Merge tag 'mm-hotfixes-stable-2024-11-09-22-40' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "20 hotfixes, 14 of which are cc:stable.

  Three affect DAMON. Lorenzo's five-patch series to address the
  mmap_region error handling is here also.

  Apart from that, various singletons"

* tag 'mm-hotfixes-stable-2024-11-09-22-40' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mailmap: add entry for Thorsten Blum
  ocfs2: remove entry once instead of null-ptr-dereference in ocfs2_xa_remove()
  signal: restore the override_rlimit logic
  fs/proc: fix compile warning about variable 'vmcore_mmap_ops'
  ucounts: fix counter leak in inc_rlimit_get_ucounts()
  selftests: hugetlb_dio: check for initial conditions to skip in the start
  mm: fix docs for the kernel parameter ``thp_anon=``
  mm/damon/core: avoid overflow in damon_feed_loop_next_input()
  mm/damon/core: handle zero schemes apply interval
  mm/damon/core: handle zero {aggregation,ops_update} intervals
  mm/mlock: set the correct prev on failure
  objpool: fix to make percpu slot allocation more robust
  mm/page_alloc: keep track of free highatomic
  mm: resolve faulty mmap_region() error path behaviour
  mm: refactor arch_calc_vm_flag_bits() and arm64 MTE handling
  mm: refactor map_deny_write_exec()
  mm: unconditionally close VMAs on error
  mm: avoid unsafe VMA hook invocation when error arises on mmap hook
  mm/thp: fix deferred split unqueue naming and locking
  mm/thp: fix deferred split queue not partially_mapped

.mailmap

@@ -665,6 +665,7 @@ Tomeu Vizoso <tomeu@tomeuvizoso.net> <tomeu.vizoso@collabora.com>
 Thomas Graf <tgraf@suug.ch>
 Thomas Körper <socketcan@esd.eu> <thomas.koerper@esd.eu>
 Thomas Pedersen <twp@codeaurora.org>
+Thorsten Blum <thorsten.blum@linux.dev> <thorsten.blum@toblux.com>
 Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com>
 Tingwei Zhang <quic_tingwei@quicinc.com> <tingwei@codeaurora.org>
 Tirupathi Reddy <quic_tirupath@quicinc.com> <tirupath@codeaurora.org>

Documentation/admin-guide/kernel-parameters.txt

@@ -6688,7 +6688,7 @@
 			0: no polling (default)
 
 	thp_anon=	[KNL]
-			Format: <size>,<size>[KMG]:<state>;<size>-<size>[KMG]:<state>
+			Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state>
 			state is one of "always", "madvise", "never" or "inherit".
 			Control the default behavior of the system with respect
 			to anonymous transparent hugepages.

Documentation/admin-guide/mm/transhuge.rst

@@ -303,7 +303,7 @@ control by passing the parameter ``transparent_hugepage=always`` or
 kernel command line.
 
 Alternatively, each supported anonymous THP size can be controlled by
-passing ``thp_anon=<size>,<size>[KMG]:<state>;<size>-<size>[KMG]:<state>``,
+passing ``thp_anon=<size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state>``,
 where ``<size>`` is the THP size (must be a power of 2 of PAGE_SIZE and
 supported anonymous THP)  and ``<state>`` is one of ``always``, ``madvise``,
 ``never`` or ``inherit``.

arch/arm64/include/asm/mman.h

@@ -6,6 +6,8 @@
 
 #ifndef BUILD_VDSO
 #include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/shmem_fs.h>
 #include <linux/types.h>
 
