Merge tag 'mm-hotfixes-stable-2024-03-27-11-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

torvalds · torvalds · commit dc189b8e6adb · 2024-03-27T13:30:48.000-07:00
Pull misc fixes from Andrew Morton:
 "Various hotfixes. About half are cc:stable and the remainder address
  post-6.8 issues or aren't considered suitable for backporting.

  zswap figures prominently in the post-6.8 issues - folloup against the
  large amount of changes we have just made to that code.

  Apart from that, all over the map"

* tag 'mm-hotfixes-stable-2024-03-27-11-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (21 commits)
  crash: use macro to add crashk_res into iomem early for specific arch
  mm: zswap: fix data loss on SWP_SYNCHRONOUS_IO devices
  selftests/mm: fix ARM related issue with fork after pthread_create
  hexagon: vmlinux.lds.S: handle attributes section
  userfaultfd: fix deadlock warning when locking src and dst VMAs
  tmpfs: fix race on handling dquot rbtree
  selftests/mm: sigbus-wp test requires UFFD_FEATURE_WP_HUGETLBFS_SHMEM
  mm: zswap: fix writeback shinker GFP_NOIO/GFP_NOFS recursion
  ARM: prctl: reject PR_SET_MDWE on pre-ARMv6
  prctl: generalize PR_SET_MDWE support check to be per-arch
  MAINTAINERS: remove incorrect M: tag for dm-devel@lists.linux.dev
  mm: zswap: fix kernel BUG in sg_init_one
  selftests: mm: restore settings from only parent process
  tools/Makefile: remove cgroup target
  mm: cachestat: fix two shmem bugs
  mm: increase folio batch size
  mm,page_owner: fix recursion
  mailmap: update entry for Leonard Crestez
  init: open /initrd.image with O_LARGEFILE
  selftests/mm: Fix build with _FORTIFY_SOURCE
  ...
diff --git a/.mailmap b/.mailmap
@@ -340,7 +340,8 @@ Lee Jones <lee@kernel.org> <joneslee@google.com>
 Lee Jones <lee@kernel.org> <lee.jones@canonical.com>
 Lee Jones <lee@kernel.org> <lee.jones@linaro.org>
 Lee Jones <lee@kernel.org> <lee@ubuntu.com>
-Leonard Crestez <leonard.crestez@nxp.com> Leonard Crestez <cdleonard@gmail.com>
+Leonard Crestez <cdleonard@gmail.com> <leonard.crestez@nxp.com>
+Leonard Crestez <cdleonard@gmail.com> <leonard.crestez@intel.com>
 Leonardo Bras <leobras.c@gmail.com> <leonardo@linux.ibm.com>
 Leonard Göhrs <l.goehrs@pengutronix.de>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
diff --git a/MAINTAINERS b/MAINTAINERS
@@ -6173,7 +6173,6 @@ F:	include/uapi/linux/dm-*.h
 
 DEVICE-MAPPER VDO TARGET
 M:	Matthew Sakai <msakai@redhat.com>
-M:	dm-devel@lists.linux.dev
 L:	dm-devel@lists.linux.dev
 S:	Maintained
 F:	Documentation/admin-guide/device-mapper/vdo*.rst
diff --git a/arch/arm/include/asm/mman.h b/arch/arm/include/asm/mman.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#include <asm/system_info.h>
+#include <uapi/asm/mman.h>
+
+static inline bool arch_memory_deny_write_exec_supported(void)
+{
+	return cpu_architecture() >= CPU_ARCH_ARMv6;
+}
+#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
+
+#endif /* __ASM_MMAN_H__ */
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
@@ -63,6 +63,7 @@ SECTIONS
 	STABS_DEBUG
 	DWARF_DEBUG
 	ELF_DETAILS
+	.hexagon.attributes 0 : { *(.hexagon.attributes) }
 
