diff options
148 files changed, 4672 insertions, 2076 deletions
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon index b35649a46a2f..bfa5b8288d8d 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-damon +++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -25,12 +25,14 @@ Description: Writing 'on' or 'off' to this file makes the kdamond starts or stops, respectively. Reading the file returns the keywords based on the current status. Writing 'commit' to this file makes the kdamond reads the user inputs in the sysfs files - except 'state' again. Writing 'update_schemes_stats' to the - file updates contents of schemes stats files of the kdamond. - Writing 'update_schemes_tried_regions' to the file updates - contents of 'tried_regions' directory of every scheme directory - of this kdamond. Writing 'update_schemes_tried_bytes' to the - file updates only '.../tried_regions/total_bytes' files of this + except 'state' again. Writing 'commit_schemes_quota_goals' to + this file makes the kdamond reads the quota goal files again. + Writing 'update_schemes_stats' to the file updates contents of + schemes stats files of the kdamond. Writing + 'update_schemes_tried_regions' to the file updates contents of + 'tried_regions' directory of every scheme directory of this + kdamond. Writing 'update_schemes_tried_bytes' to the file + updates only '.../tried_regions/total_bytes' files of this kdamond. Writing 'clear_schemes_tried_regions' to the file removes contents of the 'tried_regions' directory. @@ -212,6 +214,25 @@ Contact: SeongJae Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the quotas charge reset interval of the scheme in milliseconds. +What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/nr_goals +Date: Nov 2023 +Contact: SeongJae Park <sj@kernel.org> +Description: Writing a number 'N' to this file creates the number of + directories for setting automatic tuning of the scheme's + aggressiveness named '0' to 'N-1' under the goals/ directory. + +What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/target_value +Date: Nov 2023 +Contact: SeongJae Park <sj@kernel.org> +Description: Writing to and reading from this file sets and gets the target + value of the goal metric. + +What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/goals/<G>/current_value +Date: Nov 2023 +Contact: SeongJae Park <sj@kernel.org> +Description: Writing to and reading from this file sets and gets the current + value of the goal metric. + What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/quotas/weights/sz_permil Date: Mar 2022 Contact: SeongJae Park <sj@kernel.org> diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst index e4551579cb12..ee2b0030d416 100644 --- a/Documentation/admin-guide/blockdev/zram.rst +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -328,7 +328,7 @@ as idle:: From now on, any pages on zram are idle pages. The idle mark will be removed until someone requests access of the block. IOW, unless there is access request, those pages are still idle pages. -Additionally, when CONFIG_ZRAM_MEMORY_TRACKING is enabled pages can be +Additionally, when CONFIG_ZRAM_TRACK_ENTRY_ACTIME is enabled pages can be marked as idle based on how long (in seconds) it's been since they were last accessed:: diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index da94feb97ed1..ff9f62e65722 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -83,6 +83,8 @@ comma (","). :: │ │ │ │ │ │ │ │ age/min,max │ │ │ │ │ │ │ quotas/ms,bytes,reset_interval_ms │ │ │ │ │ │ │ │ weights/sz_permil,nr_accesses_permil,age_permil + │ │ │ │ │ │ │ │ goals/nr_goals + │ │ │ │ │ │ │ │ │ 0/target_value,current_value │ │ │ │ │ │ │ watermarks/metric,interval_us,high,mid,low │ │ │ │ │ │ │ filters/nr_filters │ │ │ │ │ │ │ │ 0/type,matching,memcg_id @@ -113,6 +115,8 @@ details) exists. In the beginning, this directory has only one file, child directories named ``0`` to ``N-1``. Each directory represents each kdamond. +.. _sysfs_kdamond: + kdamonds/<N>/ ------------- @@ -121,11 +125,18 @@ In each kdamond directory, two files (``state`` and ``pid``) and one directory Reading ``state`` returns ``on`` if the kdamond is currently running, or ``off`` if it is not running. Writing ``on`` or ``off`` makes the kdamond be -in the state. Writing ``commit`` to the ``state`` file makes kdamond reads the +in the state. + +Writing ``commit`` to the ``state`` file makes kdamond reads the user inputs in the sysfs files except ``state`` file again. Writing -``update_schemes_stats`` to ``state`` file updates the contents of stats files -for each DAMON-based operation scheme of the kdamond. For details of the -stats, please refer to :ref:`stats section <sysfs_schemes_stats>`. +``commit_schemes_quota_goals`` to the ``state`` file makes kdamond reads the +DAMON-based operation schemes' :ref:`quota goals <sysfs_schemes_quota_goals>` +of the kdamond. + +Writing ``update_schemes_stats`` to ``state`` file updates the +contents of stats files for each DAMON-based operation scheme of the kdamond. +For details of the stats, please refer to :ref:`stats section +<sysfs_schemes_stats>`. Writing ``update_schemes_tried_regions`` to ``state`` file updates the DAMON-based operation scheme action tried regions directory for each @@ -319,8 +330,7 @@ The directory for the :ref:`quotas <damon_design_damos_quotas>` of the given DAMON-based operation scheme. Under ``quotas`` directory, three files (``ms``, ``bytes``, -``reset_interval_ms``) and one directory (``weights``) having three files -(``sz_permil``, ``nr_accesses_permil``, and ``age_permil``) in it exist. +``reset_interval_ms``) and two directores (``weights`` and ``goals``) exist. You can set the ``time quota`` in milliseconds, ``size quota`` in bytes, and ``reset interval`` in milliseconds by writing the values to the three files, @@ -330,11 +340,35 @@ apply the action to only up to ``bytes`` bytes of memory regions within the ``reset_interval_ms``. Setting both ``ms`` and ``bytes`` zero disables the quota limits. -You can also set the :ref:`prioritization weights +Under ``weights`` directory, three files (``sz_permil``, +``nr_accesses_permil``, and ``age_permil``) exist. +You can set the :ref:`prioritization weights <damon_design_damos_quotas_prioritization>` for size, access frequency, and age in per-thousand unit by writing the values to the three files under the ``weights`` directory. +.. _sysfs_schemes_quota_goals: + +schemes/<N>/quotas/goals/ +------------------------- + +The directory for the :ref:`automatic quota tuning goals +<damon_design_damos_quotas_auto_tuning>` of the given DAMON-based operation +scheme. + +In the beginning, this directory has only one file, ``nr_goals``. Writing a +number (``N``) to the file creates the number of child directories named ``0`` +to ``N-1``. Each directory represents each goal and current achievement. +Among the multiple feedback, the best one is used. + +Each goal directory contains two files, namely ``target_value`` and +``current_value``. Users can set and get any number to those files to set the +feedback. User space main workload's latency or throughput, system metrics +like free memory ratio or memory pressure stall time (PSI) could be example +metrics for the values. Note that users should write +``commit_schemes_quota_goals`` to the ``state`` file of the :ref:`kdamond +directory <sysfs_kdamond>` to pass the feedback to DAMON. + schemes/<N>/watermarks/ ----------------------- diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index fe17cf210426..f5f065c67615 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -253,6 +253,7 @@ Following flags about pages are currently supported: - ``PAGE_IS_SWAPPED`` - Page is in swapped - ``PAGE_IS_PFNZERO`` - Page has zero PFN - ``PAGE_IS_HUGE`` - Page is THP or Hugetlb backed +- ``PAGE_IS_SOFT_DIRTY`` - Page is soft-dirty The ``struct pm_scan_arg`` is used as the argument of the IOCTL. diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst index 45b98390e938..62fc244ec702 100644 --- a/Documentation/admin-guide/mm/zswap.rst +++ b/Documentation/admin-guide/mm/zswap.rst @@ -153,6 +153,16 @@ attribute, e. g.:: Setting this parameter to 100 will disable the hysteresis. +When there is a sizable amount of cold memory residing in the zswap pool, it +can be advantageous to proactively write these cold pages to swap and reclaim +the memory for other use cases. By default, the zswap shrinker is disabled. +User can enable it as follows: + + echo Y > /sys/module/zswap/parameters/shrinker_enabled + +This can be enabled at the boot time if ``CONFIG_ZSWAP_SHRINKER_DEFAULT_ON`` is +selected. + A debugfs interface is provided for various statistic about pool size, number of pages stored, same-value filled pages and various counters for the reasons pages are rejected. diff --git a/Documentation/core-api/maple_tree.rst b/Documentation/core-api/maple_tree.rst index 96f3d5f076b5..ccdd1615cf97 100644 --- a/Documentation/core-api/maple_tree.rst +++ b/Documentation/core-api/maple_tree.rst @@ -81,6 +81,9 @@ section. Sometimes it is necessary to ensure the next call to store to a maple tree does not allocate memory, please see :ref:`maple-tree-advanced-api` for this use case. +You can use mtree_dup() to duplicate an entire maple tree. It is a more +efficient way than inserting all elements one by one into a new tree. + Finally, you can remove all entries from a maple tree by calling mtree_destroy(). If the maple tree entries are pointers, you may wish to free the entries first. @@ -112,6 +115,7 @@ Takes ma_lock internally: * mtree_insert() * mtree_insert_range() * mtree_erase() + * mtree_dup() * mtree_destroy() * mt_set_in_rcu() * mt_clear_in_rcu() diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 7be2900806c8..421daf837940 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -261,7 +261,7 @@ prototypes:: struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate)(struct folio *, size_t from, size_t count); - int (*error_remove_page)(struct