diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers b/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers
index 45985e411f13..721a05b90109 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers
@@ -10,7 +10,7 @@ Description:	A collection of all the memory tiers allocated.
 
 
 What:		/sys/devices/virtual/memory_tiering/memory_tierN/
-		/sys/devices/virtual/memory_tiering/memory_tierN/nodes
+		/sys/devices/virtual/memory_tiering/memory_tierN/nodelist
 Date:		August 2022
 Contact:	Linux memory management mailing list <linux-mm@kvack.org>
 Description:	Directory with details of a specific memory tier
@@ -21,5 +21,5 @@ Description:	Directory with details of a specific memory tier
 		A smaller value of N implies a higher (faster) memory tier in the
 		hierarchy.
 
-		nodes: NUMA nodes that are part of this memory tier.
+		nodelist: NUMA nodes that are part of this memory tier.
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 31ccadd0f8de..7a7e83165395 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14530,7 +14530,7 @@ L:	linux-nilfs@vger.kernel.org
 S:	Supported
 W:	https://nilfs.sourceforge.io/
 W:	https://nilfs.osdn.jp/
-T:	git git://github.com/konis/nilfs2.git
+T:	git https://github.com/konis/nilfs2.git
 F:	Documentation/filesystems/nilfs2.rst
 F:	fs/nilfs2/
 F:	include/trace/events/nilfs2.h
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
index fab8332fe1ad..751921f6db46 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
@@ -32,6 +32,11 @@ static inline void arch_enter_lazy_mmu_mode(void)
 
 	if (radix_enabled())
 		return;
+	/*
+	 * apply_to_page_range can call us this preempt enabled when
+	 * operating on kernel page tables.
+	 */
+	preempt_disable();
 	batch = this_cpu_ptr(&ppc64_tlb_batch);
 	batch->active = 1;
 }
@@ -47,6 +52,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	if (batch->index)
 		__flush_tlb_pending(batch);
 	batch->active = 0;
+	preempt_enable();
 }
 
 #define arch_flush_lazy_mmu_mode()      do {} while (0)
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 930e36099015..2f68fb2ee4fc 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -813,6 +813,13 @@ kernel_dbg_exc:
 	EXCEPTION_COMMON(0x260)
 	CHECK_NAPPING()
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+	/*
+	 * XXX: Returning from performance_monitor_exception taken as a
+	 * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return
+	 * and could cause bugs in return or elsewhere. That case should just
+	 * restore registers and return. There is a workaround for one known
+	 * problem in interrupt_exit_kernel_prepare().
+	 */
 	bl	performance_monitor_exception
 	b	interrupt_return
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 5381a43e50fe..651c36b056bd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2357,9 +2357,21 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
 EXC_COMMON_BEGIN(performance_monitor_common)
 	GEN_COMMON performance_monitor
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	performance_monitor_exception
+	lbz	r4,PACAIRQSOFTMASK(r13)
+	cmpdi	r4,IRQS_ENABLED
+	bne	1f
+	bl	performance_monitor_exception_async
 	b	interrupt_return_srr
+1:
+	bl	performance_monitor_exception_nmi
+	/* Clear MSR_RI before setting SRR0 and SRR1. */
+	li	r9,0
+	mtmsrd	r9,1
 
+	kuap_kernel_restore r9, r10
+
+	EXCEPTION_RESTORE_REGS hsrr=0
+	RFI_TO_KERNEL
 
 /**
  * Interrupt 0xf20 - Vector Unavailable Interrupt.
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index f9db0a172401..fc6631a80527 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -374,10 +374,18 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 	if (regs_is_unrecoverable(regs))
 		unrecoverable_exception(regs);
 	/*
-	 * CT_WARN_ON comes here via program_check_exception,
-	 * so avoid recursion.
+	 * CT_WARN_ON comes here via program_check_exception, so avoid
+	 * recursion.
+	 *
+	 * Skip the assertion on PMIs on 64e to work around a problem caused
+	 * by NMI PMIs incorrectly taking this interrupt return path, it's
+	 * possible for this to hit after interrupt exit to user switches
+	 * context to user. See also the comment in the performance monitor
+	 * handler in exceptions-64e.S
 	 */
-	if (TRAP(regs) != INTERRUPT_PROGRAM)
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
+	    TRAP(regs) != INTERRUPT_PROGRAM &&
+	    TRAP(regs) != INTERRUPT_PERFMON)
 		CT_WARN_ON(ct_state() == CONTEXT_USER);
 
 	kuap = kuap_get_and_assert_locked();
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index 978a173eb339..a019ed6fc839 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -532,15 +532,24 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
 	 * Returning to soft-disabled context.
 	 * Check if a MUST_HARD_MASK interrupt has become pending, in which
 	 * case we need to disable MSR[EE] in the return context.
+	 *
+	 * The MSR[EE] check catches among other things the short incoherency
+	 * in hard_irq_disable() between clearing MSR[EE] and setting
+	 * PACA_IRQ_HARD_DIS.
 	 */
 	ld	r12,_MSR(r1)
 	andi.	r10,r12,MSR_EE
 	beq	.Lfast_kernel_interrupt_return_\srr\() // EE already disabled
 	lbz	r11,PACAIRQHAPPENED(r13)
 	andi.	r10,r11,PACA_IRQ_MUST_HARD_MASK
-	beq	.Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending
+	bne	1f // HARD_MASK is pending
+	// No HARD_MASK pending, clear possible HARD_DIS set by interrupt
+	andi.	r11,r11,(~PACA_IRQ_HARD_DIS)@l
+	stb	r11,PACAIRQHAPPENED(r13)
+	b	.Lfast_kernel_interrupt_return_\srr\()
 
-	/* Must clear MSR_EE from _MSR */
+
+1:	/* Must clear MSR_EE from _MSR */
 #ifdef CONFIG_PPC_BOOK3S
 	li	r10,0
 	/* Clear valid before changing _MSR */
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 61cdd782d3c5..a9f57dad6d91 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -51,6 +51,7 @@ config KVM_BOOK3S_HV_POSSIBLE
 config KVM_BOOK3S_32
 	tristate "KVM support for PowerPC book3s_32 processors"
 	depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_BOOK3S_32_HANDLER
 	select KVM_BOOK3S_PR_POSSIBLE
@@ -105,6 +106,7 @@ config KVM_BOOK3S_64_HV
 config KVM_BOOK3S_64_PR
 	tristate "KVM support without using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
+	depends on !CONTEXT_TRACKING_USER
 	select KVM_BOOK3S_PR_POSSIBLE
 	help
 	  Support running guest kernels in virtual machines on processors
@@ -190,6 +192,7 @@ config KVM_EXIT_TIMING
 config KVM_E500V2
 	bool "KVM support for PowerPC E500v2 processors"
 	depends on PPC_E500 && !PPC_E500MC
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
 	select MMU_NOTIFIER
@@ -205,6 +208,7 @@ config KVM_E500V2
 config KVM_E500MC
 	bool "KVM support for PowerPC E500MC/E5500/E6500 processors"
 	depends on PPC_E500MC
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index f76a50291fd7..d491da8d1838 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -36,7 +36,17 @@ int exit_vmx_usercopy(void)
 {
 	disable_kernel_altivec();
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_no_resched();
+	/*
+	 * Must never explicitly call schedule (including preempt_enable())
+	 * while in a kuap-unlocked user copy, because the AMR register will
+	 * not be saved and restored across context switch. However preempt
+	 * kernels need to be preempted as soon as possible if need_resched is
+	 * set and we are preemptible. The hack here is to schedule a
+	 * decrementer to fire here and reschedule for us if necessary.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT) && need_resched())
+		set_dec(1);
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c
index 623a7b7ab38b..9342e79870df 100644
--- a/arch/powerpc/mm/book3s64/hash_native.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -43,6 +43,29 @@
 
 static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map hpte_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("hpte_lock", &hpte_lock_map);
+
+static void acquire_hpte_lock(void)
+{
+	lock_map_acquire(&hpte_lock_map);
+}
+
+static void release_hpte_lock(void)
+{
+	lock_map_release(&hpte_lock_map);
+}
+#else
+static void acquire_hpte_lock(void)
+{
+}
+
+static void release_hpte_lock(void)
+{
+}
+#endif
+
 static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 						int apsize, int ssize)
 {
@@ -220,6 +243,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep)
 {
 	unsigned long *word = (unsigned long *)&hptep->v;
 
+	acquire_hpte_lock();
 	while (1) {
 		if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word))
 			break;
@@ -234,6 +258,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep)
 {
 	unsigned long *word = (unsigned long *)&hptep->v;
 
+	release_hpte_lock();
 	clear_bit_unlock(HPTE_LOCK_BIT, word);
 }
 
@@ -243,8 +268,11 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 {
 	struct hash_pte *hptep = htab_address + hpte_group;
 	unsigned long hpte_v, hpte_r;
+	unsigned long flags;
 	int i;
 
+	local_irq_save(flags);
+
 	if (!(vflags & HPTE_V_BOLTED)) {
 		DBG_LOW("    insert(group=%lx, vpn=%016lx, pa=%016lx,"
 			" rflags=%lx, vflags=%lx, psize=%d)\n",
@@ -263,8 +291,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 		hptep++;
 	}
 
