",
@@ -1508,6 +1510,7 @@ static void __init rk3399_clk_init(struct device_node *np)
 	ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
 	if (IS_ERR(ctx)) {
 		pr_err("%s: rockchip clk init failed\n", __func__);
+		iounmap(reg_base);
 		return;
 	}
 
@@ -1553,6 +1556,7 @@ static void __init rk3399_pmu_clk_init(struct device_node *np)
 	ctx = rockchip_clk_init(np, reg_base, CLKPMU_NR_CLKS);
 	if (IS_ERR(ctx)) {
 		pr_err("%s: rockchip pmu clk init failed\n", __func__);
+		iounmap(reg_base);
 		return;
 	}
 
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 3646b143bbf5..0bb44d5b5df4 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -79,15 +79,16 @@ static const struct of_device_id machines[] __initconst = {
 static int __init cpufreq_dt_platdev_init(void)
 {
 	struct device_node *np = of_find_node_by_path("/");
+	const struct of_device_id *match;
 
 	if (!np)
 		return -ENODEV;
 
-	if (!of_match_node(machines, np))
+	match = of_match_node(machines, np);
+	of_node_put(np);
+	if (!match)
 		return -ENODEV;
 
-	of_node_put(of_root);
-
 	return PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt", -1,
 							       NULL, 0));
 }
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 9009295f5134..5617c7087d77 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2261,6 +2261,10 @@ int cpufreq_update_policy(unsigned int cpu)
 	 * -> ask driver for current freq and notify governors about a change
 	 */
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
+		if (cpufreq_suspended) {
+			ret = -EAGAIN;
+			goto unlock;
+		}
 		new_policy.cur = cpufreq_update_current_freq(policy);
 		if (WARN_ON(!new_policy.cur)) {
 			ret = -EIO;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index fe9dc17ea873..1fa1a32928d7 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1400,6 +1400,9 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
 {
 	struct cpudata *cpu = all_cpu_data[cpu_num];
 
+	if (cpu->update_util_set)
+		return;
+
 	/* Prevent intel_pstate_update_util() from using stale data. */
 	cpu->sample.time = 0;
 	cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
@@ -1440,8 +1443,6 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
 
-	intel_pstate_clear_update_util_hook(policy->cpu);
-
 	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
 		 policy->cpuinfo.max_freq, policy->max);
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index a4d0059e232c..c73207abb5a4 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -173,7 +173,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 
 	struct cpuidle_state *target_state = &drv->states[index];
 	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
-	u64 time_start, time_end;
+	ktime_t time_start, time_end;
 	s64 diff;
 
 	/*
@@ -195,13 +195,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	sched_idle_set_state(target_state);
 
 	trace_cpu_idle_rcuidle(index, dev->cpu);
-	time_start = local_clock();
+	time_start = ns_to_ktime(local_clock());
 
 	stop_critical_timings();
 	entered_state = target_state->enter(dev, drv, index);
 	start_critical_timings();
 
-	time_end = local_clock();
+	time_end = ns_to_ktime(local_clock());
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
 	/* The cpu is no longer idle or about to enter idle. */
@@ -217,11 +217,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	if (!cpuidle_state_is_coupled(drv, index))
 		local_irq_enable();
 
-	/*
-	 * local_clock() returns the time in nanosecond, let's shift
-	 * by 10 (divide by 1024) to have microsecond based time.
-	 */
-	diff = (time_end - time_start) >> 10;
+	diff = ktime_us_delta(time_end, time_start);
 	if (diff > INT_MAX)
 		diff = INT_MAX;
 
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index cebcb405812e..536112fd2466 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -49,7 +49,7 @@ config GPIO_DEVRES
 
 config OF_GPIO
 	def_bool y
-	depends on OF || COMPILE_TEST
+	depends on OF
 
 config GPIO_ACPI
 	def_bool y
diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c
index e85e7539cf5d..eb43ae4835c1 100644
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@@ -61,9 +61,8 @@ static unsigned sch_gpio_bit(struct sch_gpio *sch, unsigned gpio)
 	return gpio % 8;
 }
 
-static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg)
+static int sch_gpio_reg_get(struct sch_gpio *sch, unsigned gpio, unsigned reg)
 {
-	struct sch_gpio *sch = gpiochip_get_data(gc);
 	unsigned short offset, bit;
 	u8 reg_val;
 
@@ -75,10 +74,9 @@ static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg)
 	return reg_val;
 }
 
-static void sch_gpio_reg_set(struct gpio_chip *gc, unsigned gpio, unsigned reg,
+static void sch_gpio_reg_set(struct sch_gpio *sch, unsigned gpio, unsigned reg,
 			     int val)
 {
-	struct sch_gpio *sch = gpiochip_get_data(gc);
 	unsigned short offset, bit;
 	u8 reg_val;
 
@@ -98,14 +96,15 @@ static int sch_gpio_direction_in(struct gpio_chip *gc, unsigned gpio_num)
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GIO, 1);
+	sch_gpio_reg_set(sch, gpio_num, GIO, 1);
 	spin_unlock(&sch->lock);
 	return 0;
 }
 
 static int sch_gpio_get(struct gpio_chip *gc, unsigned gpio_num)
 {
-	return sch_gpio_reg_get(gc, gpio_num, GLV);
+	struct sch_gpio *sch = gpiochip_get_data(gc);
+	return sch_gpio_reg_get(sch, gpio_num, GLV);
 }
 
 static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val)
@@ -113,7 +112,7 @@ static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val)
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GLV, val);
+	sch_gpio_reg_set(sch, gpio_num, GLV, val);
 	spin_unlock(&sch->lock);
 }
 
@@ -123,7 +122,7 @@ static int sch_gpio_direction_out(struct gpio_chip *gc, unsigned gpio_num,
 	struct sch_gpio *sch = gpiochip_get_data(gc);
 
 	spin_lock(&sch->lock);
-	sch_gpio_reg_set(gc, gpio_num, GIO, 0);
+	sch_gpio_reg_set(sch, gpio_num, GIO, 0);
 	spin_unlock(&sch->lock);
 
 	/*
@@ -182,13 +181,13 @@ static int sch_gpio_probe(struct platform_device *pdev)
 		 * GPIO7 is configured by the CMC as SLPIOVR
 		 * Enable GPIO[9:8] core powered gpios explicitly
 		 */
-		sch_gpio_reg_set(&sch->chip, 8, GEN, 1);
-		sch_gpio_reg_set(&sch->chip, 9, GEN, 1);
+		sch_gpio_reg_set(sch, 8, GEN, 1);
+		sch_gpio_reg_set(sch, 9, GEN, 1);
 		/*
 		 * SUS_GPIO[2:0] enabled by default
 		 * Enable SUS_GPIO3 resume powered gpio explicitly
 		 */
-		sch_gpio_reg_set(&sch->chip, 13, GEN, 1);
+		sch_gpio_reg_set(sch, 13, GEN, 1);
 		break;
 
 	case PCI_DEVICE_ID_INTEL_ITC_LPC:
diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c
index 3a5c7011ad3b..8b830996fe02 100644
--- a/drivers/gpio/gpiolib-legacy.c
+++ b/drivers/gpio/gpiolib-legacy.c
@@ -28,6 +28,10 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 	if (!desc && gpio_is_valid(gpio))
 		return -EPROBE_DEFER;
 
+	err = gpiod_request(desc, label);
+	if (err)
+		return err;
+
 	if (flags & GPIOF_OPEN_DRAIN)
 		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
 
@@ -37,10 +41,6 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 	if (flags & GPIOF_ACTIVE_LOW)
 		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
-	err = gpiod_request(desc, label);
-	if (err)
-		return err;
-
 	if (flags & GPIOF_DIR_IN)
 		err = gpiod_direction_input(desc);
 	else
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 570771ed19e6..be74bd370f1f 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1352,14 +1352,6 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label)
 		spin_lock_irqsave(&gpio_lock, flags);
 	}
 done:
-	if (status < 0) {
-		/* Clear flags that might have been set by the caller before
-		 * requesting the GPIO.
-		 */
-		clear_bit(FLAG_ACTIVE_LOW, &desc->flags);
-		clear_bit(FLAG_OPEN_DRAIN, &desc->flags);
-		clear_bit(FLAG_OPEN_SOURCE, &desc->flags);
-	}
 	spin_unlock_irqrestore(&gpio_lock, flags);
 	return status;
 }
@@ -2587,28 +2579,13 @@ struct gpio_desc *__must_check gpiod_get_optional(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(gpiod_get_optional);
 
-/**
- * gpiod_parse_flags - helper function to parse GPIO lookup flags
- * @desc:	gpio to be setup
- * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
- *		of_get_gpio_hog()
- *
- * Set the GPIO descriptor flags based on the given GPIO lookup flags.
- */
-static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags)
-{
-	if (lflags & GPIO_ACTIVE_LOW)
-		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
-	if (lflags & GPIO_OPEN_DRAIN)
-		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
-	if (lflags & GPIO_OPEN_SOURCE)
-		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
-}
 
 /**
  * gpiod_configure_flags - helper function to configure a given GPIO
  * @desc:	gpio whose value will be assigned
  * @con_id:	function within the GPIO consumer
+ * @lflags:	gpio_lookup_flags - returned from of_find_gpio() or
+ *		of_get_gpio_hog()
  * @dflags:	gpiod_flags - optional GPIO initialization flags
  *
  * Return 0 on success, -ENOENT if no GPIO has been assigned to the
@@ -2616,10 +2593,17 @@ static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags)
  * occurred while trying to acquire the GPIO.
  */
 static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
-				 enum gpiod_flags dflags)
+		unsigned long lflags, enum gpiod_flags dflags)
 {
 	int status;
 
+	if (lflags & GPIO_ACTIVE_LOW)
+		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
+	if (lflags & GPIO_OPEN_DRAIN)
+		set_bit(FLAG_OPEN_DRAIN, &desc->flags);
+	if (lflags & GPIO_OPEN_SOURCE)
+		set_bit(FLAG_OPEN_SOURCE, &desc->flags);
+
 	/* No particular flag request, return here... */
 	if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) {
 		pr_debug("no flags found for %s\n", con_id);
@@ -2686,13 +2670,11 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
 		return desc;
 	}
 
-	gpiod_parse_flags(desc, lookupflags);
-
 	status = gpiod_request(desc, con_id);
 	if (status < 0)
 		return ERR_PTR(status);
 
-	status = gpiod_configure_flags(desc, con_id, flags);
+	status = gpiod_configure_flags(desc, con_id, lookupflags, flags);
 	if (status < 0) {
 		dev_dbg(dev, "setup of GPIO %s failed\n", con_id);
 		gpiod_put(desc);
@@ -2748,6 +2730,10 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
 	if (IS_ERR(desc))
 		return desc;
 
+	ret = gpiod_request(desc, NULL);
+	if (ret)
+		return ERR_PTR(ret);
+
 	if (active_low)
 		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
@@ -2758,10 +2744,6 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
 			set_bit(FLAG_OPEN_SOURCE, &desc->flags);
 	}
 
-	ret = gpiod_request(desc, NULL);
-	if (ret)
-		return ERR_PTR(ret);
-
 	return desc;
 }
 EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod);
@@ -2814,8 +2796,6 @@ int gpiod_hog(struct gpio_desc *desc, const char *name,
 	chip = gpiod_to_chip(desc);
 	hwnum = gpio_chip_hwgpio(desc);
 
-	gpiod_parse_flags(desc, lflags);
-
 	local_desc = gpiochip_request_own_desc(chip, hwnum, name);
 	if (IS_ERR(local_desc)) {
 		status = PTR_ERR(local_desc);
@@ -2824,7 +2804,7 @@ int gpiod_hog(struct gpio_desc *desc, const char *name,
 		return status;
 	}
 
-	status = gpiod_configure_flags(desc, name, dflags);
+	status = gpiod_configure_flags(desc, name, lflags, dflags);
 	if (status < 0) {
 		pr_err("setup of hog GPIO %s (chip %s, offset %d) failed, %d\n",
 		       name, chip->label, hwnum, status);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index e19520c4b4b6..d9c88d13f8db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -1106,6 +1106,10 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 	if (fences == 0 && handles == 0) {
 		if (adev->pm.dpm_enabled) {
 			amdgpu_dpm_enable_uvd(adev, false);
+			/* just work around for uvd clock remain high even
+			 * when uvd dpm disabled on Polaris10 */
+			if (adev->asic_type == CHIP_POLARIS10)
+				amdgpu_asic_set_uvd_clocks(adev, 0, 0);
 		} else {
 			amdgpu_asic_set_uvd_clocks(adev, 0, 0);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 1a5cbaff1e34..b2ebd4fef6cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -47,6 +47,8 @@
 #include "dce/dce_10_0_d.h"
 #include "dce/dce_10_0_sh_mask.h"
 
+#include "smu/smu_7_1_3_d.h"
+
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_NUM_COMPUTE_RINGS 8
 
@@ -693,6 +695,7 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev)
 		amdgpu_program_register_sequence(adev,
 						 polaris10_golden_common_all,
 						 (const u32)ARRAY_SIZE(polaris10_golden_common_all));
+		WREG32_SMC(ixCG_ACLK_CNTL, 0x0000001C);
 		break;
 	case CHIP_CARRIZO:
 		amdgpu_program_register_sequence(adev,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
index 64ee78f7d41e..91e25f942d90 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
@@ -732,7 +732,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			table->Smio[level] |=
 				data->mvdd_voltage_table.entries[level].smio_low;
 		}
-		table->SmioMask2 = data->vddci_voltage_table.mask_low;
+		table->SmioMask2 = data->mvdd_voltage_table.mask_low;
 
 		table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count);
 	}
@@ -1422,22 +1422,19 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 
 	table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
 
-	if (!data->sclk_dpm_key_disabled) {
-		/* Get MinVoltage and Frequency from DPM0,
-		 * already converted to SMC_UL */
-		sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value;
-		result = polaris10_get_dependency_volt_by_clk(hwmgr,
-				table_info->vdd_dep_on_sclk,
-				table->ACPILevel.SclkFrequency,
-				&table->ACPILevel.MinVoltage, &mvdd);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"Cannot find ACPI VDDC voltage value "
-				"in Clock Dependency Table", );
-	} else {
-		sclk_frequency = data->vbios_boot_state.sclk_bootup_value;
-		table->ACPILevel.MinVoltage =
-				data->vbios_boot_state.vddc_bootup_value * VOLTAGE_SCALE;
-	}
+
+	/* Get MinVoltage and Frequency from DPM0,
+	 * already converted to SMC_UL */
+	sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value;
+	result = polaris10_get_dependency_volt_by_clk(hwmgr,
+			table_info->vdd_dep_on_sclk,
+			sclk_frequency,
+			&table->ACPILevel.MinVoltage, &mvdd);
+	PP_ASSERT_WITH_CODE((0 == result),
+			"Cannot find ACPI VDDC voltage value "
+			"in Clock Dependency Table",
+			);
+
 
 	result = polaris10_calculate_sclk_params(hwmgr, sclk_frequency,  &(table->ACPILevel.SclkSetting));
 	PP_ASSERT_WITH_CODE(result == 0, "Error retrieving Engine Clock dividers from VBIOS.", return result);
@@ -1462,24 +1459,18 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw1_frac);
 	CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Sclk_ss_slew_rate);
 
-	if (!data->mclk_dpm_key_disabled) {
-		/* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */
-		table->MemoryACPILevel.MclkFrequency =
-				data->dpm_table.mclk_table.dpm_levels[0].value;
-		result = polaris10_get_dependency_volt_by_clk(hwmgr,
-				table_info->vdd_dep_on_mclk,
-				table->MemoryACPILevel.MclkFrequency,
-				&table->MemoryACPILevel.MinVoltage, &mvdd);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"Cannot find ACPI VDDCI voltage value "
-				"in Clock Dependency Table",
-				);
-	} else {
-		table->MemoryACPILevel.MclkFrequency =
-				data->vbios_boot_state.mclk_bootup_value;
-		table->MemoryACPILevel.MinVoltage =
-				data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE;
-	}
+
+	/* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */
+	table->MemoryACPILevel.MclkFrequency =
+			data->dpm_table.mclk_table.dpm_levels[0].value;
+	result = polaris10_get_dependency_volt_by_clk(hwmgr,
+			table_info->vdd_dep_on_mclk,
+			table->MemoryACPILevel.MclkFrequency,
+			&table->MemoryACPILevel.MinVoltage, &mvdd);
+	PP_ASSERT_WITH_CODE((0 == result),
+			"Cannot find ACPI VDDCI voltage value "
+			"in Clock Dependency Table",
+			);
 
 	us_mvdd = 0;
 	if ((POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
@@ -1524,6 +1515,7 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
 	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
 			table_info->mm_dep_table;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
 
 	table->VceLevelCount = (uint8_t)(mm_table->count);
 	table->VceBootLevel = 0;
@@ -1533,9 +1525,18 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
 		table->VceLevel[count].MinVoltage = 0;
 		table->VceLevel[count].MinVoltage |=
 				(mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
+
+		if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+
 		table->VceLevel[count].MinVoltage |=
-				((mm_table->entries[count].vddc - data->vddc_vddci_delta) *
-						VOLTAGE_SCALE) << VDDCI_SHIFT;
+				(vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
 		table->VceLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
 
 		/*retrieve divider value for VBIOS */
@@ -1564,6 +1565,7 @@ static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
 	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
 			table_info->mm_dep_table;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
 
 	table->SamuBootLevel = 0;
 	table->SamuLevelCount = (uint8_t)(mm_table->count);
@@ -1574,8 +1576,16 @@ static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
 		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
 		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
 				VOLTAGE_SCALE) << VDDC_SHIFT;
-		table->SamuLevel[count].MinVoltage |= ((mm_table->entries[count].vddc -
-				data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
 		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
 
 		/* retrieve divider value for VBIOS */
@@ -1658,6 +1668,7 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr,
 	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
 			table_info->mm_dep_table;
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+	uint32_t vddci;
 
 	table->UvdLevelCount = (uint8_t)(mm_table->count);
 	table->UvdBootLevel = 0;
@@ -1668,8 +1679,16 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr,
 		table->UvdLevel[count].DclkFrequency = mm_table->entries[count].dclk;
 		table->UvdLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
 				VOLTAGE_SCALE) << VDDC_SHIFT;
-		table->UvdLevel[count].MinVoltage |= ((mm_table->entries[count].vddc -
-				data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
+			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
+						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
+		else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
+			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
+		else
+			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
+
+		table->UvdLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
 		table->UvdLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
 
 		/* retrieve divider value for VBIOS */
@@ -1690,8 +1709,8 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr,
 		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].VclkFrequency);
 		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].DclkFrequency);
 		CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].MinVoltage);
-
 	}
+
 	return result;
 }
 
@@ -1791,20 +1810,26 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 	for (i = 0; i < sclk_table->count; i++) {
 		data->smc_state_table.Sclk_CKS_masterEn0_7 |=
 				sclk_table->entries[i].cks_enable << i;
-
-		volt_without_cks =  (uint32_t)(((ro - 40) * 1000 - 2753594 - sclk_table->entries[i].clk/100 * 136418 /1000) / \
-					(sclk_table->entries[i].clk/100 * 1132925 /10000 - 242418)/100);
-
-		volt_with_cks = (uint32_t)((ro * 1000 -2396351 - sclk_table->entries[i].clk/100 * 329021/1000) / \
-				(sclk_table->entries[i].clk/10000 * 649434 /1000  - 18005)/10);
+		if (hwmgr->chip_id == CHIP_POLARIS10) {
+			volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \
+						(2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000));
+			volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 * 3232 - (ro - 65) * 1000000) / \
+					(2522480 - sclk_table->entries[i].clk/100 * 115764/100));
+		} else {
+			volt_without_cks = (uint32_t)((2416794800U + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \
+						(2625416 - (sclk_table->entries[i].clk/100) * (12586807/10000)));
+			volt_with_cks = (uint32_t)((2999656000U - sclk_table->entries[i].clk/100 * 392803 - (ro - 44) * 1000000) / \
+					(3422454 - sclk_table->entries[i].clk/100 * (18886376/10000)));
+		}
 
 		if (volt_without_cks >= volt_with_cks)
 			volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks +
-					sclk_table->entries[i].cks_voffset) * 100 / 625) + 1);
+					sclk_table->entries[i].cks_voffset) * 100 + 624) / 625);
 
 		data->smc_state_table.Sclk_voltageOffset[i] = volt_offset;
 	}
 
+	data->smc_state_table.LdoRefSel = (table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ? table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 6;
 	/* Populate CKS Lookup Table */
 	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
 		stretch_amount2 = 0;
@@ -2487,6 +2512,8 @@ int polaris10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to enable VR hot GPIO interrupt!", result = tmp_result);
 
+	smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay);
+
 	tmp_result = polaris10_enable_sclk_control(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to enable SCLK control!", result = tmp_result);
@@ -2655,7 +2682,7 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
 	uint16_t vv_id;
-	uint16_t vddc = 0;
+	uint32_t vddc = 0;
 	uint16_t i, j;
 	uint32_t sclk = 0;
 	struct phm_ppt_v1_information *table_info =
@@ -2686,8 +2713,9 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr)
 						continue);
 
 
-			/* need to make sure vddc is less than 2v or else, it could burn the ASIC. */
-			PP_ASSERT_WITH_CODE((vddc < 2000 && vddc != 0),
+			/* need to make sure vddc is less than 2v or else, it could burn the ASIC.
+			 * real voltage level in unit of 0.01mv */
+			PP_ASSERT_WITH_CODE((vddc < 200000 && vddc != 0),
 					"Invalid VDDC value", result = -EINVAL;);
 
 			/* the voltage should not be zero nor equal to leakage ID */
@@ -2913,6 +2941,31 @@ static int polaris10_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+int polaris10_patch_voltage_workaround(struct pp_hwmgr *hwmgr)
+{
+	struct phm_ppt_v1_information *table_info =
+		       (struct phm_ppt_v1_information *)(hwmgr->pptable);
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_mclk_table =
+			table_info->vdd_dep_on_mclk;
+	struct phm_ppt_v1_voltage_lookup_table *lookup_table =
+			table_info->vddc_lookup_table;
+	uint32_t i;
+
+	if (hwmgr->chip_id == CHIP_POLARIS10 && hwmgr->hw_revision == 0xC7) {
+		if (lookup_table->entries[dep_mclk_table->entries[dep_mclk_table->count-1].vddInd].us_vdd >= 1000)
+			return 0;
+
+		for (i = 0; i < lookup_table->count; i++) {
+			if (lookup_table->entries[i].us_vdd < 0xff01 && lookup_table->entries[i].us_vdd >= 1000) {
+				dep_mclk_table->entries[dep_mclk_table->count-1].vddInd = (uint8_t) i;
+				return 0;
+			}
+		}
+	}
+	return 0;
+}
+
+
 int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
@@ -2990,6 +3043,7 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 
 	polaris10_set_features_platform_caps(hwmgr);
 
+	polaris10_patch_voltage_workaround(hwmgr);
 	polaris10_init_dpm_defaults(hwmgr);
 
 	/* Get leakage voltage based on leakage ID. */
@@ -4359,6 +4413,15 @@ static int polaris10_notify_link_speed_change_after_state_change(
 	return 0;
 }
 
+static int polaris10_notify_smc_display(struct pp_hwmgr *hwmgr)
+{
+	struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend);
+
+	smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+		(PPSMC_Msg)PPSMC_MSG_SetVBITimeout, data->frame_time_x2);
+	return (smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay) == 0) ?  0 : -EINVAL;
+}
+
 static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input)
 {
 	int tmp_result, result = 0;
@@ -4407,6 +4470,11 @@ static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *i
 			"Failed to program memory timing parameters!",
 			result = tmp_result);
 
+	tmp_result = polaris10_notify_smc_display(hwmgr);
+	PP_ASSERT_WITH_CODE((0 == tmp_result),
+			"Failed to notify smc display settings!",
+			result = tmp_result);
+
 	tmp_result = polaris10_unfreeze_sclk_mclk_dpm(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to unfreeze SCLK MCLK DPM!",
@@ -4441,6 +4509,7 @@ static int polaris10_set_max_fan_pwm_output(struct pp_hwmgr *hwmgr, uint16_t us_
 			PPSMC_MSG_SetFanPwmMax, us_max_fan_pwm);
 }
 
+
 int polaris10_notify_smc_display_change(struct pp_hwmgr *hwmgr, bool has_display)
 {
 	PPSMC_Msg msg = has_display ? (PPSMC_Msg)PPSMC_HasDisplay : (PPSMC_Msg)PPSMC_NoDisplay;
@@ -4460,8 +4529,6 @@ int polaris10_notify_smc_display_config_after_ps_adjustment(struct pp_hwmgr *hwm
 
 	if (num_active_displays > 1)  /* to do && (pHwMgr->pPECI->displayConfiguration.bMultiMonitorInSync != TRUE)) */
 		polaris10_notify_smc_display_change(hwmgr, false);
-	else
-		polaris10_notify_smc_display_change(hwmgr, true);
 
 	return 0;
 }
@@ -4502,6 +4569,8 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr)
 	frame_time_in_us = 1000000 / refresh_rate;
 
 	pre_vbi_time_in_us = frame_time_in_us - 200 - mode_info.vblank_time_us;
+	data->frame_time_x2 = frame_time_in_us * 2 / 100;
+
 	display_gap2 = pre_vbi_time_in_us * (ref_clock / 100);
 
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCG_DISPLAY_GAP_CNTL2, display_gap2);
@@ -4510,8 +4579,6 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr)
 
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, data->soft_regs_start + offsetof(SMU74_SoftRegisters, VBlankTimeout), (frame_time_in_us - pre_vbi_time_in_us));
 
-	polaris10_notify_smc_display_change(hwmgr, num_active_displays != 0);
-
 	return 0;
 }
 
@@ -4623,7 +4690,7 @@ int polaris10_upload_mc_firmware(struct pp_hwmgr *hwmgr)
 		return 0;
 	}
 
-	data->need_long_memory_training = true;
+	data->need_long_memory_training = false;
 
 /*
  *	PPMCME_FirmwareDescriptorEntry *pfd = NULL;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
index d717789441f5..afc3434822d1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h
@@ -315,6 +315,7 @@ struct polaris10_hwmgr {
 
 	uint32_t                              avfs_vdroop_override_setting;
 	bool                                  apply_avfs_cks_off_voltage;
+	uint32_t                              frame_time_x2;
 };
 
 /* To convert to Q8.8 format for firmware */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index bf4e18fd3872..90b35c5c10a4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1256,7 +1256,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 }
 
 int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
-				uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage)
+				uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage)
 {
 
 	int result;
@@ -1274,7 +1274,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
 	if (0 != result)
 		return result;
 
-	*voltage = get_voltage_info_param_space.usVoltageLevel;
+	*voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel;
 
 	return result;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
index 248c5db5f380..1e35a9625baf 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h
@@ -305,7 +305,7 @@ extern int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, uint32_t
 extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock,
 								uint8_t level);
 extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
-				uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage);
+				uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage);
 extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table);
 
 extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 233eb7f36c1d..5d0f655bf160 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -1302,7 +1302,7 @@ static int tonga_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			table->Smio[count] |=
 				data->mvdd_voltage_table.entries[count].smio_low;
 		}
-		table->SmioMask2 = data->vddci_voltage_table.mask_low;
+		table->SmioMask2 = data->mvdd_voltage_table.mask_low;
 
 		CONVERT_FROM_HOST_TO_SMC_UL(table->MvddLevelCount);
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
index 671fdb4d615a..dccc859f638c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
@@ -302,7 +302,7 @@ static int init_dpm_2_parameters(
 			(((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usPPMTableOffset));
 
 		if (0 != powerplay_table->usPPMTableOffset) {
-			if (1 == get_platform_power_management_table(hwmgr, atom_ppm_table)) {
+			if (get_platform_power_management_table(hwmgr, atom_ppm_table) == 0) {
 				phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 					PHM_PlatformCaps_EnablePlatformPowerManagement);
 			}
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 28f571449495..77e8e33d5870 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -411,6 +411,8 @@ struct phm_cac_tdp_table {
 	uint8_t  ucVr_I2C_Line;
 	uint8_t  ucPlx_I2C_address;
 	uint8_t  ucPlx_I2C_Line;
+	uint32_t usBoostPowerLimit;
+	uint8_t  ucCKS_LDO_REFSEL;
 };
 
 struct phm_ppm_table {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
index d41d37ab5b7c..b8f4b73c322e 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h
@@ -392,6 +392,8 @@ typedef uint16_t PPSMC_Result;
 #define PPSMC_MSG_SetGpuPllDfsForSclk         ((uint16_t) 0x300)
 #define PPSMC_MSG_Didt_Block_Function		  ((uint16_t) 0x301)
 
+#define PPSMC_MSG_SetVBITimeout               ((uint16_t) 0x306)
+
 #define PPSMC_MSG_SecureSRBMWrite             ((uint16_t) 0x600)
 #define PPSMC_MSG_SecureSRBMRead              ((uint16_t) 0x601)
 #define PPSMC_MSG_SetAddress                  ((uint16_t) 0x800)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
index b85ff5400e57..899d6d8108c2 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h
@@ -270,7 +270,8 @@ struct SMU74_Discrete_DpmTable {
 	uint8_t                             BootPhases;
 
 	uint8_t                             VRHotLevel;
-	uint8_t                             Reserved1[3];
+	uint8_t                             LdoRefSel;
+	uint8_t                             Reserved1[2];
 	uint16_t                            FanStartTemperature;
 	uint16_t                            FanStopTemperature;
 	uint16_t                            MaxVoltage;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 32690332d441..103546834b60 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2365,16 +2365,16 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 		task = get_pid_task(file->pid, PIDTYPE_PID);
 		if (!task) {
 			ret = -ESRCH;
-			goto out_put;
+			goto out_unlock;
 		}
 		seq_printf(m, "\nproc: %s\n", task->comm);
 		put_task_struct(task);
 		idr_for_each(&file_priv->context_idr, per_file_ctx,
 			     (void *)(unsigned long)m);
 	}
+out_unlock:
 	mutex_unlock(&dev->filelist_mutex);
 
-out_put:
 	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 56a1637c864f..04452cf3eae8 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8447,16 +8447,16 @@ static void lpt_reset_fdi_mphy(struct drm_i915_private *dev_priv)
 	tmp |= FDI_MPHY_IOSFSB_RESET_CTL;
 	I915_WRITE(SOUTH_CHICKEN2, tmp);
 
-	if (wait_for_atomic_us(I915_READ(SOUTH_CHICKEN2) &
-			       FDI_MPHY_IOSFSB_RESET_STATUS, 100))
+	if (wait_for_us(I915_READ(SOUTH_CHICKEN2) &
+			FDI_MPHY_IOSFSB_RESET_STATUS, 100))
 		DRM_ERROR("FDI mPHY reset assert timeout\n");
 
 	tmp = I915_READ(SOUTH_CHICKEN2);
 	tmp &= ~FDI_MPHY_IOSFSB_RESET_CTL;
 	I915_WRITE(SOUTH_CHICKEN2, tmp);
 
-	if (wait_for_atomic_us((I915_READ(SOUTH_CHICKEN2) &
-				FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100))
+	if (wait_for_us((I915_READ(SOUTH_CHICKEN2) &
+			 FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100))
 		DRM_ERROR("FDI mPHY reset de-assert timeout\n");
 }
 
@@ -9440,8 +9440,8 @@ static void hsw_disable_lcpll(struct drm_i915_private *dev_priv,
 		val |= LCPLL_CD_SOURCE_FCLK;
 		I915_WRITE(LCPLL_CTL, val);
 
-		if (wait_for_atomic_us(I915_READ(LCPLL_CTL) &
-				       LCPLL_CD_SOURCE_FCLK_DONE, 1))
+		if (wait_for_us(I915_READ(LCPLL_CTL) &
+				LCPLL_CD_SOURCE_FCLK_DONE, 1))
 			DRM_ERROR("Switching to FCLK failed\n");
 
 		val = I915_READ(LCPLL_CTL);
@@ -9514,8 +9514,8 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 		val &= ~LCPLL_CD_SOURCE_FCLK;
 		I915_WRITE(LCPLL_CTL, val);
 
-		if (wait_for_atomic_us((I915_READ(LCPLL_CTL) &
-					LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
+		if (wait_for_us((I915_READ(LCPLL_CTL) &
+				 LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
 			DRM_ERROR("Switching back to LCPLL failed\n");
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 79cf2d5f5a20..40745e38d438 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -663,7 +663,7 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
 		done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
 					  msecs_to_jiffies_timeout(10));
 	else
-		done = wait_for_atomic(C, 10) == 0;
+		done = wait_for(C, 10) == 0;
 	if (!done)
 		DRM_ERROR("dp aux hw did not signal timeout (has irq: %i)!\n",
 			  has_aux_irq);
@@ -4899,13 +4899,15 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
 
 void intel_dp_encoder_reset(struct drm_encoder *encoder)
 {
-	struct intel_dp *intel_dp;
+	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+
+	if (!HAS_DDI(dev_priv))
+		intel_dp->DP = I915_READ(intel_dp->output_reg);
 
 	if (to_intel_encoder(encoder)->type != INTEL_OUTPUT_EDP)
 		return;
 
