Merge tag 'mm-hotfixes-stable-2024-09-27-09-45' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

torvalds · torvalds · commit eee280841e1c · 2024-09-27T10:27:22.000-07:00
Pull  misc fixes from Andrew Morton:
 "19 hotfixes.  13 are cc:stable.

  There's a focus on fixes for the memfd_pin_folios() work which was
  added into 6.11. Apart from that, the usual shower of singleton fixes"

* tag 'mm-hotfixes-stable-2024-09-27-09-45' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  ocfs2: fix uninit-value in ocfs2_get_block()
  zram: don't free statically defined names
  memory tiers: use default_dram_perf_ref_source in log message
  Revert "list: test: fix tests for list_cut_position()"
  kselftests: mm: fix wrong __NR_userfaultfd value
  compiler.h: specify correct attribute for .rodata..c_jump_table
  mm/damon/Kconfig: update DAMON doc URL
  mm: kfence: fix elapsed time for allocated/freed track
  ocfs2: fix deadlock in ocfs2_get_system_file_inode
  ocfs2: reserve space for inline xattr before attaching reflink tree
  mm: migrate: annotate data-race in migrate_folio_unmap()
  mm/hugetlb: simplify refs in memfd_alloc_folio
  mm/gup: fix memfd_pin_folios alloc race panic
  mm/gup: fix memfd_pin_folios hugetlb page allocation
  mm/hugetlb: fix memfd_pin_folios resv_huge_pages leak
  mm/hugetlb: fix memfd_pin_folios free_huge_pages leak
  mm/filemap: fix filemap_get_folios_contig THP panic
  mm: make SPLIT_PTE_PTLOCKS depend on SMP
  tools: fix shared radix-tree build
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
@@ -2115,8 +2115,10 @@ static void zram_destroy_comps(struct zram *zram)
 		zram->num_active_comps--;
 	}
 
-	for (prio = ZRAM_SECONDARY_COMP; prio < ZRAM_MAX_COMPS; prio++) {
-		kfree(zram->comp_algs[prio]);
+	for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) {
+		/* Do not free statically defined compression algorithms */
+		if (zram->comp_algs[prio] != default_compressor)
+			kfree(zram->comp_algs[prio]);
 		zram->comp_algs[prio] = NULL;
 	}
 
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
@@ -156,9 +156,8 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock,
 	err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
 					  &ext_flags);
 	if (err) {
-		mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
-		     "%llu, NULL)\n", err, inode, (unsigned long long)iblock,
-		     (unsigned long long)p_blkno);
+		mlog(ML_ERROR, "get_blocks() failed, inode: 0x%p, "
+		     "block: %llu\n", inode, (unsigned long long)iblock);
 		goto bail;
 	}
 
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
@@ -973,7 +973,13 @@ int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr,
 	}
 
 	while (done < nr) {
-		down_read(&OCFS2_I(inode)->ip_alloc_sem);
+		if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
+			rc = -EAGAIN;
+			mlog(ML_ERROR,
+				 "Inode #%llu ip_alloc_sem is temporarily unavailable\n",
+				 (unsigned long long)OCFS2_I(inode)->ip_blkno);
+			break;
+		}
 		rc = ocfs2_extent_map_get_blocks(inode, v_block + done,
 						 &p_block, &p_count, NULL);
 		up_read(&OCFS2_I(inode)->ip_alloc_sem);
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
@@ -25,6 +25,7 @@
 #include "namei.h"
 #include "ocfs2_trace.h"
 #include "file.h"
+#include "symlink.h"
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>
@@ -4148,8 +4149,9 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
 	int ret;
 	struct inode *inode = d_inode(old_dentry);
 	struct buffer_head *new_bh = NULL;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
-	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
+	if (oi->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
 		ret = -EINVAL;
 		mlog_errno(ret);
 		goto out;
@@ -4175,14 +4177,34 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
 		goto out_unlock;
 	}
 