-	if (i == HPTES_PER_GROUP)
+	if (i == HPTES_PER_GROUP) {
+		local_irq_restore(flags);
 		return -1;
+	}
 
 	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
 	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
@@ -286,10 +316,13 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	 * Now set the first dword including the valid bit
 	 * NOTE: this also unlocks the hpte
 	 */
+	release_hpte_lock();
 	hptep->v = cpu_to_be64(hpte_v);
 
 	__asm__ __volatile__ ("ptesync" : : : "memory");
 
+	local_irq_restore(flags);
+
 	return i | (!!(vflags & HPTE_V_SECONDARY) << 3);
 }
 
@@ -327,6 +360,7 @@ static long native_hpte_remove(unsigned long hpte_group)
 		return -1;
 
 	/* Invalidate the hpte. NOTE: this also unlocks it */
+	release_hpte_lock();
 	hptep->v = 0;
 
 	return i;
@@ -339,6 +373,9 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
 	int ret = 0, local = 0;
+	unsigned long irqflags;
+
+	local_irq_save(irqflags);
 
 	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 
@@ -382,6 +419,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	if (!(flags & HPTE_NOHPTE_UPDATE))
 		tlbie(vpn, bpsize, apsize, ssize, local);
 
+	local_irq_restore(irqflags);
+
 	return ret;
 }
 
@@ -445,6 +484,9 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	unsigned long vsid;
 	long slot;
 	struct hash_pte *hptep;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	vsid = get_kernel_vsid(ea, ssize);
 	vpn = hpt_vpn(ea, vsid, ssize);
@@ -463,6 +505,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	 * actual page size will be same.
 	 */
 	tlbie(vpn, psize, psize, ssize, 0);
+
+	local_irq_restore(flags);
 }
 
 /*
@@ -476,6 +520,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
 	unsigned long vsid;
 	long slot;
 	struct hash_pte *hptep;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	vsid = get_kernel_vsid(ea, ssize);
 	vpn = hpt_vpn(ea, vsid, ssize);
@@ -493,6 +540,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
 
 	/* Invalidate the TLB */
 	tlbie(vpn, psize, psize, ssize, 0);
+
+	local_irq_restore(flags);
+
 	return 0;
 }
 
@@ -517,10 +567,11 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 		/* recheck with locks held */
 		hpte_v = hpte_get_old_v(hptep);
 
-		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
+		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) {
 			/* Invalidate the hpte. NOTE: this also unlocks it */
+			release_hpte_lock();
 			hptep->v = 0;
-		else
+		} else
 			native_unlock_hpte(hptep);
 	}
 	/*
@@ -580,10 +631,8 @@ static void native_hugepage_invalidate(unsigned long vsid,
 			hpte_v = hpte_get_old_v(hptep);
 
 			if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) {
-				/*
-				 * Invalidate the hpte. NOTE: this also unlocks it
-				 */
-
+				/* Invalidate the hpte. NOTE: this also unlocks it */
+				release_hpte_lock();
 				hptep->v = 0;
 			} else
 				native_unlock_hpte(hptep);
@@ -765,8 +814,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 
 			if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
 				native_unlock_hpte(hptep);
-			else
+			else {
+				release_hpte_lock();
 				hptep->v = 0;
+			}
 
 		} pte_iterate_hashed_end();
 	}
diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c
index 747492edb75a..51f48984abca 100644
--- a/arch/powerpc/mm/book3s64/hash_pgtable.c
+++ b/arch/powerpc/mm/book3s64/hash_pgtable.c
@@ -404,7 +404,8 @@ EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage);
 
 struct change_memory_parms {
 	unsigned long start, end, newpp;
-	unsigned int step, nr_cpus, master_cpu;
+	unsigned int step, nr_cpus;
+	atomic_t master_cpu;
 	atomic_t cpu_counter;
 };
 
@@ -478,7 +479,8 @@ static int change_memory_range_fn(void *data)
 {
 	struct change_memory_parms *parms = data;
 
-	if (parms->master_cpu != smp_processor_id())
+	// First CPU goes through, all others wait.
+	if (atomic_xchg(&parms->master_cpu, 1) == 1)
 		return chmem_secondary_loop(parms);
 
 	// Wait for all but one CPU (this one) to call-in
@@ -516,7 +518,7 @@ static bool hash__change_memory_range(unsigned long start, unsigned long end,
 		chmem_parms.end = end;
 		chmem_parms.step = step;
 		chmem_parms.newpp = newpp;
-		chmem_parms.master_cpu = smp_processor_id();
+		atomic_set(&chmem_parms.master_cpu, 0);
 
 		cpus_read_lock();
 
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index df008edf7be0..6df4c6d38b66 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1981,7 +1981,7 @@ repeat:
 }
 
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-static DEFINE_SPINLOCK(linear_map_hash_lock);
+static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
 
 static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 {
@@ -2005,10 +2005,10 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 				    mmu_linear_psize, mmu_kernel_ssize);
 
 	BUG_ON (ret < 0);
-	spin_lock(&linear_map_hash_lock);
+	raw_spin_lock(&linear_map_hash_lock);
 	BUG_ON(linear_map_hash_slots[lmi] & 0x80);
 	linear_map_hash_slots[lmi] = ret | 0x80;
-	spin_unlock(&linear_map_hash_lock);
+	raw_spin_unlock(&linear_map_hash_lock);
 }
 
 static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
@@ -2018,14 +2018,14 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
 
 	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
-	spin_lock(&linear_map_hash_lock);
+	raw_spin_lock(&linear_map_hash_lock);
 	if (!(linear_map_hash_slots[lmi] & 0x80)) {
-		spin_unlock(&linear_map_hash_lock);
+		raw_spin_unlock(&linear_map_hash_lock);
 		return;
 	}
 	hidx = linear_map_hash_slots[lmi] & 0x7f;
 	linear_map_hash_slots[lmi] = 0;
-	spin_unlock(&linear_map_hash_lock);
+	raw_spin_unlock(&linear_map_hash_lock);
 	if (hidx & _PTEIDX_SECONDARY)
 		hash = ~hash;
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 507dc0b5987d..63fd925ccbb8 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -35,6 +35,7 @@
 #include <asm/drmem.h>
 
 #include "pseries.h"
+#include "vas.h"	/* pseries_vas_dlpar_cpu() */
 
 /*
  * This isn't a module but we expose that to userspace
@@ -748,6 +749,16 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf,
 			return -EINVAL;
 
 		retval = update_ppp(new_entitled_ptr, NULL);
+
+		if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
+			/*
+			 * The hypervisor assigns VAS resources based
+			 * on entitled capacity for shared mode.
+			 * Reconfig VAS windows based on DLPAR CPU events.
+			 */
+			if (pseries_vas_dlpar_cpu() != 0)
+				retval = H_HARDWARE;
+		}
 	} else if (!strcmp(kbuf, "capacity_weight")) {
 		char *endp;
 		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index 0e0524cbe20c..4ad6e510d405 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -200,16 +200,41 @@ static irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
 	struct vas_user_win_ref *tsk_ref;
 	int rc;
 
-	rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
-	if (!rc) {
-		tsk_ref = &txwin->vas_win.task_ref;
-		vas_dump_crb(&crb);
-		vas_update_csb(&crb, tsk_ref);
+	while (atomic_read(&txwin->pending_faults)) {
+		rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
+		if (!rc) {
+			tsk_ref = &txwin->vas_win.task_ref;
+			vas_dump_crb(&crb);
+			vas_update_csb(&crb, tsk_ref);
+		}
+		atomic_dec(&txwin->pending_faults);
 	}
 
 	return IRQ_HANDLED;
 }
 
+/*
+ * irq_default_primary_handler() can be used only with IRQF_ONESHOT
+ * which disables IRQ before executing the thread handler and enables
+ * it after. But this disabling interrupt sets the VAS IRQ OFF
+ * state in the hypervisor. If the NX generates fault interrupt
+ * during this window, the hypervisor will not deliver this
+ * interrupt to the LPAR. So use VAS specific IRQ handler instead
+ * of calling the default primary handler.
+ */
+static irqreturn_t pseries_vas_irq_handler(int irq, void *data)
+{
+	struct pseries_vas_window *txwin = data;
+
+	/*
+	 * The thread hanlder will process this interrupt if it is
+	 * already running.
+	 */
+	atomic_inc(&txwin->pending_faults);
+
+	return IRQ_WAKE_THREAD;
+}
+
 /*
  * Allocate window and setup IRQ mapping.
  */
@@ -240,8 +265,9 @@ static int allocate_setup_window(struct pseries_vas_window *txwin,
 		goto out_irq;
 	}
 