-	intel_dp = enc_to_intel_dp(encoder);
-
 	pps_lock(intel_dp);
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index baf6f5584cbd..58f60b27837e 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -1377,8 +1377,8 @@ static void bxt_ddi_pll_enable(struct drm_i915_private *dev_priv,
 	I915_WRITE(BXT_PORT_PLL_ENABLE(port), temp);
 	POSTING_READ(BXT_PORT_PLL_ENABLE(port));
 
-	if (wait_for_atomic_us((I915_READ(BXT_PORT_PLL_ENABLE(port)) &
-			PORT_PLL_LOCK), 200))
+	if (wait_for_us((I915_READ(BXT_PORT_PLL_ENABLE(port)) & PORT_PLL_LOCK),
+			200))
 		DRM_ERROR("PLL %d not locked\n", port);
 
 	/*
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
index 22706c0a54b5..49bd5da194e1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
@@ -40,7 +40,8 @@ static int
 gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
 	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
-	nvkm_mask(device, 0x61c110, 0x0f0f0f0f, 0x01010101 * pattern);
+	const u32 soff = gf119_sor_soff(outp);
+	nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, 0x01010101 * pattern);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c
index 4182a21f5923..41cacecbea9a 100644
--- a/drivers/gpu/drm/sun4i/sun4i_crtc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c
@@ -65,6 +65,14 @@ static void sun4i_crtc_disable(struct drm_crtc *crtc)
 	DRM_DEBUG_DRIVER("Disabling the CRTC\n");
 
 	sun4i_tcon_disable(drv->tcon);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+
+		crtc->state->event = NULL;
+	}
 }
 
 static void sun4i_crtc_enable(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 257d2b4f3645..937394cbc241 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -92,7 +92,7 @@ static struct drm_driver sun4i_drv_driver = {
 	/* Frame Buffer Operations */
 
 	/* VBlank Operations */
-	.get_vblank_counter	= drm_vblank_count,
+	.get_vblank_counter	= drm_vblank_no_hw_counter,
 	.enable_vblank		= sun4i_drv_enable_vblank,
 	.disable_vblank		= sun4i_drv_disable_vblank,
 };
@@ -310,6 +310,7 @@ static int sun4i_drv_probe(struct platform_device *pdev)
 
 		count += sun4i_drv_add_endpoints(&pdev->dev, &match,
 						pipeline);
+		of_node_put(pipeline);
 
 		DRM_DEBUG_DRIVER("Queued %d outputs on pipeline %d\n",
 				 count, i);
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 923f56598d4b..3a9f106787d2 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -81,7 +81,7 @@ static int kxsd9_write_scale(struct iio_dev *indio_dev, int micro)
 
 	mutex_lock(&st->buf_lock);
 	ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
-	if (ret)
+	if (ret < 0)
 		goto error_ret;
 	st->tx[0] = KXSD9_WRITE(KXSD9_REG_CTRL_C);
 	st->tx[1] = (ret & ~KXSD9_FS_MASK) | i;
@@ -163,7 +163,7 @@ static int kxsd9_read_raw(struct iio_dev *indio_dev,
 		break;
 	case IIO_CHAN_INFO_SCALE:
 		ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
-		if (ret)
+		if (ret < 0)
 			goto error_ret;
 		*val2 = kxsd9_micro_scales[ret & KXSD9_FS_MASK];
 		ret = IIO_VAL_INT_PLUS_MICRO;
diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 21e19b60e2b9..2123f0ac2e2a 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -396,8 +396,8 @@ static int ad7266_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 
-	st->reg = devm_regulator_get(&spi->dev, "vref");
-	if (!IS_ERR_OR_NULL(st->reg)) {
+	st->reg = devm_regulator_get_optional(&spi->dev, "vref");
+	if (!IS_ERR(st->reg)) {
 		ret = regulator_enable(st->reg);
 		if (ret)
 			return ret;
@@ -408,6 +408,9 @@ static int ad7266_probe(struct spi_device *spi)
 
 		st->vref_mv = ret / 1000;
 	} else {
+		/* Any other error indicates that the regulator does exist */
+		if (PTR_ERR(st->reg) != -ENODEV)
+			return PTR_ERR(st->reg);
 		/* Use internal reference */
 		st->vref_mv = 2500;
 	}
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
index f62b8bd9ad7e..dd6fc6d21f9d 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_acpi.c
@@ -56,6 +56,7 @@ static int asus_acpi_get_sensor_info(struct acpi_device *adev,
 	int i;
 	acpi_status status;
 	union acpi_object *cpm;
+	int ret;
 
 	status = acpi_evaluate_object(adev->handle, "CNF0", NULL, &buffer);
 	if (ACPI_FAILURE(status))
@@ -82,10 +83,10 @@ static int asus_acpi_get_sensor_info(struct acpi_device *adev,
 			}
 		}
 	}
-
+	ret = cpm->package.count;
 	kfree(buffer.pointer);
 
-	return cpm->package.count;
+	return ret;
 }
 
 static int acpi_i2c_check_resource(struct acpi_resource *ares, void *data)
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 9e0034196e10..59741ead7e15 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1107,13 +1107,13 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				break;
 			}
 
+			devid = e->devid;
 			DUMP_printk("  DEV_ACPI_HID(%s[%s])\t\tdevid: %02x:%02x.%x\n",
 				    hid, uid,
 				    PCI_BUS_NUM(devid),
 				    PCI_SLOT(devid),
 				    PCI_FUNC(devid));
 
-			devid  = e->devid;
 			flags = e->flags;
 
 			ret = add_acpi_hid_device(hid, uid, &devid, false);
@@ -1568,13 +1568,23 @@ static int __init amd_iommu_init_pci(void)
 			break;
 	}
 
+	/*
+	 * Order is important here to make sure any unity map requirements are
+	 * fulfilled. The unity mappings are created and written to the device
+	 * table during the amd_iommu_init_api() call.
+	 *
+	 * After that we call init_device_table_dma() to make sure any
+	 * uninitialized DTE will block DMA, and in the end we flush the caches
+	 * of all IOMMUs to make sure the changes to the device table are
+	 * active.
+	 */
+	ret = amd_iommu_init_api();
+
 	init_device_table_dma();
 
 	for_each_iommu(iommu)
 		iommu_flush_all_caches(iommu);
 
-	ret = amd_iommu_init_api();
-
 	if (!ret)
 		print_iommu_info();
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 10700945994e..323dac9900ba 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4602,13 +4602,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu)
 	for (i = 0; i < g_num_of_iommus; i++) {
 		struct intel_iommu *iommu = g_iommus[i];
 		struct dmar_domain *domain;
-		u16 did;
+		int did;
 
 		if (!iommu)
 			continue;
 
-		for (did = 0; did < 0xffff; did++) {
-			domain = get_iommu_domain(iommu, did);
+		for (did = 0; did < cap_ndoms(iommu->cap); did++) {
+			domain = get_iommu_domain(iommu, (u16)did);
 
 			if (!domain)
 				continue;
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index ba764a0835d3..e23001bfcfee 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -420,8 +420,10 @@ retry:
 
 		/* Try replenishing IOVAs by flushing rcache. */
 		flushed_rcache = true;
+		preempt_disable();
 		for_each_online_cpu(cpu)
 			free_cpu_cached_iovas(cpu, iovad);
+		preempt_enable();
 		goto retry;
 	}
 
@@ -749,7 +751,7 @@ static bool __iova_rcache_insert(struct iova_domain *iovad,
 	bool can_insert = false;
 	unsigned long flags;
 
-	cpu_rcache = this_cpu_ptr(rcache->cpu_rcaches);
+	cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches);
 	spin_lock_irqsave(&cpu_rcache->lock, flags);
 
 	if (!iova_magazine_full(cpu_rcache->loaded)) {
@@ -779,6 +781,7 @@ static bool __iova_rcache_insert(struct iova_domain *iovad,
 		iova_magazine_push(cpu_rcache->loaded, iova_pfn);
 
 	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+	put_cpu_ptr(rcache->cpu_rcaches);
 
 	if (mag_to_free) {
 		iova_magazine_free_pfns(mag_to_free, iovad);
@@ -812,7 +815,7 @@ static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
 	bool has_pfn = false;
 	unsigned long flags;
 
-	cpu_rcache = this_cpu_ptr(rcache->cpu_rcaches);
+	cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches);
 	spin_lock_irqsave(&cpu_rcache->lock, flags);
 
 	if (!iova_magazine_empty(cpu_rcache->loaded)) {
@@ -834,6 +837,7 @@ static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
 		iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn);
 
 	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+	put_cpu_ptr(rcache->cpu_rcaches);
 
 	return iova_pfn;
 }
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 8a4adbeb2b8c..70ed1d0151b8 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -718,7 +718,7 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,
 
 	spin_lock_irqsave(&gic_lock, flags);
 	gic_map_to_pin(intr, gic_cpu_pin);
-	gic_map_to_vpe(intr, vpe);
+	gic_map_to_vpe(intr, mips_cm_vp_id(vpe));
 	for (i = 0; i < min(gic_vpes, NR_CPUS); i++)
 		clear_bit(intr, pcpu_masks[i].pcpu_mask);
 	set_bit(intr, pcpu_masks[vpe].pcpu_mask);
@@ -959,7 +959,7 @@ int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node,
 	switch (bus_token) {
 	case DOMAIN_BUS_IPI:
 		is_ipi = d->bus_token == bus_token;
-		return to_of_node(d->fwnode) == node && is_ipi;
+		return (!node || to_of_node(d->fwnode) == node) && is_ipi;
 		break;
 	default:
 		return 0;
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index ca81f46ea1aa..edc70ffad660 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -101,11 +101,14 @@ enum ad_link_speed_type {
 #define MAC_ADDRESS_EQUAL(A, B)	\
 	ether_addr_equal_64bits((const u8 *)A, (const u8 *)B)
 
-static struct mac_addr null_mac_addr = { { 0, 0, 0, 0, 0, 0 } };
+static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = {
+	0, 0, 0, 0, 0, 0
+};
 static u16 ad_ticks_per_sec;
 static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000;
 
-static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
+static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned =
+	MULTICAST_LACPDU_ADDR;
 
 /* ================= main 802.3ad protocol functions ================== */
 static int ad_lacpdu_send(struct port *port);
@@ -1739,7 +1742,7 @@ static void ad_clear_agg(struct aggregator *aggregator)
 		aggregator->is_individual = false;
 		aggregator->actor_admin_aggregator_key = 0;
 		aggregator->actor_oper_aggregator_key = 0;
-		aggregator->partner_system = null_mac_addr;
+		eth_zero_addr(aggregator->partner_system.mac_addr_value);
 		aggregator->partner_system_priority = 0;
 		aggregator->partner_oper_aggregator_key = 0;
 		aggregator->receive_state = 0;
@@ -1761,7 +1764,7 @@ static void ad_initialize_agg(struct aggregator *aggregator)
 	if (aggregator) {
 		ad_clear_agg(aggregator);
 
-		aggregator->aggregator_mac_address = null_mac_addr;
+		eth_zero_addr(aggregator->aggregator_mac_address.mac_addr_value);
 		aggregator->aggregator_identifier = 0;
 		aggregator->slave = NULL;
 	}
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index c5ac160a8ae9..551f0f8dead3 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -42,13 +42,10 @@
 
 
 
-#ifndef __long_aligned
-#define __long_aligned __attribute__((aligned((sizeof(long)))))
-#endif
-static const u8 mac_bcast[ETH_ALEN] __long_aligned = {
+static const u8 mac_bcast[ETH_ALEN + 2] __long_aligned = {
 	0xff, 0xff, 0xff, 0xff, 0xff, 0xff
 };
-static const u8 mac_v6_allmcast[ETH_ALEN] __long_aligned = {
+static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = {
 	0x33, 0x33, 0x00, 0x00, 0x00, 0x01
 };
 static const int alb_delta_in_ticks = HZ / ALB_TIMER_TICKS_PER_SEC;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 941ec99cd3b6..a2afa3be17a4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1584,6 +1584,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	}
 
 	/* check for initial state */
+	new_slave->link = BOND_LINK_NOCHANGE;
 	if (bond->params.miimon) {
 		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
 			if (bond->params.updelay) {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 543bf38105c9..bfa26a2590c9 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -392,7 +392,7 @@ static void bcm_sysport_get_stats(struct net_device *dev,
 		else
 			p = (char *)priv;
 		p += s->stat_offset;
-		data[i] = *(u32 *)p;
+		data[i] = *(unsigned long *)p;
 	}
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index c4b262ca7d43..2accab386323 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -36,8 +36,8 @@
 #define __T4FW_VERSION_H__
 
 #define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x0E
-#define T4FW_VERSION_MICRO 0x04
+#define T4FW_VERSION_MINOR 0x0F
+#define T4FW_VERSION_MICRO 0x25
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -45,8 +45,8 @@
 #define T4FW_MIN_VERSION_MICRO 0x00
 
 #define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x0E
-#define T5FW_VERSION_MICRO 0x04
+#define T5FW_VERSION_MINOR 0x0F
+#define T5FW_VERSION_MICRO 0x25
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -54,8 +54,8 @@
 #define T5FW_MIN_VERSION_MICRO 0x00
 
 #define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x0E
-#define T6FW_VERSION_MICRO 0x04
+#define T6FW_VERSION_MINOR 0x0F
+#define T6FW_VERSION_MICRO 0x25
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 73f745205a1c..2b2e2f8c6369 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -154,16 +154,6 @@ void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
 	writel(val, hw->hw_addr + reg);
 }
 
-static bool e1000e_vlan_used(struct e1000_adapter *adapter)
-{
-	u16 vid;
-
-	for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID)
-		return true;
-
-	return false;
-}
-
 /**
  * e1000_regdump - register printout routine
  * @hw: pointer to the HW structure
@@ -3453,8 +3443,7 @@ static void e1000e_set_rx_mode(struct net_device *netdev)
 
 	ew32(RCTL, rctl);
 
-	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX ||
-	    e1000e_vlan_used(adapter))
+	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
 		e1000e_vlan_strip_enable(adapter);
 	else
 		e1000e_vlan_strip_disable(adapter);
@@ -6926,6 +6915,14 @@ static netdev_features_t e1000_fix_features(struct net_device *netdev,
 	if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN))
 		features &= ~NETIF_F_RXFCS;
 
+	/* Since there is no support for separate Rx/Tx vlan accel
+	 * enable/disable make sure Tx flag is always in same state as Rx.
+	 */
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		features |= NETIF_F_HW_VLAN_CTAG_TX;
+	else
+		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
+
 	return features;
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c
index 61a80da8b6f0..2819abc454c7 100644
--- a/drivers/net/ethernet/intel/ixgbevf/mbx.c
+++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c
@@ -85,7 +85,7 @@ static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw)
 static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	if (!mbx->ops.read)
 		goto out;
@@ -111,7 +111,7 @@ out:
 static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
-	s32 ret_val = -IXGBE_ERR_MBX;
+	s32 ret_val = IXGBE_ERR_MBX;
 
 	/* exit if either we can't write or there isn't a defined timeout */
 	if (!mbx->ops.write || !mbx->timeout)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index a6d26d351dfc..d5d263bda333 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3458,6 +3458,8 @@ static int mvneta_open(struct net_device *dev)
 	return 0;
 
 err_free_irq:
+	unregister_cpu_notifier(&pp->cpu_notifier);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(pp->dev->irq, pp->ports);
 err_cleanup_txqs:
 	mvneta_cleanup_txqs(pp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 0b4986268cc9..d6e2a1cae19a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -295,6 +295,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_FLOW_GROUP:
 	case MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_DEALLOC_FLOW_COUNTER:
+	case MLX5_CMD_OP_2ERR_QP:
+	case MLX5_CMD_OP_2RST_QP:
+	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
+	case MLX5_CMD_OP_MODIFY_FLOW_TABLE:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+	case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -321,8 +327,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_RTR2RTS_QP:
 	case MLX5_CMD_OP_RTS2RTS_QP:
 	case MLX5_CMD_OP_SQERR2RTS_QP:
-	case MLX5_CMD_OP_2ERR_QP:
-	case MLX5_CMD_OP_2RST_QP:
 	case MLX5_CMD_OP_QUERY_QP:
 	case MLX5_CMD_OP_SQD_RTS_QP:
 	case MLX5_CMD_OP_INIT2INIT_QP:
@@ -342,7 +346,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT:
-	case MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT:
 	case MLX5_CMD_OP_QUERY_ROCE_ADDRESS:
 	case MLX5_CMD_OP_SET_ROCE_ADDRESS:
 	case MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT:
@@ -390,11 +393,12 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_RQT:
 	case MLX5_CMD_OP_MODIFY_RQT:
 	case MLX5_CMD_OP_QUERY_RQT:
+
 	case MLX5_CMD_OP_CREATE_FLOW_TABLE:
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE:
 	case MLX5_CMD_OP_CREATE_FLOW_GROUP:
 	case MLX5_CMD_OP_QUERY_FLOW_GROUP:
-	case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
+
 	case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY:
 	case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
 	case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
@@ -602,11 +606,36 @@ static void dump_command(struct mlx5_core_dev *dev,
 		pr_debug("\n");
 }
 
+static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
+{
+	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
+
+	return be16_to_cpu(hdr->opcode);
+}
+
+static void cb_timeout_handler(struct work_struct *work)
+{
+	struct delayed_work *dwork = container_of(work, struct delayed_work,
+						  work);
+	struct mlx5_cmd_work_ent *ent = container_of(dwork,
+						     struct mlx5_cmd_work_ent,
+						     cb_timeout_work);
+	struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev,
+						 cmd);
+
+	ent->ret = -ETIMEDOUT;
+	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
+		       mlx5_command_str(msg_to_opcode(ent->in)),
+		       msg_to_opcode(ent->in));
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+}
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
 	struct mlx5_cmd *cmd = ent->cmd;
 	struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd);
+	unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
@@ -647,6 +676,9 @@ static void cmd_work_handler(struct work_struct *work)
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
 
+	if (ent->callback)
+		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -691,13 +723,6 @@ static const char *deliv_status_to_str(u8 status)
 	}
 }
 
-static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
-{
-	struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data);
-
-	return be16_to_cpu(hdr->opcode);
-}
-
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 {
 	unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
@@ -706,13 +731,13 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 
 	if (cmd->mode == CMD_MODE_POLLING) {
 		wait_for_completion(&ent->done);
-		err = ent->ret;
-	} else {
-		if (!wait_for_completion_timeout(&ent->done, timeout))
-			err = -ETIMEDOUT;
-		else
-			err = 0;
+	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
+		ent->ret = -ETIMEDOUT;
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
 	}
+
+	err = ent->ret;
+
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
@@ -761,6 +786,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (!callback)
 		init_completion(&ent->done);
 
+	INIT_DELAYED_WORK(&ent->cb_timeout_work, cb_timeout_handler);
 	INIT_WORK(&ent->work, cmd_work_handler);
 	if (page_queue) {
 		cmd_work_handler(&ent->work);
@@ -770,28 +796,26 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 		goto out_free;
 	}
 
-	if (!callback) {
-		err = wait_func(dev, ent);
-		if (err == -ETIMEDOUT)
-			goto out;
-
-		ds = ent->ts2 - ent->ts1;
-		op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
-		if (op < ARRAY_SIZE(cmd->stats)) {
-			stats = &cmd->stats[op];
-			spin_lock_irq(&stats->lock);
-			stats->sum += ds;
-			++stats->n;
-			spin_unlock_irq(&stats->lock);
-		}
-		mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
-				   "fw exec time for %s is %lld nsec\n",
-				   mlx5_command_str(op), ds);
-		*status = ent->status;
-		free_cmd(ent);
-	}
+	if (callback)
+		goto out;
 
-	return err;
+	err = wait_func(dev, ent);
+	if (err == -ETIMEDOUT)
+		goto out_free;
+
+	ds = ent->ts2 - ent->ts1;
+	op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
+	if (op < ARRAY_SIZE(cmd->stats)) {
+		stats = &cmd->stats[op];
+		spin_lock_irq(&stats->lock);
+		stats->sum += ds;
+		++stats->n;
+		spin_unlock_irq(&stats->lock);
+	}
+	mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
+			   "fw exec time for %s is %lld nsec\n",
+			   mlx5_command_str(op), ds);
+	*status = ent->status;
 
 out_free:
 	free_cmd(ent);
@@ -1181,41 +1205,30 @@ err_dbg:
 	return err;
 }
 
-void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
+static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		down(&cmd->sem);
-
 	down(&cmd->pages_sem);
 
-	flush_workqueue(cmd->wq);
-
-	cmd->mode = CMD_MODE_EVENTS;
+	cmd->mode = mode;
 
 	up(&cmd->pages_sem);
 	for (i = 0; i < cmd->max_reg_cmds; i++)
 		up(&cmd->sem);
 }
 
-void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
+void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
 {
-	struct mlx5_cmd *cmd = &dev->cmd;
-	int i;
-
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		down(&cmd->sem);
-
-	down(&cmd->pages_sem);
-
-	flush_workqueue(cmd->wq);
-	cmd->mode = CMD_MODE_POLLING;
+	mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS);
+}
 
-	up(&cmd->pages_sem);
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		up(&cmd->sem);
+void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
+{
+	mlx5_cmd_change_mod(dev, CMD_MODE_POLLING);
 }
 
 static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
@@ -1251,6 +1264,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+			if (ent->callback)
+				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
 				sem = &cmd->pages_sem;
 			else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index baa991a23475..943b1bd434bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -145,7 +145,6 @@ struct mlx5e_umr_wqe {
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
-#define MLX5E_MIN_BW_ALLOC 1   /* Min percentage of BW allocation */
 #endif
 
 struct mlx5e_params {
@@ -191,6 +190,7 @@ struct mlx5e_tstamp {
 enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 	MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
+	MLX5E_RQ_STATE_FLUSH_TIMEOUT,
 };
 
 struct mlx5e_cq {
@@ -220,6 +220,8 @@ typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq *rq,
 typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,
 				  u16 ix);
 
+typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq *rq, u16 ix);
+
 struct mlx5e_dma_info {
 	struct page	*page;
 	dma_addr_t	addr;
@@ -241,6 +243,7 @@ struct mlx5e_rq {
 	struct mlx5e_cq        cq;
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 	mlx5e_fp_alloc_wqe     alloc_wqe;
+	mlx5e_fp_dealloc_wqe   dealloc_wqe;
 
 	unsigned long          state;
 	int                    ix;
@@ -305,6 +308,7 @@ struct mlx5e_sq_dma {
 enum {
 	MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
 	MLX5E_SQ_STATE_BF_ENABLE,
+	MLX5E_SQ_STATE_TX_TIMEOUT,
 };
 
 struct mlx5e_ico_wqe_info {
@@ -538,6 +542,7 @@ struct mlx5e_priv {
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
 	struct work_struct         set_rx_mode_work;
+	struct work_struct         tx_timeout_work;
 	struct delayed_work        update_stats_work;
 
 	struct mlx5_core_dev      *mdev;
@@ -589,12 +594,16 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
 int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_post_rx_fragmented_mpwqe(struct mlx5e_rq *rq);
 void mlx5e_complete_rx_linear_mpwqe(struct mlx5e_rq *rq,
 				    struct mlx5_cqe64 *cqe,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index b2db180ae2a5..c585349e05c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -96,7 +96,7 @@ static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw,
 			tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC;
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
-			tc_tx_bw[i] = ets->tc_tx_bw[i] ?: MLX5E_MIN_BW_ALLOC;
+			tc_tx_bw[i] = ets->tc_tx_bw[i];
 			break;
 		}
 	}
@@ -140,8 +140,12 @@ static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets)
 
 	/* Validate Bandwidth Sum */
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS)
+		if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
+			if (!ets->tc_tx_bw[i])
+				return -EINVAL;
+
 			bw_sum += ets->tc_tx_bw[i];
+		}
 	}
 
 	if (bw_sum != 0 && bw_sum != 100)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cb6defd71fc1..7a0dca29c642 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,6 +39,13 @@
 #include "eswitch.h"
 #include "vxlan.h"
 
+enum {
+	MLX5_EN_QP_FLUSH_TIMEOUT_MS	= 5000,
+	MLX5_EN_QP_FLUSH_MSLEEP_QUANT	= 20,
+	MLX5_EN_QP_FLUSH_MAX_ITER	= MLX5_EN_QP_FLUSH_TIMEOUT_MS /
+					  MLX5_EN_QP_FLUSH_MSLEEP_QUANT,
+};
+
 struct mlx5e_rq_param {
 	u32                        rqc[MLX5_ST_SZ_DW(rqc)];
 	struct mlx5_wq_param       wq;
@@ -74,10 +81,13 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	port_state = mlx5_query_vport_state(mdev,
 		MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0);
 
-	if (port_state == VPORT_STATE_UP)
+	if (port_state == VPORT_STATE_UP) {
+		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
-	else
+	} else {
+		netdev_info(priv->netdev, "Link down\n");
 		netif_carrier_off(priv->netdev);
+	}
 }
 
 static void mlx5e_update_carrier_work(struct work_struct *work)
@@ -91,6 +101,26 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
 	mutex_unlock(&priv->state_lock);
 }
 
+static void mlx5e_tx_timeout_work(struct work_struct *work)
+{
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       tx_timeout_work);
+	int err;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+	mlx5e_close_locked(priv->netdev);
+	err = mlx5e_open_locked(priv->netdev);
+	if (err)
+		netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   err);
+unlock:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+}
+
 static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5e_sw_stats *s = &priv->stats.sw;
@@ -305,6 +335,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		}
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
 		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
 		rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
 		rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
@@ -320,6 +351,7 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 		}
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
 		rq->alloc_wqe = mlx5e_alloc_rx_wqe;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
 		rq->wqe_sz = (priv->params.lro_en) ?
 				priv->params.lro_wqe_sz :
@@ -525,17 +557,25 @@ err_destroy_rq:
 
 static void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
+	int tout = 0;
+	int err;
+
 	clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
 	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
 
-	mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
-	while (!mlx5_wq_ll_is_empty(&rq->wq))
-		msleep(20);
+	err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
+	while (!mlx5_wq_ll_is_empty(&rq->wq) && !err &&
+	       tout++ < MLX5_EN_QP_FLUSH_MAX_ITER)
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+
+	if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER)
+		set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state);
 
 	/* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */
 	napi_synchronize(&rq->channel->napi);
 
 	mlx5e_disable_rq(rq);
+	mlx5e_free_rx_descs(rq);
 	mlx5e_destroy_rq(rq);
 }
 
@@ -782,6 +822,9 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_close_sq(struct mlx5e_sq *sq)
 {
+	int tout = 0;
+	int err;
+
 	if (sq->txq) {
 		clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
 		/* prevent netif_tx_wake_queue */
@@ -792,15 +835,24 @@ static void mlx5e_close_sq(struct mlx5e_sq *sq)
 		if (mlx5e_sq_has_room_for(sq, 1))
 			mlx5e_send_nop(sq, true);
 
-		mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
+		err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
+				      MLX5_SQC_STATE_ERR);
+		if (err)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
 	}
 
-	while (sq->cc != sq->pc) /* wait till sq is empty */
-		msleep(20);
+	/* wait till sq is empty, unless a TX timeout occurred on this SQ */
+	while (sq->cc != sq->pc &&
+	       !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) {
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+		if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+	}
 
 	/* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
 	napi_synchronize(&sq->channel->napi);
 
+	mlx5e_free_tx_descs(sq);
 	mlx5e_disable_sq(sq);
 	mlx5e_destroy_sq(sq);
 }
@@ -1658,8 +1710,11 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 
 	netdev_set_num_tc(netdev, ntc);
 
+	/* Map netdev TCs to offset 0
+	 * We have our own UP to TXQ mapping for QoS
+	 */
 	for (tc = 0; tc < ntc; tc++)
-		netdev_set_tc_queue(netdev, tc, nch, tc * nch);
+		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
 int mlx5e_open_locked(struct net_device *netdev)
@@ -2590,6 +2645,29 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	return features;
 }
 
+static void mlx5e_tx_timeout(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	bool sched_work = false;
+	int i;
+
+	netdev_err(dev, "TX timeout detected\n");
+
+	for (i = 0; i < priv->params.num_channels * priv->params.num_tc; i++) {
+		struct mlx5e_sq *sq = priv->txq_to_sq_map[i];
+
+		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
+			continue;
+		sched_work = true;
+		set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+		netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n",
+			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc);
+	}
+
+	if (sched_work && test_bit(MLX5E_STATE_OPENED, &priv->state))
+		schedule_work(&priv->tx_timeout_work);
+}
+
 static const struct net_device_ops mlx5e_netdev_ops_basic = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
@@ -2607,6 +2685,7 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
+	.ndo_tx_timeout          = mlx5e_tx_timeout,
 };
 
 static const struct net_device_ops mlx5e_netdev_ops_sriov = {
@@ -2636,6 +2715,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
+	.ndo_tx_timeout          = mlx5e_tx_timeout,
 };
 
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -2838,6 +2918,7 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 
 	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
 	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
+	INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work);
 	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 022acc2e8922..9f2a16a507e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -212,6 +212,20 @@ err_free_skb:
 	return -ENOMEM;
 }
 
+void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
+{
+	struct sk_buff *skb = rq->skb[ix];
+
+	if (skb) {
+		rq->skb[ix] = NULL;
+		dma_unmap_single(rq->pdev,
+				 *((dma_addr_t *)skb->cb),
+				 rq->wqe_sz,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb(skb);
+	}
+}
+
 static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq)
 {
 	return rq->mpwqe_num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
@@ -574,6 +588,30 @@ int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
 	return 0;
 }
 
+void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
+{
+	struct mlx5e_mpw_info *wi = &rq->wqe_info[ix];
+
+	wi->free_wqe(rq, wi);
+}
+
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq = &rq->wq;
+	struct mlx5e_rx_wqe *wqe;
+	__be16 wqe_ix_be;
+	u16 wqe_ix;
+
+	while (!mlx5_wq_ll_is_empty(wq)) {
+		wqe_ix_be = *wq->tail_next;
+		wqe_ix    = be16_to_cpu(wqe_ix_be);
+		wqe       = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
+		rq->dealloc_wqe(rq, wqe_ix);
+		mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
+			       &wqe->next.next_wqe_index);
+	}
+}
+
 #define RQ_CANNOT_POST(rq) \
 		(!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \
 		 test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
@@ -878,6 +916,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
 	int work_done = 0;
 
+	if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state)))
+		return 0;
+
 	if (cq->decmprs_left)
 		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 5a750b9cd006..5740b465ef84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -110,8 +110,20 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int channel_ix = fallback(dev, skb);
-	int up = (netdev_get_num_tc(dev) && skb_vlan_tag_present(skb)) ?
-		 skb->vlan_tci >> VLAN_PRIO_SHIFT : 0;
+	int up = 0;
+
+	if (!netdev_get_num_tc(dev))
+		return channel_ix;
+
+	if (skb_vlan_tag_present(skb))
+		up = skb->vlan_tci >> VLAN_PRIO_SHIFT;
+
+	/* channel_ix can be larger than num_channels since
+	 * dev->num_real_tx_queues = num_channels * num_tc
+	 */
+	if (channel_ix >= priv->params.num_channels)
+		channel_ix = reciprocal_scale(channel_ix,
+					      priv->params.num_channels);
 
 	return priv->channeltc_to_txq_map[channel_ix][up];
 }
@@ -123,7 +135,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
 	 * headers and occur before the data gather.
 	 * Therefore these headers must be copied into the WQE
 	 */
-#define MLX5E_MIN_INLINE ETH_HLEN
+#define MLX5E_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 
 	if (bf) {
 		u16 ihs = skb_headlen(skb);
@@ -135,7 +147,7 @@ static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
 			return skb_headlen(skb);
 	}
 
-	return MLX5E_MIN_INLINE;
+	return max(skb_network_offset(skb), MLX5E_MIN_INLINE);
 }
 
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
@@ -341,6 +353,35 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	return mlx5e_sq_xmit(sq, skb);
 }
 
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
+{
+	struct mlx5e_tx_wqe_info *wi;
+	struct sk_buff *skb;
+	u16 ci;
+	int i;
+
+	while (sq->cc != sq->pc) {
+		ci = sq->cc & sq->wq.sz_m1;
+		skb = sq->skb[ci];
+		wi = &sq->wqe_info[ci];
+
+		if (!skb) { /* nop */
+			sq->cc++;
+			continue;
+		}
+
+		for (i = 0; i < wi->num_dma; i++) {
+			struct mlx5e_sq_dma *dma =
+				mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+
+			mlx5e_tx_dma_unmap(sq->pdev, dma);
+		}
+
+		dev_kfree_skb_any(skb);
+		sq->cc += wi->num_wqebbs;
+	}
+}
+
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_sq *sq;
@@ -352,6 +393,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	sq = container_of(cq, struct mlx5e_sq, cq);
 