address_space *, struct page *); + int (*error_remove_folio)(struct address_space *, struct folio *); int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span) int (*swap_deactivate)(struct file *); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); @@ -287,7 +287,7 @@ direct_IO: migrate_folio: yes (both) launder_folio: yes is_partially_uptodate: yes -error_remove_page: yes +error_remove_folio: yes swap_activate: no swap_deactivate: no swap_rw: yes, unlocks diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 99acc2e98673..dd99ce5912d8 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -823,7 +823,7 @@ cache in your filesystem. The following members are defined: bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback)(struct folio *, bool *, bool *); - int (*error_remove_page) (struct mapping *mapping, struct page *page); + int (*error_remove_folio)(struct mapping *mapping, struct folio *); int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span) int (*swap_deactivate)(struct file *); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); @@ -1034,8 +1034,8 @@ cache in your filesystem. The following members are defined: VM if a folio should be treated as dirty or writeback for the purposes of stalling. -``error_remove_page`` - normally set to generic_error_remove_page if truncation is ok +``error_remove_folio`` + normally set to generic_error_remove_folio if truncation is ok for this address space. Used for memory failure handling. Setting this implies you deal with pages going away under you, unless you have them locked or reference counts increased. diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst index c82e3ee20e51..2466d3363af7 100644 --- a/Documentation/mm/arch_pgtable_helpers.rst +++ b/Documentation/mm/arch_pgtable_helpers.rst @@ -18,8 +18,6 @@ PTE Page Table Helpers +---------------------------+--------------------------------------------------+ | pte_same | Tests whether both PTE entries are the same | +---------------------------+--------------------------------------------------+ -| pte_bad | Tests a non-table mapped PTE | -+---------------------------+--------------------------------------------------+ | pte_present | Tests a valid mapped PTE | +---------------------------+--------------------------------------------------+ | pte_young | Tests a young PTE | diff --git a/Documentation/mm/damon/design.rst b/Documentation/mm/damon/design.rst index 1f7e0586b5fa..8b4a49ac057d 100644 --- a/Documentation/mm/damon/design.rst +++ b/Documentation/mm/damon/design.rst @@ -346,6 +346,19 @@ the weight will be respected are up to the underlying prioritization mechanism implementation. +.. _damon_design_damos_quotas_auto_tuning: + +Aim-oriented Feedback-driven Auto-tuning +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Automatic feedback-driven quota tuning. Instead of setting the absolute quota +value, users can repeatedly provide numbers representing how much of their goal +for the scheme is achieved as feedback. DAMOS then automatically tunes the +aggressiveness (the quota) of the corresponding scheme. For example, if DAMOS +is under achieving the goal, DAMOS automatically increases the quota. If DAMOS +is over achieving the goal, it decreases the quota. + + .. _damon_design_damos_watermarks: Watermarks diff --git a/MAINTAINERS b/MAINTAINERS index 5c9d3d854671..6f5d6962d26d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5339,6 +5339,7 @@ L: linux-mm@kvack.org S: Maintained F: mm/memcontrol.c F: mm/swap_cgroup.c +F: samples/cgroup/* F: tools/testing/selftests/cgroup/memcg_protection.m F: tools/testing/selftests/cgroup/test_hugetlb_memcg.c F: tools/testing/selftests/cgroup/test_kmem.c diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index 6e65ff12d5c7..8fe21f868f72 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -226,32 +226,6 @@ static void __init node_mem_init(unsigned int node) #ifdef CONFIG_ACPI_NUMA -/* - * Sanity check to catch more bad NUMA configurations (they are amazingly - * common). Make sure the nodes cover all memory. - */ -static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) -{ - int i; - u64 numaram, biosram; - - numaram = 0; - for (i = 0; i < mi->nr_blks; i++) { - u64 s = mi->blk[i].start >> PAGE_SHIFT; - u64 e = mi->blk[i].end >> PAGE_SHIFT; - - numaram += e - s; - numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); - if ((s64)numaram < 0) - numaram = 0; - } - max_pfn = max_low_pfn; - biosram = max_pfn - absent_pages_in_range(0, max_pfn); - - BUG_ON((s64)(biosram - numaram) >= (1 << (20 - PAGE_SHIFT))); - return true; -} - static void __init add_node_intersection(u32 node, u64 start, u64 size, u32 type) { static unsigned long num_physpages; @@ -396,7 +370,7 @@ int __init init_numa_memory(void) return -EINVAL; init_node_memblock(); - if (numa_meminfo_cover_memory(&numa_meminfo) == false) + if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; for_each_node_mask(node, node_possible_map) { diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index b29ceb19e46e..adc497b93f03 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -450,37 +450,6 @@ int __node_distance(int from, int to) EXPORT_SYMBOL(__node_distance); /* - * Sanity check to catch more bad NUMA configurations (they are amazingly - * common). Make sure the nodes cover all memory. - */ -static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) -{ - u64 numaram, e820ram; - int i; - - numaram = 0; - for (i = 0; i < mi->nr_blks; i++) { - u64 s = mi->blk[i].start >> PAGE_SHIFT; - u64 e = mi->blk[i].end >> PAGE_SHIFT; - numaram += e - s; - numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); - if ((s64)numaram < 0) - numaram = 0; - } - - e820ram = max_pfn - absent_pages_in_range(0, max_pfn); - - /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ - if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { - printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n", - (numaram << PAGE_SHIFT) >> 20, - (e820ram << PAGE_SHIFT) >> 20); - return false; - } - return true; -} - -/* * Mark all currently memblock-reserved physical memory (which covers the * kernel's own memory ranges) as hot-unswappable. */ @@ -585,7 +554,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) return -EINVAL; } } - if (!numa_meminfo_cover_memory(mi)) + + if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; /* Finally register nodes. */ diff --git a/block/fops.c b/block/fops.c index 0abaac705daf..0bdad1e8d514 100644 --- a/block/fops.c +++ b/block/fops.c @@ -500,7 +500,7 @@ const struct address_space_operations def_blk_aops = { .readahead = blkdev_readahead, .writepages = blkdev_writepages, .is_partially_uptodate = iomap_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, .migrate_folio = filemap_migrate_folio, }; #endif /* CONFIG_BUFFER_HEAD */ diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 138f6d43d13b..f69d30c9f50f 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -234,7 +234,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, if (page->page_ptr) { trace_binder_alloc_lru_start(alloc, index); - on_lru = list_lru_del(&binder_alloc_lru, &page->lru); + on_lru = list_lru_del_obj(&binder_alloc_lru, &page->lru); WARN_ON(!on_lru); trace_binder_alloc_lru_end(alloc, index); @@ -285,7 +285,7 @@ free_range: trace_binder_free_lru_start(alloc, index); - ret = list_lru_add(&binder_alloc_lru, &page->lru); + ret = list_lru_add_obj(&binder_alloc_lru, &page->lru); WARN_ON(!ret); trace_binder_free_lru_end(alloc, index); @@ -848,7 +848,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) if (!alloc->pages[i].page_ptr) continue; - on_lru = list_lru_del(&binder_alloc_lru, + on_lru = list_lru_del_obj(&binder_alloc_lru, &alloc->pages[i].lru); page_addr = alloc->buffer + i * PAGE_SIZE; binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, @@ -1287,4 +1287,3 @@ int binder_alloc_copy_from_buffer(struct binder_alloc *alloc, return binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset, dest, bytes); } - diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index 0386b7da02aa..7b29cce60ab2 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -59,8 +59,8 @@ config ZRAM_WRITEBACK bool "Write back incompressible or idle page to backing device" depends on ZRAM help - With incompressible page, there is no memory saving to keep it - in memory. Instead, write it out to backing device. + This lets zram entries (incompressible or idle pages) be written + back to a backing device, helping save memory. For this feature, admin should set up backing device via /sys/block/zramX/backing_dev. @@ -69,9 +69,18 @@ config ZRAM_WRITEBACK See Documentation/admin-guide/blockdev/zram.rst for more information. +config ZRAM_TRACK_ENTRY_ACTIME + bool "Track access time of zram entries" + depends on ZRAM + help + With this feature zram tracks access time of every stored + entry (page), which can be used for a more fine grained IDLE + pages writeback. + config ZRAM_MEMORY_TRACKING bool "Track zRam block status" depends on ZRAM && DEBUG_FS + select ZRAM_TRACK_ENTRY_ACTIME help With this feature, admin can track the state of allocated blocks of zRAM. Admin could see the information via @@ -86,4 +95,4 @@ config ZRAM_MULTI_COMP This will enable multi-compression streams, so that ZRAM can re-compress pages using a potentially slower but more effective compression algorithm. Note, that IDLE page recompression - requires ZRAM_MEMORY_TRACKING. + requires ZRAM_TRACK_ENTRY_ACTIME. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d77d3664ca08..2b1d82473be8 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -174,6 +174,14 @@ static inline u32 zram_get_priority(struct zram *zram, u32 index) return prio & ZRAM_COMP_PRIORITY_MASK; } +static void zram_accessed(struct zram *zram, u32 index) +{ + zram_clear_flag(zram, index, ZRAM_IDLE); +#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME + zram->table[index].ac_time = ktime_get_boottime(); +#endif +} + static inline void update_used_max(struct zram *zram, const unsigned long pages) { @@ -293,8 +301,9 @@ static void mark_idle(struct zram *zram, ktime_t cutoff) zram_slot_lock(zram, index); if (zram_allocated(zram, index) && !zram_test_flag(zram, index, ZRAM_UNDER_WB)) { -#ifdef CONFIG_ZRAM_MEMORY_TRACKING - is_idle = !cutoff || ktime_after(cutoff, zram->table[index].ac_time); +#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME + is_idle = !cutoff || ktime_after(cutoff, + zram->table[index].ac_time); #endif if (is_idle) zram_set_flag(zram, index, ZRAM_IDLE); @@ -317,7 +326,7 @@ static ssize_t idle_store(struct device *dev, */ u64 age_sec; - if (IS_ENABLED(CONFIG_ZRAM_MEMORY_TRACKING) && !kstrtoull(buf, 0, &age_sec)) + if (IS_ENABLED(CONFIG_ZRAM_TRACK_ENTRY_ACTIME) && !kstrtoull(buf, 0, &age_sec)) cutoff_time = ktime_sub(ktime_get_boottime(), ns_to_ktime(age_sec * NSEC_PER_SEC)); else @@ -841,12 +850,6 @@ static void zram_debugfs_destroy(void) debugfs_remove_recursive(zram_debugfs_root); } -static void zram_accessed(struct zram *zram, u32 index) -{ - zram_clear_flag(zram, index, ZRAM_IDLE); - zram->table[index].ac_time = ktime_get_boottime(); -} - static ssize_t read_block_state(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -930,10 +933,6 @@ static void zram_debugfs_unregister(struct zram *zram) #else static void zram_debugfs_create(void) {}; static void zram_debugfs_destroy(void) {}; -static void zram_accessed(struct zram *zram, u32 index) -{ - zram_clear_flag(zram, index, ZRAM_IDLE); -}; static void zram_debugfs_register(struct zram *zram) {}; static void zram_debugfs_unregister(struct zram *zram) {}; #endif @@ -1254,7 +1253,7 @@ static void zram_free_page(struct zram *zram, size_t index) { unsigned long handle; -#ifdef CONFIG_ZRAM_MEMORY_TRACKING +#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME zram->table[index].ac_time = 0; #endif if (zram_test_flag(zram, index, ZRAM_IDLE)) @@ -1322,9 +1321,9 @@ static int zram_read_from_zspool(struct zram *zram, struct page *page, void *mem; value = handle ? zram_get_element(zram, index) : 0; - mem = kmap_atomic(page); + mem = kmap_local_page(page); zram_fill_page(mem, PAGE_SIZE, value); - kunmap_atomic(mem); + kunmap_local(mem); return 0; } @@ -1337,14 +1336,14 @@ static int zram_read_from_zspool(struct zram *zram, struct page *page, src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); if (size == PAGE_SIZE) { - dst = kmap_atomic(page); + dst = kmap_local_page(page); memcpy(dst, src, PAGE_SIZE); - kunmap_atomic(dst); + kunmap_local(dst); ret = 0; } else { - dst = kmap_atomic(page); + dst = kmap_local_page(page); ret = zcomp_decompress(zstrm, src, size, dst); - kunmap_atomic(dst); + kunmap_local(dst); zcomp_stream_put(zram->comps[prio]); } zs_unmap_object(zram->mem_pool, handle); @@ -1417,21 +1416,21 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) unsigned long element = 0; enum zram_pageflags flags = 0; - mem = kmap_atomic(page); + mem = kmap_local_page(page); if (page_same_filled(mem, &element)) { - kunmap_atomic(mem); + kunmap_local(mem); /* Free memory associated with this sector now. */ flags = ZRAM_SAME; atomic64_inc(&zram->stats.same_pages); goto out; } - kunmap_atomic(mem); + kunmap_local(mem); compress_again: zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]); - src = kmap_atomic(page); + src = kmap_local_page(page); ret = zcomp_compress(zstrm, src, &comp_len); - kunmap_atomic(src); + kunmap_local(src); if (unlikely(ret)) { zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); @@ -1495,10 +1494,10 @@ compress_again: src = zstrm->buffer; if (comp_len == PAGE_SIZE) - src = kmap_atomic(page); + src = kmap_local_page(page); memcpy(dst, src, comp_len); if (comp_len == PAGE_SIZE) - kunmap_atomic(src); + kunmap_local(src); zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]); zs_unmap_object(zram->mem_pool, handle); @@ -1615,9 +1614,9 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, num_recomps++; zstrm = zcomp_stream_get(zram->comps[prio]); - src = kmap_atomic(page); + src = kmap_local_page(page); ret = zcomp_compress(zstrm, src, &comp_len_new); - kunmap_atomic(src); + kunmap_local(src); if (ret) { zcomp_stream_put(zram->comps[prio]); diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index d090753f97be..3b94d12f41b4 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -69,7 +69,7 @@ struct zram_table_entry { unsigned long element; }; unsigned long flags; -#ifdef CONFIG_ZRAM_MEMORY_TRACKING +#ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME ktime_t ac_time; #endif }; diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 1659b787b65f..1ff1ab5fa105 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -367,6 +367,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr, .dax_region = dax_region, .size = 0, .id = -1, + .memmap_on_memory = false, }; struct dev_dax *dev_dax = devm_create_dev_dax(&data); @@ -1400,6 +1401,8 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) dev_dax->align = dax_region->align; ida_init(&dev_dax->ida); + dev_dax->memmap_on_memory = data->memmap_on_memory; + inode = dax_inode(dax_dev); dev->devt = inode->i_rdev; dev->bus = &dax_bus_type; diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h index 1ccd23360124..cbbf64443098 100644 --- a/drivers/dax/bus.h +++ b/drivers/dax/bus.h @@ -23,6 +23,7 @@ struct dev_dax_data { struct dev_pagemap *pgmap; resource_size_t size; int id; + bool memmap_on_memory; }; struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data); diff --git a/drivers/dax/cxl.c b/drivers/dax/cxl.c index 8bc9d04034d6..c696837ab23c 100644 --- a/drivers/dax/cxl.c +++ b/drivers/dax/cxl.c @@ -26,6 +26,7 @@ static int cxl_dax_region_probe(struct device *dev) .dax_region = dax_region, .id = -1, .size = range_len(&cxlr_dax->hpa_range), + .memmap_on_memory = true, }; return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data)); diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index 27cf2daaaa79..446617b73aea 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -70,6 +70,7 @@ struct dev_dax { struct ida ida; struct device dev; struct dev_pagemap *pgmap; + bool memmap_on_memory; int nr_range; struct dev_dax_range { unsigned long pgoff; diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c index 5d2ddef0f8f5..b9da69f92697 100644 --- a/drivers/dax/hmem/hmem.c +++ b/drivers/dax/hmem/hmem.c @@ -36,6 +36,7 @@ static int dax_hmem_probe(struct platform_device *pdev) .dax_region = dax_region, .id = -1, .size = region_idle ? 0 : range_len(&mri->range), + .memmap_on_memory = false, }; return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data)); diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index 369c698b7706..42ee360cf4e3 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/mman.h> #include <linux/memory-tiers.h> +#include <linux/memory_hotplug.h> #include "dax-private.h" #include "bus.h" @@ -93,6 +94,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) struct dax_kmem_data *data; struct memory_dev_type *mtype; int i, rc, mapped = 0; + mhp_t mhp_flags; int numa_node; int adist = MEMTIER_DEFAULT_DAX_ADISTANCE; @@ -179,12 +181,16 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) */ res->flags = IORESOURCE_SYSTEM_RAM; + mhp_flags = MHP_NID_IS_MGID; + if (dev_dax->memmap_on_memory) + mhp_flags |= MHP_MEMMAP_ON_MEMORY; + /* * Ensure that future kexec'd kernels will not treat * this as RAM automatically. */ rc = add_memory_driver_managed(data->mgid, range.start, - range_len(&range), kmem_name, MHP_NID_IS_MGID); + range_len(&range), kmem_name, mhp_flags); if (rc) { dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n", diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index ae0cb113a5d3..f3c6c67b8412 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -63,6 +63,7 @@ static struct dev_dax *__dax_pmem_probe(struct device *dev) .id = id, .pgmap = &pgmap, .size = range_len(&range), + .memmap_on_memory = false, }; return devm_create_dev_dax(&data); diff --git a/fs/Kconfig b/fs/Kconfig index 42837617a55b..cf62d86b514f 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -254,7 +254,7 @@ config TMPFS_QUOTA config ARCH_SUPPORTS_HUGETLBFS def_bool n -config HUGETLBFS +menuconfig HUGETLBFS bool "HugeTLB file system support" depends on X86 || SPARC64 || ARCH_SUPPORTS_HUGETLBFS || BROKEN depends on (SYSFS || SYSCTL) @@ -266,6 +266,17 @@ config HUGETLBFS If unsure, say N. +if HUGETLBFS +config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON + bool "HugeTLB Vmemmap Optimization (HVO) defaults to on" + default n + depends on HUGETLB_PAGE_OPTIMIZE_VMEMMAP + help + The HugeTLB Vmemmap Optimization (HVO) defaults to off. Say Y here to + enable HVO by default. It can be disabled via hugetlb_free_vmemmap=off + (boot command line) or hugetlb_optimize_vmemmap (sysctl). +endif # HUGETLBFS + config HUGETLB_PAGE def_bool HUGETLBFS select XARRAY_MULTI @@ -275,15 +286,6 @@ config HUGETLB_PAGE_OPTIMIZE_VMEMMAP depends on ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP depends on SPARSEMEM_VMEMMAP -config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON - bool "HugeTLB Vmemmap Optimization (HVO) defaults to on" - default n - depends on HUGETLB_PAGE_OPTIMIZE_VMEMMAP - help - The HugeTLB VmemmapvOptimization (HVO) defaults to off. Say Y here to - enable HVO by default. It can be disabled via hugetlb_free_vmemmap=off - (boot command line) or hugetlb_optimize_vmemmap (sysctl). - config ARCH_HAS_GIGANTIC_PAGE bool diff --git a/fs/afs/write.c b/fs/afs/write.c index 4a168781936b..e87b52b1f34c 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -242,7 +242,7 @@ static void afs_kill_pages(struct address_space *mapping, folio_clear_uptodate(folio); folio_end_writeback(folio); folio_lock(folio); - generic_error_remove_page(mapping, &folio->page); + generic_error_remove_folio(mapping, folio); folio_unlock(folio); folio_put(folio); @@ -559,8 +559,7 @@ static void afs_extend_writeback(struct address_space *mapping, if (!folio_clear_dirty_for_io(folio)) BUG(); - if (folio_start_writeback(folio)) - BUG(); + folio_start_writeback(folio); afs_folio_start_fscache(caching, folio); *_count -= folio_nr_pages(folio); @@ -595,8 +594,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, _enter(",%lx,%llx-%llx", folio_index(folio), start, end); - if (folio_start_writeback(folio)) - BUG(); + folio_start_writeback(folio); afs_folio_start_fscache(caching, folio); count -= folio_nr_pages(folio); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 4d51be813509..df4a97b6637b 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1103,7 +1103,7 @@ static const struct address_space_operations bch_address_space_operations = { #ifdef CONFIG_MIGRATION .migrate_folio = filemap_migrate_folio, #endif - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, }; struct bcachefs_fid { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9f5a9894f88f..ff7b4efca24f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10930,7 +10930,7 @@ static const struct address_space_operations btrfs_aops = { .release_folio = btrfs_release_folio, .migrate_folio = btrfs_migrate_folio, .dirty_folio = filemap_dirty_folio, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, .swap_activate = btrfs_swap_activate, .swap_deactivate = btrfs_swap_deactivate, }; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 85be3bf18cdf..13af429ab030 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -907,8 +907,8 @@ static void writepages_finish(struct ceph_osd_request *req) doutc(cl, "unlocking %p\n", page); if (remove_page) - generic_error_remove_page(inode->i_mapping, - page); + generic_error_remove_folio(inode->i_mapping, + page_folio(page)); unlock_page(page); } diff --git a/fs/dcache.c b/fs/dcache.c index c82ae731df9a..2ba37643b9c5 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -428,7 +428,8 @@ static void d_lru_add(struct dentry *dentry) this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); - WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); + WARN_ON_ONCE(!list_lru_add_obj( + &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) @@ -438,7 +439,8 @@ static void d_lru_del(struct dentry *dentry) this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); - WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); + WARN_ON_ONCE(!list_lru_del_obj( + &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) @@ -1240,7 +1242,7 @@ static enum lru_status dentry_lru_isolate(struct list_head *item, * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like - * list_lru_add and list_lru_del. List movement in this file + * list_lru_add_obj and list_lru_del_obj. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 464faf6c217e..5a4272b2c6b0 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -969,7 +969,7 @@ const struct address_space_operations ext2_aops = { .writepages = ext2_writepages, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, }; static const struct address_space_operations ext2_dax_aops = { diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 9a84a5f9fef4..d5bd1e3a5d36 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -502,9 +502,8 @@ static int ext4_read_inline_folio(struct inode *inode, struct folio *folio) BUG_ON(len > PAGE_SIZE); kaddr = kmap_local_folio(folio, 0); ret = ext4_read_inline_data(inode, kaddr, len, &iloc); - flush_dcache_folio(folio); + kaddr = folio_zero_tail(folio, len, kaddr + len); kunmap_local(kaddr); - folio_zero_segment(folio, len, folio_size(folio)); folio_mark_uptodate(folio); brelse(iloc.bh); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 61277f7f8722..d7729b17a66b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3564,7 +3564,7 @@ static const struct address_space_operations ext4_aops = { .direct_IO = noop_direct_IO, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, .swap_activate = ext4_iomap_swap_activate, }; @@ -3581,7 +3581,7 @@ static const struct address_space_operations ext4_journalled_aops = { .direct_IO = noop_direct_IO, .migrate_folio = buffer_migrate_folio_norefs, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, .swap_activate = ext4_iomap_swap_activate, }; @@ -3598,7 +3598,7 @@ static const struct address_space_operations ext4_da_aops = { .direct_IO = noop_direct_IO, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, .swap_activate = ext4_iomap_swap_activate, }; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 36e5dab6baae..6b2af514660d 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1944,7 +1944,7 @@ void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino) continue; } - generic_error_remove_page(mapping, &folio->page); + generic_error_remove_folio(mapping, folio); folio_unlock(folio); } folio_batch_release(&fbatch); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 560bfcad1af2..a9eb3891f417 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -600,7 +600,7 @@ make_now: #ifdef CONFIG_F2FS_FS_COMPRESSION inode->i_mapping->a_ops = &f2fs_compress_aops; /* - * generic_error_remove_page only truncates pages of regular + * generic_error_remove_folio only truncates pages of regular * inode */ inode->i_mode |= S_IFREG; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 9611bfceda4b..5cffb079b87c 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -403,18 +403,18 @@ static int gfs2_jdata_writepages(struct address_space *mapping, } /** - * stuffed_readpage - Fill in a Linux folio with stuffed file data + * stuffed_read_folio - Fill in a Linux folio with stuffed file data * @ip: the inode * @folio: the folio * * Returns: errno */ -static int stuffed_readpage(struct gfs2_inode *ip, struct folio *folio) +static int stuffed_read_folio(struct gfs2_inode *ip, struct folio *folio) { - struct buffer_head *dibh; - size_t i_size = i_size_read(&ip->i_inode); - void *data; - int error; + struct buffer_head *dibh = NULL; + size_t dsize = i_size_read(&ip->i_inode); + void *from = NULL; + int error = 0; /* * Due to the order of unstuffing files and ->fault(), we can be @@ -422,22 +422,20 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct folio *folio) * so we need to supply one here. It doesn't happen often. */ if (unlikely(folio->index)) { - folio_zero_range(folio, 0, folio_size(folio)); - folio_mark_uptodate(folio); - return 0; + dsize = 0; + } else { + error = gfs2_meta_inode_buffer(ip, &dibh); + if (error) + goto out; + from = dibh->b_data + sizeof(struct gfs2_dinode); } - error = gfs2_meta_inode_buffer(ip, &dibh); - if (error) - return error; - - data = dibh->b_data + sizeof(struct gfs2_dinode); - memcpy_to_folio(folio, 0, data, i_size); - folio_zero_range(folio, i_size, folio_size(folio) - i_size); + folio_fill_tail(folio, 0, from, dsize); brelse(dibh); - folio_mark_uptodate(folio); +out: + folio_end_read(folio, error == 0); - return 0; + return error; } /** @@ -456,8 +454,7 @@ static int gfs2_read_folio(struct file *file, struct folio *folio) (i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) { error = iomap_read_folio(folio, &gfs2_iomap_ops); } else if (gfs2_is_stuffed(ip)) { - error = stuffed_readpage(ip, folio); - folio_unlock(folio); + error = stuffed_read_folio(ip, folio); } else { error = mpage_read_folio(folio, gfs2_block_map); } @@ -748,7 +745,7 @@ static const struct address_space_operations gfs2_aops = { .bmap = gfs2_bmap, .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, }; static const struct address_space_operations gfs2_jdata_aops = { @@ -761,7 +758,7 @@ static const struct address_space_operations gfs2_jdata_aops = { .invalidate_folio = gfs2_invalidate_folio, .release_folio = gfs2_release_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, }; void gfs2_set_aops(struct inode *inode) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 95dae7838b4e..b57f8c7b35be 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -271,7 +271,7 @@ static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash, if (qd->qd_sbd != sdp) continue; if (lockref_get_not_dead(&qd->qd_lockref)) { - list_lru_del(&gfs2_qd_lru, &qd->qd_lru); + list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); return qd; } } @@ -344,7 +344,7 @@ static void qd_put(struct gfs2_quota_data *qd) } qd->qd_lockref.count = 0; - list_lru_add(&gfs2_qd_lru, &qd->qd_lru); + list_lru_add_obj(&gfs2_qd_lru, &qd->qd_lru); spin_unlock(&qd->qd_lockref.lock); } @@ -1517,7 +1517,7 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp) lockref_mark_dead(&qd->qd_lockref); spin_unlock(&qd->qd_lockref.lock); - list_lru_del(&gfs2_qd_lru, &qd->qd_lru); + list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); list_add(&qd->qd_lru, &dispose); } spin_unlock(&qd_lock); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f757d4f7ad98..36132c9125f9 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1129,8 +1129,8 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping, #define hugetlbfs_migrate_folio NULL #endif -static int hugetlbfs_error_remove_page(struct address_space *mapping, - struct page *page) +static int hugetlbfs_error_remove_folio(struct address_space *mapping, + struct folio *folio) { return 0; } @@ -1277,7 +1277,7 @@ static const struct address_space_operations hugetlbfs_aops = { .write_end = hugetlbfs_write_end, .dirty_folio = noop_dirty_folio, .migrate_folio = hugetlbfs_migrate_folio, - .error_remove_page = hugetlbfs_error_remove_page, + .error_remove_folio = hugetlbfs_error_remove_folio, }; diff --git a/fs/inode.c b/fs/inode.c index f238d987dec9..ef2034a985e0 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -464,7 +464,7 @@ static void __inode_add_lru(struct inode *inode, bool rotate) if (!mapping_shrinkable(&inode->i_data)) return; - if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) + if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else if (rotate) inode->i_state |= I_REFERENCED; @@ -482,7 +482,7 @@ void inode_add_lru(struct inode *inode) static void inode_lru_list_del(struct inode *inode) { - if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) + if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f72df2babe56..093c4515b22a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -305,28 +305,18 @@ static