-	rc = request_threaded_irq(txwin->fault_virq, NULL,
-				  pseries_vas_fault_thread_fn, IRQF_ONESHOT,
+	rc = request_threaded_irq(txwin->fault_virq,
+				  pseries_vas_irq_handler,
+				  pseries_vas_fault_thread_fn, 0,
 				  txwin->name, txwin);
 	if (rc) {
 		pr_err("VAS-Window[%d]: Request IRQ(%u) failed with %d\n",
@@ -826,6 +852,25 @@ int vas_reconfig_capabilties(u8 type, int new_nr_creds)
 	mutex_unlock(&vas_pseries_mutex);
 	return rc;
 }
+
+int pseries_vas_dlpar_cpu(void)
+{
+	int new_nr_creds, rc;
+
+	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
+				      vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
+				      (u64)virt_to_phys(&hv_cop_caps));
+	if (!rc) {
+		new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
+		rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, new_nr_creds);
+	}
+
+	if (rc)
+		pr_err("Failed reconfig VAS capabilities with DLPAR\n");
+
+	return rc;
+}
+
 /*
  * Total number of default credits available (target_credits)
  * in LPAR depends on number of cores configured. It varies based on
@@ -840,7 +885,15 @@ static int pseries_vas_notifier(struct notifier_block *nb,
 	struct of_reconfig_data *rd = data;
 	struct device_node *dn = rd->dn;
 	const __be32 *intserv = NULL;
-	int new_nr_creds, len, rc = 0;
+	int len;
+
+	/*
+	 * For shared CPU partition, the hypervisor assigns total credits
+	 * based on entitled core capacity. So updating VAS windows will
+	 * be called from lparcfg_write().
+	 */
+	if (is_shared_processor())
+		return NOTIFY_OK;
 
 	if ((action == OF_RECONFIG_ATTACH_NODE) ||
 		(action == OF_RECONFIG_DETACH_NODE))
@@ -852,19 +905,7 @@ static int pseries_vas_notifier(struct notifier_block *nb,
 	if (!intserv)
 		return NOTIFY_OK;
 
-	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
-					vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
-					(u64)virt_to_phys(&hv_cop_caps));
-	if (!rc) {
-		new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
-		rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE,
-						new_nr_creds);
-	}
-
-	if (rc)
-		pr_err("Failed reconfig VAS capabilities with DLPAR\n");
-
-	return rc;
+	return pseries_vas_dlpar_cpu();
 }
 
 static struct notifier_block pseries_vas_nb = {
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 333ffa2f9f42..7115043ec488 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -132,6 +132,7 @@ struct pseries_vas_window {
 	u64 flags;
 	char *name;
 	int fault_virq;
+	atomic_t pending_faults; /* Number of pending faults */
 };
 
 int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps);
@@ -140,10 +141,15 @@ int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps);
 
 #ifdef CONFIG_PPC_VAS
 int vas_migration_handler(int action);
+int pseries_vas_dlpar_cpu(void);
 #else
 static inline int vas_migration_handler(int action)
 {
 	return 0;
 }
+static inline int pseries_vas_dlpar_cpu(void)
+{
+	return 0;
+}
 #endif
 #endif /* _VAS_H */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 3b87d889b6e1..888731ccf1f6 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -10,10 +10,13 @@
 /* Even with __builtin_ the compiler may decide to use the out of line
    function. */
 
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
+#include <linux/kmsan_string.h>
+#endif
+
 #define __HAVE_ARCH_MEMCPY 1
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
 #undef memcpy
-void *__msan_memcpy(void *dst, const void *src, size_t size);
 #define memcpy __msan_memcpy
 #else
 extern void *memcpy(void *to, const void *from, size_t len);
@@ -21,7 +24,7 @@ extern void *memcpy(void *to, const void *from, size_t len);
 extern void *__memcpy(void *to, const void *from, size_t len);
 
 #define __HAVE_ARCH_MEMSET
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
 extern void *__msan_memset(void *s, int c, size_t n);
 #undef memset
 #define memset __msan_memset
@@ -67,7 +70,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 }
 
 #define __HAVE_ARCH_MEMMOVE
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
 #undef memmove
 void *__msan_memmove(void *dest, const void *src, size_t len);
 #define memmove __msan_memmove
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8bc614cfe21b..1cc756eafa44 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -254,24 +254,25 @@ extern void __put_user_nocheck_8(void);
 #define __put_user_size(x, ptr, size, label)				\
 do {									\
 	__typeof__(*(ptr)) __x = (x); /* eval x once */			\
-	__chk_user_ptr(ptr);						\
+	__typeof__(ptr) __ptr = (ptr); /* eval ptr once */		\
+	__chk_user_ptr(__ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__put_user_goto(__x, ptr, "b", "iq", label);		\
+		__put_user_goto(__x, __ptr, "b", "iq", label);		\
 		break;							\
 	case 2:								\
-		__put_user_goto(__x, ptr, "w", "ir", label);		\
+		__put_user_goto(__x, __ptr, "w", "ir", label);		\
 		break;							\
 	case 4:								\
-		__put_user_goto(__x, ptr, "l", "ir", label);		\
+		__put_user_goto(__x, __ptr, "l", "ir", label);		\
 		break;							\
 	case 8:								\
-		__put_user_goto_u64(__x, ptr, label);			\
+		__put_user_goto_u64(__x, __ptr, label);			\
 		break;							\
 	default:							\
 		__put_user_bad();					\
 	}								\
-	instrument_put_user(__x, ptr, size);				\
+	instrument_put_user(__x, __ptr, size);				\
 } while (0)
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 58a200dc762d..17f09dc26381 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -26,6 +26,7 @@ GCOV_PROFILE	:= n
 KASAN_SANITIZE	:= n
 UBSAN_SANITIZE	:= n
 KCSAN_SANITIZE	:= n
+KMSAN_SANITIZE	:= n
 KCOV_INSTRUMENT := n
 
 # These are adjustments to the compiler flags used for objects that
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 33292c01875d..75c8296b6feb 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -611,6 +611,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 		.nr_tags	= 1,
 	};
 	u64 alloc_time_ns = 0;
+	struct request *rq;
 	unsigned int cpu;
 	unsigned int tag;
 	int ret;
@@ -660,8 +661,12 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	tag = blk_mq_get_tag(&data);
 	if (tag == BLK_MQ_NO_TAG)
 		goto out_queue_exit;
-	return blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
+	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
 					alloc_time_ns);
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
+	return rq;
 
 out_queue_exit:
 	blk_queue_exit(q);
diff --git a/block/genhd.c b/block/genhd.c
index 17b33c62423d..fee90eb98b4a 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -410,9 +410,10 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	 * Otherwise just allocate the device numbers for both the whole device
 	 * and all partitions from the extended dev_t space.
 	 */
+	ret = -EINVAL;
 	if (disk->major) {
 		if (WARN_ON(!disk->minors))
-			return -EINVAL;
+			goto out_exit_elevator;
 
 		if (disk->minors > DISK_MAX_PARTS) {
 			pr_err("block: can't allocate more than %d partitions\n",
@@ -420,14 +421,14 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 			disk->minors = DISK_MAX_PARTS;
 		}
 		if (disk->first_minor + disk->minors > MINORMASK + 1)
-			return -EINVAL;
+			goto out_exit_elevator;
 	} else {
 		if (WARN_ON(disk->minors))
-			return -EINVAL;
+			goto out_exit_elevator;
 
 		ret = blk_alloc_ext_minor();
 		if (ret < 0)
-			return ret;
+			goto out_exit_elevator;
 		disk->major = BLOCK_EXT_MAJOR;
 		disk->first_minor = ret;
 	}
@@ -540,6 +541,9 @@ out_device_del:
 out_free_ext_minor:
 	if (disk->major == BLOCK_EXT_MAJOR)
 		blk_free_ext_minor(disk->first_minor);
+out_exit_elevator:
+	if (disk->queue->elevator)
+		elevator_exit(disk->queue);
 	return ret;
 }
 EXPORT_SYMBOL(device_add_disk);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index f9e39301c4af..04453f4a319c 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -7222,8 +7222,10 @@ static int __init rbd_sysfs_init(void)
 	int ret;
 
 	ret = device_register(&rbd_root_dev);
-	if (ret < 0)
+	if (ret < 0) {
+		put_device(&rbd_root_dev);
 		return ret;
+	}
 
 	ret = bus_register(&rbd_bus_type);
 	if (ret < 0)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 2fe28eeb2f38..69754155300e 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -791,13 +791,13 @@ void __init random_init_early(const char *command_line)
 #endif
 
 	for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) {
-		longs = arch_get_random_seed_longs(entropy, ARRAY_SIZE(entropy) - i);
+		longs = arch_get_random_seed_longs_early(entropy, ARRAY_SIZE(entropy) - i);
 		if (longs) {
 			_mix_pool_bytes(entropy, sizeof(*entropy) * longs);
 			i += longs;
 			continue;
 		}
-		longs = arch_get_random_longs(entropy, ARRAY_SIZE(entropy) - i);
+		longs = arch_get_random_longs_early(entropy, ARRAY_SIZE(entropy) - i);
 		if (longs) {
 			_mix_pool_bytes(entropy, sizeof(*entropy) * longs);
 			i += longs;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0ea7e441e080..93e2138a8b42 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -516,6 +516,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	/* set to a default value of 512 until the disk is validated */
 	blk_queue_logical_block_size(head->disk->queue, 512);
 	blk_set_stacking_limits(&head->disk->queue->limits);
+	blk_queue_dma_alignment(head->disk->queue, 3);
 
 	/* we need to propagate up the VMC settings */
 	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 1eed0fc26b3a..9b47dcb2a7d9 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -387,7 +387,7 @@ static inline void nvme_tcp_ddgst_update(struct ahash_request *hash,
 {
 	struct scatterlist sg;
 
