Merge tag 'mm-hotfixes-stable-2023-09-23-10-31' of...

Merge tag 'mm-hotfixes-stable-2023-09-23-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "13 hotfixes, 10 of which pertain to post-6.5 issues. The other three
  are cc:stable"

* tag 'mm-hotfixes-stable-2023-09-23-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  proc: nommu: fix empty /proc/<pid>/maps
  filemap: add filemap_map_order0_folio() to handle order0 folio
  proc: nommu: /proc/<pid>/maps: release mmap read lock
  mm: memcontrol: fix GFP_NOFS recursion in memory.high enforcement
  pidfd: prevent a kernel-doc warning
  argv_split: fix kernel-doc warnings
  scatterlist: add missing function params to kernel-doc
  selftests/proc: fixup proc-empty-vm test after KSM changes
  revert "scripts/gdb/symbols: add specific ko module load command"
  selftests: link libasan statically for tests with -fsanitize=address
  task_work: add kerneldoc annotation for 'data' argument
  mm: page_alloc: fix CMA and HIGHATOMIC landing on the wrong buddy list
  sh: mm: re-add lost __ref to ioremap_prot() to fix modpost warning

arch/sh/mm/ioremap.c

@@ -72,8 +72,8 @@ __ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot)
 #define __ioremap_29bit(offset, size, prot)		NULL
 #endif /* CONFIG_29BIT */
 
-void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   unsigned long prot)
+void __iomem __ref *ioremap_prot(phys_addr_t phys_addr, size_t size,
+				 unsigned long prot)
 {
 	void __iomem *mapped;
 	pgprot_t pgprot = __pgprot(prot);

fs/proc/internal.h

@@ -289,9 +289,7 @@ struct proc_maps_private {
 	struct inode *inode;
 	struct task_struct *task;
 	struct mm_struct *mm;
-#ifdef CONFIG_MMU
 	struct vma_iterator iter;
-#endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *task_mempolicy;
 #endif

fs/proc/task_nommu.c

@@ -175,15 +175,28 @@ static int show_map(struct seq_file *m, void *_p)
 	return nommu_vma_show(m, _p);
 }
 
-static void *m_start(struct seq_file *m, loff_t *pos)
+static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv,
+						loff_t *ppos)
+{
+	struct vm_area_struct *vma = vma_next(&priv->iter);
+
+	if (vma) {
+		*ppos = vma->vm_start;
+	} else {
+		*ppos = -1UL;
+	}
+
+	return vma;
+}
+
+static void *m_start(struct seq_file *m, loff_t *ppos)
 {
 	struct proc_maps_private *priv = m->private;
+	unsigned long last_addr = *ppos;
 	struct mm_struct *mm;
-	struct vm_area_struct *vma;
-	unsigned long addr = *pos;
 
-	/* See m_next(). Zero at the start or after lseek. */
-	if (addr == -1UL)
+	/* See proc_get_vma(). Zero at the start or after lseek. */
+	if (last_addr == -1UL)
 		return NULL;
 
 	/* pin the task and mm whilst we play with them */
@@ -192,44 +205,41 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 		return ERR_PTR(-ESRCH);
 
 	mm = priv->mm;
-	if (!mm || !mmget_not_zero(mm))
+	if (!mm || !mmget_not_zero(mm)) {
+		put_task_struct(priv->task);
+		priv->task = NULL;
 		return NULL;
+	}
 
 	if (mmap_read_lock_killable(mm)) {
 		mmput(mm);
+		put_task_struct(priv->task);
+		priv->task = NULL;
 		return ERR_PTR(-EINTR);
 	}
 
-	/* start the next element from addr */
-	vma = find_vma(mm, addr);
-	if (vma)
-		return vma;
+	vma_iter_init(&priv->iter, mm, last_addr);
 
-	mmap_read_unlock(mm);
-	mmput(mm);
-	return NULL;
+	return proc_get_vma(priv, ppos);
 }
 
-static void m_stop(struct seq_file *m, void *_vml)
+static void m_stop(struct seq_file *m, void *v)
 {
 	struct proc_maps_private *priv = m->private;
+	struct mm_struct *mm = priv->mm;
 