int iomap_read_inline_data(const struct iomap_iter *iter, { const struct iomap *iomap = iomap_iter_srcmap(iter); size_t size = i_size_read(iter->inode) - iomap->offset; - size_t poff = offset_in_page(iomap->offset); size_t offset = offset_in_folio(folio, iomap->offset); - void *addr; if (folio_test_uptodate(folio)) return 0; - if (WARN_ON_ONCE(size > PAGE_SIZE - poff)) - return -EIO; - if (WARN_ON_ONCE(size > PAGE_SIZE - - offset_in_page(iomap->inline_data))) - return -EIO; if (WARN_ON_ONCE(size > iomap->length)) return -EIO; if (offset > 0) ifs_alloc(iter->inode, folio, iter->flags); - addr = kmap_local_folio(folio, offset); - memcpy(addr, iomap->inline_data, size); - memset(addr + size, 0, PAGE_SIZE - poff - size); - kunmap_local(addr); - iomap_set_range_uptodate(folio, offset, PAGE_SIZE - poff); + folio_fill_tail(folio, offset, iomap->inline_data, size); + iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset); return 0; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 3f9768810427..e8cccb94b927 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -567,7 +567,7 @@ const struct address_space_operations nfs_file_aops = { .migrate_folio = nfs_migrate_folio, .launder_folio = nfs_launder_folio, .is_dirty_writeback = nfs_check_dirty_writeback, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, .swap_activate = nfs_swap_activate, .swap_deactivate = nfs_swap_deactivate, .swap_rw = nfs_swap_rw, diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index 2ad66a8922f4..49aaf28a6950 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -132,7 +132,7 @@ nfs4_xattr_entry_lru_add(struct nfs4_xattr_entry *entry) lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; - return list_lru_add(lru, &entry->lru); + return list_lru_add_obj(lru, &entry->lru); } static bool @@ -143,7 +143,7 @@ nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry) lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; - return list_lru_del(lru, &entry->lru); + return list_lru_del_obj(lru, &entry->lru); } /* @@ -349,7 +349,7 @@ nfs4_xattr_cache_unlink(struct inode *inode) oldcache = nfsi->xattr_cache; if (oldcache != NULL) { - list_lru_del(&nfs4_xattr_cache_lru, &oldcache->lru); + list_lru_del_obj(&nfs4_xattr_cache_lru, &oldcache->lru); oldcache->inode = NULL; } nfsi->xattr_cache = NULL; @@ -474,7 +474,7 @@ nfs4_xattr_get_cache(struct inode *inode, int add) kref_get(&cache->ref); nfsi->xattr_cache = cache; cache->inode = inode; - list_lru_add(&nfs4_xattr_cache_lru, &cache->lru); + list_lru_add_obj(&nfs4_xattr_cache_lru, &cache->lru); } spin_unlock(&inode->i_lock); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index ef063f93fde9..6c2decfdeb4b 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -322,7 +322,7 @@ nfsd_file_check_writeback(struct nfsd_file *nf) static bool nfsd_file_lru_add(struct nfsd_file *nf) { set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) { + if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) { trace_nfsd_file_lru_add(nf); return true; } @@ -331,7 +331,7 @@ static bool nfsd_file_lru_add(struct nfsd_file *nf) static bool nfsd_file_lru_remove(struct nfsd_file *nf) { - if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) { + if (list_lru_del_obj(&nfsd_file_lru, &nf->nf_lru)) { trace_nfsd_file_lru_del(nf); return true; } diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 71e31e789b29..70479ce915e8 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -1644,7 +1644,7 @@ const struct address_space_operations ntfs_normal_aops = { .bmap = ntfs_bmap, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, }; /* @@ -1658,7 +1658,7 @@ const struct address_space_operations ntfs_compressed_aops = { #endif /* NTFS_RW */ .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, }; /* @@ -1673,7 +1673,7 @@ const struct address_space_operations ntfs_mst_aops = { #endif /* NTFS_RW */ .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, }; #ifdef NTFS_RW diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index ba790219d528..795997806326 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2480,5 +2480,5 @@ const struct address_space_operations ocfs2_aops = { .release_folio = ocfs2_release_folio, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, }; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 435b61054b5b..d19924bf0a39 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1761,7 +1761,7 @@ static int pagemap_release(struct inode *inode, struct file *file) #define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \ PAGE_IS_FILE | PAGE_IS_PRESENT | \ PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \ - PAGE_IS_HUGE) + PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY) #define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC) struct pagemap_scan_private { @@ -1793,6 +1793,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, if (is_zero_pfn(pte_pfn(pte))) categories |= PAGE_IS_PFNZERO; + if (pte_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pte(pte)) { swp_entry_t swp; @@ -1806,6 +1808,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, !PageAnon(pfn_swap_entry_to_page(swp))) categories |= PAGE_IS_FILE; } + if (pte_swp_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } return categories; @@ -1853,12 +1857,16 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, if (is_zero_pfn(pmd_pfn(pmd))) categories |= PAGE_IS_PFNZERO; + if (pmd_soft_dirty(pmd)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pmd(pmd)) { swp_entry_t swp; categories |= PAGE_IS_SWAPPED; if (!pmd_swp_uffd_wp(pmd)) categories |= PAGE_IS_WRITTEN; + if (pmd_swp_soft_dirty(pmd)) + categories |= PAGE_IS_SOFT_DIRTY; if (p->masks_of_interest & PAGE_IS_FILE) { swp = pmd_to_swp_entry(pmd); @@ -1905,10 +1913,14 @@ static unsigned long pagemap_hugetlb_category(pte_t pte) categories |= PAGE_IS_FILE; if (is_zero_pfn(pte_pfn(pte))) categories |= PAGE_IS_PFNZERO; + if (pte_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pte(pte)) { categories |= PAGE_IS_SWAPPED; if (!pte_swp_uffd_wp_any(pte)) categories |= PAGE_IS_WRITTEN; + if (pte_swp_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } return categories; @@ -2007,6 +2019,9 @@ static int pagemap_scan_test_walk(unsigned long start, unsigned long end, if (wp_allowed) vma_category |= PAGE_IS_WPALLOWED; + if (vma->vm_flags & VM_SOFTDIRTY) + vma_category |= PAGE_IS_SOFT_DIRTY; + if (!pagemap_scan_is_interesting_vma(vma_category, p)) return 1; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index cf17e3dd703e..45ca492c141c 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -2706,8 +2706,7 @@ static void cifs_extend_writeback(struct address_space *mapping, */ if (!folio_clear_dirty_for_io(folio)) WARN_ON(1); - if (folio_start_writeback(folio)) - WARN_ON(1); + folio_start_writeback(folio); *_count -= folio_nr_pages(folio); folio_unlock(folio); @@ -2742,8 +2741,7 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, int rc; /* The folio should be locked, dirty and not undergoing writeback. */ - if (folio_start_writeback(folio)) - WARN_ON(1); + folio_start_writeback(folio); count -= folio_nr_pages(folio); len = folio_size(folio); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 465d7630bb21..813f85156b0c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -584,7 +584,7 @@ const struct address_space_operations xfs_address_space_operations = { .bmap = xfs_vm_bmap, .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, .swap_activate = xfs_iomap_swapfile_activate, }; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 545c7991b9b5..669332849680 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -169,7 +169,7 @@ xfs_buf_stale( atomic_set(&bp->b_lru_ref, 0); if (!(bp->b_state & XFS_BSTATE_DISPOSE) && - (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru))) + (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru))) atomic_dec(&bp->b_hold); ASSERT(atomic_read(&bp->b_hold) >= 1); @@ -1047,7 +1047,7 @@ xfs_buf_rele( * buffer for the LRU and clear the (now stale) dispose list * state flag */ - if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) { + if (list_lru_add_obj(&bp->b_target->bt_lru, &bp->b_lru)) { bp->b_state &= ~XFS_BSTATE_DISPOSE; atomic_inc(&bp->b_hold); } @@ -1060,7 +1060,7 @@ xfs_buf_rele( * was on was the disposal list */ if (!(bp->b_state & XFS_BSTATE_DISPOSE)) { - list_lru_del(&bp->b_target->bt_lru, &bp->b_lru); + list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru); } else { ASSERT(list_empty(&bp->b_lru)); } diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index a013b87ab8d5..61a45a86ffe8 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -1065,7 +1065,7 @@ xfs_qm_dqput( struct xfs_quotainfo *qi = dqp->q_mount->m_quotainfo; trace_xfs_dqput_free(dqp); - if (list_lru_add(&qi->qi_lru, &dqp->q_lru)) + if (list_lru_add_obj(&qi->qi_lru, &dqp->q_lru)) XFS_STATS_INC(dqp->q_mount, xs_qm_dquot_unused); } xfs_dqunlock(dqp); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 94a7932ac570..67d0a8564ff3 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -171,7 +171,7 @@ xfs_qm_dqpurge( * hits zero, so it really should be on the freelist here. */ ASSERT(!list_empty(&dqp->q_lru)); - list_lru_del(&qi->qi_lru, &dqp->q_lru); + list_lru_del_obj(&qi->qi_lru, &dqp->q_lru); XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused); xfs_qm_dqdestroy(dqp); diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index b2c9b35df8f7..6ab2318a9c8e 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -180,7 +180,7 @@ const struct address_space_operations zonefs_file_aops = { .invalidate_folio = iomap_invalidate_folio, .