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

Conflicts are simple overlapping changes.

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

5 files changed, 77 insertions, 76 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 924553aa8f78..dfc940d5221d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5440,8 +5440,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			continue;
 		}
 
-		refs = min3(pages_per_huge_page(h) - pfn_offset,
-			    (vma->vm_end - vaddr) >> PAGE_SHIFT, remainder);
+		/* vaddr may not be aligned to PAGE_SIZE */
+		refs = min3(pages_per_huge_page(h) - pfn_offset, remainder,
+		    (vma->vm_end - ALIGN_DOWN(vaddr, PAGE_SIZE)) >> PAGE_SHIFT);
 
 		if (pages || vmas)
 			record_subpages_vmas(mem_map_offset(page, pfn_offset),
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 98e3059bfea4..d739cdd1621a 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -9,6 +9,7 @@
 #ifdef CONFIG_KASAN_HW_TAGS
 
 #include <linux/static_key.h>
+#include "../slab.h"
 
 DECLARE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
 extern bool kasan_flag_async __ro_after_init;
@@ -387,6 +388,17 @@ static inline void kasan_unpoison(const void *addr, size_t size, bool init)
 
 	if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK))
 		return;
+	/*
+	 * Explicitly initialize the memory with the precise object size to
+	 * avoid overwriting the SLAB redzone. This disables initialization in
+	 * the arch code and may thus lead to performance penalty. The penalty
+	 * is accepted since SLAB redzones aren't enabled in production builds.
+	 */
+	if (__slub_debug_enabled() &&
+	    init && ((unsigned long)size & KASAN_GRANULE_MASK)) {
+		init = false;
+		memzero_explicit((void *)addr, size);
+	}
 	size = round_up(size, KASAN_GRANULE_SIZE);
 
 	hw_set_mem_tag_range((void *)addr, size, tag, init);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3b97e17806be..3e97e68aef7a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3820,7 +3820,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 
 #endif /* CONFIG_FAIL_PAGE_ALLOC */
 
-static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
 	return __should_fail_alloc_page(gfp_mask, order);
 }
@@ -5221,9 +5221,6 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
 	int nr_populated = 0, nr_account = 0;
 
-	if (unlikely(nr_pages <= 0))
-		return 0;
-
 	/*
 	 * Skip populated array elements to determine if any pages need
 	 * to be allocated before disabling IRQs.
@@ -5231,19 +5228,35 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 	while (page_array && nr_populated < nr_pages && page_array[nr_populated])
 		nr_populated++;
 
+	/* No pages requested? */
+	if (unlikely(nr_pages <= 0))
+		goto out;
+
 	/* Already populated array? */
 	if (unlikely(page_array && nr_pages - nr_populated == 0))
-		return nr_populated;
+		goto out;
 
 	/* Use the single page allocator for one page. */
 	if (nr_pages - nr_populated == 1)
 		goto failed;
 
+#ifdef CONFIG_PAGE_OWNER
+	/*
+	 * PAGE_OWNER may recurse into the allocator to allocate space to
+	 * save the stack with pagesets.lock held. Releasing/reacquiring
+	 * removes much of the performance benefit of bulk allocation so
+	 * force the caller to allocate one page at a time as it'll have
+	 * similar performance to added complexity to the bulk allocator.
+	 */
+	if (static_branch_unlikely(&page_owner_inited))
+		goto failed;
+#endif
+
 	/* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
 	gfp &= gfp_allowed_mask;
 	alloc_gfp = gfp;
 	if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags))
-		return 0;
+		goto out;
 	gfp = alloc_gfp;
 
 	/* Find an allowed local zone that meets the low watermark. */
@@ -5311,6 +5324,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 	__count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account);
 	zone_statistics(ac.preferred_zoneref->zone, zone, nr_account);
 
+out:
 	return nr_populated;
 
 failed_irq:
@@ -5326,7 +5340,7 @@ failed:
 		nr_populated++;
 	}
 
-	return nr_populated;
+	goto out;
 }
 EXPORT_SYMBOL_GPL(__alloc_pages_bulk);
 
diff --git a/mm/slab.h b/mm/slab.h
index 67e06637ff2e..f997fd5e42c8 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -216,10 +216,18 @@ DECLARE_STATIC_KEY_FALSE(slub_debug_enabled);
 #endif
 extern void print_tracking(struct kmem_cache *s, void *object);
 long validate_slab_cache(struct kmem_cache *s);
+static inline bool __slub_debug_enabled(void)
+{
+	return static_branch_unlikely(&slub_debug_enabled);
+}
 #else
 static inline void print_tracking(struct kmem_cache *s, void *object)
 {
 }
+static inline bool __slub_debug_enabled(void)
+{
+	return false;
+}
 #endif
 
 /*
@@ -229,11 +237,10 @@ static inline void print_tracking(struct kmem_cache *s, void *object)
  */
 static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags)
 {
-#ifdef CONFIG_SLUB_DEBUG
-	VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
-	if (static_branch_unlikely(&slub_debug_enabled))
+	if (IS_ENABLED(CONFIG_SLUB_DEBUG))
+		VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
+	if (__slub_debug_enabled())
 		return s->flags & flags;
-#endif
 	return false;
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index dc863c1ea324..090fa14628f9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -26,7 +26,6 @@
 #include <linux/cpuset.h>
 #include <linux/mempolicy.h>
 #include <linux/ctype.h>
-#include <linux/stackdepot.h>
 #include <linux/debugobjects.h>
 #include <linux/kallsyms.h>
 #include <linux/kfence.h>
@@ -120,25 +119,11 @@
  */
 
