19 hotfixes. 14 are cc:stable and the remainder address issues which were

introduced during this -rc cycle or which were considered inappropriate
 for a backport.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZIdw7QAKCRDdBJ7gKXxA
 jki4AQCygi1UoqVPq4N/NzJbv2GaNDXNmcJIoLvPpp3MYFhucAEAtQNzAYO9z6CT
 iLDMosnuh+1KLTaKNGL5iak3NAxnxQw=
 =mTdI
 -----END PGP SIGNATURE-----

Merge tag 'mm-hotfixes-stable-2023-06-12-12-22' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "19 hotfixes. 14 are cc:stable and the remainder address issues which
  were introduced during this development cycle or which were considered
  inappropriate for a backport"

* tag 'mm-hotfixes-stable-2023-06-12-12-22' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  zswap: do not shrink if cgroup may not zswap
  page cache: fix page_cache_next/prev_miss off by one
  ocfs2: check new file size on fallocate call
  mailmap: add entry for John Keeping
  mm/damon/core: fix divide error in damon_nr_accesses_to_accesses_bp()
  epoll: ep_autoremove_wake_function should use list_del_init_careful
  mm/gup_test: fix ioctl fail for compat task
  nilfs2: reject devices with insufficient block count
  ocfs2: fix use-after-free when unmounting read-only filesystem
  lib/test_vmalloc.c: avoid garbage in page array
  nilfs2: fix possible out-of-bounds segment allocation in resize ioctl
  riscv/purgatory: remove PGO flags
  powerpc/purgatory: remove PGO flags
  x86/purgatory: remove PGO flags
  kexec: support purgatories with .text.hot sections
  mm/uffd: allow vma to merge as much as possible
  mm/uffd: fix vma operation where start addr cuts part of vma
  radix-tree: move declarations to header
  nilfs2: fix incomplete buffer cleanup in nilfs_btnode_abort_change_key()

.mailmap

@@ -233,6 +233,7 @@ Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com>
 Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
 Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
 John Crispin <john@phrozen.org> <blogic@openwrt.org>
+John Keeping <john@keeping.me.uk> <john@metanate.com>
 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
 John Stultz <johnstul@us.ibm.com>
 <jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com>

arch/powerpc/purgatory/Makefile

@@ -5,6 +5,11 @@ KCSAN_SANITIZE := n
 
 targets += trampoline_$(BITS).o purgatory.ro
 
+# When profile-guided optimization is enabled, llvm emits two different
+# overlapping text sections, which is not supported by kexec. Remove profile
+# optimization flags.
+KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
+
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined
 
 $(obj)/purgatory.ro: $(obj)/trampoline_$(BITS).o FORCE

arch/riscv/purgatory/Makefile

@@ -35,6 +35,11 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS
 CFLAGS_string.o := -D__DISABLE_EXPORTS
 CFLAGS_ctype.o := -D__DISABLE_EXPORTS
 
+# When profile-guided optimization is enabled, llvm emits two different
+# overlapping text sections, which is not supported by kexec. Remove profile
+# optimization flags.
+KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
+
 # When linking purgatory.ro with -r unresolved symbols are not checked,
 # also link a purgatory.chk binary without -r to check for unresolved symbols.
 PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib

arch/x86/purgatory/Makefile

@@ -14,6 +14,11 @@ $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
 
 CFLAGS_sha256.o := -D__DISABLE_EXPORTS
 
+# When profile-guided optimization is enabled, llvm emits two different
+# overlapping text sections, which is not supported by kexec. Remove profile
+# optimization flags.
+KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
+
 # When linking purgatory.ro with -r unresolved symbols are not checked,
 # also link a purgatory.chk binary without -r to check for unresolved symbols.
 PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib

fs/eventpoll.c

@@ -1805,7 +1805,11 @@ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry,
 {
 	int ret = default_wake_function(wq_entry, mode, sync, key);
 