-	sg_init_marker(&sg, 1);
+	sg_init_table(&sg, 1);
 	sg_set_page(&sg, page, len, off);
 	ahash_request_set_crypt(hash, &sg, NULL, len);
 	crypto_ahash_update(hash);
@@ -1141,6 +1141,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
 static int nvme_tcp_try_send(struct nvme_tcp_queue *queue)
 {
 	struct nvme_tcp_request *req;
+	unsigned int noreclaim_flag;
 	int ret = 1;
 
 	if (!queue->request) {
@@ -1150,12 +1151,13 @@ static int nvme_tcp_try_send(struct nvme_tcp_queue *queue)
 	}
 	req = queue->request;
 
+	noreclaim_flag = memalloc_noreclaim_save();
 	if (req->state == NVME_TCP_SEND_CMD_PDU) {
 		ret = nvme_tcp_try_send_cmd_pdu(req);
 		if (ret <= 0)
 			goto done;
 		if (!nvme_tcp_has_inline_data(req))
-			return ret;
+			goto out;
 	}
 
 	if (req->state == NVME_TCP_SEND_H2C_PDU) {
@@ -1181,6 +1183,8 @@ done:
 		nvme_tcp_fail_request(queue->request);
 		nvme_tcp_done_send_req(queue);
 	}
+out:
+	memalloc_noreclaim_restore(noreclaim_flag);
 	return ret;
 }
 
@@ -1296,6 +1300,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 	struct page *page;
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+	unsigned int noreclaim_flag;
 
 	if (!test_and_clear_bit(NVME_TCP_Q_ALLOCATED, &queue->flags))
 		return;
@@ -1308,7 +1313,11 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 		__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
 		queue->pf_cache.va = NULL;
 	}
+
+	noreclaim_flag = memalloc_noreclaim_save();
 	sock_release(queue->sock);
+	memalloc_noreclaim_restore(noreclaim_flag);
+
 	kfree(queue->pdu);
 	mutex_destroy(&queue->send_mutex);
 	mutex_destroy(&queue->queue_lock);
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index ac0c7ccf2eae..852b025e2fec 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2582,7 +2582,7 @@ static int lpfcdiag_loop_self_unreg(struct lpfc_hba *phba, uint16_t rpi)
  *
  * This function obtains the transmit and receive ids required to send
  * an unsolicited ct command with a payload. A special lpfc FsType and CmdRsp
- * flags are used to the unsolicted response handler is able to process
+ * flags are used to the unsolicited response handler is able to process
  * the ct command sent on the same port.
  **/
 static int lpfcdiag_loop_get_xri(struct lpfc_hba *phba, uint16_t rpi,
@@ -2874,7 +2874,7 @@ out:
  * @len: Number of data bytes
  *
  * This function allocates and posts a data buffer of sufficient size to receive
- * an unsolicted CT command.
+ * an unsolicited CT command.
  **/
 static int lpfcdiag_sli3_loop_post_rxbufs(struct lpfc_hba *phba, uint16_t rxxri,
 					  size_t len)
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 75fd2bfc212b..e941a99aa965 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -90,7 +90,7 @@ lpfc_ct_ignore_hbq_buffer(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq,
 				get_job_ulpstatus(phba, piocbq));
 	}
 	lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
-			"0145 Ignoring unsolicted CT HBQ Size:%d "
+			"0145 Ignoring unsolicited CT HBQ Size:%d "
 			"status = x%x\n",
 			size, get_job_ulpstatus(phba, piocbq));
 }
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 9be4ba61a076..d265a2d9d082 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5874,10 +5874,6 @@ fallback:
 static
 int megasas_get_device_list(struct megasas_instance *instance)
 {
-	memset(instance->pd_list, 0,
-	       (MEGASAS_MAX_PD * sizeof(struct megasas_pd_list)));
-	memset(instance->ld_ids, 0xff, MEGASAS_MAX_LD_IDS);
-
 	if (instance->enable_fw_dev_list) {
 		if (megasas_host_device_list_query(instance, true))
 			return FAILED;
@@ -7220,7 +7216,7 @@ int megasas_alloc_ctrl_dma_buffers(struct megasas_instance *instance)
 
 		if (!fusion->ioc_init_request) {
 			dev_err(&pdev->dev,
-				"Failed to allocate PD list buffer\n");
+				"Failed to allocate ioc init request\n");
 			return -ENOMEM;
 		}
 
@@ -7439,7 +7435,6 @@ static inline void megasas_init_ctrl_params(struct megasas_instance *instance)
 	    (instance->pdev->device == PCI_DEVICE_ID_LSI_SAS0071SKINNY))
 		instance->flag_ieee = 1;
 
-	megasas_dbg_lvl = 0;
 	instance->flag = 0;
 	instance->unload = 1;
 	instance->last_time = 0;
@@ -8762,33 +8757,26 @@ static
 int megasas_update_device_list(struct megasas_instance *instance,
 			       int event_type)
 {
-	int dcmd_ret = DCMD_SUCCESS;
+	int dcmd_ret;
 
 	if (instance->enable_fw_dev_list) {
-		dcmd_ret = megasas_host_device_list_query(instance, false);
-		if (dcmd_ret != DCMD_SUCCESS)
-			goto out;
+		return megasas_host_device_list_query(instance, false);
 	} else {
 		if (event_type & SCAN_PD_CHANNEL) {
 			dcmd_ret = megasas_get_pd_list(instance);
-
 			if (dcmd_ret != DCMD_SUCCESS)
-				goto out;
+				return dcmd_ret;
 		}
 
 		if (event_type & SCAN_VD_CHANNEL) {
 			if (!instance->requestorId ||
 			megasas_get_ld_vf_affiliation(instance, 0)) {
-				dcmd_ret = megasas_ld_list_query(instance,
+				return megasas_ld_list_query(instance,
 						MR_LD_QUERY_TYPE_EXPOSED_TO_HOST);
-				if (dcmd_ret != DCMD_SUCCESS)
-					goto out;
 			}
 		}
 	}
-
-out:
-	return dcmd_ret;
+	return DCMD_SUCCESS;
 }
 
 /**
@@ -8918,7 +8906,7 @@ megasas_aen_polling(struct work_struct *work)
 			sdev1 = scsi_device_lookup(instance->host,
 						   MEGASAS_MAX_PD_CHANNELS +
 						   (ld_target_id / MEGASAS_MAX_DEV_PER_CHANNEL),
-						   (ld_target_id - MEGASAS_MAX_DEV_PER_CHANNEL),
+						   (ld_target_id % MEGASAS_MAX_DEV_PER_CHANNEL),
 						   0);
 			if (sdev1)
 				megasas_remove_scsi_device(sdev1);
@@ -9016,6 +9004,7 @@ static int __init megasas_init(void)
 	 */
 	pr_info("megasas: %s\n", MEGASAS_VERSION);
 
+	megasas_dbg_lvl = 0;
 	support_poll_for_event = 2;
 	support_device_change = 1;
 	support_nvme_encapsulation = true;
diff --git a/drivers/scsi/mpi3mr/Kconfig b/drivers/scsi/mpi3mr/Kconfig
index 8997531940c2..f48740cd5b95 100644
--- a/drivers/scsi/mpi3mr/Kconfig
+++ b/drivers/scsi/mpi3mr/Kconfig
@@ -4,5 +4,6 @@ config SCSI_MPI3MR
 	tristate "Broadcom MPI3 Storage Controller Device Driver"
 	depends on PCI && SCSI
 	select BLK_DEV_BSGLIB
+	select SCSI_SAS_ATTRS
 	help
 	MPI3 based Storage & RAID Controllers Driver.
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 2ff2fac1e403..7a7d63aa90e2 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -99,6 +99,7 @@ static void pm8001_map_queues(struct Scsi_Host *shost)
 static struct scsi_host_template pm8001_sht = {
 	.module			= THIS_MODULE,
 	.name			= DRV_NAME,
+	.proc_name		= DRV_NAME,
 	.queuecommand		= sas_queuecommand,
 	.dma_need_drain		= ata_scsi_dma_need_drain,
 	.target_alloc		= sas_target_alloc,
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index fa1fcbfb946f..b67ad30d56e6 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -951,9 +951,9 @@ qla2x00_sysfs_read_dcbx_tlv(struct file *filp, struct kobject *kobj,
 	if (!capable(CAP_SYS_ADMIN) || off != 0 || count > DCBX_TLV_DATA_SIZE)
 		return 0;
 
+	mutex_lock(&vha->hw->optrom_mutex);
 	if (ha->dcbx_tlv)
 		goto do_read;
-	mutex_lock(&vha->hw->optrom_mutex);
 	if (qla2x00_chip_is_down(vha)) {
 		mutex_unlock(&vha->hw->optrom_mutex);
 		return 0;
@@ -3330,11 +3330,34 @@ struct fc_function_template qla2xxx_transport_vport_functions = {
 	.bsg_timeout = qla24xx_bsg_timeout,
 };
 