+	if ((oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) &&
+	    (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) {
+		/*
+		 * Adjust extent record count to reserve space for extended attribute.
+		 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
+		 */
+		struct ocfs2_inode_info *new_oi = OCFS2_I(new_inode);
+
+		if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
+		    !(ocfs2_inode_is_fast_symlink(new_inode))) {
+			struct ocfs2_dinode *new_di = (struct ocfs2_dinode *)new_bh->b_data;
+			struct ocfs2_dinode *old_di = (struct ocfs2_dinode *)old_bh->b_data;
+			struct ocfs2_extent_list *el = &new_di->id2.i_list;
+			int inline_size = le16_to_cpu(old_di->i_xattr_inline_size);
+
+			le16_add_cpu(&el->l_count, -(inline_size /
+					sizeof(struct ocfs2_extent_rec)));
+		}
+	}
+
 	ret = ocfs2_create_reflink_node(inode, old_bh,
 					new_inode, new_bh, preserve);
 	if (ret) {
 		mlog_errno(ret);
 		goto inode_unlock;
 	}
 
-	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_XATTR_FL) {
+	if (oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) {
 		ret = ocfs2_reflink_xattrs(inode, old_bh,
 					   new_inode, new_bh,
 					   preserve);
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
@@ -6511,16 +6511,7 @@ static int ocfs2_reflink_xattr_inline(struct ocfs2_xattr_reflink *args)
 	}
 
 	new_oi = OCFS2_I(args->new_inode);
-	/*
-	 * Adjust extent record count to reserve space for extended attribute.
-	 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
-	 */
-	if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
-	    !(ocfs2_inode_is_fast_symlink(args->new_inode))) {
-		struct ocfs2_extent_list *el = &new_di->id2.i_list;
-		le16_add_cpu(&el->l_count, -(inline_size /
-					sizeof(struct ocfs2_extent_rec)));
-	}
+
 	spin_lock(&new_oi->ip_lock);
 	new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL;
 	new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features);
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
@@ -133,7 +133,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #define annotate_unreachable() __annotate_unreachable(__COUNTER__)
 
 /* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(".rodata..c_jump_table")
+#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #")
 
 #else /* !CONFIG_OBJTOOL */
 #define annotate_reachable()
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
@@ -692,6 +692,9 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 				nodemask_t *nmask, gfp_t gfp_mask,
 				bool allow_alloc_fallback);
+struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
+					  nodemask_t *nmask, gfp_t gfp_mask);
+
 int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,
 			pgoff_t idx);
 void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
@@ -1059,6 +1062,13 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	return NULL;
 }
 
+static inline struct folio *
+alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
+			    nodemask_t *nmask, gfp_t gfp_mask)
+{
+	return NULL;
+}
+
 static inline struct folio *
 alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 			nodemask_t *nmask, gfp_t gfp_mask,
diff --git a/lib/list-test.c b/lib/list-test.c
@@ -408,13 +408,10 @@ static void list_test_list_cut_position(struct kunit *test)
 
 	KUNIT_EXPECT_EQ(test, i, 2);
 
-	i = 0;
 	list_for_each(cur, &list1) {
 		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
 		i++;
 	}
-
-	KUNIT_EXPECT_EQ(test, i, 1);
 }
 
 static void list_test_list_cut_before(struct kunit *test)
@@ -439,13 +436,10 @@ static void list_test_list_cut_before(struct kunit *test)
 
 	KUNIT_EXPECT_EQ(test, i, 1);
 
-	i = 0;
 	list_for_each(cur, &list1) {
 		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
 		i++;
 	}
-
-	KUNIT_EXPECT_EQ(test, i, 2);
 }
 
 static void list_test_list_splice(struct kunit *test)
diff --git a/mm/Kconfig b/mm/Kconfig
@@ -595,6 +595,7 @@ config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 config SPLIT_PTE_PTLOCKS
 	def_bool y
 	depends on MMU
+	depends on SMP
 	depends on NR_CPUS >= 4
 	depends on !ARM || CPU_CACHE_VIPT
 	depends on !PARISC || PA20
diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
@@ -9,7 +9,7 @@ config DAMON
 	  access frequency of each memory region. The information can be useful
 	  for performance-centric DRAM level memory management.
 
