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

net/ipv6/ip6_gre.c is a case of parallel adds.

include/trace/events/tcp.h is a little bit more tricky.  The removal
of in-trace-macro ifdefs in 'net' paralleled with moving
show_tcp_state_name and friends over to include/trace/events/sock.h
in 'net-next'.

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

212 files changed, 2378 insertions, 1204 deletions

diff --git a/Documentation/devicetree/bindings/sound/da7218.txt b/Documentation/devicetree/bindings/sound/da7218.txt
index 5ca5a709b6aa..3ab9dfef38d1 100644
--- a/Documentation/devicetree/bindings/sound/da7218.txt
+++ b/Documentation/devicetree/bindings/sound/da7218.txt
@@ -73,7 +73,7 @@ Example:
 		compatible = "dlg,da7218";
 		reg = <0x1a>;
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 		wakeup-source;
 
 		VDD-supply = <&reg_audio>;
diff --git a/Documentation/devicetree/bindings/sound/da7219.txt b/Documentation/devicetree/bindings/sound/da7219.txt
index cf61681826b6..5b54d2d045c3 100644
--- a/Documentation/devicetree/bindings/sound/da7219.txt
+++ b/Documentation/devicetree/bindings/sound/da7219.txt
@@ -77,7 +77,7 @@ Example:
 		reg = <0x1a>;
 
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 
 		VDD-supply = <&reg_audio>;
 		VDDMIC-supply = <&reg_audio>;
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 3448e675b462..51101708a03a 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -1,6 +1,4 @@
 
-<previous description obsolete, deleted>
-
 Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
@@ -14,13 +12,15 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
 ... unused hole ...
+fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable)
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space (variable)
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Virtual memory map with 5 level page tables:
@@ -36,19 +36,22 @@ ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
 ... unused hole ...
 ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
 ... unused hole ...
+fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Architecture defines a 64-bit virtual address. Implementations can support
 less. Currently supported are 48- and 57-bit virtual addresses. Bits 63
-through to the most-significant implemented bit are set to either all ones
-or all zero. This causes hole between user space and kernel addresses.
+through to the most-significant implemented bit are sign extended.
+This causes hole between user space and kernel addresses if you interpret them
+as unsigned.
 
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
@@ -58,9 +61,6 @@ vmalloc space is lazily synchronized into the different PML4/PML5 pages of
 the processes using the page fault handler, with init_top_pgt as
 reference.
 
-Current X86-64 implementations support up to 46 bits of address space (64 TB),
-which is our current limit. This expands into MBZ space in the page tables.
-
 We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual
 memory window (this size is arbitrary, it can be raised later if needed).
 The mappings are not part of any other kernel PGD and are only available
@@ -72,5 +72,3 @@ following fixmap section.
 Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all
 physical memory, vmalloc/ioremap space and virtual memory map are randomized.
 Their order is preserved but their base will be offset early at boot time.
-
--Andi Kleen, Jul 2004
diff --git a/Makefile b/Makefile
index 7e02f951b284..ac8c441866b7 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 6177d43f0ce8..e2a2b8400490 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -160,9 +160,10 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
 #endif
 }
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 #ifndef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 5acb5a176dbe..72be0c32e902 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1403,7 +1403,7 @@ void show_regs(struct pt_regs * regs)
 
 	printk("NIP:  "REG" LR: "REG" CTR: "REG"\n",
 	       regs->nip, regs->link, regs->ctr);
-	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
+	printk("REGS: %px TRAP: %04lx   %s  (%s)\n",
 	       regs, regs->trap, print_tainted(), init_utsname()->release);
 	printk("MSR:  "REG" ", regs->msr);
 	print_msr_bits(regs->msr);
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index bf457843e032..0d750d274c4e 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -725,7 +725,8 @@ u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu)
 
 	/* Return the per-cpu state for state saving/migration */
 	return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT |
-	       (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT;
+	       (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT |
+	       (u64)0xff << KVM_REG_PPC_ICP_PPRI_SHIFT;
 }
 
 int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
@@ -1558,7 +1559,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 
 	/*
 	 * Restore P and Q. If the interrupt was pending, we
-	 * force both P and Q, which will trigger a resend.
+	 * force Q and !P, which will trigger a resend.
 	 *
 	 * That means that a guest that had both an interrupt
 	 * pending (queued) and Q set will restore with only
@@ -1566,7 +1567,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	 * is perfectly fine as coalescing interrupts that haven't
 	 * been presented yet is always allowed.
 	 */
-	if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
+	if (val & KVM_XICS_PRESENTED && !(val & KVM_XICS_PENDING))
 		state->old_p = true;
 	if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING)
 		state->old_q = true;
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 153812966365..fce545774d50 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -410,8 +410,12 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	int ret;
 	__u64 target;
 
-	if (is_kernel_addr(addr))
-		return branch_target((unsigned int *)addr);
+	if (is_kernel_addr(addr)) {
+		if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+			return 0;
+
+		return branch_target(&instr);
+	}
 
 	/* Userspace: need copy instruction here then translate it */
 	pagefault_disable();
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 0ead3cd73caa..be4e7f84f70a 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -310,6 +310,19 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu)
 		return 0;
 
 	/*
+	 * Check whether nest_imc is registered. We could end up here if the
+	 * cpuhotplug callback registration fails. i.e, callback invokes the
+	 * offline path for all successfully registered nodes. At this stage,
+	 * nest_imc pmu will not be registered and we should return here.
+	 *
+	 * We return with a zero since this is not an offline failure. And
+	 * cpuhp_setup_state() returns the actual failure reason to the caller,
+	 * which in turn will call the cleanup routine.
+	 */
+	if (!nest_pmus)
+		return 0;
+
+	/*
 	 * Now that this cpu is one of the designated,
 	 * find a next cpu a) which is online and b) in same chip.
 	 */
@@ -1171,6 +1184,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		if (nest_pmus == 1) {
 			cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
 			kfree(nest_imc_refc);
+			kfree(per_nest_pmu_arr);
 		}
 
 		if (nest_pmus > 0)
@@ -1195,7 +1209,6 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
 	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
 	kfree(pmu_ptr);
-	kfree(per_nest_pmu_arr);
 	return;
 }
 
@@ -1309,6 +1322,8 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 			ret = nest_pmu_cpumask_init();
 			if (ret) {
 				mutex_unlock(&nest_init_lock);
+				kfree(nest_imc_refc);
+				kfree(per_nest_pmu_arr);
 				goto err_free;
 			}
 		}
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index b668e351fd6c..fca34b2177e2 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -15,9 +15,10 @@ extern void uml_setup_stubs(struct mm_struct *mm);
 /*
  * Needed since we do not use the asm-generic/mm_hooks.h:
  */
-static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	uml_setup_stubs(mm);
+	return 0;
 }
 extern void arch_exit_mmap(struct mm_struct *mm);
 static inline void arch_unmap(struct mm_struct *mm,
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index 59b06b48f27d..5c205a9cb5a6 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -81,9 +81,10 @@ do { \
 	} \
 } while (0)
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 static inline void arch_unmap(struct mm_struct *mm,
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 04d66e6fa447..45dc6233f2b9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -927,7 +927,8 @@ config MAXSMP
 config NR_CPUS
 	int "Maximum number of CPUs" if SMP && !MAXSMP
 	range 2 8 if SMP && X86_32 && !X86_BIGSMP
-	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK
+	range 2 64 if SMP && X86_32 && X86_BIGSMP
+	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64
 	range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
 	default "1" if !SMP
 	default "8192" if MAXSMP
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index bd8b57a5c874..ace8f321a5a1 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -942,9 +942,9 @@ ENTRY(debug)
 
 	/* Are we currently on the SYSENTER stack? */
 	movl	PER_CPU_VAR(cpu_entry_area), %ecx
-	addl	$CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Ldebug_from_sysenter_stack
 
 	TRACE_IRQS_OFF
@@ -986,9 +986,9 @@ ENTRY(nmi)
 
 	/* Are we currently on the SYSENTER stack? */
 	movl	PER_CPU_VAR(cpu_entry_area), %ecx
-	addl	$CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Lnmi_from_sysenter_stack
 
 	/* Not on SYSENTER stack. */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 423885bee398..3d19c830e1b1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -158,8 +158,8 @@ END(native_usergs_sysret64)
 	_entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
 
 /* The top word of the SYSENTER stack is hot and is usable as scratch space. */
-#define RSP_SCRATCH	CPU_ENTRY_AREA_SYSENTER_stack + \
-			SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA
+#define RSP_SCRATCH	CPU_ENTRY_AREA_entry_stack + \
+			SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA
 
 ENTRY(entry_SYSCALL_64_trampoline)
 	UNWIND_HINT_EMPTY
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index f279ba2643dc..1faf40f2dda9 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -37,6 +37,7 @@
 #include <asm/unistd.h>
 #include <asm/fixmap.h>
 #include <asm/traps.h>
+#include <asm/paravirt.h>
 
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
@@ -138,6 +139,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	WARN_ON_ONCE(address != regs->ip);
 
+	/* This should be unreachable in NATIVE mode. */
+	if (WARN_ON(vsyscall_mode == NATIVE))
+		return false;
+
 	if (vsyscall_mode == NONE) {
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall attempted with vsyscall=none");
@@ -329,16 +334,47 @@ int in_gate_area_no_mm(unsigned long addr)
 	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
 }
 
+/*
+ * The VSYSCALL page is the only user-accessible page in the kernel address
+ * range.  Normally, the kernel page tables can have _PAGE_USER clear, but
+ * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
+ * are enabled.
+ *
+ * Some day we may create a "minimal" vsyscall mode in which we emulate
+ * vsyscalls but leave the page not present.  If so, we skip calling
+ * this.
+ */
+static void __init set_vsyscall_pgtable_user_bits(void)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_k(VSYSCALL_ADDR);
+	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+#if CONFIG_PGTABLE_LEVELS >= 5
+	p4d->p4d |= _PAGE_USER;
+#endif
+	pud = pud_offset(p4d, VSYSCALL_ADDR);
+	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
+	pmd = pmd_offset(pud, VSYSCALL_ADDR);
+	set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
+}
+
 void __init map_vsyscall(void)
 {
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 
-	if (vsyscall_mode != NONE)
+	if (vsyscall_mode != NONE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
 			     vsyscall_mode == NATIVE
 			     ? PAGE_KERNEL_VSYSCALL
 			     : PAGE_KERNEL_VVAR);
+		set_vsyscall_pgtable_user_bits();
+	}
 
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
new file mode 100644
index 000000000000..2fbc69a0916e
--- /dev/null
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _ASM_X86_CPU_ENTRY_AREA_H
+#define _ASM_X86_CPU_ENTRY_AREA_H
+
+#include <linux/percpu-defs.h>
+#include <asm/processor.h>
+
+/*
+ * cpu_entry_area is a percpu region that contains things needed by the CPU
+ * and early entry/exit code.  Real types aren't used for all fields here
+ * to avoid circular header dependencies.
+ *
+ * Every field is a virtual alias of some other allocated backing store.
+ * There is no direct allocation of a struct cpu_entry_area.
+ */
+struct cpu_entry_area {
+	char gdt[PAGE_SIZE];
+
+	/*
+	 * The GDT is just below entry_stack and thus serves (on x86_64) as
+	 * a a read-only guard page.
+	 */
+	struct entry_stack_page entry_stack_page;
+
+	/*
+	 * On x86_64, the TSS is mapped RO.  On x86_32, it's mapped RW because
+	 * we need task switches to work, and task switches write to the TSS.
+	 */
+	struct tss_struct tss;
+
+	char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Exception stacks used for IST entries.
+	 *
+	 * In the future, this should have a separate slot for each stack
+	 * with guard pages between them.
+	 */
+	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
+};
+
+#define CPU_ENTRY_AREA_SIZE	(sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+
+extern void setup_cpu_entry_areas(void);
+extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+
+#define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
+#define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
+
+#define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
+
+#define CPU_ENTRY_AREA_MAP_SIZE			\
+	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+
+extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
+
+static inline struct entry_stack *cpu_entry_stack(int cpu)
+{
+	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
+}
+
+#endif
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index aab4fe9f49f8..ec8be07c0cda 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -7,6 +7,7 @@
 #include <asm/mmu.h>
 #include <asm/fixmap.h>
 #include <asm/irq_vectors.h>
+#include <asm/cpu_entry_area.h>
 
 #include <linux/smp.h>
 #include <linux/percpu.h>
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 0211029076ea..6777480d8a42 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_ESPFIX_H
 #define _ASM_X86_ESPFIX_H
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_ESPFIX64
 
 #include <asm/percpu.h>
 
@@ -11,7 +11,8 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
 extern void init_espfix_ap(int cpu);
-
-#endif /* CONFIG_X86_64 */
+#else
+static inline void init_espfix_ap(int cpu) { }
+#endif
 
 #endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 94fc4fa14127..64c4a30e0d39 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -45,46 +45,6 @@ extern unsigned long __FIXADDR_TOP;
 #endif
 
 /*
- * cpu_entry_area is a percpu region in the fixmap that contains things
- * needed by the CPU and early entry/exit code.  Real types aren't used
- * for all fields here to avoid circular header dependencies.
- *
- * Every field is a virtual alias of some other allocated backing store.
- * There is no direct allocation of a struct cpu_entry_area.
- */
-struct cpu_entry_area {
-	char gdt[PAGE_SIZE];
-
-	/*
-	 * The GDT is just below SYSENTER_stack and thus serves (on x86_64) as
-	 * a a read-only guard page.
-	 */
-	struct SYSENTER_stack_page SYSENTER_stack_page;
-
-	/*
-	 * On x86_64, the TSS is mapped RO.  On x86_32, it's mapped RW because
-	 * we need task switches to work, and task switches write to the TSS.
-	 */
-	struct tss_struct tss;
-
-	char entry_trampoline[PAGE_SIZE];
-
-#ifdef CONFIG_X86_64
-	/*
-	 * Exception stacks used for IST entries.
-	 *
-	 * In the future, this should have a separate slot for each stack
-	 * with guard pages between them.
-	 */
-	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
-#endif
-};
-
-#define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE)
-
-extern void setup_cpu_entry_areas(void);
-
-/*
  * Here we define all the compile-time 'special' virtual
  * addresses. The point is to have a constant address at
  * compile time, but to set the physical address only
@@ -123,7 +83,6 @@ enum fixed_addresses {
 	FIX_IO_APIC_BASE_0,
 	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
 #endif
-	FIX_RO_IDT,	/* Virtual mapping for read-only IDT */
 #ifdef CONFIG_X86_32
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -139,9 +98,6 @@ enum fixed_addresses {
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
-	/* Fixmap entries to remap the GDTs, one per processor. */
-	FIX_CPU_ENTRY_AREA_TOP,
-	FIX_CPU_ENTRY_AREA_BOTTOM = FIX_CPU_ENTRY_AREA_TOP + (CPU_ENTRY_AREA_PAGES * NR_CPUS) - 1,
 
 #ifdef CONFIG_ACPI_APEI_GHES
 	/* Used for GHES mapping from assorted contexts */
@@ -182,7 +138,7 @@ enum fixed_addresses {
 extern void reserve_top_address(unsigned long reserve);
 
 #define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
 
 extern int fixmaps_set;
 
@@ -230,30 +186,5 @@ void __init *early_memremap_decrypted_wp(resource_size_t phys_addr,
 void __early_set_fixmap(enum fixed_addresses idx,
 			phys_addr_t phys, pgprot_t flags);
 
-static inline unsigned int __get_cpu_entry_area_page_index(int cpu, int page)
-{
-	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
-
-	return FIX_CPU_ENTRY_AREA_BOTTOM - cpu*CPU_ENTRY_AREA_PAGES - page;
-}
-
-#define __get_cpu_entry_area_offset_index(cpu, offset) ({		\
-	BUILD_BUG_ON(offset % PAGE_SIZE != 0);				\
-	__get_cpu_entry_area_page_index(cpu, offset / PAGE_SIZE);	\
-	})
-
-#define get_cpu_entry_area_index(cpu, field)				\
-	__get_cpu_entry_area_offset_index((cpu), offsetof(struct cpu_entry_area, field))
-
-static inline struct cpu_entry_area *get_cpu_entry_area(int cpu)
-{
-	return (struct cpu_entry_area *)__fix_to_virt(__get_cpu_entry_area_page_index(cpu, 0));
-}
-
-static inline struct SYSENTER_stack *cpu_SYSENTER_stack(int cpu)
-{
-	return &get_cpu_entry_area(cpu)->SYSENTER_stack_page.stack;
-}
-
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_FIXMAP_H */
diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
new file mode 100644
index 000000000000..989cfa86de85
--- /dev/null
+++ b/arch/x86/include/asm/invpcid.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVPCID
+#define _ASM_X86_INVPCID
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
+#endif /* _ASM_X86_INVPCID */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 9ea26f167497..5ff3e8af2c20 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_MMU_H
 
 #include <linux/spinlock.h>
+#include <linux/rwsem.h>
 #include <linux/mutex.h>
 #include <linux/atomic.h>
 
@@ -27,7 +28,8 @@ typedef struct {
 	atomic64_t tlb_gen;
 
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
-	struct ldt_struct *ldt;
+	struct rw_semaphore	ldt_usr_sem;
+	struct ldt_struct	*ldt;
 #endif
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 6d16d15d09a0..5ede7cae1d67 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -57,11 +57,17 @@ struct ldt_struct {
 /*
  * Used for LDT copy/destruction.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+static inline void init_new_context_ldt(struct mm_struct *mm)
+{
+	mm->context.ldt = NULL;
+	init_rwsem(&mm->context.ldt_usr_sem);
+}
+int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
 void destroy_context_ldt(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context_ldt(struct task_struct *tsk,
-				       struct mm_struct *mm)
+static inline void init_new_context_ldt(struct mm_struct *mm) { }
+static inline int ldt_dup_context(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
 {
 	return 0;
 }
@@ -132,18 +138,21 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	mutex_init(&mm->context.lock);
+
 	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	atomic64_set(&mm->context.tlb_gen, 0);
 
-	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
 		/* pkey 0 is the default and always allocated */
 		mm->context.pkey_allocation_map = 0x1;
 		/* -1 means unallocated or invalid */
 		mm->context.execute_only_pkey = -1;
 	}
-	#endif
-	return init_new_context_ldt(tsk, mm);
+#endif
+	init_new_context_ldt(mm);
+	return 0;
 }
 static inline void destroy_context(struct mm_struct *mm)
 {
@@ -176,10 +185,10 @@ do {						\
 } while (0)
 #endif
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	paravirt_arch_dup_mmap(oldmm, mm);
+	return ldt_dup_context(oldmm, mm);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
@@ -282,33 +291,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 }
 
 /*
- * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
- * bits.  This serves two purposes.  It prevents a nasty situation in
- * which PCID-unaware code saves CR3, loads some other value (with PCID
- * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
- * the saved ASID was nonzero.  It also means that any bugs involving
- * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
- * deterministically.
- */
-
-static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
-{
-	if (static_cpu_has(X86_FEATURE_PCID)) {
-		VM_WARN_ON_ONCE(asid > 4094);
-		return __sme_pa(mm->pgd) | (asid + 1);
-	} else {
-		VM_WARN_ON_ONCE(asid != 0);
-		return __sme_pa(mm->pgd);
-	}
-}
-
-static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
-{
-	VM_WARN_ON_ONCE(asid > 4094);
-	return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
-}
-
-/*
  * This can be used from process context to figure out what the value of
  * CR3 is without needing to do a (slow) __read_cr3().
  *
@@ -317,7 +299,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
  */
 static inline unsigned long __get_current_cr3_fast(void)
 {
-	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
 		this_cpu_read(cpu_tlbstate.loaded_mm_asid));
 
 	/* For now, be very restrictive about when this can be called. */
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index f2ca9b28fd68..ce245b0cdfca 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 #define LAST_PKMAP 1024
 #endif
 
-#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
-		    & PMD_MASK)
+/*
+ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
+ * to avoid include recursion hell
+ */
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
+
+#define CPU_ENTRY_AREA_BASE				\
+	((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK)
+
+#define PKMAP_BASE		\
+	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
+# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 6d5f45dcd4a1..3d27831bc58d 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -76,32 +76,41 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#define MAXMEM			_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+
 #ifdef CONFIG_X86_5LEVEL
-#define VMALLOC_SIZE_TB _AC(16384, UL)
-#define __VMALLOC_BASE	_AC(0xff92000000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffd4000000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(16384, UL)
+# define __VMALLOC_BASE		_AC(0xff92000000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffd4000000000000, UL)
 #else
-#define VMALLOC_SIZE_TB	_AC(32, UL)
-#define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(32, UL)
+# define __VMALLOC_BASE		_AC(0xffffc90000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffffea0000000000, UL)
 #endif
+
 #ifdef CONFIG_RANDOMIZE_MEMORY
-#define VMALLOC_START	vmalloc_base
-#define VMEMMAP_START	vmemmap_base
+# define VMALLOC_START		vmalloc_base
+# define VMEMMAP_START		vmemmap_base
 #else
-#define VMALLOC_START	__VMALLOC_BASE
-#define VMEMMAP_START	__VMEMMAP_BASE
+# define VMALLOC_START		__VMALLOC_BASE
+# define VMEMMAP_START		__VMEMMAP_BASE
 #endif /* CONFIG_RANDOMIZE_MEMORY */
-#define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
-#define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
+
+#define VMALLOC_END		(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+
+#define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 /* The module sections ends with the start of the fixmap */
-#define MODULES_END   __fix_to_virt(__end_of_fixed_addresses + 1)
-#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
-#define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
-#define EFI_VA_START	 ( -4 * (_AC(1, UL) << 30))
-#define EFI_VA_END	 (-68 * (_AC(1, UL) << 30))
+#define MODULES_END		__fix_to_virt(__end_of_fixed_addresses + 1)
+#define MODULES_LEN		(MODULES_END - MODULES_VADDR)
+
+#define ESPFIX_PGD_ENTRY	_AC(-2, UL)
+#define ESPFIX_BASE_ADDR	(ESPFIX_PGD_ENTRY << P4D_SHIFT)
+
+#define CPU_ENTRY_AREA_PGD	_AC(-3, UL)
+#define CPU_ENTRY_AREA_BASE	(CPU_ENTRY_AREA_PGD << P4D_SHIFT)
+
+#define EFI_VA_START		( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END		(-68 * (_AC(1, UL) << 30))
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 1f2434ee9f80..cad8dab266bc 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -337,12 +337,12 @@ struct x86_hw_tss {
 #define IO_BITMAP_OFFSET		(offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
 #define INVALID_IO_BITMAP_OFFSET	0x8000
 
-struct SYSENTER_stack {
+struct entry_stack {
 	unsigned long		words[64];
 };
 
-struct SYSENTER_stack_page {
-	struct SYSENTER_stack stack;
+struct entry_stack_page {
+	struct entry_stack stack;
 } __aligned(PAGE_SIZE);
 
 struct tss_struct {
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f8062bfd43a0..f73706878772 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -16,7 +16,7 @@ enum stack_type {
 	STACK_TYPE_TASK,
 	STACK_TYPE_IRQ,
 	STACK_TYPE_SOFTIRQ,
-	STACK_TYPE_SYSENTER,
+	STACK_TYPE_ENTRY,
 	STACK_TYPE_EXCEPTION,
 	STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
 };
@@ -29,7 +29,7 @@ struct stack_info {
 bool in_task_stack(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info);
 
-bool in_sysenter_stack(unsigned long *stack, struct stack_info *info);
+bool in_entry_stack(unsigned long *stack, struct stack_info *info);
 
 int get_stack_info(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info, unsigned long *visit_mask);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 877b5c1a1b12..e1884cf35257 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -9,70 +9,66 @@
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 #include <asm/smp.h>
+#include <asm/invpcid.h>
 
-static inline void __invpcid(unsigned long pcid, unsigned long addr,
-			     unsigned long type)
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 {
-	struct { u64 d[2]; } desc = { { pcid, addr } };
-
 	/*
-	 * The memory clobber is because the whole point is to invalidate
-	 * stale TLB entries and, especially if we're flushing global
-	 * mappings, we don't want the compiler to reorder any subsequent
-	 * memory accesses before the TLB flush.
-	 *
-	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
-	 * invpcid (%rcx), %rax in long mode.
+	 * Bump the generation count.  This also serves as a full barrier
+	 * that synchronizes with switch_mm(): callers are required to order
+	 * their read of mm_cpumask after their writes to the paging
+	 * structures.
 	 */
-	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
-		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+	return atomic64_inc_return(&mm->context.tlb_gen);
 }
 
-#define INVPCID_TYPE_INDIV_ADDR		0
-#define INVPCID_TYPE_SINGLE_CTXT	1
-#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
-#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+/* There are 12 bits of space for ASIDS in CR3 */
+#define CR3_HW_ASID_BITS		12
+/*
+ * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * user/kernel switches
+ */
+#define PTI_CONSUMED_ASID_BITS		0
 
-/* Flush all mappings for a given pcid and addr, not including globals. */
-static inline void invpcid_flush_one(unsigned long pcid,
-				     unsigned long addr)
-{
-	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
-}
+#define CR3_AVAIL_ASID_BITS (CR3_HW_ASID_BITS - PTI_CONSUMED_ASID_BITS)
+/*
+ * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
+ * for them being zero-based.  Another -1 is because ASID 0 is reserved for
+ * use by non-PCID-aware users.
+ */
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_ASID_BITS) - 2)
 
-/* Flush all mappings for a given PCID, not including globals. */
-static inline void invpcid_flush_single_context(unsigned long pcid)
+static inline u16 kern_pcid(u16 asid)
 {
-	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+	/*
+	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
+	 * PCID bits.  This serves two purposes.  It prevents a nasty
+	 * situation in which PCID-unaware code saves CR3, loads some other
+	 * value (with PCID == 0), and then restores CR3, thus corrupting
+	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
+	 * that any bugs involving loading a PCID-enabled CR3 with
+	 * CR4.PCIDE off will trigger deterministically.
+	 */
+	return asid + 1;
 }
 
-/* Flush all mappings, including globals, for all PCIDs. */
-static inline void invpcid_flush_all(void)
+struct pgd_t;
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+	if (static_cpu_has(X86_FEATURE_PCID)) {
+		return __sme_pa(pgd) | kern_pcid(asid);
+	} else {
+		VM_WARN_ON_ONCE(asid != 0);
+		return __sme_pa(pgd);
+	}
 }
 
-/* Flush all mappings for all PCIDs except globals. */
-static inline void invpcid_flush_all_nonglobals(void)
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
-}
-
-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
-{
-	u64 new_tlb_gen;
-
-	/*
-	 * Bump the generation count.  This also serves as a full barrier
-	 * that synchronizes with switch_mm(): callers are required to order
-	 * their read of mm_cpumask after their writes to the paging
-	 * structures.
-	 */
-	smp_mb__before_atomic();
-	new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen);
-	smp_mb__after_atomic();
-
-	return new_tlb_gen;
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+	VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID));
+	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
 }
 
 #ifdef CONFIG_PARAVIRT
@@ -237,6 +233,9 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 extern void initialize_tlbstate_and_flush(void);
 
+/*
+ * flush the entire current user mapping
+ */
 static inline void __native_flush_tlb(void)
 {
 	/*
@@ -249,20 +248,12 @@ static inline void __native_flush_tlb(void)
 	preempt_enable();
 }
 
-static inline void __native_flush_tlb_global_irq_disabled(void)
-{
-	unsigned long cr4;
-
-	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	/* clear PGE */
-	native_write_cr4(cr4 & ~X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
-}
-
+/*
+ * flush everything
+ */
 static inline void __native_flush_tlb_global(void)
 {
-	unsigned long flags;
+	unsigned long cr4, flags;
 
 	if (static_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
@@ -280,22 +271,36 @@ static inline void __native_flush_tlb_global(void)
 	 */
 	raw_local_irq_save(flags);
 
-	__native_flush_tlb_global_irq_disabled();
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	/* toggle PGE */
+	native_write_cr4(cr4 ^ X86_CR4_PGE);
+	/* write old PGE again and flush TLBs */
+	native_write_cr4(cr4);
 
 	raw_local_irq_restore(flags);
 }
 
+/*
+ * flush one page in the user mapping
+ */
 static inline void __native_flush_tlb_single(unsigned long addr)
 {
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
 }
 
+/*
+ * flush everything
+ */
 static inline void __flush_tlb_all(void)
 {
-	if (boot_cpu_has(X86_FEATURE_PGE))
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		__flush_tlb_global();
-	else
+	} else {
+		/*
+		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
+		 */
 		__flush_tlb();
+	}
 
 	/*
 	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
@@ -306,6 +311,9 @@ static inline void __flush_tlb_all(void)
 	 */
 }
 
+/*
+ * flush one page in the kernel mapping
+ */
 static inline void __flush_tlb_one(unsigned long addr)
 {
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index cd360a5e0dca..676b7cf4b62b 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -97,6 +97,6 @@ void common(void) {
 	/* Layout info for cpu_entry_area */
 	OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
 	OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
-	OFFSET(CPU_ENTRY_AREA_SYSENTER_stack, cpu_entry_area, SYSENTER_stack_page);
-	DEFINE(SIZEOF_SYSENTER_stack, sizeof(struct SYSENTER_stack));
+	OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
+	DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
 }
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 7d20d9c0b3d6..fa1261eefa16 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -48,7 +48,7 @@ void foo(void)
 
 	/* Offset from the sysenter stack to tss.sp0 */
 	DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
-	       offsetofend(struct cpu_entry_area, SYSENTER_stack_page.stack));
+	       offsetofend(struct cpu_entry_area, entry_stack_page.stack));
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	BLANK();
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7416da3ec4df..c9757f07d738 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -506,102 +506,8 @@ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
 	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
 	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
 };
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-#endif
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(struct SYSENTER_stack_page,
-				   SYSENTER_stack_storage);
-
-static void __init
-set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot)
-{
-	for ( ; pages; pages--, idx--, ptr += PAGE_SIZE)
-		__set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot);
-}
-
-/* Setup the fixmap mappings only once per-processor */
-static void __init setup_cpu_entry_area(int cpu)
-{
-#ifdef CONFIG_X86_64
-	extern char _entry_trampoline[];
-
-	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
-	pgprot_t gdt_prot = PAGE_KERNEL_RO;
-	pgprot_t tss_prot = PAGE_KERNEL_RO;
-#else
-	/*
-	 * On native 32-bit systems, the GDT cannot be read-only because
-	 * our double fault handler uses a task gate, and entering through
-	 * a task gate needs to change an available TSS to busy.  If the
-	 * GDT is read-only, that will triple fault.  The TSS cannot be
-	 * read-only because the CPU writes to it on task switches.
-	 *
-	 * On Xen PV, the GDT must be read-only because the hypervisor
-	 * requires it.
-	 */
-	pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ?
-		PAGE_KERNEL_RO : PAGE_KERNEL;
-	pgprot_t tss_prot = PAGE_KERNEL;
-#endif
-
-	__set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot);
-	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, SYSENTER_stack_page),
-				per_cpu_ptr(&SYSENTER_stack_storage, cpu), 1,
-				PAGE_KERNEL);
-
-	/*
-	 * The Intel SDM says (Volume 3, 7.2.1):
-	 *
-	 *  Avoid placing a page boundary in the part of the TSS that the
-	 *  processor reads during a task switch (the first 104 bytes). The
-	 *  processor may not correctly perform address translations if a
-	 *  boundary occurs in this area. During a task switch, the processor
-	 *  reads and writes into the first 104 bytes of each TSS (using
-	 *  contiguous physical addresses beginning with the physical address
-	 *  of the first byte of the TSS). So, after TSS access begins, if
-	 *  part of the 104 bytes is not physically contiguous, the processor
-	 *  will access incorrect information without generating a page-fault
-	 *  exception.
-	 *
-	 * There are also a lot of errata involving the TSS spanning a page
-	 * boundary.  Assert that we're not doing that.
-	 */
-	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
-		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
-	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
-	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, tss),
-				&per_cpu(cpu_tss_rw, cpu),
-				sizeof(struct tss_struct) / PAGE_SIZE,
-				tss_prot);
-
-#ifdef CONFIG_X86_32
-	per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
 #endif
 
-#ifdef CONFIG_X86_64
-	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
-	BUILD_BUG_ON(sizeof(exception_stacks) !=
-		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
-	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks),
-				&per_cpu(exception_stacks, cpu),
-				sizeof(exception_stacks) / PAGE_SIZE,
-				PAGE_KERNEL);
-
-	__set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline),
-		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
-#endif
-}
-
-void __init setup_cpu_entry_areas(void)
-{
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu)
-		setup_cpu_entry_area(cpu);
-}
-
 /* Load the original GDT from the per-cpu structure */
 void load_direct_gdt(int cpu)
 {
@@ -1348,7 +1254,7 @@ void enable_sep_cpu(void)
 
 	tss->x86_tss.ss1 = __KERNEL_CS;
 	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
-	wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1), 0);
+	wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
 	put_cpu();
@@ -1465,7 +1371,7 @@ void syscall_init(void)
 	 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1));
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
@@ -1680,7 +1586,7 @@ void cpu_init(void)
 	 */
 	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
-	load_sp0((unsigned long)(cpu_SYSENTER_stack(cpu) + 1));
+	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);
 