-	if (!IS_ERR_OR_NULL(_vml)) {
-		mmap_read_unlock(priv->mm);
-		mmput(priv->mm);
-	}
-	if (priv->task) {
-		put_task_struct(priv->task);
-		priv->task = NULL;
-	}
+	if (!priv->task)
+		return;
+
+	mmap_read_unlock(mm);
+	mmput(mm);
+	put_task_struct(priv->task);
+	priv->task = NULL;
 }
 
-static void *m_next(struct seq_file *m, void *_p, loff_t *pos)
+static void *m_next(struct seq_file *m, void *_p, loff_t *ppos)
 {
-	struct vm_area_struct *vma = _p;
-
-	*pos = vma->vm_end;
-	return find_vma(vma->vm_mm, vma->vm_end);
+	return proc_get_vma(m->private, ppos);
 }
 
 static const struct seq_operations proc_pid_maps_ops = {

include/linux/memcontrol.h

@@ -920,7 +920,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
 	return READ_ONCE(mz->lru_zone_size[zone_idx][lru]);
 }
 
-void mem_cgroup_handle_over_high(void);
+void mem_cgroup_handle_over_high(gfp_t gfp_mask);
 
 unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
 
@@ -1458,7 +1458,7 @@ static inline void mem_cgroup_unlock_pages(void)
 	rcu_read_unlock();
 }
 
-static inline void mem_cgroup_handle_over_high(void)
+static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 {
 }
 

include/linux/resume_user_mode.h

@@ -55,7 +55,7 @@ static inline void resume_user_mode_work(struct pt_regs *regs)
 	}
 #endif
 
-	mem_cgroup_handle_over_high();
+	mem_cgroup_handle_over_high(GFP_KERNEL);
 	blkcg_maybe_throttle_current();
 
 	rseq_handle_notify_resume(NULL, regs);

kernel/pid.c

@@ -609,7 +609,7 @@ int pidfd_create(struct pid *pid, unsigned int flags)
 }
 
 /**
- * pidfd_open() - Open new pid file descriptor.
+ * sys_pidfd_open() - Open new pid file descriptor.
  *
  * @pid:   pid for which to retrieve a pidfd
  * @flags: flags to pass

kernel/task_work.c

@@ -78,6 +78,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
  * task_work_cancel_match - cancel a pending work added by task_work_add()
  * @task: the task which should execute the work
  * @match: match function to call
+ * @data: data to be passed in to match function
  *
  * RETURNS:
  * The found work or NULL if not found.

lib/argv_split.c

@@ -28,7 +28,7 @@ static int count_argc(const char *str)
 
 /**
  * argv_free - free an argv
- * @argv - the argument vector to be freed
+ * @argv: the argument vector to be freed
  *
  * Frees an argv and the strings it points to.
  */
@@ -46,7 +46,7 @@ EXPORT_SYMBOL(argv_free);
  * @str: the string to be split
  * @argcp: returned argument count
  *
- * Returns an array of pointers to strings which are split out from
+ * Returns: an array of pointers to strings which are split out from
  * @str.  This is performed by strictly splitting on white-space; no
  * quote processing is performed.  Multiple whitespace characters are
  * considered to be a single argument separator.  The returned array

lib/scatterlist.c

@@ -265,7 +265,8 @@ EXPORT_SYMBOL(sg_free_table);
  * @table:	The sg table header to use
  * @nents:	Number of entries in sg list
  * @max_ents:	The maximum number of entries the allocator returns per call
- * @nents_first_chunk: Number of entries int the (preallocated) first
+ * @first_chunk: first SGL if preallocated (may be %NULL)
+ * @nents_first_chunk: Number of entries in the (preallocated) first
  * 	scatterlist chunk, 0 means no such preallocated chunk provided by user
  * @gfp_mask:	GFP allocation mask
  * @alloc_fn:	Allocator to use
@@ -788,6 +789,7 @@ EXPORT_SYMBOL(__sg_page_iter_dma_next);
  * @miter: sg mapping iter to be started
  * @sgl: sg list to iterate over
  * @nents: number of sg entries
+ * @flags: sg iterator flags
  *
  * Description:
  *   Starts mapping iterator @miter.

mm/filemap.c

@@ -3475,13 +3475,11 @@ static struct folio *next_uptodate_folio(struct xa_state *xas,
  */
 static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 			struct folio *folio, unsigned long start,
-			unsigned long addr, unsigned int nr_pages)
+			unsigned long addr, unsigned int nr_pages,
+			unsigned int *mmap_miss)
 {
 	vm_fault_t ret = 0;
-	struct vm_area_struct *vma = vmf->vma;
-	struct file *file = vma->vm_file;
 	struct page *page = folio_page(folio, start);
-	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
 	unsigned int count = 0;
 	pte_t *old_ptep = vmf->pte;
 
