Merge branch 'mm-stable' of https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

2026-08-13 14:19:53 -07:00 · 2026-07-31 14:13:29 +01:00
parent 56b1d0e0dc 3ef8e3fdc8
commit f84f2c75f8
176 changed files with 4813 additions and 2427 deletions
@@ -3096,6 +3096,10 @@ N: Jens Osterkamp
 E: jens@de.ibm.com
 D: Maintainer of Spidernet network driver for Cell

+N: Kent Overstreet
+E: kent.overstreet@linux.dev
+D: Co-authored and contributed to Memory Allocation Profiling
+
 N: Gadi Oxman
 E: gadio@netvision.net.il
 D: Original author and maintainer of IDE/ATAPI floppy/tape drivers
@@ -152,15 +152,15 @@ Description:
 		compression algorithm parameters.

 What:		/sys/block/zram<id>/compressed_writeback
-Date:		Decemeber 2025
+Date:		December 2025
 Contact:	Richard Chang <richardycc@google.com>
 Description:
-		The compressed_writeback device atrribute toggles compressed
+		The compressed_writeback device attribute toggles compressed
 		writeback feature.

 What:		/sys/block/zram<id>/writeback_batch_size
 Date:		November 2025
 Contact:	Sergey Senozhatsky <senozhatsky@chromium.org>
 Description:
-		The writeback_batch_size device atrribute sets the maximum
+		The writeback_batch_size device attribute sets the maximum
 		number of in-flight writeback operations.
@@ -157,6 +157,46 @@ Description:	Writing a value to this file sets the maximum number of
 		monitoring regions of the DAMON context as the value.  Reading
 		this file returns the value.

+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/probes/nr_probes
+Date:		May 2026
+Contact:	SJ Park <sj@kernel.org>
+Description:	Writing a number 'N' to this file creates the number of
+		directories for each DAMON probe named '0' to 'N-1' under the
+		probes/ directory.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/probes/<P>/filters/nr_filters
+Date:		May 2026
+Contact:	SJ Park <sj@kernel.org>
+Description:	Writing a number 'N' to this file creates the number of
+		directories for each DAMON probe filter named '0' to 'N-1'
+		under the filters/ directory.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/probes/<P>/filters/<F>/type
+Date:		May 2026
+Contact:	SJ Park <sj@kernel.org>
+Description:	Writing to and reading from this file sets and gets the type of
+		the memory of the interest.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/probes/<P>/filters/<F>/path
+Date:		May 2026
+Contact:	SJ Park <sj@kernel.org>
+Description:	If 'memcg' is written to the 'type' file, writing to and
+		reading from this file sets and gets the path to the memory
+		cgroup of the interest.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/probes/<P>/filters/<F>/matching
+Date:		May 2026
+Contact:	SJ Park <sj@kernel.org>
+Description:	Writing 'Y' or 'N' to this file sets whether the filter is for
+		the memory of the 'type', or all except the 'type'.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/probes/<P>/filters/<F>/allow
+Date:		May 2026
+Contact:	SJ Park <sj@kernel.org>
+Description:	Writing 'Y' or 'N' to this file sets whether to allow or reject
+		hitting the probe for the memory that satisfies the 'type' and
+		the 'matching' of the directory.
+
 What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/targets/nr_targets
 Date:		Mar 2022
 Contact:	SJ Park <sj@kernel.org>
@@ -284,7 +284,7 @@ take action.
 ==>
    Unless this feature is enabled by writing "1" to the special file
    /dev/cpuset/memory_pressure_enabled, the hook in the rebalance
-    code of __alloc_pages() for this metric reduces to simply noticing
+    code of the page allocator for this metric reduces to simply noticing
    that the cpuset_memory_pressure_enabled flag is zero.  So only
    systems that enable this feature will compute the metric.

@@ -246,7 +246,7 @@ writing to and reading from the files.
 Under ``nr_regions`` directory, two files for the lower-bound and upper-bound
 of DAMON's monitoring regions (``min`` and ``max``, respectively), which
 controls the monitoring overhead, exist.  You can set and get the values by
-writing to and rading from the files.
+writing to and reading from the files.