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 7dbcb7adf797..8ccdca6d3f9e 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -565,15 +565,6 @@ static void print_ucode(struct ucode_cpu_info *uci)
 }
 #else
 
-/*
- * Flush global tlb. We only do this in x86_64 where paging has been enabled
- * already and PGE should be enabled as well.
- */
-static inline void flush_tlb_early(void)
-{
-	__native_flush_tlb_global_irq_disabled();
-}
-
 static inline void print_ucode(struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *mc;
@@ -602,10 +593,6 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (rev != mc->hdr.rev)
 		return -1;
 
-#ifdef CONFIG_X86_64
-	/* Flush global tlb. This is precaution. */
-	flush_tlb_early();
-#endif
 	uci->cpu_sig.rev = rev;
 
 	if (early)
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index bbd6d986e2d0..36b17e0febe8 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -18,6 +18,7 @@
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
@@ -43,9 +44,9 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
 	return true;
 }
 
-bool in_sysenter_stack(unsigned long *stack, struct stack_info *info)
+bool in_entry_stack(unsigned long *stack, struct stack_info *info)
 {
-	struct SYSENTER_stack *ss = cpu_SYSENTER_stack(smp_processor_id());
+	struct entry_stack *ss = cpu_entry_stack(smp_processor_id());
 
 	void *begin = ss;
 	void *end = ss + 1;
@@ -53,7 +54,7 @@ bool in_sysenter_stack(unsigned long *stack, struct stack_info *info)
 	if ((void *)stack < begin || (void *)stack >= end)
 		return false;
 
-	info->type	= STACK_TYPE_SYSENTER;
+	info->type	= STACK_TYPE_ENTRY;
 	info->begin	= begin;
 	info->end	= end;
 	info->next_sp	= NULL;
@@ -111,13 +112,13 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - task stack
 	 * - interrupt stack
 	 * - HW exception stacks (double fault, nmi, debug, mce)
-	 * - SYSENTER stack
+	 * - entry stack
 	 *
 	 * x86-32 can have up to four stacks:
 	 * - task stack
 	 * - softirq stack
 	 * - hardirq stack
-	 * - SYSENTER stack
+	 * - entry stack
 	 */
 	for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
 		const char *stack_name;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 5ff13a6b3680..04170f63e3a1 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -26,8 +26,8 @@ const char *stack_type_name(enum stack_type type)
 	if (type == STACK_TYPE_SOFTIRQ)
 		return "SOFTIRQ";
 
-	if (type == STACK_TYPE_SYSENTER)
-		return "SYSENTER";
+	if (type == STACK_TYPE_ENTRY)
+		return "ENTRY_TRAMPOLINE";
 
 	return NULL;
 }
@@ -96,7 +96,7 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	if (task != current)
 		goto unknown;
 
-	if (in_sysenter_stack(stack, info))
+	if (in_entry_stack(stack, info))
 		goto recursion_check;
 
 	if (in_hardirq_stack(stack, info))
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index abc828f8c297..563e28d14f2c 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -37,8 +37,14 @@ const char *stack_type_name(enum stack_type type)
 	if (type == STACK_TYPE_IRQ)
 		return "IRQ";
 
-	if (type == STACK_TYPE_SYSENTER)
-		return "SYSENTER";
+	if (type == STACK_TYPE_ENTRY) {
+		/*
+		 * On 64-bit, we have a generic entry stack that we
+		 * use for all the kernel entry points, including
+		 * SYSENTER.
+		 */
+		return "ENTRY_TRAMPOLINE";
+	}
 
 	if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST)
 		return exception_stack_names[type - STACK_TYPE_EXCEPTION];
@@ -118,7 +124,7 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	if (in_irq_stack(stack, info))
 		goto recursion_check;
 
-	if (in_sysenter_stack(stack, info))
+	if (in_entry_stack(stack, info))
 		goto recursion_check;
 
 	goto unknown;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 1c1eae961340..a6b5d62f45a7 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -5,6 +5,11 @@
  * Copyright (C) 2002 Andi Kleen
  *
  * This handles calls from both 32bit and 64bit mode.
+ *
+ * Lock order:
+ *	contex.ldt_usr_sem
+ *	  mmap_sem
+ *	    context.lock
  */
 
 #include <linux/errno.h>
@@ -42,7 +47,7 @@ static void refresh_ldt_segments(void)
 #endif
 }
 
-/* context.lock is held for us, so we don't need any locking. */
+/* context.lock is held by the task which issued the smp function call */
 static void flush_ldt(void *__mm)
 {
 	struct mm_struct *mm = __mm;
@@ -99,15 +104,17 @@ static void finalize_ldt_struct(struct ldt_struct *ldt)
 	paravirt_alloc_ldt(ldt->entries, ldt->nr_entries);
 }
 
-/* context.lock is held */
-static void install_ldt(struct mm_struct *current_mm,
-			struct ldt_struct *ldt)
+static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt)
 {
+	mutex_lock(&mm->context.lock);
+
 	/* Synchronizes with READ_ONCE in load_mm_ldt. */
-	smp_store_release(&current_mm->context.ldt, ldt);
+	smp_store_release(&mm->context.ldt, ldt);
 
-	/* Activate the LDT for all CPUs using current_mm. */
-	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+	/* Activate the LDT for all CPUs using currents mm. */
+	on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true);
+
+	mutex_unlock(&mm->context.lock);
 }
 
 static void free_ldt_struct(struct ldt_struct *ldt)
@@ -124,27 +131,20 @@ static void free_ldt_struct(struct ldt_struct *ldt)
 }
 
 /*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
+ * Called on fork from arch_dup_mmap(). Just copy the current LDT state,
+ * the new task is not running, so nothing can be installed.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
+int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
 {
 	struct ldt_struct *new_ldt;
-	struct mm_struct *old_mm;
 	int retval = 0;
 
-	mutex_init(&mm->context.lock);
-	old_mm = current->mm;
-	if (!old_mm) {
-		mm->context.ldt = NULL;
+	if (!old_mm)
 		return 0;
-	}
 
 	mutex_lock(&old_mm->context.lock);
-	if (!old_mm->context.ldt) {
-		mm->context.ldt = NULL;
+	if (!old_mm->context.ldt)
 		goto out_unlock;
-	}
 
 	new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries);
 	if (!new_ldt) {
@@ -180,7 +180,7 @@ static int read_ldt(void __user *ptr, unsigned long bytecount)
 	unsigned long entries_size;
 	int retval;
 
-	mutex_lock(&mm->context.lock);
+	down_read(&mm->context.ldt_usr_sem);
 
 	if (!mm->context.ldt) {
 		retval = 0;
@@ -209,7 +209,7 @@ static int read_ldt(void __user *ptr, unsigned long bytecount)
 	retval = bytecount;
 
 out_unlock:
-	mutex_unlock(&mm->context.lock);
+	up_read(&mm->context.ldt_usr_sem);
 	return retval;
 }
 
@@ -269,7 +269,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 			ldt.avl = 0;
 	}
 
-	mutex_lock(&mm->context.lock);
+	if (down_write_killable(&mm->context.ldt_usr_sem))
+		return -EINTR;
 
 	old_ldt       = mm->context.ldt;
 	old_nr_entries = old_ldt ? old_ldt->nr_entries : 0;
@@ -291,7 +292,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	error = 0;
 
 out_unlock:
-	mutex_unlock(&mm->context.lock);
+	up_write(&mm->context.ldt_usr_sem);
 out:
 	return error;
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 35cb20994e32..c5970efa8557 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -932,12 +932,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	initial_code = (unsigned long)start_secondary;
 	initial_stack  = idle->thread.sp;
 
-	/*
-	 * Enable the espfix hack for this CPU
-	*/
-#ifdef CONFIG_X86_ESPFIX64
+	/* Enable the espfix hack for this CPU */
 	init_espfix_ap(cpu);
-#endif
 
 	/* So we see what's up */
 	announce_cpu(cpu, apicid);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e98f8b66a460..f69dbd47d733 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -51,6 +51,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
+#include <asm/cpu_entry_area.h>
 #include <asm/mce.h>
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
@@ -951,8 +952,9 @@ void __init trap_init(void)
 	 * "sidt" instruction will not leak the location of the kernel, and
 	 * to defend the IDT against arbitrary memory write vulnerabilities.
 	 * It will be reloaded in cpu_init() */
-	__set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
-	idt_descr.address = fix_to_virt(FIX_RO_IDT);
+	cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table),
+		    PAGE_KERNEL_RO);
+	idt_descr.address = CPU_ENTRY_AREA_RO_IDT;
 
 	/*
 	 * Should be a barrier for any external CPU state:
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 8e13b8cc6bed..52195ee3f6d5 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -10,7 +10,7 @@ CFLAGS_REMOVE_mem_encrypt.o	= -pg
 endif
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o
+	    pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
new file mode 100644
index 000000000000..fe814fd5e014
--- /dev/null
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+
+#include <asm/cpu_entry_area.h>
+#include <asm/pgtable.h>
+#include <asm/fixmap.h>
+#include <asm/desc.h>
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
+
+#ifdef CONFIG_X86_64
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+#endif
+
+struct cpu_entry_area *get_cpu_entry_area(int cpu)
+{
+	unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE;
+	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
+
+	return (struct cpu_entry_area *) va;
+}
+EXPORT_SYMBOL(get_cpu_entry_area);
+
+void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags)
+{
+	unsigned long va = (unsigned long) cea_vaddr;
+
+	set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags));
+}
+
+static void __init
+cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
+{
+	for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE)
+		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
+}
+
+/* Setup the fixmap mappings only once per-processor */
+static void __init setup_cpu_entry_area(int cpu)
+{
+#ifdef CONFIG_X86_64
+	extern char _entry_trampoline[];
+
+	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
+	pgprot_t gdt_prot = PAGE_KERNEL_RO;
+	pgprot_t tss_prot = PAGE_KERNEL_RO;
+#else
+	/*
+	 * On native 32-bit systems, the GDT cannot be read-only because
+	 * our double fault handler uses a task gate, and entering through
+	 * a task gate needs to change an available TSS to busy.  If the
+	 * GDT is read-only, that will triple fault.  The TSS cannot be
+	 * read-only because the CPU writes to it on task switches.
+	 *
+	 * On Xen PV, the GDT must be read-only because the hypervisor
+	 * requires it.
+	 */
+	pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ?
+		PAGE_KERNEL_RO : PAGE_KERNEL;
+	pgprot_t tss_prot = PAGE_KERNEL;
+#endif
+
+	cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu),
+		    gdt_prot);
+
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page,
+			     per_cpu_ptr(&entry_stack_storage, cpu), 1,
+			     PAGE_KERNEL);
+
+	/*
+	 * The Intel SDM says (Volume 3, 7.2.1):
+	 *
+	 *  Avoid placing a page boundary in the part of the TSS that the
+	 *  processor reads during a task switch (the first 104 bytes). The
+	 *  processor may not correctly perform address translations if a
+	 *  boundary occurs in this area. During a task switch, the processor
+	 *  reads and writes into the first 104 bytes of each TSS (using
+	 *  contiguous physical addresses beginning with the physical address
+	 *  of the first byte of the TSS). So, after TSS access begins, if
+	 *  part of the 104 bytes is not physically contiguous, the processor
+	 *  will access incorrect information without generating a page-fault
+	 *  exception.
+	 *
+	 * There are also a lot of errata involving the TSS spanning a page
+	 * boundary.  Assert that we're not doing that.
+	 */
+	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
+		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
+	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss,
+			     &per_cpu(cpu_tss_rw, cpu),
+			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
+
+#ifdef CONFIG_X86_32
+	per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
+#endif
+
+#ifdef CONFIG_X86_64
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+	BUILD_BUG_ON(sizeof(exception_stacks) !=
+		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
+	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks,
+			     &per_cpu(exception_stacks, cpu),
+			     sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL);
+
+	cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
+		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
+#endif
+}
+
+static __init void setup_cpu_entry_area_ptes(void)
+{
+#ifdef CONFIG_X86_32
+	unsigned long start, end;
+
+	BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE);
+	BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
+
+	start = CPU_ENTRY_AREA_BASE;
+	end = start + CPU_ENTRY_AREA_MAP_SIZE;
+
+	/* Careful here: start + PMD_SIZE might wrap around */
+	for (; start < end && start >= CPU_ENTRY_AREA_BASE; start += PMD_SIZE)
+		populate_extra_pte(start);
+#endif
+}
+
+void __init setup_cpu_entry_areas(void)
+{
+	unsigned int cpu;
+
+	setup_cpu_entry_area_ptes();
+
+	for_each_possible_cpu(cpu)
+		setup_cpu_entry_area(cpu);
+}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 5e3ac6fe6c9e..43dedbfb7257 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -44,10 +44,12 @@ struct addr_marker {
 	unsigned long max_lines;
 };
 
-/* indices for address_markers; keep sync'd w/ address_markers below */
+/* Address space markers hints */
+
+#ifdef CONFIG_X86_64
+
 enum address_markers_idx {
 	USER_SPACE_NR = 0,
-#ifdef CONFIG_X86_64
 	KERNEL_SPACE_NR,
 	LOW_KERNEL_NR,
 	VMALLOC_START_NR,
@@ -56,56 +58,74 @@ enum address_markers_idx {
 	KASAN_SHADOW_START_NR,
 	KASAN_SHADOW_END_NR,
 #endif
-# ifdef CONFIG_X86_ESPFIX64
+	CPU_ENTRY_AREA_NR,
+#ifdef CONFIG_X86_ESPFIX64
 	ESPFIX_START_NR,
-# endif
+#endif
+#ifdef CONFIG_EFI
+	EFI_END_NR,
+#endif
 	HIGH_KERNEL_NR,
 	MODULES_VADDR_NR,
 	MODULES_END_NR,
-#else
+	FIXADDR_START_NR,
+	END_OF_SPACE_NR,
+};
+
+static struct addr_marker address_markers[] = {
+	[USER_SPACE_NR]		= { 0,			"User Space" },
+	[KERNEL_SPACE_NR]	= { (1UL << 63),	"Kernel Space" },
+	[LOW_KERNEL_NR]		= { 0UL,		"Low Kernel Mapping" },
+	[VMALLOC_START_NR]	= { 0UL,		"vmalloc() Area" },
+	[VMEMMAP_START_NR]	= { 0UL,		"Vmemmap" },
+#ifdef CONFIG_KASAN
+	[KASAN_SHADOW_START_NR]	= { KASAN_SHADOW_START,	"KASAN shadow" },
+	[KASAN_SHADOW_END_NR]	= { KASAN_SHADOW_END,	"KASAN shadow end" },
+#endif
+	[CPU_ENTRY_AREA_NR]	= { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
+#ifdef CONFIG_X86_ESPFIX64
+	[ESPFIX_START_NR]	= { ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
+#endif
+#ifdef CONFIG_EFI
+	[EFI_END_NR]		= { EFI_VA_END,		"EFI Runtime Services" },
+#endif
+	[HIGH_KERNEL_NR]	= { __START_KERNEL_map,	"High Kernel Mapping" },
+	[MODULES_VADDR_NR]	= { MODULES_VADDR,	"Modules" },
+	[MODULES_END_NR]	= { MODULES_END,	"End Modules" },
+	[FIXADDR_START_NR]	= { FIXADDR_START,	"Fixmap Area" },
+	[END_OF_SPACE_NR]	= { -1,			NULL }
+};
+
+#else /* CONFIG_X86_64 */
+
+enum address_markers_idx {
+	USER_SPACE_NR = 0,
 	KERNEL_SPACE_NR,
 	VMALLOC_START_NR,
 	VMALLOC_END_NR,
-# ifdef CONFIG_HIGHMEM
+#ifdef CONFIG_HIGHMEM
 	PKMAP_BASE_NR,
-# endif
-	FIXADDR_START_NR,
 #endif
+	CPU_ENTRY_AREA_NR,
+	FIXADDR_START_NR,
+	END_OF_SPACE_NR,
 };
 
-/* Address space markers hints */
 static struct addr_marker address_markers[] = {
-	{ 0, "User Space" },
-#ifdef CONFIG_X86_64
-	{ 0x8000000000000000UL, "Kernel Space" },
-	{ 0/* PAGE_OFFSET */,   "Low Kernel Mapping" },
-	{ 0/* VMALLOC_START */, "vmalloc() Area" },
-	{ 0/* VMEMMAP_START */, "Vmemmap" },
-#ifdef CONFIG_KASAN
-	{ KASAN_SHADOW_START,	"KASAN shadow" },
-	{ KASAN_SHADOW_END,	"KASAN shadow end" },
+	[USER_SPACE_NR]		= { 0,			"User Space" },
+	[KERNEL_SPACE_NR]	= { PAGE_OFFSET,	"Kernel Mapping" },
+	[VMALLOC_START_NR]	= { 0UL,		"vmalloc() Area" },
+	[VMALLOC_END_NR]	= { 0UL,		"vmalloc() End" },
+#ifdef CONFIG_HIGHMEM
+	[PKMAP_BASE_NR]		= { 0UL,		"Persistent kmap() Area" },
 #endif
-# ifdef CONFIG_X86_ESPFIX64
-	{ ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
-# endif
-# ifdef CONFIG_EFI
-	{ EFI_VA_END,		"EFI Runtime Services" },
-# endif
-	{ __START_KERNEL_map,   "High Kernel Mapping" },
-	{ MODULES_VADDR,        "Modules" },
-	{ MODULES_END,          "End Modules" },
-#else
-	{ PAGE_OFFSET,          "Kernel Mapping" },
-	{ 0/* VMALLOC_START */, "vmalloc() Area" },
-	{ 0/*VMALLOC_END*/,     "vmalloc() End" },
-# ifdef CONFIG_HIGHMEM
-	{ 0/*PKMAP_BASE*/,      "Persistent kmap() Area" },
-# endif
-	{ 0/*FIXADDR_START*/,   "Fixmap Area" },
-#endif
-	{ -1, NULL }		/* End of list */
+	[CPU_ENTRY_AREA_NR]	= { 0UL,		"CPU entry area" },
+	[FIXADDR_START_NR]	= { 0UL,		"Fixmap area" },
+	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
 
+#endif /* !CONFIG_X86_64 */
+
 /* Multipliers for offsets within the PTEs */
 #define PTE_LEVEL_MULT (PAGE_SIZE)
 #define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT)
@@ -140,7 +160,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 	static const char * const level_name[] =
 		{ "cr3", "pgd", "p4d", "pud", "pmd", "pte" };
 
-	if (!pgprot_val(prot)) {
+	if (!(pr & _PAGE_PRESENT)) {
 		/* Not present */
 		pt_dump_cont_printf(m, dmsg, "                              ");
 	} else {
@@ -525,8 +545,8 @@ static int __init pt_dump_init(void)
 	address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE;
 # endif
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
+	address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
 #endif
-
 	return 0;
 }
 __initcall(pt_dump_init);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8a64a6f2848d..135c9a7898c7 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -50,6 +50,7 @@
 #include <asm/setup.h>
 #include <asm/set_memory.h>
 #include <asm/page_types.h>
+#include <asm/cpu_entry_area.h>
 #include <asm/init.h>
 
 #include "mm_internal.h"
@@ -766,6 +767,7 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 	printk(KERN_INFO "virtual kernel memory layout:\n"
 		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+		"  cpu_entry : 0x%08lx - 0x%08lx   (%4ld kB)\n"
 #ifdef CONFIG_HIGHMEM
 		"    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\n"
 #endif
@@ -777,6 +779,10 @@ void __init mem_init(void)
 		FIXADDR_START, FIXADDR_TOP,
 		(FIXADDR_TOP - FIXADDR_START) >> 10,
 
+		CPU_ENTRY_AREA_BASE,
+		CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE,
+		CPU_ENTRY_AREA_MAP_SIZE >> 10,
+
 #ifdef CONFIG_HIGHMEM
 		PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
 		(LAST_PKMAP*PAGE_SIZE) >> 10,
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 9ec70d780f1f..47388f0c0e59 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -15,6 +15,7 @@
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
+#include <asm/cpu_entry_area.h>
 
 extern struct range pfn_mapped[E820_MAX_ENTRIES];
 
@@ -322,31 +323,33 @@ void __init kasan_init(void)
 		map_range(&pfn_mapped[i]);
 	}
 
-	kasan_populate_zero_shadow(
-		kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
-		kasan_mem_to_shadow((void *)__START_KERNEL_map));
-
-	kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext),
-			      (unsigned long)kasan_mem_to_shadow(_end),
-			      early_pfn_to_nid(__pa(_stext)));
-
-	shadow_cpu_entry_begin = (void *)__fix_to_virt(FIX_CPU_ENTRY_AREA_BOTTOM);
+	shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE;
 	shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin);
 	shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin,
 						PAGE_SIZE);
 
-	shadow_cpu_entry_end = (void *)(__fix_to_virt(FIX_CPU_ENTRY_AREA_TOP) + PAGE_SIZE);
+	shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE +
+					CPU_ENTRY_AREA_MAP_SIZE);
 	shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end);
 	shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end,
 					PAGE_SIZE);
 
-	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
-				   shadow_cpu_entry_begin);
+	kasan_populate_zero_shadow(
+		kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
+		shadow_cpu_entry_begin);
 
 	kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
 			      (unsigned long)shadow_cpu_entry_end, 0);
 
-	kasan_populate_zero_shadow(shadow_cpu_entry_end, (void *)KASAN_SHADOW_END);
+	kasan_populate_zero_shadow(shadow_cpu_entry_end,
+				kasan_mem_to_shadow((void *)__START_KERNEL_map));
+
+	kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext),
+			      (unsigned long)kasan_mem_to_shadow(_end),
+			      early_pfn_to_nid(__pa(_stext)));
+
+	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
+				(void *)KASAN_SHADOW_END);
 
 	load_cr3(init_top_pgt);
 	__flush_tlb_all();
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 6b9bf023a700..c3c5274410a9 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -10,6 +10,7 @@
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 3118392cdf75..0a1be3adc97e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -128,7 +128,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	 * isn't free.
 	 */
 #ifdef CONFIG_DEBUG_VM
-	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) {
+	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) {
 		/*
 		 * If we were to BUG here, we'd be very likely to kill
 		 * the system so hard that we don't see the call trace.
@@ -195,7 +195,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		if (need_flush) {
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-			write_cr3(build_cr3(next, new_asid));
+			write_cr3(build_cr3(next->pgd, new_asid));
 
 			/*
 			 * NB: This gets called via leave_mm() in the idle path
@@ -208,7 +208,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 		} else {
 			/* The new ASID is already up to date. */
-			write_cr3(build_cr3_noflush(next, new_asid));
+			write_cr3(build_cr3_noflush(next->pgd, new_asid));
 
 			/* See above wrt _rcuidle. */
 			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
@@ -288,7 +288,7 @@ void initialize_tlbstate_and_flush(void)
 		!(cr4_read_shadow() & X86_CR4_PCIDE));
 
 	/* Force ASID 0 and force a TLB flush. */
-	write_cr3(build_cr3(mm, 0));
+	write_cr3(build_cr3(mm->pgd, 0));
 
 	/* Reinitialize tlbstate. */
 	this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
@@ -551,7 +551,7 @@ static void do_kernel_range_flush(void *info)
 
 	/* flush range by one by one 'invlpg' */
 	for (addr = f->start; addr < f->end; addr += PAGE_SIZE)
-		__flush_tlb_single(addr);
+		__flush_tlb_one(addr);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index f44c0bc95aa2..8538a6723171 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp,
 		local_flush_tlb();
 		stat->d_alltlb++;
 	} else {
-		__flush_tlb_one(msg->address);
+		__flush_tlb_single(msg->address);
 		stat->d_onetlb++;
 	}
 	stat->d_requestee++;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d669e9d89001..c9081c6671f0 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1,8 +1,12 @@
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+#include <linux/bootmem.h>
+#endif
 #include <linux/cpu.h>
 #include <linux/kexec.h>
 
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/interface/memory.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -331,3 +335,80 @@ void xen_arch_unregister_cpu(int num)
 }
 EXPORT_SYMBOL(xen_arch_unregister_cpu);
 #endif
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+void __init arch_xen_balloon_init(struct resource *hostmem_resource)
+{
+	struct xen_memory_map memmap;
+	int rc;
+	unsigned int i, last_guest_ram;
+	phys_addr_t max_addr = PFN_PHYS(max_pfn);
+	struct e820_table *xen_e820_table;
+	const struct e820_entry *entry;
+	struct resource *res;
+
+	if (!xen_initial_domain())
+		return;
+
+	xen_e820_table = kmalloc(sizeof(*xen_e820_table), GFP_KERNEL);
+	if (!xen_e820_table)
+		return;
+
+	memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries);
+	set_xen_guest_handle(memmap.buffer, xen_e820_table->entries);
+	rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap);
+	if (rc) {
+		pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc);
+		goto out;
+	}
+
+	last_guest_ram = 0;
+	for (i = 0; i < memmap.nr_entries; i++) {
+		if (xen_e820_table->entries[i].addr >= max_addr)
+			break;
+		if (xen_e820_table->entries[i].type == E820_TYPE_RAM)
+			last_guest_ram = i;
+	}
+
+	entry = &xen_e820_table->entries[last_guest_ram];
+	if (max_addr >= entry->addr + entry->size)
+		goto out; /* No unallocated host RAM. */
+
+	hostmem_resource->start = max_addr;
+	hostmem_resource->end = entry->addr + entry->size;
+
+	/*
+	 * Mark non-RAM regions between the end of dom0 RAM and end of host RAM
+	 * as unavailable. The rest of that region can be used for hotplug-based
+	 * ballooning.
+	 */
+	for (; i < memmap.nr_entries; i++) {
+		entry = &xen_e820_table->entries[i];
+
+		if (entry->type == E820_TYPE_RAM)
+			continue;
+
+		if (entry->addr >= hostmem_resource->end)
+			break;
+
+		res = kzalloc(sizeof(*res), GFP_KERNEL);
+		if (!res)
+			goto out;
+
+		res->name = "Unavailable host RAM";
+		res->start = entry->addr;
+		res->end = (entry->addr + entry->size < hostmem_resource->end) ?
+			    entry->addr + entry->size : hostmem_resource->end;
+		rc = insert_resource(hostmem_resource, res);
+		if (rc) {
+			pr_warn("%s: Can't insert [%llx - %llx) (%d)\n",
+				__func__, res->start, res->end, rc);
+			kfree(res);
+			goto  out;
+		}
+	}
+
+ out:
+	kfree(xen_e820_table);
+}
+#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 7beeee1443b3..c047f42552e1 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -88,6 +88,8 @@
 #include "multicalls.h"
 #include "pmu.h"
 
+#include "../kernel/cpu/cpu.h" /* get_cpu_cap() */
+
 void *xen_initial_gdt;
 
 static int xen_cpu_up_prepare_pv(unsigned int cpu);
@@ -1258,6 +1260,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
 
 	/* Work out if we support NX */
+	get_cpu_cap(&boot_cpu_data);
 	x86_configure_nx();
 
 	/* Get mfn list */
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 6cf801ca1142..4d62c071b166 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1902,6 +1902,18 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
+	/*
+	 * Zap execute permission from the ident map. Due to the sharing of
+	 * L1 entries we need to do this in the L2.
+	 */
+	if (__supported_pte_mask & _PAGE_NX) {
+		for (i = 0; i < PTRS_PER_PMD; ++i) {
+			if (pmd_none(level2_ident_pgt[i]))
+				continue;
+			level2_ident_pgt[i] = pmd_set_flags(level2_ident_pgt[i], _PAGE_NX);
+		}
+	}
+
 	/* Copy the initial P->M table mappings if necessary. */
 	i = pgd_index(xen_start_info->mfn_list);
 	if (i && i < pgd_index(__START_KERNEL_map))
@@ -2261,7 +2273,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 	switch (idx) {
 	case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
-	case FIX_RO_IDT:
 #ifdef CONFIG_X86_32
 	case FIX_WP_TEST:
 # ifdef CONFIG_HIGHMEM
@@ -2272,7 +2283,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
-	case FIX_CPU_ENTRY_AREA_TOP ... FIX_CPU_ENTRY_AREA_BOTTOM:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index c114ca767b3b..6e0d2086eacb 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -808,7 +808,6 @@ char * __init xen_memory_setup(void)
 	addr = xen_e820_table.entries[0].addr;
 	size = xen_e820_table.entries[0].size;
 	while (i < xen_e820_table.nr_entries) {
-		bool discard = false;
 
 		chunk_size = size;
 		type = xen_e820_table.entries[i].type;
@@ -824,11 +823,10 @@ char * __init xen_memory_setup(void)
 				xen_add_extra_mem(pfn_s, n_pfns);
 				xen_max_p2m_pfn = pfn_s + n_pfns;
 			} else
-				discard = true;
+				type = E820_TYPE_UNUSABLE;
 		}
 
-		if (!discard)
-			xen_align_and_add_e820_region(addr, chunk_size, type);
+		xen_align_and_add_e820_region(addr, chunk_size, type);
 
 		addr += chunk_size;
 		size -= chunk_size;
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 415a54ced4d6..444a387df219 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1138,12 +1138,6 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
 		if (!af_alg_readable(sk))
 			break;
 
-		if (!ctx->used) {
-			err = af_alg_wait_for_data(sk, flags);
-			if (err)
-				return err;
-		}
-
 		seglen = min_t(size_t, (maxsize - len),
 			       msg_data_left(msg));
 
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 48b34e9c6834..ddcc45f77edd 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -111,6 +111,12 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 	size_t usedpages = 0;		/* [in]  RX bufs to be used from user */
 	size_t processed = 0;		/* [in]  TX bufs to be consumed */
 
+	if (!ctx->used) {
+		err = af_alg_wait_for_data(sk, flags);
+		if (err)
+			return err;
+	}
+
 	/*
 	 * Data length provided by caller via sendmsg/sendpage that has not
 	 * yet been processed.
@@ -285,6 +291,10 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 		/* AIO operation */
 		sock_hold(sk);
 		areq->iocb = msg->msg_iocb;
+
+		/* Remember output size that will be generated. */
+		areq->outlen = outlen;
+
 		aead_request_set_callback(&areq->cra_u.aead_req,
 					  CRYPTO_TFM_REQ_MAY_BACKLOG,
 					  af_alg_async_cb, areq);
@@ -292,12 +302,8 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 				 crypto_aead_decrypt(&areq->cra_u.aead_req);
 
 		/* AIO operation in progress */
-		if (err == -EINPROGRESS || err == -EBUSY) {
-			/* Remember output size that will be generated. */
-			areq->outlen = outlen;
-
+		if (err == -EINPROGRESS || err == -EBUSY)
 			return -EIOCBQUEUED;
-		}
 
 		sock_put(sk);
 	} else {
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 30cff827dd8f..baef9bfccdda 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -72,6 +72,12 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	int err = 0;
 	size_t len = 0;
 
+	if (!ctx->used) {
+		err = af_alg_wait_for_data(sk, flags);
+		if (err)
+			return err;
+	}
+
 	/* Allocate cipher request for current operation. */
 	areq = af_alg_alloc_areq(sk, sizeof(struct af_alg_async_req) +
 				     crypto_skcipher_reqsize(tfm));
@@ -119,6 +125,10 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 		/* AIO operation */
 		sock_hold(sk);
 		areq->iocb = msg->msg_iocb;
+
+		/* Remember output size that will be generated. */
+		areq->outlen = len;
+
 		skcipher_request_set_callback(&areq->cra_u.skcipher_req,
 					      CRYPTO_TFM_REQ_MAY_SLEEP,
 					      af_alg_async_cb, areq);
@@ -127,12 +137,8 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 			crypto_skcipher_decrypt(&areq->cra_u.skcipher_req);
 
 		/* AIO operation in progress */
-		if (err == -EINPROGRESS || err == -EBUSY) {
-			/* Remember output size that will be generated. */
-			areq->outlen = len;
-
+		if (err == -EINPROGRESS || err == -EBUSY)
 			return -EIOCBQUEUED;
-		}
 
 		sock_put(sk);
 	} else {
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index 4e6472658852..eca04d3729b3 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -81,6 +81,7 @@ static int mcryptd_init_queue(struct mcryptd_queue *queue,
 		pr_debug("cpu_queue #%d %p\n", cpu, queue->cpu_queue);
 		crypto_init_queue(&cpu_queue->queue, max_cpu_qlen);
 		INIT_WORK(&cpu_queue->work, mcryptd_queue_worker);
+		spin_lock_init(&cpu_queue->q_lock);
 	}
 	return 0;
 }
@@ -104,15 +105,16 @@ static int mcryptd_enqueue_request(struct mcryptd_queue *queue,
 	int cpu, err;
 	struct mcryptd_cpu_queue *cpu_queue;
 