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
@@ -31,19 +33,21 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
-static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+static inline unsigned long arch_calc_vm_flag_bits(struct file *file,
+						   unsigned long flags)
 {
 	/*
 	 * Only allow MTE on anonymous mappings as these are guaranteed to be
 	 * backed by tags-capable memory. The vm_flags may be overridden by a
 	 * filesystem supporting MTE (RAM-based).
 	 */
-	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+	if (system_supports_mte() &&
+	    ((flags & MAP_ANONYMOUS) || shmem_file(file)))
 		return VM_MTE_ALLOWED;
 
 	return 0;
 }
-#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags)
 
 static inline bool arch_validate_prot(unsigned long prot,
 	unsigned long addr __always_unused)

arch/parisc/include/asm/mman.h

@@ -2,6 +2,7 @@
 #ifndef __ASM_MMAN_H__
 #define __ASM_MMAN_H__
 
+#include <linux/fs.h>
 #include <uapi/asm/mman.h>
 
 /* PARISC cannot allow mdwe as it needs writable stacks */
@@ -11,7 +12,7 @@ static inline bool arch_memory_deny_write_exec_supported(void)
 }
 #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
 
-static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+static inline unsigned long arch_calc_vm_flag_bits(struct file *file, unsigned long flags)
 {
 	/*
 	 * The stack on parisc grows upwards, so if userspace requests memory
@@ -23,6 +24,6 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
 
 	return 0;
 }
-#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags)
 
 #endif /* __ASM_MMAN_H__ */

fs/ocfs2/xattr.c

@@ -2036,8 +2036,7 @@ static int ocfs2_xa_remove(struct ocfs2_xa_loc *loc,
 				rc = 0;
 			ocfs2_xa_cleanup_value_truncate(loc, "removing",
 							orig_clusters);
-			if (rc)
-				goto out;
+			goto out;
 		}
 	}
 

fs/proc/vmcore.c

@@ -457,10 +457,6 @@ static vm_fault_t mmap_vmcore_fault(struct vm_fault *vmf)
 #endif
 }
 
-static const struct vm_operations_struct vmcore_mmap_ops = {
-	.fault = mmap_vmcore_fault,
-};
-
 /**
  * vmcore_alloc_buf - allocate buffer in vmalloc memory
  * @size: size of buffer
@@ -488,6 +484,11 @@ static inline char *vmcore_alloc_buf(size_t size)
  * virtually contiguous user-space in ELF layout.
  */
 #ifdef CONFIG_MMU
+
+static const struct vm_operations_struct vmcore_mmap_ops = {
+	.fault = mmap_vmcore_fault,
+};
+
 /*
  * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages
  * reported as not being ram with the zero page.

include/linux/mman.h

@@ -2,6 +2,7 @@
 #ifndef _LINUX_MMAN_H
 #define _LINUX_MMAN_H
 
+#include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/percpu_counter.h>
 
@@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages)
 #endif
 
 #ifndef arch_calc_vm_flag_bits
-#define arch_calc_vm_flag_bits(flags) 0
+#define arch_calc_vm_flag_bits(file, flags) 0
 #endif
 
 #ifndef arch_validate_prot
@@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
  * Combine the mmap "flags" argument into "vm_flags" used internally.
  */
 static inline unsigned long
-calc_vm_flag_bits(unsigned long flags)
+calc_vm_flag_bits(struct file *file, unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
 	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
 	       _calc_vm_trans(flags, MAP_STACK,	     VM_NOHUGEPAGE) |
-	       arch_calc_vm_flag_bits(flags);
+	       arch_calc_vm_flag_bits(file, flags);
 }
 
 unsigned long vm_commit_limit(void);
@@ -188,16 +189,31 @@ static inline bool arch_memory_deny_write_exec_supported(void)
  *
  *	d)	mmap(PROT_READ | PROT_EXEC)
  *		mmap(PROT_READ | PROT_EXEC | PROT_BTI)
+ *
+ * This is only applicable if the user has set the Memory-Deny-Write-Execute
+ * (MDWE) protection mask for the current process.
+ *
+ * @old specifies the VMA flags the VMA originally possessed, and @new the ones
+ * we propose to set.
+ *
+ * Return: false if proposed change is OK, true if not ok and should be denied.
  */
-static inline bool map_deny_write_exec(struct vm_area_struct *vma,  unsigned long vm_flags)
+static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
 {
+	/* If MDWE is disabled, we have nothing to deny. */
 	if (!test_bit(MMF_HAS_MDWE, &current->mm->flags))
 		return false;
 