 For more details about the intervals and monitoring regions range, please refer
 to the Design document (:doc:`/mm/damon/design`).
@@ -264,7 +264,7 @@ Please refer to  the :ref:`design document of the feature
 <damon_design_monitoring_intervals_autotuning>` for the internal of the tuning
 mechanism.  Reading and writing the four files under ``intervals_goal``
 directory shows and updates the tuning parameters that described in the
-:ref:design doc <damon_design_monitoring_intervals_autotuning>` with the same
+:ref:`design doc <damon_design_monitoring_intervals_autotuning>` with the same
 names.  The tuning starts with the user-set ``sample_us`` and ``aggr_us``.  The
 tuning-applied current values of the two intervals can be read from the
 ``sample_us`` and ``aggr_us`` files after writing ``update_tuned_intervals`` to
@@ -377,7 +377,7 @@ schemes/<N>/
 In each scheme directory, nine directories (``access_pattern``, ``quotas``,
 ``watermarks``, ``core_filters``, ``ops_filters``, ``filters``, ``dests``,
 ``stats``, and ``tried_regions``) and three files (``action``, ``target_nid``
-and ``apply_interval``) exist.
+and ``apply_interval_us``) exist.

 The ``action`` file is for setting and getting the scheme's :ref:`action
 <damon_design_damos_action>`.  The keywords that can be written to and read
@@ -743,7 +743,7 @@ counter).  Finally the tenth field (``X``) shows the ``age`` of the region
 (refer to :ref:`design <damon_design_age_tracking>` for more details of the
 counter).

-If the event was ``damon:damos_beofre_apply``, the ``perf script`` output would
+If the event was ``damon:damos_before_apply``, the ``perf script`` output would
 be somewhat like below::

    kdamond.0 47293 [000] 80801.060214: damon:damos_before_apply: ctx_idx=0 scheme_idx=0 target_idx=0 nr_regions=11 121932607488-135128711168: 0 136
@@ -761,7 +761,7 @@ compact_fail
 	but failed.

 It is possible to establish how long the stalls were using the function
-tracer to record how long was spent in __alloc_pages() and
+tracer to record how long was spent in the page allocator and
 using the mm_page_alloc tracepoint to identify which allocations were
 for huge pages.

@@ -73,6 +73,7 @@ Readahead
 Writeback
 ---------

+.. kernel-doc:: include/linux/writeback.h
 .. kernel-doc:: mm/page-writeback.c
   :export:

@@ -90,6 +90,9 @@ Reference counting
 .. kernel-doc:: lib/refcount.c
   :export:

+.. kernel-doc:: include/linux/percpu-refcount.h
+.. kernel-doc:: lib/percpu-refcount.c
+
 Atomics
 -------

@@ -86,7 +86,7 @@ To know how user-space can do the configuration via :ref:`DAMON sysfs interface
 documentation.


- .. _damon_design_vaddr_target_regions_construction:
+.. _damon_design_vaddr_target_regions_construction:

 VMA-based Target Address Range Construction
 -------------------------------------------
@@ -686,9 +686,11 @@ mechanism tries to make ``current_value`` of ``target_metric`` be same to
  (1/10,000).
 - ``inactive_mem_bp``: Inactive to active + inactive (LRU) memory size ratio in
  bp (1/10,000).
+- ``node_eligible_mem_bp``: Scheme target access pattern-eligible memory ratio
+  of a node in bp (1/10,000).

-``nid`` is optionally required for only ``node_mem_used_bp``,
-``node_mem_free_bp``, ``node_memcg_used_bp`` and ``node_memcg_free_bp`` to
+``nid`` is optionally required for ``node_mem_used_bp``, ``node_mem_free_bp``,
+``node_memcg_used_bp``, ``node_memcg_free_bp`` and ``node_eligible_mem_bp`` to
 point the specific NUMA node.