+static uint
+qla2x00_get_host_supported_speeds(scsi_qla_host_t *vha, uint speeds)
+{
+	uint supported_speeds = FC_PORTSPEED_UNKNOWN;
+
+	if (speeds & FDMI_PORT_SPEED_64GB)
+		supported_speeds |= FC_PORTSPEED_64GBIT;
+	if (speeds & FDMI_PORT_SPEED_32GB)
+		supported_speeds |= FC_PORTSPEED_32GBIT;
+	if (speeds & FDMI_PORT_SPEED_16GB)
+		supported_speeds |= FC_PORTSPEED_16GBIT;
+	if (speeds & FDMI_PORT_SPEED_8GB)
+		supported_speeds |= FC_PORTSPEED_8GBIT;
+	if (speeds & FDMI_PORT_SPEED_4GB)
+		supported_speeds |= FC_PORTSPEED_4GBIT;
+	if (speeds & FDMI_PORT_SPEED_2GB)
+		supported_speeds |= FC_PORTSPEED_2GBIT;
+	if (speeds & FDMI_PORT_SPEED_1GB)
+		supported_speeds |= FC_PORTSPEED_1GBIT;
+
+	return supported_speeds;
+}
+
 void
 qla2x00_init_host_attr(scsi_qla_host_t *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
-	u32 speeds = FC_PORTSPEED_UNKNOWN;
+	u32 speeds = 0, fdmi_speed = 0;
 
 	fc_host_dev_loss_tmo(vha->host) = ha->port_down_retry_count;
 	fc_host_node_name(vha->host) = wwn_to_u64(vha->node_name);
@@ -3344,7 +3367,8 @@ qla2x00_init_host_attr(scsi_qla_host_t *vha)
 	fc_host_max_npiv_vports(vha->host) = ha->max_npiv_vports;
 	fc_host_npiv_vports_inuse(vha->host) = ha->cur_vport_count;
 
-	speeds = qla25xx_fdmi_port_speed_capability(ha);
+	fdmi_speed = qla25xx_fdmi_port_speed_capability(ha);
+	speeds = qla2x00_get_host_supported_speeds(vha, fdmi_speed);
 
 	fc_host_supported_speeds(vha->host) = speeds;
 }
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index b7f16ee8aa0e..cb4f7cc02f8f 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -284,6 +284,25 @@ void target_pr_kref_release(struct kref *kref)
 	complete(&deve->pr_comp);
 }
 
+/*
+ * Establish UA condition on SCSI device - all LUNs
+ */
+void target_dev_ua_allocate(struct se_device *dev, u8 asc, u8 ascq)
+{
+	struct se_dev_entry *se_deve;
+	struct se_lun *lun;
+
+	spin_lock(&dev->se_port_lock);
+	list_for_each_entry(lun, &dev->dev_sep_list, lun_dev_link) {
+
+		spin_lock(&lun->lun_deve_lock);
+		list_for_each_entry(se_deve, &lun->lun_deve_list, lun_link)
+			core_scsi3_ua_allocate(se_deve, asc, ascq);
+		spin_unlock(&lun->lun_deve_lock);
+	}
+	spin_unlock(&dev->se_port_lock);
+}
+
 static void
 target_luns_data_has_changed(struct se_node_acl *nacl, struct se_dev_entry *new,
 			     bool skip_new)
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 8351c974cee3..d9266cf558dc 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -230,14 +230,12 @@ static void iblock_unplug_device(struct se_dev_plug *se_plug)
 	clear_bit(IBD_PLUGF_PLUGGED, &ib_dev_plug->flags);
 }
 
-static unsigned long long iblock_emulate_read_cap_with_block_size(
-	struct se_device *dev,
-	struct block_device *bd,
-	struct request_queue *q)
+static sector_t iblock_get_blocks(struct se_device *dev)
 {
-	u32 block_size = bdev_logical_block_size(bd);
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	u32 block_size = bdev_logical_block_size(ib_dev->ibd_bd);
 	unsigned long long blocks_long =
-		div_u64(bdev_nr_bytes(bd), block_size) - 1;
+		div_u64(bdev_nr_bytes(ib_dev->ibd_bd), block_size) - 1;
 
 	if (block_size == dev->dev_attrib.block_size)
 		return blocks_long;
@@ -829,15 +827,6 @@ fail:
 	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
 
-static sector_t iblock_get_blocks(struct se_device *dev)
-{
-	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
-	struct block_device *bd = ib_dev->ibd_bd;
-	struct request_queue *q = bdev_get_queue(bd);
-
-	return iblock_emulate_read_cap_with_block_size(dev, bd, q);
-}
-
 static sector_t iblock_get_alignment_offset_lbas(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 30fcf69e1a1d..38a6d08f75b3 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -89,6 +89,7 @@ int	target_configure_device(struct se_device *dev);
 void	target_free_device(struct se_device *);
 int	target_for_each_device(int (*fn)(struct se_device *dev, void *data),
 			       void *data);
+void	target_dev_ua_allocate(struct se_device *dev, u8 asc, u8 ascq);
 
 /* target_core_configfs.c */
 extern struct configfs_item_operations target_core_dev_item_ops;
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index a1d67554709f..1493b1d01194 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -2956,13 +2956,28 @@ core_scsi3_pro_preempt(struct se_cmd *cmd, int type, int scope, u64 res_key,
 			__core_scsi3_complete_pro_preempt(dev, pr_reg_n,
 				(preempt_type == PREEMPT_AND_ABORT) ? &preempt_and_abort_list : NULL,
 				type, scope, preempt_type);
-
-			if (preempt_type == PREEMPT_AND_ABORT)
-				core_scsi3_release_preempt_and_abort(
-					&preempt_and_abort_list, pr_reg_n);
 		}
+
 		spin_unlock(&dev->dev_reservation_lock);
 
+		/*
+		 * SPC-4 5.12.11.2.6 Preempting and aborting
+		 * The actions described in this subclause shall be performed
+		 * for all I_T nexuses that are registered with the non-zero
+		 * SERVICE ACTION RESERVATION KEY value, without regard for
+		 * whether the preempted I_T nexuses hold the persistent
+		 * reservation. If the SERVICE ACTION RESERVATION KEY field is
+		 * set to zero and an all registrants persistent reservation is
+		 * present, the device server shall abort all commands for all
+		 * registered I_T nexuses.
+		 */
+		if (preempt_type == PREEMPT_AND_ABORT) {
+			core_tmr_lun_reset(dev, NULL, &preempt_and_abort_list,
+					   cmd);
+			core_scsi3_release_preempt_and_abort(
+				&preempt_and_abort_list, pr_reg_n);
+		}
+
 		if (pr_tmpl->pr_aptpl_active)
 			core_scsi3_update_and_write_aptpl(cmd->se_dev, true);
 
@@ -3022,7 +3037,7 @@ core_scsi3_pro_preempt(struct se_cmd *cmd, int type, int scope, u64 res_key,
 		if (calling_it_nexus)
 			continue;
 
-		if (pr_reg->pr_res_key != sa_res_key)
+		if (sa_res_key && pr_reg->pr_res_key != sa_res_key)
 			continue;
 
 		pr_reg_nacl = pr_reg->pr_reg_nacl;
@@ -3425,8 +3440,6 @@ after_iport_check:
 	 *       transport protocols where port names are not required;
 	 * d) Register the reservation key specified in the SERVICE ACTION
 	 *    RESERVATION KEY field;
-	 * e) Retain the reservation key specified in the SERVICE ACTION
-	 *    RESERVATION KEY field and associated information;
 	 *
 	 * Also, It is not an error for a REGISTER AND MOVE service action to
 	 * register an I_T nexus that is already registered with the same
@@ -3448,6 +3461,12 @@ after_iport_check:
 		dest_pr_reg = __core_scsi3_locate_pr_reg(dev, dest_node_acl,
 						iport_ptr);
 		new_reg = 1;
+	} else {
+		/*
+		 * e) Retain the reservation key specified in the SERVICE ACTION
+		 *    RESERVATION KEY field and associated information;
+		 */
+		dest_pr_reg->pr_res_key = sa_res_key;
 	}
 	/*
 	 * f) Release the persistent reservation for the persistent reservation
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 7838dc20f713..5926316252eb 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -3531,8 +3531,7 @@ static void target_tmr_work(struct work_struct *work)
 		tmr->response = (!ret) ? TMR_FUNCTION_COMPLETE :
 					 TMR_FUNCTION_REJECTED;
 		if (tmr->response == TMR_FUNCTION_COMPLETE) {
-			target_ua_allocate_lun(cmd->se_sess->se_node_acl,
-					       cmd->orig_fe_lun, 0x29,
+			target_dev_ua_allocate(dev, 0x29,
 					       ASCQ_29H_BUS_DEVICE_RESET_FUNCTION_OCCURRED);
 		}
 		break;
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index d50fe7558cf8..ad93e3868e47 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -779,7 +779,7 @@ static inline void ufshcd_utrl_clear(struct ufs_hba *hba, u32 mask)
 }
 