+	if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)))
+		return false;
+
 	npkts = 0;
 	nbytes = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 42d16b9458e4..96a59463ae65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -108,15 +108,21 @@ static int in_fatal(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev)
 {
+	mutex_lock(&dev->intf_state_mutex);
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		return;
+		goto unlock;
 
 	mlx5_core_err(dev, "start\n");
-	if (pci_channel_offline(dev->pdev) || in_fatal(dev))
+	if (pci_channel_offline(dev->pdev) || in_fatal(dev)) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		trigger_cmd_completions(dev);
+	}
 
 	mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0);
 	mlx5_core_err(dev, "end\n");
+
+unlock:
+	mutex_unlock(&dev->intf_state_mutex);
 }
 
 static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
@@ -245,7 +251,6 @@ static void poll_health(unsigned long data)
 	u32 count;
 
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-		trigger_cmd_completions(dev);
 		mod_timer(&health->timer, get_next_poll_jiffies());
 		return;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c65f4a13e17e..6695893ddd2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1422,46 +1422,31 @@ void mlx5_disable_device(struct mlx5_core_dev *dev)
 	mlx5_pci_err_detected(dev->pdev, 0);
 }
 
-/* wait for the device to show vital signs. For now we check
- * that we can read the device ID and that the health buffer
- * shows a non zero value which is different than 0xffffffff
+/* wait for the device to show vital signs by waiting
+ * for the health counter to start counting.
  */
-static void wait_vital(struct pci_dev *pdev)
+static int wait_vital(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 	struct mlx5_core_health *health = &dev->priv.health;
 	const int niter = 100;
+	u32 last_count = 0;
 	u32 count;
-	u16 did;
 	int i;
 
-	/* Wait for firmware to be ready after reset */
-	msleep(1000);
-	for (i = 0; i < niter; i++) {
-		if (pci_read_config_word(pdev, 2, &did)) {
-			dev_warn(&pdev->dev, "failed reading config word\n");
-			break;
-		}
-		if (did == pdev->device) {
-			dev_info(&pdev->dev, "device ID correctly read after %d iterations\n", i);
-			break;
-		}
-		msleep(50);
-	}
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
-
 	for (i = 0; i < niter; i++) {
 		count = ioread32be(health->health_counter);
 		if (count && count != 0xffffffff) {
-			dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
-			break;
+			if (last_count && last_count != count) {
+				dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+				return 0;
+			}
+			last_count = count;
 		}
 		msleep(50);
 	}
 
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
+	return -ETIMEDOUT;
 }
 
 static void mlx5_pci_resume(struct pci_dev *pdev)
@@ -1473,7 +1458,11 @@ static void mlx5_pci_resume(struct pci_dev *pdev)
 	dev_info(&pdev->dev, "%s was called\n", __func__);
 
 	pci_save_state(pdev);
-	wait_vital(pdev);
+	err = wait_vital(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+		return;
+	}
 
 	err = mlx5_load_one(dev, priv);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 9eeee0545f1c..32dea3524cee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -345,7 +345,6 @@ retry:
 			       func_id, npages, err);
 		goto out_4k;
 	}
-	dev->priv.fw_pages += npages;
 
 	err = mlx5_cmd_status_to_err(&out.hdr);
 	if (err) {
@@ -373,6 +372,33 @@ out_free:
 	return err;
 }
 
+static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
+			     struct mlx5_manage_pages_inbox *in, int in_size,
+			     struct mlx5_manage_pages_outbox *out, int out_size)
+{
+	struct fw_page *fwp;
+	struct rb_node *p;
+	u32 npages;
+	u32 i = 0;
+
+	if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		return mlx5_cmd_exec_check_status(dev, (u32 *)in, in_size,
+						  (u32 *)out, out_size);
+
+	npages = be32_to_cpu(in->num_entries);
+
+	p = rb_first(&dev->priv.page_root);
+	while (p && i < npages) {
+		fwp = rb_entry(p, struct fw_page, rb_node);
+		out->pas[i] = cpu_to_be64(fwp->addr);
+		p = rb_next(p);
+		i++;
+	}
+
+	out->num_entries = cpu_to_be32(i);
+	return 0;
+}
+
 static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 			 int *nclaimed)
 {
@@ -398,15 +424,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	in.func_id = cpu_to_be16(func_id);
 	in.num_entries = cpu_to_be32(npages);
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
+	err = reclaim_pages_cmd(dev, &in, sizeof(in), out, outlen);
 	if (err) {
-		mlx5_core_err(dev, "failed reclaiming pages\n");
-		goto out_free;
-	}
-	dev->priv.fw_pages -= npages;
-
-	if (out->hdr.status) {
-		err = mlx5_cmd_status_to_err(&out->hdr);
+		mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
 		goto out_free;
 	}
 
@@ -417,13 +437,15 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 		err = -EINVAL;
 		goto out_free;
 	}
-	if (nclaimed)
-		*nclaimed = num_claimed;
 
 	for (i = 0; i < num_claimed; i++) {
 		addr = be64_to_cpu(out->pas[i]);
 		free_4k(dev, addr);
 	}
+
+	if (nclaimed)
+		*nclaimed = num_claimed;
+
 	dev->priv.fw_pages -= num_claimed;
 	if (func_id)
 		dev->priv.vfs_pages -= num_claimed;
@@ -514,14 +536,10 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 		p = rb_first(&dev->priv.page_root);
 		if (p) {
 			fwp = rb_entry(p, struct fw_page, rb_node);
-			if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-				free_4k(dev, fwp->addr);
-				nclaimed = 1;
-			} else {
-				err = reclaim_pages(dev, fwp->func_id,
-						    optimal_reclaimed_pages(),
-						    &nclaimed);
-			}
+			err = reclaim_pages(dev, fwp->func_id,
+					    optimal_reclaimed_pages(),
+					    &nclaimed);
+
 			if (err) {
 				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
 					       err);
@@ -536,6 +554,13 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 		}
 	} while (p);
 
+	WARN(dev->priv.fw_pages,
+	     "FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.fw_pages);
+	WARN(dev->priv.vfs_pages,
+	     "VFs FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.vfs_pages);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index daf44cd4c566..91846dfcbe9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -513,7 +513,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
 	void *nic_vport_context;
-	u8 *guid;
 	void *in;
 	int err;
 
@@ -535,8 +534,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 
 	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
 					 in, nic_vport_context);
-	guid = MLX5_ADDR_OF(nic_vport_context, nic_vport_context,
-			    node_guid);
 	MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid);
 
 	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c
index 7066954c39d6..0a26b11ca8f6 100644
--- a/drivers/net/ethernet/microchip/enc28j60.c
+++ b/drivers/net/ethernet/microchip/enc28j60.c
@@ -1151,7 +1151,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 			enc28j60_phy_read(priv, PHIR);
 		}
 		/* TX complete handler */
-		if ((intflags & EIR_TXIF) != 0) {
+		if (((intflags & EIR_TXIF) != 0) &&
+		    ((intflags & EIR_TXERIF) == 0)) {
 			bool err = false;
 			loop++;
 			if (netif_msg_intr(priv))
@@ -1203,7 +1204,7 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 					enc28j60_tx_clear(ndev, true);
 			} else
 				enc28j60_tx_clear(ndev, true);
-			locked_reg_bfclr(priv, EIR, EIR_TXERIF);
+			locked_reg_bfclr(priv, EIR, EIR_TXERIF | EIR_TXIF);
 		}
 		/* RX Error handler */
 		if ((intflags & EIR_RXERIF) != 0) {
@@ -1238,6 +1239,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
  */
 static void enc28j60_hw_tx(struct enc28j60_net *priv)
 {
+	BUG_ON(!priv->tx_skb);
+
 	if (netif_msg_tx_queued(priv))
 		printk(KERN_DEBUG DRV_NAME
 			": Tx Packet Len:%d\n", priv->tx_skb->len);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 607bb7d4514d..87c642d3b075 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -772,6 +772,8 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	tx_ring->tx_stats.tx_bytes += skb->len;
 	tx_ring->tx_stats.xmit_called++;
 
+	/* Ensure writes are complete before HW fetches Tx descriptors */
+	wmb();
 	qlcnic_update_cmd_producer(tx_ring);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a473c182c91d..e4071265be76 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2804,7 +2804,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 				priv->tx_path_in_lpi_mode = true;
 			if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE)
 				priv->tx_path_in_lpi_mode = false;
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW)
+			if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr)
 				priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
 							priv->rx_tail_addr,
 							STMMAC_CHAN0);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index cc39cefeae45..9b3dc3c61e00 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1072,12 +1072,17 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
+	struct geneve_dev *geneve = netdev_priv(dev);
 	/* The max_mtu calculation does not take account of GENEVE
 	 * options, to avoid excluding potentially valid
 	 * configurations.
 	 */
-	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - sizeof(struct iphdr)
-		- dev->hard_header_len;
+	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len;
+
+	if (geneve->remote.sa.sa_family == AF_INET6)
+		max_mtu -= sizeof(struct ipv6hdr);
+	else
+		max_mtu -= sizeof(struct iphdr);
 
 	if (new_mtu < 68)
 		return -EINVAL;
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 0e7eff7f1cd2..8bcd78f94966 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2640,6 +2640,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 		u64_stats_update_begin(&secy_stats->syncp);
 		secy_stats->stats.OutPktsUntagged++;
 		u64_stats_update_end(&secy_stats->syncp);
+		skb->dev = macsec->real_dev;
 		len = skb->len;
 		ret = dev_queue_xmit(skb);
 		count_tx(dev, ret, len);
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 2afa61b51d41..91177a4a32ad 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -57,6 +57,7 @@
 
 /* PHY CTRL bits */
 #define DP83867_PHYCR_FIFO_DEPTH_SHIFT		14
+#define DP83867_PHYCR_FIFO_DEPTH_MASK		(3 << 14)
 
 /* RGMIIDCTL bits */
 #define DP83867_RGMII_TX_CLK_DELAY_SHIFT	4
@@ -133,8 +134,8 @@ static int dp83867_of_init(struct phy_device *phydev)
 static int dp83867_config_init(struct phy_device *phydev)
 {
 	struct dp83867_private *dp83867;
-	int ret;
-	u16 val, delay;
+	int ret, val;
+	u16 delay;
 
 	if (!phydev->priv) {
 		dp83867 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83867),
@@ -151,8 +152,12 @@ static int dp83867_config_init(struct phy_device *phydev)
 	}
 
 	if (phy_interface_is_rgmii(phydev)) {
-		ret = phy_write(phydev, MII_DP83867_PHYCTRL,
-			(dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT));
+		val = phy_read(phydev, MII_DP83867_PHYCTRL);
+		if (val < 0)
+			return val;
+		val &= ~DP83867_PHYCR_FIFO_DEPTH_MASK;
+		val |= (dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT);
+		ret = phy_write(phydev, MII_DP83867_PHYCTRL, val);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 53759c315b97..877c9516e781 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -854,6 +854,13 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	if (cdc_ncm_init(dev))
 		goto error2;
 
+	/* Some firmwares need a pause here or they will silently fail
+	 * to set up the interface properly.  This value was decided
+	 * empirically on a Sierra Wireless MC7455 running 02.08.02.00
+	 * firmware.
+	 */
+	usleep_range(10000, 20000);
+
 	/* configure data interface */
 	temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
 	if (temp) {
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 4e257b8d8f3e..0da72d39b4f9 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -31,7 +31,7 @@
 #define NETNEXT_VERSION		"08"
 
 /* Information for net */
-#define NET_VERSION		"4"
+#define NET_VERSION		"5"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -624,6 +624,7 @@ struct r8152 {
 		int (*eee_get)(struct r8152 *, struct ethtool_eee *);
 		int (*eee_set)(struct r8152 *, struct ethtool_eee *);
 		bool (*in_nway)(struct r8152 *);
+		void (*autosuspend_en)(struct r8152 *tp, bool enable);
 	} rtl_ops;
 
 	int intr_interval;
@@ -2408,9 +2409,6 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 	if (enable) {
 		u32 ocp_data;
 
-		r8153_u1u2en(tp, false);
-		r8153_u2p3en(tp, false);
-
 		__rtl_set_wol(tp, WAKE_ANY);
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
@@ -2421,7 +2419,28 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
 	} else {
+		u32 ocp_data;
+
 		__rtl_set_wol(tp, tp->saved_wolopts);
+
+		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
+
+		ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34);
+		ocp_data &= ~LINK_OFF_WAKE_EN;
+		ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data);
+
+		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
+	}
+}
+
+static void rtl8153_runtime_enable(struct r8152 *tp, bool enable)
+{
+	rtl_runtime_suspend_enable(tp, enable);
+
+	if (enable) {
+		r8153_u1u2en(tp, false);
+		r8153_u2p3en(tp, false);
+	} else {
 		r8153_u2p3en(tp, true);
 		r8153_u1u2en(tp, true);
 	}
@@ -3512,7 +3531,7 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
 		napi_disable(&tp->napi);
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_stop_rx(tp);
-			rtl_runtime_suspend_enable(tp, true);
+			tp->rtl_ops.autosuspend_en(tp, true);
 		} else {
 			cancel_delayed_work_sync(&tp->schedule);
 			tp->rtl_ops.down(tp);
@@ -3538,7 +3557,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 
 	if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
-			rtl_runtime_suspend_enable(tp, false);
+			tp->rtl_ops.autosuspend_en(tp, false);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 			napi_disable(&tp->napi);
 			set_bit(WORK_ENABLE, &tp->flags);
@@ -3557,7 +3576,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 		usb_submit_urb(tp->intr_urb, GFP_KERNEL);
 	} else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 		if (tp->netdev->flags & IFF_UP)
-			rtl_runtime_suspend_enable(tp, false);
+			tp->rtl_ops.autosuspend_en(tp, false);
 		clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 	}
 
@@ -4137,6 +4156,7 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->eee_get		= r8152_get_eee;
 		ops->eee_set		= r8152_set_eee;
 		ops->in_nway		= rtl8152_in_nway;
+		ops->autosuspend_en	= rtl_runtime_suspend_enable;
 		break;
 
 	case RTL_VER_03:
@@ -4152,6 +4172,7 @@ static int rtl_ops_init(struct r8152 *tp)
 		ops->eee_get		= r8153_get_eee;
 		ops->eee_set		= r8153_set_eee;
 		ops->in_nway		= rtl8153_in_nway;
+		ops->autosuspend_en	= rtl8153_runtime_enable;
 		break;
 
 	default:
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 61ba46404937..6086a0163249 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -395,8 +395,11 @@ int usbnet_change_mtu (struct net_device *net, int new_mtu)
 	dev->hard_mtu = net->mtu + net->hard_header_len;
 	if (dev->rx_urb_size == old_hard_mtu) {
 		dev->rx_urb_size = dev->hard_mtu;
-		if (dev->rx_urb_size > old_rx_urb_size)
+		if (dev->rx_urb_size > old_rx_urb_size) {
+			usbnet_pause_rx(dev);
 			usbnet_unlink_rx_urbs(dev);
+			usbnet_resume_rx(dev);
+		}
 	}
 
 	/* max qlen depend on hard_mtu and rx_urb_size */
@@ -1508,8 +1511,9 @@ static void usbnet_bh (unsigned long param)
 	} else if (netif_running (dev->net) &&
 		   netif_device_present (dev->net) &&
 		   netif_carrier_ok(dev->net) &&
-		   !timer_pending (&dev->delay) &&
-		   !test_bit (EVENT_RX_HALT, &dev->flags)) {
+		   !timer_pending(&dev->delay) &&
+		   !test_bit(EVENT_RX_PAUSED, &dev->flags) &&
+		   !test_bit(EVENT_RX_HALT, &dev->flags)) {
 		int	temp = dev->rxq.qlen;
 
 		if (temp < RX_QLEN(dev)) {
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index f7718ec685fa..cea8350fbc7e 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -344,6 +344,8 @@ struct device *nd_pfn_create(struct nd_region *nd_region)
 int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 {
 	u64 checksum, offset;
+	unsigned long align;
+	enum nd_pfn_mode mode;
 	struct nd_namespace_io *nsio;
 	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
@@ -386,22 +388,50 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 		return -ENXIO;
 	}
 
+	align = le32_to_cpu(pfn_sb->align);
+	offset = le64_to_cpu(pfn_sb->dataoff);
+	if (align == 0)
+		align = 1UL << ilog2(offset);
+	mode = le32_to_cpu(pfn_sb->mode);
+
 	if (!nd_pfn->uuid) {
-		/* from probe we allocate */
+		/*
+		 * When probing a namepace via nd_pfn_probe() the uuid
+		 * is NULL (see: nd_pfn_devinit()) we init settings from
+		 * pfn_sb
+		 */
 		nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL);
 		if (!nd_pfn->uuid)
 			return -ENOMEM;
+		nd_pfn->align = align;
+		nd_pfn->mode = mode;
 	} else {
-		/* from init we validate */
+		/*
+		 * When probing a pfn / dax instance we validate the
+		 * live settings against the pfn_sb
+		 */
 		if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
 			return -ENODEV;
+
+		/*
+		 * If the uuid validates, but other settings mismatch
+		 * return EINVAL because userspace has managed to change
+		 * the configuration without specifying new
+		 * identification.
+		 */
+		if (nd_pfn->align != align || nd_pfn->mode != mode) {
+			dev_err(&nd_pfn->dev,
+					"init failed, settings mismatch\n");
+			dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n",
+					nd_pfn->align, align, nd_pfn->mode,
+					mode);
+			return -EINVAL;
+		}
 	}
 
-	if (nd_pfn->align == 0)
-		nd_pfn->align = le32_to_cpu(pfn_sb->align);
-	if (nd_pfn->align > nvdimm_namespace_capacity(ndns)) {
+	if (align > nvdimm_namespace_capacity(ndns)) {
 		dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
-				nd_pfn->align, nvdimm_namespace_capacity(ndns));
+				align, nvdimm_namespace_capacity(ndns));
 		return -EINVAL;
 	}
 
@@ -411,7 +441,6 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 	 * namespace has changed since the pfn superblock was
 	 * established.
 	 */
-	offset = le64_to_cpu(pfn_sb->dataoff);
 	nsio = to_nd_namespace_io(&ndns->dev);
 	if (offset >= resource_size(&nsio->res)) {
 		dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
@@ -419,10 +448,11 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 		return -EBUSY;
 	}
 
-	if ((nd_pfn->align && !IS_ALIGNED(offset, nd_pfn->align))
+	if ((align && !IS_ALIGNED(offset, align))
 			|| !IS_ALIGNED(offset, PAGE_SIZE)) {
-		dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled\n",
-				offset);
+		dev_err(&nd_pfn->dev,
+				"bad offset: %#llx dax disabled align: %#lx\n",
+				offset, align);
 		return -ENXIO;
 	}
 
@@ -502,7 +532,6 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
 	res->start += start_pad;
 	res->end -= end_trunc;
 
-	nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
 	if (nd_pfn->mode == PFN_MODE_RAM) {
 		if (offset < SZ_8K)
 			return ERR_PTR(-EINVAL);
diff --git a/drivers/phy/phy-bcm-ns-usb2.c b/drivers/phy/phy-bcm-ns-usb2.c
index 95ab6b2a0de5..58dff80e9386 100644
--- a/drivers/phy/phy-bcm-ns-usb2.c
+++ b/drivers/phy/phy-bcm-ns-usb2.c
@@ -109,8 +109,8 @@ static int bcm_ns_usb2_probe(struct platform_device *pdev)
 	}
 
 	usb2->phy = devm_phy_create(dev, NULL, &ops);
-	if (IS_ERR(dev))
-		return PTR_ERR(dev);
+	if (IS_ERR(usb2->phy))
+		return PTR_ERR(usb2->phy);
 
 	phy_set_drvdata(usb2->phy, usb2);
 	platform_set_drvdata(pdev, usb2);
diff --git a/drivers/phy/phy-miphy28lp.c b/drivers/phy/phy-miphy28lp.c
index 3acd2a1808df..213e2e15339c 100644
--- a/drivers/phy/phy-miphy28lp.c
+++ b/drivers/phy/phy-miphy28lp.c
@@ -1143,7 +1143,8 @@ static int miphy28lp_probe_resets(struct device_node *node,
 	struct miphy28lp_dev *miphy_dev = miphy_phy->phydev;
 	int err;
 
-	miphy_phy->miphy_rst = of_reset_control_get(node, "miphy-sw-rst");
+	miphy_phy->miphy_rst =
+		of_reset_control_get_shared(node, "miphy-sw-rst");
 
 	if (IS_ERR(miphy_phy->miphy_rst)) {
 		dev_err(miphy_dev->dev,
diff --git a/drivers/phy/phy-rcar-gen3-usb2.c b/drivers/phy/phy-rcar-gen3-usb2.c
index 76bb88f0700a..4be3f5dbbc9f 100644
--- a/drivers/phy/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/phy-rcar-gen3-usb2.c
@@ -144,12 +144,6 @@ static void rcar_gen3_init_for_peri(struct rcar_gen3_chan *ch)
 	extcon_set_cable_state_(ch->extcon, EXTCON_USB, true);
 }
 
-static bool rcar_gen3_check_vbus(struct rcar_gen3_chan *ch)
-{
-	return !!(readl(ch->base + USB2_ADPCTRL) &
-		  USB2_ADPCTRL_OTGSESSVLD);
-}
-
 static bool rcar_gen3_check_id(struct rcar_gen3_chan *ch)
 {
 	return !!(readl(ch->base + USB2_ADPCTRL) & USB2_ADPCTRL_IDDIG);
@@ -157,13 +151,7 @@ static bool rcar_gen3_check_id(struct rcar_gen3_chan *ch)
 
 static void rcar_gen3_device_recognition(struct rcar_gen3_chan *ch)
 {
-	bool is_host = true;
-
-	/* B-device? */
-	if (rcar_gen3_check_id(ch) && rcar_gen3_check_vbus(ch))
-		is_host = false;
-
-	if (is_host)
+	if (!rcar_gen3_check_id(ch))
 		rcar_gen3_init_for_host(ch);
 	else
 		rcar_gen3_init_for_peri(ch);
diff --git a/drivers/phy/phy-rockchip-dp.c b/drivers/phy/phy-rockchip-dp.c
index 793ecb6d87bc..8b267a746576 100644
--- a/drivers/phy/phy-rockchip-dp.c
+++ b/drivers/phy/phy-rockchip-dp.c
@@ -90,7 +90,7 @@ static int rockchip_dp_phy_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	dp = devm_kzalloc(dev, sizeof(*dp), GFP_KERNEL);
-	if (IS_ERR(dp))
+	if (!dp)
 		return -ENOMEM;
 
 	dp->dev = dev;
diff --git a/drivers/phy/phy-stih407-usb.c b/drivers/phy/phy-stih407-usb.c
index 53cf8d1b4116..b1f44ab669fb 100644
--- a/drivers/phy/phy-stih407-usb.c
+++ b/drivers/phy/phy-stih407-usb.c
@@ -111,7 +111,7 @@ static int stih407_usb2_picophy_probe(struct platform_device *pdev)
 		return PTR_ERR(phy_dev->rstc);
 	}
 
-	phy_dev->rstport = devm_reset_control_get(dev, "port");
+	phy_dev->rstport = devm_reset_control_get_exclusive(dev, "port");
 	if (IS_ERR(phy_dev->rstport)) {
 		dev_err(dev, "failed to ctrl picoPHY reset\n");
 		return PTR_ERR(phy_dev->rstport);
diff --git a/drivers/phy/phy-sun4i-usb.c b/drivers/phy/phy-sun4i-usb.c
index bae54f7a1f48..de3101fbbf40 100644
--- a/drivers/phy/phy-sun4i-usb.c
+++ b/drivers/phy/phy-sun4i-usb.c
@@ -175,7 +175,7 @@ static void sun4i_usb_phy_write(struct sun4i_usb_phy *phy, u32 addr, u32 data,
 {
 	struct sun4i_usb_phy_data *phy_data = to_sun4i_usb_phy_data(phy);
 	u32 temp, usbc_bit = BIT(phy->index * 2);
-	void *phyctl = phy_data->base + phy_data->cfg->phyctl_offset;
+	void __iomem *phyctl = phy_data->base + phy_data->cfg->phyctl_offset;
 	int i;
 
 	mutex_lock(&phy_data->mutex);
@@ -514,9 +514,9 @@ static int sun4i_usb_phy_remove(struct platform_device *pdev)
 
 	if (data->vbus_power_nb_registered)
 		power_supply_unreg_notifier(&data->vbus_power_nb);
-	if (data->id_det_irq >= 0)
+	if (data->id_det_irq > 0)
 		devm_free_irq(dev, data->id_det_irq, data);
-	if (data->vbus_det_irq >= 0)
+	if (data->vbus_det_irq > 0)
 		devm_free_irq(dev, data->vbus_det_irq, data);
 
 	cancel_delayed_work_sync(&data->detect);
@@ -645,11 +645,11 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev)
 
 	data->id_det_irq = gpiod_to_irq(data->id_det_gpio);
 	data->vbus_det_irq = gpiod_to_irq(data->vbus_det_gpio);
-	if ((data->id_det_gpio && data->id_det_irq < 0) ||
-	    (data->vbus_det_gpio && data->vbus_det_irq < 0))
+	if ((data->id_det_gpio && data->id_det_irq <= 0) ||
+	    (data->vbus_det_gpio && data->vbus_det_irq <= 0))
 		data->phy0_poll = true;
 
-	if (data->id_det_irq >= 0) {
+	if (data->id_det_irq > 0) {
 		ret = devm_request_irq(dev, data->id_det_irq,
 				sun4i_usb_phy0_id_vbus_det_irq,
 				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
@@ -660,7 +660,7 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (data->vbus_det_irq >= 0) {
+	if (data->vbus_det_irq > 0) {
 		ret = devm_request_irq(dev, data->vbus_det_irq,
 				sun4i_usb_phy0_id_vbus_det_irq,
 				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
diff --git a/drivers/platform/chrome/cros_ec_dev.c b/drivers/platform/chrome/cros_ec_dev.c
index 6d8ee3b15872..8abd80dbcbed 100644
--- a/drivers/platform/chrome/cros_ec_dev.c
+++ b/drivers/platform/chrome/cros_ec_dev.c
@@ -151,13 +151,19 @@ static long ec_device_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg)
 		goto exit;
 	}
 
+	if (u_cmd.outsize != s_cmd->outsize ||
+	    u_cmd.insize != s_cmd->insize) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
 	s_cmd->command += ec->cmd_offset;
 	ret = cros_ec_cmd_xfer(ec->ec_dev, s_cmd);
 	/* Only copy data to userland if data was received. */
 	if (ret < 0)
 		goto exit;
 
-	if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + u_cmd.insize))
+	if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + s_cmd->insize))
 		ret = -EFAULT;
 exit:
 	kfree(s_cmd);
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 63cd5e68c864..3a6d0290c54c 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -296,7 +296,7 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 		if (!sreg->sel && !strcmp(sreg->name, "vddpu"))
 			sreg->sel = 22;
 
-		if (!sreg->sel) {
+		if (!sreg->bypass && !sreg->sel) {
 			dev_err(&pdev->dev, "Failed to read a valid default voltage selector.\n");
 			return -EINVAL;
 		}
diff --git a/drivers/regulator/max77620-regulator.c b/drivers/regulator/max77620-regulator.c
index 321e804aeab0..a1b49a6d538f 100644
--- a/drivers/regulator/max77620-regulator.c
+++ b/drivers/regulator/max77620-regulator.c
@@ -123,6 +123,9 @@ static int max77620_regulator_set_fps_src(struct max77620_regulator *pmic,
 	unsigned int val;
 	int ret;
 
+	if (!rinfo)
+		return 0;
+
 	switch (fps_src) {
 	case MAX77620_FPS_SRC_0:
 	case MAX77620_FPS_SRC_1:
@@ -171,6 +174,9 @@ static int max77620_regulator_set_fps_slots(struct max77620_regulator *pmic,
 	int pd = rpdata->active_fps_pd_slot;
 	int ret = 0;
 
+	if (!rinfo)
+		return 0;
+
 	if (is_suspend) {
 		pu = rpdata->suspend_fps_pu_slot;
 		pd = rpdata->suspend_fps_pd_slot;
@@ -680,7 +686,6 @@ static struct max77620_regulator_info max77620_regs_info[MAX77620_NUM_REGS] = {
 	RAIL_SD(SD1, sd1, "in-sd1", SD1, 600000, 1550000, 12500, 0x22, SD1),
 	RAIL_SD(SD2, sd2, "in-sd2", SDX, 600000, 3787500, 12500, 0xFF, NONE),
 	RAIL_SD(SD3, sd3, "in-sd3", SDX, 600000, 3787500, 12500, 0xFF, NONE),
-	RAIL_SD(SD4, sd4, "in-sd4", SDX, 600000, 3787500, 12500, 0xFF, NONE),
 
 	RAIL_LDO(LDO0, ldo0, "in-ldo0-1", N, 800000, 2375000, 25000),
 	RAIL_LDO(LDO1, ldo1, "in-ldo0-1", N, 800000, 2375000, 25000),
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 80b1979e8d95..df036b872b05 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1051,6 +1051,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l2_set_offline(cgdev);
 
 	if (card->dev) {
+		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
 		card->dev = NULL;
 	}
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ac544330daeb..709b52339ff9 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3226,6 +3226,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l3_set_offline(cgdev);
 
 	if (card->dev) {
+		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
 		card->dev = NULL;
 	}
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index d6a691e27d33..d6803a9e5ab8 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -10093,6 +10093,7 @@ static int ipr_probe_ioa(struct pci_dev *pdev,
 		ioa_cfg->intr_flag = IPR_USE_MSI;
 	else {
 		ioa_cfg->intr_flag = IPR_USE_LSI;
+		ioa_cfg->clear_isr = 1;
 		ioa_cfg->nvectors = 1;
 		dev_info(&pdev->dev, "Cannot enable MSI.\n");
 	}
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 5649c200d37c..a92a62dea793 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2548,7 +2548,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 	if (!vha->flags.online)
 		return;
 
-	if (rsp->msix->cpuid != smp_processor_id()) {
+	if (rsp->msix && rsp->msix->cpuid != smp_processor_id()) {
 		/* if kernel does not notify qla of IRQ's CPU change,
 		 * then set it here.
 		 */
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index ff41c310c900..eaccd651ccda 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -429,7 +429,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 	 * here, and we don't know what device it is
 	 * trying to work with, leave it as-is.
 	 */
-	vmax = 8;	/* max length of vendor */
+	vmax = sizeof(devinfo->vendor);
 	vskip = vendor;
 	while (vmax > 0 && *vskip == ' ') {
 		vmax--;
@@ -439,7 +439,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 	while (vmax > 0 && vskip[vmax - 1] == ' ')
 		--vmax;
 
-	mmax = 16;	/* max length of model */
+	mmax = sizeof(devinfo->model);
 	mskip = model;
 	while (mmax > 0 && *mskip == ' ') {
 		mmax--;
@@ -455,10 +455,12 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor,
 			 * Behave like the older version of get_device_flags.
 			 */
 			if (memcmp(devinfo->vendor, vskip, vmax) ||
-					devinfo->vendor[vmax])
+					(vmax < sizeof(devinfo->vendor) &&
+						devinfo->vendor[vmax]))
 				continue;
 			if (memcmp(devinfo->model, mskip, mmax) ||
-					devinfo->model[mmax])
+					(mmax < sizeof(devinfo->model) &&
+						devinfo->model[mmax]))
 				continue;
 			return devinfo;
 		} else {
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index cd89682065b9..1026e180eed7 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -578,7 +578,7 @@ static int rockchip_spi_transfer_one(
 		struct spi_device *spi,
 		struct spi_transfer *xfer)
 {
-	int ret = 1;
+	int ret = 0;
 	struct rockchip_spi *rs = spi_master_get_devdata(master);
 
 	WARN_ON(readl_relaxed(rs->regs + ROCKCHIP_SPI_SSIENR) &&
@@ -627,6 +627,8 @@ static int rockchip_spi_transfer_one(
 			spi_enable_chip(rs, 1);
 			ret = rockchip_spi_prepare_dma(rs);
 		}
+		/* successful DMA prepare means the transfer is in progress */
+		ret = ret ? ret : 1;
 	} else {
 		spi_enable_chip(rs, 1);
 		ret = rockchip_spi_pio_transfer(rs);
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index 1ddd9e2309b6..cf007f3b83ec 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -173,13 +173,17 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 {
 	struct sun4i_spi *sspi = spi_master_get_devdata(master);
 	unsigned int mclk_rate, div, timeout;
+	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
 	u32 reg;
 
 	/* We don't support transfer larger than the FIFO */
 	if (tfr->len > SUN4I_FIFO_DEPTH)
-		return -EINVAL;
+		return -EMSGSIZE;
+
+	if (tfr->tx_buf && tfr->len >= SUN4I_FIFO_DEPTH)
+		return -EMSGSIZE;
 
 	reinit_completion(&sspi->done);
 	sspi->tx_buf = tfr->tx_buf;
@@ -269,8 +273,12 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 	sun4i_spi_write(sspi, SUN4I_BURST_CNT_REG, SUN4I_BURST_CNT(tfr->len));
 	sun4i_spi_write(sspi, SUN4I_XMIT_CNT_REG, SUN4I_XMIT_CNT(tx_len));
 