-	cpu = get_cpu();
-	cpu_queue = this_cpu_ptr(queue->cpu_queue);
-	rctx->tag.cpu = cpu;
+	cpu_queue = raw_cpu_ptr(queue->cpu_queue);
+	spin_lock(&cpu_queue->q_lock);
+	cpu = smp_processor_id();
+	rctx->tag.cpu = smp_processor_id();
 
 	err = crypto_enqueue_request(&cpu_queue->queue, request);
 	pr_debug("enqueue request: cpu %d cpu_queue %p request %p\n",
 		 cpu, cpu_queue, request);
+	spin_unlock(&cpu_queue->q_lock);
 	queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
-	put_cpu();
 
 	return err;
 }
@@ -161,16 +163,11 @@ static void mcryptd_queue_worker(struct work_struct *work)
 	cpu_queue = container_of(work, struct mcryptd_cpu_queue, work);
 	i = 0;
 	while (i < MCRYPTD_BATCH || single_task_running()) {
-		/*
-		 * preempt_disable/enable is used to prevent
-		 * being preempted by mcryptd_enqueue_request()
-		 */
-		local_bh_disable();
-		preempt_disable();
+
+		spin_lock_bh(&cpu_queue->q_lock);
 		backlog = crypto_get_backlog(&cpu_queue->queue);
 		req = crypto_dequeue_request(&cpu_queue->queue);
-		preempt_enable();
-		local_bh_enable();
+		spin_unlock_bh(&cpu_queue->q_lock);
 
 		if (!req) {
 			mcryptd_opportunistic_flush();
@@ -185,7 +182,7 @@ static void mcryptd_queue_worker(struct work_struct *work)
 		++i;
 	}
 	if (cpu_queue->queue.qlen)
-		queue_work(kcrypto_wq, &cpu_queue->work);
+		queue_work_on(smp_processor_id(), kcrypto_wq, &cpu_queue->work);
 }
 
 void mcryptd_flusher(struct work_struct *__work)
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 778e0ff42bfa..11af5fd6a443 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -449,6 +449,8 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk,
 
 	walk->total = req->cryptlen;
 	walk->nbytes = 0;
+	walk->iv = req->iv;
+	walk->oiv = req->iv;
 
 	if (unlikely(!walk->total))
 		return 0;
@@ -456,9 +458,6 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk,
 	scatterwalk_start(&walk->in, req->src);
 	scatterwalk_start(&walk->out, req->dst);
 
-	walk->iv = req->iv;
-	walk->oiv = req->iv;
-
 	walk->flags &= ~SKCIPHER_WALK_SLEEP;
 	walk->flags |= req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
 		       SKCIPHER_WALK_SLEEP : 0;
@@ -510,6 +509,8 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk,
 	int err;
 
 	walk->nbytes = 0;
+	walk->iv = req->iv;
+	walk->oiv = req->iv;
 
 	if (unlikely(!walk->total))
 		return 0;
@@ -525,9 +526,6 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk,
 	scatterwalk_done(&walk->in, 0, walk->total);
 	scatterwalk_done(&walk->out, 0, walk->total);
 
-	walk->iv = req->iv;
-	walk->oiv = req->iv;
-
 	if (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP)
 		walk->flags |= SKCIPHER_WALK_SLEEP;
 	else
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index ff2580e7611d..abeb4df4f22e 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1670,6 +1670,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 				dev_name(&adev_dimm->dev));
 		return -ENXIO;
 	}
+	/*
+	 * Record nfit_mem for the notification path to track back to
+	 * the nfit sysfs attributes for this dimm device object.
+	 */
+	dev_set_drvdata(&adev_dimm->dev, nfit_mem);
 
 	/*
 	 * Until standardization materializes we need to consider 4
@@ -1752,9 +1757,11 @@ static void shutdown_dimm_notify(void *data)
 			sysfs_put(nfit_mem->flags_attr);
 			nfit_mem->flags_attr = NULL;
 		}
-		if (adev_dimm)
+		if (adev_dimm) {
 			acpi_remove_notify_handler(adev_dimm->handle,
 					ACPI_DEVICE_NOTIFY, acpi_nvdimm_notify);
+			dev_set_drvdata(&adev_dimm->dev, NULL);
+		}
 	}
 	mutex_unlock(&acpi_desc->init_mutex);
 }
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 647d056df88c..b56c11f51baf 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -220,7 +220,8 @@ static bool clk_core_is_enabled(struct clk_core *core)
 
 	ret = core->ops->is_enabled(core->hw);
 done:
-	clk_pm_runtime_put(core);
+	if (core->dev)
+		pm_runtime_put(core->dev);
 
 	return ret;
 }
@@ -1564,6 +1565,9 @@ static void clk_change_rate(struct clk_core *core)
 		best_parent_rate = core->parent->rate;
 	}
 
+	if (clk_pm_runtime_get(core))
+		return;
+
 	if (core->flags & CLK_SET_RATE_UNGATE) {
 		unsigned long flags;
 
@@ -1634,6 +1638,8 @@ static void clk_change_rate(struct clk_core *core)
 	/* handle the new child who might not be in core->children yet */
 	if (core->new_child)
 		clk_change_rate(core->new_child);
+
+	clk_pm_runtime_put(core);
 }
 
 static int clk_core_set_rate_nolock(struct clk_core *core,
diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c
index a1a634253d6f..f00d8758ba24 100644
--- a/drivers/clk/sunxi/clk-sun9i-mmc.c
+++ b/drivers/clk/sunxi/clk-sun9i-mmc.c
@@ -16,6 +16,7 @@
 
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
+#include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -83,9 +84,20 @@ static int sun9i_mmc_reset_deassert(struct reset_controller_dev *rcdev,
 	return 0;
 }
 
+static int sun9i_mmc_reset_reset(struct reset_controller_dev *rcdev,
+				 unsigned long id)
+{
+	sun9i_mmc_reset_assert(rcdev, id);
+	udelay(10);
+	sun9i_mmc_reset_deassert(rcdev, id);
+
+	return 0;
+}
+
 static const struct reset_control_ops sun9i_mmc_reset_ops = {
 	.assert		= sun9i_mmc_reset_assert,
 	.deassert	= sun9i_mmc_reset_deassert,
+	.reset		= sun9i_mmc_reset_reset,
 };
 
 static int sun9i_a80_mmc_config_clk_probe(struct platform_device *pdev)
diff --git a/drivers/gpio/gpio-reg.c b/drivers/gpio/gpio-reg.c
index 23e771dba4c1..e85903eddc68 100644
--- a/drivers/gpio/gpio-reg.c
+++ b/drivers/gpio/gpio-reg.c
@@ -103,8 +103,8 @@ static int gpio_reg_to_irq(struct gpio_chip *gc, unsigned offset)
 	struct gpio_reg *r = to_gpio_reg(gc);
 	int irq = r->irqs[offset];
 
-	if (irq >= 0 && r->irq.domain)
-		irq = irq_find_mapping(r->irq.domain, irq);
+	if (irq >= 0 && r->irqdomain)
+		irq = irq_find_mapping(r->irqdomain, irq);
 
 	return irq;
 }
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index eb4528c87c0b..d6f3d9ee1350 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1074,7 +1074,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip)
 	}
 
 	if (!chip->names)
-		devprop_gpiochip_set_names(chip);
+		devprop_gpiochip_set_names(chip, dev_fwnode(chip->parent));
 
 	acpi_gpiochip_request_regions(acpi_gpio);
 	acpi_gpiochip_scan_gpios(acpi_gpio);
diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c
index 27f383bda7d9..f748aa3e77f7 100644
--- a/drivers/gpio/gpiolib-devprop.c
+++ b/drivers/gpio/gpiolib-devprop.c
@@ -19,30 +19,27 @@
 /**
  * devprop_gpiochip_set_names - Set GPIO line names using device properties
  * @chip: GPIO chip whose lines should be named, if possible
+ * @fwnode: Property Node containing the gpio-line-names property
  *
  * Looks for device property "gpio-line-names" and if it exists assigns
  * GPIO line names for the chip. The memory allocated for the assigned
  * names belong to the underlying firmware node and should not be released
  * by the caller.
  */
-void devprop_gpiochip_set_names(struct gpio_chip *chip)
+void devprop_gpiochip_set_names(struct gpio_chip *chip,
+				const struct fwnode_handle *fwnode)
 {
 	struct gpio_device *gdev = chip->gpiodev;
 	const char **names;
 	int ret, i;
 
-	if (!chip->parent) {
-		dev_warn(&gdev->dev, "GPIO chip parent is NULL\n");
-		return;
-	}
-
-	ret = device_property_read_string_array(chip->parent, "gpio-line-names",
+	ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
 						NULL, 0);
 	if (ret < 0)
 		return;
 
 	if (ret != gdev->ngpio) {
-		dev_warn(chip->parent,
+		dev_warn(&gdev->dev,
 			 "names %d do not match number of GPIOs %d\n", ret,
 			 gdev->ngpio);
 		return;
@@ -52,10 +49,10 @@ void devprop_gpiochip_set_names(struct gpio_chip *chip)
 	if (!names)
 		return;
 
-	ret = device_property_read_string_array(chip->parent, "gpio-line-names",
+	ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
 						names, gdev->ngpio);
 	if (ret < 0) {
-		dev_warn(chip->parent, "failed to read GPIO line names\n");
+		dev_warn(&gdev->dev, "failed to read GPIO line names\n");
 		kfree(names);
 		return;
 	}
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index e0d59e61b52f..72a0695d2ac3 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -493,7 +493,8 @@ int of_gpiochip_add(struct gpio_chip *chip)
 
 	/* If the chip defines names itself, these take precedence */
 	if (!chip->names)
-		devprop_gpiochip_set_names(chip);
+		devprop_gpiochip_set_names(chip,
+					   of_fwnode_handle(chip->of_node));
 
 	of_node_get(chip->of_node);
 
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index af48322839c3..6c44d1652139 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -228,7 +228,8 @@ static inline int gpio_chip_hwgpio(const struct gpio_desc *desc)
 	return desc - &desc->gdev->descs[0];
 }
 
-void devprop_gpiochip_set_names(struct gpio_chip *chip);
+void devprop_gpiochip_set_names(struct gpio_chip *chip,
+				const struct fwnode_handle *fwnode);
 
 /* With descriptor prefix */
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index da43813d67a4..5aeb5f8816f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2467,7 +2467,7 @@ static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev)
 				  PACKET3_MAP_QUEUES_PIPE(ring->pipe) |
 				  PACKET3_MAP_QUEUES_ME((ring->me == 1 ? 0 : 1)) |
 				  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
-				  PACKET3_MAP_QUEUES_ALLOC_FORMAT(1) | /* alloc format: all_on_one_pipe */
+				  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
 				  PACKET3_MAP_QUEUES_ENGINE_SEL(0) | /* engine_sel: compute */
 				  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
 		amdgpu_ring_write(kiq_ring, PACKET3_MAP_QUEUES_DOORBELL_OFFSET(ring->doorbell_index));
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index f71fe6d2ddda..bb5fa895fb64 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2336,7 +2336,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 		       const struct dm_connector_state *dm_state)
 {
 	struct drm_display_mode *preferred_mode = NULL;
-	const struct drm_connector *drm_connector;
+	struct drm_connector *drm_connector;
 	struct dc_stream_state *stream = NULL;
 	struct drm_display_mode mode = *drm_mode;
 	bool native_mode_found = false;
@@ -2355,11 +2355,13 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 
 	if (!aconnector->dc_sink) {
 		/*
-		 * Exclude MST from creating fake_sink
-		 * TODO: need to enable MST into fake_sink feature
+		 * Create dc_sink when necessary to MST
+		 * Don't apply fake_sink to MST
 		 */
-		if (aconnector->mst_port)
-			goto stream_create_fail;
+		if (aconnector->mst_port) {
+			dm_dp_mst_dc_sink_create(drm_connector);
+			goto mst_dc_sink_create_done;
+		}
 
 		if (create_fake_sink(aconnector))
 			goto stream_create_fail;
@@ -2410,6 +2412,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 stream_create_fail:
 dm_state_null:
 drm_connector_null:
+mst_dc_sink_create_done:
 	return stream;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 117521c6a6ed..0230250a1164 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -189,6 +189,8 @@ struct amdgpu_dm_connector {
 	struct mutex hpd_lock;
 
 	bool fake_enable;
+
+	bool mst_connected;
 };
 
 #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index f8efb98b1fa7..638c2c2b5cd7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -185,6 +185,42 @@ static int dm_connector_update_modes(struct drm_connector *connector,
 	return ret;
 }
 
+void dm_dp_mst_dc_sink_create(struct drm_connector *connector)
+{
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	struct edid *edid;
+	struct dc_sink *dc_sink;
+	struct dc_sink_init_data init_params = {
+			.link = aconnector->dc_link,
+			.sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST };
+
+	edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
+
+	if (!edid) {
+		drm_mode_connector_update_edid_property(
+			&aconnector->base,
+			NULL);
+		return;
+	}
+
+	aconnector->edid = edid;
+
+	dc_sink = dc_link_add_remote_sink(
+		aconnector->dc_link,
+		(uint8_t *)aconnector->edid,
+		(aconnector->edid->extensions + 1) * EDID_LENGTH,
+		&init_params);
+
+	dc_sink->priv = aconnector;
+	aconnector->dc_sink = dc_sink;
+
+	amdgpu_dm_add_sink_to_freesync_module(
+			connector, aconnector->edid);
+
+	drm_mode_connector_update_edid_property(
+					&aconnector->base, aconnector->edid);
+}
+
 static int dm_dp_mst_get_modes(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
@@ -311,6 +347,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 			drm_mode_connector_set_path_property(connector, pathprop);
 
 			drm_connector_list_iter_end(&conn_iter);
+			aconnector->mst_connected = true;
 			return &aconnector->base;
 		}
 	}
@@ -363,6 +400,8 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	 */
 	amdgpu_dm_connector_funcs_reset(connector);
 
+	aconnector->mst_connected = true;
+
 	DRM_INFO("DM_MST: added connector: %p [id: %d] [master: %p]\n",
 			aconnector, connector->base.id, aconnector->mst_port);
 
@@ -394,6 +433,8 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	drm_mode_connector_update_edid_property(
 			&aconnector->base,
 			NULL);
+
+	aconnector->mst_connected = false;
 }
 
 static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
@@ -404,10 +445,18 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
 	drm_kms_helper_hotplug_event(dev);
 }
 
+static void dm_dp_mst_link_status_reset(struct drm_connector *connector)
+{
+	mutex_lock(&connector->dev->mode_config.mutex);
+	drm_mode_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
+	mutex_unlock(&connector->dev->mode_config.mutex);
+}
+
 static void dm_dp_mst_register_connector(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
 	if (adev->mode_info.rfbdev)
 		drm_fb_helper_add_one_connector(&adev->mode_info.rfbdev->helper, connector);
@@ -416,6 +465,8 @@ static void dm_dp_mst_register_connector(struct drm_connector *connector)
 
 	drm_connector_register(connector);
 
+	if (aconnector->mst_connected)
+		dm_dp_mst_link_status_reset(connector);
 }
 
 static const struct drm_dp_mst_topology_cbs dm_mst_cbs = {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index 2da851b40042..8cf51da26657 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -31,5 +31,6 @@ struct amdgpu_dm_connector;
 
 void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 				       struct amdgpu_dm_connector *aconnector);
+void dm_dp_mst_dc_sink_create(struct drm_connector *connector);
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 3dce35e66b09..b142629a1058 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -900,6 +900,15 @@ bool dcn_validate_bandwidth(
 			v->override_vta_ps[input_idx] = pipe->plane_res.scl_data.taps.v_taps;
 			v->override_hta_pschroma[input_idx] = pipe->plane_res.scl_data.taps.h_taps_c;
 			v->override_vta_pschroma[input_idx] = pipe->plane_res.scl_data.taps.v_taps_c;
+			/*
+			 * Spreadsheet doesn't handle taps_c is one properly,
+			 * need to force Chroma to always be scaled to pass
+			 * bandwidth validation.
+			 */
+			if (v->override_hta_pschroma[input_idx] == 1)
+				v->override_hta_pschroma[input_idx] = 2;
+			if (v->override_vta_pschroma[input_idx] == 1)
+				v->override_vta_pschroma[input_idx] = 2;
 			v->source_scan[input_idx] = (pipe->plane_state->rotation % 2) ? dcn_bw_vert : dcn_bw_hor;
 		}
 		if (v->is_line_buffer_bpp_fixed == dcn_bw_yes)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index e27ed4a45265..42a111b9505d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1801,7 +1801,7 @@ static void disable_link(struct dc_link *link, enum signal_type signal)
 		link->link_enc->funcs->disable_output(link->link_enc, signal, link);
 }
 
-bool dp_active_dongle_validate_timing(
+static bool dp_active_dongle_validate_timing(
 		const struct dc_crtc_timing *timing,
 		const struct dc_dongle_caps *dongle_caps)
 {
@@ -1833,6 +1833,8 @@ bool dp_active_dongle_validate_timing(
 	/* Check Color Depth and Pixel Clock */
 	if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
 		required_pix_clk /= 2;
+	else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
+		required_pix_clk = required_pix_clk * 2 / 3;
 
 	switch (timing->display_color_depth) {
 	case COLOR_DEPTH_666:
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 07ff8d2faf3f..d844fadcd56f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -2866,16 +2866,19 @@ static void dce110_apply_ctx_for_surface(
 		int num_planes,
 		struct dc_state *context)
 {
-	int i, be_idx;
+	int i;
 
 	if (num_planes == 0)
 		return;
 
-	be_idx = -1;
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (stream == context->res_ctx.pipe_ctx[i].stream) {
-			be_idx = context->res_ctx.pipe_ctx[i].stream_res.tg->inst;
-			break;
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (stream == pipe_ctx->stream) {
+			if (!pipe_ctx->top_pipe &&
+				(pipe_ctx->plane_state || old_pipe_ctx->plane_state))
+				dc->hwss.pipe_control_lock(dc, pipe_ctx, true);
 		}
 	}
 
@@ -2895,9 +2898,22 @@ static void dce110_apply_ctx_for_surface(
 					context->stream_count);
 
 		dce110_program_front_end_for_pipe(dc, pipe_ctx);
+
+		dc->hwss.update_plane_addr(dc, pipe_ctx);
+
 		program_surface_visibility(dc, pipe_ctx);
 
 	}
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if ((stream == pipe_ctx->stream) &&
+			(!pipe_ctx->top_pipe) &&
+			(pipe_ctx->plane_state || old_pipe_ctx->plane_state))
+			dc->hwss.pipe_control_lock(dc, pipe_ctx, false);
+	}
 }
 
 static void dce110_power_down_fe(struct dc *dc, int fe_idx)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index 74e7c82bdc76..a9d55d0dd69e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -159,11 +159,10 @@ bool dpp_get_optimal_number_of_taps(
 			scl_data->taps.h_taps = 1;
 		if (IDENTITY_RATIO(scl_data->ratios.vert))
 			scl_data->taps.v_taps = 1;
-		/*
-		 * Spreadsheet doesn't handle taps_c is one properly,
-		 * need to force Chroma to always be scaled to pass
-		 * bandwidth validation.
-		 */
+		if (IDENTITY_RATIO(scl_data->ratios.horz_c))
+			scl_data->taps.h_taps_c = 1;
+		if (IDENTITY_RATIO(scl_data->ratios.vert_c))
+			scl_data->taps.v_taps_c = 1;
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index 59849f02e2ad..1402c0e71b03 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -220,17 +220,6 @@ static struct drm_master *drm_lease_create(struct drm_master *lessor, struct idr
 
 	mutex_lock(&dev->mode_config.idr_mutex);
 
-	/* Insert the new lessee into the tree */
-	id = idr_alloc(&(drm_lease_owner(lessor)->lessee_idr), lessee, 1, 0, GFP_KERNEL);
-	if (id < 0) {
-		error = id;
-		goto out_lessee;
-	}
-
-	lessee->lessee_id = id;
-	lessee->lessor = drm_master_get(lessor);
-	list_add_tail(&lessee->lessee_list, &lessor->lessees);
-
 	idr_for_each_entry(leases, entry, object) {
 		error = 0;
 		if (!idr_find(&dev->mode_config.crtc_idr, object))
@@ -246,6 +235,17 @@ static struct drm_master *drm_lease_create(struct drm_master *lessor, struct idr
 		}
 	}
 
+	/* Insert the new lessee into the tree */
+	id = idr_alloc(&(drm_lease_owner(lessor)->lessee_idr), lessee, 1, 0, GFP_KERNEL);
+	if (id < 0) {
+		error = id;
+		goto out_lessee;
+	}
+
+	lessee->lessee_id = id;
+	lessee->lessor = drm_master_get(lessor);
+	list_add_tail(&lessee->lessee_list, &lessor->lessees);
+
 	/* Move the leases over */
 	lessee->leases = *leases;
 	DRM_DEBUG_LEASE("new lessee %d %p, lessor %d %p\n", lessee->lessee_id, lessee, lessor->lessee_id, lessor);
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 37a93cdffb4a..2c90519576a3 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -558,11 +558,10 @@ int drm_plane_check_pixel_format(const struct drm_plane *plane, u32 format)
 }
 
 /*
- * setplane_internal - setplane handler for internal callers
+ * __setplane_internal - setplane handler for internal callers
  *
- * Note that we assume an extra reference has already been taken on fb.  If the
- * update fails, this reference will be dropped before return; if it succeeds,
- * the previous framebuffer (if any) will be unreferenced instead.
+ * This function will take a reference on the new fb for the plane
+ * on success.
  *
  * src_{x,y,w,h} are provided in 16.16 fixed point format
  */
@@ -630,14 +629,12 @@ static int __setplane_internal(struct drm_plane *plane,
 	if (!ret) {
 		plane->crtc = crtc;
 		plane->fb = fb;
-		fb = NULL;
+		drm_framebuffer_get(plane->fb);
 	} else {
 		plane->old_fb = NULL;
 	}
 
 out:
-	if (fb)
-		drm_framebuffer_put(fb);
 	if (plane->old_fb)
 		drm_framebuffer_put(plane->old_fb);
 	plane->old_fb = NULL;
@@ -685,6 +682,7 @@ int drm_mode_setplane(struct drm_device *dev, void *data,
 	struct drm_plane *plane;
 	struct drm_crtc *crtc = NULL;
 	struct drm_framebuffer *fb = NULL;
+	int ret;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
@@ -717,15 +715,16 @@ int drm_mode_setplane(struct drm_device *dev, void *data,
 		}
 	}
 
-	/*
-	 * setplane_internal will take care of deref'ing either the old or new
-	 * framebuffer depending on success.
-	 */
-	return setplane_internal(plane, crtc, fb,
-				 plane_req->crtc_x, plane_req->crtc_y,
-				 plane_req->crtc_w, plane_req->crtc_h,
-				 plane_req->src_x, plane_req->src_y,
-				 plane_req->src_w, plane_req->src_h);
+	ret = setplane_internal(plane, crtc, fb,
+				plane_req->crtc_x, plane_req->crtc_y,
+				plane_req->crtc_w, plane_req->crtc_h,
+				plane_req->src_x, plane_req->src_y,
+				plane_req->src_w, plane_req->src_h);
+
+	if (fb)
+		drm_framebuffer_put(fb);
+
+	return ret;
 }
 
 static int drm_mode_cursor_universal(struct drm_crtc *crtc,
@@ -788,13 +787,12 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 		src_h = fb->height << 16;
 	}
 
-	/*
-	 * setplane_internal will take care of deref'ing either the old or new
-	 * framebuffer depending on success.
-	 */
 	ret = __setplane_internal(crtc->cursor, crtc, fb,
-				crtc_x, crtc_y, crtc_w, crtc_h,
-				0, 0, src_w, src_h, ctx);
+				  crtc_x, crtc_y, crtc_w, crtc_h,
+				  0, 0, src_w, src_h, ctx);
+
+	if (fb)
+		drm_framebuffer_put(fb);
 
 	/* Update successful; save new cursor position, if necessary */
 	if (ret == 0 && req->flags & DRM_MODE_CURSOR_MOVE) {
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index f776fc1cc543..cb4d09c70fd4 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -369,40 +369,26 @@ static const struct file_operations drm_syncobj_file_fops = {
 	.release = drm_syncobj_file_release,
 };
 
-static int drm_syncobj_alloc_file(struct drm_syncobj *syncobj)
-{
-	struct file *file = anon_inode_getfile("syncobj_file",
-					       &drm_syncobj_file_fops,
-					       syncobj, 0);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	drm_syncobj_get(syncobj);
-	if (cmpxchg(&syncobj->file, NULL, file)) {
-		/* lost the race */
-		fput(file);
-	}
-
-	return 0;
-}
-
 int drm_syncobj_get_fd(struct drm_syncobj *syncobj, int *p_fd)
 {
-	int ret;
+	struct file *file;
 	int fd;
 
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0)
 		return fd;
 
-	if (!syncobj->file) {
-		ret = drm_syncobj_alloc_file(syncobj);
-		if (ret) {
-			put_unused_fd(fd);
-			return ret;
-		}
+	file = anon_inode_getfile("syncobj_file",
+				  &drm_syncobj_file_fops,
+				  syncobj, 0);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		return PTR_ERR(file);
 	}
-	fd_install(fd, syncobj->file);
+
+	drm_syncobj_get(syncobj);
+	fd_install(fd, file);
+
 	*p_fd = fd;
 	return 0;
 }
@@ -422,31 +408,24 @@ static int drm_syncobj_handle_to_fd(struct drm_file *file_private,
 	return ret;
 }
 
-static struct drm_syncobj *drm_syncobj_fdget(int fd)
-{
-	struct file *file = fget(fd);
-
-	if (!file)
-		return NULL;
-	if (file->f_op != &drm_syncobj_file_fops)
-		goto err;
-
-	return file->private_data;
-err:
-	fput(file);
-	return NULL;
-};
-
 static int drm_syncobj_fd_to_handle(struct drm_file *file_private,
 				    int fd, u32 *handle)
 {
-	struct drm_syncobj *syncobj = drm_syncobj_fdget(fd);
+	struct drm_syncobj *syncobj;
+	struct file *file;
 	int ret;
 
-	if (!syncobj)
+	file = fget(fd);
+	if (!file)
 		return -EINVAL;
 
+	if (file->f_op != &drm_syncobj_file_fops) {
+		fput(file);
+		return -EINVAL;
+	}
+
 	/* take a reference to put in the idr */
+	syncobj = file->private_data;
 	drm_syncobj_get(syncobj);
 
 	idr_preload(GFP_KERNEL);
@@ -455,12 +434,14 @@ static int drm_syncobj_fd_to_handle(struct drm_file *file_private,
 	spin_unlock(&file_private->syncobj_table_lock);
 	idr_preload_end();
 
-	if (ret < 0) {
-		fput(syncobj->file);
-		return ret;
-	}
-	*handle = ret;
-	return 0;
+	if (ret > 0) {
+		*handle = ret;
+		ret = 0;
+	} else
+		drm_syncobj_put(syncobj);
+
+	fput(file);
+	return ret;
 }
 
 static int drm_syncobj_import_sync_file_fence(struct drm_file *file_private,
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 355120865efd..309f3fa6794a 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -266,6 +266,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	/* Clear host CRT status, so guest couldn't detect this host CRT. */
 	if (IS_BROADWELL(dev_priv))
 		vgpu_vreg(vgpu, PCH_ADPA) &= ~ADPA_CRT_HOTPLUG_MONITOR_MASK;
+
+	vgpu_vreg(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
 }
 
 static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num)
@@ -282,7 +284,6 @@ static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num)
 static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
 				    int type, unsigned int resolution)
 {
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct intel_vgpu_port *port = intel_vgpu_port(vgpu, port_num);
 
 	if (WARN_ON(resolution >= GVT_EDID_NUM))
@@ -308,7 +309,7 @@ static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num,
 	port->type = type;
 
 	emulate_monitor_status_change(vgpu);
-	vgpu_vreg(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ad4050f7ab3b..18de6569d04a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -330,17 +330,10 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 	 * must wait for all rendering to complete to the object (as unbinding
 	 * must anyway), and retire the requests.
 	 */
-	ret = i915_gem_object_wait(obj,
-				   I915_WAIT_INTERRUPTIBLE |
-				   I915_WAIT_LOCKED |
-				   I915_WAIT_ALL,
-				   MAX_SCHEDULE_TIMEOUT,
-				   NULL);
+	ret = i915_gem_object_set_to_cpu_domain(obj, false);
 	if (ret)
 		return ret;
 
-	i915_gem_retire_requests(to_i915(obj->base.dev));
-
 	while ((vma = list_first_entry_or_null(&obj->vma_list,
 					       struct i915_vma,
 					       obj_link))) {
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index e8ca67a129d2..ac236b88c99c 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -367,6 +367,7 @@ struct i915_sw_dma_fence_cb {
 	struct dma_fence *dma;
 	struct timer_list timer;
 	struct irq_work work;
+	struct rcu_head rcu;
 };
 
 static void timer_i915_sw_fence_wake(struct timer_list *t)
@@ -406,7 +407,7 @@ static void irq_i915_sw_fence_work(struct irq_work *wrk)
 	del_timer_sync(&cb->timer);
 	dma_fence_put(cb->dma);
 
-	kfree(cb);
+	kfree_rcu(cb, rcu);
 }
 
 int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 5f8b9f1f40f1..bcbc7abe6693 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -186,7 +186,7 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
 	struct intel_wait *wait, *n, *first;
 
 	if (!b->irq_armed)
-		return;
+		goto wakeup_signaler;
 
 	/* We only disarm the irq when we are idle (all requests completed),
 	 * so if the bottom-half remains asleep, it missed the request
@@ -208,6 +208,14 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
 	b->waiters = RB_ROOT;
 
 	spin_unlock_irq(&b->rb_lock);
+
+	/*
+	 * The signaling thread may be asleep holding a reference to a request,
+	 * that had its signaling cancelled prior to being preempted. We need
+	 * to kick the signaler, just in case, to release any such reference.
+	 */
+wakeup_signaler:
+	wake_up_process(b->signaler);
 }
 
 static bool use_fake_irq(const struct intel_breadcrumbs *b)
@@ -651,23 +659,15 @@ static int intel_breadcrumbs_signaler(void *arg)
 		}
 
 		if (unlikely(do_schedule)) {
-			DEFINE_WAIT(exec);
-
 			if (kthread_should_park())
 				kthread_parkme();
 
-			if (kthread_should_stop()) {
-				GEM_BUG_ON(request);
+			if (unlikely(kthread_should_stop())) {
+				i915_gem_request_put(request);
 				break;
 			}
 
-			if (request)
-				add_wait_queue(&request->execute, &exec);
-
 			schedule();
-
-			if (request)
-				remove_wait_queue(&request->execute, &exec);
 		}
 		i915_gem_request_put(request);
 	} while (1);
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e0843bb99169..58a3755544b2 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -2128,6 +2128,8 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder,
 	if (WARN_ON(!pll))
 		return;
 
+	 mutex_lock(&dev_priv->dpll_lock);
+
 	if (IS_CANNONLAKE(dev_priv)) {
 		/* Configure DPCLKA_CFGCR0 to map the DPLL to the DDI. */
 		val = I915_READ(DPCLKA_CFGCR0);
@@ -2157,6 +2159,8 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder,
 	} else if (INTEL_INFO(dev_priv)->gen < 9) {
 		I915_WRITE(PORT_CLK_SEL(port), hsw_pll_to_ddi_pll_sel(pll));
 	}
+
+	mutex_unlock(&dev_priv->dpll_lock);
 }
 
 static void intel_ddi_clk_disable(struct intel_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e8ccf89cb17b..30cf273d57aa 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9944,11 +9944,10 @@ found:
 	}
 
 	ret = intel_modeset_setup_plane_state(state, crtc, mode, fb, 0, 0);
+	drm_framebuffer_put(fb);
 	if (ret)
 		goto fail;
 
-	drm_framebuffer_put(fb);
-
 	ret = drm_atomic_set_mode_for_crtc(&crtc_state->base, mode);
 	if (ret)
 		goto fail;
@@ -13195,7 +13194,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	primary->frontbuffer_bit = INTEL_FRONTBUFFER_PRIMARY(pipe);
 	primary->check_plane = intel_check_primary_plane;
 