-	list_del_init(&wq_entry->entry);
+	/*
+	 * Pairs with list_empty_careful in ep_poll, and ensures future loop
+	 * iterations see the cause of this wakeup.
+	 */
+	list_del_init_careful(&wq_entry->entry);
 	return ret;
 }
 

fs/nilfs2/btnode.c

@@ -285,6 +285,14 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc,
 	if (nbh == NULL) {	/* blocksize == pagesize */
 		xa_erase_irq(&btnc->i_pages, newkey);
 		unlock_page(ctxt->bh->b_page);
-	} else
-		brelse(nbh);
+	} else {
+		/*
+		 * When canceling a buffer that a prepare operation has
+		 * allocated to copy a node block to another location, use
+		 * nilfs_btnode_delete() to initialize and release the buffer
+		 * so that the buffer flags will not be in an inconsistent
+		 * state when it is reallocated.
+		 */
+		nilfs_btnode_delete(nbh);
+	}
 }

fs/nilfs2/sufile.c

@@ -779,6 +779,15 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
 			goto out_header;
 
 		sui->ncleansegs -= nsegs - newnsegs;
+
+		/*
+		 * If the sufile is successfully truncated, immediately adjust
+		 * the segment allocation space while locking the semaphore
+		 * "mi_sem" so that nilfs_sufile_alloc() never allocates
+		 * segments in the truncated space.
+		 */
+		sui->allocmax = newnsegs - 1;
+		sui->allocmin = 0;
 	}
 
 	kaddr = kmap_atomic(header_bh->b_page);

fs/nilfs2/the_nilfs.c

@@ -405,6 +405,18 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs)
 				  100));
 }
 
+/**
+ * nilfs_max_segment_count - calculate the maximum number of segments
+ * @nilfs: nilfs object
+ */
+static u64 nilfs_max_segment_count(struct the_nilfs *nilfs)
+{
+	u64 max_count = U64_MAX;
+
+	do_div(max_count, nilfs->ns_blocks_per_segment);
+	return min_t(u64, max_count, ULONG_MAX);
+}
+
 void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs)
 {
 	nilfs->ns_nsegments = nsegs;
@@ -414,6 +426,8 @@ void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs)
 static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 				   struct nilfs_super_block *sbp)
 {
+	u64 nsegments, nblocks;
+
 	if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) {
 		nilfs_err(nilfs->ns_sb,
 			  "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).",
@@ -457,7 +471,34 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 		return -EINVAL;
 	}
 
-	nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments));
+	nsegments = le64_to_cpu(sbp->s_nsegments);
+	if (nsegments > nilfs_max_segment_count(nilfs)) {
+		nilfs_err(nilfs->ns_sb,
+			  "segment count %llu exceeds upper limit (%llu segments)",
+			  (unsigned long long)nsegments,
+			  (unsigned long long)nilfs_max_segment_count(nilfs));
+		return -EINVAL;
+	}
+
+	nblocks = sb_bdev_nr_blocks(nilfs->ns_sb);
+	if (nblocks) {
+		u64 min_block_count = nsegments * nilfs->ns_blocks_per_segment;
+		/*
+		 * To avoid failing to mount early device images without a
+		 * second superblock, exclude that block count from the
+		 * "min_block_count" calculation.
+		 */
+
+		if (nblocks < min_block_count) {
+			nilfs_err(nilfs->ns_sb,
+				  "total number of segment blocks %llu exceeds device size (%llu blocks)",
+				  (unsigned long long)min_block_count,
+				  (unsigned long long)nblocks);
+			return -EINVAL;
+		}
+	}
+
+	nilfs_set_nsegments(nilfs, nsegments);
 	nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed);
 	return 0;
 }

fs/ocfs2/file.c

@@ -2100,14 +2100,20 @@ static long ocfs2_fallocate(struct file *file, int mode, loff_t offset,
 	struct ocfs2_space_resv sr;
 	int change_size = 1;
 	int cmd = OCFS2_IOC_RESVSP64;
+	int ret = 0;
 
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return -EOPNOTSUPP;
 	if (!ocfs2_writes_unwritten_extents(osb))
 		return -EOPNOTSUPP;
 
-	if (mode & FALLOC_FL_KEEP_SIZE)
+	if (mode & FALLOC_FL_KEEP_SIZE) {
 		change_size = 0;
+	} else {
+		ret = inode_newsize_ok(inode, offset + len);
+		if (ret)
+			return ret;
+	}
 
 	if (mode & FALLOC_FL_PUNCH_HOLE)
 		cmd = OCFS2_IOC_UNRESVSP64;

fs/ocfs2/super.c

@@ -952,8 +952,10 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (!sb_has_quota_loaded(sb, type))
 			continue;
-		oinfo = sb_dqinfo(sb, type)->dqi_priv;
-		cancel_delayed_work_sync(&oinfo->dqi_sync_work);
+		if (!sb_has_quota_suspended(sb, type)) {
+			oinfo = sb_dqinfo(sb, type)->dqi_priv;
+			cancel_delayed_work_sync(&oinfo->dqi_sync_work);
+		}
 		inode = igrab(sb->s_dquot.files[type]);
 		/* Turn off quotas. This will remove all dquot structures from
 		 * memory and so they will be automatically synced to global

fs/userfaultfd.c

@@ -1332,6 +1332,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	bool basic_ioctls;
 	unsigned long start, end, vma_end;
 	struct vma_iterator vmi;
+	pgoff_t pgoff;
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
 