-	/* Fill the TX FIFO */
-	sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH);
+	/*
+	 * Fill the TX FIFO
+	 * Filling the FIFO fully causes timeout for some reason
+	 * at least on spi2 on A10s
+	 */
+	sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH - 1);
 
 	/* Enable the interrupts */
 	sun4i_spi_write(sspi, SUN4I_INT_CTL_REG, SUN4I_INT_CTL_TC);
@@ -279,9 +287,16 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 	reg = sun4i_spi_read(sspi, SUN4I_CTL_REG);
 	sun4i_spi_write(sspi, SUN4I_CTL_REG, reg | SUN4I_CTL_XCH);
 
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(1000));
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
 	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index 42e2c4bd690a..7fce79a60608 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -160,6 +160,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 {
 	struct sun6i_spi *sspi = spi_master_get_devdata(master);
 	unsigned int mclk_rate, div, timeout;
+	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
 	u32 reg;
@@ -269,9 +270,16 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
 	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH);
 
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(1000));
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
 	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 443f664534e1..29ea8d2f9824 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -646,6 +646,13 @@ free_master:
 
 static int ti_qspi_remove(struct platform_device *pdev)
 {
+	struct ti_qspi *qspi = platform_get_drvdata(pdev);
+	int rc;
+
+	rc = spi_master_suspend(qspi->master);
+	if (rc)
+		return rc;
+
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
diff --git a/drivers/staging/iio/accel/sca3000_core.c b/drivers/staging/iio/accel/sca3000_core.c
index a8f533af9eca..ec12181822e6 100644
--- a/drivers/staging/iio/accel/sca3000_core.c
+++ b/drivers/staging/iio/accel/sca3000_core.c
@@ -594,7 +594,7 @@ static ssize_t sca3000_read_frequency(struct device *dev,
 		goto error_ret_mut;
 	ret = sca3000_read_ctrl_reg(st, SCA3000_REG_CTRL_SEL_OUT_CTRL);
 	mutex_unlock(&st->lock);
-	if (ret)
+	if (ret < 0)
 		goto error_ret;
 	val = ret;
 	if (base_freq > 0)
diff --git a/drivers/staging/iio/adc/ad7606_spi.c b/drivers/staging/iio/adc/ad7606_spi.c
index 825da0769936..9587fa86dc69 100644
--- a/drivers/staging/iio/adc/ad7606_spi.c
+++ b/drivers/staging/iio/adc/ad7606_spi.c
@@ -21,7 +21,7 @@ static int ad7606_spi_read_block(struct device *dev,
 {
 	struct spi_device *spi = to_spi_device(dev);
 	int i, ret;
-	unsigned short *data;
+	unsigned short *data = buf;
 	__be16 *bdata = buf;
 
 	ret = spi_read(spi, buf, count * 2);
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 9f43976f4ef2..170ac980abcb 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -444,10 +444,10 @@ static ssize_t ad5933_store(struct device *dev,
 		st->settling_cycles = val;
 
 		/* 2x, 4x handling, see datasheet */
-		if (val > 511)
-			val = (val >> 1) | (1 << 9);
-		else if (val > 1022)
+		if (val > 1022)
 			val = (val >> 2) | (3 << 9);
+		else if (val > 511)
+			val = (val >> 1) | (1 << 9);
 
 		dat = cpu_to_be16(val);
 		ret = ad5933_i2c_write(st->client,
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index f856c4544eea..51e0d32883ba 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -667,8 +667,11 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty)
 		fsi = tty->driver_data;
 	else
 		fsi = tty->link->driver_data;
-	devpts_kill_index(fsi, tty->index);
-	devpts_release(fsi);
+
+	if (fsi) {
+		devpts_kill_index(fsi, tty->index);
+		devpts_release(fsi);
+	}
 }
 
 static const struct tty_operations ptm_unix98_ops = {
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index dc125322f48f..5b0fe97c46ca 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -750,6 +750,7 @@ static void visual_init(struct vc_data *vc, int num, int init)
 	vc->vc_complement_mask = 0;
 	vc->vc_can_do_color = 0;
 	vc->vc_panic_force_write = false;
+	vc->vc_cur_blink_ms = DEFAULT_CURSOR_BLINK_MS;
 	vc->vc_sw->con_init(vc, init);
 	if (!vc->vc_complement_mask)
 		vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800;
diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c
index 9059b7dc185e..2f537bbdda09 100644
--- a/drivers/usb/common/usb-otg-fsm.c
+++ b/drivers/usb/common/usb-otg-fsm.c
@@ -21,6 +21,7 @@
  * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/mutex.h>
@@ -450,3 +451,4 @@ int otg_statemachine(struct otg_fsm *fsm)
 	return fsm->state_changed;
 }
 EXPORT_SYMBOL_GPL(otg_statemachine);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 34b837ae1ed7..d2e3f655c26f 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2598,26 +2598,23 @@ EXPORT_SYMBOL_GPL(usb_create_hcd);
  * Don't deallocate the bandwidth_mutex until the last shared usb_hcd is
  * deallocated.
  *
- * Make sure to only deallocate the bandwidth_mutex when the primary HCD is
- * freed.  When hcd_release() is called for either hcd in a peer set
- * invalidate the peer's ->shared_hcd and ->primary_hcd pointers to
- * block new peering attempts
+ * Make sure to deallocate the bandwidth_mutex only when the last HCD is
+ * freed.  When hcd_release() is called for either hcd in a peer set,
+ * invalidate the peer's ->shared_hcd and ->primary_hcd pointers.
  */
 static void hcd_release(struct kref *kref)
 {
 	struct usb_hcd *hcd = container_of (kref, struct usb_hcd, kref);
 
 	mutex_lock(&usb_port_peer_mutex);
-	if (usb_hcd_is_primary_hcd(hcd)) {
-		kfree(hcd->address0_mutex);
-		kfree(hcd->bandwidth_mutex);
-	}
 	if (hcd->shared_hcd) {
 		struct usb_hcd *peer = hcd->shared_hcd;
 
 		peer->shared_hcd = NULL;
-		if (peer->primary_hcd == hcd)
-			peer->primary_hcd = NULL;
+		peer->primary_hcd = NULL;
+	} else {
+		kfree(hcd->address0_mutex);
+		kfree(hcd->bandwidth_mutex);
 	}
 	mutex_unlock(&usb_port_peer_mutex);
 	kfree(hcd);
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index 055c55b0fb54..89a2f712fdfe 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -233,7 +233,8 @@ static int st_dwc3_probe(struct platform_device *pdev)
 	dev_vdbg(&pdev->dev, "glue-logic addr 0x%p, syscfg-reg offset 0x%x\n",
 		 dwc3_data->glue_base, dwc3_data->syscfg_reg_off);
 
-	dwc3_data->rstc_pwrdn = devm_reset_control_get(dev, "powerdown");
+	dwc3_data->rstc_pwrdn =
+		devm_reset_control_get_exclusive(dev, "powerdown");
 	if (IS_ERR(dwc3_data->rstc_pwrdn)) {
 		dev_err(&pdev->dev, "could not get power controller\n");
 		ret = PTR_ERR(dwc3_data->rstc_pwrdn);
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 076970a54f89..4ce10bcca18b 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -423,36 +423,7 @@ upload:
 
 	return 0;
 }
-static int __init check_prereq(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	if (!xen_initial_domain())
-		return -ENODEV;
-
-	if (!acpi_gbl_FADT.smi_command)
-		return -ENODEV;
-
-	if (c->x86_vendor == X86_VENDOR_INTEL) {
-		if (!cpu_has(c, X86_FEATURE_EST))
-			return -ENODEV;
 
-		return 0;
-	}
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/* Copied from powernow-k8.h, can't include ../cpufreq/powernow
-		 * as we get compile warnings for the static functions.
-		 */
-#define CPUID_FREQ_VOLT_CAPABILITIES    0x80000007
-#define USE_HW_PSTATE                   0x00000080
-		u32 eax, ebx, ecx, edx;
-		cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
-		if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE)
-			return -ENODEV;
-		return 0;
-	}
-	return -ENODEV;
-}
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance __percpu *acpi_perf_data;
 
@@ -509,10 +480,10 @@ struct notifier_block xen_acpi_processor_resume_nb = {
 static int __init xen_acpi_processor_init(void)
 {
 	unsigned int i;
-	int rc = check_prereq();
+	int rc;
 
-	if (rc)
-		return rc;
+	if (!xen_initial_domain())
+		return -ENODEV;
 
 	nr_acpi_bits = get_max_acpi_id() + 1;
 	acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index cacf30d14747..7487971f9f78 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -316,11 +316,18 @@ static int xenbus_write_transaction(unsigned msg_type,
 			rc = -ENOMEM;
 			goto out;
 		}
+	} else {
+		list_for_each_entry(trans, &u->transactions, list)
+			if (trans->handle.id == u->u.msg.tx_id)
+				break;
+		if (&trans->list == &u->transactions)
+			return -ESRCH;
 	}
 
 	reply = xenbus_dev_request_and_reply(&u->u.msg);
 	if (IS_ERR(reply)) {
-		kfree(trans);
+		if (msg_type == XS_TRANSACTION_START)
+			kfree(trans);
 		rc = PTR_ERR(reply);
 		goto out;
 	}
@@ -333,12 +340,7 @@ static int xenbus_write_transaction(unsigned msg_type,
 			list_add(&trans->list, &u->transactions);
 		}
 	} else if (u->u.msg.type == XS_TRANSACTION_END) {
-		list_for_each_entry(trans, &u->transactions, list)
-			if (trans->handle.id == u->u.msg.tx_id)
-				break;
-		BUG_ON(&trans->list == &u->transactions);
 		list_del(&trans->list);
-
 		kfree(trans);
 	}
 
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index 374b12af8812..22f7cd711c57 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -232,10 +232,10 @@ static void transaction_resume(void)
 void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 {
 	void *ret;
-	struct xsd_sockmsg req_msg = *msg;
+	enum xsd_sockmsg_type type = msg->type;
 	int err;
 
-	if (req_msg.type == XS_TRANSACTION_START)
+	if (type == XS_TRANSACTION_START)
 		transaction_start();
 
 	mutex_lock(&xs_state.request_mutex);
@@ -249,12 +249,8 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg)
 
 	mutex_unlock(&xs_state.request_mutex);
 
-	if (IS_ERR(ret))
-		return ret;
-
 	if ((msg->type == XS_TRANSACTION_END) ||
-	    ((req_msg.type == XS_TRANSACTION_START) &&
-	     (msg->type == XS_ERROR)))
+	    ((type == XS_TRANSACTION_START) && (msg->type == XS_ERROR)))
 		transaction_end();
 
 	return ret;
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index b84c291ba1eb..d7b78d531e63 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -74,7 +74,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
 					v9fs_proto_dotu(v9ses));
 	fid = file->private_data;
 	if (!fid) {
-		fid = v9fs_fid_clone(file->f_path.dentry);
+		fid = v9fs_fid_clone(file_dentry(file));
 		if (IS_ERR(fid))
 			return PTR_ERR(fid);
 
@@ -100,7 +100,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
 		 * because we want write after unlink usecase
 		 * to work.
 		 */
-		fid = v9fs_writeback_fid(file->f_path.dentry);
+		fid = v9fs_writeback_fid(file_dentry(file));
 		if (IS_ERR(fid)) {
 			err = PTR_ERR(fid);
 			mutex_unlock(&v9inode->v_mutex);
@@ -516,7 +516,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
 		 * because we want write after unlink usecase
 		 * to work.
 		 */
-		fid = v9fs_writeback_fid(filp->f_path.dentry);
+		fid = v9fs_writeback_fid(file_dentry(filp));
 		if (IS_ERR(fid)) {
 			retval = PTR_ERR(fid);
 			mutex_unlock(&v9inode->v_mutex);
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 6e72c98162d5..1780218a48f0 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -95,10 +95,8 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
 	}
 
 	dentry = d_obtain_alias(inode);
-	if (IS_ERR(dentry)) {
-		iput(inode);
+	if (IS_ERR(dentry))
 		return dentry;
-	}
 	err = ceph_init_dentry(dentry);
 	if (err < 0) {
 		dput(dentry);
@@ -167,10 +165,8 @@ static struct dentry *__get_parent(struct super_block *sb,
 		return ERR_PTR(-ENOENT);
 
 	dentry = d_obtain_alias(inode);
-	if (IS_ERR(dentry)) {
-		iput(inode);
+	if (IS_ERR(dentry))
 		return dentry;
-	}
 	err = ceph_init_dentry(dentry);
 	if (err < 0) {
 		dput(dentry);
@@ -210,7 +206,7 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
 
 	dout("fh_to_parent %llx\n", cfh->parent_ino);
 	dentry = __get_parent(sb, NULL, cfh->ino);
-	if (IS_ERR(dentry) && PTR_ERR(dentry) == -ENOENT)
+	if (unlikely(dentry == ERR_PTR(-ENOENT)))
 		dentry = __fh_to_dentry(sb, cfh->parent_ino);
 	return dentry;
 }
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index 33b7ee34eda5..bbc1252a59f5 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -357,8 +357,6 @@ configfs_write_bin_file(struct file *file, const char __user *buf,
 
 	len = simple_write_to_buffer(buffer->bin_buffer,
 			buffer->bin_buffer_size, ppos, buf, count);
-	if (len > 0)
-		*ppos += len;
 out:
 	mutex_unlock(&buffer->mutex);
 	return len;
diff --git a/fs/dax.c b/fs/dax.c
index 761495bf5eb9..e207f8f9b700 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -208,7 +208,12 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 				dax.addr += first;
 				size = map_len - first;
 			}
-			max = min(pos + size, end);
+			/*
+			 * pos + size is one past the last offset for IO,
+			 * so pos + size can overflow loff_t at extreme offsets.
+			 * Cast to u64 to catch this and get the true minimum.
+			 */
+			max = min_t(u64, pos + size, end);
 		}
 
 		if (iov_iter_rw(iter) == WRITE) {
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 0d8eb3455b34..e5e29f8c920b 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -45,7 +45,7 @@
  * ecryptfs_to_hex
  * @dst: Buffer to take hex character representation of contents of
  *       src; must be at least of size (src_size * 2)
- * @src: Buffer to be converted to a hex string respresentation
+ * @src: Buffer to be converted to a hex string representation
  * @src_size: number of bytes to convert
  */
 void ecryptfs_to_hex(char *dst, char *src, size_t src_size)
@@ -60,7 +60,7 @@ void ecryptfs_to_hex(char *dst, char *src, size_t src_size)
  * ecryptfs_from_hex
  * @dst: Buffer to take the bytes from src hex; must be at least of
  *       size (src_size / 2)
- * @src: Buffer to be converted from a hex string respresentation to raw value
+ * @src: Buffer to be converted from a hex string representation to raw value
  * @dst_size: size of dst buffer, or number of hex characters pairs to convert
  */
 void ecryptfs_from_hex(char *dst, char *src, int dst_size)
@@ -953,7 +953,7 @@ struct ecryptfs_cipher_code_str_map_elem {
 };
 
 /* Add support for additional ciphers by adding elements here. The
- * cipher_code is whatever OpenPGP applicatoins use to identify the
+ * cipher_code is whatever OpenPGP applications use to identify the
  * ciphers. List in order of probability. */
 static struct ecryptfs_cipher_code_str_map_elem
 ecryptfs_cipher_code_str_map[] = {
@@ -1410,7 +1410,7 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
  *
  * Common entry point for reading file metadata. From here, we could
  * retrieve the header information from the header region of the file,
- * the xattr region of the file, or some other repostory that is
+ * the xattr region of the file, or some other repository that is
  * stored separately from the file itself. The current implementation
  * supports retrieving the metadata information from the file contents
  * and from the xattr region.
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 7000b96b783e..ca4e83750214 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -169,9 +169,22 @@ out:
 	return rc;
 }
 
+static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct file *lower_file = ecryptfs_file_to_lower(file);
+	/*
+	 * Don't allow mmap on top of file systems that don't support it
+	 * natively.  If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs
+	 * allows recursive mounting, this will need to be extended.
+	 */
+	if (!lower_file->f_op->mmap)
+		return -ENODEV;
+	return generic_file_mmap(file, vma);
+}
+
 /**
  * ecryptfs_open
- * @inode: inode speciying file to open
+ * @inode: inode specifying file to open
  * @file: Structure to return filled in
  *
  * Opens the file specified by inode.
@@ -240,7 +253,7 @@ out:
 
 /**
  * ecryptfs_dir_open
- * @inode: inode speciying file to open
+ * @inode: inode specifying file to open
  * @file: Structure to return filled in
  *
  * Opens the file specified by inode.
@@ -403,7 +416,7 @@ const struct file_operations ecryptfs_main_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.mmap = generic_file_mmap,
+	.mmap = ecryptfs_mmap,
 	.open = ecryptfs_open,
 	.flush = ecryptfs_flush,
 	.release = ecryptfs_release,
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index e818f5ac7a26..866bb18efefe 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 #include <linux/mount.h>
-#include <linux/file.h>
 #include "ecryptfs_kernel.h"
 
 struct ecryptfs_open_req {
@@ -148,7 +147,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
 	flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR;
 	(*lower_file) = dentry_open(&req.path, flags, cred);
 	if (!IS_ERR(*lower_file))
-		goto have_file;
+		goto out;
 	if ((flags & O_ACCMODE) == O_RDONLY) {
 		rc = PTR_ERR((*lower_file));
 		goto out;
@@ -166,16 +165,8 @@ int ecryptfs_privileged_open(struct file **lower_file,
 	mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	wake_up(&ecryptfs_kthread_ctl.wait);
 	wait_for_completion(&req.done);
-	if (IS_ERR(*lower_file)) {
+	if (IS_ERR(*lower_file))
 		rc = PTR_ERR(*lower_file);
-		goto out;
-	}
-have_file:
-	if ((*lower_file)->f_op->mmap == NULL) {
-		fput(*lower_file);
-		*lower_file = NULL;
-		rc = -EMEDIUMTYPE;
-	}
 out:
 	return rc;
 }
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 1698132d0e57..612004495141 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -738,8 +738,7 @@ static void ecryptfs_free_kmem_caches(void)
 		struct ecryptfs_cache_info *info;
 
 		info = &ecryptfs_cache_infos[i];
-		if (*(info->cache))
-			kmem_cache_destroy(*(info->cache));
+		kmem_cache_destroy(*(info->cache));
 	}
 }
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 989a2cef6b76..fe7e83a45eff 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -483,9 +483,9 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 		goto out_free;
 	}
 	inode->i_state |= I_WB_SWITCH;
+	__iget(inode);
 	spin_unlock(&inode->i_lock);
 
-	ihold(inode);
 	isw->inode = inode;
 
 	atomic_inc(&isw_nr_in_flight);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index ccd4971cc6c1..264f07c7754e 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -341,8 +341,10 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 	struct dentry *newent;
 	bool outarg_valid = true;
 
+	fuse_lock_inode(dir);
 	err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name,
 			       &outarg, &inode);
+	fuse_unlock_inode(dir);
 	if (err == -ENOENT) {
 		outarg_valid = false;
 		err = 0;
@@ -1341,7 +1343,9 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx)
 		fuse_read_fill(req, file, ctx->pos, PAGE_SIZE,
 			       FUSE_READDIR);
 	}
+	fuse_lock_inode(inode);
 	fuse_request_send(fc, req);
+	fuse_unlock_inode(inode);
 	nbytes = req->out.args[0].size;
 	err = req->out.h.error;
 	fuse_put_request(fc, req);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index eddbe02c4028..929c383432b0 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -110,6 +110,9 @@ struct fuse_inode {
 
 	/** Miscellaneous bits describing inode state */
 	unsigned long state;
+
+	/** Lock for serializing lookup and readdir for back compatibility*/
+	struct mutex mutex;
 };
 
 /** FUSE inode state bits */
@@ -540,6 +543,9 @@ struct fuse_conn {
 	/** write-back cache policy (default is write-through) */
 	unsigned writeback_cache:1;
 
+	/** allow parallel lookups and readdir (default is serialized) */
+	unsigned parallel_dirops:1;
+
 	/*
 	 * The following bitfields are only for optimization purposes
 	 * and hence races in setting them will not cause malfunction
@@ -956,4 +962,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
 
 void fuse_set_initialized(struct fuse_conn *fc);
 
+void fuse_unlock_inode(struct inode *inode);
+void fuse_lock_inode(struct inode *inode);
+
 #endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 1ce67668a8e1..9961d8432ce3 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -97,6 +97,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	INIT_LIST_HEAD(&fi->queued_writes);
 	INIT_LIST_HEAD(&fi->writepages);
 	init_waitqueue_head(&fi->page_waitq);
+	mutex_init(&fi->mutex);
 	fi->forget = fuse_alloc_forget();
 	if (!fi->forget) {
 		kmem_cache_free(fuse_inode_cachep, inode);
@@ -117,6 +118,7 @@ static void fuse_destroy_inode(struct inode *inode)
 	struct fuse_inode *fi = get_fuse_inode(inode);
 	BUG_ON(!list_empty(&fi->write_files));
 	BUG_ON(!list_empty(&fi->queued_writes));
+	mutex_destroy(&fi->mutex);
 	kfree(fi->forget);
 	call_rcu(&inode->i_rcu, fuse_i_callback);
 }
@@ -351,6 +353,18 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
 	return 0;
 }
 
+void fuse_lock_inode(struct inode *inode)
+{
+	if (!get_fuse_conn(inode)->parallel_dirops)
+		mutex_lock(&get_fuse_inode(inode)->mutex);
+}
+
+void fuse_unlock_inode(struct inode *inode)
+{
+	if (!get_fuse_conn(inode)->parallel_dirops)
+		mutex_unlock(&get_fuse_inode(inode)->mutex);
+}
+
 static void fuse_umount_begin(struct super_block *sb)
 {
 	fuse_abort_conn(get_fuse_conn_super(sb));
@@ -898,6 +912,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 				fc->async_dio = 1;
 			if (arg->flags & FUSE_WRITEBACK_CACHE)
 				fc->writeback_cache = 1;
+			if (arg->flags & FUSE_PARALLEL_DIROPS)
+				fc->parallel_dirops = 1;
 			if (arg->time_gran && arg->time_gran <= 1000000000)
 				fc->sb->s_time_gran = arg->time_gran;
 		} else {
@@ -928,7 +944,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 		FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
 		FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
 		FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
-		FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT;
+		FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
+		FUSE_PARALLEL_DIROPS;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
diff --git a/fs/libfs.c b/fs/libfs.c
index cedeacbae303..74dc8b9e7f53 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -84,6 +84,61 @@ int dcache_dir_close(struct inode *inode, struct file *file)
 }
 EXPORT_SYMBOL(dcache_dir_close);
 
+/* parent is locked at least shared */
+static struct dentry *next_positive(struct dentry *parent,
+				    struct list_head *from,
+				    int count)
+{
+	unsigned *seq = &parent->d_inode->i_dir_seq, n;
+	struct dentry *res;
+	struct list_head *p;
+	bool skipped;
+	int i;
+
+retry:
+	i = count;
+	skipped = false;
+	n = smp_load_acquire(seq) & ~1;
+	res = NULL;
+	rcu_read_lock();
+	for (p = from->next; p != &parent->d_subdirs; p = p->next) {
+		struct dentry *d = list_entry(p, struct dentry, d_child);
+		if (!simple_positive(d)) {
+			skipped = true;
+		} else if (!--i) {
+			res = d;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	if (skipped) {
+		smp_rmb();
+		if (unlikely(*seq != n))
+			goto retry;
+	}
+	return res;
+}
+
+static void move_cursor(struct dentry *cursor, struct list_head *after)
+{
+	struct dentry *parent = cursor->d_parent;
+	unsigned n, *seq = &parent->d_inode->i_dir_seq;
+	spin_lock(&parent->d_lock);
+	for (;;) {
+		n = *seq;
+		if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
+			break;
+		cpu_relax();
+	}
+	__list_del(cursor->d_child.prev, cursor->d_child.next);
+	if (after)
+		list_add(&cursor->d_child, after);
+	else
+		list_add_tail(&cursor->d_child, &parent->d_subdirs);
+	smp_store_release(seq, n + 2);
+	spin_unlock(&parent->d_lock);
+}
+
 loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 {
 	struct dentry *dentry = file->f_path.dentry;
@@ -99,25 +154,14 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 	if (offset != file->f_pos) {
 		file->f_pos = offset;
 		if (file->f_pos >= 2) {
-			struct list_head *p;
 			struct dentry *cursor = file->private_data;
+			struct dentry *to;
 			loff_t n = file->f_pos - 2;
 
-			spin_lock(&dentry->d_lock);
-			/* d_lock not required for cursor */
-			list_del(&cursor->d_child);
-			p = dentry->d_subdirs.next;
-			while (n && p != &dentry->d_subdirs) {
-				struct dentry *next;
-				next = list_entry(p, struct dentry, d_child);
-				spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
-				if (simple_positive(next))
-					n--;
-				spin_unlock(&next->d_lock);
-				p = p->next;
-			}
-			list_add_tail(&cursor->d_child, p);
-			spin_unlock(&dentry->d_lock);
+			inode_lock_shared(dentry->d_inode);
+			to = next_positive(dentry, &dentry->d_subdirs, n);
+			move_cursor(cursor, to ? &to->d_child : NULL);
+			inode_unlock_shared(dentry->d_inode);
 		}
 	}
 	return offset;
@@ -140,36 +184,25 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct dentry *cursor = file->private_data;
-	struct list_head *p, *q = &cursor->d_child;
+	struct list_head *p = &cursor->d_child;
+	struct dentry *next;
+	bool moved = false;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
-	spin_lock(&dentry->d_lock);
-	if (ctx->pos == 2)
-		list_move(q, &dentry->d_subdirs);
 
-	for (p = q->next; p != &dentry->d_subdirs; p = p->next) {
-		struct dentry *next = list_entry(p, struct dentry, d_child);
-		spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
-		if (!simple_positive(next)) {
-			spin_unlock(&next->d_lock);
-			continue;
-		}
-
-		spin_unlock(&next->d_lock);
-		spin_unlock(&dentry->d_lock);
+	if (ctx->pos == 2)
+		p = &dentry->d_subdirs;
+	while ((next = next_positive(dentry, p, 1)) != NULL) {
 		if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
 			      d_inode(next)->i_ino, dt_type(d_inode(next))))
-			return 0;
-		spin_lock(&dentry->d_lock);
-		spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
-		/* next is still alive */
-		list_move(q, p);
-		spin_unlock(&next->d_lock);
-		p = q;
+			break;
+		moved = true;
+		p = &next->d_child;
 		ctx->pos++;
 	}
-	spin_unlock(&dentry->d_lock);
+	if (moved)
+		move_cursor(cursor, p);
 	return 0;
 }
 EXPORT_SYMBOL(dcache_readdir);
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 154a107cd376..fc4084ef4736 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -335,12 +335,17 @@ static struct notifier_block lockd_inet6addr_notifier = {
 };
 #endif
 
-static void lockd_svc_exit_thread(void)
+static void lockd_unregister_notifiers(void)
 {
 	unregister_inetaddr_notifier(&lockd_inetaddr_notifier);
 #if IS_ENABLED(CONFIG_IPV6)
 	unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
 #endif
+}
+
+static void lockd_svc_exit_thread(void)
+{
+	lockd_unregister_notifiers();
 	svc_exit_thread(nlmsvc_rqst);
 }
 
@@ -462,7 +467,7 @@ int lockd_up(struct net *net)
 	 * Note: svc_serv structures have an initial use count of 1,
 	 * so we exit through here on both success and failure.
 	 */
-err_net:
+err_put:
 	svc_destroy(serv);
 err_create:
 	mutex_unlock(&nlmsvc_mutex);
@@ -470,7 +475,9 @@ err_create:
 
 err_start:
 	lockd_down_net(serv, net);
-	goto err_net;
+err_net:
+	lockd_unregister_notifiers();
+	goto err_put;
 }
 EXPORT_SYMBOL_GPL(lockd_up);
 
diff --git a/fs/locks.c b/fs/locks.c
index 7c5f91be9b65..ee1b15f6fc13 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1628,7 +1628,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 {
 	struct file_lock *fl, *my_fl = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
diff --git a/fs/namespace.c b/fs/namespace.c
index 783004af5707..419f746d851d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1562,6 +1562,7 @@ void __detach_mounts(struct dentry *dentry)
 		goto out_unlock;
 
 	lock_mount_hash();
+	event++;
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
 		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index d81f96aacd51..656f68f7fe53 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -925,7 +925,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	if (hdr_arg.minorversion == 0) {
 		cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident);
 		if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
-			return rpc_drop_reply;
+			goto out_invalidcred;
 	}
 
 	cps.minorversion = hdr_arg.minorversion;
@@ -953,6 +953,10 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	nfs_put_client(cps.clp);
 	dprintk("%s: done, status = %u\n", __func__, ntohl(status));
 	return rpc_success;
+
+out_invalidcred:
+	pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n");
+	return rpc_autherr_badcred;
 }
 
 /*
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 1dbeab6cf96e..c831c2e5f803 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -59,16 +59,37 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err)
 		goto out;
 
+	if (attr->ia_valid & ATTR_SIZE) {
+		struct inode *realinode = d_inode(ovl_dentry_real(dentry));
+
+		err = -ETXTBSY;
+		if (atomic_read(&realinode->i_writecount) < 0)
+			goto out_drop_write;
+	}
+
 	err = ovl_copy_up(dentry);
 	if (!err) {
+		struct inode *winode = NULL;
+
 		upperdentry = ovl_dentry_upper(dentry);
 
+		if (attr->ia_valid & ATTR_SIZE) {
+			winode = d_inode(upperdentry);
+			err = get_write_access(winode);
+			if (err)
+				goto out_drop_write;
+		}
+
 		inode_lock(upperdentry->d_inode);
 		err = notify_change(upperdentry, attr, NULL);
 		if (!err)
 			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
 		inode_unlock(upperdentry->d_inode);
+
+		if (winode)
+			put_write_access(winode);
 	}
+out_drop_write:
 	ovl_drop_write(dentry);
 out:
 	return err;
@@ -121,16 +142,18 @@ int ovl_permission(struct inode *inode, int mask)
 
 		err = vfs_getattr(&realpath, &stat);
 		if (err)
-			return err;
+			goto out_dput;
 
+		err = -ESTALE;
 		if ((stat.mode ^ inode->i_mode) & S_IFMT)
-			return -ESTALE;
+			goto out_dput;
 
 		inode->i_mode = stat.mode;
 		inode->i_uid = stat.uid;
 		inode->i_gid = stat.gid;
 
-		return generic_permission(inode, mask);
+		err = generic_permission(inode, mask);
+		goto out_dput;
 	}
 
 	/* Careful in RCU walk mode */
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index ce02f46029da..9a7693d5f8ff 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1082,11 +1082,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			if (err < 0)
 				goto out_put_workdir;
 
-			if (!err) {
-				pr_err("overlayfs: upper fs needs to support d_type.\n");
-				err = -EINVAL;
-				goto out_put_workdir;
-			}
+			/*
+			 * We allowed this configuration and don't want to
+			 * break users over kernel upgrade. So warn instead
+			 * of erroring out.
+			 */
+			if (!err)
+				pr_warn("overlayfs: upper fs needs to support d_type.\n");
 		}
 	}
 
diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h
index 797ae2ec8eee..29c691265b49 100644
--- a/include/acpi/acpi_drivers.h
+++ b/include/acpi/acpi_drivers.h
@@ -78,6 +78,7 @@
 
 /* ACPI PCI Interrupt Link (pci_link.c) */
 
+int acpi_irq_penalty_init(void);
 int acpi_pci_link_allocate_irq(acpi_handle handle, int index, int *triggering,
 			       int *polarity, char **name);
 int acpi_pci_link_free_irq(acpi_handle handle);
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 9094599a1150..33466bfc6440 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -309,6 +309,7 @@
 	INTEL_VGA_DEVICE(0x5906, info), /* ULT GT1 */ \
 	INTEL_VGA_DEVICE(0x590E, info), /* ULX GT1 */ \
 	INTEL_VGA_DEVICE(0x5902, info), /* DT  GT1 */ \
+	INTEL_VGA_DEVICE(0x5908, info), /* Halo GT1 */ \
 	INTEL_VGA_DEVICE(0x590B, info), /* Halo GT1 */ \
 	INTEL_VGA_DEVICE(0x590A, info) /* SRV GT1 */
 
@@ -322,15 +323,12 @@
 	INTEL_VGA_DEVICE(0x591D, info) /* WKS GT2 */
 
 #define INTEL_KBL_GT3_IDS(info) \
+	INTEL_VGA_DEVICE(0x5923, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x5926, info), /* ULT GT3 */ \
-	INTEL_VGA_DEVICE(0x592B, info), /* Halo GT3 */ \
-	INTEL_VGA_DEVICE(0x592A, info) /* SRV GT3 */
+	INTEL_VGA_DEVICE(0x5927, info) /* ULT GT3 */
 
