Merge branch 'sched/urgent' into sched/core, to resolve conflicts

The following fix in sched/urgent:

  e08d007f9d81 ("sched/debug: Fix avg_vruntime() usage")

is in conflict with this pending commit in sched/core:

  4823725d9d1d ("sched/fair: Increase weight bits for avg_vruntime")

Both modify the same variable definition and initialization blocks,
resolve it by merging the two.

 Conflicts:
	kernel/sched/debug.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

27 files changed, 406 insertions, 204 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4872d2a6c42d..71f9143fe90f 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1787,7 +1787,16 @@ static void btf_free_id(struct btf *btf)
 	 * of the _bh() version.
 	 */
 	spin_lock_irqsave(&btf_idr_lock, flags);
-	idr_remove(&btf_idr, btf->id);
+	if (btf->id) {
+		idr_remove(&btf_idr, btf->id);
+		/*
+		 * Clear the id here to make this function idempotent, since it will get
+		 * called a couple of times for module BTFs: on module unload, and then
+		 * the final btf_put(). btf_alloc_id() starts IDs with 1, so we can use
+		 * 0 as sentinel value.
+		 */
+		WRITE_ONCE(btf->id, 0);
+	}
 	spin_unlock_irqrestore(&btf_idr_lock, flags);
 }
 
@@ -8115,7 +8124,7 @@ static void bpf_btf_show_fdinfo(struct seq_file *m, struct file *filp)
 {
 	const struct btf *btf = filp->private_data;
 
-	seq_printf(m, "btf_id:\t%u\n", btf->id);
+	seq_printf(m, "btf_id:\t%u\n", READ_ONCE(btf->id));
 }
 #endif
 
@@ -8197,7 +8206,7 @@ int btf_get_info_by_fd(const struct btf *btf,
 	if (copy_from_user(&info, uinfo, info_copy))
 		return -EFAULT;
 
-	info.id = btf->id;
+	info.id = READ_ONCE(btf->id);
 	ubtf = u64_to_user_ptr(info.btf);
 	btf_copy = min_t(u32, btf->data_size, info.btf_size);
 	if (copy_to_user(ubtf, btf->data, btf_copy))
@@ -8260,7 +8269,7 @@ int btf_get_fd_by_id(u32 id)
 
 u32 btf_obj_id(const struct btf *btf)
 {
-	return btf->id;
+	return READ_ONCE(btf->id);
 }
 
 bool btf_is_kernel(const struct btf *btf)
@@ -8382,6 +8391,13 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			if (btf_mod->module != module)
 				continue;
 
+			/*
+			 * For modules, we do the freeing of BTF IDR as soon as
+			 * module goes away to disable BTF discovery, since the
+			 * btf_try_get_module() on such BTFs will fail. This may
+			 * be called again on btf_put(), but it's ok to do so.
+			 */
+			btf_free_id(btf_mod->btf);
 			list_del(&btf_mod->list);
 			if (btf_mod->sysfs_attr)
 				sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 3ece2da55625..7b675a451ec8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1422,6 +1422,27 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
 		*to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off);
 		break;
+
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_B:
+		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^
+				      from->imm);
+		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		/*
+		 * Cannot use BPF_STX_MEM() macro here as it
+		 * hardcodes BPF_MEM mode, losing PROBE_MEM32
+		 * and breaking arena addressing in the JIT.
+		 */
+		*to++ = (struct bpf_insn) {
+			.code  = BPF_STX | BPF_PROBE_MEM32 |
+				 BPF_SIZE(from->code),
+			.dst_reg = from->dst_reg,
+			.src_reg = BPF_REG_AX,
+			.off   = from->off,
+		};
+		break;
 	}
 out:
 	return to - to_buff;
@@ -1736,6 +1757,12 @@ bool bpf_opcode_in_insntable(u8 code)
 }
 