-	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 10) {
 		intel_primary_formats = skl_primary_formats;
 		num_formats = ARRAY_SIZE(skl_primary_formats);
 		modifiers = skl_format_modifiers_ccs;
diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c
index 3bf65288ffff..5809b29044fc 100644
--- a/drivers/gpu/drm/i915/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/intel_lpe_audio.c
@@ -193,7 +193,7 @@ static bool lpe_audio_detect(struct drm_i915_private *dev_priv)
 		};
 
 		if (!pci_dev_present(atom_hdaudio_ids)) {
-			DRM_INFO("%s\n", "HDaudio controller not detected, using LPE audio instead\n");
+			DRM_INFO("HDaudio controller not detected, using LPE audio instead\n");
 			lpe_present = true;
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 2615912430cc..435ff8662cfa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -224,7 +224,7 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
 		/* Determine if we can get a cache-coherent map, forcing
 		 * uncached mapping if we can't.
 		 */
-		if (mmu->type[drm->ttm.type_host].type & NVIF_MEM_UNCACHED)
+		if (!nouveau_drm_use_coherent_gpu_mapping(drm))
 			nvbo->force_coherent = true;
 	}
 
@@ -262,7 +262,8 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
 		if (cli->device.info.family > NV_DEVICE_INFO_V0_CURIE &&
 		    (flags & TTM_PL_FLAG_VRAM) && !vmm->page[i].vram)
 			continue;
-		if ((flags & TTM_PL_FLAG_TT  ) && !vmm->page[i].host)
+		if ((flags & TTM_PL_FLAG_TT) &&
+		    (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
 			continue;
 
 		/* Select this page size if it's the first that supports
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 8d4a5be3b913..56fe261b6268 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -152,9 +152,9 @@ nouveau_cli_work_queue(struct nouveau_cli *cli, struct dma_fence *fence,
 	work->cli = cli;
 	mutex_lock(&cli->lock);
 	list_add_tail(&work->head, &cli->worker);
-	mutex_unlock(&cli->lock);
 	if (dma_fence_add_callback(fence, &work->cb, nouveau_cli_work_fence))
 		nouveau_cli_work_fence(fence, &work->cb);
+	mutex_unlock(&cli->lock);
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 3331e82ae9e7..96f6bd8aee5d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -157,8 +157,8 @@ struct nouveau_drm {
 		struct nvif_object copy;
 		int mtrr;
 		int type_vram;
-		int type_host;
-		int type_ncoh;
+		int type_host[2];
+		int type_ncoh[2];
 	} ttm;
 
 	/* GEM interface support */
@@ -217,6 +217,13 @@ nouveau_drm(struct drm_device *dev)
 	return dev->dev_private;
 }
 
+static inline bool
+nouveau_drm_use_coherent_gpu_mapping(struct nouveau_drm *drm)
+{
+	struct nvif_mmu *mmu = &drm->client.mmu;
+	return !(mmu->type[drm->ttm.type_host[0]].type & NVIF_MEM_UNCACHED);
+}
+
 int nouveau_pmops_suspend(struct device *);
 int nouveau_pmops_resume(struct device *);
 bool nouveau_pmops_runtime(void);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index c533d8e04afc..be7357bf2246 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -429,7 +429,7 @@ nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon)
 	drm_fb_helper_unregister_fbi(&fbcon->helper);
 	drm_fb_helper_fini(&fbcon->helper);
 
-	if (nouveau_fb->nvbo) {
+	if (nouveau_fb && nouveau_fb->nvbo) {
 		nouveau_vma_del(&nouveau_fb->vma);
 		nouveau_bo_unmap(nouveau_fb->nvbo);
 		nouveau_bo_unpin(nouveau_fb->nvbo);
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index 589a9621db76..c002f8968507 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -103,10 +103,10 @@ nouveau_mem_host(struct ttm_mem_reg *reg, struct ttm_dma_tt *tt)
 	u8 type;
 	int ret;
 
-	if (mmu->type[drm->ttm.type_host].type & NVIF_MEM_UNCACHED)
-		type = drm->ttm.type_ncoh;
+	if (!nouveau_drm_use_coherent_gpu_mapping(drm))
+		type = drm->ttm.type_ncoh[!!mem->kind];
 	else
-		type = drm->ttm.type_host;
+		type = drm->ttm.type_host[0];
 
 	if (mem->kind && !(mmu->type[type].type & NVIF_MEM_KIND))
 		mem->comp = mem->kind = 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 08b974b30482..dff51a0ee028 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -235,27 +235,46 @@ nouveau_ttm_global_release(struct nouveau_drm *drm)
 	drm->ttm.mem_global_ref.release = NULL;
 }
 
-int
-nouveau_ttm_init(struct nouveau_drm *drm)
+static int
+nouveau_ttm_init_host(struct nouveau_drm *drm, u8 kind)
 {
-	struct nvkm_device *device = nvxx_device(&drm->client.device);
-	struct nvkm_pci *pci = device->pci;
 	struct nvif_mmu *mmu = &drm->client.mmu;
-	struct drm_device *dev = drm->dev;
-	int typei, ret;
+	int typei;
 
 	typei = nvif_mmu_type(mmu, NVIF_MEM_HOST | NVIF_MEM_MAPPABLE |
-						   NVIF_MEM_COHERENT);
+					    kind | NVIF_MEM_COHERENT);
 	if (typei < 0)
 		return -ENOSYS;
 
-	drm->ttm.type_host = typei;
+	drm->ttm.type_host[!!kind] = typei;
 
-	typei = nvif_mmu_type(mmu, NVIF_MEM_HOST | NVIF_MEM_MAPPABLE);
+	typei = nvif_mmu_type(mmu, NVIF_MEM_HOST | NVIF_MEM_MAPPABLE | kind);
 	if (typei < 0)
 		return -ENOSYS;
 
-	drm->ttm.type_ncoh = typei;
+	drm->ttm.type_ncoh[!!kind] = typei;
+	return 0;
+}
+
+int
+nouveau_ttm_init(struct nouveau_drm *drm)
+{
+	struct nvkm_device *device = nvxx_device(&drm->client.device);
+	struct nvkm_pci *pci = device->pci;
+	struct nvif_mmu *mmu = &drm->client.mmu;
+	struct drm_device *dev = drm->dev;
+	int typei, ret;
+
+	ret = nouveau_ttm_init_host(drm, 0);
+	if (ret)
+		return ret;
+
+	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA &&
+	    drm->client.device.info.chipset != 0x50) {
+		ret = nouveau_ttm_init_host(drm, NVIF_MEM_KIND);
+		if (ret)
+			return ret;
+	}
 
 	if (drm->client.device.info.platform != NV_DEVICE_INFO_V0_SOC &&
 	    drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c
index 9e2628dd8e4d..f5371d96b003 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c
@@ -67,8 +67,8 @@ nouveau_vma_del(struct nouveau_vma **pvma)
 			nvif_vmm_put(&vma->vmm->vmm, &tmp);
 		}
 		list_del(&vma->head);
-		*pvma = NULL;
 		kfree(*pvma);
+		*pvma = NULL;
 	}
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index e14643615698..00eeaaffeae5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2369,7 +2369,7 @@ nv13b_chipset = {
 	.imem = gk20a_instmem_new,
 	.ltc = gp100_ltc_new,
 	.mc = gp10b_mc_new,
-	.mmu = gf100_mmu_new,
+	.mmu = gp10b_mmu_new,
 	.secboot = gp10b_secboot_new,
 	.pmu = gm20b_pmu_new,
 	.timer = gk20a_timer_new,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
index 972370ed36f0..7c7efa4ea0d0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c
@@ -36,6 +36,7 @@ nvbios_dp_table(struct nvkm_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 			if (data) {
 				*ver = nvbios_rd08(bios, data + 0x00);
 				switch (*ver) {
+				case 0x20:
 				case 0x21:
 				case 0x30:
 				case 0x40:
@@ -63,6 +64,7 @@ nvbios_dpout_entry(struct nvkm_bios *bios, u8 idx,
 	if (data && idx < *cnt) {
 		u16 outp = nvbios_rd16(bios, data + *hdr + idx * *len);
 		switch (*ver * !!outp) {
+		case 0x20:
 		case 0x21:
 		case 0x30:
 			*hdr = nvbios_rd08(bios, data + 0x04);
@@ -96,12 +98,16 @@ nvbios_dpout_parse(struct nvkm_bios *bios, u8 idx,
 		info->type = nvbios_rd16(bios, data + 0x00);
 		info->mask = nvbios_rd16(bios, data + 0x02);
 		switch (*ver) {
+		case 0x20:
+			info->mask |= 0x00c0; /* match any link */
+			/* fall-through */
 		case 0x21:
 		case 0x30:
 			info->flags     = nvbios_rd08(bios, data + 0x05);
 			info->script[0] = nvbios_rd16(bios, data + 0x06);
 			info->script[1] = nvbios_rd16(bios, data + 0x08);
-			info->lnkcmp    = nvbios_rd16(bios, data + 0x0a);
+			if (*len >= 0x0c)
+				info->lnkcmp    = nvbios_rd16(bios, data + 0x0a);
 			if (*len >= 0x0f) {
 				info->script[2] = nvbios_rd16(bios, data + 0x0c);
 				info->script[3] = nvbios_rd16(bios, data + 0x0e);
@@ -170,6 +176,7 @@ nvbios_dpcfg_parse(struct nvkm_bios *bios, u16 outp, u8 idx,
 	memset(info, 0x00, sizeof(*info));
 	if (data) {
 		switch (*ver) {
+		case 0x20:
 		case 0x21:
 			info->dc    = nvbios_rd08(bios, data + 0x02);
 			info->pe    = nvbios_rd08(bios, data + 0x03);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
index 1ba7289684aa..db48a1daca0c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
@@ -249,7 +249,7 @@ nv50_instobj_acquire(struct nvkm_memory *memory)
 			iobj->base.memory.ptrs = &nv50_instobj_fast;
 		else
 			iobj->base.memory.ptrs = &nv50_instobj_slow;
-		refcount_inc(&iobj->maps);
+		refcount_set(&iobj->maps, 1);
 	}
 
 	mutex_unlock(&imem->subdev.mutex);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
index b1b1f3626b96..deb96de54b00 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
@@ -136,6 +136,13 @@ nvkm_pci_init(struct nvkm_subdev *subdev)
 		return ret;
 
 	pci->irq = pdev->irq;
+
+	/* Ensure MSI interrupts are armed, for the case where there are
+	 * already interrupts pending (for whatever reason) at load time.
+	 */
+	if (pci->msi)
+		pci->func->msi_rearm(pci);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index dda904ec0534..500b6fb3e028 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -175,11 +175,31 @@ static void sun4i_hdmi_mode_set(struct drm_encoder *encoder,
 	writel(val, hdmi->base + SUN4I_HDMI_VID_TIMING_POL_REG);
 }
 
+static enum drm_mode_status sun4i_hdmi_mode_valid(struct drm_encoder *encoder,
+					const struct drm_display_mode *mode)
+{
+	struct sun4i_hdmi *hdmi = drm_encoder_to_sun4i_hdmi(encoder);
+	unsigned long rate = mode->clock * 1000;
+	unsigned long diff = rate / 200; /* +-0.5% allowed by HDMI spec */
+	long rounded_rate;
+
+	/* 165 MHz is the typical max pixelclock frequency for HDMI <= 1.2 */
+	if (rate > 165000000)
+		return MODE_CLOCK_HIGH;
+	rounded_rate = clk_round_rate(hdmi->tmds_clk, rate);
+	if (rounded_rate > 0 &&
+	    max_t(unsigned long, rounded_rate, rate) -
+	    min_t(unsigned long, rounded_rate, rate) < diff)
+		return MODE_OK;
+	return MODE_NOCLOCK;
+}
+
 static const struct drm_encoder_helper_funcs sun4i_hdmi_helper_funcs = {
 	.atomic_check	= sun4i_hdmi_atomic_check,
 	.disable	= sun4i_hdmi_disable,
 	.enable		= sun4i_hdmi_enable,
 	.mode_set	= sun4i_hdmi_mode_set,
+	.mode_valid	= sun4i_hdmi_mode_valid,
 };
 
 static const struct drm_encoder_funcs sun4i_hdmi_funcs = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index e122f5b2a395..f4284b51bdca 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -724,12 +724,12 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master,
 	if (IS_ERR(tcon->crtc)) {
 		dev_err(dev, "Couldn't create our CRTC\n");
 		ret = PTR_ERR(tcon->crtc);
-		goto err_free_clocks;
+		goto err_free_dotclock;
 	}
 
 	ret = sun4i_rgb_init(drm, tcon);
 	if (ret < 0)
-		goto err_free_clocks;
+		goto err_free_dotclock;
 
 	if (tcon->quirks->needs_de_be_mux) {
 		/*
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 44343a2bf55c..b5ba6441489f 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -455,6 +455,7 @@ ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		freed += (nr_free_pool - shrink_pages) << pool->order;
 		if (freed >= sc->nr_to_scan)
 			break;
+		shrink_pages <<= pool->order;
 	}
 	mutex_unlock(&lock);
 	return freed;
@@ -543,7 +544,7 @@ static int ttm_alloc_new_pages(struct list_head *pages, gfp_t gfp_flags,
 	int r = 0;
 	unsigned i, j, cpages;
 	unsigned npages = 1 << order;
-	unsigned max_cpages = min(count, (unsigned)NUM_PAGES_TO_ALLOC);
+	unsigned max_cpages = min(count << order, (unsigned)NUM_PAGES_TO_ALLOC);
 
 	/* allocate array for page caching change */
 	caching_array = kmalloc(max_cpages*sizeof(struct page *), GFP_KERNEL);
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index c9790e2c3440..af5123042990 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -143,6 +143,7 @@ static int hwmon_thermal_add_sensor(struct device *dev,
 				    struct hwmon_device *hwdev, int index)
 {
 	struct hwmon_thermal_data *tdata;
+	struct thermal_zone_device *tzd;
 
 	tdata = devm_kzalloc(dev, sizeof(*tdata), GFP_KERNEL);
 	if (!tdata)
@@ -151,8 +152,14 @@ static int hwmon_thermal_add_sensor(struct device *dev,
 	tdata->hwdev = hwdev;
 	tdata->index = index;
 
-	devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata,
-					     &hwmon_thermal_ops);
+	tzd = devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata,
+						   &hwmon_thermal_ops);
+	/*
+	 * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV,
+	 * so ignore that error but forward any other error.
+	 */
+	if (IS_ERR(tzd) && (PTR_ERR(tzd) != -ENODEV))
+		return PTR_ERR(tzd);
 
 	return 0;
 }
@@ -621,14 +628,20 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 				if (!chip->ops->is_visible(drvdata, hwmon_temp,
 							   hwmon_temp_input, j))
 					continue;
-				if (info[i]->config[j] & HWMON_T_INPUT)
-					hwmon_thermal_add_sensor(dev, hwdev, j);
+				if (info[i]->config[j] & HWMON_T_INPUT) {
+					err = hwmon_thermal_add_sensor(dev,
+								hwdev, j);
+					if (err)
+						goto free_device;
+				}
 			}
 		}
 	}
 
 	return hdev;
 
+free_device:
+	device_unregister(hdev);
 free_hwmon:
 	kfree(hwdev);
 ida_remove:
diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index feafdb961c48..59b2f96d986a 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -386,6 +386,9 @@ int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev)
 	if (ret)
 		return ret;
 
+	if (!qp->qp_sec)
+		return 0;
+
 	mutex_lock(&real_qp->qp_sec->mutex);
 	ret = check_qp_port_pkey_settings(real_qp->qp_sec->ports_pkeys,
 					  qp->qp_sec);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index d0202bb176a4..840b24096690 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2074,8 +2074,8 @@ int ib_uverbs_ex_modify_qp(struct ib_uverbs_file *file,
 		return -EOPNOTSUPP;
 
 	if (ucore->inlen > sizeof(cmd)) {
-		if (ib_is_udata_cleared(ucore, sizeof(cmd),
-					ucore->inlen - sizeof(cmd)))
+		if (!ib_is_udata_cleared(ucore, sizeof(cmd),
+					 ucore->inlen - sizeof(cmd)))
 			return -EOPNOTSUPP;
 	}
 
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 3fb8fb6cc824..e36d27ed4daa 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1438,7 +1438,8 @@ int ib_close_qp(struct ib_qp *qp)
 	spin_unlock_irqrestore(&real_qp->device->event_handler_lock, flags);
 
 	atomic_dec(&real_qp->usecnt);
-	ib_close_shared_qp_security(qp->qp_sec);
+	if (qp->qp_sec)
+		ib_close_shared_qp_security(qp->qp_sec);
 	kfree(qp);
 
 	return 0;
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index b7bfc536e00f..6f2b26126c64 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -395,7 +395,7 @@ next_cqe:
 
 static int cqe_completes_wr(struct t4_cqe *cqe, struct t4_wq *wq)
 {
-	if (CQE_OPCODE(cqe) == C4IW_DRAIN_OPCODE) {
+	if (DRAIN_CQE(cqe)) {
 		WARN_ONCE(1, "Unexpected DRAIN CQE qp id %u!\n", wq->sq.qid);
 		return 0;
 	}
@@ -494,7 +494,7 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 	/*
 	 * Special cqe for drain WR completions...
 	 */
-	if (CQE_OPCODE(hw_cqe) == C4IW_DRAIN_OPCODE) {
+	if (DRAIN_CQE(hw_cqe)) {
 		*cookie = CQE_DRAIN_COOKIE(hw_cqe);
 		*cqe = *hw_cqe;
 		goto skip_cqe;
@@ -571,10 +571,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 			ret = -EAGAIN;
 			goto skip_cqe;
 		}
-		if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) {
+		if (unlikely(!CQE_STATUS(hw_cqe) &&
+			     CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) {
 			t4_set_wq_in_error(wq);
-			hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN));
-			goto proc_cqe;
+			hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN));
 		}
 		goto proc_cqe;
 	}
@@ -748,9 +748,6 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 				c4iw_invalidate_mr(qhp->rhp,
 						   CQE_WRID_FR_STAG(&cqe));
 			break;
-		case C4IW_DRAIN_OPCODE:
-			wc->opcode = IB_WC_SEND;
-			break;
 		default:
 			pr_err("Unexpected opcode %d in the CQE received for QPID=0x%0x\n",
 			       CQE_OPCODE(&cqe), CQE_QPID(&cqe));
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 470f97a79ebb..65dd3726ca02 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -693,8 +693,6 @@ static inline int to_ib_qp_state(int c4iw_qp_state)
 	return IB_QPS_ERR;
 }
 
-#define C4IW_DRAIN_OPCODE FW_RI_SGE_EC_CR_RETURN
-
 static inline u32 c4iw_ib_to_tpt_access(int a)
 {
 	return (a & IB_ACCESS_REMOTE_WRITE ? FW_RI_MEM_ACCESS_REM_WRITE : 0) |
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 38bddd02a943..d5c92fc520d6 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -790,21 +790,57 @@ static int ring_kernel_rq_db(struct c4iw_qp *qhp, u16 inc)
 	return 0;
 }
 
-static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
+static int ib_to_fw_opcode(int ib_opcode)
+{
+	int opcode;
+
+	switch (ib_opcode) {
+	case IB_WR_SEND_WITH_INV:
+		opcode = FW_RI_SEND_WITH_INV;
+		break;
+	case IB_WR_SEND:
+		opcode = FW_RI_SEND;
+		break;
+	case IB_WR_RDMA_WRITE:
+		opcode = FW_RI_RDMA_WRITE;
+		break;
+	case IB_WR_RDMA_READ:
+	case IB_WR_RDMA_READ_WITH_INV:
+		opcode = FW_RI_READ_REQ;
+		break;
+	case IB_WR_REG_MR:
+		opcode = FW_RI_FAST_REGISTER;
+		break;
+	case IB_WR_LOCAL_INV:
+		opcode = FW_RI_LOCAL_INV;
+		break;
+	default:
+		opcode = -EINVAL;
+	}
+	return opcode;
+}
+
+static int complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
 {
 	struct t4_cqe cqe = {};
 	struct c4iw_cq *schp;
 	unsigned long flag;
 	struct t4_cq *cq;
+	int opcode;
 
 	schp = to_c4iw_cq(qhp->ibqp.send_cq);
 	cq = &schp->cq;
 
+	opcode = ib_to_fw_opcode(wr->opcode);
+	if (opcode < 0)
+		return opcode;
+
 	cqe.u.drain_cookie = wr->wr_id;
 	cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
-				 CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+				 CQE_OPCODE_V(opcode) |
 				 CQE_TYPE_V(1) |
 				 CQE_SWCQE_V(1) |
+				 CQE_DRAIN_V(1) |
 				 CQE_QPID_V(qhp->wq.sq.qid));
 
 	spin_lock_irqsave(&schp->lock, flag);
@@ -819,6 +855,23 @@ static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
 					   schp->ibcq.cq_context);
 		spin_unlock_irqrestore(&schp->comp_handler_lock, flag);
 	}
+	return 0;
+}
+
+static int complete_sq_drain_wrs(struct c4iw_qp *qhp, struct ib_send_wr *wr,
+				struct ib_send_wr **bad_wr)
+{
+	int ret = 0;
+
+	while (wr) {
+		ret = complete_sq_drain_wr(qhp, wr);
+		if (ret) {
+			*bad_wr = wr;
+			break;
+		}
+		wr = wr->next;
+	}
+	return ret;
 }
 
 static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
@@ -833,9 +886,10 @@ static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
 
 	cqe.u.drain_cookie = wr->wr_id;
 	cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
-				 CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+				 CQE_OPCODE_V(FW_RI_SEND) |
 				 CQE_TYPE_V(0) |
 				 CQE_SWCQE_V(1) |
+				 CQE_DRAIN_V(1) |
 				 CQE_QPID_V(qhp->wq.sq.qid));
 
 	spin_lock_irqsave(&rchp->lock, flag);
@@ -852,6 +906,14 @@ static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
 	}
 }
 
+static void complete_rq_drain_wrs(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
+{
+	while (wr) {
+		complete_rq_drain_wr(qhp, wr);
+		wr = wr->next;
+	}
+}
+
 int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		   struct ib_send_wr **bad_wr)
 {
@@ -875,7 +937,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	 */
 	if (qhp->wq.flushed) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
-		complete_sq_drain_wr(qhp, wr);
+		err = complete_sq_drain_wrs(qhp, wr, bad_wr);
 		return err;
 	}
 	num_wrs = t4_sq_avail(&qhp->wq);
@@ -1023,7 +1085,7 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 	 */
 	if (qhp->wq.flushed) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
-		complete_rq_drain_wr(qhp, wr);
+		complete_rq_drain_wrs(qhp, wr);
 		return err;
 	}
 	num_wrs = t4_rq_avail(&qhp->wq);
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index e9ea94268d51..79e8ee12c391 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -197,6 +197,11 @@ struct t4_cqe {
 #define CQE_SWCQE_G(x)    ((((x) >> CQE_SWCQE_S)) & CQE_SWCQE_M)
 #define CQE_SWCQE_V(x)	  ((x)<<CQE_SWCQE_S)
 
+#define CQE_DRAIN_S       10
+#define CQE_DRAIN_M       0x1
+#define CQE_DRAIN_G(x)    ((((x) >> CQE_DRAIN_S)) & CQE_DRAIN_M)
+#define CQE_DRAIN_V(x)	  ((x)<<CQE_DRAIN_S)
+
 #define CQE_STATUS_S      5
 #define CQE_STATUS_M      0x1F
 #define CQE_STATUS_G(x)   ((((x) >> CQE_STATUS_S)) & CQE_STATUS_M)
@@ -213,6 +218,7 @@ struct t4_cqe {
 #define CQE_OPCODE_V(x)   ((x)<<CQE_OPCODE_S)
 
 #define SW_CQE(x)         (CQE_SWCQE_G(be32_to_cpu((x)->header)))
+#define DRAIN_CQE(x)      (CQE_DRAIN_G(be32_to_cpu((x)->header)))
 #define CQE_QPID(x)       (CQE_QPID_G(be32_to_cpu((x)->header)))
 #define CQE_TYPE(x)       (CQE_TYPE_G(be32_to_cpu((x)->header)))
 #define SQ_TYPE(x)	  (CQE_TYPE((x)))
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 4a9b4d7efe63..8ce9118d4a7f 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1131,7 +1131,6 @@ struct hfi1_devdata {
 	u16 pcie_lnkctl;
 	u16 pcie_devctl2;
 	u32 pci_msix0;
-	u32 pci_lnkctl3;
 	u32 pci_tph2;
 
 	/*
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 09e50fd2a08f..8c7e7a60b715 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -411,15 +411,12 @@ int restore_pci_variables(struct hfi1_devdata *dd)
 	if (ret)
 		goto error;
 
-	ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
-				     dd->pci_lnkctl3);
-	if (ret)
-		goto error;
-
-	ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2);
-	if (ret)
-		goto error;
-
+	if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+		ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+					     dd->pci_tph2);
+		if (ret)
+			goto error;
+	}
 	return 0;
 
 error:
@@ -469,15 +466,12 @@ int save_pci_variables(struct hfi1_devdata *dd)
 	if (ret)
 		goto error;
 
-	ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
-				    &dd->pci_lnkctl3);
-	if (ret)
-		goto error;
-
-	ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2);
-	if (ret)
-		goto error;
-
+	if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+		ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+					    &dd->pci_tph2);
+		if (ret)
+			goto error;
+	}
 	return 0;
 
 error:
diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index 470995fa38d2..6f6712f87a73 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -47,17 +47,6 @@ int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey)
 	return err;
 }
 
-int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
-				bool reset, void *out, int out_size)
-{
-	u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { };
-
-	MLX5_SET(query_cong_statistics_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_CONG_STATISTICS);
-	MLX5_SET(query_cong_statistics_in, in, clear, reset);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
-}
-
 int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
 			       void *out, int out_size)
 {
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index af4c24596274..78ffded7cc2c 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -37,8 +37,6 @@
 #include <linux/mlx5/driver.h>
 
 int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey);
-int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
-				bool reset, void *out, int out_size);
 int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
 			       void *out, int out_size);
 int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *mdev,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 543d0a4c8bf3..8ac50de2b242 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1463,6 +1463,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	}
 
 	INIT_LIST_HEAD(&context->vma_private_list);
+	mutex_init(&context->vma_private_list_mutex);
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
 
@@ -1624,7 +1625,9 @@ static void  mlx5_ib_vma_close(struct vm_area_struct *area)
 	 * mlx5_ib_disassociate_ucontext().
 	 */
 	mlx5_ib_vma_priv_data->vma = NULL;
+	mutex_lock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
 	list_del(&mlx5_ib_vma_priv_data->list);
+	mutex_unlock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
 	kfree(mlx5_ib_vma_priv_data);
 }
 
@@ -1644,10 +1647,13 @@ static int mlx5_ib_set_vma_data(struct vm_area_struct *vma,
 		return -ENOMEM;
 
 	vma_prv->vma = vma;
+	vma_prv->vma_private_list_mutex = &ctx->vma_private_list_mutex;
 	vma->vm_private_data = vma_prv;
 	vma->vm_ops =  &mlx5_ib_vm_ops;
 
+	mutex_lock(&ctx->vma_private_list_mutex);
 	list_add(&vma_prv->list, vma_head);
+	mutex_unlock(&ctx->vma_private_list_mutex);
 
 	return 0;
 }
@@ -1690,6 +1696,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 	 * mlx5_ib_vma_close.
 	 */
 	down_write(&owning_mm->mmap_sem);
+	mutex_lock(&context->vma_private_list_mutex);
 	list_for_each_entry_safe(vma_private, n, &context->vma_private_list,
 				 list) {
 		vma = vma_private->vma;
@@ -1704,6 +1711,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 		list_del(&vma_private->list);
 		kfree(vma_private);
 	}
+	mutex_unlock(&context->vma_private_list_mutex);
 	up_write(&owning_mm->mmap_sem);
 	mmput(owning_mm);
 	put_task_struct(owning_process);
@@ -3737,34 +3745,6 @@ free:
 	return ret;
 }
 
-static int mlx5_ib_query_cong_counters(struct mlx5_ib_dev *dev,
-				       struct mlx5_ib_port *port,
-				       struct rdma_hw_stats *stats)
-{
-	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
-	void *out;
-	int ret, i;
-	int offset = port->cnts.num_q_counters;
-
-	out = kvzalloc(outlen, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	ret = mlx5_cmd_query_cong_counter(dev->mdev, false, out, outlen);
-	if (ret)
-		goto free;
-
-	for (i = 0; i < port->cnts.num_cong_counters; i++) {
-		stats->value[i + offset] =
-			be64_to_cpup((__be64 *)(out +
-				     port->cnts.offsets[i + offset]));
-	}
-
-free:
-	kvfree(out);
-	return ret;
-}
-
 static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 				struct rdma_hw_stats *stats,
 				u8 port_num, int index)
@@ -3782,7 +3762,12 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev,
 	num_counters = port->cnts.num_q_counters;
 
 	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
-		ret = mlx5_ib_query_cong_counters(dev, port, stats);
+		ret = mlx5_lag_query_cong_counters(dev->mdev,
+						   stats->value +
+						   port->cnts.num_q_counters,
+						   port->cnts.num_cong_counters,
+						   port->cnts.offsets +
+						   port->cnts.num_q_counters);
 		if (ret)
 			return ret;
 		num_counters += port->cnts.num_cong_counters;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 6dd8cac78de2..2c5f3533bbc9 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -115,6 +115,8 @@ enum {
 struct mlx5_ib_vma_private_data {
 	struct list_head list;
 	struct vm_area_struct *vma;
+	/* protect vma_private_list add/del */
+	struct mutex *vma_private_list_mutex;
 };
 
 struct mlx5_ib_ucontext {
@@ -129,6 +131,8 @@ struct mlx5_ib_ucontext {
 	/* Transport Domain number */
 	u32			tdn;
 	struct list_head	vma_private_list;
+	/* protect vma_private_list add/del */
+	struct mutex		vma_private_list_mutex;
 
 	unsigned long		upd_xlt_page;
 	/* protect ODP/KSM */
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index ee0ee1f9994b..d109fe8290a7 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1637,6 +1637,7 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
 	MLX5_SET(mkc, mkc, access_mode, mr->access_mode);
 	MLX5_SET(mkc, mkc, umr_en, 1);
 
+	mr->ibmr.device = pd->device;
 	err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen);
 	if (err)
 		goto err_destroy_psv;
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
index 63bc2efc34eb..4f7bd3b6a315 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h
@@ -94,7 +94,7 @@ struct pvrdma_cq {
 	u32 cq_handle;
 	bool is_kernel;
 	atomic_t refcnt;
-	wait_queue_head_t wait;
+	struct completion free;
 };
 
 struct pvrdma_id_table {
@@ -175,7 +175,7 @@ struct pvrdma_srq {
 	u32 srq_handle;
 	int npages;
 	refcount_t refcnt;
-	wait_queue_head_t wait;
+	struct completion free;
 };
 
 struct pvrdma_qp {
@@ -197,7 +197,7 @@ struct pvrdma_qp {
 	bool is_kernel;
 	struct mutex mutex; /* QP state mutex. */
 	atomic_t refcnt;
-	wait_queue_head_t wait;
+	struct completion free;
 };
 
 struct pvrdma_dev {
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
index 3562c0c30492..e529622cefad 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
@@ -179,7 +179,7 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev,
 		pvrdma_page_dir_insert_umem(&cq->pdir, cq->umem, 0);
 
 	atomic_set(&cq->refcnt, 1);
-	init_waitqueue_head(&cq->wait);
+	init_completion(&cq->free);
 	spin_lock_init(&cq->cq_lock);
 
 	memset(cmd, 0, sizeof(*cmd));
@@ -230,8 +230,9 @@ err_cq:
 
 static void pvrdma_free_cq(struct pvrdma_dev *dev, struct pvrdma_cq *cq)
 {
-	atomic_dec(&cq->refcnt);
-	wait_event(cq->wait, !atomic_read(&cq->refcnt));
+	if (atomic_dec_and_test(&cq->refcnt))
+		complete(&cq->free);
+	wait_for_completion(&cq->free);
 
 	if (!cq->is_kernel)
 		ib_umem_release(cq->umem);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 1f4e18717a00..e92681878c93 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -346,9 +346,8 @@ static void pvrdma_qp_event(struct pvrdma_dev *dev, u32 qpn, int type)
 		ibqp->event_handler(&e, ibqp->qp_context);
 	}
 	if (qp) {
-		atomic_dec(&qp->refcnt);
-		if (atomic_read(&qp->refcnt) == 0)
-			wake_up(&qp->wait);
+		if (atomic_dec_and_test(&qp->refcnt))
+			complete(&qp->free);
 	}
 }
 
@@ -373,9 +372,8 @@ static void pvrdma_cq_event(struct pvrdma_dev *dev, u32 cqn, int type)
 		ibcq->event_handler(&e, ibcq->cq_context);
 	}
 	if (cq) {
-		atomic_dec(&cq->refcnt);
-		if (atomic_read(&cq->refcnt) == 0)
-			wake_up(&cq->wait);
+		if (atomic_dec_and_test(&cq->refcnt))
+			complete(&cq->free);
 	}
 }
 