@@ -3489,8 +3487,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 		if (PageHWPoison(page + count))
 			goto skip;
 
-		if (mmap_miss > 0)
-			mmap_miss--;
+		(*mmap_miss)++;
 
 		/*
 		 * NOTE: If there're PTE markers, we'll leave them to be
@@ -3525,7 +3522,35 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 	}
 
 	vmf->pte = old_ptep;
-	WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
+
+	return ret;
+}
+
+static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf,
+		struct folio *folio, unsigned long addr,
+		unsigned int *mmap_miss)
+{
+	vm_fault_t ret = 0;
+	struct page *page = &folio->page;
+
+	if (PageHWPoison(page))
+		return ret;
+
+	(*mmap_miss)++;
+
+	/*
+	 * NOTE: If there're PTE markers, we'll leave them to be
+	 * handled in the specific fault path, and it'll prohibit
+	 * the fault-around logic.
+	 */
+	if (!pte_none(ptep_get(vmf->pte)))
+		return ret;
+
+	if (vmf->address == addr)
+		ret = VM_FAULT_NOPAGE;
+
+	set_pte_range(vmf, folio, page, 1, addr);
+	folio_ref_inc(folio);
 
 	return ret;
 }
@@ -3541,7 +3566,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct folio *folio;
 	vm_fault_t ret = 0;
-	int nr_pages = 0;
+	unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved;
 
 	rcu_read_lock();
 	folio = next_uptodate_folio(&xas, mapping, end_pgoff);
@@ -3569,25 +3594,27 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		end = folio->index + folio_nr_pages(folio) - 1;
 		nr_pages = min(end, end_pgoff) - xas.xa_index + 1;
 
-		/*
-		 * NOTE: If there're PTE markers, we'll leave them to be
-		 * handled in the specific fault path, and it'll prohibit the
-		 * fault-around logic.
-		 */
-		if (!pte_none(ptep_get(vmf->pte)))
-			goto unlock;
-
-		ret |= filemap_map_folio_range(vmf, folio,
-				xas.xa_index - folio->index, addr, nr_pages);
+		if (!folio_test_large(folio))
+			ret |= filemap_map_order0_folio(vmf,
+					folio, addr, &mmap_miss);
+		else
+			ret |= filemap_map_folio_range(vmf, folio,
+					xas.xa_index - folio->index, addr,
+					nr_pages, &mmap_miss);
 
-unlock:
 		folio_unlock(folio);
 		folio_put(folio);
-		folio = next_uptodate_folio(&xas, mapping, end_pgoff);
-	} while (folio);
+	} while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
 	rcu_read_unlock();
+
+	mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss);
+	if (mmap_miss >= mmap_miss_saved)
+		WRITE_ONCE(file->f_ra.mmap_miss, 0);
+	else
+		WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss);
+
 	return ret;
 }
 EXPORT_SYMBOL(filemap_map_pages);

mm/memcontrol.c

@@ -2555,7 +2555,7 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
  * Scheduled by try_charge() to be executed from the userland return path
  * and reclaims memory over the high limit.
  */
-void mem_cgroup_handle_over_high(void)
+void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 {
 	unsigned long penalty_jiffies;
 	unsigned long pflags;
@@ -2583,7 +2583,7 @@ void mem_cgroup_handle_over_high(void)
 	 */
 	nr_reclaimed = reclaim_high(memcg,
 				    in_retry ? SWAP_CLUSTER_MAX : nr_pages,
-				    GFP_KERNEL);
+				    gfp_mask);
 