-	  See https://damonitor.github.io/doc/html/latest-damon/index.html for
+	  See https://www.kernel.org/doc/html/latest/mm/damon/index.html for
 	  more information.
 
 config DAMON_KUNIT_TEST
diff --git a/mm/filemap.c b/mm/filemap.c
@@ -2196,6 +2196,10 @@ unsigned filemap_get_folios_contig(struct address_space *mapping,
 		if (xa_is_value(folio))
 			goto update_start;
 
+		/* If we landed in the middle of a THP, continue at its end. */
+		if (xa_is_sibling(folio))
+			goto update_start;
+
 		if (!folio_try_get(folio))
 			goto retry;
 
diff --git a/mm/gup.c b/mm/gup.c
@@ -3700,6 +3700,7 @@ long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end,
 					ret = PTR_ERR(folio);
 					if (ret != -EEXIST)
 						goto err;
+					folio = NULL;
 				}
 			}
 		}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
@@ -2390,6 +2390,23 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h,
 	return folio;
 }
 
+struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
+		nodemask_t *nmask, gfp_t gfp_mask)
+{
+	struct folio *folio;
+
+	spin_lock_irq(&hugetlb_lock);
+	folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid,
+					       nmask);
+	if (folio) {
+		VM_BUG_ON(!h->resv_huge_pages);
+		h->resv_huge_pages--;
+	}
+
+	spin_unlock_irq(&hugetlb_lock);
+	return folio;
+}
+
 /* folio migration callback function */
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 		nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback)
diff --git a/mm/kfence/report.c b/mm/kfence/report.c
@@ -109,7 +109,7 @@ static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadat
 	const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track;
 	u64 ts_sec = track->ts_nsec;
 	unsigned long rem_nsec = do_div(ts_sec, NSEC_PER_SEC);
-	u64 interval_nsec = local_clock() - meta->alloc_track.ts_nsec;
+	u64 interval_nsec = local_clock() - track->ts_nsec;
 	unsigned long rem_interval_nsec = do_div(interval_nsec, NSEC_PER_SEC);
 
 	/* Timestamp matches printk timestamp format. */
diff --git a/mm/memfd.c b/mm/memfd.c
@@ -79,23 +79,25 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 		 * alloc from. Also, the folio will be pinned for an indefinite
 		 * amount of time, so it is not expected to be migrated away.
 		 */
-		gfp_mask = htlb_alloc_mask(hstate_file(memfd));
+		struct hstate *h = hstate_file(memfd);
+
+		gfp_mask = htlb_alloc_mask(h);
 		gfp_mask &= ~(__GFP_HIGHMEM | __GFP_MOVABLE);
+		idx >>= huge_page_order(h);
 
-		folio = alloc_hugetlb_folio_nodemask(hstate_file(memfd),
-						     numa_node_id(),
-						     NULL,
-						     gfp_mask,
-						     false);
-		if (folio && folio_try_get(folio)) {
+		folio = alloc_hugetlb_folio_reserve(h,
+						    numa_node_id(),
+						    NULL,
+						    gfp_mask);
+		if (folio) {
 			err = hugetlb_add_to_page_cache(folio,
 							memfd->f_mapping,
 							idx);
 			if (err) {
 				folio_put(folio);
-				free_huge_folio(folio);
 				return ERR_PTR(err);
 			}
+			folio_unlock(folio);
 			return folio;
 		}
 		return ERR_PTR(-ENOMEM);
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
@@ -768,10 +768,10 @@ int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 		pr_info(
 "memory-tiers: the performance of DRAM node %d mismatches that of the reference\n"
 "DRAM node %d.\n", nid, default_dram_perf_ref_nid);
-		pr_info("  performance of reference DRAM node %d:\n",
-			default_dram_perf_ref_nid);
+		pr_info("  performance of reference DRAM node %d from %s:\n",
+			default_dram_perf_ref_nid, default_dram_perf_ref_source);
 		dump_hmem_attrs(&default_dram_perf, "    ");
-		pr_info("  performance of DRAM node %d:\n", nid);
+		pr_info("  performance of DRAM node %d from %s:\n", nid, source);
 		dump_hmem_attrs(perf, "    ");
 		pr_info(
 "  disable default DRAM node performance based abstract distance algorithm.\n");
diff --git a/mm/migrate.c b/mm/migrate.c
@@ -1196,7 +1196,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
 	int rc = -EAGAIN;
 	int old_page_state = 0;
 	struct anon_vma *anon_vma = NULL;
-	bool is_lru = !__folio_test_movable(src);
+	bool is_lru = data_race(!__folio_test_movable(src));
 	bool locked = false;
 	bool dst_locked = false;
 