@@ -404,7 +402,7 @@ static void pvrdma_srq_event(struct pvrdma_dev *dev, u32 srqn, int type)
 	}
 	if (srq) {
 		if (refcount_dec_and_test(&srq->refcnt))
-			wake_up(&srq->wait);
+			complete(&srq->free);
 	}
 }
 
@@ -539,9 +537,8 @@ static irqreturn_t pvrdma_intrx_handler(int irq, void *dev_id)
 		if (cq && cq->ibcq.comp_handler)
 			cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
 		if (cq) {
-			atomic_dec(&cq->refcnt);
-			if (atomic_read(&cq->refcnt))
-				wake_up(&cq->wait);
+			if (atomic_dec_and_test(&cq->refcnt))
+				complete(&cq->free);
 		}
 		pvrdma_idx_ring_inc(&ring->cons_head, ring_slots);
 	}
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
index 10420a18d02f..4059308e1454 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c
@@ -246,7 +246,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 		spin_lock_init(&qp->rq.lock);
 		mutex_init(&qp->mutex);
 		atomic_set(&qp->refcnt, 1);
-		init_waitqueue_head(&qp->wait);
+		init_completion(&qp->free);
 
 		qp->state = IB_QPS_RESET;
 
@@ -428,8 +428,16 @@ static void pvrdma_free_qp(struct pvrdma_qp *qp)
 
 	pvrdma_unlock_cqs(scq, rcq, &scq_flags, &rcq_flags);
 
-	atomic_dec(&qp->refcnt);
-	wait_event(qp->wait, !atomic_read(&qp->refcnt));
+	if (atomic_dec_and_test(&qp->refcnt))
+		complete(&qp->free);
+	wait_for_completion(&qp->free);
+
+	if (!qp->is_kernel) {
+		if (qp->rumem)
+			ib_umem_release(qp->rumem);
+		if (qp->sumem)
+			ib_umem_release(qp->sumem);
+	}
 
 	pvrdma_page_dir_cleanup(dev, &qp->pdir);
 
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
index 826ccb864596..5acebb1ef631 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
@@ -149,7 +149,7 @@ struct ib_srq *pvrdma_create_srq(struct ib_pd *pd,
 
 	spin_lock_init(&srq->lock);
 	refcount_set(&srq->refcnt, 1);
-	init_waitqueue_head(&srq->wait);
+	init_completion(&srq->free);
 
 	dev_dbg(&dev->pdev->dev,
 		"create shared receive queue from user space\n");
@@ -236,8 +236,9 @@ static void pvrdma_free_srq(struct pvrdma_dev *dev, struct pvrdma_srq *srq)
 	dev->srq_tbl[srq->srq_handle] = NULL;
 	spin_unlock_irqrestore(&dev->srq_tbl_lock, flags);
 
-	refcount_dec(&srq->refcnt);
-	wait_event(srq->wait, !refcount_read(&srq->refcnt));
+	if (refcount_dec_and_test(&srq->refcnt))
+		complete(&srq->free);
+	wait_for_completion(&srq->free);
 
 	/* There is no support for kernel clients, so this is safe. */
 	ib_umem_release(srq->umem);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 3b96cdaf9a83..e6151a29c412 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -1236,13 +1236,10 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 		ipoib_ib_dev_down(dev);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
-		rtnl_lock();
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 			ipoib_ib_dev_stop(dev);
 
-		result = ipoib_ib_dev_open(dev);
-		rtnl_unlock();
-		if (result)
+		if (ipoib_ib_dev_open(dev))
 			return;
 
 		if (netif_queue_stopped(dev))
@@ -1282,7 +1279,9 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work)
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_heavy);
 
+	rtnl_lock();
 	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0);
+	rtnl_unlock();
 }
 
 void ipoib_ib_dev_cleanup(struct net_device *dev)
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index fd83c7f77a95..f3654fd2eaf3 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -186,7 +186,7 @@ void led_blink_set(struct led_classdev *led_cdev,
 		   unsigned long *delay_on,
 		   unsigned long *delay_off)
 {
-	del_timer_sync(&led_cdev->blink_timer);
+	led_stop_software_blink(led_cdev);
 
 	clear_bit(LED_BLINK_ONESHOT, &led_cdev->work_flags);
 	clear_bit(LED_BLINK_ONESHOT_STOP, &led_cdev->work_flags);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 01b7f2fc249c..57eb26dfc059 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3029,7 +3029,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
 
 	del_timer_sync(&bp->timer);
 
-	if (IS_PF(bp)) {
+	if (IS_PF(bp) && !BP_NOMCP(bp)) {
 		/* Set ALWAYS_ALIVE bit in shmem */
 		bp->fw_drv_pulse_wr_seq |= DRV_PULSE_ALWAYS_ALIVE;
 		bnx2x_drv_pulse(bp);
@@ -3115,7 +3115,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
 	bp->cnic_loaded = false;
 
 	/* Clear driver version indication in shmem */
-	if (IS_PF(bp))
+	if (IS_PF(bp) && !BP_NOMCP(bp))
 		bnx2x_update_mng_version(bp);
 
 	/* Check if there are pending parity attentions. If there are - set
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 4d0654813de1..7b08323e3f3d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9578,6 +9578,15 @@ static int bnx2x_init_shmem(struct bnx2x *bp)
 
 	do {
 		bp->common.shmem_base = REG_RD(bp, MISC_REG_SHARED_MEM_ADDR);
+
+		/* If we read all 0xFFs, means we are in PCI error state and
+		 * should bail out to avoid crashes on adapter's FW reads.
+		 */
+		if (bp->common.shmem_base == 0xFFFFFFFF) {
+			bp->flags |= NO_MCP_FLAG;
+			return -ENODEV;
+		}
+
 		if (bp->common.shmem_base) {
 			val = SHMEM_RD(bp, validity_map[BP_PORT(bp)]);
 			if (val & SHR_MEM_VALIDITY_MB)
@@ -14322,7 +14331,10 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev)
 		BNX2X_ERR("IO slot reset --> driver unload\n");
 
 		/* MCP should have been reset; Need to wait for validity */
-		bnx2x_init_shmem(bp);
+		if (bnx2x_init_shmem(bp)) {
+			rtnl_unlock();
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
 
 		if (IS_PF(bp) && SHMEM2_HAS(bp, drv_capabilities_flag)) {
 			u32 v;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index d09c5a9c53b5..8995cfefbfcf 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -4,11 +4,13 @@
  * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com)
  * Copyright (C) 2001, 2002, 2003 Jeff Garzik (jgarzik@pobox.com)
  * Copyright (C) 2004 Sun Microsystems Inc.
- * Copyright (C) 2005-2014 Broadcom Corporation.
+ * Copyright (C) 2005-2016 Broadcom Corporation.
+ * Copyright (C) 2016-2017 Broadcom Limited.
  *
  * Firmware is:
  *	Derived from proprietary unpublished source code,
- *	Copyright (C) 2000-2003 Broadcom Corporation.
+ *	Copyright (C) 2000-2016 Broadcom Corporation.
+ *	Copyright (C) 2016-2017 Broadcom Ltd.
  *
  *	Permission is hereby granted for the distribution of this firmware
  *	data in hexadecimal or equivalent format, provided this copyright
@@ -10052,6 +10054,16 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy)
 
 	tw32(GRC_MODE, tp->grc_mode | val);
 
+	/* On one of the AMD platform, MRRS is restricted to 4000 because of
+	 * south bridge limitation. As a workaround, Driver is setting MRRS
+	 * to 2048 instead of default 4096.
+	 */
+	if (tp->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL &&
+	    tp->pdev->subsystem_device == TG3PCI_SUBDEVICE_ID_DELL_5762) {
+		val = tr32(TG3PCI_DEV_STATUS_CTRL) & ~MAX_READ_REQ_MASK;
+		tw32(TG3PCI_DEV_STATUS_CTRL, val | MAX_READ_REQ_SIZE_2048);
+	}
+
 	/* Setup the timer prescalar register.  Clock is always 66Mhz. */
 	val = tr32(GRC_MISC_CFG);
 	val &= ~0xff;
@@ -14227,7 +14239,8 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 	 */
 	if (tg3_asic_rev(tp) == ASIC_REV_57766 ||
 	    tg3_asic_rev(tp) == ASIC_REV_5717 ||
-	    tg3_asic_rev(tp) == ASIC_REV_5719)
+	    tg3_asic_rev(tp) == ASIC_REV_5719 ||
+	    tg3_asic_rev(tp) == ASIC_REV_5720)
 		reset_phy = true;
 
 	err = tg3_restart_hw(tp, reset_phy);
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index c2d02d02d1e6..1f0271fa7c74 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -5,7 +5,8 @@
  * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com)
  * Copyright (C) 2001 Jeff Garzik (jgarzik@pobox.com)
  * Copyright (C) 2004 Sun Microsystems Inc.
- * Copyright (C) 2007-2014 Broadcom Corporation.
+ * Copyright (C) 2007-2016 Broadcom Corporation.
+ * Copyright (C) 2016-2017 Broadcom Limited.
  */
 
 #ifndef _T3_H
@@ -96,6 +97,7 @@
 #define TG3PCI_SUBDEVICE_ID_DELL_JAGUAR		0x0106
 #define TG3PCI_SUBDEVICE_ID_DELL_MERLOT		0x0109
 #define TG3PCI_SUBDEVICE_ID_DELL_SLIM_MERLOT	0x010a
+#define TG3PCI_SUBDEVICE_ID_DELL_5762		0x07f0
 #define TG3PCI_SUBVENDOR_ID_COMPAQ		PCI_VENDOR_ID_COMPAQ
 #define TG3PCI_SUBDEVICE_ID_COMPAQ_BANSHEE	0x007c
 #define TG3PCI_SUBDEVICE_ID_COMPAQ_BANSHEE_2	0x009a
@@ -281,6 +283,9 @@
 #define TG3PCI_STD_RING_PROD_IDX	0x00000098 /* 64-bit */
 #define TG3PCI_RCV_RET_RING_CON_IDX	0x000000a0 /* 64-bit */
 /* 0xa8 --> 0xb8 unused */
+#define TG3PCI_DEV_STATUS_CTRL		0x000000b4
+#define  MAX_READ_REQ_SIZE_2048		 0x00004000
+#define  MAX_READ_REQ_MASK		 0x00007000
 #define TG3PCI_DUAL_MAC_CTRL		0x000000b8
 #define  DUAL_MAC_CTRL_CH_MASK		 0x00000003
 #define  DUAL_MAC_CTRL_ID		 0x00000004
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2d1b06579c1a..e17d10b8b041 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -818,6 +818,12 @@ static void fec_enet_bd_init(struct net_device *dev)
 		for (i = 0; i < txq->bd.ring_size; i++) {
 			/* Initialize the BD for every fragment in the page. */
 			bdp->cbd_sc = cpu_to_fec16(0);
+			if (bdp->cbd_bufaddr &&
+			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
 			if (txq->tx_skbuff[i]) {
 				dev_kfree_skb_any(txq->tx_skbuff[i]);
 				txq->tx_skbuff[i] = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index f26f97fe4666..582b2f18010a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -137,6 +137,17 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag);
 
+static int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
+				       bool reset, void *out, int out_size)
+{
+	u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { };
+
+	MLX5_SET(query_cong_statistics_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_CONG_STATISTICS);
+	MLX5_SET(query_cong_statistics_in, in, clear, reset);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
+}
+
 static struct mlx5_lag *mlx5_lag_dev_get(struct mlx5_core_dev *dev)
 {
 	return dev->priv.lag;
@@ -633,3 +644,48 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	/* If bonded, we do not add an IB device for PF1. */
 	return false;
 }
+
+int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
+				 u64 *values,
+				 int num_counters,
+				 size_t *offsets)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
+	struct mlx5_core_dev *mdev[MLX5_MAX_PORTS];
+	struct mlx5_lag *ldev;
+	int num_ports;
+	int ret, i, j;
+	void *out;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	memset(values, 0, sizeof(*values) * num_counters);
+
+	mutex_lock(&lag_mutex);
+	ldev = mlx5_lag_dev_get(dev);
+	if (ldev && mlx5_lag_is_bonded(ldev)) {
+		num_ports = MLX5_MAX_PORTS;
+		mdev[0] = ldev->pf[0].dev;
+		mdev[1] = ldev->pf[1].dev;
+	} else {
+		num_ports = 1;
+		mdev[0] = dev;
+	}
+
+	for (i = 0; i < num_ports; ++i) {
+		ret = mlx5_cmd_query_cong_counter(mdev[i], false, out, outlen);
+		if (ret)
+			goto unlock;
+
+		for (j = 0; j < num_counters; ++j)
+			values[j] += be64_to_cpup((__be64 *)(out + offsets[j]));
+	}
+
+unlock:
+	mutex_unlock(&lag_mutex);
+	kvfree(out);
+	return ret;
+}
+EXPORT_SYMBOL(mlx5_lag_query_cong_counters);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index fd500b18e77f..0f45310300f6 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -624,6 +624,7 @@ static int ksz9031_read_status(struct phy_device *phydev)
 		phydev->link = 0;
 		if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
 			phydev->drv->config_intr(phydev);
+		return genphy_config_aneg(phydev);
 	}
 
 	return 0;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 2ec140ec7923..82166a26f5c6 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -567,6 +567,7 @@ struct phylink *phylink_create(struct net_device *ndev,
 	pl->link_config.pause = MLO_PAUSE_AN;
 	pl->link_config.speed = SPEED_UNKNOWN;
 	pl->link_config.duplex = DUPLEX_UNKNOWN;
+	pl->link_config.an_enabled = true;
 	pl->ops = ops;
 	__set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
 
@@ -1139,6 +1140,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 	mutex_lock(&pl->state_mutex);
 	/* Configure the MAC to match the new settings */
 	linkmode_copy(pl->link_config.advertising, our_kset.link_modes.advertising);
+	pl->link_config.interface = config.interface;
 	pl->link_config.speed = our_kset.base.speed;
 	pl->link_config.duplex = our_kset.base.duplex;
 	pl->link_config.an_enabled = our_kset.base.autoneg != AUTONEG_DISABLE;
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index e949e3302af4..c586bcdb5190 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -211,12 +211,12 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping,
 	return ret;
 }
 
-static int btt_log_read_pair(struct arena_info *arena, u32 lane,
-			struct log_entry *ent)
+static int btt_log_group_read(struct arena_info *arena, u32 lane,
+			struct log_group *log)
 {
 	return arena_read_bytes(arena,
-			arena->logoff + (2 * lane * LOG_ENT_SIZE), ent,
-			2 * LOG_ENT_SIZE, 0);
+			arena->logoff + (lane * LOG_GRP_SIZE), log,
+			LOG_GRP_SIZE, 0);
 }
 
 static struct dentry *debugfs_root;
@@ -256,6 +256,8 @@ static void arena_debugfs_init(struct arena_info *a, struct dentry *parent,
 	debugfs_create_x64("logoff", S_IRUGO, d, &a->logoff);
 	debugfs_create_x64("info2off", S_IRUGO, d, &a->info2off);
 	debugfs_create_x32("flags", S_IRUGO, d, &a->flags);
+	debugfs_create_u32("log_index_0", S_IRUGO, d, &a->log_index[0]);
+	debugfs_create_u32("log_index_1", S_IRUGO, d, &a->log_index[1]);
 }
 
 static void btt_debugfs_init(struct btt *btt)
@@ -274,6 +276,11 @@ static void btt_debugfs_init(struct btt *btt)
 	}
 }
 
+static u32 log_seq(struct log_group *log, int log_idx)
+{
+	return le32_to_cpu(log->ent[log_idx].seq);
+}
+
 /*
  * This function accepts two log entries, and uses the
  * sequence number to find the 'older' entry.
@@ -283,8 +290,10 @@ static void btt_debugfs_init(struct btt *btt)
  *
  * TODO The logic feels a bit kludge-y. make it better..
  */
-static int btt_log_get_old(struct log_entry *ent)
+static int btt_log_get_old(struct arena_info *a, struct log_group *log)
 {
+	int idx0 = a->log_index[0];
+	int idx1 = a->log_index[1];
 	int old;
 
 	/*
@@ -292,23 +301,23 @@ static int btt_log_get_old(struct log_entry *ent)
 	 * the next time, the following logic works out to put this
 	 * (next) entry into [1]
 	 */
-	if (ent[0].seq == 0) {
-		ent[0].seq = cpu_to_le32(1);
+	if (log_seq(log, idx0) == 0) {
+		log->ent[idx0].seq = cpu_to_le32(1);
 		return 0;
 	}
 
-	if (ent[0].seq == ent[1].seq)
+	if (log_seq(log, idx0) == log_seq(log, idx1))
 		return -EINVAL;
-	if (le32_to_cpu(ent[0].seq) + le32_to_cpu(ent[1].seq) > 5)
+	if (log_seq(log, idx0) + log_seq(log, idx1) > 5)
 		return -EINVAL;
 
-	if (le32_to_cpu(ent[0].seq) < le32_to_cpu(ent[1].seq)) {
-		if (le32_to_cpu(ent[1].seq) - le32_to_cpu(ent[0].seq) == 1)
+	if (log_seq(log, idx0) < log_seq(log, idx1)) {
+		if ((log_seq(log, idx1) - log_seq(log, idx0)) == 1)
 			old = 0;
 		else
 			old = 1;
 	} else {
-		if (le32_to_cpu(ent[0].seq) - le32_to_cpu(ent[1].seq) == 1)
+		if ((log_seq(log, idx0) - log_seq(log, idx1)) == 1)
 			old = 1;
 		else
 			old = 0;
@@ -328,17 +337,18 @@ static int btt_log_read(struct arena_info *arena, u32 lane,
 {
 	int ret;
 	int old_ent, ret_ent;
-	struct log_entry log[2];
+	struct log_group log;
 
-	ret = btt_log_read_pair(arena, lane, log);
+	ret = btt_log_group_read(arena, lane, &log);
 	if (ret)
 		return -EIO;
 
-	old_ent = btt_log_get_old(log);
+	old_ent = btt_log_get_old(arena, &log);
 	if (old_ent < 0 || old_ent > 1) {
 		dev_err(to_dev(arena),
 				"log corruption (%d): lane %d seq [%d, %d]\n",
-			old_ent, lane, log[0].seq, log[1].seq);
+				old_ent, lane, log.ent[arena->log_index[0]].seq,
+				log.ent[arena->log_index[1]].seq);
 		/* TODO set error state? */
 		return -EIO;
 	}
@@ -346,7 +356,7 @@ static int btt_log_read(struct arena_info *arena, u32 lane,
 	ret_ent = (old_flag ? old_ent : (1 - old_ent));
 
 	if (ent != NULL)
-		memcpy(ent, &log[ret_ent], LOG_ENT_SIZE);
+		memcpy(ent, &log.ent[arena->log_index[ret_ent]], LOG_ENT_SIZE);
 
 	return ret_ent;
 }
@@ -360,17 +370,13 @@ static int __btt_log_write(struct arena_info *arena, u32 lane,
 			u32 sub, struct log_entry *ent, unsigned long flags)
 {
 	int ret;
-	/*
-	 * Ignore the padding in log_entry for calculating log_half.
-	 * The entry is 'committed' when we write the sequence number,
-	 * and we want to ensure that that is the last thing written.
-	 * We don't bother writing the padding as that would be extra
-	 * media wear and write amplification
-	 */
-	unsigned int log_half = (LOG_ENT_SIZE - 2 * sizeof(u64)) / 2;
-	u64 ns_off = arena->logoff + (((2 * lane) + sub) * LOG_ENT_SIZE);
+	u32 group_slot = arena->log_index[sub];
+	unsigned int log_half = LOG_ENT_SIZE / 2;
 	void *src = ent;
+	u64 ns_off;
 
+	ns_off = arena->logoff + (lane * LOG_GRP_SIZE) +
+		(group_slot * LOG_ENT_SIZE);
 	/* split the 16B write into atomic, durable halves */
 	ret = arena_write_bytes(arena, ns_off, src, log_half, flags);
 	if (ret)
@@ -453,7 +459,7 @@ static int btt_log_init(struct arena_info *arena)
 {
 	size_t logsize = arena->info2off - arena->logoff;
 	size_t chunk_size = SZ_4K, offset = 0;
-	struct log_entry log;
+	struct log_entry ent;
 	void *zerobuf;
 	int ret;
 	u32 i;
@@ -485,11 +491,11 @@ static int btt_log_init(struct arena_info *arena)
 	}
 
 	for (i = 0; i < arena->nfree; i++) {
-		log.lba = cpu_to_le32(i);
-		log.old_map = cpu_to_le32(arena->external_nlba + i);
-		log.new_map = cpu_to_le32(arena->external_nlba + i);
-		log.seq = cpu_to_le32(LOG_SEQ_INIT);
-		ret = __btt_log_write(arena, i, 0, &log, 0);
+		ent.lba = cpu_to_le32(i);
+		ent.old_map = cpu_to_le32(arena->external_nlba + i);
+		ent.new_map = cpu_to_le32(arena->external_nlba + i);
+		ent.seq = cpu_to_le32(LOG_SEQ_INIT);
+		ret = __btt_log_write(arena, i, 0, &ent, 0);
 		if (ret)
 			goto free;
 	}
@@ -594,6 +600,123 @@ static int btt_freelist_init(struct arena_info *arena)
 	return 0;
 }
 
+static bool ent_is_padding(struct log_entry *ent)
+{
+	return (ent->lba == 0) && (ent->old_map == 0) && (ent->new_map == 0)
+		&& (ent->seq == 0);
+}
+
+/*
+ * Detecting valid log indices: We read a log group (see the comments in btt.h
+ * for a description of a 'log_group' and its 'slots'), and iterate over its
+ * four slots. We expect that a padding slot will be all-zeroes, and use this
+ * to detect a padding slot vs. an actual entry.
+ *
+ * If a log_group is in the initial state, i.e. hasn't been used since the
+ * creation of this BTT layout, it will have three of the four slots with
+ * zeroes. We skip over these log_groups for the detection of log_index. If
+ * all log_groups are in the initial state (i.e. the BTT has never been
+ * written to), it is safe to assume the 'new format' of log entries in slots
+ * (0, 1).
+ */
+static int log_set_indices(struct arena_info *arena)
+{
+	bool idx_set = false, initial_state = true;
+	int ret, log_index[2] = {-1, -1};
+	u32 i, j, next_idx = 0;
+	struct log_group log;
+	u32 pad_count = 0;
+
+	for (i = 0; i < arena->nfree; i++) {
+		ret = btt_log_group_read(arena, i, &log);
+		if (ret < 0)
+			return ret;
+
+		for (j = 0; j < 4; j++) {
+			if (!idx_set) {
+				if (ent_is_padding(&log.ent[j])) {
+					pad_count++;
+					continue;
+				} else {
+					/* Skip if index has been recorded */
+					if ((next_idx == 1) &&
+						(j == log_index[0]))
+						continue;
+					/* valid entry, record index */
+					log_index[next_idx] = j;
+					next_idx++;
+				}
+				if (next_idx == 2) {
+					/* two valid entries found */
+					idx_set = true;
+				} else if (next_idx > 2) {
+					/* too many valid indices */
+					return -ENXIO;
+				}
+			} else {
+				/*
+				 * once the indices have been set, just verify
+				 * that all subsequent log groups are either in
+				 * their initial state or follow the same
+				 * indices.
+				 */
+				if (j == log_index[0]) {
+					/* entry must be 'valid' */
+					if (ent_is_padding(&log.ent[j]))
+						return -ENXIO;
+				} else if (j == log_index[1]) {
+					;
+					/*
+					 * log_index[1] can be padding if the
+					 * lane never got used and it is still
+					 * in the initial state (three 'padding'
+					 * entries)
+					 */
+				} else {
+					/* entry must be invalid (padding) */
+					if (!ent_is_padding(&log.ent[j]))
+						return -ENXIO;
+				}
+			}
+		}
+		/*
+		 * If any of the log_groups have more than one valid,
+		 * non-padding entry, then the we are no longer in the
+		 * initial_state
+		 */
+		if (pad_count < 3)
+			initial_state = false;
+		pad_count = 0;
+	}
+
+	if (!initial_state && !idx_set)
+		return -ENXIO;
+
+	/*
+	 * If all the entries in the log were in the initial state,
+	 * assume new padding scheme
+	 */
+	if (initial_state)
+		log_index[1] = 1;
+
+	/*
+	 * Only allow the known permutations of log/padding indices,
+	 * i.e. (0, 1), and (0, 2)
+	 */
+	if ((log_index[0] == 0) && ((log_index[1] == 1) || (log_index[1] == 2)))
+		; /* known index possibilities */
+	else {
+		dev_err(to_dev(arena), "Found an unknown padding scheme\n");
+		return -ENXIO;
+	}
+
+	arena->log_index[0] = log_index[0];
+	arena->log_index[1] = log_index[1];
+	dev_dbg(to_dev(arena), "log_index_0 = %d\n", log_index[0]);
+	dev_dbg(to_dev(arena), "log_index_1 = %d\n", log_index[1]);
+	return 0;
+}
+
 static int btt_rtt_init(struct arena_info *arena)
 {
 	arena->rtt = kcalloc(arena->nfree, sizeof(u32), GFP_KERNEL);
@@ -650,8 +773,7 @@ static struct arena_info *alloc_arena(struct btt *btt, size_t size,
 	available -= 2 * BTT_PG_SIZE;
 
 	/* The log takes a fixed amount of space based on nfree */
-	logsize = roundup(2 * arena->nfree * sizeof(struct log_entry),
-				BTT_PG_SIZE);
+	logsize = roundup(arena->nfree * LOG_GRP_SIZE, BTT_PG_SIZE);
 	available -= logsize;
 
 	/* Calculate optimal split between map and data area */
@@ -668,6 +790,10 @@ static struct arena_info *alloc_arena(struct btt *btt, size_t size,
 	arena->mapoff = arena->dataoff + datasize;
 	arena->logoff = arena->mapoff + mapsize;
 	arena->info2off = arena->logoff + logsize;
+
+	/* Default log indices are (0,1) */
+	arena->log_index[0] = 0;
+	arena->log_index[1] = 1;
 	return arena;
 }
 
@@ -758,6 +884,13 @@ static int discover_arenas(struct btt *btt)
 		arena->external_lba_start = cur_nlba;
 		parse_arena_meta(arena, super, cur_off);
 
+		ret = log_set_indices(arena);
+		if (ret) {
+			dev_err(to_dev(arena),
+				"Unable to deduce log/padding indices\n");
+			goto out;
+		}
+
 		mutex_init(&arena->err_lock);
 		ret = btt_freelist_init(arena);
 		if (ret)
diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h
index 578c2057524d..db3cb6d4d0d4 100644
--- a/drivers/nvdimm/btt.h
+++ b/drivers/nvdimm/btt.h
@@ -27,6 +27,7 @@
 #define MAP_ERR_MASK (1 << MAP_ERR_SHIFT)
 #define MAP_LBA_MASK (~((1 << MAP_TRIM_SHIFT) | (1 << MAP_ERR_SHIFT)))
 #define MAP_ENT_NORMAL 0xC0000000
+#define LOG_GRP_SIZE sizeof(struct log_group)
 #define LOG_ENT_SIZE sizeof(struct log_entry)
 #define ARENA_MIN_SIZE (1UL << 24)	/* 16 MB */
 #define ARENA_MAX_SIZE (1ULL << 39)	/* 512 GB */
@@ -50,12 +51,52 @@ enum btt_init_state {
 	INIT_READY
 };
 
+/*
+ * A log group represents one log 'lane', and consists of four log entries.
+ * Two of the four entries are valid entries, and the remaining two are
+ * padding. Due to an old bug in the padding location, we need to perform a
+ * test to determine the padding scheme being used, and use that scheme
+ * thereafter.
+ *
+ * In kernels prior to 4.15, 'log group' would have actual log entries at
+ * indices (0, 2) and padding at indices (1, 3), where as the correct/updated
+ * format has log entries at indices (0, 1) and padding at indices (2, 3).
+ *
+ * Old (pre 4.15) format:
+ * +-----------------+-----------------+
+ * |      ent[0]     |      ent[1]     |
+ * |       16B       |       16B       |
+ * | lba/old/new/seq |       pad       |
+ * +-----------------------------------+
+ * |      ent[2]     |      ent[3]     |
+ * |       16B       |       16B       |
+ * | lba/old/new/seq |       pad       |
+ * +-----------------+-----------------+
+ *
+ * New format:
+ * +-----------------+-----------------+
+ * |      ent[0]     |      ent[1]     |
+ * |       16B       |       16B       |
+ * | lba/old/new/seq | lba/old/new/seq |
+ * +-----------------------------------+
+ * |      ent[2]     |      ent[3]     |
+ * |       16B       |       16B       |
+ * |       pad       |       pad       |
+ * +-----------------+-----------------+
+ *
+ * We detect during start-up which format is in use, and set
+ * arena->log_index[(0, 1)] with the detected format.
+ */
+
 struct log_entry {
 	__le32 lba;
 	__le32 old_map;
 	__le32 new_map;
 	__le32 seq;
-	__le64 padding[2];
+};
+
+struct log_group {
+	struct log_entry ent[4];
 };
 
 struct btt_sb {
@@ -125,6 +166,8 @@ struct aligned_lock {
  * @list:		List head for list of arenas
  * @debugfs_dir:	Debugfs dentry
  * @flags:		Arena flags - may signify error states.
+ * @err_lock:		Mutex for synchronizing error clearing.
+ * @log_index:		Indices of the valid log entries in a log_group
  *
  * arena_info is a per-arena handle. Once an arena is narrowed down for an
  * IO, this struct is passed around for the duration of the IO.
@@ -157,6 +200,7 @@ struct arena_info {
 	/* Arena flags */
 	u32 flags;
 	struct mutex err_lock;
+	int log_index[2];
 };
 
 /**
@@ -176,6 +220,7 @@ struct arena_info {
  * @init_lock:		Mutex used for the BTT initialization
  * @init_state:		Flag describing the initialization state for the BTT
  * @num_arenas:		Number of arenas in the BTT instance
+ * @phys_bb:		Pointer to the namespace's badblocks structure
  */
 struct btt {
 	struct gendisk *btt_disk;
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 65cc171c721d..2adada1a5855 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -364,9 +364,9 @@ 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;
+	unsigned long align, start_pad;
 	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
 	const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev);
@@ -410,6 +410,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 
 	align = le32_to_cpu(pfn_sb->align);
 	offset = le64_to_cpu(pfn_sb->dataoff);
+	start_pad = le32_to_cpu(pfn_sb->start_pad);
 	if (align == 0)
 		align = 1UL << ilog2(offset);
 	mode = le32_to_cpu(pfn_sb->mode);
@@ -468,7 +469,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 		return -EBUSY;
 	}
 
-	if ((align && !IS_ALIGNED(offset, align))
+	if ((align && !IS_ALIGNED(nsio->res.start + offset + start_pad, align))
 			|| !IS_ALIGNED(offset, PAGE_SIZE)) {
 		dev_err(&nd_pfn->dev,
 				"bad offset: %#llx dax disabled align: %#lx\n",
@@ -582,6 +583,12 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
 	return altmap;
 }
 
+static u64 phys_pmem_align_down(struct nd_pfn *nd_pfn, u64 phys)
+{
+	return min_t(u64, PHYS_SECTION_ALIGN_DOWN(phys),
+			ALIGN_DOWN(phys, nd_pfn->align));
+}
+
 static int nd_pfn_init(struct nd_pfn *nd_pfn)
 {
 	u32 dax_label_reserve = is_nd_dax(&nd_pfn->dev) ? SZ_128K : 0;
@@ -637,13 +644,16 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	start = nsio->res.start;
 	size = PHYS_SECTION_ALIGN_UP(start + size) - start;
 	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
-				IORES_DESC_NONE) == REGION_MIXED) {
+				IORES_DESC_NONE) == REGION_MIXED
+			|| !IS_ALIGNED(start + resource_size(&nsio->res),
+				nd_pfn->align)) {
 		size = resource_size(&nsio->res);
-		end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size);
+		end_trunc = start + size - phys_pmem_align_down(nd_pfn,
+				start + size);
 	}
 
 	if (start_pad + end_trunc)
-		dev_info(&nd_pfn->dev, "%s section collision, truncate %d bytes\n",
+		dev_info(&nd_pfn->dev, "%s alignment collision, truncate %d bytes\n",
 				dev_name(&ndns->dev), start_pad + end_trunc);
 
 	/*
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index bdedb6325c72..4471fd94e1fe 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1620,6 +1620,22 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 			clear_bit(i, chip->irq.valid_mask);
 	}
 