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+/* Absolute value of s32 without undefined behavior for S32_MIN */
+static u32 abs_s32(s32 x)
+{
+	return x >= 0 ? (u32)x : -(u32)x;
+}
+
 /**
  *	___bpf_prog_run - run eBPF program on a given context
  *	@regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1900,8 +1927,8 @@ select_insn:
 			DST = do_div(AX, (u32) SRC);
 			break;
 		case 1:
-			AX = abs((s32)DST);
-			AX = do_div(AX, abs((s32)SRC));
+			AX = abs_s32((s32)DST);
+			AX = do_div(AX, abs_s32((s32)SRC));
 			if ((s32)DST < 0)
 				DST = (u32)-AX;
 			else
@@ -1928,8 +1955,8 @@ select_insn:
 			DST = do_div(AX, (u32) IMM);
 			break;
 		case 1:
-			AX = abs((s32)DST);
-			AX = do_div(AX, abs((s32)IMM));
+			AX = abs_s32((s32)DST);
+			AX = do_div(AX, abs_s32((s32)IMM));
 			if ((s32)DST < 0)
 				DST = (u32)-AX;
 			else
@@ -1955,8 +1982,8 @@ select_insn:
 			DST = (u32) AX;
 			break;
 		case 1:
-			AX = abs((s32)DST);
-			do_div(AX, abs((s32)SRC));
+			AX = abs_s32((s32)DST);
+			do_div(AX, abs_s32((s32)SRC));
 			if (((s32)DST < 0) == ((s32)SRC < 0))
 				DST = (u32)AX;
 			else
@@ -1982,8 +2009,8 @@ select_insn:
 			DST = (u32) AX;
 			break;
 		case 1:
-			AX = abs((s32)DST);
-			do_div(AX, abs((s32)IMM));
+			AX = abs_s32((s32)DST);
+			do_div(AX, abs_s32((s32)IMM));
 			if (((s32)DST < 0) == ((s32)IMM < 0))
 				DST = (u32)AX;
 			else
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 159b25f8269d..f108c01ff6d0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -15910,6 +15910,13 @@ static void scalar_byte_swap(struct bpf_reg_state *dst_reg, struct bpf_insn *ins
 	/* Apply bswap if alu64 or switch between big-endian and little-endian machines */
 	bool need_bswap = alu64 || (to_le == is_big_endian);
 
+	/*
+	 * If the register is mutated, manually reset its scalar ID to break
+	 * any existing ties and avoid incorrect bounds propagation.
+	 */
+	if (need_bswap || insn->imm == 16 || insn->imm == 32)
+		dst_reg->id = 0;
+
 	if (need_bswap) {
 		if (insn->imm == 16)
 			dst_reg->var_off = tnum_bswap16(dst_reg->var_off);
@@ -15992,7 +15999,7 @@ static int maybe_fork_scalars(struct bpf_verifier_env *env, struct bpf_insn *ins
 	else
 		return 0;
 
-	branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
+	branch = push_stack(env, env->insn_idx, env->insn_idx, false);
 	if (IS_ERR(branch))
 		return PTR_ERR(branch);
 
@@ -17408,6 +17415,12 @@ static void sync_linked_regs(struct bpf_verifier_env *env, struct bpf_verifier_s
 			continue;
 		if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST))
 			continue;
+		/*
+		 * Skip mixed 32/64-bit links: the delta relationship doesn't
+		 * hold across different ALU widths.
+		 */
+		if (((reg->id ^ known_reg->id) & BPF_ADD_CONST) == BPF_ADD_CONST)
+			continue;
 		if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) ||
 		    reg->off == known_reg->off) {
 			s32 saved_subreg_def = reg->subreg_def;
@@ -17435,7 +17448,7 @@ static void sync_linked_regs(struct bpf_verifier_env *env, struct bpf_verifier_s
 			scalar32_min_max_add(reg, &fake_reg);
 			scalar_min_max_add(reg, &fake_reg);
 			reg->var_off = tnum_add(reg->var_off, fake_reg.var_off);
-			if (known_reg->id & BPF_ADD_CONST32)
+			if ((reg->id | known_reg->id) & BPF_ADD_CONST32)
 				zext_32_to_64(reg);
 			reg_bounds_sync(reg);
 		}
@@ -19863,11 +19876,14 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		 * Also verify that new value satisfies old value range knowledge.
 		 */
 