 	DISCARDS
 }
diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#include <uapi/asm/mman.h>
+
+/* PARISC cannot allow mdwe as it needs writable stacks */
+static inline bool arch_memory_deny_write_exec_supported(void)
+{
+	return false;
+}
+#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
+
+#endif /* __ASM_MMAN_H__ */
diff --git a/arch/x86/include/asm/crash_reserve.h b/arch/x86/include/asm/crash_reserve.h
@@ -39,4 +39,6 @@ static inline unsigned long crash_low_size_default(void)
 #endif
 }
 
+#define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
+
 #endif /* _X86_CRASH_RESERVE_H */
diff --git a/include/linux/mman.h b/include/linux/mman.h
@@ -162,6 +162,14 @@ calc_vm_flag_bits(unsigned long flags)
 
 unsigned long vm_commit_limit(void);
 
+#ifndef arch_memory_deny_write_exec_supported
+static inline bool arch_memory_deny_write_exec_supported(void)
+{
+	return true;
+}
+#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
+#endif
+
 /*
  * Denies creating a writable executable mapping or gaining executable permissions.
  *
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
@@ -11,8 +11,8 @@
 
 #include <linux/types.h>
 
-/* 15 pointers + header align the folio_batch structure to a power of two */
-#define PAGEVEC_SIZE	15
+/* 31 pointers + header align the folio_batch structure to a power of two */
+#define PAGEVEC_SIZE	31
 
 struct folio;
 
diff --git a/init/initramfs.c b/init/initramfs.c
@@ -682,7 +682,7 @@ static void __init populate_initrd_image(char *err)
 
 	printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n",
 			err);
-	file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700);
+	file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700);
 	if (IS_ERR(file))
 		return;
 
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
@@ -366,7 +366,9 @@ static int __init reserve_crashkernel_low(unsigned long long low_size)
 
 	crashk_low_res.start = low_base;
 	crashk_low_res.end   = low_base + low_size - 1;
+#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 	insert_resource(&iomem_resource, &crashk_low_res);
+#endif
 #endif
 	return 0;
 }
@@ -448,8 +450,12 @@ void __init reserve_crashkernel_generic(char *cmdline,
 
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
+#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
+	insert_resource(&iomem_resource, &crashk_res);
+#endif
 }
 
+#ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 static __init int insert_crashkernel_resources(void)
 {
 	if (crashk_res.start < crashk_res.end)
@@ -462,3 +468,4 @@ static __init int insert_crashkernel_resources(void)
 }
 early_initcall(insert_crashkernel_resources);
 #endif
+#endif
diff --git a/kernel/sys.c b/kernel/sys.c
@@ -2408,8 +2408,11 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
 	if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN))
 		return -EINVAL;
 
-	/* PARISC cannot allow mdwe as it needs writable stacks */
-	if (IS_ENABLED(CONFIG_PARISC))
+	/*
+	 * EOPNOTSUPP might be more appropriate here in principle, but
+	 * existing userspace depends on EINVAL specifically.
+	 */
+	if (!arch_memory_deny_write_exec_supported())
 		return -EINVAL;
 
 	current_bits = get_current_mdwe();
diff --git a/mm/filemap.c b/mm/filemap.c
@@ -4197,7 +4197,23 @@ static void filemap_cachestat(struct address_space *mapping,
 				/* shmem file - in swap cache */
 				swp_entry_t swp = radix_to_swp_entry(folio);
 
+				/* swapin error results in poisoned entry */
+				if (non_swap_entry(swp))
+					goto resched;
+
+				/*
+				 * Getting a swap entry from the shmem
+				 * inode means we beat
+				 * shmem_unuse(). rcu_read_lock()
+				 * ensures swapoff waits for us before
+				 * freeing the swapper space. However,
+				 * we can race with swapping and
+				 * invalidation, so there might not be
+				 * a shadow in the swapcache (yet).
+				 */
 				shadow = get_shadow_from_swap_cache(swp);
+				if (!shadow)
+					goto resched;
 			}
 #endif
 			if (workingset_test_recent(shadow, true, &workingset))
diff --git a/mm/memory.c b/mm/memory.c
@@ -1536,7 +1536,9 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
 		ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm);
 		arch_check_zapped_pte(vma, ptent);
 		tlb_remove_tlb_entry(tlb, pte, addr);
-		VM_WARN_ON_ONCE(userfaultfd_wp(vma));
+		if (userfaultfd_pte_wp(vma, ptent))
+			zap_install_uffd_wp_if_needed(vma, addr, pte, 1,
+						      details, ptent);
 		ksm_might_unmap_zero_page(mm, ptent);
 		return 1;
 	}
diff --git a/mm/page_owner.c b/mm/page_owner.c
@@ -54,6 +54,22 @@ static depot_stack_handle_t early_handle;
 