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, + .error_remove_folio = generic_error_remove_folio, .swap_activate = zonefs_swap_activate, }; diff --git a/include/linux/damon.h b/include/linux/damon.h index e00ddf1ed39c..12510d8c51c6 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -136,6 +136,9 @@ enum damos_action { * @weight_nr_accesses: Weight of the region's nr_accesses for prioritization. * @weight_age: Weight of the region's age for prioritization. * + * @get_score: Feedback function for self-tuning quota. + * @get_score_arg: Parameter for @get_score + * * To avoid consuming too much CPU time or IO resources for applying the * &struct damos->action to large memory, DAMON allows users to set time and/or * size quotas. The quotas can be set by writing non-zero values to &ms and @@ -153,6 +156,17 @@ enum damos_action { * You could customize the prioritization logic by setting &weight_sz, * &weight_nr_accesses, and &weight_age, because monitoring operations are * encouraged to respect those. + * + * If @get_score function pointer is set, DAMON calls it back with + * @get_score_arg and get the return value of it for every @reset_interval. + * Then, DAMON adjusts the effective quota using the return value as a feedback + * score to the current quota, using its internal feedback loop algorithm. + * + * The feedback loop algorithem assumes the quota input and the feedback score + * output are in a positive proportional relationship, and the goal of the + * tuning is getting the feedback screo value of 10,000. If @ms and/or @sz are + * set together, those work as a hard limit quota. If neither @ms nor @sz are + * set, the mechanism starts from the quota of one byte. */ struct damos_quota { unsigned long ms; @@ -163,6 +177,9 @@ struct damos_quota { unsigned int weight_nr_accesses; unsigned int weight_age; + unsigned long (*get_score)(void *arg); + void *get_score_arg; + /* private: */ /* For throughput estimation */ unsigned long total_charged_sz; @@ -179,6 +196,9 @@ struct damos_quota { /* For prioritization */ unsigned long histogram[DAMOS_MAX_SCORE + 1]; unsigned int min_score; + + /* For feedback loop */ + unsigned long esz_bp; }; /** diff --git a/include/linux/fs.h b/include/linux/fs.h index 98b7a7a8c42e..31b2cf963db9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -434,7 +434,7 @@ struct address_space_operations { bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); - int (*error_remove_page)(struct address_space *, struct page *); + int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 6583a58670c5..ae994534a12a 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -274,7 +274,8 @@ typedef unsigned int __bitwise gfp_t; * accounted to kmemcg. * * %GFP_NOWAIT is for kernel allocations that should not stall for direct - * reclaim, start physical IO or use any filesystem callback. + * reclaim, start physical IO or use any filesystem callback. It is very + * likely to fail to allocate memory, even for very small allocations. * * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. @@ -325,7 +326,7 @@ typedef unsigned int __bitwise gfp_t; #define GFP_ATOMIC (__GFP_HIGH|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) -#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) +#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM | __GFP_NOWARN) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) #define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index be20cff4ba73..451c1dff0e87 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -484,6 +484,82 @@ static inline void memcpy_to_folio(struct folio *folio, size_t offset, } /** + * folio_zero_tail - Zero the tail of a folio. + * @folio: The folio to zero. + * @offset: The byte offset in the folio to start zeroing at. + * @kaddr: The address the folio is currently mapped to. + * + * If you have already used kmap_local_folio() to map a folio, written + * some data to it and now need to zero the end of the folio (and flush + * the dcache), you can use this function. If you do not have the + * folio kmapped (eg the folio has been partially populated by DMA), + * use folio_zero_range() or folio_zero_segment() instead. + * + * Return: An address which can be passed to kunmap_local(). + */ +static inline __must_check void *folio_zero_tail(struct folio *folio, + size_t offset, void *kaddr) +{ + size_t len = folio_size(folio) - offset; + + if (folio_test_highmem(folio)) { + size_t max = PAGE_SIZE - offset_in_page(offset); + + while (len > max) { + memset(kaddr, 0, max); + kunmap_local(kaddr); + len -= max; + offset += max; + max = PAGE_SIZE; + kaddr = kmap_local_folio(folio, offset); + } + } + + memset(kaddr, 0, len); + flush_dcache_folio(folio); + + return kaddr; +} + +/** + * folio_fill_tail - Copy some data to a folio and pad with zeroes. + * @folio: The destination folio. + * @offset: The offset into @folio at which to start copying. + * @from: The data to copy. + * @len: How many bytes of data to copy. + * + * This function is most useful for filesystems which support inline data. + * When they want to copy data from the inode into the page cache, this + * function does everything for them. It supports large folios even on + * HIGHMEM configurations. + */ +static inline void folio_fill_tail(struct folio *folio, size_t offset, + const char *from, size_t len) +{ + char *to = kmap_local_folio(folio, offset); + + VM_BUG_ON(offset + len > folio_size(folio)); + + if (folio_test_highmem(folio)) { + size_t max = PAGE_SIZE - offset_in_page(offset); + + while (len > max) { + memcpy(to, from, max); + kunmap_local(to); + len -= max; + from += max; + offset += max; + max = PAGE_SIZE; + to = kmap_local_folio(folio, offset); + } + } + + memcpy(to, from, len); + to = folio_zero_tail(folio, offset + len, to + len); + kunmap_local(to); +} + +/** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. * @folio: The folio to copy from. diff --git a/include/linux/ksm.h b/include/linux/ksm.h index c2dd786a30e1..4643d5244e77 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -77,7 +77,7 @@ static inline void ksm_exit(struct mm_struct *mm) * but what if the vma was unmerged while the page was swapped out? */ struct page *ksm_might_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address); + struct vm_area_struct *vma, unsigned long addr); void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); @@ -130,7 +130,7 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, } static inline struct page *ksm_might_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address) + struct vm_area_struct *vma, unsigned long addr) { return page; } diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index b35968ee9fb5..7675a48a0701 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -73,8 +73,10 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren /** * list_lru_add: add an element to the lru list's tail - * @list_lru: the lru pointer + * @lru: the lru pointer * @item: the item to be added. + * @nid: the node id of the sublist to add the item to. + * @memcg: the cgroup of the sublist to add the item to. * * If the element is already part of a list, this function returns doing * nothing. Therefore the caller does not need to keep state about whether or @@ -83,24 +85,54 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren * the caller organize itself in a way that elements can be in more than * one type of list, it is up to the caller to fully remove the item from * the previous list (with list_lru_del() for instance) before moving it - * to @list_lru + * to @lru. + * + * Return: true if the list was updated, false otherwise + */ +bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, + struct mem_cgroup *memcg); + +/** + * list_lru_add_obj: add an element to the lru list's tail + * @lru: the lru pointer + * @item: the item to be added. + * + * This function is similar to list_lru_add(), but the NUMA node and the + * memcg of the sublist is determined by @item list_head. This assumption is + * valid for slab objects LRU such as dentries, inodes, etc. * * Return value: true if the list was updated, false otherwise */ -bool list_lru_add(struct list_lru *lru, struct list_head *item); +bool list_lru_add_obj(struct list_lru *lru, struct list_head *item); /** - * list_lru_del: delete an element to the lru list - * @list_lru: the lru pointer + * list_lru_del: delete an element from the lru list + * @lru: the lru pointer * @item: the item to be deleted. + * @nid: the node id of the sublist to delete the item from. + * @memcg: the cgroup of the sublist to delete the item from. * - * This function works analogously as list_lru_add in terms of list + * This function works analogously as list_lru_add() in terms of list * manipulation. The comments about an element already pertaining to - * a list are also valid for list_lru_del. + * a list are also valid for list_lru_del(). * - * Return value: true if the list was updated, false otherwise + * Return: true if the list was updated, false otherwise */ -bool list_lru_del(struct list_lru *lru, struct list_head *item); +bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, + struct mem_cgroup *memcg); + +/** + * list_lru_del_obj: delete an element from the lru list + * @lru: the lru pointer + * @item: the item to be deleted. + * + * This function is similar to list_lru_del(), but the NUMA node and the + * memcg of the sublist is determined by @item list_head. This assumption is + * valid for slab objects LRU such as dentries, inodes, etc. + * + * Return value: true if the list was updated, false otherwise. + */ +bool list_lru_del_obj(struct list_lru *lru, struct list_head *item); /** * list_lru_count_one: return the number of objects currently held by @lru @@ -108,9 +140,11 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item); * @nid: the node id to count from. * @memcg: the cgroup to count from. * - * Always return a non-negative number, 0 for empty lists. There is no - * guarantee that the list is not updated while the count is being computed. - * Callers that want such a guarantee need to provide an outer lock. + * There is no guarantee that the list is not updated while the count is being + * computed. Callers that want such a guarantee need to provide an outer lock. + * + * Return: 0 for empty lists, otherwise the number of objects + * currently held by @lru. */ unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg); @@ -136,12 +170,28 @@ static inline unsigned long list_lru_count(struct list_lru *lru) void list_lru_isolate(struct list_lru_one *list, struct list_head *item); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); +/** + * list_lru_putback: undo list_lru_isolate + * @lru: the lru pointer. + * @item: the item to put back. + * @nid: the node id of the sublist to put the item back to. + * @memcg: the cgroup of the sublist to put the item back to. + * + * Put back an isolated item into its original LRU. Note that unlike + * list_lru_add, this does not increment the node LRU count (as + * list_lru_isolate does not originally decrement this count). + * + * Since we might have dropped the LRU lock in between, recompute list_lru_one + * from the node's id and memcg. + */ +void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid, + struct mem_cgroup *memcg); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, struct list_lru_one *list, spinlock_t *lock, void *cb_arg); /** - * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items. + * list_lru_walk_one: walk a @lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. @@ -150,24 +200,24 @@ typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * - * This function will scan all elements in a particular list_lru, calling the + * This function will scan all elements in a particular @lru, calling the * @isolate callback for each of those items, along with the current list * spinlock and a caller-provided opaque. The @isolate callback can choose to * drop the lock internally, but *must* return with the lock held. The callback - * will return an enum lru_status telling the list_lru infrastructure what to + * will return an enum lru_status telling the @lru infrastructure what to * do with the object being scanned. * - * Please note that nr_to_walk does not mean how many objects will be freed, + * Please note that @nr_to_walk does not mean how many objects will be freed, * just how many objects will be scanned. * - * Return value: the number of objects effectively removed from the LRU. + * Return: the number of objects effectively removed from the LRU. */ unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); /** - * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items. + * list_lru_walk_one_irq: walk a @lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. @@ -176,7 +226,7 @@ unsigned long list_lru_walk_one(struct list_lru *lru, * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * - * Same as @list_lru_walk_one except that the spinlock is acquired with + * Same as list_lru_walk_one() except that the spinlock is acquired with * spin_lock_irq(). */ unsigned long list_lru_walk_one_irq(struct list_lru *lru, diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index d01e850b570f..b3d63123b945 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -256,6 +256,8 @@ struct maple_tree { struct maple_tree name = MTREE_INIT(name, 0) #define mtree_lock(mt) spin_lock((&(mt)->ma_lock)) +#define mtree_lock_nested(mas, subclass) \ + spin_lock_nested((&(mt)->ma_lock), subclass) #define mtree_unlock(mt) spin_unlock((&(mt)->ma_lock)) /* @@ -327,6 +329,9 @@ int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp); void *mtree_erase(struct maple_tree *mt, unsigned long index); +int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); +int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp); + void mtree_destroy(struct maple_tree *mt); void __mt_destroy(struct maple_tree *mt); @@ -345,6 +350,36 @@ static inline bool mtree_empty(const struct maple_tree *mt) /* Advanced API */ /* + * Maple State Status + * ma_active means the maple state is pointing to a node and offset and can + * continue operating on the tree. + * ma_start means we have not searched the tree. + * ma_root means we have searched the tree and the entry we found lives in + * the root of the tree (ie it has index 0, length 1 and is the only entry in + * the tree). + * ma_none means we have searched the tree and there is no node in the + * tree for this entry. For example, we searched for index 1 in an empty + * tree. Or we have a tree which points to a full leaf node and we + * searched for an entry which is larger than can be contained in that + * leaf node. + * ma_pause means the data within the maple state may be stale, restart the + * operation + * ma_overflow means the search has reached the upper limit of the search + * ma_underflow means the search has reached the lower limit of the search + * ma_error means there was an error, check the node for the error number. + */ +enum maple_status { + ma_active, + ma_start, + ma_root, + ma_none, + ma_pause, + ma_overflow, + ma_underflow, + ma_error, +}; + +/* * The maple state is defined in the struct ma_state and is used to keep track * of information during operations, and even between operations when using the * advanced API. @@ -376,6 +411,13 @@ static inline bool mtree_empty(const struct maple_tree *mt) * When returning a value the maple state index and last respectively contain * the start and end of the range for the entry. Ranges are inclusive in the * Maple Tree. + * + * The status of the state is used to determine how the next action should treat + * the state. For instance, if the status is ma_start then the next action + * should start at the root of the tree and walk down. If the status is + * ma_pause then the node may be stale data and should be discarded. If the + * status is ma_overflow, then the last action hit the upper limit. + * */ struct ma_state { struct maple_tree *tree; /* The tree we're operating in */ @@ -385,9 +427,11 @@ struct ma_state { unsigned long min; /* The minimum index of this node - implied pivot min */ unsigned long max; /* The maximum index of this node - implied pivot max */ struct maple_alloc *alloc; /* Allocated nodes for this operation */ + enum maple_status status; /* The status of the state (active, start, none, etc) */ unsigned char depth; /* depth of tree descent during write */ unsigned char offset; unsigned char mas_flags; + unsigned char end; /* The end of the node */ }; struct ma_wr_state { @@ -397,7 +441,6 @@ struct ma_wr_state { unsigned long r_max; /* range max */ enum maple_type type; /* mas->node type */ unsigned char offset_end; /* The offset where the write ends */ - unsigned char node_end; /* mas->node end */ unsigned long *pivots; /* mas->node->pivots pointer */ unsigned long end_piv; /* The pivot at the offset end */ void __rcu **slots; /* mas->node->slots pointer */ @@ -406,30 +449,16 @@ struct ma_wr_state { }; #define mas_lock(mas) spin_lock(&((mas)->tree->ma_lock)) +#define mas_lock_nested(mas, subclass) \ + spin_lock_nested(&((mas)->tree->ma_lock), subclass) #define mas_unlock(mas) spin_unlock(&((mas)->tree->ma_lock)) - /* * Special values for ma_state.node. - * MAS_START means we have not searched the tree. - * MAS_ROOT means we have searched the tree and the entry we found lives in - * the root of the tree (ie it has index 0, length 1 and is the only entry in - * the tree). - * MAS_NONE means we have searched the tree and there is no node in the - * tree for this entry. For example, we searched for index 1 in an empty - * tree. Or we have a tree which points to a full leaf node and we - * searched for an entry which is larger than can be contained in that - * leaf node. * MA_ERROR represents an errno. After dropping the lock and attempting * to resolve the error, the walk would have to be restarted from the * top of the tree as the tree may have been modified. */ -#define MAS_START ((struct maple_enode *)1UL) -#define MAS_ROOT ((struct maple_enode *)5UL) -#define MAS_NONE ((struct maple_enode *)9UL) -#define MAS_PAUSE ((struct maple_enode *)17UL) -#define MAS_OVERFLOW ((struct maple_enode *)33UL) -#define MAS_UNDERFLOW ((struct maple_enode *)65UL) #define MA_ERROR(err) \ ((struct maple_enode *)(((unsigned long)err << 2) | 2UL)) @@ -438,7 +467,8 @@ struct ma_wr_state { .tree = mt, \ .index = first, \ .last = end, \ - .node = MAS_START, \ + .node = NULL, \ + .status = ma_start, \ .min = 0, \ .max = ULONG_MAX, \ .alloc = NULL, \ @@ -469,7 +499,6 @@ void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); -bool mas_is_err(struct ma_state *mas); bool mas_nomem(struct ma_state *mas, gfp_t gfp); void mas_pause(struct ma_state *mas); @@ -498,28 +527,18 @@ static inline void mas_init(struct ma_state *mas, struct maple_tree *tree, mas->tree = tree; mas->index = mas->last = addr; mas->max = ULONG_MAX; - mas->node = MAS_START; -} - -/* Checks if a mas has not found anything */ -static inline bool mas_is_none(const struct ma_state *mas) -{ - return mas->node == MAS_NONE; + mas->status = ma_start; + mas->node = NULL; } -/* Checks if a mas has been paused */ -static inline bool mas_is_paused(const struct ma_state *mas) +static inline bool mas_is_active(struct ma_state *mas) { - return mas->node == MAS_PAUSE; + return mas->status == ma_active; } -/* Check if the mas is pointing to a node or not */ -static inline bool mas_is_active(struct ma_state *mas) +static inline bool mas_is_err(struct ma_state *mas) { - if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE) - return true; - - return false; + return mas->status == ma_error; } /** @@ -532,9 +551,10 @@ static inline bool mas_is_active(struct ma_state *mas) * * Context: Any context. */ -static inline void mas_reset(struct ma_state *mas) +static __always_inline void mas_reset(struct ma_state *mas) { - mas->node = MAS_START; + mas->status = ma_start; + mas->node = NULL; } /** @@ -550,6 +570,131 @@ static inline void mas_reset(struct ma_state *mas) */ #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) + +#ifdef CONFIG_DEBUG_MAPLE_TREE +enum mt_dump_format { + mt_dump_dec, + mt_dump_hex, +}; + +extern atomic_t maple_tree_tests_run; +extern atomic_t maple_tree_tests_passed; + +void mt_dump(const struct maple_tree *mt, enum mt_dump_format format); +void mas_dump(const struct ma_state *mas); +void mas_wr_dump(const struct ma_wr_state *wr_mas); +void mt_validate(struct maple_tree *mt); +void mt_cache_shrink(void); +#define MT_BUG_ON(__tree, __x) do { \ + atomic_inc(&maple_tree_tests_run); \ + if (__x) { \ + pr_info("BUG at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mt_dump(__tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ +} while (0) + +#define MAS_BUG_ON(__mas, __x) do { \ + atomic_inc(&maple_tree_tests_run); \ + if (__x) { \ + pr_info("BUG at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mas_dump(__mas); \ + mt_dump((__mas)->tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ +} while (0) + +#define MAS_WR_BUG_ON(__wrmas, __x) do { \ + atomic_inc(&maple_tree_tests_run); \ + if (__x) { \ + pr_info("BUG at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mas_wr_dump(__wrmas); \ + mas_dump((__wrmas)->mas); \ + mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ +} while (0) + +#define MT_WARN_ON(__tree, __x) ({ \ + int ret = !!