-		/* ADD_CONST mismatch: different linking semantics */
-		if ((rold->id & BPF_ADD_CONST) && !(rcur->id & BPF_ADD_CONST))
-			return false;
-
-		if (rold->id && !(rold->id & BPF_ADD_CONST) && (rcur->id & BPF_ADD_CONST))
+		/*
+		 * ADD_CONST flags must match exactly: BPF_ADD_CONST32 and
+		 * BPF_ADD_CONST64 have different linking semantics in
+		 * sync_linked_regs() (alu32 zero-extends, alu64 does not),
+		 * so pruning across different flag types is unsafe.
+		 */
+		if (rold->id &&
+		    (rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST))
 			return false;
 
 		/* Both have offset linkage: offsets must match */
@@ -20904,7 +20920,8 @@ static int process_bpf_exit_full(struct bpf_verifier_env *env,
 	 * state when it exits.
 	 */
 	int err = check_resource_leak(env, exception_exit,
-				      !env->cur_state->curframe,
+				      exception_exit || !env->cur_state->curframe,
+				      exception_exit ? "bpf_throw" :
 				      "BPF_EXIT instruction in main prog");
 	if (err)
 		return err;
diff --git a/kernel/crash_dump_dm_crypt.c b/kernel/crash_dump_dm_crypt.c
index 1f4067fbdb94..a20d4097744a 100644
--- a/kernel/crash_dump_dm_crypt.c
+++ b/kernel/crash_dump_dm_crypt.c
@@ -168,8 +168,8 @@ static int read_key_from_user_keying(struct dm_crypt_key *dm_key)
 
 	memcpy(dm_key->data, ukp->data, ukp->datalen);
 	dm_key->key_size = ukp->datalen;
-	kexec_dprintk("Get dm crypt key (size=%u) %s: %8ph\n", dm_key->key_size,
-		      dm_key->key_desc, dm_key->data);
+	kexec_dprintk("Get dm crypt key (size=%u) %s\n", dm_key->key_size,
+		      dm_key->key_desc);
 
 out:
 	up_read(&key->sem);
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 86f87e43438c..0677918f06a8 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -453,7 +453,7 @@ static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
 	return overlap;
 }
 
-static void active_cacheline_inc_overlap(phys_addr_t cln)
+static void active_cacheline_inc_overlap(phys_addr_t cln, bool is_cache_clean)
 {
 	int overlap = active_cacheline_read_overlap(cln);
 
@@ -462,7 +462,7 @@ static void active_cacheline_inc_overlap(phys_addr_t cln)
 	/* If we overflowed the overlap counter then we're potentially
 	 * leaking dma-mappings.
 	 */
-	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+	WARN_ONCE(!is_cache_clean && overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
 		  pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"),
 		  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
 }
@@ -495,7 +495,7 @@ static int active_cacheline_insert(struct dma_debug_entry *entry,
 	if (rc == -EEXIST) {
 		struct dma_debug_entry *existing;
 
-		active_cacheline_inc_overlap(cln);
+		active_cacheline_inc_overlap(cln, entry->is_cache_clean);
 		existing = radix_tree_lookup(&dma_active_cacheline, cln);
 		/* A lookup failure here after we got -EEXIST is unexpected. */
 		WARN_ON(!existing);
@@ -601,7 +601,8 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
 	unsigned long flags;
 	int rc;
 
