Merge tag 'mm-hotfixes-stable-2024-05-25-09-13' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "16 hotfixes, 11 of which are cc:stable.

  A few nilfs2 fixes, the remainder are for MM: a couple of selftests
  fixes, various singletons fixing various issues in various parts"

* tag 'mm-hotfixes-stable-2024-05-25-09-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm/ksm: fix possible UAF of stable_node
  mm/memory-failure: fix handling of dissolved but not taken off from buddy pages
  mm: /proc/pid/smaps_rollup: avoid skipping vma after getting mmap_lock again
  nilfs2: fix potential hang in nilfs_detach_log_writer()
  nilfs2: fix unexpected freezing of nilfs_segctor_sync()
  nilfs2: fix use-after-free of timer for log writer thread
  selftests/mm: fix build warnings on ppc64
  arm64: patching: fix handling of execmem addresses
  selftests/mm: compaction_test: fix bogus test success and reduce probability of OOM-killer invocation
  selftests/mm: compaction_test: fix incorrect write of zero to nr_hugepages
  selftests/mm: compaction_test: fix bogus test success on Aarch64
  mailmap: update email address for Satya Priya
  mm/huge_memory: don't unpoison huge_zero_folio
  kasan, fortify: properly rename memintrinsics
  lib: add version into /proc/allocinfo output
  mm/vmalloc: fix vmalloc which may return null if called with __GFP_NOFAIL

.mailmap

@@ -572,7 +572,7 @@ Sarangdhar Joshi <spjoshi@codeaurora.org>
 Sascha Hauer <s.hauer@pengutronix.de>
 Sahitya Tummala <quic_stummala@quicinc.com> <stummala@codeaurora.org>
 Sathishkumar Muruganandam <quic_murugana@quicinc.com> <murugana@codeaurora.org>
-Satya Priya <quic_c_skakit@quicinc.com> <skakit@codeaurora.org>
+Satya Priya <quic_skakitap@quicinc.com> <quic_c_skakit@quicinc.com> <skakit@codeaurora.org>
 S.Çağlar Onur <caglar@pardus.org.tr>
 Sayali Lokhande <quic_sayalil@quicinc.com> <sayalil@codeaurora.org>
 Sean Christopherson <seanjc@google.com> <sean.j.christopherson@intel.com>

Documentation/filesystems/proc.rst

@@ -961,13 +961,14 @@ Provides information about memory allocations at all locations in the code
 base. Each allocation in the code is identified by its source file, line
 number, module (if originates from a loadable module) and the function calling
 the allocation. The number of bytes allocated and number of calls at each
-location are reported.
+location are reported. The first line indicates the version of the file, the
+second line is the header listing fields in the file.
 
 Example output.
 
 ::
 
-    > sort -rn /proc/allocinfo
+    > tail -n +3 /proc/allocinfo | sort -rn
    127664128    31168 mm/page_ext.c:270 func:alloc_page_ext
     56373248     4737 mm/slub.c:2259 func:alloc_slab_page
     14880768     3633 mm/readahead.c:247 func:page_cache_ra_unbounded

arch/arm64/kernel/patching.c

@@ -36,7 +36,7 @@ static void __kprobes *patch_map(void *addr, int fixmap)
 
 	if (image)
 		page = phys_to_page(__pa_symbol(addr));
-	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+	else if (IS_ENABLED(CONFIG_EXECMEM))
 		page = vmalloc_to_page(addr);
 	else
 		return addr;

fs/nilfs2/segment.c

@@ -2118,8 +2118,10 @@ static void nilfs_segctor_start_timer(struct nilfs_sc_info *sci)
 {
 	spin_lock(&sci->sc_state_lock);
 	if (!(sci->sc_state & NILFS_SEGCTOR_COMMIT)) {
-		sci->sc_timer.expires = jiffies + sci->sc_interval;
-		add_timer(&sci->sc_timer);
+		if (sci->sc_task) {
+			sci->sc_timer.expires = jiffies + sci->sc_interval;
+			add_timer(&sci->sc_timer);
+		}
 		sci->sc_state |= NILFS_SEGCTOR_COMMIT;
 	}
 	spin_unlock(&sci->sc_state_lock);
@@ -2166,19 +2168,36 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci)
 	struct nilfs_segctor_wait_request wait_req;
 	int err = 0;
 