 #define INTEL_KBL_GT4_IDS(info) \
-	INTEL_VGA_DEVICE(0x5932, info), /* DT  GT4 */ \
-	INTEL_VGA_DEVICE(0x593B, info), /* Halo GT4 */ \
-	INTEL_VGA_DEVICE(0x593A, info), /* SRV GT4 */ \
-	INTEL_VGA_DEVICE(0x593D, info)  /* WKS GT4 */
+	INTEL_VGA_DEVICE(0x593B, info) /* Halo GT4 */
 
 #define INTEL_KBL_IDS(info) \
 	INTEL_KBL_GT1_IDS(info), \
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 80776d0c52dc..fd72ecf0ce9f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -629,6 +629,7 @@ struct mlx5_cmd_work_ent {
 	void		       *uout;
 	int			uout_size;
 	mlx5_cmd_cbk_t		callback;
+	struct delayed_work	cb_timeout_work;
 	void		       *context;
 	int			idx;
 	struct completion	done;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ee38a4127475..f39b37180c41 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1062,6 +1062,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
 }
 
 void __skb_get_hash(struct sk_buff *skb);
+u32 __skb_get_hash_symmetric(struct sk_buff *skb);
 u32 skb_get_poff(const struct sk_buff *skb);
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen);
@@ -2870,6 +2871,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb,
 }
 
 /**
+ *	skb_push_rcsum - push skb and update receive checksum
+ *	@skb: buffer to update
+ *	@len: length of data pulled
+ *
+ *	This function performs an skb_push on the packet and updates
+ *	the CHECKSUM_COMPLETE checksum.  It should be used on
+ *	receive path processing instead of skb_push unless you know
+ *	that the checksum difference is zero (e.g., a valid IP header)
+ *	or you are setting ip_summed to CHECKSUM_NONE.
+ */
+static inline unsigned char *skb_push_rcsum(struct sk_buff *skb,
+					    unsigned int len)
+{
+	skb_push(skb, len);
+	skb_postpush_rcsum(skb, skb->data, len);
+	return skb->data;
+}
+
+/**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
  *	@len: new length
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index f890a295a7ff..4ccf184e971f 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -109,6 +109,9 @@ struct rpc_auth {
 	/* per-flavor data */
 };
 
+/* rpc_auth au_flags */
+#define RPCAUTH_AUTH_DATATOUCH	0x00000002
+
 struct rpc_auth_create_args {
 	rpc_authflavor_t pseudoflavor;
 	const char *target_name;
diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h
index 1f911ccb2a75..68ec78c1aa48 100644
--- a/include/linux/sunrpc/gss_api.h
+++ b/include/linux/sunrpc/gss_api.h
@@ -73,6 +73,7 @@ u32 gss_delete_sec_context(
 rpc_authflavor_t gss_svc_to_pseudoflavor(struct gss_api_mech *, u32 qop,
 					u32 service);
 u32 gss_pseudoflavor_to_service(struct gss_api_mech *, u32 pseudoflavor);
+bool gss_pseudoflavor_to_datatouch(struct gss_api_mech *, u32 pseudoflavor);
 char *gss_service_to_auth_domain_name(struct gss_api_mech *, u32 service);
 
 struct pf_desc {
@@ -81,6 +82,7 @@ struct pf_desc {
 	u32	service;
 	char	*name;
 	char	*auth_domain_name;
+	bool	datatouch;
 };
 
 /* Different mechanisms (e.g., krb5 or spkm3) may implement gss-api, and
diff --git a/include/linux/usb/ehci_def.h b/include/linux/usb/ehci_def.h
index 966889a20ea3..e479033bd782 100644
--- a/include/linux/usb/ehci_def.h
+++ b/include/linux/usb/ehci_def.h
@@ -180,11 +180,11 @@ struct ehci_regs {
  * PORTSCx
  */
 	/* HOSTPC: offset 0x84 */
-	u32		hostpc[1];	/* HOSTPC extension */
+	u32		hostpc[0];	/* HOSTPC extension */
 #define HOSTPC_PHCD	(1<<22)		/* Phy clock disable */
 #define HOSTPC_PSPD	(3<<25)		/* Port speed detection */
 
-	u32		reserved5[16];
+	u32		reserved5[17];
 
 	/* USBMODE_EX: offset 0xc8 */
 	u32		usbmode_ex;	/* USB Device mode extension */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 791800ddd6d9..6360c259da6d 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -34,6 +34,9 @@
 
 #define BOND_DEFAULT_MIIMON	100
 
+#ifndef __long_aligned
+#define __long_aligned __attribute__((aligned((sizeof(long)))))
+#endif
 /*
  * Less bad way to call ioctl from within the kernel; this needs to be
  * done some other way to get the call out of interrupt context.
@@ -138,7 +141,9 @@ struct bond_params {
 	struct reciprocal_value reciprocal_packets_per_slave;
 	u16 ad_actor_sys_prio;
 	u16 ad_user_port_key;
-	u8 ad_actor_system[ETH_ALEN];
+
+	/* 2 bytes of padding : see ether_addr_equal_64bits() */
+	u8 ad_actor_system[ETH_ALEN + 2];
 };
 
 struct bond_parm_tbl {
diff --git a/include/net/ip.h b/include/net/ip.h
index 37165fba3741..08f36cd2b874 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -313,10 +313,9 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	return min(dst->dev->mtu, IP_MAX_MTU);
 }
 
-static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
+static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
+					  const struct sk_buff *skb)
 {
-	struct sock *sk = skb->sk;
-
 	if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
 		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 5974fae54e12..27e17363263a 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -105,6 +105,9 @@
  *
  *  7.24
  *  - add FUSE_LSEEK for SEEK_HOLE and SEEK_DATA support
+ *
+ *  7.25
+ *  - add FUSE_PARALLEL_DIROPS
  */
 
 #ifndef _LINUX_FUSE_H
@@ -140,7 +143,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 24
+#define FUSE_KERNEL_MINOR_VERSION 25
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -234,6 +237,7 @@ struct fuse_file_lock {
  * FUSE_ASYNC_DIO: asynchronous direct I/O submission
  * FUSE_WRITEBACK_CACHE: use writeback cache for buffered writes
  * FUSE_NO_OPEN_SUPPORT: kernel supports zero-message opens
+ * FUSE_PARALLEL_DIROPS: allow parallel lookups and readdir
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -253,6 +257,7 @@ struct fuse_file_lock {
 #define FUSE_ASYNC_DIO		(1 << 15)
 #define FUSE_WRITEBACK_CACHE	(1 << 16)
 #define FUSE_NO_OPEN_SUPPORT	(1 << 17)
+#define FUSE_PARALLEL_DIROPS    (1 << 18)
 
 /**
  * CUSE INIT request/reply flags
diff --git a/init/Kconfig b/init/Kconfig
index f755a602d4a1..c02d89777713 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1458,6 +1458,7 @@ config KALLSYMS_ALL
 
 config KALLSYMS_ABSOLUTE_PERCPU
 	bool
+	depends on KALLSYMS
 	default X86_64 && SMP
 
 config KALLSYMS_BASE_RELATIVE
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 85cd41878a74..43d43a2d5811 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1678,12 +1678,33 @@ static bool is_orphaned_event(struct perf_event *event)
 	return event->state == PERF_EVENT_STATE_DEAD;
 }
 
-static inline int pmu_filter_match(struct perf_event *event)
+static inline int __pmu_filter_match(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
 	return pmu->filter_match ? pmu->filter_match(event) : 1;
 }
 
+/*
+ * Check whether we should attempt to schedule an event group based on
+ * PMU-specific filtering. An event group can consist of HW and SW events,
+ * potentially with a SW leader, so we must check all the filters, to
+ * determine whether a group is schedulable:
+ */
+static inline int pmu_filter_match(struct perf_event *event)
+{
+	struct perf_event *child;
+
+	if (!__pmu_filter_match(event))
+		return 0;
+
+	list_for_each_entry(child, &event->sibling_list, group_entry) {
+		if (!__pmu_filter_match(child))
+			return 0;
+	}
+
+	return 1;
+}
+
 static inline int
 event_filter_match(struct perf_event *event)
 {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bdcbeea90c95..c8c5d2d48424 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -735,8 +735,6 @@ void post_init_entity_util_avg(struct sched_entity *se)
 	}
 }
 
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
-static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
 #else
 void init_entity_runnable_average(struct sched_entity *se)
 {
@@ -2499,28 +2497,22 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 # ifdef CONFIG_SMP
-static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
-	long tg_weight;
+	long tg_weight, load, shares;
 
 	/*
-	 * Use this CPU's real-time load instead of the last load contribution
-	 * as the updating of the contribution is delayed, and we will use the
-	 * the real-time load to calc the share. See update_tg_load_avg().
+	 * This really should be: cfs_rq->avg.load_avg, but instead we use
+	 * cfs_rq->load.weight, which is its upper bound. This helps ramp up
+	 * the shares for small weight interactive tasks.
 	 */
-	tg_weight = atomic_long_read(&tg->load_avg);
-	tg_weight -= cfs_rq->tg_load_avg_contrib;
-	tg_weight += cfs_rq->load.weight;
+	load = scale_load_down(cfs_rq->load.weight);
 
-	return tg_weight;
-}
-
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
-{
-	long tg_weight, load, shares;
+	tg_weight = atomic_long_read(&tg->load_avg);
 
-	tg_weight = calc_tg_weight(tg, cfs_rq);
-	load = cfs_rq->load.weight;
+	/* Ensure tg_weight >= load */
+	tg_weight -= cfs_rq->tg_load_avg_contrib;
+	tg_weight += load;
 
 	shares = (tg->shares * load);
 	if (tg_weight)
@@ -2539,6 +2531,7 @@ static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 	return tg->shares;
 }
 # endif /* CONFIG_SMP */
+
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
@@ -4946,19 +4939,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 		return wl;
 
 	for_each_sched_entity(se) {
-		long w, W;
+		struct cfs_rq *cfs_rq = se->my_q;
+		long W, w = cfs_rq_load_avg(cfs_rq);
 
-		tg = se->my_q->tg;
+		tg = cfs_rq->tg;
 
 		/*
 		 * W = @wg + \Sum rw_j
 		 */
-		W = wg + calc_tg_weight(tg, se->my_q);
+		W = wg + atomic_long_read(&tg->load_avg);
+
+		/* Ensure \Sum rw_j >= rw_i */
+		W -= cfs_rq->tg_load_avg_contrib;
+		W += w;
 
 		/*
 		 * w = rw_i + @wl
 		 */
-		w = cfs_rq_load_avg(se->my_q) + wl;
+		w += wl;
 
 		/*
 		 * wl = S * s'_i; see (2)
diff --git a/mm/shmem.c b/mm/shmem.c
index 24463b67b6ef..171dee7a131f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2225,9 +2225,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 			error = shmem_getpage(inode, index, &page, SGP_FALLOC);
 		if (error) {
 			/* Remove the !PageUptodate pages we added */
-			shmem_undo_range(inode,
-				(loff_t)start << PAGE_SHIFT,
-				((loff_t)index << PAGE_SHIFT) - 1, true);
+			if (index > start) {
+				shmem_undo_range(inode,
+				    (loff_t)start << PAGE_SHIFT,
+				    ((loff_t)index << PAGE_SHIFT) - 1, true);
+			}
 			goto undone;
 		}
 
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 2d25979273a6..77e7f69bf80d 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -700,7 +700,7 @@ static int
 br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		  int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
-	unsigned int mtu = ip_skb_dst_mtu(skb);
+	unsigned int mtu = ip_skb_dst_mtu(sk, skb);
 	struct iphdr *iph = ip_hdr(skb);
 
 	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index a669dea146c6..61ad43f61c5e 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -651,6 +651,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest,
 }
 EXPORT_SYMBOL(make_flow_keys_digest);
 
+static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
+
+u32 __skb_get_hash_symmetric(struct sk_buff *skb)
+{
+	struct flow_keys keys;
+
+	__flow_hash_secret_init();
+
+	memset(&keys, 0, sizeof(keys));
+	__skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys,
+			   NULL, 0, 0, 0,
+			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+	return __flow_hash_from_keys(&keys, hashrnd);
+}
+EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
+
 /**
  * __skb_get_hash: calculate a flow hash
  * @skb: sk_buff to calculate flow hash from
@@ -868,6 +885,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = {
 	},
 };
 
+static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v4addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v6addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+};
+
 static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
@@ -889,6 +929,9 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_dissector,
 				flow_keys_dissector_keys,
 				ARRAY_SIZE(flow_keys_dissector_keys));
+	skb_flow_dissector_init(&flow_keys_dissector_symmetric,
+				flow_keys_dissector_symmetric_keys,
+				ARRAY_SIZE(flow_keys_dissector_symmetric_keys));
 	skb_flow_dissector_init(&flow_keys_buf_dissector,
 				flow_keys_buf_dissector_keys,
 				ARRAY_SIZE(flow_keys_buf_dissector_keys));
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f2b77e549c03..eb12d2161fb2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3016,24 +3016,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
 EXPORT_SYMBOL_GPL(skb_append_pagefrags);
 
 /**
- *	skb_push_rcsum - push skb and update receive checksum
- *	@skb: buffer to update
- *	@len: length of data pulled
- *
- *	This function performs an skb_push on the packet and updates
- *	the CHECKSUM_COMPLETE checksum.  It should be used on
- *	receive path processing instead of skb_push unless you know
- *	that the checksum difference is zero (e.g., a valid IP header)
- *	or you are setting ip_summed to CHECKSUM_NONE.
- */
-static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len)
-{
-	skb_push(skb, len);
-	skb_postpush_rcsum(skb, skb->data, len);
-	return skb->data;
-}
-
-/**
  *	skb_pull_rcsum - pull skb and update receive checksum
  *	@skb: buffer to update
  *	@len: length of data pulled
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index df4803437888..a796fc7cbc35 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -41,6 +41,7 @@
 #include <net/dn_fib.h>
 #include <net/dn_neigh.h>
 #include <net/dn_dev.h>
+#include <net/nexthop.h>
 
 #define RT_MIN_TABLE 1
 
@@ -150,14 +151,13 @@ static int dn_fib_count_nhs(const struct nlattr *attr)
 	struct rtnexthop *nhp = nla_data(attr);
 	int nhs = 0, nhlen = nla_len(attr);
 
-	while(nhlen >= (int)sizeof(struct rtnexthop)) {
-		if ((nhlen -= nhp->rtnh_len) < 0)
-			return 0;
+	while (rtnh_ok(nhp, nhlen)) {
 		nhs++;
-		nhp = RTNH_NEXT(nhp);
+		nhp = rtnh_next(nhp, &nhlen);
 	}
 
-	return nhs;
+	/* leftover implies invalid nexthop configuration, discard it */
+	return nhlen > 0 ? 0 : nhs;
 }
 
 static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr,
@@ -167,21 +167,24 @@ static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr,
 	int nhlen = nla_len(attr);
 
 	change_nexthops(fi) {
-		int attrlen = nhlen - sizeof(struct rtnexthop);
-		if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0)
+		int attrlen;
+
+		if (!rtnh_ok(nhp, nhlen))
 			return -EINVAL;
 
 		nh->nh_flags  = (r->rtm_flags&~0xFF) | nhp->rtnh_flags;
 		nh->nh_oif    = nhp->rtnh_ifindex;
 		nh->nh_weight = nhp->rtnh_hops + 1;
 
-		if (attrlen) {
+		attrlen = rtnh_attrlen(nhp);
+		if (attrlen > 0) {
 			struct nlattr *gw_attr;
 
 			gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY);
 			nh->nh_gw = gw_attr ? nla_get_le16(gw_attr) : 0;
 		}
-		nhp = RTNH_NEXT(nhp);
+
+		nhp = rtnh_next(nhp, &nhlen);
 	} endfor_nexthops(fi);
 
 	return 0;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 124bf0a66328..4bd4921639c3 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -271,7 +271,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 		return dst_output(net, sk, skb);
 	}
 #endif
-	mtu = ip_skb_dst_mtu(skb);
+	mtu = ip_skb_dst_mtu(sk, skb);
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
@@ -541,7 +541,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 
 	iph = ip_hdr(skb);
 
-	mtu = ip_skb_dst_mtu(skb);
+	mtu = ip_skb_dst_mtu(sk, skb);
 	if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu)
 		mtu = IPCB(skb)->frag_max_size;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1bcef2369d64..771be1fa4176 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -177,6 +177,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 		}
 	}
 
+	free_percpu(non_pcpu_rt->rt6i_pcpu);
 	non_pcpu_rt->rt6i_pcpu = NULL;
 }
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9bff6ef16fa7..9f0983fa4d52 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1341,7 +1341,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return reciprocal_scale(skb_get_hash(skb), num);
+	return reciprocal_scale(__skb_get_hash_symmetric(skb), num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 74ee126a6fe6..c8a7b4c90190 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -616,7 +616,7 @@ static int rds_tcp_init(void)
 
 	ret = rds_tcp_recv_init();
 	if (ret)
-		goto out_slab;
+		goto out_pernet;
 
 	ret = rds_trans_register(&rds_tcp_transport);
 	if (ret)
@@ -628,8 +628,9 @@ static int rds_tcp_init(void)
 
 out_recv:
 	rds_tcp_recv_exit();
-out_slab:
+out_pernet:
 	unregister_pernet_subsys(&rds_tcp_net_ops);
+out_slab:
 	kmem_cache_destroy(rds_tcp_conn_slab);
 out:
 	return ret;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 128942bc9e42..1f5bd6ccbd2c 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -181,7 +181,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	if (!(at & AT_EGRESS)) {
 		if (m->tcfm_ok_push)
-			skb_push(skb2, skb->mac_len);
+			skb_push_rcsum(skb2, skb->mac_len);
 	}
 
 	/* mirror is always swallowed */
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 813a3cdfb573..23c8e7c39656 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1018,6 +1018,8 @@ gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt)
 	auth->au_flags = 0;
 	auth->au_ops = &authgss_ops;
 	auth->au_flavor = flavor;
+	if (gss_pseudoflavor_to_datatouch(gss_auth->mech, flavor))
+		auth->au_flags |= RPCAUTH_AUTH_DATATOUCH;
 	atomic_set(&auth->au_count, 1);
 	kref_init(&gss_auth->kref);
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 65427492b1c9..60595835317a 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -745,12 +745,14 @@ static struct pf_desc gss_kerberos_pfs[] = {
 		.qop = GSS_C_QOP_DEFAULT,
 		.service = RPC_GSS_SVC_INTEGRITY,
 		.name = "krb5i",
+		.datatouch = true,
 	},
 	[2] = {
 		.pseudoflavor = RPC_AUTH_GSS_KRB5P,
 		.qop = GSS_C_QOP_DEFAULT,
 		.service = RPC_GSS_SVC_PRIVACY,
 		.name = "krb5p",
+		.datatouch = true,
 	},
 };
 
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index 7063d856a598..5fec3abbe19b 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -361,6 +361,18 @@ gss_pseudoflavor_to_service(struct gss_api_mech *gm, u32 pseudoflavor)
 }
 EXPORT_SYMBOL(gss_pseudoflavor_to_service);
 
+bool
+gss_pseudoflavor_to_datatouch(struct gss_api_mech *gm, u32 pseudoflavor)
+{
+	int i;
+
+	for (i = 0; i < gm->gm_pf_num; i++) {
+		if (gm->gm_pfs[i].pseudoflavor == pseudoflavor)
+			return gm->gm_pfs[i].datatouch;
+	}
+	return false;
+}
+
 char *
 gss_service_to_auth_domain_name(struct gss_api_mech *gm, u32 service)
 {
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index cc9852897395..c5b0cb4f4056 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1188,11 +1188,17 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 
 		/* Encode reply */
-		if (test_bit(RQ_DROPME, &rqstp->rq_flags)) {
+		if (*statp == rpc_drop_reply ||
+		    test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 			if (procp->pc_release)
 				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
 			goto dropit;
 		}
+		if (*statp == rpc_autherr_badcred) {
+			if (procp->pc_release)
+				procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+			goto err_bad_auth;
+		}
 		if (*statp == rpc_success &&
 		    (xdr = procp->pc_encode) &&
 		    !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) {
diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile
index dc9f3b513a05..ef19fa42c50f 100644
--- a/net/sunrpc/xprtrdma/Makefile
+++ b/net/sunrpc/xprtrdma/Makefile
@@ -1,7 +1,7 @@
 obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o
 
 rpcrdma-y := transport.o rpc_rdma.o verbs.o \
-	fmr_ops.o frwr_ops.o physical_ops.o \
+	fmr_ops.o frwr_ops.o \
 	svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \
 	svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \
 	module.o
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 6326ebe8b595..21cb3b150b37 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -19,13 +19,6 @@
  * verb (fmr_op_unmap).
  */
 
-/* Transport recovery
- *
- * After a transport reconnect, fmr_op_map re-uses the MR already
- * allocated for the RPC, but generates a fresh rkey then maps the
- * MR again. This process is synchronous.
- */
-
 #include "xprt_rdma.h"
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
@@ -35,62 +28,132 @@
 /* Maximum scatter/gather per FMR */
 #define RPCRDMA_MAX_FMR_SGES	(64)
 
-static struct workqueue_struct *fmr_recovery_wq;
-
-#define FMR_RECOVERY_WQ_FLAGS		(WQ_UNBOUND)
+/* Access mode of externally registered pages */
+enum {
+	RPCRDMA_FMR_ACCESS_FLAGS	= IB_ACCESS_REMOTE_WRITE |
+					  IB_ACCESS_REMOTE_READ,
+};
 
-int
-fmr_alloc_recovery_wq(void)
+bool
+fmr_is_supported(struct rpcrdma_ia *ia)
 {
-	fmr_recovery_wq = alloc_workqueue("fmr_recovery", WQ_UNBOUND, 0);
-	return !fmr_recovery_wq ? -ENOMEM : 0;
+	if (!ia->ri_device->alloc_fmr) {
+		pr_info("rpcrdma: 'fmr' mode is not supported by device %s\n",
+			ia->ri_device->name);
+		return false;
+	}
+	return true;
 }
 
-void
-fmr_destroy_recovery_wq(void)
+static int
+fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *mw)
 {
-	struct workqueue_struct *wq;
+	static struct ib_fmr_attr fmr_attr = {
+		.max_pages	= RPCRDMA_MAX_FMR_SGES,
+		.max_maps	= 1,
+		.page_shift	= PAGE_SHIFT
+	};
 
-	if (!fmr_recovery_wq)
-		return;
+	mw->fmr.fm_physaddrs = kcalloc(RPCRDMA_MAX_FMR_SGES,
+				       sizeof(u64), GFP_KERNEL);
+	if (!mw->fmr.fm_physaddrs)
+		goto out_free;
 
-	wq = fmr_recovery_wq;
-	fmr_recovery_wq = NULL;
-	destroy_workqueue(wq);
+	mw->mw_sg = kcalloc(RPCRDMA_MAX_FMR_SGES,
+			    sizeof(*mw->mw_sg), GFP_KERNEL);
+	if (!mw->mw_sg)
+		goto out_free;
+
+	sg_init_table(mw->mw_sg, RPCRDMA_MAX_FMR_SGES);
+
+	mw->fmr.fm_mr = ib_alloc_fmr(ia->ri_pd, RPCRDMA_FMR_ACCESS_FLAGS,
+				     &fmr_attr);
+	if (IS_ERR(mw->fmr.fm_mr))
+		goto out_fmr_err;
+
+	return 0;
+
+out_fmr_err:
+	dprintk("RPC:       %s: ib_alloc_fmr returned %ld\n", __func__,
+		PTR_ERR(mw->fmr.fm_mr));
+
+out_free:
+	kfree(mw->mw_sg);
+	kfree(mw->fmr.fm_physaddrs);
+	return -ENOMEM;
 }
 
 static int
 __fmr_unmap(struct rpcrdma_mw *mw)
 {
 	LIST_HEAD(l);
+	int rc;
 
-	list_add(&mw->fmr.fmr->list, &l);
-	return ib_unmap_fmr(&l);
+	list_add(&mw->fmr.fm_mr->list, &l);
+	rc = ib_unmap_fmr(&l);
+	list_del_init(&mw->fmr.fm_mr->list);
+	return rc;
 }
 
-/* Deferred reset of a single FMR. Generate a fresh rkey by
- * replacing the MR. There's no recovery if this fails.
- */
 static void
-__fmr_recovery_worker(struct work_struct *work)
+fmr_op_release_mr(struct rpcrdma_mw *r)
 {
-	struct rpcrdma_mw *mw = container_of(work, struct rpcrdma_mw,
-					    mw_work);
-	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+	LIST_HEAD(unmap_list);
+	int rc;
 
-	__fmr_unmap(mw);
-	rpcrdma_put_mw(r_xprt, mw);
-	return;
+	/* Ensure MW is not on any rl_registered list */
+	if (!list_empty(&r->mw_list))
+		list_del(&r->mw_list);
+
+	kfree(r->fmr.fm_physaddrs);
+	kfree(r->mw_sg);
+
+	/* In case this one was left mapped, try to unmap it
+	 * to prevent dealloc_fmr from failing with EBUSY
+	 */
+	rc = __fmr_unmap(r);
+	if (rc)
+		pr_err("rpcrdma: final ib_unmap_fmr for %p failed %i\n",
+		       r, rc);
+
+	rc = ib_dealloc_fmr(r->fmr.fm_mr);
+	if (rc)
+		pr_err("rpcrdma: final ib_dealloc_fmr for %p returned %i\n",
+		       r, rc);
+
+	kfree(r);
 }
 
-/* A broken MR was discovered in a context that can't sleep.
- * Defer recovery to the recovery worker.
+/* Reset of a single FMR.
  */
 static void
-__fmr_queue_recovery(struct rpcrdma_mw *mw)
+fmr_op_recover_mr(struct rpcrdma_mw *mw)
 {
-	INIT_WORK(&mw->mw_work, __fmr_recovery_worker);
-	queue_work(fmr_recovery_wq, &mw->mw_work);
+	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+	int rc;
+
+	/* ORDER: invalidate first */
+	rc = __fmr_unmap(mw);
+
+	/* ORDER: then DMA unmap */
+	ib_dma_unmap_sg(r_xprt->rx_ia.ri_device,
+			mw->mw_sg, mw->mw_nents, mw->mw_dir);
+	if (rc)
+		goto out_release;
+
+	rpcrdma_put_mw(r_xprt, mw);
+	r_xprt->rx_stats.mrs_recovered++;
+	return;
+
+out_release:
+	pr_err("rpcrdma: FMR reset failed (%d), %p released\n", rc, mw);
+	r_xprt->rx_stats.mrs_orphaned++;
+
+	spin_lock(&r_xprt->rx_buf.rb_mwlock);
+	list_del(&mw->mw_all);
+	spin_unlock(&r_xprt->rx_buf.rb_mwlock);
+
+	fmr_op_release_mr(mw);
 }
 
 static int
@@ -112,86 +175,21 @@ fmr_op_maxpages(struct rpcrdma_xprt *r_xprt)
 		     RPCRDMA_MAX_HDR_SEGS * RPCRDMA_MAX_FMR_SGES);
 }
 
-static int
-fmr_op_init(struct rpcrdma_xprt *r_xprt)
-{
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ;
-	struct ib_fmr_attr fmr_attr = {
-		.max_pages	= RPCRDMA_MAX_FMR_SGES,
-		.max_maps	= 1,
-		.page_shift	= PAGE_SHIFT
-	};
-	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
-	struct rpcrdma_mw *r;
-	int i, rc;
-
-	spin_lock_init(&buf->rb_mwlock);
-	INIT_LIST_HEAD(&buf->rb_mws);
-	INIT_LIST_HEAD(&buf->rb_all);
-
-	i = max_t(int, RPCRDMA_MAX_DATA_SEGS / RPCRDMA_MAX_FMR_SGES, 1);
-	i += 2;				/* head + tail */
-	i *= buf->rb_max_requests;	/* one set for each RPC slot */
-	dprintk("RPC:       %s: initalizing %d FMRs\n", __func__, i);
-
-	rc = -ENOMEM;
-	while (i--) {
-		r = kzalloc(sizeof(*r), GFP_KERNEL);
-		if (!r)
-			goto out;
-
-		r->fmr.physaddrs = kmalloc(RPCRDMA_MAX_FMR_SGES *
-					   sizeof(u64), GFP_KERNEL);
-		if (!r->fmr.physaddrs)
-			goto out_free;
-
-		r->fmr.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr);
-		if (IS_ERR(r->fmr.fmr))
-			goto out_fmr_err;
-
-		r->mw_xprt = r_xprt;
-		list_add(&r->mw_list, &buf->rb_mws);
-		list_add(&r->mw_all, &buf->rb_all);
-	}
-	return 0;
-
-out_fmr_err:
-	rc = PTR_ERR(r->fmr.fmr);
-	dprintk("RPC:       %s: ib_alloc_fmr status %i\n", __func__, rc);
-	kfree(r->fmr.physaddrs);
-out_free:
-	kfree(r);
-out:
-	return rc;
-}
-
 /* Use the ib_map_phys_fmr() verb to register a memory region
  * for remote access via RDMA READ or RDMA WRITE.
  */
 static int
 fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
-	   int nsegs, bool writing)
+	   int nsegs, bool writing, struct rpcrdma_mw **out)
 {
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct ib_device *device = ia->ri_device;
-	enum dma_data_direction direction = rpcrdma_data_dir(writing);
 	struct rpcrdma_mr_seg *seg1 = seg;
 	int len, pageoff, i, rc;
 	struct rpcrdma_mw *mw;
+	u64 *dma_pages;
 
-	mw = seg1->rl_mw;
-	seg1->rl_mw = NULL;
-	if (!mw) {
-		mw = rpcrdma_get_mw(r_xprt);
-		if (!mw)
-			return -ENOMEM;
-	} else {
-		/* this is a retransmit; generate a fresh rkey */
-		rc = __fmr_unmap(mw);
-		if (rc)
-			return rc;
-	}
+	mw = rpcrdma_get_mw(r_xprt);
+	if (!mw)
+		return -ENOBUFS;
 
 	pageoff = offset_in_page(seg1->mr_offset);
 	seg1->mr_offset -= pageoff;	/* start of page */
@@ -200,8 +198,14 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	if (nsegs > RPCRDMA_MAX_FMR_SGES)
 		nsegs = RPCRDMA_MAX_FMR_SGES;
 	for (i = 0; i < nsegs;) {
-		rpcrdma_map_one(device, seg, direction);
-		mw->fmr.physaddrs[i] = seg->mr_dma;
+		if (seg->mr_page)
+			sg_set_page(&mw->mw_sg[i],
+				    seg->mr_page,
+				    seg->mr_len,
+				    offset_in_page(seg->mr_offset));
+		else
+			sg_set_buf(&mw->mw_sg[i], seg->mr_offset,
+				   seg->mr_len);
 		len += seg->mr_len;
 		++seg;
 		++i;
@@ -210,49 +214,54 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
 			break;
 	}
-
-	rc = ib_map_phys_fmr(mw->fmr.fmr, mw->fmr.physaddrs,
-			     i, seg1->mr_dma);
+	mw->mw_nents = i;
+	mw->mw_dir = rpcrdma_data_dir(writing);
+	if (i == 0)
+		goto out_dmamap_err;
+
+	if (!ib_dma_map_sg(r_xprt->rx_ia.ri_device,
+			   mw->mw_sg, mw->mw_nents, mw->mw_dir))
+		goto out_dmamap_err;
+
+	for (i = 0, dma_pages = mw->fmr.fm_physaddrs; i < mw->mw_nents; i++)
+		dma_pages[i] = sg_dma_address(&mw->mw_sg[i]);
+	rc = ib_map_phys_fmr(mw->fmr.fm_mr, dma_pages, mw->mw_nents,
+			     dma_pages[0]);
 	if (rc)
 		goto out_maperr;
 
-	seg1->rl_mw = mw;
-	seg1->mr_rkey = mw->fmr.fmr->rkey;
-	seg1->mr_base = seg1->mr_dma + pageoff;
-	seg1->mr_nsegs = i;
-	seg1->mr_len = len;
-	return i;
+	mw->mw_handle = mw->fmr.fm_mr->rkey;
+	mw->mw_length = len;
+	mw->mw_offset = dma_pages[0] + pageoff;
 
-out_maperr:
-	dprintk("RPC:       %s: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n",
-		__func__, len, (unsigned long long)seg1->mr_dma,
-		pageoff, i, rc);
-	while (i--)
-		rpcrdma_unmap_one(device, --seg);
-	return rc;
-}
+	*out = mw;
+	return mw->mw_nents;
 
-static void
-__fmr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg)
-{
-	struct ib_device *device = r_xprt->rx_ia.ri_device;
-	int nsegs = seg->mr_nsegs;
+out_dmamap_err:
+	pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n",
+	       mw->mw_sg, mw->mw_nents);
+	rpcrdma_defer_mr_recovery(mw);
+	return -EIO;
 
-	while (nsegs--)
-		rpcrdma_unmap_one(device, seg++);
+out_maperr:
+	pr_err("rpcrdma: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n",
+	       len, (unsigned long long)dma_pages[0],
+	       pageoff, mw->mw_nents, rc);
+	rpcrdma_defer_mr_recovery(mw);
+	return -EIO;
 }
 