 #ifdef CONFIG_SLUB_DEBUG
-
 #ifdef CONFIG_SLUB_DEBUG_ON
 DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
 #else
 DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
 #endif
-
-static inline bool __slub_debug_enabled(void)
-{
-	return static_branch_unlikely(&slub_debug_enabled);
-}
-
-#else		/* CONFIG_SLUB_DEBUG */
-
-static inline bool __slub_debug_enabled(void)
-{
-	return false;
-}
-
 #endif		/* CONFIG_SLUB_DEBUG */
 
 static inline bool kmem_cache_debug(struct kmem_cache *s)
@@ -221,8 +206,8 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
 #define TRACK_ADDRS_COUNT 16
 struct track {
 	unsigned long addr;	/* Called from address */
-#ifdef CONFIG_STACKDEPOT
-	depot_stack_handle_t handle;
+#ifdef CONFIG_STACKTRACE
+	unsigned long addrs[TRACK_ADDRS_COUNT];	/* Called from address */
 #endif
 	int cpu;		/* Was running on cpu */
 	int pid;		/* Pid context */
@@ -626,27 +611,22 @@ static struct track *get_track(struct kmem_cache *s, void *object,
 	return kasan_reset_tag(p + alloc);
 }
 
-#ifdef CONFIG_STACKDEPOT
-static depot_stack_handle_t save_stack_depot_trace(gfp_t flags)
-{
-	unsigned long entries[TRACK_ADDRS_COUNT];
-	depot_stack_handle_t handle;
-	unsigned int nr_entries;
-
-	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 4);
-	handle = stack_depot_save(entries, nr_entries, flags);
-	return handle;
-}
-#endif
-
 static void set_track(struct kmem_cache *s, void *object,
 			enum track_item alloc, unsigned long addr)
 {
 	struct track *p = get_track(s, object, alloc);
 
 	if (addr) {
-#ifdef CONFIG_STACKDEPOT
-		p->handle = save_stack_depot_trace(GFP_NOWAIT);
+#ifdef CONFIG_STACKTRACE
+		unsigned int nr_entries;
+
+		metadata_access_enable();
+		nr_entries = stack_trace_save(kasan_reset_tag(p->addrs),
+					      TRACK_ADDRS_COUNT, 3);
+		metadata_access_disable();
+
+		if (nr_entries < TRACK_ADDRS_COUNT)
+			p->addrs[nr_entries] = 0;
 #endif
 		p->addr = addr;
 		p->cpu = smp_processor_id();
@@ -673,19 +653,14 @@ static void print_track(const char *s, struct track *t, unsigned long pr_time)
 
 	pr_err("%s in %pS age=%lu cpu=%u pid=%d\n",
 	       s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
-#ifdef CONFIG_STACKDEPOT
+#ifdef CONFIG_STACKTRACE
 	{
-		depot_stack_handle_t handle;
-		unsigned long *entries;
-		unsigned int nr_entries;
-
-		handle = READ_ONCE(t->handle);
-		if (!handle) {
-			pr_err("object allocation/free stack trace missing\n");
-		} else {
-			nr_entries = stack_depot_fetch(handle, &entries);
-			stack_trace_print(entries, nr_entries, 0);
-		}
+		int i;
+		for (i = 0; i < TRACK_ADDRS_COUNT; i++)
+			if (t->addrs[i])
+				pr_err("\t%pS\n", (void *)t->addrs[i]);
+			else
+				break;
 	}
 #endif
 }
@@ -4059,26 +4034,18 @@ void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
 	objp = fixup_red_left(s, objp);
 	trackp = get_track(s, objp, TRACK_ALLOC);
 	kpp->kp_ret = (void *)trackp->addr;
-#ifdef CONFIG_STACKDEPOT
-	{
-		depot_stack_handle_t handle;
-		unsigned long *entries;
-		unsigned int nr_entries;
-
-		handle = READ_ONCE(trackp->handle);
-		if (handle) {
-			nr_entries = stack_depot_fetch(handle, &entries);
-			for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++)
-				kpp->kp_stack[i] = (void *)entries[i];
-		}
+#ifdef CONFIG_STACKTRACE
+	for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
+		kpp->kp_stack[i] = (void *)trackp->addrs[i];
+		if (!kpp->kp_stack[i])
+			break;
+	}
 
-		trackp = get_track(s, objp, TRACK_FREE);
-		handle = READ_ONCE(trackp->handle);
-		if (handle) {
-			nr_entries = stack_depot_fetch(handle, &entries);
-			for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++)
-				kpp->kp_free_stack[i] = (void *)entries[i];
-		}
+	trackp = get_track(s, objp, TRACK_FREE);
+	for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
+		kpp->kp_free_stack[i] = (void *)trackp->addrs[i];
+		if (!kpp->kp_free_stack[i])
+			break;
 	}
 #endif
 #endif