-	spin_lock(&sci->sc_state_lock);
 	init_wait(&wait_req.wq);
 	wait_req.err = 0;
 	atomic_set(&wait_req.done, 0);
+	init_waitqueue_entry(&wait_req.wq, current);
+
+	/*
+	 * To prevent a race issue where completion notifications from the
+	 * log writer thread are missed, increment the request sequence count
+	 * "sc_seq_request" and insert a wait queue entry using the current
+	 * sequence number into the "sc_wait_request" queue at the same time
+	 * within the lock section of "sc_state_lock".
+	 */
+	spin_lock(&sci->sc_state_lock);
 	wait_req.seq = ++sci->sc_seq_request;
+	add_wait_queue(&sci->sc_wait_request, &wait_req.wq);
 	spin_unlock(&sci->sc_state_lock);
 
-	init_waitqueue_entry(&wait_req.wq, current);
-	add_wait_queue(&sci->sc_wait_request, &wait_req.wq);
-	set_current_state(TASK_INTERRUPTIBLE);
 	wake_up(&sci->sc_wait_daemon);
 
 	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		/*
+		 * Synchronize only while the log writer thread is alive.
+		 * Leave flushing out after the log writer thread exits to
+		 * the cleanup work in nilfs_segctor_destroy().
+		 */
+		if (!sci->sc_task)
+			break;
+
 		if (atomic_read(&wait_req.done)) {
 			err = wait_req.err;
 			break;
@@ -2194,15 +2213,15 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci)
 	return err;
 }
 
-static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err)
+static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err, bool force)
 {
 	struct nilfs_segctor_wait_request *wrq, *n;
 	unsigned long flags;
 
 	spin_lock_irqsave(&sci->sc_wait_request.lock, flags);
 	list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) {
 		if (!atomic_read(&wrq->done) &&
-		    nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) {
+		    (force || nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq))) {
 			wrq->err = err;
 			atomic_set(&wrq->done, 1);
 		}
@@ -2320,10 +2339,21 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
  */
 static void nilfs_segctor_accept(struct nilfs_sc_info *sci)
 {
+	bool thread_is_alive;
+
 	spin_lock(&sci->sc_state_lock);
 	sci->sc_seq_accepted = sci->sc_seq_request;
+	thread_is_alive = (bool)sci->sc_task;
 	spin_unlock(&sci->sc_state_lock);
-	del_timer_sync(&sci->sc_timer);
+
+	/*
+	 * This function does not race with the log writer thread's
+	 * termination.  Therefore, deleting sc_timer, which should not be
+	 * done after the log writer thread exits, can be done safely outside
+	 * the area protected by sc_state_lock.
+	 */
+	if (thread_is_alive)
+		del_timer_sync(&sci->sc_timer);
 }
 
 /**
@@ -2340,7 +2370,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err)
 	if (mode == SC_LSEG_SR) {
 		sci->sc_state &= ~NILFS_SEGCTOR_COMMIT;
 		sci->sc_seq_done = sci->sc_seq_accepted;
-		nilfs_segctor_wakeup(sci, err);
+		nilfs_segctor_wakeup(sci, err, false);
 		sci->sc_flush_request = 0;
 	} else {
 		if (mode == SC_FLUSH_FILE)
@@ -2349,7 +2379,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err)
 			sci->sc_flush_request &= ~FLUSH_DAT_BIT;
 
 		/* re-enable timer if checkpoint creation was not done */
-		if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) &&
+		if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && sci->sc_task &&
 		    time_before(jiffies, sci->sc_timer.expires))
 			add_timer(&sci->sc_timer);
 	}
@@ -2539,6 +2569,7 @@ static int nilfs_segctor_thread(void *arg)
 	int timeout = 0;
 
 	sci->sc_timer_task = current;
+	timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0);
 