-	if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE))
+	/* If the new VMA is not executable, we have nothing to deny. */
+	if (!(new & VM_EXEC))
+		return false;
+
+	/* Under MDWE we do not accept newly writably executable VMAs... */
+	if (new & VM_WRITE)
 		return true;
 
-	if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC))
+	/* ...nor previously non-executable VMAs becoming executable. */
+	if (!(old & VM_EXEC))
 		return true;
 
 	return false;

include/linux/mmzone.h

@@ -823,6 +823,7 @@ struct zone {
 	unsigned long watermark_boost;
 
 	unsigned long nr_reserved_highatomic;
+	unsigned long nr_free_highatomic;
 
 	/*
 	 * We don't know if the memory that we're going to allocate will be

include/linux/user_namespace.h

@@ -141,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty
 
 long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
 bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type);
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type,
+			    bool override_rlimit);
 void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type);
 bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max);
 

kernel/signal.c

@@ -419,7 +419,8 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
 	 */
 	rcu_read_lock();
 	ucounts = task_ucounts(t);
-	sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
+	sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING,
+					    override_rlimit);
 	rcu_read_unlock();
 	if (!sigpending)
 		return NULL;

kernel/ucount.c

@@ -307,7 +307,8 @@ void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 	do_dec_rlimit_put_ucounts(ucounts, NULL, type);
 }
 
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type,
+			    bool override_rlimit)
 {
 	/* Caller must hold a reference to ucounts */
 	struct ucounts *iter;
@@ -317,10 +318,11 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
 		long new = atomic_long_add_return(1, &iter->rlimit[type]);
 		if (new < 0 || new > max)
-			goto unwind;
+			goto dec_unwind;
 		if (iter == ucounts)
 			ret = new;
-		max = get_userns_rlimit_max(iter->ns, type);
+		if (!override_rlimit)
+			max = get_userns_rlimit_max(iter->ns, type);
 		/*
 		 * Grab an extra ucount reference for the caller when
 		 * the rlimit count was previously 0.
@@ -334,7 +336,6 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 dec_unwind:
 	dec = atomic_long_sub_return(1, &iter->rlimit[type]);
 	WARN_ON_ONCE(dec < 0);
-unwind:
 	do_dec_rlimit_put_ucounts(ucounts, iter, type);
 	return 0;
 }

lib/objpool.c

@@ -74,15 +74,21 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs,
 		 * warm caches and TLB hits. in default vmalloc is used to
 		 * reduce the pressure of kernel slab system. as we know,
 		 * mimimal size of vmalloc is one page since vmalloc would
-		 * always align the requested size to page size
+		 * always align the requested size to page size.
+		 * but if vmalloc fails or it is not available (e.g. GFP_ATOMIC)
+		 * allocate percpu slot with kmalloc.
 		 */
-		if ((pool->gfp & GFP_ATOMIC) == GFP_ATOMIC)
-			slot = kmalloc_node(size, pool->gfp, cpu_to_node(i));
-		else
+		slot = NULL;
+
+		if ((pool->gfp & (GFP_ATOMIC | GFP_KERNEL)) != GFP_ATOMIC)
 			slot = __vmalloc_node(size, sizeof(void *), pool->gfp,
 				cpu_to_node(i), __builtin_return_address(0));
-		if (!slot)
-			return -ENOMEM;
+
+		if (!slot) {
+			slot = kmalloc_node(size, pool->gfp, cpu_to_node(i));
+			if (!slot)
+				return -ENOMEM;
+		}
 		memset(slot, 0, size);
 		pool->cpu_slots[i] = slot;
 

mm/damon/core.c

@@ -1412,7 +1412,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c,
 	damon_for_each_scheme(s, c) {
 		struct damos_quota *quota = &s->quota;
 