 /**
- * ufshcd_utmrl_clear - Clear a bit in UTRMLCLR register
+ * ufshcd_utmrl_clear - Clear a bit in UTMRLCLR register
  * @hba: per adapter instance
  * @pos: position of the bit to be cleared
  */
@@ -3118,7 +3118,7 @@ int ufshcd_query_flag_retry(struct ufs_hba *hba,
 
 	if (ret)
 		dev_err(hba->dev,
-			"%s: query attribute, opcode %d, idn %d, failed with error %d after %d retries\n",
+			"%s: query flag, opcode %d, idn %d, failed with error %d after %d retries\n",
 			__func__, opcode, idn, ret, retries);
 	return ret;
 }
diff --git a/drivers/ufs/core/ufshpb.c b/drivers/ufs/core/ufshpb.c
index 3d69a81c5b17..b7f412d0f301 100644
--- a/drivers/ufs/core/ufshpb.c
+++ b/drivers/ufs/core/ufshpb.c
@@ -383,7 +383,7 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	rgn = hpb->rgn_tbl + rgn_idx;
 	srgn = rgn->srgn_tbl + srgn_idx;
 
-	/* If command type is WRITE or DISCARD, set bitmap as drity */
+	/* If command type is WRITE or DISCARD, set bitmap as dirty */
 	if (ufshpb_is_write_or_discard(cmd)) {
 		ufshpb_iterate_rgn(hpb, rgn_idx, srgn_idx, srgn_offset,
 				   transfer_len, true);
@@ -616,7 +616,7 @@ static void ufshpb_activate_subregion(struct ufshpb_lu *hpb,
 static enum rq_end_io_ret ufshpb_umap_req_compl_fn(struct request *req,
 						   blk_status_t error)
 {
-	struct ufshpb_req *umap_req = (struct ufshpb_req *)req->end_io_data;
+	struct ufshpb_req *umap_req = req->end_io_data;
 
 	ufshpb_put_req(umap_req->hpb, umap_req);
 	return RQ_END_IO_NONE;
@@ -625,7 +625,7 @@ static enum rq_end_io_ret ufshpb_umap_req_compl_fn(struct request *req,
 static enum rq_end_io_ret ufshpb_map_req_compl_fn(struct request *req,
 						  blk_status_t error)
 {
-	struct ufshpb_req *map_req = (struct ufshpb_req *) req->end_io_data;
+	struct ufshpb_req *map_req = req->end_io_data;
 	struct ufshpb_lu *hpb = map_req->hpb;
 	struct ufshpb_subregion *srgn;
 	unsigned long flags;
diff --git a/drivers/ufs/host/ufs-qcom-ice.c b/drivers/ufs/host/ufs-qcom-ice.c
index 745e48ec598f..62387ccd5b30 100644
--- a/drivers/ufs/host/ufs-qcom-ice.c
+++ b/drivers/ufs/host/ufs-qcom-ice.c
@@ -118,7 +118,6 @@ int ufs_qcom_ice_init(struct ufs_qcom_host *host)
 	host->ice_mmio = devm_ioremap_resource(dev, res);
 	if (IS_ERR(host->ice_mmio)) {
 		err = PTR_ERR(host->ice_mmio);
-		dev_err(dev, "Failed to map ICE registers; err=%d\n", err);
 		return err;
 	}
 
diff --git a/fs/exec.c b/fs/exec.c
index 32dc8cf5fceb..a0b1f0337a62 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1012,7 +1012,6 @@ static int exec_mmap(struct mm_struct *mm)
 	active_mm = tsk->active_mm;
 	tsk->active_mm = mm;
 	tsk->mm = mm;
-	lru_gen_add_mm(mm);
 	/*
 	 * This prevents preemption while active_mm is being loaded and
 	 * it and mm are being updated, which could cause problems for
@@ -1025,6 +1024,7 @@ static int exec_mmap(struct mm_struct *mm)
 	activate_mm(active_mm, mm);
 	if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
 		local_irq_enable();
+	lru_gen_add_mm(mm);
 	task_unlock(tsk);
 	lru_gen_use_mm(mm);
 	if (old_mm) {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 989365b878a6..7950904fbf04 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1741,10 +1741,6 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
 
 #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
 
-static const char deprecated_msg[] =
-	"Mount option \"%s\" will be removed by %s\n"
-	"Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
-
 #define MOPT_SET	0x0001
 #define MOPT_CLEAR	0x0002
 #define MOPT_NOSUPPORT	0x0004
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index e56510964b22..8ba8c4c50770 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -506,8 +506,9 @@ static int squashfs_readahead_fragment(struct page **page,
 		squashfs_i(inode)->fragment_size);
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 	unsigned int n, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
+	int error = buffer->error;
 
-	if (buffer->error)
+	if (error)
 		goto out;
 
 	expected += squashfs_i(inode)->fragment_offset;
@@ -529,7 +530,7 @@ static int squashfs_readahead_fragment(struct page **page,
 
 out:
 	squashfs_cache_put(buffer);
-	return buffer->error;
+	return error;
 }
 
 static void squashfs_readahead(struct readahead_control *ractl)
@@ -557,6 +558,13 @@ static void squashfs_readahead(struct readahead_control *ractl)
 		int res, bsize;
 		u64 block = 0;
 		unsigned int expected;
+		struct page *last_page;
+
+		expected = start >> msblk->block_log == file_end ?
+			   (i_size_read(inode) & (msblk->block_size - 1)) :
+			    msblk->block_size;
+
+		max_pages = (expected + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 		nr_pages = __readahead_batch(ractl, pages, max_pages);
 		if (!nr_pages)
@@ -566,13 +574,10 @@ static void squashfs_readahead(struct readahead_control *ractl)
 			goto skip_pages;
 
 		index = pages[0]->index >> shift;
+
 		if ((pages[nr_pages - 1]->index >> shift) != index)
 			goto skip_pages;
 
-		expected = index == file_end ?
-			   (i_size_read(inode) & (msblk->block_size - 1)) :
-			    msblk->block_size;
-
 		if (index == file_end && squashfs_i(inode)->fragment_block !=
 						SQUASHFS_INVALID_BLK) {
 			res = squashfs_readahead_fragment(pages, nr_pages,
@@ -593,15 +598,15 @@ static void squashfs_readahead(struct readahead_control *ractl)
 
 		res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
 
-		squashfs_page_actor_free(actor);
+		last_page = squashfs_page_actor_free(actor);
 
 		if (res == expected) {
 			int bytes;
 
 			/* Last page (if present) may have trailing bytes not filled */
 			bytes = res % PAGE_SIZE;
-			if (pages[nr_pages - 1]->index == file_end && bytes)
-				memzero_page(pages[nr_pages - 1], bytes,
+			if (index == file_end && bytes && last_page)
+				memzero_page(last_page, bytes,
 					     PAGE_SIZE - bytes);
 
 			for (i = 0; i < nr_pages; i++) {
diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
index 54b93bf4a25c..81af6c4ca115 100644
--- a/fs/squashfs/page_actor.c
+++ b/fs/squashfs/page_actor.c
@@ -71,11 +71,13 @@ static void *handle_next_page(struct squashfs_page_actor *actor)
 			(actor->next_index != actor->page[actor->next_page]->index)) {
 		actor->next_index++;
 		actor->returned_pages++;
+		actor->last_page = NULL;
 		return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM);
 	}
 
 	actor->next_index++;
 	actor->returned_pages++;
+	actor->last_page = actor->page[actor->next_page];
 	return actor->pageaddr = kmap_local_page(actor->page[actor->next_page++]);
 }
 
@@ -125,6 +127,7 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_
 	actor->returned_pages = 0;
 	actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1);
 	actor->pageaddr = NULL;
+	actor->last_page = NULL;
 	actor->alloc_buffer = msblk->decompressor->alloc_buffer;
 	actor->squashfs_first_page = direct_first_page;
 	actor->squashfs_next_page = direct_next_page;
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
index 95ffbb543d91..97d4983559b1 100644
--- a/fs/squashfs/page_actor.h
+++ b/fs/squashfs/page_actor.h
@@ -16,6 +16,7 @@ struct squashfs_page_actor {
 	void    *(*squashfs_first_page)(struct squashfs_page_actor *);
 	void    *(*squashfs_next_page)(struct squashfs_page_actor *);
 	void    (*squashfs_finish_page)(struct squashfs_page_actor *);
+	struct page *last_page;
 	int	pages;
 	int	length;
 	int	next_page;
@@ -29,10 +30,13 @@ extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
 extern struct squashfs_page_actor *squashfs_page_actor_init_special(
 				struct squashfs_sb_info *msblk,
 				struct page **page, int pages, int length);
-static inline void squashfs_page_actor_free(struct squashfs_page_actor *actor)
+static inline struct page *squashfs_page_actor_free(struct squashfs_page_actor *actor)
 {
+	struct page *last_page = actor->last_page;
+
 	kfree(actor->tmp_buffer);
 	kfree(actor);
+	return last_page;
 }
 static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
 {
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ba18e9bdb799..d6119c5d1069 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -853,7 +853,8 @@ static inline bool blk_mq_add_to_batch(struct request *req,
 				       struct io_comp_batch *iob, int ioerror,
 				       void (*complete)(struct io_comp_batch *))
 {
-	if (!iob || (req->rq_flags & RQF_ELV) || ioerror)
+	if (!iob || (req->rq_flags & RQF_ELV) || ioerror ||
+			(req->end_io && !blk_rq_is_passthrough(req)))
 		return false;
 