 static void init_early_allocated_pages(void);
 
+static inline void set_current_in_page_owner(void)
+{
+	/*
+	 * Avoid recursion.
+	 *
+	 * We might need to allocate more memory from page_owner code, so make
+	 * sure to signal it in order to avoid recursion.
+	 */
+	current->in_page_owner = 1;
+}
+
+static inline void unset_current_in_page_owner(void)
+{
+	current->in_page_owner = 0;
+}
+
 static int __init early_page_owner_param(char *buf)
 {
 	int ret = kstrtobool(buf, &page_owner_enabled);
@@ -133,23 +149,16 @@ static noinline depot_stack_handle_t save_stack(gfp_t flags)
 	depot_stack_handle_t handle;
 	unsigned int nr_entries;
 
-	/*
-	 * Avoid recursion.
-	 *
-	 * Sometimes page metadata allocation tracking requires more
-	 * memory to be allocated:
-	 * - when new stack trace is saved to stack depot
-	 */
 	if (current->in_page_owner)
 		return dummy_handle;
-	current->in_page_owner = 1;
 
+	set_current_in_page_owner();
 	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
 	handle = stack_depot_save(entries, nr_entries, flags);
 	if (!handle)
 		handle = failure_handle;
+	unset_current_in_page_owner();
 
-	current->in_page_owner = 0;
 	return handle;
 }
 
@@ -164,9 +173,13 @@ static void add_stack_record_to_list(struct stack_record *stack_record,
 	gfp_mask &= (GFP_ATOMIC | GFP_KERNEL);
 	gfp_mask |= __GFP_NOWARN;
 
+	set_current_in_page_owner();
 	stack = kmalloc(sizeof(*stack), gfp_mask);
-	if (!stack)
+	if (!stack) {
+		unset_current_in_page_owner();
 		return;
+	}
+	unset_current_in_page_owner();
 
 	stack->stack_record = stack_record;
 	stack->next = NULL;
diff --git a/mm/shmem_quota.c b/mm/shmem_quota.c
@@ -116,7 +116,7 @@ static int shmem_free_file_info(struct super_block *sb, int type)
 static int shmem_get_next_id(struct super_block *sb, struct kqid *qid)
 {
 	struct mem_dqinfo *info = sb_dqinfo(sb, qid->type);
-	struct rb_node *node = ((struct rb_root *)info->dqi_priv)->rb_node;
+	struct rb_node *node;
 	qid_t id = from_kqid(&init_user_ns, *qid);
 	struct quota_info *dqopt = sb_dqopt(sb);
 	struct quota_id *entry = NULL;
@@ -126,6 +126,7 @@ static int shmem_get_next_id(struct super_block *sb, struct kqid *qid)
 		return -ESRCH;
 
 	down_read(&dqopt->dqio_sem);
+	node = ((struct rb_root *)info->dqi_priv)->rb_node;
 	while (node) {
 		entry = rb_entry(node, struct quota_id, node);
 