 	/* start sync. */
 	sci->sc_task = current;
@@ -2606,6 +2637,7 @@ static int nilfs_segctor_thread(void *arg)
  end_thread:
 	/* end sync. */
 	sci->sc_task = NULL;
+	timer_shutdown_sync(&sci->sc_timer);
 	wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */
 	spin_unlock(&sci->sc_state_lock);
 	return 0;
@@ -2669,7 +2701,6 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
 	INIT_LIST_HEAD(&sci->sc_gc_inodes);
 	INIT_LIST_HEAD(&sci->sc_iput_queue);
 	INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
-	timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0);
 
 	sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
 	sci->sc_mjcp_freq = HZ * NILFS_SC_DEFAULT_SR_FREQ;
@@ -2723,6 +2754,13 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 		|| sci->sc_seq_request != sci->sc_seq_done);
 	spin_unlock(&sci->sc_state_lock);
 
+	/*
+	 * Forcibly wake up tasks waiting in nilfs_segctor_sync(), which can
+	 * be called from delayed iput() via nilfs_evict_inode() and can race
+	 * with the above log writer thread termination.
+	 */
+	nilfs_segctor_wakeup(sci, 0, true);
+
 	if (flush_work(&sci->sc_iput_work))
 		flag = true;
 
@@ -2748,7 +2786,6 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 
 	down_write(&nilfs->ns_segctor_sem);
 
-	timer_shutdown_sync(&sci->sc_timer);
 	kfree(sci);
 }
 

fs/proc/task_mmu.c

@@ -970,12 +970,17 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 				break;
 
 			/* Case 1 and 2 above */
-			if (vma->vm_start >= last_vma_end)
+			if (vma->vm_start >= last_vma_end) {
+				smap_gather_stats(vma, &mss, 0);
+				last_vma_end = vma->vm_end;
 				continue;
+			}
 
 			/* Case 4 above */
-			if (vma->vm_end > last_vma_end)
+			if (vma->vm_end > last_vma_end) {
 				smap_gather_stats(vma, &mss, last_vma_end);
+				last_vma_end = vma->vm_end;
+			}
 		}
 	} for_each_vma(vmi, vma);
 

include/linux/fortify-string.h

@@ -75,17 +75,30 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("
 	__ret;							\
 })
 
-#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+#if defined(__SANITIZE_ADDRESS__)
+
+#if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY)
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
+#elif defined(CONFIG_KASAN_GENERIC)
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy);
+#else /* CONFIG_KASAN_SW_TAGS */
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy);
+#endif
+
 extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr);
 extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp);
-extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
-extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove);
-extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset);
 extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat);
 extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy);
 extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen);
 extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat);
 extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy);
+
 #else
 
 #if defined(__SANITIZE_MEMORY__)
@@ -110,6 +123,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
 #define __underlying_strlen	__builtin_strlen
 #define __underlying_strncat	__builtin_strncat
 #define __underlying_strncpy	__builtin_strncpy
+
 #endif
 
 /**

lib/alloc_tag.c

@@ -16,47 +16,60 @@ EXPORT_SYMBOL(_shared_alloc_tag);
 DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
 			mem_alloc_profiling_key);
 
+struct allocinfo_private {
+	struct codetag_iterator iter;
+	bool print_header;
+};
+
 static void *allocinfo_start(struct seq_file *m, loff_t *pos)
 {
-	struct codetag_iterator *iter;
+	struct allocinfo_private *priv;
 	struct codetag *ct;
 	loff_t node = *pos;
 
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	m->private = iter;
-	if (!iter)
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	m->private = priv;
+	if (!priv)
 		return NULL;
 
+	priv->print_header = (node == 0);
 	codetag_lock_module_list(alloc_tag_cttype, true);
-	*iter = codetag_get_ct_iter(alloc_tag_cttype);
-	while ((ct = codetag_next_ct(iter)) != NULL && node)
+	priv->iter = codetag_get_ct_iter(alloc_tag_cttype);
+	while ((ct = codetag_next_ct(&priv->iter)) != NULL && node)
 		node--;
 
