Merge tag 'mm-hotfixes-stable-2024-01-05-11-35' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/akpm/mm Pull misc mm fixes from Andrew Morton: "12 hotfixes. Two are cc:stable and the remainder either address post-6.7 issues or aren't considered necessary for earlier kernel versions" * tag 'mm-hotfixes-stable-2024-01-05-11-35' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: mm: shrinker: use kvzalloc_node() from expand_one_shrinker_info() mailmap: add entries for Mathieu Othacehe MAINTAINERS: change vmware.com addresses to broadcom.com arch/mm/fault: fix major fault accounting when retrying under per-VMA lock mm/mglru: skip special VMAs in lru_gen_look_around() MAINTAINERS: hand over hwpoison maintainership to Miaohe Lin MAINTAINERS: remove hugetlb maintainer Mike Kravetz mm: fix unmap_mapping_range high bits shift bug mm: memcg: fix split queue list crash when large folio migration mm: fix arithmetic for max_prop_frac when setting max_ratio mm: fix arithmetic for bdi min_ratio mm: align larger anonymous mappings on THP boundaries
wafgo · Jan 5, 2024 · 95c8a35 · 95c8a35
2 parents 0d3ac66 + 7fba942
commit 95c8a35
Show file tree

Hide file tree

Showing 15 changed files with 52 additions and 19 deletions.
diff --git a/.mailmap b/.mailmap
@@ -377,7 +377,7 @@ Martin Kepplinger <[email protected]> <[email protected]>
 Martin Kepplinger <[email protected]> <[email protected]>
 Martin Kepplinger <[email protected]> <[email protected]>
 Martyna Szapar-Mudlaw <[email protected]> <[email protected]>
-Mathieu Othacehe <[email protected]>
+Mathieu Othacehe <[email protected]> <[email protected]>
 Mat Martineau <[email protected]> <[email protected]>
 Mat Martineau <[email protected]> <[email protected]>
 Matthew Wilcox <[email protected]> <[email protected]>
@@ -638,4 +638,5 @@ Wolfram Sang <[email protected]> <[email protected]>
 Wolfram Sang <[email protected]> <[email protected]>
 Yakir Yang <[email protected]> <[email protected]>
 Yusuke Goda <[email protected]>
+Zack Rusin <[email protected]> <[email protected]>
 Zhu Yanjun <[email protected]> <[email protected]>
diff --git a/CREDITS b/CREDITS
@@ -2130,6 +2130,10 @@ S: 2213 La Terrace Circle
 S: San Jose, CA 95123
 S: USA
 
+N: Mike Kravetz
+E: [email protected]
+D: Maintenance and development of the hugetlb subsystem
+
 N: Andreas S. Krebs
 E: [email protected]
 D: CYPRESS CY82C693 chipset IDE, Digital's PC-Alpha 164SX boards

diff --git a/MAINTAINERS b/MAINTAINERS
@@ -6901,8 +6901,8 @@ T:	git git://anongit.freedesktop.org/drm/drm-misc
 F:	drivers/gpu/drm/vboxvideo/
 
 DRM DRIVER FOR VMWARE VIRTUAL GPU
-M:	Zack Rusin <zackr@vmware.com>
-R:	VMware Graphics Reviewers <linux-graphics-maintainer@vmware.com>
+M:	Zack Rusin <zack.rusin@broadcom.com>
+R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	[email protected]
 S:	Supported
 T:	git git://anongit.freedesktop.org/drm/drm-misc
@@ -9767,7 +9767,6 @@ F:	Documentation/networking/device_drivers/ethernet/huawei/hinic.rst
 F:	drivers/net/ethernet/huawei/hinic/
 
 HUGETLB SUBSYSTEM
-M:	Mike Kravetz <[email protected]>
 M:	Muchun Song <[email protected]>
 L:	[email protected]
 S:	Maintained
@@ -9791,8 +9790,8 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/platform/st/sti/hva
 
 HWPOISON MEMORY FAILURE HANDLING
-M:	Naoya Horiguchi <naoya.horiguchi@nec.com>
-R:	Miaohe Lin <linmiaohe@huawei.com>
+M:	Miaohe Lin <linmiaohe@huawei.com>
+R:	Naoya Horiguchi <naoya.horiguchi@nec.com>
 L:	[email protected]
 S:	Maintained
 F:	mm/hwpoison-inject.c
@@ -23215,9 +23214,8 @@ F:	drivers/misc/vmw_vmci/
 F:	include/linux/vmw_vmci*
 
 VMWARE VMMOUSE SUBDRIVER
-M:	Zack Rusin <[email protected]>
-R:	VMware Graphics Reviewers <[email protected]>
-R:	VMware PV-Drivers Reviewers <[email protected]>
+M:	Zack Rusin <[email protected]>
+R:	Broadcom internal kernel review list <[email protected]>
 L:	[email protected]
 S:	Supported
 F:	drivers/input/mouse/vmmouse.c