 	if (!iob->complete)
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 4029fe368a4f..18a31b125f9d 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -43,11 +43,24 @@ extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen);
 extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat);
 extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy);
 #else
-#define __underlying_memchr	__builtin_memchr
-#define __underlying_memcmp	__builtin_memcmp
+
+#if defined(__SANITIZE_MEMORY__)
+/*
+ * For KMSAN builds all memcpy/memset/memmove calls should be replaced by the
+ * corresponding __msan_XXX functions.
+ */
+#include <linux/kmsan_string.h>
+#define __underlying_memcpy	__msan_memcpy
+#define __underlying_memmove	__msan_memmove
+#define __underlying_memset	__msan_memset
+#else
 #define __underlying_memcpy	__builtin_memcpy
 #define __underlying_memmove	__builtin_memmove
 #define __underlying_memset	__builtin_memset
+#endif
+
+#define __underlying_memchr	__builtin_memchr
+#define __underlying_memcmp	__builtin_memcmp
 #define __underlying_strcat	__builtin_strcat
 #define __underlying_strcpy	__builtin_strcpy
 #define __underlying_strlen	__builtin_strlen
diff --git a/include/linux/kmsan_string.h b/include/linux/kmsan_string.h
new file mode 100644
index 000000000000..7287da6f52ef
--- /dev/null
+++ b/include/linux/kmsan_string.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KMSAN string functions API used in other headers.
+ *
+ * Copyright (C) 2022 Google LLC
+ * Author: Alexander Potapenko <glider@google.com>
+ *
+ */
+#ifndef _LINUX_KMSAN_STRING_H
+#define _LINUX_KMSAN_STRING_H
+
+/*
+ * KMSAN overrides the default memcpy/memset/memmove implementations in the
+ * kernel, which requires having __msan_XXX function prototypes in several other
+ * headers. Keep them in one place instead of open-coding.
+ */
+void *__msan_memcpy(void *dst, const void *src, size_t size);
+void *__msan_memset(void *s, int c, size_t n);
+void *__msan_memmove(void *dest, const void *src, size_t len);
+
+#endif /* _LINUX_KMSAN_STRING_H */
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index f07e6998bb68..9df0b9a762cc 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -146,9 +146,9 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 static inline bool vma_can_userfault(struct vm_area_struct *vma,
 				     unsigned long vm_flags)
 {
-	if (vm_flags & VM_UFFD_MINOR)
-		return is_vm_hugetlb_page(vma) || vma_is_shmem(vma);
-
+	if ((vm_flags & VM_UFFD_MINOR) &&
+	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
+		return false;
 #ifndef CONFIG_PTE_MARKER_UFFD_WP
 	/*
 	 * If user requested uffd-wp but not enabled pte markers for
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 6cc16e39b27f..ac8c488e3077 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1173,7 +1173,7 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
 	}
 }
 
-int __io_run_local_work(struct io_ring_ctx *ctx, bool locked)
+int __io_run_local_work(struct io_ring_ctx *ctx, bool *locked)
 {
 	struct llist_node *node;
 	struct llist_node fake;
@@ -1192,7 +1192,7 @@ again:
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    io_task_work.node);
 		prefetch(container_of(next, struct io_kiocb, io_task_work.node));
-		req->io_task_work.func(req, &locked);
+		req->io_task_work.func(req, locked);
 		ret++;
 		node = next;
 	}
@@ -1208,7 +1208,7 @@ again:
 		goto again;
 	}
 
-	if (locked)
+	if (*locked)
 		io_submit_flush_completions(ctx);
 	trace_io_uring_local_work_run(ctx, ret, loops);
 	return ret;
@@ -1225,7 +1225,7 @@ int io_run_local_work(struct io_ring_ctx *ctx)
 
 	__set_current_state(TASK_RUNNING);
 	locked = mutex_trylock(&ctx->uring_lock);
-	ret = __io_run_local_work(ctx, locked);
+	ret = __io_run_local_work(ctx, &locked);
 	if (locked)
 		mutex_unlock(&ctx->uring_lock);
 
@@ -1446,8 +1446,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
 		    io_task_work_pending(ctx)) {
 			u32 tail = ctx->cached_cq_tail;
 
-			if (!llist_empty(&ctx->work_llist))
-				__io_run_local_work(ctx, true);
+			(void) io_run_local_work_locked(ctx);
 
 			if (task_work_pending(current) ||
 			    wq_list_empty(&ctx->iopoll_list)) {
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index ef77d2aa3172..e99a79f2df9b 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -27,7 +27,7 @@ enum {
 struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow);
 bool io_req_cqe_overflow(struct io_kiocb *req);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);
-int __io_run_local_work(struct io_ring_ctx *ctx, bool locked);
+int __io_run_local_work(struct io_ring_ctx *ctx, bool *locked);
 int io_run_local_work(struct io_ring_ctx *ctx);
 void io_req_complete_failed(struct io_kiocb *req, s32 res);
 void __io_req_complete(struct io_kiocb *req, unsigned issue_flags);
@@ -277,9 +277,18 @@ static inline int io_run_task_work_ctx(struct io_ring_ctx *ctx)
 
 static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
 {
+	bool locked;
+	int ret;
+
 	if (llist_empty(&ctx->work_llist))
 		return 0;
-	return __io_run_local_work(ctx, true);
+
+	locked = true;
+	ret = __io_run_local_work(ctx, &locked);
+	/* shouldn't happen! */
+	if (WARN_ON_ONCE(!locked))
+		mutex_lock(&ctx->uring_lock);
+	return ret;
 }
 
 static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
diff --git a/ipc/msg.c b/ipc/msg.c
index e4e0990e08f7..fd08b3cb36d7 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -1329,11 +1329,11 @@ fail_msg_bytes:
 #ifdef CONFIG_IPC_NS
 void msg_exit_ns(struct ipc_namespace *ns)
 {
-	percpu_counter_destroy(&ns->percpu_msg_bytes);
-	percpu_counter_destroy(&ns->percpu_msg_hdrs);
 	free_ipcs(ns, &msg_ids(ns), freeque);
 	idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr);
 	rhashtable_destroy(&ns->ids[IPC_MSG_IDS].key_ht);
+	percpu_counter_destroy(&ns->percpu_msg_bytes);
+	percpu_counter_destroy(&ns->percpu_msg_hdrs);
 }
 #endif
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 3fc7abffc7aa..29280072dc0e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -400,8 +400,9 @@ config FRAME_WARN
 	default 1536 if (!64BIT && XTENSA)
 	default 1024 if !64BIT
 	default 2048 if 64BIT
+	default 0 if KMSAN
 	help
-	  Tell gcc to warn at build time for stack frames larger than this.
+	  Tell the compiler to warn at build time for stack frames larger than this.
 	  Setting this too low will cause a lot of warnings.
 	  Setting it to 0 disables the warning.
 
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index e1743803c851..fbde494444b8 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -2903,8 +2903,8 @@ static inline void *mtree_range_walk(struct ma_state *mas)
 	unsigned long max, min;
 	unsigned long prev_max, prev_min;
 
-	last = next = mas->node;
-	prev_min = min = mas->min;
+	next = mas->node;
+	min = mas->min;
 	max = mas->max;
 	do {
 		offset = 0;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 03fc7e5edf07..561a42567477 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2462,7 +2462,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	 * Fix up and warn once if private is unexpectedly set.
 	 */
 	if (!folio_test_swapcache(page_folio(head))) {
-		VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, head);
+		VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, page_tail);
 		page_tail->private = 0;
 	}
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 37af2dc8dac9..646e2979641f 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1460,6 +1460,27 @@ static void scan_gray_list(void)
 	WARN_ON(!list_empty(&gray_list));
 }
 
+/*
+ * Conditionally call resched() in a object iteration loop while making sure
+ * that the given object won't go away without RCU read lock by performing a
+ * get_object() if !pinned.
+ *
+ * Return: false if can't do a cond_resched() due to get_object() failure
+ *	   true otherwise
+ */
+static bool kmemleak_cond_resched(struct kmemleak_object *object, bool pinned)
+{
+	if (!pinned && !get_object(object))
+		return false;
+
+	rcu_read_unlock();
+	cond_resched();
+	rcu_read_lock();
+	if (!pinned)
+		put_object(object);
+	return true;
+}
+
 /*
  * Scan data sections and all the referenced memory blocks allocated via the
  * kernel's standard allocators. This function must be called with the
@@ -1471,7 +1492,7 @@ static void kmemleak_scan(void)
 	struct zone *zone;
 	int __maybe_unused i;
 	int new_leaks = 0;
-	int loop1_cnt = 0;
+	int loop_cnt = 0;
 
 	jiffies_last_scan = jiffies;
 
@@ -1480,7 +1501,6 @@ static void kmemleak_scan(void)
 	list_for_each_entry_rcu(object, &object_list, object_list) {
 		bool obj_pinned = false;
 
-		loop1_cnt++;
 		raw_spin_lock_irq(&object->lock);
 #ifdef DEBUG
 		/*
@@ -1514,24 +1534,11 @@ static void kmemleak_scan(void)
 		raw_spin_unlock_irq(&object->lock);
 