-	return ct ? iter : NULL;
+	return ct ? priv : NULL;
 }
 
 static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos)
 {
-	struct codetag_iterator *iter = (struct codetag_iterator *)arg;
-	struct codetag *ct = codetag_next_ct(iter);
+	struct allocinfo_private *priv = (struct allocinfo_private *)arg;
+	struct codetag *ct = codetag_next_ct(&priv->iter);
 
 	(*pos)++;
 	if (!ct)
 		return NULL;
 
-	return iter;
+	return priv;
 }
 
 static void allocinfo_stop(struct seq_file *m, void *arg)
 {
-	struct codetag_iterator *iter = (struct codetag_iterator *)m->private;
+	struct allocinfo_private *priv = (struct allocinfo_private *)m->private;
 
-	if (iter) {
+	if (priv) {
 		codetag_lock_module_list(alloc_tag_cttype, false);
-		kfree(iter);
+		kfree(priv);
 	}
 }
 
+static void print_allocinfo_header(struct seq_buf *buf)
+{
+	/* Output format version, so we can change it. */
+	seq_buf_printf(buf, "allocinfo - version: 1.0\n");
+	seq_buf_printf(buf, "#     <size>  <calls> <tag info>\n");
+}
+
 static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct)
 {
 	struct alloc_tag *tag = ct_to_alloc_tag(ct);
@@ -71,13 +84,17 @@ static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct)
 
 static int allocinfo_show(struct seq_file *m, void *arg)
 {
-	struct codetag_iterator *iter = (struct codetag_iterator *)arg;
+	struct allocinfo_private *priv = (struct allocinfo_private *)arg;
 	char *bufp;
 	size_t n = seq_get_buf(m, &bufp);
 	struct seq_buf buf;
 
 	seq_buf_init(&buf, bufp, n);
-	alloc_tag_to_text(&buf, iter->ct);
+	if (priv->print_header) {
+		print_allocinfo_header(&buf);
+		priv->print_header = false;
+	}
+	alloc_tag_to_text(&buf, priv->iter.ct);
 	seq_commit(m, seq_buf_used(&buf));
 	return 0;
 }

mm/ksm.c

@@ -2153,7 +2153,6 @@ static struct ksm_stable_node *stable_tree_insert(struct folio *kfolio)
 
 	INIT_HLIST_HEAD(&stable_node_dup->hlist);
 	stable_node_dup->kpfn = kpfn;
-	folio_set_stable_node(kfolio, stable_node_dup);
 	stable_node_dup->rmap_hlist_len = 0;
 	DO_NUMA(stable_node_dup->nid = nid);
 	if (!need_chain) {
@@ -2172,6 +2171,8 @@ static struct ksm_stable_node *stable_tree_insert(struct folio *kfolio)
 		stable_node_chain_add_dup(stable_node_dup, stable_node);
 	}
 
+	folio_set_stable_node(kfolio, stable_node_dup);
+
 	return stable_node_dup;
 }
 

mm/memory-failure.c

@@ -1221,7 +1221,7 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 		 * subpages.
 		 */
 		folio_put(folio);
-		if (__page_handle_poison(p) >= 0) {
+		if (__page_handle_poison(p) > 0) {
 			page_ref_inc(p);
 			res = MF_RECOVERED;
 		} else {
@@ -2091,7 +2091,7 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb
 	 */
 	if (res == 0) {
 		folio_unlock(folio);
-		if (__page_handle_poison(p) >= 0) {
+		if (__page_handle_poison(p) > 0) {
 			page_ref_inc(p);
 			res = MF_RECOVERED;
 		} else {
@@ -2546,6 +2546,13 @@ int unpoison_memory(unsigned long pfn)
 		goto unlock_mutex;
 	}
 
+	if (is_huge_zero_folio(folio)) {
+		unpoison_pr_info("Unpoison: huge zero page is not supported %#lx\n",
+				 pfn, &unpoison_rs);
+		ret = -EOPNOTSUPP;
+		goto unlock_mutex;
+	}
+
 	if (!PageHWPoison(p)) {
 		unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n",
 				 pfn, &unpoison_rs);