 ``path`` is optionally required for only ``node_memcg_used_bp`` and
@@ -930,11 +932,11 @@ control parameters for the usage would also need to be optimized for the
 purpose.

 To support such cases, yet more DAMON API user kernel modules that provide more
-simple and optimized user space interfaces are available.  Currently, two
-modules for proactive reclamation and LRU lists manipulation are provided.  For
-more detail, please read the usage documents for those
-(:doc:`/admin-guide/mm/damon/stat`, :doc:`/admin-guide/mm/damon/reclaim` and
-:doc:`/admin-guide/mm/damon/lru_sort`).
+simple and optimized user space interfaces are available.  Currently, three
+modules for access monitoring statistics, proactive reclamation, and LRU lists
+manipulation are provided.  For more detail, please read the usage documents for
+those (:doc:`/admin-guide/mm/damon/stat`, :doc:`/admin-guide/mm/damon/reclaim`
+and :doc:`/admin-guide/mm/damon/lru_sort`).

 .. _damon_design_special_purpose_modules_exclusivity:

@@ -65,7 +65,15 @@ un-tracking state.
 Usage
 =====

-1) Build user-space helper::
+1) Build user-space helpers:
+::
+
+   To filter page_owner output:
+
+	cd tools/mm
+	make page_owner_filter
+
+   To sort and analyze page_owner output:

 	cd tools/mm
 	make page_owner_sort
@@ -74,7 +82,11 @@ Usage

 3) Do the job that you want to debug.

-4) Analyze information from page owner::
+4) (Optional) Filter page_owner output::
+
+	./page_owner_filter -m handle -n 0,1,2 > filtered_page_owner.txt
+
+5) Analyze information from page owner::

 	cat /sys/kernel/debug/page_owner_stacks/show_stacks > stacks.txt
 	cat stacks.txt
@@ -263,3 +275,65 @@ STANDARD FORMAT SPECIFIERS
 	f		free		whether the page has been released or not
 	st		stacktrace	stack trace of the page allocation
 	ator		allocator	memory allocator for pages
+
+Filtering page_owner output
+============================
+
+page_owner supports filtering output at the kernel level before reading,
+which reduces the amount of data that needs to be processed in userspace.
+
+The page_owner_filter tool provides a convenient interface for this filtering
+capability. It supports two types of filters:
+
+1. **print_mode filter**: Control what information is printed for each page
+	- ``stack``: Print full stack traces (default, compatible with existing usage)
+	- ``handle``: Print only stack handle numbers (much faster, smaller output)
+	- ``stack_handle``: Print both stack traces and handle numbers
+
+	The ``handle`` mode uses numeric identifiers instead of full stack traces.
+	The mapping from handles to actual stack traces can be obtained via the
+	show_stacks_handles interface.
+
+2. **NUMA node filter**: Filter pages by NUMA node ID
+	- Supports single node: ``-n 0``
+	- Multiple nodes: ``-n 0,1,2``
+	- Ranges: ``-n 0-3``
+	- Mixed format: ``-n 0,2-3,5``
+
+Usage examples::
+
+	# Filter by print mode
+	./page_owner_filter -m handle
+	./page_owner_filter -m stack_handle
+
+	# Filter by NUMA node
+	./page_owner_filter -n 0
+	./page_owner_filter -n 0-3
+
+	# Combined filters
+	./page_owner_filter -m stack -n 0,1,2
+	./page_owner_filter -m handle -n 0,2-3
+
+	# Save to file
+	./page_owner_filter -m handle -o filtered_output.txt
+
+The handle mode is particularly useful for monitoring and performance-critical
+scenarios as it dramatically reduces output size. Testing shows handle mode can
+reduce output size by ~66% (84MB vs 244MB) and improve read performance by ~4.4x
+compared to full stack output.
+
+The NUMA node filter is useful for NUMA-aware memory allocation analysis and debugging.
+
+Behind the scenes, page_owner_filter opens /sys/kernel/debug/page_owner and
+writes filter commands before reading the filtered output. The filtering uses
+per-file-descriptor state, allowing each open() to have independent filter settings.
+
+Each file descriptor maintains its own filter state, so you can have multiple
+independent filtering operations running concurrently. For example, in different
+terminals you can run different filters simultaneously::
+
+	# Terminal 1: Filter node 0
+	./page_owner_filter -n 0 > node0_output.txt
+
+	# Terminal 2: Filter node 1 (runs concurrently)
+	./page_owner_filter -n 1 > node1_output.txt
@@ -16881,17 +16881,6 @@ F:	mm/mm_init.c
 F:	mm/rodata_test.c
 F:	tools/testing/memblock/