 		/*
-		 * Do a cond_resched() to avoid soft lockup every 64k objects.
-		 * Make sure a reference has been taken so that the object
-		 * won't go away without RCU read lock.
+		 * Do a cond_resched() every 64k objects to avoid soft lockup.
 		 */
-		if (!(loop1_cnt & 0xffff)) {
-			if (!obj_pinned && !get_object(object)) {
-				/* Try the next object instead */
-				loop1_cnt--;
-				continue;
-			}
-
-			rcu_read_unlock();
-			cond_resched();
-			rcu_read_lock();
-
-			if (!obj_pinned)
-				put_object(object);
-		}
+		if (!(++loop_cnt & 0xffff) &&
+		    !kmemleak_cond_resched(object, obj_pinned))
+			loop_cnt--; /* Try again on next object */
 	}
 	rcu_read_unlock();
 
@@ -1598,7 +1605,15 @@ static void kmemleak_scan(void)
 	 * scan and color them gray until the next scan.
 	 */
 	rcu_read_lock();
+	loop_cnt = 0;
 	list_for_each_entry_rcu(object, &object_list, object_list) {
+		/*
+		 * Do a cond_resched() every 64k objects to avoid soft lockup.
+		 */
+		if (!(++loop_cnt & 0xffff) &&
+		    !kmemleak_cond_resched(object, false))
+			loop_cnt--;	/* Try again on next object */
+
 		/*
 		 * This is racy but we can save the overhead of lock/unlock
 		 * calls. The missed objects, if any, should be caught in
@@ -1632,7 +1647,15 @@ static void kmemleak_scan(void)
 	 * Scanning result reporting.
 	 */
 	rcu_read_lock();
+	loop_cnt = 0;
 	list_for_each_entry_rcu(object, &object_list, object_list) {
+		/*
+		 * Do a cond_resched() every 64k objects to avoid soft lockup.
+		 */
+		if (!(++loop_cnt & 0xffff) &&
+		    !kmemleak_cond_resched(object, false))
+			loop_cnt--;	/* Try again on next object */
+
 		/*
 		 * This is racy but we can save the overhead of lock/unlock
 		 * calls. The missed objects, if any, should be caught in
diff --git a/mm/kmsan/instrumentation.c b/mm/kmsan/instrumentation.c
index 280d15413268..271f135f97a1 100644
--- a/mm/kmsan/instrumentation.c
+++ b/mm/kmsan/instrumentation.c
@@ -14,6 +14,7 @@
 
 #include "kmsan.h"
 #include <linux/gfp.h>
+#include <linux/kmsan_string.h>
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 
diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c
index 21e3e196ec3c..a787c04e9583 100644
--- a/mm/kmsan/shadow.c
+++ b/mm/kmsan/shadow.c
@@ -167,6 +167,7 @@ void kmsan_copy_page_meta(struct page *dst, struct page *src)
 	__memcpy(origin_ptr_for(dst), origin_ptr_for(src), PAGE_SIZE);
 	kmsan_leave_runtime();
 }
+EXPORT_SYMBOL(kmsan_copy_page_meta);
 
 void kmsan_alloc_page(struct page *page, unsigned int order, gfp_t flags)
 {
diff --git a/mm/madvise.c b/mm/madvise.c
index 2baa93ca2310..c7105ec6d08c 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -813,7 +813,14 @@ static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma,
 	if (start & ~huge_page_mask(hstate_vma(vma)))
 		return false;
 
-	*end = ALIGN(*end, huge_page_size(hstate_vma(vma)));
+	/*
+	 * Madvise callers expect the length to be rounded up to PAGE_SIZE
+	 * boundaries, and may be unaware that this VMA uses huge pages.
+	 * Avoid unexpected data loss by rounding down the number of
+	 * huge pages freed.
+	 */
+	*end = ALIGN_DOWN(*end, huge_page_size(hstate_vma(vma)));
+
 	return true;
 }
 
@@ -828,6 +835,9 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior))
 		return -EINVAL;
 
+	if (start == end)
+		return 0;
+
 	if (!userfaultfd_remove(vma, start, end)) {
 		*prev = NULL; /* mmap_lock has been dropped, prev is stale */
 
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index f116b7b6333e..fa8c9d07f9ce 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -131,8 +131,8 @@ static void memory_tier_device_release(struct device *dev)
 	kfree(tier);
 }
 
-static ssize_t nodes_show(struct device *dev,
-			  struct device_attribute *attr, char *buf)
+static ssize_t nodelist_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	int ret;
 	nodemask_t nmask;
@@ -143,10 +143,10 @@ static ssize_t nodes_show(struct device *dev,
 	mutex_unlock(&memory_tier_lock);
 	return ret;
 }
-static DEVICE_ATTR_RO(nodes);
+static DEVICE_ATTR_RO(nodelist);
 
 static struct attribute *memtier_dev_attrs[] = {
-	&dev_attr_nodes.attr,
+	&dev_attr_nodelist.attr,
 	NULL
 };
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 1379e1912772..dff333593a8a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1582,6 +1582,13 @@ out:
 	 */
 	list_splice(&ret_pages, from);
 
+	/*
+	 * Return 0 in case all subpages of fail-to-migrate THPs are
+	 * migrated successfully.
+	 */
+	if (list_empty(from))
+		rc = 0;
+
 	count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
 	count_vm_events(PGMIGRATE_FAIL, nr_failed_pages);
 	count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
diff --git a/mm/mmap.c b/mm/mmap.c
index 3696b1909199..69c2f3523102 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2853,6 +2853,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 			if (next->vm_flags != vma->vm_flags)
 				goto out;
 
+			if (start + size <= next->vm_end)
+				break;
+
 			prev = next;
 		}
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b5a6c815ae28..218b28ee49ed 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -807,6 +807,7 @@ static void prep_compound_tail(struct page *head, int tail_idx)
 
 	p->mapping = TAIL_MAPPING;
 	set_compound_head(p, head);
+	set_page_private(p, 0);
 }
 
 void prep_compound_page(struct page *page, unsigned int order)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 04141a9bea70..47fbc1696466 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -330,7 +330,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 				      zone->zone_start_pfn);
 
 	if (skip_isolation) {
-		int mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
+		int mt __maybe_unused = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
 
 		VM_BUG_ON(!is_migrate_isolate(mt));
 	} else {
diff --git a/mm/shmem.c b/mm/shmem.c
index 8280a5cb48df..c1d8b8a1aa3b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2424,9 +2424,26 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 
 		if (!zeropage) {	/* COPY */
 			page_kaddr = kmap_local_folio(folio, 0);
+			/*
+			 * The read mmap_lock is held here.  Despite the
+			 * mmap_lock being read recursive a deadlock is still
+			 * possible if a writer has taken a lock.  For example:
+			 *
+			 * process A thread 1 takes read lock on own mmap_lock
+			 * process A thread 2 calls mmap, blocks taking write lock
+			 * process B thread 1 takes page fault, read lock on own mmap lock
+			 * process B thread 2 calls mmap, blocks taking write lock
+			 * process A thread 1 blocks taking read lock on process B
+			 * process B thread 1 blocks taking read lock on process A
+			 *
+			 * Disable page faults to prevent potential deadlock
+			 * and retry the copy outside the mmap_lock.
+			 */
+			pagefault_disable();
 			ret = copy_from_user(page_kaddr,
 					     (const void __user *)src_addr,
 					     PAGE_SIZE);
+			pagefault_enable();
 			kunmap_local(page_kaddr);
 
 			/* fallback to copy_from_user outside mmap_lock */
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index e24e8a47ce8a..3d0fef3980b3 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -157,11 +157,28 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 		if (!page)
 			goto out;
 
-		page_kaddr = kmap_atomic(page);
+		page_kaddr = kmap_local_page(page);
+		/*
+		 * The read mmap_lock is held here.  Despite the
+		 * mmap_lock being read recursive a deadlock is still
+		 * possible if a writer has taken a lock.  For example:
+		 *
+		 * process A thread 1 takes read lock on own mmap_lock
+		 * process A thread 2 calls mmap, blocks taking write lock
+		 * process B thread 1 takes page fault, read lock on own mmap lock
+		 * process B thread 2 calls mmap, blocks taking write lock
+		 * process A thread 1 blocks taking read lock on process B
+		 * process B thread 1 blocks taking read lock on process A
+		 *
+		 * Disable page faults to prevent potential deadlock
+		 * and retry the copy outside the mmap_lock.
+		 */
+		pagefault_disable();
 		ret = copy_from_user(page_kaddr,
 				     (const void __user *) src_addr,
 				     PAGE_SIZE);
-		kunmap_atomic(page_kaddr);
+		pagefault_enable();
+		kunmap_local(page_kaddr);
 
 		/* fallback to copy_from_user outside mmap_lock */
 		if (unlikely(ret)) {
@@ -646,11 +663,11 @@ retry:
 			mmap_read_unlock(dst_mm);
 			BUG_ON(!page);
 
-			page_kaddr = kmap(page);
+			page_kaddr = kmap_local_page(page);
 			err = copy_from_user(page_kaddr,
 					     (const void __user *) src_addr,
 					     PAGE_SIZE);
-			kunmap(page);
+			kunmap_local(page_kaddr);
 			if (unlikely(err)) {
 				err = -EFAULT;
 				goto out;