@@ -1459,6 +1460,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 
 	vma_iter_set(&vmi, start);
 	prev = vma_prev(&vmi);
+	if (vma->vm_start < start)
+		prev = vma;
 
 	ret = 0;
 	for_each_vma_range(vmi, vma, end) {
@@ -1482,8 +1485,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		vma_end = min(end, vma->vm_end);
 
 		new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
+		pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 		prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags,
-				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+				 vma->anon_vma, vma->vm_file, pgoff,
 				 vma_policy(vma),
 				 ((struct vm_userfaultfd_ctx){ ctx }),
 				 anon_vma_name(vma));
@@ -1563,6 +1567,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	unsigned long start, end, vma_end;
 	const void __user *buf = (void __user *)arg;
 	struct vma_iterator vmi;
+	pgoff_t pgoff;
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
@@ -1625,6 +1630,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 
 	vma_iter_set(&vmi, start);
 	prev = vma_prev(&vmi);
+	if (vma->vm_start < start)
+		prev = vma;
+
 	ret = 0;
 	for_each_vma_range(vmi, vma, end) {
 		cond_resched();
@@ -1662,8 +1670,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			uffd_wp_range(vma, start, vma_end - start, false);
 
 		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
+		pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 		prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags,
-				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+				 vma->anon_vma, vma->vm_file, pgoff,
 				 vma_policy(vma),
 				 NULL_VM_UFFD_CTX, anon_vma_name(vma));
 		if (prev) {

kernel/kexec_file.c

@@ -901,10 +901,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 		}
 
 		offset = ALIGN(offset, align);
+
+		/*
+		 * Check if the segment contains the entry point, if so,
+		 * calculate the value of image->start based on it.
+		 * If the compiler has produced more than one .text section
+		 * (Eg: .text.hot), they are generally after the main .text
+		 * section, and they shall not be used to calculate
+		 * image->start. So do not re-calculate image->start if it
+		 * is not set to the initial value, and warn the user so they
+		 * have a chance to fix their purgatory's linker script.
+		 */
 		if (sechdrs[i].sh_flags & SHF_EXECINSTR &&
 		    pi->ehdr->e_entry >= sechdrs[i].sh_addr &&
 		    pi->ehdr->e_entry < (sechdrs[i].sh_addr
-					 + sechdrs[i].sh_size)) {
+					 + sechdrs[i].sh_size) &&
+		    !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) {
 			kbuf->image->start -= sechdrs[i].sh_addr;
 			kbuf->image->start += kbuf->mem + offset;
 		}

lib/radix-tree.c

@@ -27,6 +27,8 @@
 #include <linux/string.h>
 #include <linux/xarray.h>
 
+#include "radix-tree.h"
+
 /*
  * Radix tree node cache.
  */

lib/radix-tree.h

@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* radix-tree helpers that are only shared with xarray */
+
+struct kmem_cache;
+struct rcu_head;
+
+extern struct kmem_cache *radix_tree_node_cachep;
+extern void radix_tree_node_rcu_free(struct rcu_head *head);

lib/test_vmalloc.c

@@ -369,7 +369,7 @@ vm_map_ram_test(void)
 	int i;
 
 	map_nr_pages = nr_pages > 0 ? nr_pages:1;
-	pages = kmalloc(map_nr_pages * sizeof(struct page), GFP_KERNEL);
+	pages = kcalloc(map_nr_pages, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		return -1;
 

lib/xarray.c

@@ -12,6 +12,8 @@
 #include <linux/slab.h>
 #include <linux/xarray.h>
 
+#include "radix-tree.h"
+
 /*
  * Coding conventions in this file:
  *
@@ -247,10 +249,6 @@ void *xas_load(struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_load);
 