@@ -165,7 +166,7 @@ static int shmem_get_next_id(struct super_block *sb, struct kqid *qid)
 static int shmem_acquire_dquot(struct dquot *dquot)
 {
 	struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type);
-	struct rb_node **n = &((struct rb_root *)info->dqi_priv)->rb_node;
+	struct rb_node **n;
 	struct shmem_sb_info *sbinfo = dquot->dq_sb->s_fs_info;
 	struct rb_node *parent = NULL, *new_node = NULL;
 	struct quota_id *new_entry, *entry;
@@ -176,6 +177,8 @@ static int shmem_acquire_dquot(struct dquot *dquot)
 	mutex_lock(&dquot->dq_lock);
 
 	down_write(&dqopt->dqio_sem);
+	n = &((struct rb_root *)info->dqi_priv)->rb_node;
+
 	while (*n) {
 		parent = *n;
 		entry = rb_entry(parent, struct quota_id, node);
@@ -264,7 +267,7 @@ static bool shmem_is_empty_dquot(struct dquot *dquot)
 static int shmem_release_dquot(struct dquot *dquot)
 {
 	struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type);
-	struct rb_node *node = ((struct rb_root *)info->dqi_priv)->rb_node;
+	struct rb_node *node;
 	qid_t id = from_kqid(&init_user_ns, dquot->dq_id);
 	struct quota_info *dqopt = sb_dqopt(dquot->dq_sb);
 	struct quota_id *entry = NULL;
@@ -275,6 +278,7 @@ static int shmem_release_dquot(struct dquot *dquot)
 		goto out_dqlock;
 
 	down_write(&dqopt->dqio_sem);
+	node = ((struct rb_root *)info->dqi_priv)->rb_node;
 	while (node) {
 		entry = rb_entry(node, struct quota_id, node);
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
@@ -1444,7 +1444,8 @@ static int uffd_move_lock(struct mm_struct *mm,
 		 */
 		down_read(&(*dst_vmap)->vm_lock->lock);
 		if (*dst_vmap != *src_vmap)
-			down_read(&(*src_vmap)->vm_lock->lock);
+			down_read_nested(&(*src_vmap)->vm_lock->lock,
+					 SINGLE_DEPTH_NESTING);
 	}
 	mmap_read_unlock(mm);
 	return err;
diff --git a/mm/zswap.c b/mm/zswap.c
@@ -1080,7 +1080,17 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page)
 	mutex_lock(&acomp_ctx->mutex);
 
 	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
-	if (acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) {
+	/*
+	 * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer
+	 * to do crypto_acomp_decompress() which might sleep. In such cases, we must
+	 * resort to copying the buffer to a temporary one.
+	 * Meanwhile, zpool_map_handle() might return a non-linearly mapped buffer,
+	 * such as a kmap address of high memory or even ever a vmap address.
+	 * However, sg_init_one is only equipped to handle linearly mapped low memory.
+	 * In such cases, we also must copy the buffer to a temporary and lowmem one.
+	 */
+	if ((acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) ||
+	    !virt_addr_valid(src)) {
 		memcpy(acomp_ctx->buffer, src, entry->length);
 		src = acomp_ctx->buffer;
 		zpool_unmap_handle(zpool, entry->handle);
@@ -1094,7 +1104,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page)
 	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
 	mutex_unlock(&acomp_ctx->mutex);
 
-	if (!acomp_ctx->is_sleepable || zpool_can_sleep_mapped(zpool))
+	if (src != acomp_ctx->buffer)
 		zpool_unmap_handle(zpool, entry->handle);
 }
 
@@ -1313,6 +1323,14 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
 	if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg))
 		return 0;
 