-	entry->is_cache_clean = !!(attrs & DMA_ATTR_CPU_CACHE_CLEAN);
+	entry->is_cache_clean = attrs & (DMA_ATTR_DEBUGGING_IGNORE_CACHELINES |
+					 DMA_ATTR_REQUIRE_COHERENT);
 
 	bucket = get_hash_bucket(entry, &flags);
 	hash_bucket_add(bucket, entry);
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index e89f175e9c2d..6184ff303f08 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -84,7 +84,7 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 	dma_addr_t dma_addr;
 
 	if (is_swiotlb_force_bounce(dev)) {
-		if (attrs & DMA_ATTR_MMIO)
+		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 			return DMA_MAPPING_ERROR;
 
 		return swiotlb_map(dev, phys, size, dir, attrs);
@@ -98,7 +98,8 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 		dma_addr = phys_to_dma(dev, phys);
 		if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
 		    dma_kmalloc_needs_bounce(dev, size, dir)) {
-			if (is_swiotlb_active(dev))
+			if (is_swiotlb_active(dev) &&
+			    !(attrs & DMA_ATTR_REQUIRE_COHERENT))
 				return swiotlb_map(dev, phys, size, dir, attrs);
 
 			goto err_overflow;
@@ -123,7 +124,7 @@ static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr,
 {
 	phys_addr_t phys;
 
-	if (attrs & DMA_ATTR_MMIO)
+	if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 		/* nothing to do: uncached and no swiotlb */
 		return;
 
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 3928a509c44c..6d3dd0bd3a88 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -164,6 +164,9 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 	if (WARN_ON_ONCE(!dev->dma_mask))
 		return DMA_MAPPING_ERROR;
 
+	if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT))
+		return DMA_MAPPING_ERROR;
+
 	if (dma_map_direct(dev, ops) ||
 	    (!is_mmio && arch_dma_map_phys_direct(dev, phys + size)))
 		addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
@@ -235,6 +238,9 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 
 	BUG_ON(!valid_dma_direction(dir));
 
+	if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT))
+		return -EOPNOTSUPP;
+
 	if (WARN_ON_ONCE(!dev->dma_mask))
 		return 0;
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index d8e6f1d889d5..9fd73700ddcf 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -30,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
+#include <linux/kmsan-checks.h>
 #include <linux/iommu-helper.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
@@ -901,10 +902,19 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 
 			local_irq_save(flags);
 			page = pfn_to_page(pfn);
-			if (dir == DMA_TO_DEVICE)
+			if (dir == DMA_TO_DEVICE) {
+				/*
+				 * Ideally, kmsan_check_highmem_page()
+				 * could be used here to detect infoleaks,
+				 * but callers may map uninitialized buffers
+				 * that will be written by the device,
+				 * causing false positives.
+				 */
 				memcpy_from_page(vaddr, page, offset, sz);
-			else
+			} else {
+				kmsan_unpoison_memory(vaddr, sz);
 				memcpy_to_page(page, offset, vaddr, sz);
+			}
 			local_irq_restore(flags);
 
 			size -= sz;
@@ -913,8 +923,15 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 			offset = 0;
 		}
 	} else if (dir == DMA_TO_DEVICE) {
+		/*
+		 * Ideally, kmsan_check_memory() could be used here to detect
+		 * infoleaks (uninitialized data being sent to device), but
+		 * callers may map uninitialized buffers that will be written
+		 * by the device, causing false positives.
+		 */
 		memcpy(vaddr, phys_to_virt(orig_addr), size);
 	} else {
+		kmsan_unpoison_memory(vaddr, size);
 		memcpy(phys_to_virt(orig_addr), vaddr, size);
 	}
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1f5699b339ec..89b40e439717 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4813,7 +4813,7 @@ static void __perf_event_read(void *info)
 	struct perf_event *sub, *event = data->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
-	struct pmu *pmu = event->pmu;
+	struct pmu *pmu;
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -4825,7 +4825,7 @@ static void __perf_event_read(void *info)
 	if (ctx->task && cpuctx->task_ctx != ctx)
 		return;
 