 	/*
 	 * memory.high is breached and reclaim is unable to keep up. Throttle
@@ -2819,7 +2819,7 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
 	    !(current->flags & PF_MEMALLOC) &&
 	    gfpflags_allow_blocking(gfp_mask)) {
-		mem_cgroup_handle_over_high();
+		mem_cgroup_handle_over_high(gfp_mask);
 	}
 	return 0;
 }

mm/page_alloc.c

@@ -2400,7 +2400,7 @@ void free_unref_page(struct page *page, unsigned int order)
 	struct per_cpu_pages *pcp;
 	struct zone *zone;
 	unsigned long pfn = page_to_pfn(page);
-	int migratetype;
+	int migratetype, pcpmigratetype;
 
 	if (!free_unref_page_prepare(page, pfn, order))
 		return;
@@ -2408,24 +2408,24 @@ void free_unref_page(struct page *page, unsigned int order)
 	/*
 	 * We only track unmovable, reclaimable and movable on pcp lists.
 	 * Place ISOLATE pages on the isolated list because they are being
-	 * offlined but treat HIGHATOMIC as movable pages so we can get those
-	 * areas back if necessary. Otherwise, we may have to free
+	 * offlined but treat HIGHATOMIC and CMA as movable pages so we can
+	 * get those areas back if necessary. Otherwise, we may have to free
 	 * excessively into the page allocator
 	 */
-	migratetype = get_pcppage_migratetype(page);
+	migratetype = pcpmigratetype = get_pcppage_migratetype(page);
 	if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
 		if (unlikely(is_migrate_isolate(migratetype))) {
 			free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE);
 			return;
 		}
-		migratetype = MIGRATE_MOVABLE;
+		pcpmigratetype = MIGRATE_MOVABLE;
 	}
 
 	zone = page_zone(page);
 	pcp_trylock_prepare(UP_flags);
 	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (pcp) {
-		free_unref_page_commit(zone, pcp, page, migratetype, order);
+		free_unref_page_commit(zone, pcp, page, pcpmigratetype, order);
 		pcp_spin_unlock(pcp);
 	} else {
 		free_one_page(zone, page, pfn, order, migratetype, FPI_NONE);

scripts/gdb/linux/symbols.py

@@ -111,12 +111,11 @@ lx-symbols command."""
         return "{textaddr} {sections}".format(
             textaddr=textaddr, sections="".join(args))
 
-    def load_module_symbols(self, module, module_file=None):
+    def load_module_symbols(self, module):
         module_name = module['name'].string()
         module_addr = str(module['mem'][constants.LX_MOD_TEXT]['base']).split()[0]
 
-        if not module_file:
-            module_file = self._get_module_file(module_name)
+        module_file = self._get_module_file(module_name)
         if not module_file and not self.module_files_updated:
             self._update_module_files()
             module_file = self._get_module_file(module_name)
@@ -139,19 +138,6 @@ lx-symbols command."""
         else:
             gdb.write("no module object found for '{0}'\n".format(module_name))
 
-    def load_ko_symbols(self, mod_path):
-        self.loaded_modules = []
-        module_list = modules.module_list()
-
-        for module in module_list:
-            module_name = module['name'].string()
-            module_pattern = ".*/{0}\.ko(?:.debug)?$".format(
-                module_name.replace("_", r"[_\-]"))
-            if re.match(module_pattern, mod_path) and os.path.exists(mod_path):
-                self.load_module_symbols(module, mod_path)
-                return
-        raise gdb.GdbError("%s is not a valid .ko\n" % mod_path)
-
     def load_all_symbols(self):
         gdb.write("loading vmlinux\n")
 
@@ -190,11 +176,6 @@ lx-symbols command."""
         self.module_files = []
         self.module_files_updated = False
 
-        argv = gdb.string_to_argv(arg)
-        if len(argv) == 1:
-            self.load_ko_symbols(argv[0])
-            return
-
         self.load_all_symbols()
 
         if hasattr(gdb, 'Breakpoint'):

tools/testing/selftests/fchmodat2/Makefile

 # SPDX-License-Identifier: GPL-2.0-or-later
 
-CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES)
+CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan $(KHDR_INCLUDES)
 TEST_GEN_PROGS := fchmodat2_test
 
 include ../lib.mk

tools/testing/selftests/openat2/Makefile

 # SPDX-License-Identifier: GPL-2.0-or-later
 
-CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined
+CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan
 TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test
 
 include ../lib.mk

tools/testing/selftests/proc/proc-empty-vm.c

@@ -267,6 +267,7 @@ static const char g_smaps_rollup[] =
 "Private_Dirty:         0 kB\n"
 "Referenced:            0 kB\n"
 "Anonymous:             0 kB\n"
+"KSM:                   0 kB\n"
 "LazyFree:              0 kB\n"
 "AnonHugePages:         0 kB\n"
 "ShmemPmdMapped:        0 kB\n"