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
@@ -607,6 +607,8 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		mm_flags |= FAULT_FLAG_TRIED;
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
@@ -497,6 +497,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	if (fault_signal_pending(fault, regs))
 		return user_mode(regs) ? 0 : SIGBUS;

diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
@@ -304,6 +304,8 @@ void handle_page_fault(struct pt_regs *regs)
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
@@ -337,6 +337,9 @@ static void do_exception(struct pt_regs *regs, int access)
 		return;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
+
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
@@ -1370,6 +1370,8 @@ void do_user_addr_fault(struct pt_regs *regs,
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
@@ -2823,7 +2823,7 @@ void folio_undo_large_rmappable(struct folio *folio)
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
 	if (!list_empty(&folio->_deferred_list)) {
 		ds_queue->split_queue_len--;
-		list_del(&folio->_deferred_list);
+		list_del_init(&folio->_deferred_list);
 	}
 	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
 }

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
@@ -7543,6 +7543,17 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new)
 
 	/* Transfer the charge and the css ref */
 	commit_charge(new, memcg);
+	/*
+	 * If the old folio is a large folio and is in the split queue, it needs
+	 * to be removed from the split queue now, in case getting an incorrect
+	 * split queue in destroy_large_folio() after the memcg of the old folio
+	 * is cleared.
+	 *
+	 * In addition, the old folio is about to be freed after migration, so
+	 * removing from the split queue a bit earlier seems reasonable.
+	 */
+	if (folio_test_large(old) && folio_test_large_rmappable(old))
+		folio_undo_large_rmappable(old);
 	old->memcg_data = 0;
 }
 

diff --git a/mm/memory.c b/mm/memory.c
@@ -3624,8 +3624,8 @@ EXPORT_SYMBOL_GPL(unmap_mapping_pages);
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows)
 {
-	pgoff_t hba = holebegin >> PAGE_SHIFT;
-	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT;
+	pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	/* Check for overflow. */
 	if (sizeof(holelen) > sizeof(hlen)) {

diff --git a/mm/mmap.c b/mm/mmap.c
@@ -1829,6 +1829,9 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		 */
 		pgoff = 0;
 		get_area = shmem_get_unmapped_area;
+	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+		/* Ensures that larger anonymous mappings are THP aligned. */
+		get_area = thp_get_unmapped_area;
 	}
 
 	addr = get_area(file, addr, len, pgoff, flags);

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
@@ -692,7 +692,6 @@ static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ra
 
 	if (min_ratio > 100 * BDI_RATIO_SCALE)
 		return -EINVAL;
-	min_ratio *= BDI_RATIO_SCALE;
 
 	spin_lock_bh(&bdi_lock);
 	if (min_ratio > bdi->max_ratio) {
@@ -729,7 +728,8 @@ static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ra
 		ret = -EINVAL;
 	} else {
 		bdi->max_ratio = max_ratio;
-		bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100;
+		bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) /
+						(100 * BDI_RATIO_SCALE);
 	}
 	spin_unlock_bh(&bdi_lock);
 

diff --git a/mm/shrinker.c b/mm/shrinker.c
@@ -126,7 +126,7 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size,
 		if (new_nr_max <= old->map_nr_max)
 			continue;
 
-		new = kvmalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid);
+		new = kvzalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid);
 		if (!new)
 			return -ENOMEM;
 

diff --git a/mm/vmscan.c b/mm/vmscan.c
@@ -3955,6 +3955,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	int young = 0;
 	pte_t *pte = pvmw->pte;
 	unsigned long addr = pvmw->address;
+	struct vm_area_struct *vma = pvmw->vma;
 	struct folio *folio = pfn_folio(pvmw->pfn);
 	bool can_swap = !folio_is_file_lru(folio);
 	struct mem_cgroup *memcg = folio_memcg(folio);
@@ -3969,11 +3970,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	if (spin_is_contended(pvmw->ptl))
 		return;
 
+	/* exclude special VMAs containing anon pages from COW */
+	if (vma->vm_flags & VM_SPECIAL)
+		return;
+
 	/* avoid taking the LRU lock under the PTL when possible */
 	walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL;
 
-	start = max(addr & PMD_MASK, pvmw->vma->vm_start);
-	end = min(addr | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1;
+	start = max(addr & PMD_MASK, vma->vm_start);
+	end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1;
 
 	if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
 		if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
@@ -3998,7 +4003,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		unsigned long pfn;
 		pte_t ptent = ptep_get(pte + i);
 
-		pfn = get_pte_pfn(ptent, pvmw->vma, addr);
+		pfn = get_pte_pfn(ptent, vma, addr);
 		if (pfn == -1)
 			continue;
 
@@ -4009,7 +4014,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		if (!folio)
 			continue;
 
-		if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i))
+		if (!ptep_test_and_clear_young(vma, addr, pte + i))
 			VM_WARN_ON_ONCE(true);
 
 		young++;