-MEMORY ALLOCATION PROFILING
-M:	Suren Baghdasaryan <surenb@google.com>
-M:	Kent Overstreet <kent.overstreet@linux.dev>
-R:	Hao Ge <hao.ge@linux.dev>
-L:	linux-mm@kvack.org
-S:	Maintained
-F:	Documentation/mm/allocation-profiling.rst
-F:	include/linux/alloc_tag.h
-F:	include/linux/pgalloc_tag.h
-F:	lib/alloc_tag.c
-
 MEMORY CONTROLLER DRIVERS
 M:	Krzysztof Kozlowski <krzk@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -16936,6 +16925,16 @@ T:	quilt git://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new
 F:	mm/
 F:	tools/mm/

+MEMORY MANAGEMENT - ALLOCATION PROFILING (ALLOC TAG)
+M:	Suren Baghdasaryan <surenb@google.com>
+R:	Hao Ge <hao.ge@linux.dev>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	Documentation/mm/allocation-profiling.rst
+F:	include/linux/alloc_tag.h
+F:	include/linux/pgalloc_tag.h
+F:	mm/alloc_tag.c
+
 MEMORY MANAGEMENT - BALLOON
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
@@ -17168,6 +17167,7 @@ F:	mm/debug_page_alloc.c
 F:	mm/debug_page_ref.c
 F:	mm/fail_page_alloc.c
 F:	mm/page_alloc.c
+F:	mm/page_alloc.h
 F:	mm/page_ext.c
 F:	mm/page_frag_cache.c
 F:	mm/page_isolation.c
@@ -29780,8 +29780,11 @@ M:	Minchan Kim <minchan@kernel.org>
 M:	Sergey Senozhatsky <senozhatsky@chromium.org>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
+F:	Documentation/ABI/testing/sysfs-block-zram
+F:	Documentation/ABI/testing/sysfs-class-zram
 F:	Documentation/admin-guide/blockdev/zram.rst
 F:	drivers/block/zram/
+F:	tools/testing/selftests/zram/

 ZS DECSTATION Z85C30 SERIAL DRIVER
 M:	"Maciej W. Rozycki" <macro@orcam.me.uk>
@@ -17,7 +17,7 @@ config ARM64
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
-	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+	select ARCH_HAS_PMD_SOFTLEAVES if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_CC_PLATFORM
 	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
@@ -1534,10 +1534,10 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })

-#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+#ifdef CONFIG_ARCH_HAS_PMD_SOFTLEAVES
 #define __pmd_to_swp_entry(pmd)		((swp_entry_t) { pmd_val(pmd) })
 #define __swp_entry_to_pmd(swp)		__pmd((swp).val)
-#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
+#endif /* CONFIG_ARCH_HAS_PMD_SOFTLEAVES */

 /*
 * Ensure that there are not more swap files than can be encoded in the kernel
@@ -42,7 +42,12 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 * Use cache_wbinv_all() here and need to be improved in future.
 */
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
-#define flush_cache_vmap(start, end)		cache_wbinv_all()
+
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	cache_wbinv_all();
+}
+
 #define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		cache_wbinv_all()

@@ -12,7 +12,7 @@ config LOONGARCH
 	select ARCH_NEEDS_DEFER_KASAN
 	select ARCH_DISABLE_KASAN_INLINE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
-	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+	select ARCH_HAS_PMD_SOFTLEAVES if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_CURRENT_STACK_POINTER
@@ -1060,7 +1060,7 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_mksoft_dirty(pmd)  pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)))
 #define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)))