+	/*
+	 * The same set of machines in chv_no_valid_mask[] have incorrectly
+	 * configured GPIOs that generate spurious interrupts so we use
+	 * this same list to apply another quirk for them.
+	 *
+	 * See also https://bugzilla.kernel.org/show_bug.cgi?id=197953.
+	 */
+	if (!need_valid_mask) {
+		/*
+		 * Mask all interrupts the community is able to generate
+		 * but leave the ones that can only generate GPEs unmasked.
+		 */
+		chv_writel(GENMASK(31, pctrl->community->nirqs),
+			   pctrl->regs + CHV_INTMASK);
+	}
+
 	/* Clear all interrupts */
 	chv_writel(0xffff, pctrl->regs + CHV_INTSTAT);
 
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index f77e499afddd..065f0b607373 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -257,10 +257,25 @@ static void release_memory_resource(struct resource *resource)
 	kfree(resource);
 }
 
+/*
+ * Host memory not allocated to dom0. We can use this range for hotplug-based
+ * ballooning.
+ *
+ * It's a type-less resource. Setting IORESOURCE_MEM will make resource
+ * management algorithms (arch_remove_reservations()) look into guest e820,
+ * which we don't want.
+ */
+static struct resource hostmem_resource = {
+	.name   = "Host RAM",
+};
+
+void __attribute__((weak)) __init arch_xen_balloon_init(struct resource *res)
+{}
+
 static struct resource *additional_memory_resource(phys_addr_t size)
 {
-	struct resource *res;
-	int ret;
+	struct resource *res, *res_hostmem;
+	int ret = -ENOMEM;
 
 	res = kzalloc(sizeof(*res), GFP_KERNEL);
 	if (!res)
@@ -269,13 +284,42 @@ static struct resource *additional_memory_resource(phys_addr_t size)
 	res->name = "System RAM";
 	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
-	ret = allocate_resource(&iomem_resource, res,
-				size, 0, -1,
-				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
-	if (ret < 0) {
-		pr_err("Cannot allocate new System RAM resource\n");
-		kfree(res);
-		return NULL;
+	res_hostmem = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (res_hostmem) {
+		/* Try to grab a range from hostmem */
+		res_hostmem->name = "Host memory";
+		ret = allocate_resource(&hostmem_resource, res_hostmem,
+					size, 0, -1,
+					PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
+	}
+
+	if (!ret) {
+		/*
+		 * Insert this resource into iomem. Because hostmem_resource
+		 * tracks portion of guest e820 marked as UNUSABLE noone else
+		 * should try to use it.
+		 */
+		res->start = res_hostmem->start;
+		res->end = res_hostmem->end;
+		ret = insert_resource(&iomem_resource, res);
+		if (ret < 0) {
+			pr_err("Can't insert iomem_resource [%llx - %llx]\n",
+				res->start, res->end);
+			release_memory_resource(res_hostmem);
+			res_hostmem = NULL;
+			res->start = res->end = 0;
+		}
+	}
+
+	if (ret) {
+		ret = allocate_resource(&iomem_resource, res,
+					size, 0, -1,
+					PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
+		if (ret < 0) {
+			pr_err("Cannot allocate new System RAM resource\n");
+			kfree(res);
+			return NULL;
+		}
 	}
 
 #ifdef CONFIG_SPARSEMEM
@@ -287,6 +331,7 @@ static struct resource *additional_memory_resource(phys_addr_t size)
 			pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n",
 			       pfn, limit);
 			release_memory_resource(res);
+			release_memory_resource(res_hostmem);
 			return NULL;
 		}
 	}
@@ -765,6 +810,8 @@ static int __init balloon_init(void)
 	set_online_page_callback(&xen_online_page);
 	register_memory_notifier(&xen_memory_nb);
 	register_sysctl_table(xen_root);
+
+	arch_xen_balloon_init(&hostmem_resource);
 #endif
 
 #ifdef CONFIG_XEN_PV
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 0da80019a917..83ed7715f856 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -702,7 +702,7 @@ xfs_alloc_ag_vextent(
 	ASSERT(args->agbno % args->alignment == 0);
 
 	/* if not file data, insert new block into the reverse map btree */
-	if (args->oinfo.oi_owner != XFS_RMAP_OWN_UNKNOWN) {
+	if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) {
 		error = xfs_rmap_alloc(args->tp, args->agbp, args->agno,
 				       args->agbno, args->len, &args->oinfo);
 		if (error)
@@ -1682,7 +1682,7 @@ xfs_free_ag_extent(
 	bno_cur = cnt_cur = NULL;
 	mp = tp->t_mountp;
 
-	if (oinfo->oi_owner != XFS_RMAP_OWN_UNKNOWN) {
+	if (!xfs_rmap_should_skip_owner_update(oinfo)) {
 		error = xfs_rmap_free(tp, agbp, agno, bno, len, oinfo);
 		if (error)
 			goto error0;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 6249c92671de..a76914db72ef 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -212,6 +212,7 @@ xfs_attr_set(
 	int			flags)
 {
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_buf		*leaf_bp = NULL;
 	struct xfs_da_args	args;
 	struct xfs_defer_ops	dfops;
 	struct xfs_trans_res	tres;
@@ -327,9 +328,16 @@ xfs_attr_set(
 		 * GROT: another possible req'mt for a double-split btree op.
 		 */
 		xfs_defer_init(args.dfops, args.firstblock);
-		error = xfs_attr_shortform_to_leaf(&args);
+		error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
 		if (error)
 			goto out_defer_cancel;
+		/*
+		 * Prevent the leaf buffer from being unlocked so that a
+		 * concurrent AIL push cannot grab the half-baked leaf
+		 * buffer and run into problems with the write verifier.
+		 */
+		xfs_trans_bhold(args.trans, leaf_bp);
+		xfs_defer_bjoin(args.dfops, leaf_bp);
 		xfs_defer_ijoin(args.dfops, dp);
 		error = xfs_defer_finish(&args.trans, args.dfops);
 		if (error)
@@ -337,13 +345,14 @@ xfs_attr_set(
 
 		/*
 		 * Commit the leaf transformation.  We'll need another (linked)
-		 * transaction to add the new attribute to the leaf.
+		 * transaction to add the new attribute to the leaf, which
+		 * means that we have to hold & join the leaf buffer here too.
 		 */
-
 		error = xfs_trans_roll_inode(&args.trans, dp);
 		if (error)
 			goto out;
-
+		xfs_trans_bjoin(args.trans, leaf_bp);
+		leaf_bp = NULL;
 	}
 
 	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
@@ -374,8 +383,9 @@ xfs_attr_set(
 
 out_defer_cancel:
 	xfs_defer_cancel(&dfops);
-	args.trans = NULL;
 out:
+	if (leaf_bp)
+		xfs_trans_brelse(args.trans, leaf_bp);
 	if (args.trans)
 		xfs_trans_cancel(args.trans);
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 53cc8b986eac..601eaa36f1ad 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -735,10 +735,13 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args)
 }
 
 /*
- * Convert from using the shortform to the leaf.
+ * Convert from using the shortform to the leaf.  On success, return the
+ * buffer so that we can keep it locked until we're totally done with it.
  */
 int
-xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
+xfs_attr_shortform_to_leaf(
+	struct xfs_da_args	*args,
+	struct xfs_buf		**leaf_bp)
 {
 	xfs_inode_t *dp;
 	xfs_attr_shortform_t *sf;
@@ -818,7 +821,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 		sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
 	}
 	error = 0;
-
+	*leaf_bp = bp;
 out:
 	kmem_free(tmpbuffer);
 	return error;
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index f7dda0c237b0..894124efb421 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -48,7 +48,8 @@ void	xfs_attr_shortform_create(struct xfs_da_args *args);
 void	xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff);
 int	xfs_attr_shortform_lookup(struct xfs_da_args *args);
 int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
-int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
+int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args,
+			struct xfs_buf **leaf_bp);
 int	xfs_attr_shortform_remove(struct xfs_da_args *args);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 1210f684d3c2..1bddbba6b80c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5136,7 +5136,7 @@ __xfs_bunmapi(
 	 * blowing out the transaction with a mix of EFIs and reflink
 	 * adjustments.
 	 */
-	if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK)
+	if (tp && xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK)
 		max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res));
 	else
 		max_len = len;
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 072ebfe1d6ae..087fea02c389 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -249,6 +249,10 @@ xfs_defer_trans_roll(
 	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
 		xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE);
 
+	/* Hold the (previously bjoin'd) buffer locked across the roll. */
+	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++)
+		xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]);
+
 	trace_xfs_defer_trans_roll((*tp)->t_mountp, dop);
 
 	/* Roll the transaction. */
@@ -264,6 +268,12 @@ xfs_defer_trans_roll(
 	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
 		xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0);
 
+	/* Rejoin the buffers and dirty them so the log moves forward. */
+	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) {
+		xfs_trans_bjoin(*tp, dop->dop_bufs[i]);
+		xfs_trans_bhold(*tp, dop->dop_bufs[i]);
+	}
+
 	return error;
 }
 
@@ -295,6 +305,31 @@ xfs_defer_ijoin(
 		}
 	}
 
+	ASSERT(0);
+	return -EFSCORRUPTED;
+}
+
+/*
+ * Add this buffer to the deferred op.  Each joined buffer is relogged
+ * each time we roll the transaction.
+ */
+int
+xfs_defer_bjoin(
+	struct xfs_defer_ops		*dop,
+	struct xfs_buf			*bp)
+{
+	int				i;
+
+	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) {
+		if (dop->dop_bufs[i] == bp)
+			return 0;
+		else if (dop->dop_bufs[i] == NULL) {
+			dop->dop_bufs[i] = bp;
+			return 0;
+		}
+	}
+
+	ASSERT(0);
 	return -EFSCORRUPTED;
 }
 
@@ -493,9 +528,7 @@ xfs_defer_init(
 	struct xfs_defer_ops		*dop,
 	xfs_fsblock_t			*fbp)
 {
-	dop->dop_committed = false;
-	dop->dop_low = false;
-	memset(&dop->dop_inodes, 0, sizeof(dop->dop_inodes));
+	memset(dop, 0, sizeof(struct xfs_defer_ops));
 	*fbp = NULLFSBLOCK;
 	INIT_LIST_HEAD(&dop->dop_intake);
 	INIT_LIST_HEAD(&dop->dop_pending);
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index d4f046dd44bd..045beacdd37d 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -59,6 +59,7 @@ enum xfs_defer_ops_type {
 };
 
 #define XFS_DEFER_OPS_NR_INODES	2	/* join up to two inodes */
+#define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
 
 struct xfs_defer_ops {
 	bool			dop_committed;	/* did any trans commit? */
@@ -66,8 +67,9 @@ struct xfs_defer_ops {
 	struct list_head	dop_intake;	/* unlogged pending work */
 	struct list_head	dop_pending;	/* logged pending work */
 
-	/* relog these inodes with each roll */
+	/* relog these with each roll */
 	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
+	struct xfs_buf		*dop_bufs[XFS_DEFER_OPS_NR_BUFS];
 };
 
 void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
@@ -77,6 +79,7 @@ void xfs_defer_cancel(struct xfs_defer_ops *dop);
 void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
 int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
+int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);
 
 /* Description of a deferred type. */
 struct xfs_defer_op_type {
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index 89bf16b4d937..b0f31791c7e6 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -632,8 +632,6 @@ xfs_iext_insert(
 	struct xfs_iext_leaf	*new = NULL;
 	int			nr_entries, i;
 
-	trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
-
 	if (ifp->if_height == 0)
 		xfs_iext_alloc_root(ifp, cur);
 	else if (ifp->if_height == 1)
@@ -661,6 +659,8 @@ xfs_iext_insert(
 	xfs_iext_set(cur_rec(cur), irec);
 	ifp->if_bytes += sizeof(struct xfs_iext_rec);
 
+	trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
+
 	if (new)
 		xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2);
 }
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 585b35d34142..c40d26763075 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1488,27 +1488,12 @@ __xfs_refcount_cow_alloc(
 	xfs_extlen_t		aglen,
 	struct xfs_defer_ops	*dfops)
 {
-	int			error;
-
 	trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_private.a.agno,
 			agbno, aglen);
 
 	/* Add refcount btree reservation */
-	error = xfs_refcount_adjust_cow(rcur, agbno, aglen,
+	return xfs_refcount_adjust_cow(rcur, agbno, aglen,
 			XFS_REFCOUNT_ADJUST_COW_ALLOC, dfops);
-	if (error)
-		return error;
-
-	/* Add rmap entry */
-	if (xfs_sb_version_hasrmapbt(&rcur->bc_mp->m_sb)) {
-		error = xfs_rmap_alloc_extent(rcur->bc_mp, dfops,
-				rcur->bc_private.a.agno,
-				agbno, aglen, XFS_RMAP_OWN_COW);
-		if (error)
-			return error;
-	}
-
-	return error;
 }
 
 /*
@@ -1521,27 +1506,12 @@ __xfs_refcount_cow_free(
 	xfs_extlen_t		aglen,
 	struct xfs_defer_ops	*dfops)
 {
-	int			error;
-
 	trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_private.a.agno,
 			agbno, aglen);
 
 	/* Remove refcount btree reservation */
-	error = xfs_refcount_adjust_cow(rcur, agbno, aglen,
+	return xfs_refcount_adjust_cow(rcur, agbno, aglen,
 			XFS_REFCOUNT_ADJUST_COW_FREE, dfops);
-	if (error)
-		return error;
-
-	/* Remove rmap entry */
-	if (xfs_sb_version_hasrmapbt(&rcur->bc_mp->m_sb)) {
-		error = xfs_rmap_free_extent(rcur->bc_mp, dfops,
-				rcur->bc_private.a.agno,
-				agbno, aglen, XFS_RMAP_OWN_COW);
-		if (error)
-			return error;
-	}
-
-	return error;
 }
 
 /* Record a CoW staging extent in the refcount btree. */
@@ -1552,11 +1522,19 @@ xfs_refcount_alloc_cow_extent(
 	xfs_fsblock_t			fsb,
 	xfs_extlen_t			len)
 {
+	int				error;
+
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW,
+	error = __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW,
 			fsb, len);
+	if (error)
+		return error;
+
+	/* Add rmap entry */
+	return xfs_rmap_alloc_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb),
+			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
 }
 
 /* Forget a CoW staging event in the refcount btree. */
@@ -1567,9 +1545,17 @@ xfs_refcount_free_cow_extent(
 	xfs_fsblock_t			fsb,
 	xfs_extlen_t			len)
 {
+	int				error;
+
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
+	/* Remove rmap entry */
+	error = xfs_rmap_free_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb),
+			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
+	if (error)
+		return error;
+
 	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_FREE_COW,
 			fsb, len);
 }
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index dd019cee1b3b..50db920ceeeb 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -368,6 +368,51 @@ xfs_rmap_lookup_le_range(
 }
 
 /*
+ * Perform all the relevant owner checks for a removal op.  If we're doing an
+ * unknown-owner removal then we have no owner information to check.
+ */
+static int
+xfs_rmap_free_check_owner(
+	struct xfs_mount	*mp,
+	uint64_t		ltoff,
+	struct xfs_rmap_irec	*rec,
+	xfs_fsblock_t		bno,
+	xfs_filblks_t		len,
+	uint64_t		owner,
+	uint64_t		offset,
+	unsigned int		flags)
+{
+	int			error = 0;
+
+	if (owner == XFS_RMAP_OWN_UNKNOWN)
+		return 0;
+
+	/* Make sure the unwritten flag matches. */
+	XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) ==
+			(rec->rm_flags & XFS_RMAP_UNWRITTEN), out);
+
+	/* Make sure the owner matches what we expect to find in the tree. */
+	XFS_WANT_CORRUPTED_GOTO(mp, owner == rec->rm_owner, out);
+
+	/* Check the offset, if necessary. */
+	if (XFS_RMAP_NON_INODE_OWNER(owner))
+		goto out;
+
+	if (flags & XFS_RMAP_BMBT_BLOCK) {
+		XFS_WANT_CORRUPTED_GOTO(mp, rec->rm_flags & XFS_RMAP_BMBT_BLOCK,
+				out);
+	} else {
+		XFS_WANT_CORRUPTED_GOTO(mp, rec->rm_offset <= offset, out);
+		XFS_WANT_CORRUPTED_GOTO(mp,
+				ltoff + rec->rm_blockcount >= offset + len,
+				out);
+	}
+
+out:
+	return error;
+}
+
+/*
  * Find the extent in the rmap btree and remove it.
  *
  * The record we find should always be an exact match for the extent that we're
@@ -444,33 +489,40 @@ xfs_rmap_unmap(
 		goto out_done;
 	}
 
-	/* Make sure the unwritten flag matches. */
-	XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) ==
-			(ltrec.rm_flags & XFS_RMAP_UNWRITTEN), out_error);
+	/*
+	 * If we're doing an unknown-owner removal for EFI recovery, we expect
+	 * to find the full range in the rmapbt or nothing at all.  If we
+	 * don't find any rmaps overlapping either end of the range, we're
+	 * done.  Hopefully this means that the EFI creator already queued
+	 * (and finished) a RUI to remove the rmap.
+	 */
+	if (owner == XFS_RMAP_OWN_UNKNOWN &&
+	    ltrec.rm_startblock + ltrec.rm_blockcount <= bno) {
+		struct xfs_rmap_irec    rtrec;
+
+		error = xfs_btree_increment(cur, 0, &i);
+		if (error)
+			goto out_error;
+		if (i == 0)
+			goto out_done;
+		error = xfs_rmap_get_rec(cur, &rtrec, &i);
+		if (error)
+			goto out_error;
+		XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error);
+		if (rtrec.rm_startblock >= bno + len)
+			goto out_done;
+	}
 
 	/* Make sure the extent we found covers the entire freeing range. */
 	XFS_WANT_CORRUPTED_GOTO(mp, ltrec.rm_startblock <= bno &&
-		ltrec.rm_startblock + ltrec.rm_blockcount >=
-		bno + len, out_error);
+			ltrec.rm_startblock + ltrec.rm_blockcount >=
+			bno + len, out_error);
 
-	/* Make sure the owner matches what we expect to find in the tree. */
-	XFS_WANT_CORRUPTED_GOTO(mp, owner == ltrec.rm_owner ||
-				    XFS_RMAP_NON_INODE_OWNER(owner), out_error);
-
-	/* Check the offset, if necessary. */
-	if (!XFS_RMAP_NON_INODE_OWNER(owner)) {
-		if (flags & XFS_RMAP_BMBT_BLOCK) {
-			XFS_WANT_CORRUPTED_GOTO(mp,
-					ltrec.rm_flags & XFS_RMAP_BMBT_BLOCK,
-					out_error);
-		} else {
-			XFS_WANT_CORRUPTED_GOTO(mp,
-					ltrec.rm_offset <= offset, out_error);
-			XFS_WANT_CORRUPTED_GOTO(mp,
-					ltoff + ltrec.rm_blockcount >= offset + len,
-					out_error);
-		}
-	}
+	/* Check owner information. */
+	error = xfs_rmap_free_check_owner(mp, ltoff, &ltrec, bno, len, owner,
+			offset, flags);
+	if (error)
+		goto out_error;
 
 	if (ltrec.rm_startblock == bno && ltrec.rm_blockcount == len) {
 		/* exact match, simply remove the record from rmap tree */
@@ -664,6 +716,7 @@ xfs_rmap_map(
 		flags |= XFS_RMAP_UNWRITTEN;
 	trace_xfs_rmap_map(mp, cur->bc_private.a.agno, bno, len,
 			unwritten, oinfo);
+	ASSERT(!xfs_rmap_should_skip_owner_update(oinfo));
 
 	/*
 	 * For the initial lookup, look for an exact match or the left-adjacent
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 466ede637080..0fcd5b1ba729 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -61,7 +61,21 @@ static inline void
 xfs_rmap_skip_owner_update(
 	struct xfs_owner_info	*oi)
 {
-	oi->oi_owner = XFS_RMAP_OWN_UNKNOWN;
+	xfs_rmap_ag_owner(oi, XFS_RMAP_OWN_NULL);
+}
+
+static inline bool
+xfs_rmap_should_skip_owner_update(
+	struct xfs_owner_info	*oi)
+{
+	return oi->oi_owner == XFS_RMAP_OWN_NULL;
+}
+
+static inline void
+xfs_rmap_any_owner_update(
+	struct xfs_owner_info	*oi)
+{
+	xfs_rmap_ag_owner(oi, XFS_RMAP_OWN_UNKNOWN);
 }
 
 /* Reverse mapping functions. */
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 44f8c5451210..64da90655e95 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -538,7 +538,7 @@ xfs_efi_recover(
 		return error;
 	efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
 
-	xfs_rmap_skip_owner_update(&oinfo);
+	xfs_rmap_any_owner_update(&oinfo);
 	for (i = 0; i < efip->efi_format.efi_nextents; i++) {
 		extp = &efip->efi_format.efi_extents[i];
 		error = xfs_trans_free_extent(tp, efdp, extp->ext_start,
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 8f22fc579dbb..60a2e128cb6a 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -571,6 +571,11 @@ xfs_growfs_data_private(
 		 * this doesn't actually exist in the rmap btree.
 		 */
 		xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL);
+		error = xfs_rmap_free(tp, bp, agno,
+				be32_to_cpu(agf->agf_length) - new,
+				new, &oinfo);
+		if (error)
+			goto error0;
 		error = xfs_free_extent(tp,
 				XFS_AGB_TO_FSB(mp, agno,
 					be32_to_cpu(agf->agf_length) - new),
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 43005fbe8b1e..3861d61fb265 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -870,7 +870,7 @@ xfs_eofblocks_worker(
  * based on the 'speculative_cow_prealloc_lifetime' tunable (5m by default).
  * (We'll just piggyback on the post-EOF prealloc space workqueue.)
  */
-STATIC void
+void
 xfs_queue_cowblocks(
 	struct xfs_mount *mp)
 {
@@ -1536,8 +1536,23 @@ xfs_inode_free_quota_eofblocks(
 	return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks);
 }
 
+static inline unsigned long
+xfs_iflag_for_tag(
+	int		tag)
+{
+	switch (tag) {
+	case XFS_ICI_EOFBLOCKS_TAG:
+		return XFS_IEOFBLOCKS;
+	case XFS_ICI_COWBLOCKS_TAG:
+		return XFS_ICOWBLOCKS;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
 static void
-__xfs_inode_set_eofblocks_tag(
+__xfs_inode_set_blocks_tag(
 	xfs_inode_t	*ip,
 	void		(*execute)(struct xfs_mount *mp),
 	void		(*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
@@ -1552,10 +1567,10 @@ __xfs_inode_set_eofblocks_tag(
 	 * Don't bother locking the AG and looking up in the radix trees
 	 * if we already know that we have the tag set.
 	 */
-	if (ip->i_flags & XFS_IEOFBLOCKS)
+	if (ip->i_flags & xfs_iflag_for_tag(tag))
 		return;
 	spin_lock(&ip->i_flags_lock);
-	ip->i_flags |= XFS_IEOFBLOCKS;
+	ip->i_flags |= xfs_iflag_for_tag(tag);
 	spin_unlock(&ip->i_flags_lock);
 
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
@@ -1587,13 +1602,13 @@ xfs_inode_set_eofblocks_tag(
 	xfs_inode_t	*ip)
 {
 	trace_xfs_inode_set_eofblocks_tag(ip);
-	return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_eofblocks,
+	return __xfs_inode_set_blocks_tag(ip, xfs_queue_eofblocks,
 			trace_xfs_perag_set_eofblocks,
 			XFS_ICI_EOFBLOCKS_TAG);
 }
 
 static void
-__xfs_inode_clear_eofblocks_tag(
+__xfs_inode_clear_blocks_tag(
 	xfs_inode_t	*ip,
 	void		(*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
 				    int error, unsigned long caller_ip),
@@ -1603,7 +1618,7 @@ __xfs_inode_clear_eofblocks_tag(
 	struct xfs_perag *pag;
 
 	spin_lock(&ip->i_flags_lock);
-	ip->i_flags &= ~XFS_IEOFBLOCKS;
+	ip->i_flags &= ~xfs_iflag_for_tag(tag);
 	spin_unlock(&ip->i_flags_lock);
 
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
@@ -1630,7 +1645,7 @@ xfs_inode_clear_eofblocks_tag(
 	xfs_inode_t	*ip)
 {
 	trace_xfs_inode_clear_eofblocks_tag(ip);
-	return __xfs_inode_clear_eofblocks_tag(ip,
+	return __xfs_inode_clear_blocks_tag(ip,
 			trace_xfs_perag_clear_eofblocks, XFS_ICI_EOFBLOCKS_TAG);
 }
 
@@ -1724,7 +1739,7 @@ xfs_inode_set_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
 	trace_xfs_inode_set_cowblocks_tag(ip);
-	return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks,
+	return __xfs_inode_set_blocks_tag(ip, xfs_queue_cowblocks,
 			trace_xfs_perag_set_cowblocks,
 			XFS_ICI_COWBLOCKS_TAG);
 }
@@ -1734,6 +1749,6 @@ xfs_inode_clear_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
 	trace_xfs_inode_clear_cowblocks_tag(ip);
-	return __xfs_inode_clear_eofblocks_tag(ip,
+	return __xfs_inode_clear_blocks_tag(ip,
 			trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
 }
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index bff4d85e5498..d4a77588eca1 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -81,6 +81,7 @@ void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip);
 int xfs_icache_free_cowblocks(struct xfs_mount *, struct xfs_eofblocks *);
 int xfs_inode_free_quota_cowblocks(struct xfs_inode *ip);
 void xfs_cowblocks_worker(struct work_struct *);
+void xfs_queue_cowblocks(struct xfs_mount *);
 
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b41952a4ddd8..6f95bdb408ce 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1487,6 +1487,24 @@ xfs_link(
 	return error;
 }
 
+/* Clear the reflink flag and the cowblocks tag if possible. */
+static void
+xfs_itruncate_clear_reflink_flags(
+	struct xfs_inode	*ip)
+{
+	struct xfs_ifork	*dfork;
+	struct xfs_ifork	*cfork;
+
+	if (!xfs_is_reflink_inode(ip))
+		return;
+	dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	if (dfork->if_bytes == 0 && cfork->if_bytes == 0)
+		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+	if (cfork->if_bytes == 0)
+		xfs_inode_clear_cowblocks_tag(ip);
+}
+
 /*
  * Free up the underlying blocks past new_size.  The new size must be smaller
  * than the current size.  This routine can be used both for the attribute and
@@ -1583,15 +1601,7 @@ xfs_itruncate_extents(
 	if (error)
 		goto out;
 
-	/*
-	 * Clear the reflink flag if there are no data fork blocks and
-	 * there are no extents staged in the cow fork.
-	 */
-	if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) {
-		if (ip->i_d.di_nblocks == 0)
-			ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
-		xfs_inode_clear_cowblocks_tag(ip);
-	}
+	xfs_itruncate_clear_reflink_flags(ip);
 
 	/*
 	 * Always re-log the inode so that our permanent transaction can keep
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index b2136af9289f..d383e392ec9d 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -232,6 +232,7 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
  * log recovery to replay a bmap operation on the inode.
  */
 #define XFS_IRECOVERY		(1 << 11)
+#define XFS_ICOWBLOCKS		(1 << 12)/* has the cowblocks tag set */
 
 /*
  * Per-lifetime flags need to be reset when re-using a reclaimable inode during
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index cf7c8f81bebb..47aea2e82c26 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -454,6 +454,8 @@ retry:
 	if (error)
 		goto out_bmap_cancel;
 
+	xfs_inode_set_cowblocks_tag(ip);
+
 	/* Finish up. */
 	error = xfs_defer_finish(&tp, &dfops);
 	if (error)
@@ -490,8 +492,9 @@ xfs_reflink_find_cow_mapping(
 	struct xfs_iext_cursor		icur;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
-	ASSERT(xfs_is_reflink_inode(ip));
 
+	if (!xfs_is_reflink_inode(ip))
+		return false;
 	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
 	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got))
 		return false;
@@ -610,6 +613,9 @@ xfs_reflink_cancel_cow_blocks(
 
 			/* Remove the mapping from the CoW fork. */
 			xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
+		} else {
+			/* Didn't do anything, push cursor back. */
+			xfs_iext_prev(ifp, &icur);
 		}
 next_extent:
 		if (!xfs_iext_get_extent(ifp, &icur, &got))
@@ -725,7 +731,7 @@ xfs_reflink_end_cow(
 			(unsigned int)(end_fsb - offset_fsb),
 			XFS_DATA_FORK);
 	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
-			resblks, 0, 0, &tp);
+			resblks, 0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		goto out;
 
@@ -1291,6 +1297,17 @@ xfs_reflink_remap_range(
 
 	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
 
+	/*
+	 * Clear out post-eof preallocations because we don't have page cache
+	 * backing the delayed allocations and they'll never get freed on
+	 * their own.
+	 */
+	if (xfs_can_free_eofblocks(dest, true)) {
+		ret = xfs_free_eofblocks(dest);
+		if (ret)
+			goto out_unlock;
+	}
+
 	/* Set flags and remap blocks. */
 	ret = xfs_reflink_set_inode_flag(src, dest);
 	if (ret)
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 5122d3021117..1dacccc367f8 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1360,6 +1360,7 @@ xfs_fs_remount(
 			xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 			return error;
 		}
+		xfs_queue_cowblocks(mp);
 
 		/* Create the per-AG metadata reservation pool .*/
 		error = xfs_fs_reserve_ag_blocks(mp);
@@ -1369,6 +1370,14 @@ xfs_fs_remount(
 
 	/* rw -> ro */
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & SB_RDONLY)) {
+		/* Get rid of any leftover CoW reservations... */
+		cancel_delayed_work_sync(&mp->m_cowblocks_work);
+		error = xfs_icache_free_cowblocks(mp, NULL);
+		if (error) {
+			xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+			return error;
+		}
+
 		/* Free the per-AG metadata reservation pool. */
 		error = xfs_fs_unreserve_ag_blocks(mp);
 		if (error) {
diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h
index ea189d88a3cc..8ac4e68a12f0 100644
--- a/include/asm-generic/mm_hooks.h
+++ b/include/asm-generic/mm_hooks.h
@@ -7,9 +7,10 @@
 #ifndef _ASM_GENERIC_MM_HOOKS_H
 #define _ASM_GENERIC_MM_HOOKS_H
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index b234d54f2cb6..868e68561f91 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1025,6 +1025,11 @@ static inline int pmd_clear_huge(pmd_t *pmd)
 struct file;
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 			unsigned long size, pgprot_t *vma_prot);
+
+#ifndef CONFIG_X86_ESPFIX64
+static inline void init_espfix_bsp(void) { }
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #ifndef io_remap_pfn_range
diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h
index cceafa01f907..b67404fc4b34 100644
--- a/include/crypto/mcryptd.h
+++ b/include/crypto/mcryptd.h
@@ -27,6 +27,7 @@ static inline struct mcryptd_ahash *__mcryptd_ahash_cast(
 
 struct mcryptd_cpu_queue {
 	struct crypto_queue queue;
+	spinlock_t q_lock;
 	struct work_struct work;
 };
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 57b109c6e422..1f509d072026 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1165,6 +1165,10 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev);
 int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev);
+int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
+				 u64 *values,
+				 int num_counters,
+				 size_t *offsets);
 struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
 void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 6c1db823f8b9..66fd3951e6f3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1515,6 +1515,11 @@ static inline bool sock_owned_by_user(const struct sock *sk)
 	return sk->sk_lock.owned;
 }
 
+static inline bool sock_owned_by_user_nocheck(const struct sock *sk)
+{
+	return sk->sk_lock.owned;
+}
+
 /* no reclassification while locks are held */
 static inline bool sock_allow_reclassification(const struct sock *csk)
 {
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 079ea9455bcd..2e6d4fe6b0ba 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1601,6 +1601,9 @@ int xfrm_init_state(struct xfrm_state *x);
 int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
 int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
+int xfrm_trans_queue(struct sk_buff *skb,
+		     int (*finish)(struct net *, struct sock *,
+				   struct sk_buff *));
 int xfrm_output_resume(struct sk_buff *skb, int err);
 int xfrm_output(struct sock *sk, struct sk_buff *skb);
 int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
diff --git a/include/trace/events/clk.h b/include/trace/events/clk.h
index 758607226bfd..2cd449328aee 100644
--- a/include/trace/events/clk.h
+++ b/include/trace/events/clk.h
@@ -134,12 +134,12 @@ DECLARE_EVENT_CLASS(clk_parent,
 
 	TP_STRUCT__entry(
 		__string(        name,           core->name                )
-		__string(        pname,          parent->name              )
+		__string(        pname, parent ? parent->name : "none"     )
 	),
 
 	TP_fast_assign(
 		__assign_str(name, core->name);
-		__assign_str(pname, parent->name);
+		__assign_str(pname, parent ? parent->name : "none");
 	),
 