 /* Invalidate all memory regions that were registered for "req".
  *
  * Sleeps until it is safe for the host CPU to access the
  * previously mapped memory regions.
+ *
+ * Caller ensures that req->rl_registered is not empty.
  */
 static void
 fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
-	struct rpcrdma_mr_seg *seg;
-	unsigned int i, nchunks;
-	struct rpcrdma_mw *mw;
+	struct rpcrdma_mw *mw, *tmp;
 	LIST_HEAD(unmap_list);
 	int rc;
 
@@ -261,90 +270,54 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	/* ORDER: Invalidate all of the req's MRs first
 	 *
 	 * ib_unmap_fmr() is slow, so use a single call instead
-	 * of one call per mapped MR.
+	 * of one call per mapped FMR.
 	 */
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
-
-		list_add(&mw->fmr.fmr->list, &unmap_list);
-
-		i += seg->mr_nsegs;
-	}
+	list_for_each_entry(mw, &req->rl_registered, mw_list)
+		list_add_tail(&mw->fmr.fm_mr->list, &unmap_list);
 	rc = ib_unmap_fmr(&unmap_list);
 	if (rc)
-		pr_warn("%s: ib_unmap_fmr failed (%i)\n", __func__, rc);
+		goto out_reset;
 
 	/* ORDER: Now DMA unmap all of the req's MRs, and return
 	 * them to the free MW list.
 	 */
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
+	list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) {
+		list_del_init(&mw->mw_list);
+		list_del_init(&mw->fmr.fm_mr->list);
+		ib_dma_unmap_sg(r_xprt->rx_ia.ri_device,
+				mw->mw_sg, mw->mw_nents, mw->mw_dir);
+		rpcrdma_put_mw(r_xprt, mw);
+	}
 
-		__fmr_dma_unmap(r_xprt, seg);
-		rpcrdma_put_mw(r_xprt, seg->rl_mw);
+	return;
 
-		i += seg->mr_nsegs;
-		seg->mr_nsegs = 0;
-		seg->rl_mw = NULL;
-	}
+out_reset:
+	pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc);
 
-	req->rl_nchunks = 0;
+	list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) {
+		list_del_init(&mw->fmr.fm_mr->list);
+		fmr_op_recover_mr(mw);
+	}
 }
 
 /* Use a slow, safe mechanism to invalidate all memory regions
  * that were registered for "req".
- *
- * In the asynchronous case, DMA unmapping occurs first here
- * because the rpcrdma_mr_seg is released immediately after this
- * call. It's contents won't be available in __fmr_dma_unmap later.
- * FIXME.
  */
 static void
 fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		  bool sync)
 {
-	struct rpcrdma_mr_seg *seg;
 	struct rpcrdma_mw *mw;
-	unsigned int i;
-
-	for (i = 0; req->rl_nchunks; req->rl_nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
-
-		if (sync) {
-			/* ORDER */
-			__fmr_unmap(mw);
-			__fmr_dma_unmap(r_xprt, seg);
-			rpcrdma_put_mw(r_xprt, mw);
-		} else {
-			__fmr_dma_unmap(r_xprt, seg);
-			__fmr_queue_recovery(mw);
-		}
-
-		i += seg->mr_nsegs;
-		seg->mr_nsegs = 0;
-		seg->rl_mw = NULL;
-	}
-}
-
-static void
-fmr_op_destroy(struct rpcrdma_buffer *buf)
-{
-	struct rpcrdma_mw *r;
-	int rc;
-
-	while (!list_empty(&buf->rb_all)) {
-		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
-		list_del(&r->mw_all);
-		kfree(r->fmr.physaddrs);
 
-		rc = ib_dealloc_fmr(r->fmr.fmr);
-		if (rc)
-			dprintk("RPC:       %s: ib_dealloc_fmr failed %i\n",
-				__func__, rc);
+	while (!list_empty(&req->rl_registered)) {
+		mw = list_first_entry(&req->rl_registered,
+				      struct rpcrdma_mw, mw_list);
+		list_del_init(&mw->mw_list);
 
-		kfree(r);
+		if (sync)
+			fmr_op_recover_mr(mw);
+		else
+			rpcrdma_defer_mr_recovery(mw);
 	}
 }
 
@@ -352,9 +325,10 @@ const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = {
 	.ro_map				= fmr_op_map,
 	.ro_unmap_sync			= fmr_op_unmap_sync,
 	.ro_unmap_safe			= fmr_op_unmap_safe,
+	.ro_recover_mr			= fmr_op_recover_mr,
 	.ro_open			= fmr_op_open,
 	.ro_maxpages			= fmr_op_maxpages,
-	.ro_init			= fmr_op_init,
-	.ro_destroy			= fmr_op_destroy,
+	.ro_init_mr			= fmr_op_init_mr,
+	.ro_release_mr			= fmr_op_release_mr,
 	.ro_displayname			= "fmr",
 };
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index c0947544babe..892b5e1d9b09 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -73,29 +73,71 @@
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
-static struct workqueue_struct *frwr_recovery_wq;
-
-#define FRWR_RECOVERY_WQ_FLAGS		(WQ_UNBOUND | WQ_MEM_RECLAIM)
+bool
+frwr_is_supported(struct rpcrdma_ia *ia)
+{
+	struct ib_device_attr *attrs = &ia->ri_device->attrs;
+
+	if (!(attrs->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS))
+		goto out_not_supported;
+	if (attrs->max_fast_reg_page_list_len == 0)
+		goto out_not_supported;
+	return true;
+
+out_not_supported:
+	pr_info("rpcrdma: 'frwr' mode is not supported by device %s\n",
+		ia->ri_device->name);
+	return false;
+}
 
-int
-frwr_alloc_recovery_wq(void)
+static int
+frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r)
 {
-	frwr_recovery_wq = alloc_workqueue("frwr_recovery",
-					   FRWR_RECOVERY_WQ_FLAGS, 0);
-	return !frwr_recovery_wq ? -ENOMEM : 0;
+	unsigned int depth = ia->ri_max_frmr_depth;
+	struct rpcrdma_frmr *f = &r->frmr;
+	int rc;
+
+	f->fr_mr = ib_alloc_mr(ia->ri_pd, IB_MR_TYPE_MEM_REG, depth);
+	if (IS_ERR(f->fr_mr))
+		goto out_mr_err;
+
+	r->mw_sg = kcalloc(depth, sizeof(*r->mw_sg), GFP_KERNEL);
+	if (!r->mw_sg)
+		goto out_list_err;
+
+	sg_init_table(r->mw_sg, depth);
+	init_completion(&f->fr_linv_done);
+	return 0;
+
+out_mr_err:
+	rc = PTR_ERR(f->fr_mr);
+	dprintk("RPC:       %s: ib_alloc_mr status %i\n",
+		__func__, rc);
+	return rc;
+
+out_list_err:
+	rc = -ENOMEM;
+	dprintk("RPC:       %s: sg allocation failure\n",
+		__func__);
+	ib_dereg_mr(f->fr_mr);
+	return rc;
 }
 
-void
-frwr_destroy_recovery_wq(void)
+static void
+frwr_op_release_mr(struct rpcrdma_mw *r)
 {
-	struct workqueue_struct *wq;
+	int rc;
 
-	if (!frwr_recovery_wq)
-		return;
+	/* Ensure MW is not on any rl_registered list */
+	if (!list_empty(&r->mw_list))
+		list_del(&r->mw_list);
 
-	wq = frwr_recovery_wq;
-	frwr_recovery_wq = NULL;
-	destroy_workqueue(wq);
+	rc = ib_dereg_mr(r->frmr.fr_mr);
+	if (rc)
+		pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n",
+		       r, rc);
+	kfree(r->mw_sg);
+	kfree(r);
 }
 
 static int
@@ -124,93 +166,37 @@ __frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r)
 	return 0;
 }
 
-static void
-__frwr_reset_and_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw)
-{
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct rpcrdma_frmr *f = &mw->frmr;
-	int rc;
-
-	rc = __frwr_reset_mr(ia, mw);
-	ib_dma_unmap_sg(ia->ri_device, f->fr_sg, f->fr_nents, f->fr_dir);
-	if (rc)
-		return;
-
-	rpcrdma_put_mw(r_xprt, mw);
-}
-
-/* Deferred reset of a single FRMR. Generate a fresh rkey by
- * replacing the MR.
+/* Reset of a single FRMR. Generate a fresh rkey by replacing the MR.
  *
  * There's no recovery if this fails. The FRMR is abandoned, but
  * remains in rb_all. It will be cleaned up when the transport is
  * destroyed.
  */
 static void
-__frwr_recovery_worker(struct work_struct *work)
-{
-	struct rpcrdma_mw *r = container_of(work, struct rpcrdma_mw,
-					    mw_work);
-
-	__frwr_reset_and_unmap(r->mw_xprt, r);
-	return;
-}
-
-/* A broken MR was discovered in a context that can't sleep.
- * Defer recovery to the recovery worker.
- */
-static void
-__frwr_queue_recovery(struct rpcrdma_mw *r)
-{
-	INIT_WORK(&r->mw_work, __frwr_recovery_worker);
-	queue_work(frwr_recovery_wq, &r->mw_work);
-}
-
-static int
-__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device,
-	    unsigned int depth)
+frwr_op_recover_mr(struct rpcrdma_mw *mw)
 {
-	struct rpcrdma_frmr *f = &r->frmr;
+	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	int rc;
 
-	f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth);
-	if (IS_ERR(f->fr_mr))
-		goto out_mr_err;
-
-	f->fr_sg = kcalloc(depth, sizeof(*f->fr_sg), GFP_KERNEL);
-	if (!f->fr_sg)
-		goto out_list_err;
-
-	sg_init_table(f->fr_sg, depth);
-
-	init_completion(&f->fr_linv_done);
-
-	return 0;
+	rc = __frwr_reset_mr(ia, mw);
+	ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir);
+	if (rc)
+		goto out_release;
 
-out_mr_err:
-	rc = PTR_ERR(f->fr_mr);
-	dprintk("RPC:       %s: ib_alloc_mr status %i\n",
-		__func__, rc);
-	return rc;
+	rpcrdma_put_mw(r_xprt, mw);
+	r_xprt->rx_stats.mrs_recovered++;
+	return;
 
-out_list_err:
-	rc = -ENOMEM;
-	dprintk("RPC:       %s: sg allocation failure\n",
-		__func__);
-	ib_dereg_mr(f->fr_mr);
-	return rc;
-}
+out_release:
+	pr_err("rpcrdma: FRMR reset failed %d, %p release\n", rc, mw);
+	r_xprt->rx_stats.mrs_orphaned++;
 
-static void
-__frwr_release(struct rpcrdma_mw *r)
-{
-	int rc;
+	spin_lock(&r_xprt->rx_buf.rb_mwlock);
+	list_del(&mw->mw_all);
+	spin_unlock(&r_xprt->rx_buf.rb_mwlock);
 
-	rc = ib_dereg_mr(r->frmr.fr_mr);
-	if (rc)
-		dprintk("RPC:       %s: ib_dereg_mr status %i\n",
-			__func__, rc);
-	kfree(r->frmr.fr_sg);
+	frwr_op_release_mr(mw);
 }
 
 static int
@@ -346,57 +332,14 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc)
 	complete_all(&frmr->fr_linv_done);
 }
 
-static int
-frwr_op_init(struct rpcrdma_xprt *r_xprt)
-{
-	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	struct ib_device *device = r_xprt->rx_ia.ri_device;
-	unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth;
-	struct ib_pd *pd = r_xprt->rx_ia.ri_pd;
-	int i;
-
-	spin_lock_init(&buf->rb_mwlock);
-	INIT_LIST_HEAD(&buf->rb_mws);
-	INIT_LIST_HEAD(&buf->rb_all);
-
-	i = max_t(int, RPCRDMA_MAX_DATA_SEGS / depth, 1);
-	i += 2;				/* head + tail */
-	i *= buf->rb_max_requests;	/* one set for each RPC slot */
-	dprintk("RPC:       %s: initalizing %d FRMRs\n", __func__, i);
-
-	while (i--) {
-		struct rpcrdma_mw *r;
-		int rc;
-
-		r = kzalloc(sizeof(*r), GFP_KERNEL);
-		if (!r)
-			return -ENOMEM;
-
-		rc = __frwr_init(r, pd, device, depth);
-		if (rc) {
-			kfree(r);
-			return rc;
-		}
-
-		r->mw_xprt = r_xprt;
-		list_add(&r->mw_list, &buf->rb_mws);
-		list_add(&r->mw_all, &buf->rb_all);
-	}
-
-	return 0;
-}
-
-/* Post a FAST_REG Work Request to register a memory region
+/* Post a REG_MR Work Request to register a memory region
  * for remote access via RDMA READ or RDMA WRITE.
  */
 static int
 frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
-	    int nsegs, bool writing)
+	    int nsegs, bool writing, struct rpcrdma_mw **out)
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct ib_device *device = ia->ri_device;
-	enum dma_data_direction direction = rpcrdma_data_dir(writing);
-	struct rpcrdma_mr_seg *seg1 = seg;
 	struct rpcrdma_mw *mw;
 	struct rpcrdma_frmr *frmr;
 	struct ib_mr *mr;
@@ -405,14 +348,13 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	int rc, i, n, dma_nents;
 	u8 key;
 
-	mw = seg1->rl_mw;
-	seg1->rl_mw = NULL;
+	mw = NULL;
 	do {
 		if (mw)
-			__frwr_queue_recovery(mw);
+			rpcrdma_defer_mr_recovery(mw);
 		mw = rpcrdma_get_mw(r_xprt);
 		if (!mw)
-			return -ENOMEM;
+			return -ENOBUFS;
 	} while (mw->frmr.fr_state != FRMR_IS_INVALID);
 	frmr = &mw->frmr;
 	frmr->fr_state = FRMR_IS_VALID;
@@ -421,15 +363,14 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 
 	if (nsegs > ia->ri_max_frmr_depth)
 		nsegs = ia->ri_max_frmr_depth;
-
 	for (i = 0; i < nsegs;) {
 		if (seg->mr_page)
-			sg_set_page(&frmr->fr_sg[i],
+			sg_set_page(&mw->mw_sg[i],
 				    seg->mr_page,
 				    seg->mr_len,
 				    offset_in_page(seg->mr_offset));
 		else
-			sg_set_buf(&frmr->fr_sg[i], seg->mr_offset,
+			sg_set_buf(&mw->mw_sg[i], seg->mr_offset,
 				   seg->mr_len);
 
 		++seg;
@@ -440,26 +381,22 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 		    offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
 			break;
 	}
-	frmr->fr_nents = i;
-	frmr->fr_dir = direction;
-
-	dma_nents = ib_dma_map_sg(device, frmr->fr_sg, frmr->fr_nents, direction);
-	if (!dma_nents) {
-		pr_err("RPC:       %s: failed to dma map sg %p sg_nents %u\n",
-		       __func__, frmr->fr_sg, frmr->fr_nents);
-		return -ENOMEM;
-	}
+	mw->mw_nents = i;
+	mw->mw_dir = rpcrdma_data_dir(writing);
+	if (i == 0)
+		goto out_dmamap_err;
 
-	n = ib_map_mr_sg(mr, frmr->fr_sg, frmr->fr_nents, NULL, PAGE_SIZE);
-	if (unlikely(n != frmr->fr_nents)) {
-		pr_err("RPC:       %s: failed to map mr %p (%u/%u)\n",
-		       __func__, frmr->fr_mr, n, frmr->fr_nents);
-		rc = n < 0 ? n : -EINVAL;
-		goto out_senderr;
-	}
+	dma_nents = ib_dma_map_sg(ia->ri_device,
+				  mw->mw_sg, mw->mw_nents, mw->mw_dir);
+	if (!dma_nents)
+		goto out_dmamap_err;
+
+	n = ib_map_mr_sg(mr, mw->mw_sg, mw->mw_nents, NULL, PAGE_SIZE);
+	if (unlikely(n != mw->mw_nents))
+		goto out_mapmr_err;
 
 	dprintk("RPC:       %s: Using frmr %p to map %u segments (%u bytes)\n",
-		__func__, mw, frmr->fr_nents, mr->length);
+		__func__, mw, mw->mw_nents, mr->length);
 
 	key = (u8)(mr->rkey & 0x000000FF);
 	ib_update_fast_reg_key(mr, ++key);
@@ -481,24 +418,34 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	if (rc)
 		goto out_senderr;
 
-	seg1->rl_mw = mw;
-	seg1->mr_rkey = mr->rkey;
-	seg1->mr_base = mr->iova;
-	seg1->mr_nsegs = frmr->fr_nents;
-	seg1->mr_len = mr->length;
+	mw->mw_handle = mr->rkey;
+	mw->mw_length = mr->length;
+	mw->mw_offset = mr->iova;
+
+	*out = mw;
+	return mw->mw_nents;
 
-	return frmr->fr_nents;
+out_dmamap_err:
+	pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n",
+	       mw->mw_sg, mw->mw_nents);
+	rpcrdma_defer_mr_recovery(mw);
+	return -EIO;
+
+out_mapmr_err:
+	pr_err("rpcrdma: failed to map mr %p (%u/%u)\n",
+	       frmr->fr_mr, n, mw->mw_nents);
+	rpcrdma_defer_mr_recovery(mw);
+	return -EIO;
 
 out_senderr:
-	dprintk("RPC:       %s: ib_post_send status %i\n", __func__, rc);
-	__frwr_queue_recovery(mw);
-	return rc;
+	pr_err("rpcrdma: FRMR registration ib_post_send returned %i\n", rc);
+	rpcrdma_defer_mr_recovery(mw);
+	return -ENOTCONN;
 }
 
 static struct ib_send_wr *
-__frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg)
+__frwr_prepare_linv_wr(struct rpcrdma_mw *mw)
 {
-	struct rpcrdma_mw *mw = seg->rl_mw;
 	struct rpcrdma_frmr *f = &mw->frmr;
 	struct ib_send_wr *invalidate_wr;
 
@@ -518,16 +465,16 @@ __frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg)
  *
  * Sleeps until it is safe for the host CPU to access the
  * previously mapped memory regions.
+ *
+ * Caller ensures that req->rl_registered is not empty.
  */
 static void
 frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
 	struct ib_send_wr *invalidate_wrs, *pos, *prev, *bad_wr;
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct rpcrdma_mr_seg *seg;
-	unsigned int i, nchunks;
+	struct rpcrdma_mw *mw, *tmp;
 	struct rpcrdma_frmr *f;
-	struct rpcrdma_mw *mw;
 	int rc;
 
 	dprintk("RPC:       %s: req %p\n", __func__, req);
@@ -537,22 +484,18 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * Chain the LOCAL_INV Work Requests and post them with
 	 * a single ib_post_send() call.
 	 */
+	f = NULL;
 	invalidate_wrs = pos = prev = NULL;
-	seg = NULL;
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
-
-		pos = __frwr_prepare_linv_wr(seg);
+	list_for_each_entry(mw, &req->rl_registered, mw_list) {
+		pos = __frwr_prepare_linv_wr(mw);
 
 		if (!invalidate_wrs)
 			invalidate_wrs = pos;
 		else
 			prev->next = pos;
 		prev = pos;
-
-		i += seg->mr_nsegs;
+		f = &mw->frmr;
 	}
-	f = &seg->rl_mw->frmr;
 
 	/* Strong send queue ordering guarantees that when the
 	 * last WR in the chain completes, all WRs in the chain
@@ -577,39 +520,27 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * them to the free MW list.
 	 */
 unmap:
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
-		seg->rl_mw = NULL;
-
-		ib_dma_unmap_sg(ia->ri_device, f->fr_sg, f->fr_nents,
-				f->fr_dir);
+	list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) {
+		list_del_init(&mw->mw_list);
+		ib_dma_unmap_sg(ia->ri_device,
+				mw->mw_sg, mw->mw_nents, mw->mw_dir);
 		rpcrdma_put_mw(r_xprt, mw);
-
-		i += seg->mr_nsegs;
-		seg->mr_nsegs = 0;
 	}
-
-	req->rl_nchunks = 0;
 	return;
 
 reset_mrs:
-	pr_warn("%s: ib_post_send failed %i\n", __func__, rc);
+	pr_err("rpcrdma: FRMR invalidate ib_post_send returned %i\n", rc);
+	rdma_disconnect(ia->ri_id);
 
 	/* Find and reset the MRs in the LOCAL_INV WRs that did not
 	 * get posted. This is synchronous, and slow.
 	 */
-	for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
+	list_for_each_entry(mw, &req->rl_registered, mw_list) {
 		f = &mw->frmr;
-
 		if (mw->frmr.fr_mr->rkey == bad_wr->ex.invalidate_rkey) {
 			__frwr_reset_mr(ia, mw);
 			bad_wr = bad_wr->next;
 		}
-
-		i += seg->mr_nsegs;
 	}
 	goto unmap;
 }
@@ -621,38 +552,17 @@ static void
 frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		   bool sync)
 {
-	struct rpcrdma_mr_seg *seg;
 	struct rpcrdma_mw *mw;
-	unsigned int i;
 
-	for (i = 0; req->rl_nchunks; req->rl_nchunks--) {
-		seg = &req->rl_segments[i];
-		mw = seg->rl_mw;
+	while (!list_empty(&req->rl_registered)) {
+		mw = list_first_entry(&req->rl_registered,
+				      struct rpcrdma_mw, mw_list);
+		list_del_init(&mw->mw_list);
 
 		if (sync)
-			__frwr_reset_and_unmap(r_xprt, mw);
+			frwr_op_recover_mr(mw);
 		else
-			__frwr_queue_recovery(mw);
-
-		i += seg->mr_nsegs;
-		seg->mr_nsegs = 0;
-		seg->rl_mw = NULL;
-	}
-}
-
-static void
-frwr_op_destroy(struct rpcrdma_buffer *buf)
-{
-	struct rpcrdma_mw *r;
-
-	/* Ensure stale MWs for "buf" are no longer in flight */
-	flush_workqueue(frwr_recovery_wq);
-
-	while (!list_empty(&buf->rb_all)) {
-		r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
-		list_del(&r->mw_all);
-		__frwr_release(r);
-		kfree(r);
+			rpcrdma_defer_mr_recovery(mw);
 	}
 }
 
@@ -660,9 +570,10 @@ const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = {
 	.ro_map				= frwr_op_map,
 	.ro_unmap_sync			= frwr_op_unmap_sync,
 	.ro_unmap_safe			= frwr_op_unmap_safe,
+	.ro_recover_mr			= frwr_op_recover_mr,
 	.ro_open			= frwr_op_open,
 	.ro_maxpages			= frwr_op_maxpages,
-	.ro_init			= frwr_op_init,
-	.ro_destroy			= frwr_op_destroy,
+	.ro_init_mr			= frwr_op_init_mr,
+	.ro_release_mr			= frwr_op_release_mr,
 	.ro_displayname			= "frwr",
 };
diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c
deleted file mode 100644
index 3750596cc432..000000000000
--- a/net/sunrpc/xprtrdma/physical_ops.c
+++ /dev/null
@@ -1,122 +0,0 @@
-/*
- * Copyright (c) 2015 Oracle.  All rights reserved.
- * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
- */
-
-/* No-op chunk preparation. All client memory is pre-registered.
- * Sometimes referred to as ALLPHYSICAL mode.
- *
- * Physical registration is simple because all client memory is
- * pre-registered and never deregistered. This mode is good for
- * adapter bring up, but is considered not safe: the server is
- * trusted not to abuse its access to client memory not involved
- * in RDMA I/O.
- */
-
-#include "xprt_rdma.h"
-
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-# define RPCDBG_FACILITY	RPCDBG_TRANS
-#endif
-
-static int
-physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
-		 struct rpcrdma_create_data_internal *cdata)
-{
-	struct ib_mr *mr;
-
-	/* Obtain an rkey to use for RPC data payloads.
-	 */
-	mr = ib_get_dma_mr(ia->ri_pd,
-			   IB_ACCESS_LOCAL_WRITE |
-			   IB_ACCESS_REMOTE_WRITE |
-			   IB_ACCESS_REMOTE_READ);
-	if (IS_ERR(mr)) {
-		pr_err("%s: ib_get_dma_mr for failed with %lX\n",
-		       __func__, PTR_ERR(mr));
-		return -ENOMEM;
-	}
-	ia->ri_dma_mr = mr;
-
-	rpcrdma_set_max_header_sizes(ia, cdata, min_t(unsigned int,
-						      RPCRDMA_MAX_DATA_SEGS,
-						      RPCRDMA_MAX_HDR_SEGS));
-	return 0;
-}
-
-/* PHYSICAL memory registration conveys one page per chunk segment.
- */
-static size_t
-physical_op_maxpages(struct rpcrdma_xprt *r_xprt)
-{
-	return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
-		     RPCRDMA_MAX_HDR_SEGS);
-}
-
-static int
-physical_op_init(struct rpcrdma_xprt *r_xprt)
-{
-	return 0;
-}
-
-/* The client's physical memory is already exposed for
- * remote access via RDMA READ or RDMA WRITE.
- */
-static int
-physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
-		int nsegs, bool writing)
-{
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-
-	rpcrdma_map_one(ia->ri_device, seg, rpcrdma_data_dir(writing));
-	seg->mr_rkey = ia->ri_dma_mr->rkey;
-	seg->mr_base = seg->mr_dma;
-	return 1;
-}
-
-/* DMA unmap all memory regions that were mapped for "req".
- */
-static void
-physical_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
-{
-	struct ib_device *device = r_xprt->rx_ia.ri_device;
-	unsigned int i;
-
-	for (i = 0; req->rl_nchunks; --req->rl_nchunks)
-		rpcrdma_unmap_one(device, &req->rl_segments[i++]);
-}
-
-/* Use a slow, safe mechanism to invalidate all memory regions
- * that were registered for "req".
- *
- * For physical memory registration, there is no good way to
- * fence a single MR that has been advertised to the server. The
- * client has already handed the server an R_key that cannot be
- * invalidated and is shared by all MRs on this connection.
- * Tearing down the PD might be the only safe choice, but it's
- * not clear that a freshly acquired DMA R_key would be different
- * than the one used by the PD that was just destroyed.
- * FIXME.
- */
-static void
-physical_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
-		       bool sync)
-{
-	physical_op_unmap_sync(r_xprt, req);
-}
-
-static void
-physical_op_destroy(struct rpcrdma_buffer *buf)
-{
-}
-
-const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = {
-	.ro_map				= physical_op_map,
-	.ro_unmap_sync			= physical_op_unmap_sync,
-	.ro_unmap_safe			= physical_op_unmap_safe,
-	.ro_open			= physical_op_open,
-	.ro_maxpages			= physical_op_maxpages,
-	.ro_init			= physical_op_init,
-	.ro_destroy			= physical_op_destroy,
-	.ro_displayname			= "physical",
-};
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 35a81096e83d..a47f170b20ef 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -196,8 +196,7 @@ rpcrdma_tail_pullup(struct xdr_buf *buf)
  * MR when they can.
  */
 static int
-rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
-		     int n, int nsegs)
+rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, int n)
 {
 	size_t page_offset;
 	u32 remaining;
@@ -206,7 +205,7 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
 	base = vec->iov_base;
 	page_offset = offset_in_page(base);
 	remaining = vec->iov_len;
-	while (remaining && n < nsegs) {
+	while (remaining && n < RPCRDMA_MAX_SEGS) {
 		seg[n].mr_page = NULL;
 		seg[n].mr_offset = base;
 		seg[n].mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining);
@@ -230,34 +229,34 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg,
 
 static int
 rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
-	enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg, int nsegs)
+	enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg)
 {
-	int len, n = 0, p;
-	int page_base;
+	int len, n, p, page_base;
 	struct page **ppages;
 
+	n = 0;
 	if (pos == 0) {
-		n = rpcrdma_convert_kvec(&xdrbuf->head[0], seg, n, nsegs);
-		if (n == nsegs)
-			return -EIO;
+		n = rpcrdma_convert_kvec(&xdrbuf->head[0], seg, n);
+		if (n == RPCRDMA_MAX_SEGS)
+			goto out_overflow;
 	}
 
 	len = xdrbuf->page_len;
 	ppages = xdrbuf->pages + (xdrbuf->page_base >> PAGE_SHIFT);
 	page_base = xdrbuf->page_base & ~PAGE_MASK;
 	p = 0;
-	while (len && n < nsegs) {
+	while (len && n < RPCRDMA_MAX_SEGS) {
 		if (!ppages[p]) {
 			/* alloc the pagelist for receiving buffer */
 			ppages[p] = alloc_page(GFP_ATOMIC);
 			if (!ppages[p])
-				return -ENOMEM;
+				return -EAGAIN;
 		}
 		seg[n].mr_page = ppages[p];
 		seg[n].mr_offset = (void *)(unsigned long) page_base;
 		seg[n].mr_len = min_t(u32, PAGE_SIZE - page_base, len);
 		if (seg[n].mr_len > PAGE_SIZE)
-			return -EIO;
+			goto out_overflow;
 		len -= seg[n].mr_len;
 		++n;
 		++p;
@@ -265,8 +264,8 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 	}
 
 	/* Message overflows the seg array */
-	if (len && n == nsegs)
-		return -EIO;
+	if (len && n == RPCRDMA_MAX_SEGS)
+		goto out_overflow;
 
 	/* When encoding the read list, the tail is always sent inline */
 	if (type == rpcrdma_readch)
@@ -277,20 +276,24 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 		 * xdr pad bytes, saving the server an RDMA operation. */
 		if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize)
 			return n;
-		n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n, nsegs);
-		if (n == nsegs)
-			return -EIO;
+		n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n);
+		if (n == RPCRDMA_MAX_SEGS)
+			goto out_overflow;
 	}
 
 	return n;
+
+out_overflow:
+	pr_err("rpcrdma: segment array overflow\n");
+	return -EIO;
 }
 
 static inline __be32 *
-xdr_encode_rdma_segment(__be32 *iptr, struct rpcrdma_mr_seg *seg)
+xdr_encode_rdma_segment(__be32 *iptr, struct rpcrdma_mw *mw)
 {
-	*iptr++ = cpu_to_be32(seg->mr_rkey);
-	*iptr++ = cpu_to_be32(seg->mr_len);
-	return xdr_encode_hyper(iptr, seg->mr_base);
+	*iptr++ = cpu_to_be32(mw->mw_handle);
+	*iptr++ = cpu_to_be32(mw->mw_length);
+	return xdr_encode_hyper(iptr, mw->mw_offset);
 }
 
 /* XDR-encode the Read list. Supports encoding a list of read
@@ -310,7 +313,8 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 			 struct rpcrdma_req *req, struct rpc_rqst *rqst,
 			 __be32 *iptr, enum rpcrdma_chunktype rtype)
 {
-	struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+	struct rpcrdma_mr_seg *seg;
+	struct rpcrdma_mw *mw;
 	unsigned int pos;
 	int n, nsegs;
 
@@ -322,15 +326,17 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 	pos = rqst->rq_snd_buf.head[0].iov_len;
 	if (rtype == rpcrdma_areadch)
 		pos = 0;
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg,
-				     RPCRDMA_MAX_SEGS - req->rl_nchunks);
+	seg = req->rl_segments;
+	nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
 	do {
-		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, false);
-		if (n <= 0)
+		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
+						 false, &mw);
+		if (n < 0)
 			return ERR_PTR(n);
+		list_add(&mw->mw_list, &req->rl_registered);
 
 		*iptr++ = xdr_one;	/* item present */
 
@@ -338,20 +344,17 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 		 * have the same "position".
 		 */
 		*iptr++ = cpu_to_be32(pos);
-		iptr = xdr_encode_rdma_segment(iptr, seg);
+		iptr = xdr_encode_rdma_segment(iptr, mw);
 
-		dprintk("RPC: %5u %s: read segment pos %u "
-			"%d@0x%016llx:0x%08x (%s)\n",
+		dprintk("RPC: %5u %s: pos %u %u@0x%016llx:0x%08x (%s)\n",
 			rqst->rq_task->tk_pid, __func__, pos,
-			seg->mr_len, (unsigned long long)seg->mr_base,
-			seg->mr_rkey, n < nsegs ? "more" : "last");
+			mw->mw_length, (unsigned long long)mw->mw_offset,
+			mw->mw_handle, n < nsegs ? "more" : "last");
 
 		r_xprt->rx_stats.read_chunk_count++;
-		req->rl_nchunks++;
 		seg += n;
 		nsegs -= n;
 	} while (nsegs);
-	req->rl_nextseg = seg;
 
 	/* Finish Read list */
 	*iptr++ = xdr_zero;	/* Next item not present */
@@ -375,7 +378,8 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 			  struct rpc_rqst *rqst, __be32 *iptr,
 			  enum rpcrdma_chunktype wtype)
 {
-	struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+	struct rpcrdma_mr_seg *seg;
+	struct rpcrdma_mw *mw;
 	int n, nsegs, nchunks;
 	__be32 *segcount;
 
@@ -384,10 +388,10 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		return iptr;
 	}
 