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -15,7 +15,7 @@
 #include <sys/ioctl.h>
 #include <sys/stat.h>
 #include <math.h>
-#include <asm-generic/unistd.h>
+#include <asm/unistd.h>
 #include <pthread.h>
 #include <sys/resource.h>
 #include <assert.h>
diff --git a/tools/testing/shared/maple-shared.h b/tools/testing/shared/maple-shared.h
@@ -1,4 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef __MAPLE_SHARED_H__
+#define __MAPLE_SHARED_H__
 
 #define CONFIG_DEBUG_MAPLE_TREE
 #define CONFIG_MAPLE_SEARCH
@@ -7,3 +9,5 @@
 #include <stdlib.h>
 #include <time.h>
 #include "linux/init.h"
+
+#endif /* __MAPLE_SHARED_H__ */
diff --git a/tools/testing/shared/shared.h b/tools/testing/shared/shared.h
@@ -1,4 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __SHARED_H__
+#define __SHARED_H__
 
 #include <linux/types.h>
 #include <linux/bug.h>
@@ -31,3 +33,5 @@
 #ifndef dump_stack
 #define dump_stack()	assert(0)
 #endif
+
+#endif /* __SHARED_H__ */
diff --git a/tools/testing/shared/shared.mk b/tools/testing/shared/shared.mk
@@ -15,7 +15,9 @@ SHARED_DEPS = Makefile ../shared/shared.mk ../shared/*.h generated/map-shift.h \
 	../../../include/linux/maple_tree.h \
 	../../../include/linux/radix-tree.h \
 	../../../lib/radix-tree.h \
-	../../../include/linux/idr.h
+	../../../include/linux/idr.h \
+	../../../lib/maple_tree.c \
+	../../../lib/test_maple_tree.c
 
 ifndef SHIFT
 	SHIFT=3
diff --git a/tools/testing/shared/xarray-shared.h b/tools/testing/shared/xarray-shared.h
@@ -1,4 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef __XARRAY_SHARED_H__
+#define __XARRAY_SHARED_H__
 
 #define XA_DEBUG
 #include "shared.h"
+
+#endif /* __XARRAY_SHARED_H__ */

Original file line number	Diff line number	Diff line change
`@@ -2115,8 +2115,10 @@ static void zram_destroy_comps(struct zram *zram)`
`2115`	`2115`	`zram->num_active_comps--;`
`2116`	`2116`	`}`
`2117`	`2117`
`2118`		`- for (prio = ZRAM_SECONDARY_COMP; prio < ZRAM_MAX_COMPS; prio++) {`
`2119`		`- kfree(zram->comp_algs[prio]);`
	`2118`	`+ for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) {`
	`2119`	`+ /* Do not free statically defined compression algorithms */`
	`2120`	`+ if (zram->comp_algs[prio] != default_compressor)`
	`2121`	`+ kfree(zram->comp_algs[prio]);`
`2120`	`2122`	`zram->comp_algs[prio] = NULL;`
`2121`	`2123`	`}`
`2122`	`2124`
Original file line number	Diff line number	Diff line change
`@@ -408,13 +408,10 @@ static void list_test_list_cut_position(struct kunit *test)`
`408`	`408`
`409`	`409`	`KUNIT_EXPECT_EQ(test, i, 2);`
`410`	`410`
`411`		`- i = 0;`
`412`	`411`	`list_for_each(cur, &list1) {`
`413`	`412`	`KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);`
`414`	`413`	`i++;`
`415`	`414`	`}`
`416`		`-`
`417`		`- KUNIT_EXPECT_EQ(test, i, 1);`
`418`	`415`	`}`
`419`	`416`
`420`	`417`	`static void list_test_list_cut_before(struct kunit *test)`
`@@ -439,13 +436,10 @@ static void list_test_list_cut_before(struct kunit *test)`
`439`	`436`
`440`	`437`	`KUNIT_EXPECT_EQ(test, i, 1);`
`441`	`438`
`442`		`- i = 0;`
`443`	`439`	`list_for_each(cur, &list1) {`
`444`	`440`	`KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);`
`445`	`441`	`i++;`
`446`	`442`	`}`
`447`		`-`
`448`		`- KUNIT_EXPECT_EQ(test, i, 2);`
`449`	`443`	`}`
`450`	`444`
`451`	`445`	`static void list_test_list_splice(struct kunit *test)`