-		if (c->passed_sample_intervals != s->next_apply_sis)
+		if (c->passed_sample_intervals < s->next_apply_sis)
 			continue;
 
 		if (!s->wmarks.activated)
@@ -1456,17 +1456,31 @@ static unsigned long damon_feed_loop_next_input(unsigned long last_input,
 		unsigned long score)
 {
 	const unsigned long goal = 10000;
-	unsigned long score_goal_diff = max(goal, score) - min(goal, score);
-	unsigned long score_goal_diff_bp = score_goal_diff * 10000 / goal;
-	unsigned long compensation = last_input * score_goal_diff_bp / 10000;
 	/* Set minimum input as 10000 to avoid compensation be zero */
 	const unsigned long min_input = 10000;
+	unsigned long score_goal_diff, compensation;
+	bool over_achieving = score > goal;
 
-	if (goal > score)
+	if (score == goal)
+		return last_input;
+	if (score >= goal * 2)
+		return min_input;
+
+	if (over_achieving)
+		score_goal_diff = score - goal;
+	else
+		score_goal_diff = goal - score;
+
+	if (last_input < ULONG_MAX / score_goal_diff)
+		compensation = last_input * score_goal_diff / goal;
+	else
+		compensation = last_input / goal * score_goal_diff;
+
+	if (over_achieving)
+		return max(last_input - compensation, min_input);
+	if (last_input < ULONG_MAX - compensation)
 		return last_input + compensation;
-	if (last_input > compensation + min_input)
-		return last_input - compensation;
-	return min_input;
+	return ULONG_MAX;
 }
 
 #ifdef CONFIG_PSI
@@ -1622,7 +1636,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 	bool has_schemes_to_apply = false;
 
 	damon_for_each_scheme(s, c) {
-		if (c->passed_sample_intervals != s->next_apply_sis)
+		if (c->passed_sample_intervals < s->next_apply_sis)
 			continue;
 
 		if (!s->wmarks.activated)
@@ -1642,9 +1656,9 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 	}
 
 	damon_for_each_scheme(s, c) {
-		if (c->passed_sample_intervals != s->next_apply_sis)
+		if (c->passed_sample_intervals < s->next_apply_sis)
 			continue;
-		s->next_apply_sis +=
+		s->next_apply_sis = c->passed_sample_intervals +
 			(s->apply_interval_us ? s->apply_interval_us :
 			 c->attrs.aggr_interval) / sample_interval;
 	}
@@ -2000,7 +2014,7 @@ static int kdamond_fn(void *data)
 		if (ctx->ops.check_accesses)
 			max_nr_accesses = ctx->ops.check_accesses(ctx);
 
-		if (ctx->passed_sample_intervals == next_aggregation_sis) {
+		if (ctx->passed_sample_intervals >= next_aggregation_sis) {
 			kdamond_merge_regions(ctx,
 					max_nr_accesses / 10,
 					sz_limit);
@@ -2018,7 +2032,7 @@ static int kdamond_fn(void *data)
 
 		sample_interval = ctx->attrs.sample_interval ?
 			ctx->attrs.sample_interval : 1;
-		if (ctx->passed_sample_intervals == next_aggregation_sis) {
+		if (ctx->passed_sample_intervals >= next_aggregation_sis) {
 			ctx->next_aggregation_sis = next_aggregation_sis +
 				ctx->attrs.aggr_interval / sample_interval;
 
@@ -2028,7 +2042,7 @@ static int kdamond_fn(void *data)
 				ctx->ops.reset_aggregated(ctx);
 		}
 
-		if (ctx->passed_sample_intervals == next_ops_update_sis) {
+		if (ctx->passed_sample_intervals >= next_ops_update_sis) {
 			ctx->next_ops_update_sis = next_ops_update_sis +
 				ctx->attrs.ops_update_interval /
 				sample_interval;