+	seg = req->rl_segments;
 	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf,
 				     rqst->rq_rcv_buf.head[0].iov_len,
-				     wtype, seg,
-				     RPCRDMA_MAX_SEGS - req->rl_nchunks);
+				     wtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -396,26 +400,25 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 
 	nchunks = 0;
 	do {
-		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true);
-		if (n <= 0)
+		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
+						 true, &mw);
+		if (n < 0)
 			return ERR_PTR(n);
+		list_add(&mw->mw_list, &req->rl_registered);
 
-		iptr = xdr_encode_rdma_segment(iptr, seg);
+		iptr = xdr_encode_rdma_segment(iptr, mw);
 
-		dprintk("RPC: %5u %s: write segment "
-			"%d@0x016%llx:0x%08x (%s)\n",
+		dprintk("RPC: %5u %s: %u@0x016%llx:0x%08x (%s)\n",
 			rqst->rq_task->tk_pid, __func__,
-			seg->mr_len, (unsigned long long)seg->mr_base,
-			seg->mr_rkey, n < nsegs ? "more" : "last");
+			mw->mw_length, (unsigned long long)mw->mw_offset,
+			mw->mw_handle, n < nsegs ? "more" : "last");
 
 		r_xprt->rx_stats.write_chunk_count++;
 		r_xprt->rx_stats.total_rdma_request += seg->mr_len;
-		req->rl_nchunks++;
 		nchunks++;
 		seg   += n;
 		nsegs -= n;
 	} while (nsegs);
-	req->rl_nextseg = seg;
 
 	/* Update count of segments in this Write chunk */
 	*segcount = cpu_to_be32(nchunks);
@@ -442,7 +445,8 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 			   struct rpcrdma_req *req, struct rpc_rqst *rqst,
 			   __be32 *iptr, enum rpcrdma_chunktype wtype)
 {
-	struct rpcrdma_mr_seg *seg = req->rl_nextseg;
+	struct rpcrdma_mr_seg *seg;
+	struct rpcrdma_mw *mw;
 	int n, nsegs, nchunks;
 	__be32 *segcount;
 
@@ -451,8 +455,8 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 		return iptr;
 	}
 
-	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg,
-				     RPCRDMA_MAX_SEGS - req->rl_nchunks);
+	seg = req->rl_segments;
+	nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg);
 	if (nsegs < 0)
 		return ERR_PTR(nsegs);
 
@@ -461,26 +465,25 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 
 	nchunks = 0;
 	do {
-		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true);
-		if (n <= 0)
+		n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
+						 true, &mw);
+		if (n < 0)
 			return ERR_PTR(n);
+		list_add(&mw->mw_list, &req->rl_registered);
 
-		iptr = xdr_encode_rdma_segment(iptr, seg);
+		iptr = xdr_encode_rdma_segment(iptr, mw);
 
-		dprintk("RPC: %5u %s: reply segment "
-			"%d@0x%016llx:0x%08x (%s)\n",
+		dprintk("RPC: %5u %s: %u@0x%016llx:0x%08x (%s)\n",
 			rqst->rq_task->tk_pid, __func__,
-			seg->mr_len, (unsigned long long)seg->mr_base,
-			seg->mr_rkey, n < nsegs ? "more" : "last");
+			mw->mw_length, (unsigned long long)mw->mw_offset,
+			mw->mw_handle, n < nsegs ? "more" : "last");
 
 		r_xprt->rx_stats.reply_chunk_count++;
 		r_xprt->rx_stats.total_rdma_request += seg->mr_len;
-		req->rl_nchunks++;
 		nchunks++;
 		seg   += n;
 		nsegs -= n;
 	} while (nsegs);
-	req->rl_nextseg = seg;
 
 	/* Update count of segments in the Reply chunk */
 	*segcount = cpu_to_be32(nchunks);
@@ -567,6 +570,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	enum rpcrdma_chunktype rtype, wtype;
 	struct rpcrdma_msg *headerp;
+	bool ddp_allowed;
 	ssize_t hdrlen;
 	size_t rpclen;
 	__be32 *iptr;
@@ -583,6 +587,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_max_requests);
 	headerp->rm_type = rdma_msg;
 
+	/* When the ULP employs a GSS flavor that guarantees integrity
+	 * or privacy, direct data placement of individual data items
+	 * is not allowed.
+	 */
+	ddp_allowed = !(rqst->rq_cred->cr_auth->au_flags &
+						RPCAUTH_AUTH_DATATOUCH);
+
 	/*
 	 * Chunks needed for results?
 	 *
@@ -594,7 +605,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 */
 	if (rpcrdma_results_inline(r_xprt, rqst))
 		wtype = rpcrdma_noch;
-	else if (rqst->rq_rcv_buf.flags & XDRBUF_READ)
+	else if (ddp_allowed && rqst->rq_rcv_buf.flags & XDRBUF_READ)
 		wtype = rpcrdma_writech;
 	else
 		wtype = rpcrdma_replych;
@@ -617,7 +628,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 		rtype = rpcrdma_noch;
 		rpcrdma_inline_pullup(rqst);
 		rpclen = rqst->rq_svec[0].iov_len;
-	} else if (rqst->rq_snd_buf.flags & XDRBUF_WRITE) {
+	} else if (ddp_allowed && rqst->rq_snd_buf.flags & XDRBUF_WRITE) {
 		rtype = rpcrdma_readch;
 		rpclen = rqst->rq_svec[0].iov_len;
 		rpclen += rpcrdma_tail_pullup(&rqst->rq_snd_buf);
@@ -650,8 +661,6 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	 * send a Call message with a Position Zero Read chunk and a
 	 * regular Read chunk at the same time.
 	 */
-	req->rl_nchunks = 0;
-	req->rl_nextseg = req->rl_segments;
 	iptr = headerp->rm_body.rm_chunks;
 	iptr = rpcrdma_encode_read_list(r_xprt, req, rqst, iptr, rtype);
 	if (IS_ERR(iptr))
@@ -690,10 +699,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 out_overflow:
 	pr_err("rpcrdma: send overflow: hdrlen %zd rpclen %zu %s/%s\n",
 		hdrlen, rpclen, transfertypes[rtype], transfertypes[wtype]);
-	/* Terminate this RPC. Chunks registered above will be
-	 * released by xprt_release -> xprt_rmda_free .
-	 */
-	return -EIO;
+	iptr = ERR_PTR(-EIO);
 
 out_unmap:
 	r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
@@ -705,15 +711,13 @@ out_unmap:
  * RDMA'd by server. See map at rpcrdma_create_chunks()! :-)
  */
 static int
-rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __be32 **iptrp)
+rpcrdma_count_chunks(struct rpcrdma_rep *rep, int wrchunk, __be32 **iptrp)
 {
 	unsigned int i, total_len;
 	struct rpcrdma_write_chunk *cur_wchunk;
 	char *base = (char *)rdmab_to_msg(rep->rr_rdmabuf);
 
 	i = be32_to_cpu(**iptrp);
-	if (i > max)
-		return -1;
 	cur_wchunk = (struct rpcrdma_write_chunk *) (*iptrp + 1);
 	total_len = 0;
 	while (i--) {
@@ -744,45 +748,66 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b
 	return total_len;
 }
 
-/*
- * Scatter inline received data back into provided iov's.
+/**
+ * rpcrdma_inline_fixup - Scatter inline received data into rqst's iovecs
+ * @rqst: controlling RPC request
+ * @srcp: points to RPC message payload in receive buffer
+ * @copy_len: remaining length of receive buffer content
+ * @pad: Write chunk pad bytes needed (zero for pure inline)
+ *
+ * The upper layer has set the maximum number of bytes it can
+ * receive in each component of rq_rcv_buf. These values are set in
+ * the head.iov_len, page_len, tail.iov_len, and buflen fields.
+ *
+ * Unlike the TCP equivalent (xdr_partial_copy_from_skb), in
+ * many cases this function simply updates iov_base pointers in
+ * rq_rcv_buf to point directly to the received reply data, to
+ * avoid copying reply data.
+ *
+ * Returns the count of bytes which had to be memcopied.
  */
-static void
+static unsigned long
 rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 {
-	int i, npages, curlen, olen;
+	unsigned long fixup_copy_count;
+	int i, npages, curlen;
 	char *destp;
 	struct page **ppages;
 	int page_base;
 
+	/* The head iovec is redirected to the RPC reply message
+	 * in the receive buffer, to avoid a memcopy.
+	 */
+	rqst->rq_rcv_buf.head[0].iov_base = srcp;
+	rqst->rq_private_buf.head[0].iov_base = srcp;
+
+	/* The contents of the receive buffer that follow
+	 * head.iov_len bytes are copied into the page list.
+	 */
 	curlen = rqst->rq_rcv_buf.head[0].iov_len;
-	if (curlen > copy_len) {	/* write chunk header fixup */
+	if (curlen > copy_len)
 		curlen = copy_len;
-		rqst->rq_rcv_buf.head[0].iov_len = curlen;
-	}
-
 	dprintk("RPC:       %s: srcp 0x%p len %d hdrlen %d\n",
 		__func__, srcp, copy_len, curlen);
-
-	/* Shift pointer for first receive segment only */
-	rqst->rq_rcv_buf.head[0].iov_base = srcp;
 	srcp += curlen;
 	copy_len -= curlen;
 
-	olen = copy_len;
-	i = 0;
-	rpcx_to_rdmax(rqst->rq_xprt)->rx_stats.fixup_copy_count += olen;
 	page_base = rqst->rq_rcv_buf.page_base;
 	ppages = rqst->rq_rcv_buf.pages + (page_base >> PAGE_SHIFT);
 	page_base &= ~PAGE_MASK;
-
+	fixup_copy_count = 0;
 	if (copy_len && rqst->rq_rcv_buf.page_len) {
-		npages = PAGE_ALIGN(page_base +
-			rqst->rq_rcv_buf.page_len) >> PAGE_SHIFT;
-		for (; i < npages; i++) {
+		int pagelist_len;
+
+		pagelist_len = rqst->rq_rcv_buf.page_len;
+		if (pagelist_len > copy_len)
+			pagelist_len = copy_len;
+		npages = PAGE_ALIGN(page_base + pagelist_len) >> PAGE_SHIFT;
+		for (i = 0; i < npages; i++) {
 			curlen = PAGE_SIZE - page_base;
-			if (curlen > copy_len)
-				curlen = copy_len;
+			if (curlen > pagelist_len)
+				curlen = pagelist_len;
+
 			dprintk("RPC:       %s: page %d"
 				" srcp 0x%p len %d curlen %d\n",
 				__func__, i, srcp, copy_len, curlen);
@@ -792,39 +817,32 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 			kunmap_atomic(destp);
 			srcp += curlen;
 			copy_len -= curlen;
-			if (copy_len == 0)
+			fixup_copy_count += curlen;
+			pagelist_len -= curlen;
+			if (!pagelist_len)
 				break;
 			page_base = 0;
 		}
-	}
 
-	if (copy_len && rqst->rq_rcv_buf.tail[0].iov_len) {
-		curlen = copy_len;
-		if (curlen > rqst->rq_rcv_buf.tail[0].iov_len)
-			curlen = rqst->rq_rcv_buf.tail[0].iov_len;
-		if (rqst->rq_rcv_buf.tail[0].iov_base != srcp)
-			memmove(rqst->rq_rcv_buf.tail[0].iov_base, srcp, curlen);
-		dprintk("RPC:       %s: tail srcp 0x%p len %d curlen %d\n",
-			__func__, srcp, copy_len, curlen);
-		rqst->rq_rcv_buf.tail[0].iov_len = curlen;
-		copy_len -= curlen; ++i;
-	} else
-		rqst->rq_rcv_buf.tail[0].iov_len = 0;
-
-	if (pad) {
-		/* implicit padding on terminal chunk */
-		unsigned char *p = rqst->rq_rcv_buf.tail[0].iov_base;
-		while (pad--)
-			p[rqst->rq_rcv_buf.tail[0].iov_len++] = 0;
+		/* Implicit padding for the last segment in a Write
+		 * chunk is inserted inline at the front of the tail
+		 * iovec. The upper layer ignores the content of
+		 * the pad. Simply ensure inline content in the tail
+		 * that follows the Write chunk is properly aligned.
+		 */
+		if (pad)
+			srcp -= pad;
 	}
 
-	if (copy_len)
-		dprintk("RPC:       %s: %d bytes in"
-			" %d extra segments (%d lost)\n",
-			__func__, olen, i, copy_len);
+	/* The tail iovec is redirected to the remaining data
+	 * in the receive buffer, to avoid a memcopy.
+	 */
+	if (copy_len || pad) {
+		rqst->rq_rcv_buf.tail[0].iov_base = srcp;
+		rqst->rq_private_buf.tail[0].iov_base = srcp;
+	}
 
-	/* TBD avoid a warning from call_decode() */
-	rqst->rq_private_buf = rqst->rq_rcv_buf;
+	return fixup_copy_count;
 }
 
 void
@@ -960,14 +978,13 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		    (headerp->rm_body.rm_chunks[1] == xdr_zero &&
 		     headerp->rm_body.rm_chunks[2] != xdr_zero) ||
 		    (headerp->rm_body.rm_chunks[1] != xdr_zero &&
-		     req->rl_nchunks == 0))
+		     list_empty(&req->rl_registered)))
 			goto badheader;
 		if (headerp->rm_body.rm_chunks[1] != xdr_zero) {
 			/* count any expected write chunks in read reply */
 			/* start at write chunk array count */
 			iptr = &headerp->rm_body.rm_chunks[2];
-			rdmalen = rpcrdma_count_chunks(rep,
-						req->rl_nchunks, 1, &iptr);
+			rdmalen = rpcrdma_count_chunks(rep, 1, &iptr);
 			/* check for validity, and no reply chunk after */
 			if (rdmalen < 0 || *iptr++ != xdr_zero)
 				goto badheader;
@@ -988,8 +1005,10 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 			rep->rr_len -= RPCRDMA_HDRLEN_MIN;
 			status = rep->rr_len;
 		}
-		/* Fix up the rpc results for upper layer */
-		rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len, rdmalen);
+
+		r_xprt->rx_stats.fixup_copy_count +=
+			rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len,
+					     rdmalen);
 		break;
 
 	case rdma_nomsg:
@@ -997,11 +1016,11 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		if (headerp->rm_body.rm_chunks[0] != xdr_zero ||
 		    headerp->rm_body.rm_chunks[1] != xdr_zero ||
 		    headerp->rm_body.rm_chunks[2] != xdr_one ||
-		    req->rl_nchunks == 0)
+		    list_empty(&req->rl_registered))
 			goto badheader;
 		iptr = (__be32 *)((unsigned char *)headerp +
 							RPCRDMA_HDRLEN_MIN);
-		rdmalen = rpcrdma_count_chunks(rep, req->rl_nchunks, 0, &iptr);
+		rdmalen = rpcrdma_count_chunks(rep, 0, &iptr);
 		if (rdmalen < 0)
 			goto badheader;
 		r_xprt->rx_stats.total_rdma_reply += rdmalen;
@@ -1014,14 +1033,9 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 
 badheader:
 	default:
-		dprintk("%s: invalid rpcrdma reply header (type %d):"
-				" chunks[012] == %d %d %d"
-				" expected chunks <= %d\n",
-				__func__, be32_to_cpu(headerp->rm_type),
-				headerp->rm_body.rm_chunks[0],
-				headerp->rm_body.rm_chunks[1],
-				headerp->rm_body.rm_chunks[2],
-				req->rl_nchunks);
+		dprintk("RPC: %5u %s: invalid rpcrdma reply (type %u)\n",
+			rqst->rq_task->tk_pid, __func__,
+			be32_to_cpu(headerp->rm_type));
 		status = -EIO;
 		r_xprt->rx_stats.bad_reply_count++;
 		break;
@@ -1035,7 +1049,7 @@ out:
 	 * control: waking the next RPC waits until this RPC has
 	 * relinquished all its Send Queue entries.
 	 */
-	if (req->rl_nchunks)
+	if (!list_empty(&req->rl_registered))
 		r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, req);
 
 	spin_lock_bh(&xprt->transport_lock);
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 99d2e5b72726..81f0e879f019 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -558,7 +558,6 @@ out_sendbuf:
 
 out_fail:
 	rpcrdma_buffer_put(req);
-	r_xprt->rx_stats.failed_marshal_count++;
 	return NULL;
 }
 
@@ -590,8 +589,19 @@ xprt_rdma_free(void *buffer)
 	rpcrdma_buffer_put(req);
 }
 
-/*
+/**
+ * xprt_rdma_send_request - marshal and send an RPC request
+ * @task: RPC task with an RPC message in rq_snd_buf
+ *
+ * Return values:
+ *        0:	The request has been sent
+ * ENOTCONN:	Caller needs to invoke connect logic then call again
+ *  ENOBUFS:	Call again later to send the request
+ *      EIO:	A permanent error occurred. The request was not sent,
+ *		and don't try it again
+ *
  * send_request invokes the meat of RPC RDMA. It must do the following:
+ *
  *  1.  Marshal the RPC request into an RPC RDMA request, which means
  *	putting a header in front of data, and creating IOVs for RDMA
  *	from those in the request.
@@ -600,7 +610,6 @@ xprt_rdma_free(void *buffer)
  *	the request (rpcrdma_ep_post).
  *  4.  No partial sends are possible in the RPC-RDMA protocol (as in UDP).
  */
-
 static int
 xprt_rdma_send_request(struct rpc_task *task)
 {
@@ -610,6 +619,9 @@ xprt_rdma_send_request(struct rpc_task *task)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	int rc = 0;
 
+	/* On retransmit, remove any previously registered chunks */
+	r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
+
 	rc = rpcrdma_marshal_req(rqst);
 	if (rc < 0)
 		goto failed_marshal;
@@ -630,11 +642,12 @@ xprt_rdma_send_request(struct rpc_task *task)
 	return 0;
 
 failed_marshal:
-	r_xprt->rx_stats.failed_marshal_count++;
 	dprintk("RPC:       %s: rpcrdma_marshal_req failed, status %i\n",
 		__func__, rc);
 	if (rc == -EIO)
-		return -EIO;
+		r_xprt->rx_stats.failed_marshal_count++;
+	if (rc != -ENOTCONN)
+		return rc;
 drop_connection:
 	xprt_disconnect_done(xprt);
 	return -ENOTCONN;	/* implies disconnect */
@@ -660,7 +673,7 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 		   xprt->stat.bad_xids,
 		   xprt->stat.req_u,
 		   xprt->stat.bklog_u);
-	seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu\n",
+	seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu ",
 		   r_xprt->rx_stats.read_chunk_count,
 		   r_xprt->rx_stats.write_chunk_count,
 		   r_xprt->rx_stats.reply_chunk_count,
@@ -672,6 +685,10 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 		   r_xprt->rx_stats.failed_marshal_count,
 		   r_xprt->rx_stats.bad_reply_count,
 		   r_xprt->rx_stats.nomsg_call_count);
+	seq_printf(seq, "%lu %lu %lu\n",
+		   r_xprt->rx_stats.mrs_recovered,
+		   r_xprt->rx_stats.mrs_orphaned,
+		   r_xprt->rx_stats.mrs_allocated);
 }
 
 static int
@@ -741,7 +758,6 @@ void xprt_rdma_cleanup(void)
 			__func__, rc);
 
 	rpcrdma_destroy_wq();
-	frwr_destroy_recovery_wq();
 
 	rc = xprt_unregister_transport(&xprt_rdma_bc);
 	if (rc)
@@ -753,20 +769,13 @@ int xprt_rdma_init(void)
 {
 	int rc;
 
-	rc = frwr_alloc_recovery_wq();
-	if (rc)
-		return rc;
-
 	rc = rpcrdma_alloc_wq();
-	if (rc) {
-		frwr_destroy_recovery_wq();
+	if (rc)
 		return rc;
-	}
 
 	rc = xprt_register_transport(&xprt_rdma);
 	if (rc) {
 		rpcrdma_destroy_wq();
-		frwr_destroy_recovery_wq();
 		return rc;
 	}
 
@@ -774,7 +783,6 @@ int xprt_rdma_init(void)
 	if (rc) {
 		xprt_unregister_transport(&xprt_rdma);
 		rpcrdma_destroy_wq();
-		frwr_destroy_recovery_wq();
 		return rc;
 	}
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index b044d98a1370..536d0be3f61b 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -379,8 +379,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 	struct rpcrdma_ia *ia = &xprt->rx_ia;
 	int rc;
 
-	ia->ri_dma_mr = NULL;
-
 	ia->ri_id = rpcrdma_create_id(xprt, ia, addr);
 	if (IS_ERR(ia->ri_id)) {
 		rc = PTR_ERR(ia->ri_id);
@@ -391,47 +389,29 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 	ia->ri_pd = ib_alloc_pd(ia->ri_device);
 	if (IS_ERR(ia->ri_pd)) {
 		rc = PTR_ERR(ia->ri_pd);
-		dprintk("RPC:       %s: ib_alloc_pd() failed %i\n",
-			__func__, rc);
+		pr_err("rpcrdma: ib_alloc_pd() returned %d\n", rc);
 		goto out2;
 	}
 
-	if (memreg == RPCRDMA_FRMR) {
-		if (!(ia->ri_device->attrs.device_cap_flags &
-				IB_DEVICE_MEM_MGT_EXTENSIONS) ||
-		    (ia->ri_device->attrs.max_fast_reg_page_list_len == 0)) {
-			dprintk("RPC:       %s: FRMR registration "
-				"not supported by HCA\n", __func__);
-			memreg = RPCRDMA_MTHCAFMR;
-		}
-	}
-	if (memreg == RPCRDMA_MTHCAFMR) {
-		if (!ia->ri_device->alloc_fmr) {
-			dprintk("RPC:       %s: MTHCAFMR registration "
-				"not supported by HCA\n", __func__);
-			rc = -EINVAL;
-			goto out3;
-		}
-	}
-
 	switch (memreg) {
 	case RPCRDMA_FRMR:
-		ia->ri_ops = &rpcrdma_frwr_memreg_ops;
-		break;
-	case RPCRDMA_ALLPHYSICAL:
-		ia->ri_ops = &rpcrdma_physical_memreg_ops;
-		break;
+		if (frwr_is_supported(ia)) {
+			ia->ri_ops = &rpcrdma_frwr_memreg_ops;
+			break;
+		}
+		/*FALLTHROUGH*/
 	case RPCRDMA_MTHCAFMR:
-		ia->ri_ops = &rpcrdma_fmr_memreg_ops;
-		break;
+		if (fmr_is_supported(ia)) {
+			ia->ri_ops = &rpcrdma_fmr_memreg_ops;
+			break;
+		}
+		/*FALLTHROUGH*/
 	default:
-		printk(KERN_ERR "RPC: Unsupported memory "
-				"registration mode: %d\n", memreg);
-		rc = -ENOMEM;
+		pr_err("rpcrdma: Unsupported memory registration mode: %d\n",
+		       memreg);
+		rc = -EINVAL;
 		goto out3;
 	}
-	dprintk("RPC:       %s: memory registration strategy is '%s'\n",
-		__func__, ia->ri_ops->ro_displayname);
 
 	return 0;
 
@@ -585,8 +565,6 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 out2:
 	ib_free_cq(sendcq);
 out1:
-	if (ia->ri_dma_mr)
-		ib_dereg_mr(ia->ri_dma_mr);
 	return rc;
 }
 
@@ -600,8 +578,6 @@ out1:
 void
 rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 {
-	int rc;
-
 	dprintk("RPC:       %s: entering, connected is %d\n",
 		__func__, ep->rep_connected);
 
@@ -615,12 +591,6 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 
 	ib_free_cq(ep->rep_attr.recv_cq);
 	ib_free_cq(ep->rep_attr.send_cq);
-
-	if (ia->ri_dma_mr) {
-		rc = ib_dereg_mr(ia->ri_dma_mr);
-		dprintk("RPC:       %s: ib_dereg_mr returned %i\n",
-			__func__, rc);
-	}
 }
 
 /*
@@ -777,6 +747,90 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 	ib_drain_qp(ia->ri_id->qp);
 }
 
+static void
+rpcrdma_mr_recovery_worker(struct work_struct *work)
+{
+	struct rpcrdma_buffer *buf = container_of(work, struct rpcrdma_buffer,
+						  rb_recovery_worker.work);
+	struct rpcrdma_mw *mw;
+
+	spin_lock(&buf->rb_recovery_lock);
+	while (!list_empty(&buf->rb_stale_mrs)) {
+		mw = list_first_entry(&buf->rb_stale_mrs,
+				      struct rpcrdma_mw, mw_list);
+		list_del_init(&mw->mw_list);
+		spin_unlock(&buf->rb_recovery_lock);
+
+		dprintk("RPC:       %s: recovering MR %p\n", __func__, mw);
+		mw->mw_xprt->rx_ia.ri_ops->ro_recover_mr(mw);
+
+		spin_lock(&buf->rb_recovery_lock);
+	}
+	spin_unlock(&buf->rb_recovery_lock);
+}
+
+void
+rpcrdma_defer_mr_recovery(struct rpcrdma_mw *mw)
+{
+	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+
+	spin_lock(&buf->rb_recovery_lock);
+	list_add(&mw->mw_list, &buf->rb_stale_mrs);
+	spin_unlock(&buf->rb_recovery_lock);
+
+	schedule_delayed_work(&buf->rb_recovery_worker, 0);
+}
+
+static void
+rpcrdma_create_mrs(struct rpcrdma_xprt *r_xprt)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+	unsigned int count;
+	LIST_HEAD(free);
+	LIST_HEAD(all);
+
+	for (count = 0; count < 32; count++) {
+		struct rpcrdma_mw *mw;
+		int rc;
+
+		mw = kzalloc(sizeof(*mw), GFP_KERNEL);
+		if (!mw)
+			break;
+
+		rc = ia->ri_ops->ro_init_mr(ia, mw);
+		if (rc) {
+			kfree(mw);
+			break;
+		}
+
+		mw->mw_xprt = r_xprt;
+
+		list_add(&mw->mw_list, &free);
+		list_add(&mw->mw_all, &all);
+	}
+
+	spin_lock(&buf->rb_mwlock);
+	list_splice(&free, &buf->rb_mws);
+	list_splice(&all, &buf->rb_all);
+	r_xprt->rx_stats.mrs_allocated += count;
+	spin_unlock(&buf->rb_mwlock);
+
+	dprintk("RPC:       %s: created %u MRs\n", __func__, count);
+}
+
+static void
+rpcrdma_mr_refresh_worker(struct work_struct *work)
+{
+	struct rpcrdma_buffer *buf = container_of(work, struct rpcrdma_buffer,
+						  rb_refresh_worker.work);
+	struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt,
+						   rx_buf);
+
+	rpcrdma_create_mrs(r_xprt);
+}
+
 struct rpcrdma_req *
 rpcrdma_create_req(struct rpcrdma_xprt *r_xprt)
 {
@@ -793,6 +847,7 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt)
 	spin_unlock(&buffer->rb_reqslock);
 	req->rl_cqe.done = rpcrdma_wc_send;
 	req->rl_buffer = &r_xprt->rx_buf;
+	INIT_LIST_HEAD(&req->rl_registered);
 	return req;
 }
 
@@ -832,17 +887,23 @@ int
 rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 {
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	int i, rc;
 
 	buf->rb_max_requests = r_xprt->rx_data.max_requests;
 	buf->rb_bc_srv_max_requests = 0;
-	spin_lock_init(&buf->rb_lock);
 	atomic_set(&buf->rb_credits, 1);
+	spin_lock_init(&buf->rb_mwlock);
+	spin_lock_init(&buf->rb_lock);
+	spin_lock_init(&buf->rb_recovery_lock);
+	INIT_LIST_HEAD(&buf->rb_mws);
+	INIT_LIST_HEAD(&buf->rb_all);
+	INIT_LIST_HEAD(&buf->rb_stale_mrs);
+	INIT_DELAYED_WORK(&buf->rb_refresh_worker,
+			  rpcrdma_mr_refresh_worker);
+	INIT_DELAYED_WORK(&buf->rb_recovery_worker,
+			  rpcrdma_mr_recovery_worker);
 
-	rc = ia->ri_ops->ro_init(r_xprt);
-	if (rc)
-		goto out;
+	rpcrdma_create_mrs(r_xprt);
 
 	INIT_LIST_HEAD(&buf->rb_send_bufs);
 	INIT_LIST_HEAD(&buf->rb_allreqs);
@@ -862,7 +923,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 	}
 
 	INIT_LIST_HEAD(&buf->rb_recv_bufs);
-	for (i = 0; i < buf->rb_max_requests + 2; i++) {
+	for (i = 0; i < buf->rb_max_requests; i++) {
 		struct rpcrdma_rep *rep;
 
 		rep = rpcrdma_create_rep(r_xprt);
@@ -918,11 +979,39 @@ rpcrdma_destroy_req(struct rpcrdma_ia *ia, struct rpcrdma_req *req)
 	kfree(req);
 }
 
+static void
+rpcrdma_destroy_mrs(struct rpcrdma_buffer *buf)
+{
+	struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt,
+						   rx_buf);
+	struct rpcrdma_ia *ia = rdmab_to_ia(buf);
+	struct rpcrdma_mw *mw;
+	unsigned int count;
+
+	count = 0;
+	spin_lock(&buf->rb_mwlock);
+	while (!list_empty(&buf->rb_all)) {
+		mw = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all);
+		list_del(&mw->mw_all);
+
+		spin_unlock(&buf->rb_mwlock);
+		ia->ri_ops->ro_release_mr(mw);
+		count++;
+		spin_lock(&buf->rb_mwlock);
+	}
+	spin_unlock(&buf->rb_mwlock);
+	r_xprt->rx_stats.mrs_allocated = 0;
+
+	dprintk("RPC:       %s: released %u MRs\n", __func__, count);
+}
+
 void
 rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 {
 	struct rpcrdma_ia *ia = rdmab_to_ia(buf);
 
+	cancel_delayed_work_sync(&buf->rb_recovery_worker);
+
 	while (!list_empty(&buf->rb_recv_bufs)) {
 		struct rpcrdma_rep *rep;
 
@@ -944,7 +1033,7 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 	}
 	spin_unlock(&buf->rb_reqslock);
 
-	ia->ri_ops->ro_destroy(buf);
+	rpcrdma_destroy_mrs(buf);
 }
 
 struct rpcrdma_mw *
@@ -962,8 +1051,17 @@ rpcrdma_get_mw(struct rpcrdma_xprt *r_xprt)
 	spin_unlock(&buf->rb_mwlock);
 
 	if (!mw)
-		pr_err("RPC:       %s: no MWs available\n", __func__);
+		goto out_nomws;
 	return mw;
+
+out_nomws:
+	dprintk("RPC:       %s: no MWs available\n", __func__);
+	schedule_delayed_work(&buf->rb_refresh_worker, 0);
+
+	/* Allow the reply handler and refresh worker to run */
+	cond_resched();
+
+	return NULL;
 }
 
 void
@@ -978,8 +1076,6 @@ rpcrdma_put_mw(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw)
 
 /*
  * Get a set of request/reply buffers.
- *
- * Reply buffer (if available) is attached to send buffer upon return.
  */
 struct rpcrdma_req *
 rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
@@ -998,13 +1094,13 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
 
 out_reqbuf:
 	spin_unlock(&buffers->rb_lock);
-	pr_warn("RPC:       %s: out of request buffers\n", __func__);
+	pr_warn("rpcrdma: out of request buffers (%p)\n", buffers);
 	return NULL;
 out_repbuf:
+	list_add(&req->rl_free, &buffers->rb_send_bufs);
 	spin_unlock(&buffers->rb_lock);
-	pr_warn("RPC:       %s: out of reply buffers\n", __func__);
-	req->rl_reply = NULL;
-	return req;
+	pr_warn("rpcrdma: out of reply buffers (%p)\n", buffers);
+	return NULL;
 }
 
 /*
@@ -1060,14 +1156,6 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep)
  * Wrappers for internal-use kmalloc memory registration, used by buffer code.
  */
 
-void
-rpcrdma_mapping_error(struct rpcrdma_mr_seg *seg)
-{
-	dprintk("RPC:       map_one: offset %p iova %llx len %zu\n",
-		seg->mr_offset,
-		(unsigned long long)seg->mr_dma, seg->mr_dmalen);
-}
-
 /**
  * rpcrdma_alloc_regbuf - kmalloc and register memory for SEND/RECV buffers
  * @ia: controlling rpcrdma_ia
@@ -1150,7 +1238,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 	if (rep) {
 		rc = rpcrdma_ep_post_recv(ia, ep, rep);
 		if (rc)
-			goto out;
+			return rc;
 		req->rl_reply = NULL;
 	}
 
@@ -1175,10 +1263,12 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 
 	rc = ib_post_send(ia->ri_id->qp, &send_wr, &send_wr_fail);
 	if (rc)
-		dprintk("RPC:       %s: ib_post_send returned %i\n", __func__,
-			rc);
-out:
-	return rc;
+		goto out_postsend_err;
+	return 0;
+
+out_postsend_err:
+	pr_err("rpcrdma: RDMA Send ib_post_send returned %i\n", rc);
+	return -ENOTCONN;
 }
 