-	raw_spin_lock(&ctx->lock);
+	guard(raw_spinlock)(&ctx->lock);
 	ctx_time_update_event(ctx, event);
 
 	perf_event_update_time(event);
@@ -4833,25 +4833,22 @@ static void __perf_event_read(void *info)
 		perf_event_update_sibling_time(event);
 
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
-		goto unlock;
+		return;
 
 	if (!data->group) {
-		pmu->read(event);
+		perf_pmu_read(event);
 		data->ret = 0;
-		goto unlock;
+		return;
 	}
 
+	pmu = event->pmu_ctx->pmu;
 	pmu->start_txn(pmu, PERF_PMU_TXN_READ);
 
-	pmu->read(event);
-
+	perf_pmu_read(event);
 	for_each_sibling_event(sub, event)
 		perf_pmu_read(sub);
 
 	data->ret = pmu->commit_txn(pmu);
-
-unlock:
-	raw_spin_unlock(&ctx->lock);
 }
 
 static inline u64 perf_event_count(struct perf_event *event, bool self)
@@ -14744,7 +14741,7 @@ inherit_event(struct perf_event *parent_event,
 	get_ctx(child_ctx);
 	child_event->ctx = child_ctx;
 
-	pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
+	pmu_ctx = find_get_pmu_context(parent_event->pmu_ctx->pmu, child_ctx, child_event);
 	if (IS_ERR(pmu_ctx)) {
 		free_event(child_event);
 		return ERR_CAST(pmu_ctx);
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index cf7e610eac42..31e83a09789e 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -342,7 +342,7 @@ static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr)
 	if (!vma)
 		return FUTEX_NO_NODE;
 
-	mpol = vma_policy(vma);
+	mpol = READ_ONCE(vma->vm_policy);
 	if (!mpol)
 		return FUTEX_NO_NODE;
 
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index bc1f7e83a37e..7808068fa59e 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -918,7 +918,7 @@ int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to;
-	struct task_struct *exiting = NULL;
+	struct task_struct *exiting;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_q q = futex_q_init;
 	DEFINE_WAKE_Q(wake_q);
@@ -933,6 +933,7 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl
 	to = futex_setup_timer(time, &timeout, flags, 0);
 
 retry:
+	exiting = NULL;
 	ret = get_futex_key(uaddr, flags, &q.key, FUTEX_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c
index 743c7a728237..77ad9691f6a6 100644
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -459,6 +459,14 @@ SYSCALL_DEFINE4(futex_requeue,
 	if (ret)
 		return ret;
 
+	/*
+	 * For now mandate both flags are identical, like the sys_futex()
+	 * interface has. If/when we merge the variable sized futex support,
+	 * that patch can modify this test to allow a difference in size.
+	 */
+	if (futexes[0].w.flags != futexes[1].w.flags)
+		return -EINVAL;
+
 	cmpval = futexes[0].w.val;
 
 	return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags,
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 5f8c9e12eaec..5429e9f19b65 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -40,7 +40,7 @@ void pm_restore_gfp_mask(void)
 {
 	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 
-	if (WARN_ON(!saved_gfp_count) || --saved_gfp_count)
+	if (!saved_gfp_count || --saved_gfp_count)
 		return;
 
 	gfp_allowed_mask = saved_gfp_mask;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 6e1321837c66..a564650734dc 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -2855,6 +2855,17 @@ int snapshot_write_finalize(struct snapshot_handle *handle)
 {
 	int error;
 
+	/*
+	 * Call snapshot_write_next() to drain any trailing zero pages,
+	 * but make sure we're in the data page region first.
+	 * This function can return PAGE_SIZE if the kernel was expecting
+	 * another copy page. Return -ENODATA in that situation.
+	 */
+	if (handle->cur > nr_meta_pages + 1) {
+		error = snapshot_write_next(handle);
+		if (error)
+			return error > 0 ? -ENODATA : error;
+	}
 	copy_last_highmem_page();
 	error = hibernate_restore_protect_page(handle->buffer);
 	/* Do that only if we have loaded the image entirely */
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index dc5d614b372c..9b10b57b79ad 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -502,6 +502,15 @@ do {									\
 	___locked;							\
 })
 