-/* Move the radix tree node cache here */
-extern struct kmem_cache *radix_tree_node_cachep;
-extern void radix_tree_node_rcu_free(struct rcu_head *head);
-
 #define XA_RCU_FREE	((struct xarray *)1)
 
 static void xa_node_free(struct xa_node *node)

mm/damon/core.c

@@ -551,6 +551,8 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs)
 		return -EINVAL;
 	if (attrs->min_nr_regions > attrs->max_nr_regions)
 		return -EINVAL;
+	if (attrs->sample_interval > attrs->aggr_interval)
+		return -EINVAL;
 
 	damon_update_monitoring_results(ctx, attrs);
 	ctx->attrs = *attrs;

mm/filemap.c

@@ -1760,7 +1760,9 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm,
  *
  * Return: The index of the gap if found, otherwise an index outside the
  * range specified (in which case 'return - index >= max_scan' will be true).
- * In the rare case of index wrap-around, 0 will be returned.
+ * In the rare case of index wrap-around, 0 will be returned.  0 will also
+ * be returned if index == 0 and there is a gap at the index.  We can not
+ * wrap-around if passed index == 0.
  */
 pgoff_t page_cache_next_miss(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan)
@@ -1770,12 +1772,13 @@ pgoff_t page_cache_next_miss(struct address_space *mapping,
 	while (max_scan--) {
 		void *entry = xas_next(&xas);
 		if (!entry || xa_is_value(entry))
-			break;
-		if (xas.xa_index == 0)
-			break;
+			return xas.xa_index;
+		if (xas.xa_index == 0 && index != 0)
+			return xas.xa_index;
 	}
 
-	return xas.xa_index;
+	/* No gaps in range and no wrap-around, return index beyond range */
+	return xas.xa_index + 1;
 }
 EXPORT_SYMBOL(page_cache_next_miss);
 
@@ -1796,7 +1799,9 @@ EXPORT_SYMBOL(page_cache_next_miss);
  *
  * Return: The index of the gap if found, otherwise an index outside the
  * range specified (in which case 'index - return >= max_scan' will be true).
- * In the rare case of wrap-around, ULONG_MAX will be returned.
+ * In the rare case of wrap-around, ULONG_MAX will be returned.  ULONG_MAX
+ * will also be returned if index == ULONG_MAX and there is a gap at the
+ * index.  We can not wrap-around if passed index == ULONG_MAX.
  */
 pgoff_t page_cache_prev_miss(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan)
@@ -1806,12 +1811,13 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
 	while (max_scan--) {
 		void *entry = xas_prev(&xas);
 		if (!entry || xa_is_value(entry))
-			break;
-		if (xas.xa_index == ULONG_MAX)
-			break;
+			return xas.xa_index;
+		if (xas.xa_index == ULONG_MAX && index != ULONG_MAX)
+			return xas.xa_index;
 	}
 
-	return xas.xa_index;
+	/* No gaps in range and no wrap-around, return index beyond range */
+	return xas.xa_index - 1;
 }
 EXPORT_SYMBOL(page_cache_prev_miss);
 

mm/gup_test.c

@@ -381,6 +381,7 @@ static int gup_test_release(struct inode *inode, struct file *file)
 static const struct file_operations gup_test_fops = {
 	.open = nonseekable_open,
 	.unlocked_ioctl = gup_test_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
 	.release = gup_test_release,
 };
 

mm/zswap.c

@@ -1174,9 +1174,16 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 		goto reject;
 	}
 
+	/*
+	 * XXX: zswap reclaim does not work with cgroups yet. Without a
+	 * cgroup-aware entry LRU, we will push out entries system-wide based on
+	 * local cgroup limits.
+	 */
 	objcg = get_obj_cgroup_from_page(page);
-	if (objcg && !obj_cgroup_may_zswap(objcg))
-		goto shrink;
+	if (objcg && !obj_cgroup_may_zswap(objcg)) {
+		ret = -ENOMEM;
+		goto reject;
+	}
 
 	/* reclaim space if needed */
 	if (zswap_is_full()) {

tools/testing/radix-tree/Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
-CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
-	  -fsanitize=undefined
+CFLAGS += -I. -I../../include -I../../../lib -g -Og -Wall \
+	  -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder xarray maple
@@ -49,6 +49,7 @@ $(OFILES): Makefile *.h */*.h generated/map-shift.h generated/bit-length.h \
 	../../../include/linux/xarray.h \
 	../../../include/linux/maple_tree.h \
 	../../../include/linux/radix-tree.h \
+	../../../lib/radix-tree.h \
 	../../../include/linux/idr.h
 
 radix-tree.c: ../../../lib/radix-tree.c