 /*
@@ -1203,11 +1293,13 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
 				   DMA_BIDIRECTIONAL);
 
 	rc = ib_post_recv(ia->ri_id->qp, &recv_wr, &recv_wr_fail);
-
 	if (rc)
-		dprintk("RPC:       %s: ib_post_recv returned %i\n", __func__,
-			rc);
-	return rc;
+		goto out_postrecv;
+	return 0;
+
+out_postrecv:
+	pr_err("rpcrdma: ib_post_recv returned %i\n", rc);
+	return -ENOTCONN;
 }
 
 /**
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 95cdc66225ee..670fad57153a 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -68,7 +68,6 @@ struct rpcrdma_ia {
 	struct ib_device	*ri_device;
 	struct rdma_cm_id 	*ri_id;
 	struct ib_pd		*ri_pd;
-	struct ib_mr		*ri_dma_mr;
 	struct completion	ri_done;
 	int			ri_async_rc;
 	unsigned int		ri_max_frmr_depth;
@@ -172,23 +171,14 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb)
  *   o recv buffer (posted to provider)
  *   o ib_sge (also donated to provider)
  *   o status of reply (length, success or not)
- *   o bookkeeping state to get run by tasklet (list, etc)
+ *   o bookkeeping state to get run by reply handler (list, etc)
  *
- * These are allocated during initialization, per-transport instance;
- * however, the tasklet execution list itself is global, as it should
- * always be pretty short.
+ * These are allocated during initialization, per-transport instance.
  *
  * N of these are associated with a transport instance, and stored in
  * struct rpcrdma_buffer. N is the max number of outstanding requests.
  */
 
-#define RPCRDMA_MAX_DATA_SEGS	((1 * 1024 * 1024) / PAGE_SIZE)
-
-/* data segments + head/tail for Call + head/tail for Reply */
-#define RPCRDMA_MAX_SEGS 	(RPCRDMA_MAX_DATA_SEGS + 4)
-
-struct rpcrdma_buffer;
-
 struct rpcrdma_rep {
 	struct ib_cqe		rr_cqe;
 	unsigned int		rr_len;
@@ -221,9 +211,6 @@ enum rpcrdma_frmr_state {
 };
 
 struct rpcrdma_frmr {
-	struct scatterlist		*fr_sg;
-	int				fr_nents;
-	enum dma_data_direction		fr_dir;
 	struct ib_mr			*fr_mr;
 	struct ib_cqe			fr_cqe;
 	enum rpcrdma_frmr_state		fr_state;
@@ -235,18 +222,23 @@ struct rpcrdma_frmr {
 };
 
 struct rpcrdma_fmr {
-	struct ib_fmr		*fmr;
-	u64			*physaddrs;
+	struct ib_fmr		*fm_mr;
+	u64			*fm_physaddrs;
 };
 
 struct rpcrdma_mw {
+	struct list_head	mw_list;
+	struct scatterlist	*mw_sg;
+	int			mw_nents;
+	enum dma_data_direction	mw_dir;
 	union {
 		struct rpcrdma_fmr	fmr;
 		struct rpcrdma_frmr	frmr;
 	};
-	struct work_struct	mw_work;
 	struct rpcrdma_xprt	*mw_xprt;
-	struct list_head	mw_list;
+	u32			mw_handle;
+	u32			mw_length;
+	u64			mw_offset;
 	struct list_head	mw_all;
 };
 
@@ -266,33 +258,30 @@ struct rpcrdma_mw {
  * of iovs for send operations. The reason is that the iovs passed to
  * ib_post_{send,recv} must not be modified until the work request
  * completes.
- *
- * NOTES:
- *   o RPCRDMA_MAX_SEGS is the max number of addressible chunk elements we
- *     marshal. The number needed varies depending on the iov lists that
- *     are passed to us, the memory registration mode we are in, and if
- *     physical addressing is used, the layout.
  */
 
+/* Maximum number of page-sized "segments" per chunk list to be
+ * registered or invalidated. Must handle a Reply chunk:
+ */
+enum {
+	RPCRDMA_MAX_IOV_SEGS	= 3,
+	RPCRDMA_MAX_DATA_SEGS	= ((1 * 1024 * 1024) / PAGE_SIZE) + 1,
+	RPCRDMA_MAX_SEGS	= RPCRDMA_MAX_DATA_SEGS +
+				  RPCRDMA_MAX_IOV_SEGS,
+};
+
 struct rpcrdma_mr_seg {		/* chunk descriptors */
-	struct rpcrdma_mw *rl_mw;	/* registered MR */
-	u64		mr_base;	/* registration result */
-	u32		mr_rkey;	/* registration result */
 	u32		mr_len;		/* length of chunk or segment */
-	int		mr_nsegs;	/* number of segments in chunk or 0 */
-	enum dma_data_direction	mr_dir;	/* segment mapping direction */
-	dma_addr_t	mr_dma;		/* segment mapping address */
-	size_t		mr_dmalen;	/* segment mapping length */
 	struct page	*mr_page;	/* owning page, if any */
 	char		*mr_offset;	/* kva if no page, else offset */
 };
 
 #define RPCRDMA_MAX_IOVS	(2)
 
+struct rpcrdma_buffer;
 struct rpcrdma_req {
 	struct list_head	rl_free;
 	unsigned int		rl_niovs;
-	unsigned int		rl_nchunks;
 	unsigned int		rl_connect_cookie;
 	struct rpc_task		*rl_task;
 	struct rpcrdma_buffer	*rl_buffer;
@@ -300,12 +289,13 @@ struct rpcrdma_req {
 	struct ib_sge		rl_send_iov[RPCRDMA_MAX_IOVS];
 	struct rpcrdma_regbuf	*rl_rdmabuf;
 	struct rpcrdma_regbuf	*rl_sendbuf;
-	struct rpcrdma_mr_seg	rl_segments[RPCRDMA_MAX_SEGS];
-	struct rpcrdma_mr_seg	*rl_nextseg;
 
 	struct ib_cqe		rl_cqe;
 	struct list_head	rl_all;
 	bool			rl_backchannel;
+
+	struct list_head	rl_registered;	/* registered segments */
+	struct rpcrdma_mr_seg	rl_segments[RPCRDMA_MAX_SEGS];
 };
 
 static inline struct rpcrdma_req *
@@ -341,6 +331,11 @@ struct rpcrdma_buffer {
 	struct list_head	rb_allreqs;
 
 	u32			rb_bc_max_requests;
+
+	spinlock_t		rb_recovery_lock; /* protect rb_stale_mrs */
+	struct list_head	rb_stale_mrs;
+	struct delayed_work	rb_recovery_worker;
+	struct delayed_work	rb_refresh_worker;
 };
 #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia)
 
@@ -387,6 +382,9 @@ struct rpcrdma_stats {
 	unsigned long		bad_reply_count;
 	unsigned long		nomsg_call_count;
 	unsigned long		bcall_count;
+	unsigned long		mrs_recovered;
+	unsigned long		mrs_orphaned;
+	unsigned long		mrs_allocated;
 };
 
 /*
@@ -395,23 +393,25 @@ struct rpcrdma_stats {
 struct rpcrdma_xprt;
 struct rpcrdma_memreg_ops {
 	int		(*ro_map)(struct rpcrdma_xprt *,
-				  struct rpcrdma_mr_seg *, int, bool);
+				  struct rpcrdma_mr_seg *, int, bool,
+				  struct rpcrdma_mw **);
 	void		(*ro_unmap_sync)(struct rpcrdma_xprt *,
 					 struct rpcrdma_req *);
 	void		(*ro_unmap_safe)(struct rpcrdma_xprt *,
 					 struct rpcrdma_req *, bool);
+	void		(*ro_recover_mr)(struct rpcrdma_mw *);
 	int		(*ro_open)(struct rpcrdma_ia *,
 				   struct rpcrdma_ep *,
 				   struct rpcrdma_create_data_internal *);
 	size_t		(*ro_maxpages)(struct rpcrdma_xprt *);
-	int		(*ro_init)(struct rpcrdma_xprt *);
-	void		(*ro_destroy)(struct rpcrdma_buffer *);
+	int		(*ro_init_mr)(struct rpcrdma_ia *,
+				      struct rpcrdma_mw *);
+	void		(*ro_release_mr)(struct rpcrdma_mw *);
 	const char	*ro_displayname;
 };
 
 extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops;
 extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops;
-extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops;
 
 /*
  * RPCRDMA transport -- encapsulates the structures above for
@@ -446,6 +446,8 @@ extern int xprt_rdma_pad_optimize;
  */
 int rpcrdma_ia_open(struct rpcrdma_xprt *, struct sockaddr *, int);
 void rpcrdma_ia_close(struct rpcrdma_ia *);
+bool frwr_is_supported(struct rpcrdma_ia *);
+bool fmr_is_supported(struct rpcrdma_ia *);
 
 /*
  * Endpoint calls - xprtrdma/verbs.c
@@ -477,6 +479,8 @@ void rpcrdma_buffer_put(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_get(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_put(struct rpcrdma_rep *);
 
+void rpcrdma_defer_mr_recovery(struct rpcrdma_mw *);
+
 struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *,
 					    size_t, gfp_t);
 void rpcrdma_free_regbuf(struct rpcrdma_ia *,
@@ -484,9 +488,6 @@ void rpcrdma_free_regbuf(struct rpcrdma_ia *,
 
 int rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *, unsigned int);
 
-int frwr_alloc_recovery_wq(void);
-void frwr_destroy_recovery_wq(void);
-
 int rpcrdma_alloc_wq(void);
 void rpcrdma_destroy_wq(void);
 
@@ -494,45 +495,12 @@ void rpcrdma_destroy_wq(void);
  * Wrappers for chunk registration, shared by read/write chunk code.
  */
 
-void rpcrdma_mapping_error(struct rpcrdma_mr_seg *);
-
 static inline enum dma_data_direction
 rpcrdma_data_dir(bool writing)
 {
 	return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 }
 
-static inline void
-rpcrdma_map_one(struct ib_device *device, struct rpcrdma_mr_seg *seg,
-		enum dma_data_direction direction)
-{
-	seg->mr_dir = direction;
-	seg->mr_dmalen = seg->mr_len;
-
-	if (seg->mr_page)
-		seg->mr_dma = ib_dma_map_page(device,
-				seg->mr_page, offset_in_page(seg->mr_offset),
-				seg->mr_dmalen, seg->mr_dir);
-	else
-		seg->mr_dma = ib_dma_map_single(device,
-				seg->mr_offset,
-				seg->mr_dmalen, seg->mr_dir);
-
-	if (ib_dma_mapping_error(device, seg->mr_dma))
-		rpcrdma_mapping_error(seg);
-}
-
-static inline void
-rpcrdma_unmap_one(struct ib_device *device, struct rpcrdma_mr_seg *seg)
-{
-	if (seg->mr_page)
-		ib_dma_unmap_page(device,
-				  seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
-	else
-		ib_dma_unmap_single(device,
-				    seg->mr_dma, seg->mr_dmalen, seg->mr_dir);
-}
-
 /*
  * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c
  */
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 3ad9fab1985f..1fd464764765 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -604,7 +604,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 
 	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
 	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
-	nla_strlcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]),
+	nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
 		    TIPC_MAX_LINK_NAME);
 
 	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 2660fbcf94d1..7798e1608f4f 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -500,34 +500,34 @@ static int apparmor_setprocattr(struct task_struct *task, char *name,
 {
 	struct common_audit_data sa;
 	struct apparmor_audit_data aad = {0,};
-	char *command, *args = value;
+	char *command, *largs = NULL, *args = value;
 	size_t arg_size;
 	int error;
 
 	if (size == 0)
 		return -EINVAL;
-	/* args points to a PAGE_SIZE buffer, AppArmor requires that
-	 * the buffer must be null terminated or have size <= PAGE_SIZE -1
-	 * so that AppArmor can null terminate them
-	 */
-	if (args[size - 1] != '\0') {
-		if (size == PAGE_SIZE)
-			return -EINVAL;
-		args[size] = '\0';
-	}
-
 	/* task can only write its own attributes */
 	if (current != task)
 		return -EACCES;
 
-	args = value;
+	/* AppArmor requires that the buffer must be null terminated atm */
+	if (args[size - 1] != '\0') {
+		/* null terminate */
+		largs = args = kmalloc(size + 1, GFP_KERNEL);
+		if (!args)
+			return -ENOMEM;
+		memcpy(args, value, size);
+		args[size] = '\0';
+	}
+
+	error = -EINVAL;
 	args = strim(args);
 	command = strsep(&args, " ");
 	if (!args)
-		return -EINVAL;
+		goto out;
 	args = skip_spaces(args);
 	if (!*args)
-		return -EINVAL;
+		goto out;
 
 	arg_size = size - (args - (char *) value);
 	if (strcmp(name, "current") == 0) {
@@ -553,10 +553,12 @@ static int apparmor_setprocattr(struct task_struct *task, char *name,
 			goto fail;
 	} else
 		/* only support the "current" and "exec" process attributes */
-		return -EINVAL;
+		goto fail;
 
 	if (!error)
 		error = size;
+out:
+	kfree(largs);
 	return error;
 
 fail:
@@ -565,9 +567,9 @@ fail:
 	aad.profile = aa_current_profile();
 	aad.op = OP_SETPROCATTR;
 	aad.info = name;
-	aad.error = -EINVAL;
+	aad.error = error = -EINVAL;
 	aa_audit_msg(AUDIT_APPARMOR_DENIED, &sa, NULL);
-	return -EINVAL;
+	goto out;
 }
 
 static int apparmor_task_setrlimit(struct task_struct *task,
diff --git a/sound/core/timer.c b/sound/core/timer.c
index e722022d325d..9a6157ea6881 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -1955,6 +1955,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 
 		qhead = tu->qhead++;
 		tu->qhead %= tu->queue_size;
+		tu->qused--;
 		spin_unlock_irq(&tu->qlock);
 
 		if (tu->tread) {
@@ -1968,7 +1969,6 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 		}
 
 		spin_lock_irq(&tu->qlock);
-		tu->qused--;
 		if (err < 0)
 			goto _error;
 		result += unit;
diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c
index 4a054d720112..d3125c169684 100644
--- a/sound/pci/au88x0/au88x0_core.c
+++ b/sound/pci/au88x0/au88x0_core.c
@@ -1444,9 +1444,8 @@ static int vortex_wtdma_bufshift(vortex_t * vortex, int wtdma)
 	int page, p, pp, delta, i;
 
 	page =
-	    (hwread(vortex->mmio, VORTEX_WTDMA_STAT + (wtdma << 2)) &
-	     WT_SUBBUF_MASK)
-	    >> WT_SUBBUF_SHIFT;
+	    (hwread(vortex->mmio, VORTEX_WTDMA_STAT + (wtdma << 2))
+	     >> WT_SUBBUF_SHIFT) & WT_SUBBUF_MASK;
 	if (dma->nr_periods >= 4)
 		delta = (page - dma->period_real) & 3;
 	else {
diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index 1cb85aeb0cea..286f5e3686a3 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -2200,11 +2200,11 @@ static int snd_echo_resume(struct device *dev)
 	u32 pipe_alloc_mask;
 	int err;
 
-	commpage_bak = kmalloc(sizeof(struct echoaudio), GFP_KERNEL);
+	commpage_bak = kmalloc(sizeof(*commpage), GFP_KERNEL);
 	if (commpage_bak == NULL)
 		return -ENOMEM;
 	commpage = chip->comm_page;
-	memcpy(commpage_bak, commpage, sizeof(struct comm_page));
+	memcpy(commpage_bak, commpage, sizeof(*commpage));
 
 	err = init_hw(chip, chip->pci->device, chip->pci->subsystem_device);
 	if (err < 0) {
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 320445f3bf73..79c7b340acc2 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -3977,6 +3977,8 @@ static hda_nid_t set_path_power(struct hda_codec *codec, hda_nid_t nid,
 
 	for (n = 0; n < spec->paths.used; n++) {
 		path = snd_array_elem(&spec->paths, n);
+		if (!path->depth)
+			continue;
 		if (path->path[0] == nid ||
 		    path->path[path->depth - 1] == nid) {
 			bool pin_old = path->pin_enabled;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 94089fc71884..e320c44714b1 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -367,9 +367,10 @@ enum {
 #define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
 #define IS_KBL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa171)
 #define IS_KBL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d71)
+#define IS_KBL_H(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa2f0)
 #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
 #define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) || \
-			IS_KBL(pci) || IS_KBL_LP(pci)
+			IS_KBL(pci) || IS_KBL_LP(pci) || IS_KBL_H(pci)
 
 static char *driver_short_names[] = {
 	[AZX_DRIVER_ICH] = "HDA Intel",
@@ -2190,6 +2191,9 @@ static const struct pci_device_id azx_ids[] = {
 	/* Kabylake-LP */
 	{ PCI_DEVICE(0x8086, 0x9d71),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+	/* Kabylake-H */
+	{ PCI_DEVICE(0x8086, 0xa2f0),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	/* Broxton-P(Apollolake) */
 	{ PCI_DEVICE(0x8086, 0x5a98),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 900bfbc3368c..5fac786e4982 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5651,6 +5651,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x504a, "ThinkPad X260", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
 	SND_PCI_QUIRK(0x17aa, 0x5050, "Thinkpad T560p", ALC292_FIXUP_TPT460),
+	SND_PCI_QUIRK(0x17aa, 0x5051, "Thinkpad L460", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x5053, "Thinkpad T460", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 4d82a58ff6b0..f3fb98f0a995 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -483,9 +483,10 @@ config SND_SOC_DMIC
 	tristate
 
 config SND_SOC_HDMI_CODEC
-       tristate
-       select SND_PCM_ELD
-       select SND_PCM_IEC958
+	tristate
+	select SND_PCM_ELD
+	select SND_PCM_IEC958
+	select HDMI
 
 config SND_SOC_ES8328
 	tristate "Everest Semi ES8328 CODEC"
diff --git a/sound/soc/codecs/ak4613.c b/sound/soc/codecs/ak4613.c
index 647f69de6baa..5013d2ba0c10 100644
--- a/sound/soc/codecs/ak4613.c
+++ b/sound/soc/codecs/ak4613.c
@@ -146,6 +146,7 @@ static const struct regmap_config ak4613_regmap_cfg = {
 	.max_register		= 0x16,
 	.reg_defaults		= ak4613_reg,
 	.num_reg_defaults	= ARRAY_SIZE(ak4613_reg),
+	.cache_type		= REGCACHE_RBTREE,
 };
 
 static const struct of_device_id ak4613_of_match[] = {
@@ -530,7 +531,6 @@ static int ak4613_i2c_remove(struct i2c_client *client)
 static struct i2c_driver ak4613_i2c_driver = {
 	.driver = {
 		.name = "ak4613-codec",
-		.owner = THIS_MODULE,
 		.of_match_table = ak4613_of_match,
 	},
 	.probe		= ak4613_i2c_probe,
diff --git a/sound/soc/codecs/cx20442.c b/sound/soc/codecs/cx20442.c
index d6f4abbbf8a7..fb3885fe0afb 100644
--- a/sound/soc/codecs/cx20442.c
+++ b/sound/soc/codecs/cx20442.c
@@ -226,6 +226,7 @@ static int v253_open(struct tty_struct *tty)
 	if (!tty->disc_data)
 		return -ENODEV;
 
+	tty->receive_room = 16;
 	if (tty->ops->write(tty, v253_init, len) != len) {
 		ret = -EIO;
 		goto err;
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 181cd3bf0b92..2abb742fc47b 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1474,6 +1474,11 @@ static int hdmi_codec_probe(struct snd_soc_codec *codec)
 	 * exit, we call pm_runtime_suspend() so that will do for us
 	 */
 	hlink = snd_hdac_ext_bus_get_link(edev->ebus, dev_name(&edev->hdac.dev));
+	if (!hlink) {
+		dev_err(&edev->hdac.dev, "hdac link not found\n");
+		return -EIO;
+	}
+
 	snd_hdac_ext_bus_link_get(edev->ebus, hlink);
 
 	ret = create_fill_widget_route_map(dapm);
@@ -1634,6 +1639,11 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 
 	/* hold the ref while we probe */
 	hlink = snd_hdac_ext_bus_get_link(edev->ebus, dev_name(&edev->hdac.dev));
+	if (!hlink) {
+		dev_err(&edev->hdac.dev, "hdac link not found\n");
+		return -EIO;
+	}
+
 	snd_hdac_ext_bus_link_get(edev->ebus, hlink);
 
 	hdmi_priv = devm_kzalloc(&codec->dev, sizeof(*hdmi_priv), GFP_KERNEL);
@@ -1744,6 +1754,11 @@ static int hdac_hdmi_runtime_suspend(struct device *dev)
 	}
 
 	hlink = snd_hdac_ext_bus_get_link(ebus, dev_name(dev));
+	if (!hlink) {
+		dev_err(dev, "hdac link not found\n");
+		return -EIO;
+	}
+
 	snd_hdac_ext_bus_link_put(ebus, hlink);
 
 	return 0;
@@ -1765,6 +1780,11 @@ static int hdac_hdmi_runtime_resume(struct device *dev)
 		return 0;
 
 	hlink = snd_hdac_ext_bus_get_link(ebus, dev_name(dev));
+	if (!hlink) {
+		dev_err(dev, "hdac link not found\n");
+		return -EIO;
+	}
+
 	snd_hdac_ext_bus_link_get(ebus, hlink);
 
 	err = snd_hdac_display_power(bus, true);
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 3c6594da6c9c..d70847c9eeb0 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -253,7 +253,7 @@ static const struct reg_default rt5650_reg[] = {
 	{ 0x2b, 0x5454 },
 	{ 0x2c, 0xaaa0 },
 	{ 0x2d, 0x0000 },
-	{ 0x2f, 0x1002 },
+	{ 0x2f, 0x5002 },
 	{ 0x31, 0x5000 },
 	{ 0x32, 0x0000 },
 	{ 0x33, 0x0000 },
diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c
index 49a9e7049e2b..0af5ddbef1da 100644
--- a/sound/soc/codecs/rt5670.c
+++ b/sound/soc/codecs/rt5670.c
@@ -619,7 +619,7 @@ static const struct snd_kcontrol_new rt5670_snd_controls[] = {
 		RT5670_L_MUTE_SFT, RT5670_R_MUTE_SFT, 1, 1),
 	SOC_DOUBLE_TLV("HP Playback Volume", RT5670_HP_VOL,
 		RT5670_L_VOL_SFT, RT5670_R_VOL_SFT,
-		39, 0, out_vol_tlv),
+		39, 1, out_vol_tlv),
 	/* OUTPUT Control */
 	SOC_DOUBLE("OUT Channel Switch", RT5670_LOUT1,
 		RT5670_VOL_L_SFT, RT5670_VOL_R_SFT, 1, 1),
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index da60e3fe5ee7..e7fe6b7b95b7 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -1872,7 +1872,7 @@ static struct snd_soc_dai_driver wm5102_dai[] = {
 		.capture = {
 			.stream_name = "Audio Trace CPU",
 			.channels_min = 1,
-			.channels_max = 6,
+			.channels_max = 4,
 			.rates = WM5102_RATES,
 			.formats = WM5102_FORMATS,
 		},
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index b5820e4d5471..d54f1b46c9ec 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -1723,6 +1723,7 @@ static const struct snd_soc_dapm_route wm5110_dapm_routes[] = {
 	{ "OUT2L", NULL, "SYSCLK" },
 	{ "OUT2R", NULL, "SYSCLK" },
 	{ "OUT3L", NULL, "SYSCLK" },
+	{ "OUT3R", NULL, "SYSCLK" },
 	{ "OUT4L", NULL, "SYSCLK" },
 	{ "OUT4R", NULL, "SYSCLK" },
 	{ "OUT5L", NULL, "SYSCLK" },
diff --git a/sound/soc/codecs/wm8940.c b/sound/soc/codecs/wm8940.c
index f6f9395ea38e..1c600819f768 100644
--- a/sound/soc/codecs/wm8940.c
+++ b/sound/soc/codecs/wm8940.c
@@ -743,6 +743,7 @@ static const struct regmap_config wm8940_regmap = {
 	.max_register = WM8940_MONOMIX,
 	.reg_defaults = wm8940_reg_defaults,
 	.num_reg_defaults = ARRAY_SIZE(wm8940_reg_defaults),
+	.cache_type = REGCACHE_RBTREE,
 
 	.readable_reg = wm8940_readable_register,
 	.volatile_reg = wm8940_volatile_register,
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 0f66fda2c772..237dc67002ef 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -1513,8 +1513,9 @@ static struct davinci_mcasp_pdata am33xx_mcasp_pdata = {
 };
 
 static struct davinci_mcasp_pdata dra7_mcasp_pdata = {
-	.tx_dma_offset = 0x200,
-	.rx_dma_offset = 0x284,
+	/* The CFG port offset will be calculated if it is needed */
+	.tx_dma_offset = 0,
+	.rx_dma_offset = 0,
 	.version = MCASP_VERSION_4,
 };
 
@@ -1734,6 +1735,52 @@ static int davinci_mcasp_get_dma_type(struct davinci_mcasp *mcasp)
 	return PCM_EDMA;
 }
 
+static u32 davinci_mcasp_txdma_offset(struct davinci_mcasp_pdata *pdata)
+{
+	int i;
+	u32 offset = 0;
+
+	if (pdata->version != MCASP_VERSION_4)
+		return pdata->tx_dma_offset;
+
+	for (i = 0; i < pdata->num_serializer; i++) {
+		if (pdata->serial_dir[i] == TX_MODE) {
+			if (!offset) {
+				offset = DAVINCI_MCASP_TXBUF_REG(i);
+			} else {
+				pr_err("%s: Only one serializer allowed!\n",
+				       __func__);
+				break;
+			}
+		}
+	}
+
+	return offset;
+}
+
+static u32 davinci_mcasp_rxdma_offset(struct davinci_mcasp_pdata *pdata)
+{
+	int i;
+	u32 offset = 0;
+
+	if (pdata->version != MCASP_VERSION_4)
+		return pdata->rx_dma_offset;
+
+	for (i = 0; i < pdata->num_serializer; i++) {
+		if (pdata->serial_dir[i] == RX_MODE) {
+			if (!offset) {
+				offset = DAVINCI_MCASP_RXBUF_REG(i);
+			} else {
+				pr_err("%s: Only one serializer allowed!\n",
+				       __func__);
+				break;
+			}
+		}
+	}
+
+	return offset;
+}
+
 static int davinci_mcasp_probe(struct platform_device *pdev)
 {
 	struct snd_dmaengine_dai_dma_data *dma_data;
@@ -1862,7 +1909,7 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 	if (dat)
 		dma_data->addr = dat->start;
 	else
-		dma_data->addr = mem->start + pdata->tx_dma_offset;
+		dma_data->addr = mem->start + davinci_mcasp_txdma_offset(pdata);
 
 	dma = &mcasp->dma_request[SNDRV_PCM_STREAM_PLAYBACK];
 	res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
@@ -1883,7 +1930,8 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 		if (dat)
 			dma_data->addr = dat->start;
 		else
-			dma_data->addr = mem->start + pdata->rx_dma_offset;
+			dma_data->addr =
+				mem->start + davinci_mcasp_rxdma_offset(pdata);
 
 		dma = &mcasp->dma_request[SNDRV_PCM_STREAM_CAPTURE];
 		res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
diff --git a/sound/soc/davinci/davinci-mcasp.h b/sound/soc/davinci/davinci-mcasp.h
index 1e8787fb3fb7..afddc8010c54 100644
--- a/sound/soc/davinci/davinci-mcasp.h
+++ b/sound/soc/davinci/davinci-mcasp.h
@@ -85,9 +85,9 @@
 						(n << 2))
 
 /* Transmit Buffer for Serializer n */
-#define DAVINCI_MCASP_TXBUF_REG		0x200
+#define DAVINCI_MCASP_TXBUF_REG(n)	(0x200 + (n << 2))
 /* Receive Buffer for Serializer n */
-#define DAVINCI_MCASP_RXBUF_REG		0x280
+#define DAVINCI_MCASP_RXBUF_REG(n)	(0x280 + (n << 2))
 
 /* McASP FIFO Registers */
 #define DAVINCI_MCASP_V2_AFIFO_BASE	(0x1010)
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 632ecc0e3956..bedec4a32581 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -952,16 +952,16 @@ static int _fsl_ssi_set_dai_fmt(struct device *dev,
 	ssi_private->i2s_mode = CCSR_SSI_SCR_NET;
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
+		regmap_update_bits(regs, CCSR_SSI_STCCR,
+				   CCSR_SSI_SxCCR_DC_MASK,
+				   CCSR_SSI_SxCCR_DC(2));
+		regmap_update_bits(regs, CCSR_SSI_SRCCR,
+				   CCSR_SSI_SxCCR_DC_MASK,
+				   CCSR_SSI_SxCCR_DC(2));
 		switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
 		case SND_SOC_DAIFMT_CBM_CFS:
 		case SND_SOC_DAIFMT_CBS_CFS:
 			ssi_private->i2s_mode |= CCSR_SSI_SCR_I2S_MODE_MASTER;
-			regmap_update_bits(regs, CCSR_SSI_STCCR,
-					CCSR_SSI_SxCCR_DC_MASK,
-					CCSR_SSI_SxCCR_DC(2));
-			regmap_update_bits(regs, CCSR_SSI_SRCCR,
-					CCSR_SSI_SxCCR_DC_MASK,
-					CCSR_SSI_SxCCR_DC(2));
 			break;
 		case SND_SOC_DAIFMT_CBM_CFM:
 			ssi_private->i2s_mode |= CCSR_SSI_SCR_I2S_MODE_SLAVE;
diff --git a/sound/soc/intel/atom/sst-mfld-platform-compress.c b/sound/soc/intel/atom/sst-mfld-platform-compress.c
index 395168986462..1bead81bb510 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-compress.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-compress.c
@@ -182,24 +182,29 @@ static int sst_platform_compr_trigger(struct snd_compr_stream *cstream, int cmd)
 	case SNDRV_PCM_TRIGGER_START:
 		if (stream->compr_ops->stream_start)
 			return stream->compr_ops->stream_start(sst->dev, stream->id);
+		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 		if (stream->compr_ops->stream_drop)
 			return stream->compr_ops->stream_drop(sst->dev, stream->id);
+		break;
 	case SND_COMPR_TRIGGER_DRAIN:
 		if (stream->compr_ops->stream_drain)
 			return stream->compr_ops->stream_drain(sst->dev, stream->id);
+		break;
 	case SND_COMPR_TRIGGER_PARTIAL_DRAIN:
 		if (stream->compr_ops->stream_partial_drain)
 			return stream->compr_ops->stream_partial_drain(sst->dev, stream->id);
+		break;
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		if (stream->compr_ops->stream_pause)
 			return stream->compr_ops->stream_pause(sst->dev, stream->id);
+		break;
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		if (stream->compr_ops->stream_pause_release)
 			return stream->compr_ops->stream_pause_release(sst->dev, stream->id);
-	default:
-		return -EINVAL;
+		break;
 	}
+	return -EINVAL;
 }
 
 static int sst_platform_compr_pointer(struct snd_compr_stream *cstream,
diff --git a/sound/soc/intel/skylake/bxt-sst.c b/sound/soc/intel/skylake/bxt-sst.c
index 965ce40ce752..8b95e09e23e8 100644
--- a/sound/soc/intel/skylake/bxt-sst.c
+++ b/sound/soc/intel/skylake/bxt-sst.c
@@ -291,6 +291,7 @@ int bxt_sst_dsp_init(struct device *dev, void __iomem *mmio_base, int irq,
 	sst_dsp_mailbox_init(sst, (BXT_ADSP_SRAM0_BASE + SKL_ADSP_W0_STAT_SZ),
 			SKL_ADSP_W0_UP_SZ, BXT_ADSP_SRAM1_BASE, SKL_ADSP_W1_SZ);
 
+	INIT_LIST_HEAD(&sst->module_list);
 	ret = skl_ipc_init(dev, skl);
 	if (ret)
 		return ret;
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 49354d17ea55..c4c51a4d3c8f 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -518,7 +518,7 @@ static void rsnd_adg_get_clkout(struct rsnd_priv *priv,
 		}
 	}
 
-	rsnd_mod_bset(adg_mod, SSICKR, 0x00FF0000, ckr);
+	rsnd_mod_bset(adg_mod, SSICKR, 0x80FF0000, ckr);
 	rsnd_mod_write(adg_mod, BRRA,  rbga);
 	rsnd_mod_write(adg_mod, BRRB,  rbgb);
author	Trond Myklebust <trond.myklebust@primarydata.com>	2016-07-24 23:09:02 +0200
committer	Trond Myklebust <trond.myklebust@primarydata.com>	2016-07-24 23:09:02 +0200
commit	1592c4d62a89bbca895c568d65ce290dfbc36ecc (patch)
tree	6b979bc02ded2ea7e644c34e6939ffbbb7ee001d
parent	Merge branch 'pnfs' (diff)
parent	Merge tag 'nfs-rdma-4.8-2' of git://git.linux-nfs.org/projects/anna/nfs-rdma (diff)
download	linux-1592c4d62a89bbca895c568d65ce290dfbc36ecc.tar.xz linux-1592c4d62a89bbca895c568d65ce290dfbc36ecc.zip