+#define raw_spin_trylock_irqsave_rcu_node(p, flags)			\
+({									\
+	bool ___locked = raw_spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \
+									\
+	if (___locked)							\
+		smp_mb__after_unlock_lock();				\
+	___locked;							\
+})
+
 #define raw_lockdep_assert_held_rcu_node(p)				\
 	lockdep_assert_held(&ACCESS_PRIVATE(p, lock))
 
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 3450c3751ef7..a2e2d516e51b 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/export.h>
+#include <linux/irq_work.h>
 #include <linux/mutex.h>
 #include <linux/preempt.h>
 #include <linux/rcupdate_wait.h>
@@ -41,6 +42,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp)
 	ssp->srcu_idx_max = 0;
 	INIT_WORK(&ssp->srcu_work, srcu_drive_gp);
 	INIT_LIST_HEAD(&ssp->srcu_work.entry);
+	init_irq_work(&ssp->srcu_irq_work, srcu_tiny_irq_work);
 	return 0;
 }
 
@@ -84,6 +86,7 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
+	irq_work_sync(&ssp->srcu_irq_work);
 	flush_work(&ssp->srcu_work);
 	WARN_ON(ssp->srcu_gp_running);
 	WARN_ON(ssp->srcu_gp_waiting);
@@ -177,6 +180,20 @@ void srcu_drive_gp(struct work_struct *wp)
 }
 EXPORT_SYMBOL_GPL(srcu_drive_gp);
 
+/*
+ * Use an irq_work to defer schedule_work() to avoid acquiring the workqueue
+ * pool->lock while the caller might hold scheduler locks, causing lockdep
+ * splats due to workqueue_init() doing a wakeup.
+ */
+void srcu_tiny_irq_work(struct irq_work *irq_work)
+{
+	struct srcu_struct *ssp;
+
+	ssp = container_of(irq_work, struct srcu_struct, srcu_irq_work);
+	schedule_work(&ssp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(srcu_tiny_irq_work);
+
 static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 {
 	unsigned long cookie;
@@ -189,7 +206,7 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 	WRITE_ONCE(ssp->srcu_idx_max, cookie);
 	if (!READ_ONCE(ssp->srcu_gp_running)) {
 		if (likely(srcu_init_done))
-			schedule_work(&ssp->srcu_work);
+			irq_work_queue(&ssp->srcu_irq_work);
 		else if (list_empty(&ssp->srcu_work.entry))
 			list_add(&ssp->srcu_work.entry, &srcu_boot_list);
 	}
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index aef8e91ad33e..0d01cd8c4b4a 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/preempt.h>
+#include <linux/irq_work.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
@@ -75,44 +76,9 @@ static bool __read_mostly srcu_init_done;
 static void srcu_invoke_callbacks(struct work_struct *work);
 static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
 static void process_srcu(struct work_struct *work);
+static void srcu_irq_work(struct irq_work *work);
 static void srcu_delay_timer(struct timer_list *t);
 