 	TP_printk("%s %s", __get_str(name), __get_str(pname))
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 8e88a1671538..bb00459d2d4d 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -9,6 +9,35 @@
 #include <linux/tracepoint.h>
 #include <net/ipv6.h>
 
+#define TP_STORE_V4MAPPED(__entry, saddr, daddr)		\
+	do {							\
+		struct in6_addr *pin6;				\
+								\
+		pin6 = (struct in6_addr *)__entry->saddr_v6;	\
+		ipv6_addr_set_v4mapped(saddr, pin6);		\
+		pin6 = (struct in6_addr *)__entry->daddr_v6;	\
+		ipv6_addr_set_v4mapped(daddr, pin6);		\
+	} while (0)
+
+#if IS_ENABLED(CONFIG_IPV6)
+#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6)		\
+	do {								\
+		if (sk->sk_family == AF_INET6) {			\
+			struct in6_addr *pin6;				\
+									\
+			pin6 = (struct in6_addr *)__entry->saddr_v6;	\
+			*pin6 = saddr6;					\
+			pin6 = (struct in6_addr *)__entry->daddr_v6;	\
+			*pin6 = daddr6;					\
+		} else {						\
+			TP_STORE_V4MAPPED(__entry, saddr, daddr);	\
+		}							\
+	} while (0)
+#else
+#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6)	\
+	TP_STORE_V4MAPPED(__entry, saddr, daddr)
+#endif
+
 /*
  * tcp event with arguments sk and skb
  *
@@ -34,7 +63,6 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb,
 
 	TP_fast_assign(
 		struct inet_sock *inet = inet_sk(sk);
-		struct in6_addr *pin6;
 		__be32 *p32;
 
 		__entry->skbaddr = skb;
@@ -49,20 +77,8 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb,
 		p32 = (__be32 *) __entry->daddr;
 		*p32 =  inet->inet_daddr;
 
-#if IS_ENABLED(CONFIG_IPV6)
-		if (sk->sk_family == AF_INET6) {
-			pin6 = (struct in6_addr *)__entry->saddr_v6;
-			*pin6 = sk->sk_v6_rcv_saddr;
-			pin6 = (struct in6_addr *)__entry->daddr_v6;
-			*pin6 = sk->sk_v6_daddr;
-		} else
-#endif
-		{
-			pin6 = (struct in6_addr *)__entry->saddr_v6;
-			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
-			pin6 = (struct in6_addr *)__entry->daddr_v6;
-			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
-		}
+		TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr,
+			      sk->sk_v6_rcv_saddr, sk->sk_v6_daddr);
 	),
 
 	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
@@ -111,7 +127,6 @@ DECLARE_EVENT_CLASS(tcp_event_sk,
 
 	TP_fast_assign(
 		struct inet_sock *inet = inet_sk(sk);
-		struct in6_addr *pin6;
 		__be32 *p32;
 
 		__entry->skaddr = sk;
@@ -125,20 +140,8 @@ DECLARE_EVENT_CLASS(tcp_event_sk,
 		p32 = (__be32 *) __entry->daddr;
 		*p32 =  inet->inet_daddr;
 
-#if IS_ENABLED(CONFIG_IPV6)
-		if (sk->sk_family == AF_INET6) {
-			pin6 = (struct in6_addr *)__entry->saddr_v6;
-			*pin6 = sk->sk_v6_rcv_saddr;
-			pin6 = (struct in6_addr *)__entry->daddr_v6;
-			*pin6 = sk->sk_v6_daddr;
-		} else
-#endif
-		{
-			pin6 = (struct in6_addr *)__entry->saddr_v6;
-			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
-			pin6 = (struct in6_addr *)__entry->daddr_v6;
-			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
-		}
+		TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr,
+			       sk->sk_v6_rcv_saddr, sk->sk_v6_daddr);
 	),
 
 	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
@@ -181,7 +184,6 @@ TRACE_EVENT(tcp_set_state,
 
 	TP_fast_assign(
 		struct inet_sock *inet = inet_sk(sk);
-		struct in6_addr *pin6;
 		__be32 *p32;
 
 		__entry->skaddr = sk;
@@ -197,20 +199,8 @@ TRACE_EVENT(tcp_set_state,
 		p32 = (__be32 *) __entry->daddr;
 		*p32 =  inet->inet_daddr;
 
-#if IS_ENABLED(CONFIG_IPV6)
-		if (sk->sk_family == AF_INET6) {
-			pin6 = (struct in6_addr *)__entry->saddr_v6;
-			*pin6 = sk->sk_v6_rcv_saddr;
-			pin6 = (struct in6_addr *)__entry->daddr_v6;
-			*pin6 = sk->sk_v6_daddr;
-		} else
-#endif
-		{
-			pin6 = (struct in6_addr *)__entry->saddr_v6;
-			ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
-			pin6 = (struct in6_addr *)__entry->daddr_v6;
-			ipv6_addr_set_v4mapped(inet->inet_daddr, pin6);
-		}
+		TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr,
+			       sk->sk_v6_rcv_saddr, sk->sk_v6_daddr);
 	),
 
 	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s",
@@ -240,7 +230,6 @@ TRACE_EVENT(tcp_retransmit_synack,
 
 	TP_fast_assign(
 		struct inet_request_sock *ireq = inet_rsk(req);
-		struct in6_addr *pin6;
 		__be32 *p32;
 
 		__entry->skaddr = sk;
@@ -255,20 +244,8 @@ TRACE_EVENT(tcp_retransmit_synack,
 		p32 = (__be32 *) __entry->daddr;
 		*p32 = ireq->ir_rmt_addr;
 
-#if IS_ENABLED(CONFIG_IPV6)
-		if (sk->sk_family == AF_INET6) {
-			pin6 = (struct in6_addr *)__entry->saddr_v6;
-			*pin6 = ireq->ir_v6_loc_addr;
-			pin6 = (struct in6_addr *)__entry->daddr_v6;
-			*pin6 = ireq->ir_v6_rmt_addr;
-		} else
-#endif
-		{
-			pin6 = (struct in6_addr *)__entry->saddr_v6;
-			ipv6_addr_set_v4mapped(ireq->ir_loc_addr, pin6);
-			pin6 = (struct in6_addr *)__entry->daddr_v6;
-			ipv6_addr_set_v4mapped(ireq->ir_rmt_addr, pin6);
-		}
+		TP_STORE_ADDRS(__entry, ireq->ir_loc_addr, ireq->ir_rmt_addr,
+			      ireq->ir_v6_loc_addr, ireq->ir_v6_rmt_addr);
 	),
 
 	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c",
diff --git a/include/xen/balloon.h b/include/xen/balloon.h
index 4914b93a23f2..61f410fd74e4 100644
--- a/include/xen/balloon.h
+++ b/include/xen/balloon.h
@@ -44,3 +44,8 @@ static inline void xen_balloon_init(void)
 {
 }
 #endif
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+struct resource;
+void arch_xen_balloon_init(struct resource *hostmem_resource);
+#endif
diff --git a/init/main.c b/init/main.c
index e96e3a14533c..7b606fc48482 100644
--- a/init/main.c
+++ b/init/main.c
@@ -504,6 +504,8 @@ static void __init mm_init(void)
 	pgtable_init();
 	vmalloc_init();
 	ioremap_huge_init();
+	/* Should be run before the first non-init thread is created */
+	init_espfix_bsp();
 }
 
 asmlinkage __visible void __init start_kernel(void)
@@ -679,10 +681,6 @@ asmlinkage __visible void __init start_kernel(void)
 	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
-#ifdef CONFIG_X86_ESPFIX64
-	/* Should be run before the first non-init thread is created */
-	init_espfix_bsp();
-#endif
 	thread_stack_cache_init();
 	cred_init();
 	fork_init();
diff --git a/kernel/fork.c b/kernel/fork.c
index 432eadf6b58c..2295fc69717f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -721,8 +721,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			goto out;
 	}
 	/* a new mm has just been created */
-	arch_dup_mmap(oldmm, mm);
-	retval = 0;
+	retval = arch_dup_mmap(oldmm, mm);
 out:
 	up_write(&mm->mmap_sem);
 	flush_tlb_mm(oldmm);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c87766c1c204..9ab18995ff1e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 /* Missed count stored at end */
 #define RB_MISSED_STORED	(1 << 30)
 
+#define RB_MISSED_FLAGS		(RB_MISSED_EVENTS|RB_MISSED_STORED)
+
 struct buffer_data_page {
 	u64		 time_stamp;	/* page time stamp */
 	local_t		 commit;	/* write committed index */
@@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
  */
 size_t ring_buffer_page_len(void *page)
 {
-	return local_read(&((struct buffer_data_page *)page)->commit)
+	struct buffer_data_page *bpage = page;
+
+	return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
 		+ BUF_PAGE_HDR_SIZE;
 }
 
@@ -4400,8 +4404,13 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct buffer_data_page *bpage = data;
+	struct page *page = virt_to_page(bpage);
 	unsigned long flags;
 
+	/* If the page is still in use someplace else, we can't reuse it */
+	if (page_ref_count(page) > 1)
+		goto out;
+
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
@@ -4413,6 +4422,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
+ out:
 	free_page((unsigned long)bpage);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 59518b8126d0..2a8d8a294345 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6769,7 +6769,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
-	int entries, size, i;
+	int entries, i;
 	ssize_t ret = 0;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -6823,14 +6823,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		/*
-		 * zero out any left over data, this is going to
-		 * user land.
-		 */
-		size = ring_buffer_page_len(ref->page);
-		if (size < PAGE_SIZE)
-			memset(ref->page + size, 0, PAGE_SIZE - size);
-
 		page = virt_to_page(ref->page);
 
 		spd.pages[i] = page;
@@ -7588,6 +7580,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
 	buf->data = alloc_percpu(struct trace_array_cpu);
 	if (!buf->data) {
 		ring_buffer_free(buf->buffer);
+		buf->buffer = NULL;
 		return -ENOMEM;
 	}
 
@@ -7611,7 +7604,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 				    allocate_snapshot ? size : 1);
 	if (WARN_ON(ret)) {
 		ring_buffer_free(tr->trace_buffer.buffer);
+		tr->trace_buffer.buffer = NULL;
 		free_percpu(tr->trace_buffer.data);
+		tr->trace_buffer.data = NULL;
 		return -ENOMEM;
 	}
 	tr->allocated_snapshot = allocate_snapshot;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 00b0757830e2..01e8285aea73 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1177,12 +1177,12 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 	int i, new_frags;
 	u32 d_off;
 
-	if (!num_frags)
-		goto release;
-
 	if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
 		return -EINVAL;
 
+	if (!num_frags)
+		goto release;
+
 	new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	for (i = 0; i < new_frags; i++) {
 		page = alloc_page(gfp_mask);
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index e50b7fea57ee..bcfc00e88756 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -23,6 +23,12 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb)
 	return xfrm4_extract_header(skb);
 }
 
+static int xfrm4_rcv_encap_finish2(struct net *net, struct sock *sk,
+				   struct sk_buff *skb)
+{
+	return dst_input(skb);
+}
+
 static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk,
 					 struct sk_buff *skb)
 {
@@ -33,7 +39,11 @@ static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk,
 					 iph->tos, skb->dev))
 			goto drop;
 	}
-	return dst_input(skb);
+
+	if (xfrm_trans_queue(skb, xfrm4_rcv_encap_finish2))
+		goto drop;
+
+	return 0;
 drop:
 	kfree_skb(skb);
 	return NET_RX_DROP;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b345b7e484c5..db99446e0276 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1333,6 +1333,36 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 	eth_random_addr(dev->perm_addr);
 }
 
+#define GRE6_FEATURES (NETIF_F_SG |		\
+		       NETIF_F_FRAGLIST |	\
+		       NETIF_F_HIGHDMA |	\
+		       NETIF_F_HW_CSUM)
+
+static void ip6gre_tnl_init_features(struct net_device *dev)
+{
+	struct ip6_tnl *nt = netdev_priv(dev);
+
+	dev->features		|= GRE6_FEATURES;
+	dev->hw_features	|= GRE6_FEATURES;
+
+	if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
+		/* TCP offload with GRE SEQ is not supported, nor
+		 * can we support 2 levels of outer headers requiring
+		 * an update.
+		 */
+		if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
+		    nt->encap.type == TUNNEL_ENCAP_NONE) {
+			dev->features    |= NETIF_F_GSO_SOFTWARE;
+			dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+		}
+
+		/* Can use a lockless transmit, unless we generate
+		 * output sequences
+		 */
+		dev->features |= NETIF_F_LLTX;
+	}
+}
+
 static int ip6gre_tunnel_init_common(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
@@ -1371,6 +1401,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 		dev->features |= NETIF_F_NETNS_LOCAL;
 		netif_keep_dst(dev);
 	}
+	ip6gre_tnl_init_features(dev);
 
 	return 0;
 }
@@ -1705,11 +1736,6 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
 	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
-#define GRE6_FEATURES (NETIF_F_SG |		\
-		       NETIF_F_FRAGLIST |	\
-		       NETIF_F_HIGHDMA |		\
-		       NETIF_F_HW_CSUM)
-
 static int ip6erspan_tap_init(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
@@ -1848,26 +1874,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 	nt->net = dev_net(dev);
 	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
 
-	dev->features		|= GRE6_FEATURES;
-	dev->hw_features	|= GRE6_FEATURES;
-
-	if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
-		/* TCP offload with GRE SEQ is not supported, nor
-		 * can we support 2 levels of outer headers requiring
-		 * an update.
-		 */
-		if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
-		    (nt->encap.type == TUNNEL_ENCAP_NONE)) {
-			dev->features    |= NETIF_F_GSO_SOFTWARE;
-			dev->hw_features |= NETIF_F_GSO_SOFTWARE;
-		}
-
-		/* Can use a lockless transmit, unless we generate
-		 * output sequences
-		 */
-		dev->features |= NETIF_F_LLTX;
-	}
-
 	err = register_netdevice(dev);
 	if (err)
 		goto out;
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index fe04e23af986..841f4a07438e 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -32,6 +32,14 @@ int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi,
 }
 EXPORT_SYMBOL(xfrm6_rcv_spi);
 
+static int xfrm6_transport_finish2(struct net *net, struct sock *sk,
+				   struct sk_buff *skb)
+{
+	if (xfrm_trans_queue(skb, ip6_rcv_finish))
+		__kfree_skb(skb);
+	return -1;
+}
+
 int xfrm6_transport_finish(struct sk_buff *skb, int async)
 {
 	struct xfrm_offload *xo = xfrm_offload(skb);
@@ -56,7 +64,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 
 	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
 		dev_net(skb->dev), NULL, skb, skb->dev, NULL,
-		ip6_rcv_finish);
+		xfrm6_transport_finish2);
 	return -1;
 }
 
diff --git a/net/rds/send.c b/net/rds/send.c
index b52cdc8ae428..f72466c63f0c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1009,6 +1009,9 @@ static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
 			continue;
 
 		if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+			if (cmsg->cmsg_len <
+			    CMSG_LEN(sizeof(struct rds_rdma_args)))
+				return -EINVAL;
 			args = CMSG_DATA(cmsg);
 			*rdma_bytes += args->remote_vec.bytes;
 		}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 4591b87eaab5..6708b6953bfa 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -373,6 +373,8 @@ void tcf_block_put(struct tcf_block *block)
 {
 	struct tcf_block_ext_info ei = {0, };
 
+	if (!block)
+		return;
 	tcf_block_put_ext(block, block->q, &ei);
 }
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 28b2a7964133..cc069b2acf0e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1261,6 +1261,8 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
 
 	if (!tp_head) {
 		RCU_INIT_POINTER(*miniqp->p_miniq, NULL);
+		/* Wait for flying RCU callback before it is freed. */
+		rcu_barrier_bh();
 		return;
 	}
 
@@ -1276,7 +1278,7 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
 	rcu_assign_pointer(*miniqp->p_miniq, miniq);
 
 	if (miniq_old)
-		/* This is counterpart of the rcu barrier above. We need to
+		/* This is counterpart of the rcu barriers above. We need to
 		 * block potential new user of miniq_old until all readers
 		 * are not seeing it.
 		 */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index aadcd4244d9b..a5e2150ab013 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4569,7 +4569,7 @@ static int sctp_init_sock(struct sock *sk)
 	SCTP_DBG_OBJCNT_INC(sock);
 
 	local_bh_disable();
-	percpu_counter_inc(&sctp_sockets_allocated);
+	sk_sockets_allocated_inc(sk);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
 
 	/* Nothing can fail after this block, otherwise
@@ -4613,7 +4613,7 @@ static void sctp_destroy_sock(struct sock *sk)
 	}
 	sctp_endpoint_free(sp->ep);
 	local_bh_disable();
-	percpu_counter_dec(&sctp_sockets_allocated);
+	sk_sockets_allocated_dec(sk);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	local_bh_enable();
 }
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index c5fda15ba319..1fdab5c4eda8 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -401,7 +401,7 @@ void strp_data_ready(struct strparser *strp)
 	 * allows a thread in BH context to safely check if the process
 	 * lock is held. In this case, if the lock is held, queue work.
 	 */
-	if (sock_owned_by_user(strp->sk)) {
+	if (sock_owned_by_user_nocheck(strp->sk)) {
 		queue_work(strp_wq, &strp->work);
 		return;
 	}
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 47ec121574ce..c8001471da6c 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -324,6 +324,7 @@ restart:
 	if (res) {
 		pr_warn("Bearer <%s> rejected, enable failure (%d)\n",
 			name, -res);
+		kfree(b);
 		return -EINVAL;
 	}
 
@@ -347,8 +348,10 @@ restart:
 	if (skb)
 		tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr);
 
-	if (tipc_mon_create(net, bearer_id))
+	if (tipc_mon_create(net, bearer_id)) {
+		bearer_disable(net, b);
 		return -ENOMEM;
+	}
 
 	pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
 		name,
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 7ebbdeb2a90e..8e12ab55346b 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -368,18 +368,20 @@ void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack)
 	u16 prev = grp->bc_snd_nxt - 1;
 	struct tipc_member *m;
 	struct rb_node *n;
+	u16 ackers = 0;
 
 	for (n = rb_first(&grp->members); n; n = rb_next(n)) {
 		m = container_of(n, struct tipc_member, tree_node);
 		if (tipc_group_is_enabled(m)) {
 			tipc_group_update_member(m, len);
 			m->bc_acked = prev;
+			ackers++;
 		}
 	}
 
 	/* Mark number of acknowledges to expect, if any */
 	if (ack)
-		grp->bc_ackers = grp->member_cnt;
+		grp->bc_ackers = ackers;
 	grp->bc_snd_nxt++;
 }
 
@@ -848,17 +850,26 @@ void tipc_group_member_evt(struct tipc_group *grp,
 		*usr_wakeup = true;
 		m->usr_pending = false;
 		node_up = tipc_node_is_up(net, node);
-
-		/* Hold back event if more messages might be expected */
-		if (m->state != MBR_LEAVING && node_up) {
-			m->event_msg = skb;
-			tipc_group_decr_active(grp, m);
-			m->state = MBR_LEAVING;
-		} else {
-			if (node_up)
+		m->event_msg = NULL;
+
+		if (node_up) {
+			/* Hold back event if a LEAVE msg should be expected */
+			if (m->state != MBR_LEAVING) {
+				m->event_msg = skb;
+				tipc_group_decr_active(grp, m);
+				m->state = MBR_LEAVING;
+			} else {
 				msg_set_grp_bc_seqno(hdr, m->bc_syncpt);
-			else
+				__skb_queue_tail(inputq, skb);
+			}
+		} else {
+			if (m->state != MBR_LEAVING) {
+				tipc_group_decr_active(grp, m);
+				m->state = MBR_LEAVING;
 				msg_set_grp_bc_seqno(hdr, m->bc_rcv_nxt);
+			} else {
+				msg_set_grp_bc_seqno(hdr, m->bc_syncpt);
+			}
 			__skb_queue_tail(inputq, skb);
 		}
 		list_del_init(&m->list);
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 8e884ed06d4b..32dc33a94bc7 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -642,9 +642,13 @@ void tipc_mon_delete(struct net *net, int bearer_id)
 {
 	struct tipc_net *tn = tipc_net(net);
 	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
-	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *self;
 	struct tipc_peer *peer, *tmp;
 
+	if (!mon)
+		return;
+
+	self = get_self(net, bearer_id);
 	write_lock_bh(&mon->lock);
 	tn->monitors[bearer_id] = NULL;
 	list_for_each_entry_safe(peer, tmp, &self->list, list) {
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 0cdf5c2ad881..b51d5cba5094 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -727,11 +727,11 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
 
 	switch (sk->sk_state) {
 	case TIPC_ESTABLISHED:
+	case TIPC_CONNECTING:
 		if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
 			revents |= POLLOUT;
 		/* fall thru' */
 	case TIPC_LISTEN:
-	case TIPC_CONNECTING:
 		if (!skb_queue_empty(&sk->sk_receive_queue))
 			revents |= POLLIN | POLLRDNORM;
 		break;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index ac277b97e0d7..26b10eb7a206 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -8,15 +8,29 @@
  *
  */
 
+#include <linux/bottom_half.h>
+#include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/percpu.h>
 #include <net/dst.h>
 #include <net/ip.h>
 #include <net/xfrm.h>
 #include <net/ip_tunnels.h>
 #include <net/ip6_tunnel.h>
 
+struct xfrm_trans_tasklet {
+	struct tasklet_struct tasklet;
+	struct sk_buff_head queue;
+};
+
+struct xfrm_trans_cb {
+	int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb);
+};
+
+#define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0]))
+
 static struct kmem_cache *secpath_cachep __read_mostly;
 
 static DEFINE_SPINLOCK(xfrm_input_afinfo_lock);
@@ -25,6 +39,8 @@ static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[AF_INET6 + 1];
 static struct gro_cells gro_cells;
 static struct net_device xfrm_napi_dev;
 
+static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet);
+
 int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo)
 {
 	int err = 0;
@@ -207,7 +223,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	xfrm_address_t *daddr;
 	struct xfrm_mode *inner_mode;
 	u32 mark = skb->mark;
-	unsigned int family;
+	unsigned int family = AF_UNSPEC;
 	int decaps = 0;
 	int async = 0;
 	bool xfrm_gro = false;
@@ -216,6 +232,16 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 	if (encap_type < 0) {
 		x = xfrm_input_state(skb);
+
+		if (unlikely(x->km.state != XFRM_STATE_VALID)) {
+			if (x->km.state == XFRM_STATE_ACQ)
+				XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
+			else
+				XFRM_INC_STATS(net,
+					       LINUX_MIB_XFRMINSTATEINVALID);
+			goto drop;
+		}
+
 		family = x->outer_mode->afinfo->family;
 
 		/* An encap_type of -1 indicates async resumption. */
@@ -466,9 +492,41 @@ int xfrm_input_resume(struct sk_buff *skb, int nexthdr)
 }
 EXPORT_SYMBOL(xfrm_input_resume);
 
+static void xfrm_trans_reinject(unsigned long data)
+{
+	struct xfrm_trans_tasklet *trans = (void *)data;
+	struct sk_buff_head queue;
+	struct sk_buff *skb;
+
+	__skb_queue_head_init(&queue);
+	skb_queue_splice_init(&trans->queue, &queue);
+
+	while ((skb = __skb_dequeue(&queue)))
+		XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb);
+}
+
+int xfrm_trans_queue(struct sk_buff *skb,
+		     int (*finish)(struct net *, struct sock *,
+				   struct sk_buff *))
+{
+	struct xfrm_trans_tasklet *trans;
+
+	trans = this_cpu_ptr(&xfrm_trans_tasklet);
+
+	if (skb_queue_len(&trans->queue) >= netdev_max_backlog)
+		return -ENOBUFS;
+
+	XFRM_TRANS_SKB_CB(skb)->finish = finish;
+	skb_queue_tail(&trans->queue, skb);
+	tasklet_schedule(&trans->tasklet);
+	return 0;
+}
+EXPORT_SYMBOL(xfrm_trans_queue);
+
 void __init xfrm_input_init(void)
 {
 	int err;
+	int i;
 
 	init_dummy_netdev(&xfrm_napi_dev);
 	err = gro_cells_init(&gro_cells, &xfrm_napi_dev);
@@ -479,4 +537,13 @@ void __init xfrm_input_init(void)
 					   sizeof(struct sec_path),
 					   0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 					   NULL);
+
+	for_each_possible_cpu(i) {
+		struct xfrm_trans_tasklet *trans;
+
+		trans = &per_cpu(xfrm_trans_tasklet, i);
+		__skb_queue_head_init(&trans->queue);
+		tasklet_init(&trans->tasklet, xfrm_trans_reinject,
+			     (unsigned long)trans);
+	}
 }
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index e3a5aca9cdda..d8a8129b9232 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1168,9 +1168,15 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
  again:
 	pol = rcu_dereference(sk->sk_policy[dir]);
 	if (pol != NULL) {
-		bool match = xfrm_selector_match(&pol->selector, fl, family);
+		bool match;
 		int err = 0;
 
+		if (pol->family != family) {
+			pol = NULL;
+			goto out;
+		}
+
+		match = xfrm_selector_match(&pol->selector, fl, family);
 		if (match) {
 			if ((sk->sk_mark & pol->mark.m) != pol->mark.v) {
 				pol = NULL;
@@ -1835,6 +1841,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 		   sizeof(struct xfrm_policy *) * num_pols) == 0 &&
 	    xfrm_xdst_can_reuse(xdst, xfrm, err)) {
 		dst_hold(&xdst->u.dst);
+		xfrm_pols_put(pols, num_pols);
 		while (err > 0)
 			xfrm_state_put(xfrm[--err]);
 		return xdst;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 1b7856be3eeb..cc4c519cad76 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1343,6 +1343,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 
 	if (orig->aead) {
 		x->aead = xfrm_algo_aead_clone(orig->aead);
+		x->geniv = orig->geniv;
 		if (!x->aead)
 			goto error;
 	}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 983b0233767b..bdb48e5dba04 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1419,11 +1419,14 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
 
 static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
 {
+	u16 prev_family;
 	int i;
 
 	if (nr > XFRM_MAX_DEPTH)
 		return -EINVAL;
 
+	prev_family = family;
+
 	for (i = 0; i < nr; i++) {
 		/* We never validated the ut->family value, so many
 		 * applications simply leave it at zero.  The check was
@@ -1435,6 +1438,12 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
 		if (!ut[i].family)
 			ut[i].family = family;
 
+		if ((ut[i].mode == XFRM_MODE_TRANSPORT) &&
+		    (ut[i].family != prev_family))
+			return -EINVAL;
+
+		prev_family = ut[i].family;
+
 		switch (ut[i].family) {
 		case AF_INET:
 			break;
@@ -1445,6 +1454,21 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
 		default:
 			return -EINVAL;
 		}
+
+		switch (ut[i].id.proto) {
+		case IPPROTO_AH:
+		case IPPROTO_ESP:
+		case IPPROTO_COMP:
+#if IS_ENABLED(CONFIG_IPV6)
+		case IPPROTO_ROUTING:
+		case IPPROTO_DSTOPTS:
+#endif
+		case IPSEC_PROTO_ANY:
+			break;
+		default:
+			return -EINVAL;
+		}
+
 	}
 
 	return 0;
@@ -2470,7 +2494,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_PROTO]		= { .type = NLA_U8 },
 	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
 	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
-	[XFRMA_OUTPUT_MARK]	= { .len = NLA_U32 },
+	[XFRMA_OUTPUT_MARK]	= { .type = NLA_U32 },
 };
 
 static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index 038a180d3f81..cbe818eda336 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -325,7 +325,7 @@ static int hdac_component_master_match(struct device *dev, void *data)
  */
 int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops)
 {
-	if (WARN_ON(!hdac_acomp))
+	if (!hdac_acomp)
 		return -ENODEV;
 
 	hdac_acomp->audio_ops = aops;
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index a81aacf684b2..37e1cf8218ff 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -271,6 +271,8 @@ enum {
 	CXT_FIXUP_HP_SPECTRE,
 	CXT_FIXUP_HP_GATE_MIC,
 	CXT_FIXUP_MUTE_LED_GPIO,
+	CXT_FIXUP_HEADSET_MIC,
+	CXT_FIXUP_HP_MIC_NO_PRESENCE,
 };
 
 /* for hda_fixup_thinkpad_acpi() */
@@ -350,6 +352,18 @@ static void cxt_fixup_headphone_mic(struct hda_codec *codec,
 	}
 }
 
+static void cxt_fixup_headset_mic(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	struct conexant_spec *spec = codec->spec;
+
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		spec->parse_flags |= HDA_PINCFG_HEADSET_MIC;
+		break;
+	}
+}
+
 /* OPLC XO 1.5 fixup */
 
 /* OLPC XO-1.5 supports DC input mode (e.g. for use with analog sensors)
@@ -880,6 +894,19 @@ static const struct hda_fixup cxt_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cxt_fixup_mute_led_gpio,
 	},
+	[CXT_FIXUP_HEADSET_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = cxt_fixup_headset_mic,
+	},
+	[CXT_FIXUP_HP_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1a, 0x02a1113c },
+			{ }
+		},
+		.chained = true,
+		.chain_id = CXT_FIXUP_HEADSET_MIC,
+	},
 };
 
 static const struct snd_pci_quirk cxt5045_fixups[] = {
@@ -934,6 +961,8 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
+	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
 	SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 6a4db00511ab..8fd2d9c62c96 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -324,8 +324,12 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0292:
 		alc_update_coef_idx(codec, 0x4, 1<<15, 0);
 		break;
-	case 0x10ec0215:
 	case 0x10ec0225:
+	case 0x10ec0295:
+	case 0x10ec0299:
+		alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
+		/* fallthrough */
+	case 0x10ec0215:
 	case 0x10ec0233:
 	case 0x10ec0236:
 	case 0x10ec0255:
@@ -336,10 +340,8 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0286:
 	case 0x10ec0288:
 	case 0x10ec0285:
-	case 0x10ec0295:
 	case 0x10ec0298:
 	case 0x10ec0289:
-	case 0x10ec0299:
 		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
 		break;
 	case 0x10ec0275:
@@ -6328,6 +6330,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+	SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
@@ -6586,6 +6589,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x1b, 0x01011020},
 		{0x21, 0x02211010}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60130},
+		{0x14, 0x90170110},
+		{0x1b, 0x01011020},
+		{0x21, 0x0221101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60160},
 		{0x14, 0x90170120},
 		{0x21, 0x02211030}),
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 9f521a55d610..b5e41df6bb3a 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -1051,6 +1051,11 @@ static int acp_audio_probe(struct platform_device *pdev)
 	struct resource *res;
 	const u32 *pdata = pdev->dev.platform_data;
 
+	if (!pdata) {
+		dev_err(&pdev->dev, "Missing platform data\n");
+		return -ENODEV;
+	}
+
 	audio_drv_data = devm_kzalloc(&pdev->dev, sizeof(struct audio_drv_data),
 					GFP_KERNEL);
 	if (audio_drv_data == NULL)
@@ -1058,6 +1063,8 @@ static int acp_audio_probe(struct platform_device *pdev)
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	audio_drv_data->acp_mmio = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(audio_drv_data->acp_mmio))
+		return PTR_ERR(audio_drv_data->acp_mmio);
 
 	/* The following members gets populated in device 'open'
 	 * function. Till then interrupts are disabled in 'acp_init'
diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig
index 4a56f3dfba51..dcee145dd179 100644
--- a/sound/soc/atmel/Kconfig
+++ b/sound/soc/atmel/Kconfig
@@ -64,7 +64,7 @@ config SND_AT91_SOC_SAM9X5_WM8731
 config SND_ATMEL_SOC_CLASSD
 	tristate "Atmel ASoC driver for boards using CLASSD"
 	depends on ARCH_AT91 || COMPILE_TEST
-	select SND_ATMEL_SOC_DMA
+	select SND_SOC_GENERIC_DMAENGINE_PCM
 	select REGMAP_MMIO
 	help
 	  Say Y if you want to add support for Atmel ASoC driver for boards using
diff --git a/sound/soc/codecs/da7218.c b/sound/soc/codecs/da7218.c
index b2d42ec1dcd9..56564ce90cb6 100644
--- a/sound/soc/codecs/da7218.c
+++ b/sound/soc/codecs/da7218.c
@@ -2520,7 +2520,7 @@ static struct da7218_pdata *da7218_of_to_pdata(struct snd_soc_codec *codec)
 	}
 
 	if (da7218->dev_id == DA7218_DEV_ID) {
-		hpldet_np = of_find_node_by_name(np, "da7218_hpldet");
+		hpldet_np = of_get_child_by_name(np, "da7218_hpldet");
 		if (!hpldet_np)
 			return pdata;
 