+	/*
+	 * The shrinker resumes swap writeback, which will enter block
+	 * and may enter fs. XXX: Harmonize with vmscan.c __GFP_FS
+	 * rules (may_enter_fs()), which apply on a per-folio basis.
+	 */
+	if (!gfp_has_io_fs(sc->gfp_mask))
+		return 0;
+
 #ifdef CONFIG_MEMCG_KMEM
 	mem_cgroup_flush_stats(memcg);
 	nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
@@ -1618,6 +1636,7 @@ bool zswap_load(struct folio *folio)
 	swp_entry_t swp = folio->swap;
 	pgoff_t offset = swp_offset(swp);
 	struct page *page = &folio->page;
+	bool swapcache = folio_test_swapcache(folio);
 	struct zswap_tree *tree = swap_zswap_tree(swp);
 	struct zswap_entry *entry;
 	u8 *dst;
@@ -1630,7 +1649,20 @@ bool zswap_load(struct folio *folio)
 		spin_unlock(&tree->lock);
 		return false;
 	}
-	zswap_rb_erase(&tree->rbroot, entry);
+	/*
+	 * When reading into the swapcache, invalidate our entry. The
+	 * swapcache can be the authoritative owner of the page and
+	 * its mappings, and the pressure that results from having two
+	 * in-memory copies outweighs any benefits of caching the
+	 * compression work.
+	 *
+	 * (Most swapins go through the swapcache. The notable
+	 * exception is the singleton fault on SWP_SYNCHRONOUS_IO
+	 * files, which reads into a private page and may free it if
+	 * the fault fails. We remain the primary owner of the entry.)
+	 */
+	if (swapcache)
+		zswap_rb_erase(&tree->rbroot, entry);
 	spin_unlock(&tree->lock);
 
 	if (entry->length)
@@ -1645,9 +1677,10 @@ bool zswap_load(struct folio *folio)
 	if (entry->objcg)
 		count_objcg_event(entry->objcg, ZSWPIN);
 
-	zswap_entry_free(entry);
-
-	folio_mark_dirty(folio);
+	if (swapcache) {
+		zswap_entry_free(entry);
+		folio_mark_dirty(folio);
+	}
 
 	return true;
 }
diff --git a/tools/Makefile b/tools/Makefile
diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c

Original file line number	Diff line number	Diff line change
`@@ -63,6 +63,7 @@ SECTIONS`
`63`	`63`	`STABS_DEBUG`
`64`	`64`	`DWARF_DEBUG`
`65`	`65`	`ELF_DETAILS`
	`66`	`+ .hexagon.attributes 0 : { *(.hexagon.attributes) }`
`66`	`67`
`67`	`68`	`DISCARDS`
`68`	`69`	`}`
Original file line number	Diff line number	Diff line change
`@@ -39,4 +39,6 @@ static inline unsigned long crash_low_size_default(void)`
`39`	`39`	`#endif`
`40`	`40`	`}`
`41`	`41`
	`42`	`+#define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY`
	`43`	`+`
`42`	`44`	`#endif /* _X86_CRASH_RESERVE_H */`
Original file line number	Diff line number	Diff line change
`@@ -366,7 +366,9 @@ static int __init reserve_crashkernel_low(unsigned long long low_size)`
`366`	`366`
`367`	`367`	`crashk_low_res.start = low_base;`
`368`	`368`	`crashk_low_res.end = low_base + low_size - 1;`
	`369`	`+#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY`
`369`	`370`	`insert_resource(&iomem_resource, &crashk_low_res);`
	`371`	`+#endif`
`370`	`372`	`#endif`
`371`	`373`	`return 0;`
`372`	`374`	`}`
`@@ -448,8 +450,12 @@ void __init reserve_crashkernel_generic(char *cmdline,`
`448`	`450`
`449`	`451`	`crashk_res.start = crash_base;`
`450`	`452`	`crashk_res.end = crash_base + crash_size - 1;`
	`453`	`+#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY`
	`454`	`+ insert_resource(&iomem_resource, &crashk_res);`
	`455`	`+#endif`
`451`	`456`	`}`
`452`	`457`
	`458`	`+#ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY`
`453`	`459`	`static __init int insert_crashkernel_resources(void)`
`454`	`460`	`{`
`455`	`461`	`if (crashk_res.start < crashk_res.end)`
`@@ -462,3 +468,4 @@ static __init int insert_crashkernel_resources(void)`
`462`	`468`	`}`
`463`	`469`	`early_initcall(insert_crashkernel_resources);`
`464`	`470`	`#endif`
	`471`	`+#endif`