-/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
-#define spin_lock_rcu_node(p)							\
-do {										\
-	spin_lock(&ACCESS_PRIVATE(p, lock));					\
-	smp_mb__after_unlock_lock();						\
-} while (0)
-
-#define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock))
-
-#define spin_lock_irq_rcu_node(p)						\
-do {										\
-	spin_lock_irq(&ACCESS_PRIVATE(p, lock));				\
-	smp_mb__after_unlock_lock();						\
-} while (0)
-
-#define spin_unlock_irq_rcu_node(p)						\
-	spin_unlock_irq(&ACCESS_PRIVATE(p, lock))
-
-#define spin_lock_irqsave_rcu_node(p, flags)					\
-do {										\
-	spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags);			\
-	smp_mb__after_unlock_lock();						\
-} while (0)
-
-#define spin_trylock_irqsave_rcu_node(p, flags)					\
-({										\
-	bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \
-										\
-	if (___locked)								\
-		smp_mb__after_unlock_lock();					\
-	___locked;								\
-})
-
-#define spin_unlock_irqrestore_rcu_node(p, flags)				\
-	spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)			\
-
 /*
  * Initialize SRCU per-CPU data.  Note that statically allocated
  * srcu_struct structures might already have srcu_read_lock() and
@@ -131,7 +97,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp)
 	 */
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(ssp->sda, cpu);
-		spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
+		raw_spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
 		rcu_segcblist_init(&sdp->srcu_cblist);
 		sdp->srcu_cblist_invoking = false;
 		sdp->srcu_gp_seq_needed = ssp->srcu_sup->srcu_gp_seq;
@@ -186,7 +152,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 
 	/* Each pass through this loop initializes one srcu_node structure. */
 	srcu_for_each_node_breadth_first(ssp, snp) {
-		spin_lock_init(&ACCESS_PRIVATE(snp, lock));
+		raw_spin_lock_init(&ACCESS_PRIVATE(snp, lock));
 		BUILD_BUG_ON(ARRAY_SIZE(snp->srcu_have_cbs) !=
 			     ARRAY_SIZE(snp->srcu_data_have_cbs));
 		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
@@ -242,7 +208,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	if (!ssp->srcu_sup)
 		return -ENOMEM;
 	if (!is_static)
-		spin_lock_init(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
+		raw_spin_lock_init(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
 	ssp->srcu_sup->srcu_size_state = SRCU_SIZE_SMALL;
 	ssp->srcu_sup->node = NULL;
 	mutex_init(&ssp->srcu_sup->srcu_cb_mutex);
@@ -252,6 +218,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	mutex_init(&ssp->srcu_sup->srcu_barrier_mutex);
 	atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 0);
 	INIT_DELAYED_WORK(&ssp->srcu_sup->work, process_srcu);
+	init_irq_work(&ssp->srcu_sup->irq_work, srcu_irq_work);
 	ssp->srcu_sup->sda_is_static = is_static;
 	if (!is_static) {
 		ssp->sda = alloc_percpu(struct srcu_data);
@@ -263,9 +230,12 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	ssp->srcu_sup->srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL;
 	ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
-		if (!init_srcu_struct_nodes(ssp, is_static ? GFP_ATOMIC : GFP_KERNEL))
+		if (!preemptible())
+			WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_ALLOC);
+		else if (init_srcu_struct_nodes(ssp, GFP_KERNEL))
+			WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
+		else
 			goto err_free_sda;
-		WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
 	}
 	ssp->srcu_sup->srcu_ssp = ssp;
 	smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed,
@@ -394,20 +364,20 @@ static void srcu_transition_to_big(struct srcu_struct *ssp)
 	/* Double-checked locking on ->srcu_size-state. */
 	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) != SRCU_SIZE_SMALL)
 		return;
-	spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
+	raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
 	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) != SRCU_SIZE_SMALL) {
-		spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
+		raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 		return;
 	}
 	__srcu_transition_to_big(ssp);
-	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
+	raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 }
 
 /*
  * Check to see if the just-encountered contention event justifies
  * a transition to SRCU_SIZE_BIG.
  */
-static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp)
+static void raw_spin_lock_irqsave_check_contention(struct srcu_struct *ssp)
 {
 	unsigned long j;
 
@@ -429,16 +399,16 @@ static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp)
  * to SRCU_SIZE_BIG.  But only if the srcutree.convert_to_big module
  * parameter permits this.
  */
-static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags)
+static void raw_spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags)
 {