-#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+#ifdef CONFIG_ARCH_HAS_PMD_SOFTLEAVES
 #define pmd_swp_mksoft_dirty(pmd)	pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd)))
 #define pmd_swp_soft_dirty(pmd)		pte_swp_soft_dirty(pmd_pte(pmd))
 #define pmd_swp_clear_soft_dirty(pmd)	pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd)))
@@ -1314,7 +1314,6 @@ int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 	 * covering out both edges.
 	 */
 	unsigned long addr;
-	unsigned long addr_pfn = start_pfn;
 	unsigned long next;
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -1335,7 +1334,6 @@ int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,

 		if (pmd_leaf(READ_ONCE(*pmd))) {
 			/* existing huge mapping. Skip the range */
-			addr_pfn += (PMD_SIZE >> PAGE_SHIFT);
 			next = pmd_addr_end(addr, end);
 			continue;
 		}
@@ -1348,11 +1346,11 @@ int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 			 * page whose VMEMMAP_RESERVE_NR pages were mapped and
 			 * this request fall in those pages.
 			 */
-			addr_pfn += 1;
 			next = addr + PAGE_SIZE;
 			continue;
 		} else {
 			unsigned long nr_pages = pgmap_vmemmap_nr(pgmap);
+			unsigned long addr_pfn = page_to_pfn((struct page *)addr);
 			unsigned long pfn_offset = addr_pfn - ALIGN_DOWN(addr_pfn, nr_pages);
 			pte_t *tail_page_pte;

@@ -1376,7 +1374,6 @@ int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 				if (!pte)
 					return -ENOMEM;

-				addr_pfn += 2;
 				next = addr + 2 * PAGE_SIZE;
 				continue;
 			}
@@ -1392,7 +1389,6 @@ int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 					return -ENOMEM;
 				vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);

-				addr_pfn += 1;
 				next = addr + PAGE_SIZE;
 				continue;
 			}
@@ -1402,7 +1398,6 @@ int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
 				return -ENOMEM;
 			vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);

-			addr_pfn += 1;
 			next = addr + PAGE_SIZE;
 			continue;
 		}
@@ -104,17 +104,14 @@ void __init pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_p
 	}
 }

-static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate)
+static __init void *pseries_alloc_bootmem_huge_page(struct hstate *hstate)
 {
-	struct huge_bootmem_page *m;
+	void *m;
 	if (nr_gpages == 0)
-		return 0;
+		return NULL;
 	m = phys_to_virt(gpage_freearray[--nr_gpages]);
 	gpage_freearray[nr_gpages] = 0;
-	list_add(&m->list, &huge_boot_pages[0]);
-	m->hstate = hstate;
-	m->flags = 0;
-	return 1;
+	return m;
 }

 bool __init hugetlb_node_alloc_supported(void)
@@ -124,7 +121,7 @@ bool __init hugetlb_node_alloc_supported(void)
 #endif


-int __init alloc_bootmem_huge_page(struct hstate *h, int nid)
+void *__init arch_alloc_bootmem_huge_page(struct hstate *h, int nid)
 {

 #ifdef CONFIG_PPC_BOOK3S_64
@@ -112,7 +112,7 @@ config PPC_THP
       depends on PPC_RADIX_MMU || (PPC_64S_HASH_MMU && PAGE_SIZE_64KB)
       select HAVE_ARCH_TRANSPARENT_HUGEPAGE
       select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-       select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+       select ARCH_HAS_PMD_SOFTLEAVES if TRANSPARENT_HUGEPAGE

 choice
 	prompt "CPU selection"
@@ -22,7 +22,7 @@ config RISCV
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM_VMEMMAP
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
-	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+	select ARCH_HAS_PMD_SOFTLEAVES if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_BINFMT_FLAT
 	select ARCH_HAS_CC_CAN_LINK
 	select ARCH_HAS_CURRENT_STACK_POINTER
--- a/Show More
+++ b/Show More