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index 5f3c42c4f74a..066ea2f4ce7b 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -267,7 +267,7 @@
 #define MSM8916_WCD_ANALOG_RATES (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
 			SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000)
 #define MSM8916_WCD_ANALOG_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
-				    SNDRV_PCM_FMTBIT_S24_LE)
+				    SNDRV_PCM_FMTBIT_S32_LE)
 
 static int btn_mask = SND_JACK_BTN_0 | SND_JACK_BTN_1 |
 	       SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_BTN_4;
diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c
index a10a724eb448..13354d6304a8 100644
--- a/sound/soc/codecs/msm8916-wcd-digital.c
+++ b/sound/soc/codecs/msm8916-wcd-digital.c
@@ -194,7 +194,7 @@
 				   SNDRV_PCM_RATE_32000 | \
 				   SNDRV_PCM_RATE_48000)
 #define MSM8916_WCD_DIGITAL_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
-				     SNDRV_PCM_FMTBIT_S24_LE)
+				     SNDRV_PCM_FMTBIT_S32_LE)
 
 struct msm8916_wcd_digital_priv {
 	struct clk *ahbclk, *mclk;
@@ -645,7 +645,7 @@ static int msm8916_wcd_digital_hw_params(struct snd_pcm_substream *substream,
 				    RX_I2S_CTL_RX_I2S_MODE_MASK,
 				    RX_I2S_CTL_RX_I2S_MODE_16);
 		break;
-	case SNDRV_PCM_FORMAT_S24_LE:
+	case SNDRV_PCM_FORMAT_S32_LE:
 		snd_soc_update_bits(dai->codec, LPASS_CDC_CLK_TX_I2S_CTL,
 				    TX_I2S_CTL_TX_I2S_MODE_MASK,
 				    TX_I2S_CTL_TX_I2S_MODE_32);
diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index 714ce17da717..e853a6dfd33b 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -905,6 +905,7 @@ static int nau8825_adc_event(struct snd_soc_dapm_widget *w,
 
 	switch (event) {
 	case SND_SOC_DAPM_POST_PMU:
+		msleep(125);
 		regmap_update_bits(nau8825->regmap, NAU8825_REG_ENA_CTRL,
 			NAU8825_ENABLE_ADC, NAU8825_ENABLE_ADC);
 		break;
diff --git a/sound/soc/codecs/rt5514-spi.c b/sound/soc/codecs/rt5514-spi.c
index 2df91db765ac..64bf26cec20d 100644
--- a/sound/soc/codecs/rt5514-spi.c
+++ b/sound/soc/codecs/rt5514-spi.c
@@ -289,6 +289,8 @@ static int rt5514_spi_pcm_probe(struct snd_soc_platform *platform)
 			dev_err(&rt5514_spi->dev,
 				"%s Failed to reguest IRQ: %d\n", __func__,
 				ret);
+		else
+			device_init_wakeup(rt5514_dsp->dev, true);
 	}
 
 	return 0;
@@ -456,8 +458,6 @@ static int rt5514_spi_probe(struct spi_device *spi)
 		return ret;
 	}
 
-	device_init_wakeup(&spi->dev, true);
-
 	return 0;
 }
 
@@ -482,10 +482,13 @@ static int __maybe_unused rt5514_resume(struct device *dev)
 	if (device_may_wakeup(dev))
 		disable_irq_wake(irq);
 
-	if (rt5514_dsp->substream) {
-		rt5514_spi_burst_read(RT5514_IRQ_CTRL, (u8 *)&buf, sizeof(buf));
-		if (buf[0] & RT5514_IRQ_STATUS_BIT)
-			rt5514_schedule_copy(rt5514_dsp);
+	if (rt5514_dsp) {
+		if (rt5514_dsp->substream) {
+			rt5514_spi_burst_read(RT5514_IRQ_CTRL, (u8 *)&buf,
+				sizeof(buf));
+			if (buf[0] & RT5514_IRQ_STATUS_BIT)
+				rt5514_schedule_copy(rt5514_dsp);
+		}
 	}
 
 	return 0;
diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c
index 2a5b5d74e697..2dd6e9f990a4 100644
--- a/sound/soc/codecs/rt5514.c
+++ b/sound/soc/codecs/rt5514.c
@@ -496,7 +496,7 @@ static const struct snd_soc_dapm_widget rt5514_dapm_widgets[] = {
 	SND_SOC_DAPM_PGA("DMIC1", SND_SOC_NOPM, 0, 0, NULL, 0),
 	SND_SOC_DAPM_PGA("DMIC2", SND_SOC_NOPM, 0, 0, NULL, 0),
 
-	SND_SOC_DAPM_SUPPLY("DMIC CLK", SND_SOC_NOPM, 0, 0,
+	SND_SOC_DAPM_SUPPLY_S("DMIC CLK", 1, SND_SOC_NOPM, 0, 0,
 		rt5514_set_dmic_clk, SND_SOC_DAPM_PRE_PMU),
 
 	SND_SOC_DAPM_SUPPLY("ADC CLK", RT5514_CLK_CTRL1,
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index f020d2d1eef4..edc152c8a1fe 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3823,6 +3823,8 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
 	regmap_read(regmap, RT5645_VENDOR_ID, &val);
 	rt5645->v_id = val & 0xff;
 
+	regmap_write(rt5645->regmap, RT5645_AD_DA_MIXER, 0x8080);
+
 	ret = regmap_register_patch(rt5645->regmap, init_list,
 				    ARRAY_SIZE(init_list));
 	if (ret != 0)
diff --git a/sound/soc/codecs/rt5663.c b/sound/soc/codecs/rt5663.c
index b036c9dc0c8c..d329bf719d80 100644
--- a/sound/soc/codecs/rt5663.c
+++ b/sound/soc/codecs/rt5663.c
@@ -1560,6 +1560,10 @@ static int rt5663_jack_detect(struct snd_soc_codec *codec, int jack_insert)
 			RT5663_IRQ_POW_SAV_MASK, RT5663_IRQ_POW_SAV_EN);
 		snd_soc_update_bits(codec, RT5663_IRQ_1,
 			RT5663_EN_IRQ_JD1_MASK, RT5663_EN_IRQ_JD1_EN);
+		snd_soc_update_bits(codec, RT5663_EM_JACK_TYPE_1,
+			RT5663_EM_JD_MASK, RT5663_EM_JD_RST);
+		snd_soc_update_bits(codec, RT5663_EM_JACK_TYPE_1,
+			RT5663_EM_JD_MASK, RT5663_EM_JD_NOR);
 
 		while (true) {
 			regmap_read(rt5663->regmap, RT5663_INT_ST_2, &val);
diff --git a/sound/soc/codecs/rt5663.h b/sound/soc/codecs/rt5663.h
index c5a9b69579ad..03adc8004ba9 100644
--- a/sound/soc/codecs/rt5663.h
+++ b/sound/soc/codecs/rt5663.h
@@ -1029,6 +1029,10 @@
 #define RT5663_POL_EXT_JD_SHIFT			10
 #define RT5663_POL_EXT_JD_EN			(0x1 << 10)
 #define RT5663_POL_EXT_JD_DIS			(0x0 << 10)
+#define RT5663_EM_JD_MASK			(0x1 << 7)
+#define RT5663_EM_JD_SHIFT			7
+#define RT5663_EM_JD_NOR			(0x1 << 7)
+#define RT5663_EM_JD_RST			(0x0 << 7)
 
 /* DACREF LDO Control (0x0112)*/
 #define RT5663_PWR_LDO_DACREFL_MASK		(0x1 << 9)
diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h
index 730fb2058869..1ff3edb7bbb6 100644
--- a/sound/soc/codecs/tlv320aic31xx.h
+++ b/sound/soc/codecs/tlv320aic31xx.h
@@ -116,7 +116,7 @@ struct aic31xx_pdata {
 /* INT2 interrupt control */
 #define AIC31XX_INT2CTRL	AIC31XX_REG(0, 49)
 /* GPIO1 control */
-#define AIC31XX_GPIO1		AIC31XX_REG(0, 50)
+#define AIC31XX_GPIO1		AIC31XX_REG(0, 51)
 
 #define AIC31XX_DACPRB		AIC31XX_REG(0, 60)
 /* ADC Instruction Set Register */
diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c
index c482b2e7a7d2..cfe72b9d4356 100644
--- a/sound/soc/codecs/twl4030.c
+++ b/sound/soc/codecs/twl4030.c
@@ -232,7 +232,7 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
 	struct twl4030_codec_data *pdata = dev_get_platdata(codec->dev);
 	struct device_node *twl4030_codec_node = NULL;
 
-	twl4030_codec_node = of_find_node_by_name(codec->dev->parent->of_node,
+	twl4030_codec_node = of_get_child_by_name(codec->dev->parent->of_node,
 						  "codec");
 
 	if (!pdata && twl4030_codec_node) {
@@ -241,9 +241,11 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
 				     GFP_KERNEL);
 		if (!pdata) {
 			dev_err(codec->dev, "Can not allocate memory\n");
+			of_node_put(twl4030_codec_node);
 			return NULL;
 		}
 		twl4030_setup_pdata_of(pdata, twl4030_codec_node);
+		of_node_put(twl4030_codec_node);
 	}
 
 	return pdata;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 65c059b5ffd7..66e32f5d2917 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1733,7 +1733,7 @@ static int wm_adsp_load(struct wm_adsp *dsp)
 		 le64_to_cpu(footer->timestamp));
 
 	while (pos < firmware->size &&
-	       pos - firmware->size > sizeof(*region)) {
+	       sizeof(*region) < firmware->size - pos) {
 		region = (void *)&(firmware->data[pos]);
 		region_name = "Unknown";
 		reg = 0;
@@ -1782,8 +1782,8 @@ static int wm_adsp_load(struct wm_adsp *dsp)
 			 regions, le32_to_cpu(region->len), offset,
 			 region_name);
 
-		if ((pos + le32_to_cpu(region->len) + sizeof(*region)) >
-		    firmware->size) {
+		if (le32_to_cpu(region->len) >
+		    firmware->size - pos - sizeof(*region)) {
 			adsp_err(dsp,
 				 "%s.%d: %s region len %d bytes exceeds file length %zu\n",
 				 file, regions, region_name,
@@ -2253,7 +2253,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
 
 	blocks = 0;
 	while (pos < firmware->size &&
-	       pos - firmware->size > sizeof(*blk)) {
+	       sizeof(*blk) < firmware->size - pos) {
 		blk = (void *)(&firmware->data[pos]);
 
 		type = le16_to_cpu(blk->type);
@@ -2327,8 +2327,8 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
 		}
 
 		if (reg) {
-			if ((pos + le32_to_cpu(blk->len) + sizeof(*blk)) >
-			    firmware->size) {
+			if (le32_to_cpu(blk->len) >
+			    firmware->size - pos - sizeof(*blk)) {
 				adsp_err(dsp,
 					 "%s.%d: %s region len %d bytes exceeds file length %zu\n",
 					 file, blocks, region_name,
diff --git a/sound/soc/fsl/fsl_asrc.h b/sound/soc/fsl/fsl_asrc.h
index 0f163abe4ba3..52c27a358933 100644
--- a/sound/soc/fsl/fsl_asrc.h
+++ b/sound/soc/fsl/fsl_asrc.h
@@ -260,8 +260,8 @@
 #define ASRFSTi_OUTPUT_FIFO_SHIFT	12
 #define ASRFSTi_OUTPUT_FIFO_MASK	(((1 << ASRFSTi_OUTPUT_FIFO_WIDTH) - 1) << ASRFSTi_OUTPUT_FIFO_SHIFT)
 #define ASRFSTi_IAEi_SHIFT		11
-#define ASRFSTi_IAEi_MASK		(1 << ASRFSTi_OAFi_SHIFT)
-#define ASRFSTi_IAEi			(1 << ASRFSTi_OAFi_SHIFT)
+#define ASRFSTi_IAEi_MASK		(1 << ASRFSTi_IAEi_SHIFT)
+#define ASRFSTi_IAEi			(1 << ASRFSTi_IAEi_SHIFT)
 #define ASRFSTi_INPUT_FIFO_WIDTH	7
 #define ASRFSTi_INPUT_FIFO_SHIFT	0
 #define ASRFSTi_INPUT_FIFO_MASK		((1 << ASRFSTi_INPUT_FIFO_WIDTH) - 1)
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index f2f51e06e22c..424bafaf51ef 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -38,6 +38,7 @@
 #include <linux/ctype.h>
 #include <linux/device.h>
 #include <linux/delay.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/of.h>
@@ -265,6 +266,8 @@ struct fsl_ssi_private {
 
 	u32 fifo_watermark;
 	u32 dma_maxburst;
+
+	struct mutex ac97_reg_lock;
 };
 
 /*
@@ -1260,11 +1263,13 @@ static void fsl_ssi_ac97_write(struct snd_ac97 *ac97, unsigned short reg,
 	if (reg > 0x7f)
 		return;
 
+	mutex_lock(&fsl_ac97_data->ac97_reg_lock);
+
 	ret = clk_prepare_enable(fsl_ac97_data->clk);
 	if (ret) {
 		pr_err("ac97 write clk_prepare_enable failed: %d\n",
 			ret);
-		return;
+		goto ret_unlock;
 	}
 
 	lreg = reg <<  12;
@@ -1278,6 +1283,9 @@ static void fsl_ssi_ac97_write(struct snd_ac97 *ac97, unsigned short reg,
 	udelay(100);
 
 	clk_disable_unprepare(fsl_ac97_data->clk);
+
+ret_unlock:
+	mutex_unlock(&fsl_ac97_data->ac97_reg_lock);
 }
 
 static unsigned short fsl_ssi_ac97_read(struct snd_ac97 *ac97,
@@ -1285,16 +1293,18 @@ static unsigned short fsl_ssi_ac97_read(struct snd_ac97 *ac97,
 {
 	struct regmap *regs = fsl_ac97_data->regs;
 
-	unsigned short val = -1;
+	unsigned short val = 0;
 	u32 reg_val;
 	unsigned int lreg;
 	int ret;
 
+	mutex_lock(&fsl_ac97_data->ac97_reg_lock);
+
 	ret = clk_prepare_enable(fsl_ac97_data->clk);
 	if (ret) {
 		pr_err("ac97 read clk_prepare_enable failed: %d\n",
 			ret);
-		return -1;
+		goto ret_unlock;
 	}
 
 	lreg = (reg & 0x7f) <<  12;
@@ -1309,6 +1319,8 @@ static unsigned short fsl_ssi_ac97_read(struct snd_ac97 *ac97,
 
 	clk_disable_unprepare(fsl_ac97_data->clk);
 
+ret_unlock:
+	mutex_unlock(&fsl_ac97_data->ac97_reg_lock);
 	return val;
 }
 
@@ -1458,12 +1470,6 @@ static int fsl_ssi_probe(struct platform_device *pdev)
 				sizeof(fsl_ssi_ac97_dai));
 
 		fsl_ac97_data = ssi_private;
-
-		ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
-		if (ret) {
-			dev_err(&pdev->dev, "could not set AC'97 ops\n");
-			return ret;
-		}
 	} else {
 		/* Initialize this copy of the CPU DAI driver structure */
 		memcpy(&ssi_private->cpu_dai_drv, &fsl_ssi_dai_template,
@@ -1574,6 +1580,15 @@ static int fsl_ssi_probe(struct platform_device *pdev)
 			return ret;
 	}
 
+	if (fsl_ssi_is_ac97(ssi_private)) {
+		mutex_init(&ssi_private->ac97_reg_lock);
+		ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
+		if (ret) {
+			dev_err(&pdev->dev, "could not set AC'97 ops\n");
+			goto error_ac97_ops;
+		}
+	}
+
 	ret = devm_snd_soc_register_component(&pdev->dev, &fsl_ssi_component,
 					      &ssi_private->cpu_dai_drv, 1);
 	if (ret) {
@@ -1657,6 +1672,13 @@ error_sound_card:
 	fsl_ssi_debugfs_remove(&ssi_private->dbg_stats);
 
 error_asoc_register:
+	if (fsl_ssi_is_ac97(ssi_private))
+		snd_soc_set_ac97_ops(NULL);
+
+error_ac97_ops:
+	if (fsl_ssi_is_ac97(ssi_private))
+		mutex_destroy(&ssi_private->ac97_reg_lock);
+
 	if (ssi_private->soc->imx)
 		fsl_ssi_imx_clean(pdev, ssi_private);
 
@@ -1675,8 +1697,10 @@ static int fsl_ssi_remove(struct platform_device *pdev)
 	if (ssi_private->soc->imx)
 		fsl_ssi_imx_clean(pdev, ssi_private);
 
-	if (fsl_ssi_is_ac97(ssi_private))
+	if (fsl_ssi_is_ac97(ssi_private)) {
 		snd_soc_set_ac97_ops(NULL);
+		mutex_destroy(&ssi_private->ac97_reg_lock);
+	}
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c
index 6f9a8bcf20f3..6dcad0a8a0d0 100644
--- a/sound/soc/intel/boards/kbl_rt5663_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c
@@ -101,7 +101,7 @@ static const struct snd_soc_dapm_route kabylake_map[] = {
 	{ "ssp0 Tx", NULL, "spk_out" },
 
 	{ "AIF Playback", NULL, "ssp1 Tx" },
-	{ "ssp1 Tx", NULL, "hs_out" },
+	{ "ssp1 Tx", NULL, "codec1_out" },
 
 	{ "hs_in", NULL, "ssp1 Rx" },
 	{ "ssp1 Rx", NULL, "AIF Capture" },
diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
index 6072164f2d43..271ae3c2c535 100644
--- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
@@ -109,7 +109,7 @@ static const struct snd_soc_dapm_route kabylake_map[] = {
 	{ "ssp0 Tx", NULL, "spk_out" },
 
 	{ "AIF Playback", NULL, "ssp1 Tx" },
-	{ "ssp1 Tx", NULL, "hs_out" },
+	{ "ssp1 Tx", NULL, "codec1_out" },
 
 	{ "hs_in", NULL, "ssp1 Rx" },
 	{ "ssp1 Rx", NULL, "AIF Capture" },
diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c
index d14c50a60289..3eaac41090ca 100644
--- a/sound/soc/intel/skylake/skl-nhlt.c
+++ b/sound/soc/intel/skylake/skl-nhlt.c
@@ -119,11 +119,16 @@ static bool skl_check_ep_match(struct device *dev, struct nhlt_endpoint *epnt,
 
 	if ((epnt->virtual_bus_id == instance_id) &&
 			(epnt->linktype == link_type) &&
-			(epnt->direction == dirn) &&
-			(epnt->device_type == dev_type))
-		return true;
-	else
-		return false;
+			(epnt->direction == dirn)) {
+		/* do not check dev_type for DMIC link type */
+		if (epnt->linktype == NHLT_LINK_DMIC)
+			return true;
+
+		if (epnt->device_type == dev_type)
+			return true;
+	}
+
+	return false;
 }
 
 struct nhlt_specific_cfg
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index a072bcf209d2..81923da18ac2 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -2908,7 +2908,7 @@ static int skl_tplg_control_load(struct snd_soc_component *cmpnt,
 		break;
 
 	default:
-		dev_warn(bus->dev, "Control load not supported %d:%d:%d\n",
+		dev_dbg(bus->dev, "Control load not supported %d:%d:%d\n",
 			hdr->ops.get, hdr->ops.put, hdr->ops.info);
 		break;
 	}
diff --git a/sound/soc/rockchip/rockchip_spdif.c b/sound/soc/rockchip/rockchip_spdif.c
index ee5055d47d13..a89fe9b6463b 100644
--- a/sound/soc/rockchip/rockchip_spdif.c
+++ b/sound/soc/rockchip/rockchip_spdif.c
@@ -322,26 +322,30 @@ static int rk_spdif_probe(struct platform_device *pdev)
 	spdif->mclk = devm_clk_get(&pdev->dev, "mclk");
 	if (IS_ERR(spdif->mclk)) {
 		dev_err(&pdev->dev, "Can't retrieve rk_spdif master clock\n");
-		return PTR_ERR(spdif->mclk);
+		ret = PTR_ERR(spdif->mclk);
+		goto err_disable_hclk;
 	}
 
 	ret = clk_prepare_enable(spdif->mclk);
 	if (ret) {
 		dev_err(spdif->dev, "clock enable failed %d\n", ret);
-		return ret;
+		goto err_disable_clocks;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	regs = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(regs))
-		return PTR_ERR(regs);
+	if (IS_ERR(regs)) {
+		ret = PTR_ERR(regs);
+		goto err_disable_clocks;
+	}
 
 	spdif->regmap = devm_regmap_init_mmio_clk(&pdev->dev, "hclk", regs,
 						  &rk_spdif_regmap_config);
 	if (IS_ERR(spdif->regmap)) {
 		dev_err(&pdev->dev,
 			"Failed to initialise managed register map\n");
-		return PTR_ERR(spdif->regmap);
+		ret = PTR_ERR(spdif->regmap);
+		goto err_disable_clocks;
 	}
 
 	spdif->playback_dma_data.addr = res->start + SPDIF_SMPDR;
@@ -373,6 +377,10 @@ static int rk_spdif_probe(struct platform_device *pdev)
 
 err_pm_runtime:
 	pm_runtime_disable(&pdev->dev);
+err_disable_clocks:
+	clk_disable_unprepare(spdif->mclk);
+err_disable_hclk:
+	clk_disable_unprepare(spdif->hclk);
 
 	return ret;
 }
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 8ddb08714faa..4672688cac32 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -222,7 +222,7 @@ int rsnd_adg_set_cmd_timsel_gen2(struct rsnd_mod *cmd_mod,
 				   NULL, &val, NULL);
 
 	val  = val	<< shift;
-	mask = 0xffff	<< shift;
+	mask = 0x0f1f	<< shift;
 
 	rsnd_mod_bset(adg_mod, CMDOUT_TIMSEL, mask, val);
 
@@ -250,7 +250,7 @@ int rsnd_adg_set_src_timesel_gen2(struct rsnd_mod *src_mod,
 
 	in   = in	<< shift;
 	out  = out	<< shift;
-	mask = 0xffff	<< shift;
+	mask = 0x0f1f	<< shift;
 
 	switch (id / 2) {
 	case 0:
@@ -380,7 +380,7 @@ int rsnd_adg_ssi_clk_try_start(struct rsnd_mod *ssi_mod, unsigned int rate)
 			ckr = 0x80000000;
 	}
 
-	rsnd_mod_bset(adg_mod, BRGCKR, 0x80FF0000, adg->ckr | ckr);
+	rsnd_mod_bset(adg_mod, BRGCKR, 0x80770000, adg->ckr | ckr);
 	rsnd_mod_write(adg_mod, BRRA,  adg->rbga);
 	rsnd_mod_write(adg_mod, BRRB,  adg->rbgb);
 
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index c70eb2097816..f12a88a21dfa 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -1332,8 +1332,8 @@ static int rsnd_pcm_new(struct snd_soc_pcm_runtime *rtd)
 
 	return snd_pcm_lib_preallocate_pages_for_all(
 		rtd->pcm,
-		SNDRV_DMA_TYPE_CONTINUOUS,
-		snd_dma_continuous_data(GFP_KERNEL),
+		SNDRV_DMA_TYPE_DEV,
+		rtd->card->snd_card->dev,
 		PREALLOC_BUFFER, PREALLOC_BUFFER_MAX);
 }
 
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index fd557abfe390..4d750bdf8e24 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -26,10 +26,7 @@
 struct rsnd_dmaen {
 	struct dma_chan		*chan;
 	dma_cookie_t		cookie;
-	dma_addr_t		dma_buf;
 	unsigned int		dma_len;
-	unsigned int		dma_period;
-	unsigned int		dma_cnt;
 };
 
 struct rsnd_dmapp {
@@ -71,38 +68,10 @@ static struct rsnd_mod mem = {
 /*
  *		Audio DMAC
  */
-#define rsnd_dmaen_sync(dmaen, io, i)	__rsnd_dmaen_sync(dmaen, io, i, 1)
-#define rsnd_dmaen_unsync(dmaen, io, i)	__rsnd_dmaen_sync(dmaen, io, i, 0)
-static void __rsnd_dmaen_sync(struct rsnd_dmaen *dmaen, struct rsnd_dai_stream *io,
-			      int i, int sync)
-{
-	struct device *dev = dmaen->chan->device->dev;
-	enum dma_data_direction dir;
-	int is_play = rsnd_io_is_play(io);
-	dma_addr_t buf;
-	int len, max;
-	size_t period;
-
-	len	= dmaen->dma_len;
-	period	= dmaen->dma_period;
-	max	= len / period;
-	i	= i % max;
-	buf	= dmaen->dma_buf + (period * i);
-
-	dir = is_play ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
-
-	if (sync)
-		dma_sync_single_for_device(dev, buf, period, dir);
-	else
-		dma_sync_single_for_cpu(dev, buf, period, dir);
-}
-
 static void __rsnd_dmaen_complete(struct rsnd_mod *mod,
 				  struct rsnd_dai_stream *io)
 {
 	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
-	struct rsnd_dma *dma = rsnd_mod_to_dma(mod);
-	struct rsnd_dmaen *dmaen = rsnd_dma_to_dmaen(dma);
 	bool elapsed = false;
 	unsigned long flags;
 
@@ -115,22 +84,9 @@ static void __rsnd_dmaen_complete(struct rsnd_mod *mod,
 	 */
 	spin_lock_irqsave(&priv->lock, flags);
 
-	if (rsnd_io_is_working(io)) {
-		rsnd_dmaen_unsync(dmaen, io, dmaen->dma_cnt);
-
-		/*
-		 * Next period is already started.
-		 * Let's sync Next Next period
-		 * see
-		 *	rsnd_dmaen_start()
-		 */
-		rsnd_dmaen_sync(dmaen, io, dmaen->dma_cnt + 2);
-
+	if (rsnd_io_is_working(io))
 		elapsed = true;
 
-		dmaen->dma_cnt++;
-	}
-
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	if (elapsed)
@@ -165,14 +121,8 @@ static int rsnd_dmaen_stop(struct rsnd_mod *mod,
 	struct rsnd_dma *dma = rsnd_mod_to_dma(mod);
 	struct rsnd_dmaen *dmaen = rsnd_dma_to_dmaen(dma);
 
-	if (dmaen->chan) {
-		int is_play = rsnd_io_is_play(io);
-
+	if (dmaen->chan)
 		dmaengine_terminate_all(dmaen->chan);
-		dma_unmap_single(dmaen->chan->device->dev,
-				 dmaen->dma_buf, dmaen->dma_len,
-				 is_play ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
-	}
 
 	return 0;
 }
@@ -237,11 +187,7 @@ static int rsnd_dmaen_start(struct rsnd_mod *mod,
 	struct device *dev = rsnd_priv_to_dev(priv);
 	struct dma_async_tx_descriptor *desc;
 	struct dma_slave_config cfg = {};
-	dma_addr_t buf;
-	size_t len;
-	size_t period;
 	int is_play = rsnd_io_is_play(io);
-	int i;
 	int ret;
 
 	cfg.direction	= is_play ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM;
@@ -258,19 +204,10 @@ static int rsnd_dmaen_start(struct rsnd_mod *mod,
 	if (ret < 0)
 		return ret;
 
-	len	= snd_pcm_lib_buffer_bytes(substream);
-	period	= snd_pcm_lib_period_bytes(substream);
-	buf	= dma_map_single(dmaen->chan->device->dev,
-				 substream->runtime->dma_area,
-				 len,
-				 is_play ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
-	if (dma_mapping_error(dmaen->chan->device->dev, buf)) {
-		dev_err(dev, "dma map failed\n");
-		return -EIO;
-	}
-
 	desc = dmaengine_prep_dma_cyclic(dmaen->chan,
-					 buf, len, period,
+					 substream->runtime->dma_addr,
+					 snd_pcm_lib_buffer_bytes(substream),
+					 snd_pcm_lib_period_bytes(substream),
 					 is_play ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
 					 DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
@@ -282,18 +219,7 @@ static int rsnd_dmaen_start(struct rsnd_mod *mod,
 	desc->callback		= rsnd_dmaen_complete;
 	desc->callback_param	= rsnd_mod_get(dma);
 
-	dmaen->dma_buf		= buf;
-	dmaen->dma_len		= len;
-	dmaen->dma_period	= period;
-	dmaen->dma_cnt		= 0;
-
-	/*
-	 * synchronize this and next period
-	 * see
-	 *	__rsnd_dmaen_complete()
-	 */
-	for (i = 0; i < 2; i++)
-		rsnd_dmaen_sync(dmaen, io, i);
+	dmaen->dma_len		= snd_pcm_lib_buffer_bytes(substream);
 
 	dmaen->cookie = dmaengine_submit(desc);
 	if (dmaen->cookie < 0) {
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index fece1e5f582f..cbf3bf312d23 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -446,25 +446,29 @@ static bool rsnd_ssi_pointer_update(struct rsnd_mod *mod,
 				    int byte)
 {
 	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
+	bool ret = false;
+	int byte_pos;
 
-	ssi->byte_pos += byte;
+	byte_pos = ssi->byte_pos + byte;
 
-	if (ssi->byte_pos >= ssi->next_period_byte) {
+	if (byte_pos >= ssi->next_period_byte) {
 		struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
 
 		ssi->period_pos++;
 		ssi->next_period_byte += ssi->byte_per_period;
 
 		if (ssi->period_pos >= runtime->periods) {
-			ssi->byte_pos = 0;
+			byte_pos = 0;
 			ssi->period_pos = 0;
 			ssi->next_period_byte = ssi->byte_per_period;
 		}
 
-		return true;
+		ret = true;
 	}
 
-	return false;
+	WRITE_ONCE(ssi->byte_pos, byte_pos);
+
+	return ret;
 }
 
 /*
@@ -838,7 +842,7 @@ static int rsnd_ssi_pointer(struct rsnd_mod *mod,
 	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
 	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
 
-	*pointer = bytes_to_frames(runtime, ssi->byte_pos);
+	*pointer = bytes_to_frames(runtime, READ_ONCE(ssi->byte_pos));
 
 	return 0;
 }
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 4d948757d300..6ff8a36c2c82 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -125,6 +125,7 @@ static int rsnd_ssiu_init_gen2(struct rsnd_mod *mod,
 {
 	int hdmi = rsnd_ssi_hdmi_port(io);
 	int ret;
+	u32 mode = 0;
 
 	ret = rsnd_ssiu_init(mod, io, priv);
 	if (ret < 0)
@@ -136,9 +137,11 @@ static int rsnd_ssiu_init_gen2(struct rsnd_mod *mod,
 		 * see
 		 *	rsnd_ssi_config_init()
 		 */
-		rsnd_mod_write(mod, SSI_MODE, 0x1);
+		mode = 0x1;
 	}
 
+	rsnd_mod_write(mod, SSI_MODE, mode);
+
 	if (rsnd_ssi_use_busif(io)) {
 		rsnd_mod_write(mod, SSI_BUSIF_ADINR,
 			       rsnd_get_adinr_bit(mod, io) |
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e2450c8e88e6..a8c3a33dd185 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -523,21 +523,23 @@ static int do_show(int argc, char **argv)
 				break;
 			p_err("can't get next map: %s%s", strerror(errno),
 			      errno == EINVAL ? " -- kernel too old?" : "");
-			return -1;
+			break;
 		}
 
 		fd = bpf_map_get_fd_by_id(id);
 		if (fd < 0) {
+			if (errno == ENOENT)
+				continue;
 			p_err("can't get map by id (%u): %s",
 			      id, strerror(errno));
-			return -1;
+			break;
 		}
 
 		err = bpf_obj_get_info_by_fd(fd, &info, &len);
 		if (err) {
 			p_err("can't get map info: %s", strerror(errno));
 			close(fd);
-			return -1;
+			break;
 		}
 
 		if (json_output)
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 42ee8892549c..fd0873178503 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -383,6 +383,8 @@ static int do_show(int argc, char **argv)
 
 		fd = bpf_prog_get_fd_by_id(id);
 		if (fd < 0) {
+			if (errno == ENOENT)
+				continue;
 			p_err("can't get prog by id (%u): %s",
 			      id, strerror(errno));
 			err = -1;
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f1fdb36269f2..1304753d29ea 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -41,7 +41,7 @@ $(BPFOBJ): force
 CLANG ?= clang
 LLC   ?= llc
 
-PROBE := $(shell llc -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
+PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
 
 # Let newer LLVM versions transparently probe the kernel for availability
 # of full BPF instruction set.
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 66e5ce5b91f0..0304ffb714f2 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -627,13 +627,10 @@ static void do_multicpu_tests(void)
 static int finish_exec_test(void)
 {
 	/*
-	 * In a sensible world, this would be check_invalid_segment(0, 1);
-	 * For better or for worse, though, the LDT is inherited across exec.
-	 * We can probably change this safely, but for now we test it.
+	 * Older kernel versions did inherit the LDT on exec() which is
+	 * wrong because exec() starts from a clean state.
 	 */
-	check_valid_segment(0, 1,
-			    AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB,
-			    42, true);
+	check_invalid_segment(0, 1);
 
 	return nerrs ? 1 : 0;
 }