(__x); \ + atomic_inc(&maple_tree_tests_run); \ + if (ret) { \ + pr_info("WARN at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mt_dump(__tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ + unlikely(ret); \ +}) + +#define MAS_WARN_ON(__mas, __x) ({ \ + int ret = !!(__x); \ + atomic_inc(&maple_tree_tests_run); \ + if (ret) { \ + pr_info("WARN at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mas_dump(__mas); \ + mt_dump((__mas)->tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ + unlikely(ret); \ +}) + +#define MAS_WR_WARN_ON(__wrmas, __x) ({ \ + int ret = !!(__x); \ + atomic_inc(&maple_tree_tests_run); \ + if (ret) { \ + pr_info("WARN at %s:%d (%u)\n", \ + __func__, __LINE__, __x); \ + mas_wr_dump(__wrmas); \ + mas_dump((__wrmas)->mas); \ + mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ + pr_info("Pass: %u Run:%u\n", \ + atomic_read(&maple_tree_tests_passed), \ + atomic_read(&maple_tree_tests_run)); \ + dump_stack(); \ + } else { \ + atomic_inc(&maple_tree_tests_passed); \ + } \ + unlikely(ret); \ +}) +#else +#define MT_BUG_ON(__tree, __x) BUG_ON(__x) +#define MAS_BUG_ON(__mas, __x) BUG_ON(__x) +#define MAS_WR_BUG_ON(__mas, __x) BUG_ON(__x) +#define MT_WARN_ON(__tree, __x) WARN_ON(__x) +#define MAS_WARN_ON(__mas, __x) WARN_ON(__x) +#define MAS_WR_WARN_ON(__mas, __x) WARN_ON(__x) +#endif /* CONFIG_DEBUG_MAPLE_TREE */ + /** * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the * current location. @@ -563,6 +708,9 @@ static inline void mas_reset(struct ma_state *mas) static inline void __mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { + /* Ensure the range starts within the current slot */ + MAS_WARN_ON(mas, mas_is_active(mas) && + (mas->index > start || mas->last < start)); mas->index = start; mas->last = last; } @@ -580,8 +728,8 @@ static inline void __mas_set_range(struct ma_state *mas, unsigned long start, static inline void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last) { + mas_reset(mas); __mas_set_range(mas, start, last); - mas->node = MAS_START; } /** @@ -706,129 +854,4 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max); for (__entry = mt_find(__tree, &(__index), __max); \ __entry; __entry = mt_find_after(__tree, &(__index), __max)) - -#ifdef CONFIG_DEBUG_MAPLE_TREE -enum mt_dump_format { - mt_dump_dec, - mt_dump_hex, -}; - -extern atomic_t maple_tree_tests_run; -extern atomic_t maple_tree_tests_passed; - -void mt_dump(const struct maple_tree *mt, enum mt_dump_format format); -void mas_dump(const struct ma_state *mas); -void mas_wr_dump(const struct ma_wr_state *wr_mas); -void mt_validate(struct maple_tree *mt); -void mt_cache_shrink(void); -#define MT_BUG_ON(__tree, __x) do { \ - atomic_inc(&maple_tree_tests_run); \ - if (__x) { \ - pr_info("BUG at %s:%d (%u)\n", \ - __func__, __LINE__, __x); \ - mt_dump(__tree, mt_dump_hex); \ - pr_info("Pass: %u Run:%u\n", \ - atomic_read(&maple_tree_tests_passed), \ - atomic_read(&maple_tree_tests_run)); \ - dump_stack(); \ - } else { \ - atomic_inc(&maple_tree_tests_passed); \ - } \ -} while (0) - -#define MAS_BUG_ON(__mas, __x) do { \ - atomic_inc(&maple_tree_tests_run); \ - if (__x) { \ - pr_info("BUG at %s:%d (%u)\n", \ - __func__, __LINE__, __x); \ - mas_dump(__mas); \ - mt_dump((__mas)->tree, mt_dump_hex); \ - pr_info("Pass: %u Run:%u\n", \ - atomic_read(&maple_tree_tests_passed), \ - atomic_read(&maple_tree_tests_run)); \ - dump_stack(); \ - } else { \ - atomic_inc(&maple_tree_tests_passed); \ - } \ -} while (0) - -#define MAS_WR_BUG_ON(__wrmas, __x) do { \ - atomic_inc(&maple_tree_tests_run); \ - if (__x) { \ - pr_info("BUG at %s:%d (%u)\n", \ - __func__, __LINE__, __x); \ - mas_wr_dump(__wrmas); \ - mas_dump((__wrmas)->mas); \ - mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ - pr_info("Pass: %u Run:%u\n", \ - atomic_read(&maple_tree_tests_passed), \ - atomic_read(&maple_tree_tests_run)); \ - dump_stack(); \ - } else { \ - atomic_inc(&maple_tree_tests_passed); \ - } \ -} while (0) - -#define MT_WARN_ON(__tree, __x) ({ \ - int ret = !!(__x); \ - atomic_inc(&maple_tree_tests_run); \ - if (ret) { \ - pr_info("WARN at %s:%d (%u)\n", \ - __func__, __LINE__, __x); \ - mt_dump(__tree, mt_dump_hex); \ - pr_info("Pass: %u Run:%u\n", \ - atomic_read(&maple_tree_tests_passed), \ - atomic_read(&maple_tree_tests_run)); \ - dump_stack(); \ - } else { \ - atomic_inc(&maple_tree_tests_passed); \ - } \ - unlikely(ret); \ -}) - -#define MAS_WARN_ON(__mas, __x) ({ \ - int ret = !!(__x); \ - atomic_inc(&maple_tree_tests_run); \ - if (ret) { \ - pr_info("WARN at %s:%d (%u)\n", \ - __func__, __LINE__, __x); \ - mas_dump(__mas); \ - mt_dump((__mas)->tree, mt_dump_hex); \ - pr_info("Pass: %u Run:%u\n", \ - atomic_read(&maple_tree_tests_passed), \ - atomic_read(&maple_tree_tests_run)); \ - dump_stack(); \ - } else { \ - atomic_inc(&maple_tree_tests_passed); \ - } \ - unlikely(ret); \ -}) - -#define MAS_WR_WARN_ON(__wrmas, __x) ({ \ - int ret = !!(__x); \ - atomic_inc(&maple_tree_tests_run); \ - if (ret) { \ - pr_info("WARN at %s:%d (%u)\n", \ - __func__, __LINE__, __x); \ - mas_wr_dump(__wrmas); \ - mas_dump((__wrmas)->mas); \ - mt_dump((__wrmas)->mas->tree, mt_dump_hex); \ - pr_info("Pass: %u Run:%u\n", \ - atomic_read(&maple_tree_tests_passed), \ - atomic_read(&maple_tree_tests_run)); \ - dump_stack(); \ - } else { \ - atomic_inc(&maple_tree_tests_passed); \ - } \ - unlikely(ret); \ -}) -#else -#define MT_BUG_ON(__tree, __x) BUG_ON(__x) -#define MAS_BUG_ON(__mas, __x) BUG_ON(__x) -#define MAS_WR_BUG_ON(__mas, __x) BUG_ON(__x) -#define MT_WARN_ON(__tree, __x) WARN_ON(__x) -#define MAS_WARN_ON(__mas, __x) WARN_ON(__x) -#define MAS_WR_WARN_ON(__mas, __x) WARN_ON(__x) -#endif /* CONFIG_DEBUG_MAPLE_TREE */ - #endif /*_LINUX_MAPLE_TREE_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index ae3bde302f70..b695f9e946da 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -123,6 +123,7 @@ int memblock_physmem_add(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); bool memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size); +bool memblock_validate_numa_coverage(unsigned long threshold_bytes); int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7bdcf3020d7a..a308c8eacf20 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -821,6 +821,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) return !memcg || css_tryget(&memcg->css); } +static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) +{ + return !memcg || css_tryget_online(&memcg->css); +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) @@ -1187,6 +1192,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return NULL; } +static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) +{ + return NULL; +} + static inline bool folio_memcg_kmem(struct folio *folio) { return false; @@ -1349,6 +1359,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) return true; } +static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) +{ + return true; +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 1314d9c5f05b..744c830f4b13 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -196,8 +196,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); -unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); -void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); unsigned long memremap_compat_align(void); #else static inline void *devm_memremap_pages(struct device *dev, @@ -228,16 +226,6 @@ static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) return false; } -static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) -{ - return 0; -} - -static inline void vmem_altmap_free(struct vmem_altmap *altmap, - unsigned long nr_pfns) -{ -} - /* when memremap_pages() is disabled all archs can remap a single page */ static inline unsigned long memremap_compat_align(void) { diff --git a/include/linux/mm.h b/include/linux/mm.h index da5219b48d52..b72bf25a45cf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -994,6 +994,17 @@ static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi, return mas_expected_entries(&vmi->mas, count); } +static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, + unsigned long start, unsigned long end, gfp_t gfp) +{ + __mas_set_range(&vmi->mas, start, end - 1); + mas_store_gfp(&vmi->mas, NULL, gfp); + if (unlikely(mas_is_err(&vmi->mas))) + return -ENOMEM; + + return 0; +} + /* Free any unused preallocations */ static inline void vma_iter_free(struct vma_iterator *vmi) { @@ -2373,7 +2384,8 @@ extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); -int generic_error_remove_page(struct address_space *mapping, struct page *page); +int generic_error_remove_folio(struct address_space *mapping, + struct folio *folio); struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm, unsigned long address, struct pt_regs *regs); @@ -3859,6 +3871,32 @@ void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +{ + /* number of pfns from base where pfn_to_page() is valid */ + if (altmap) + return altmap->reserve + altmap->free; + return 0; +} + +static inline void vmem_altmap_free(struct vmem_altmap *altmap, + unsigned long nr_pfns) +{ + altmap->alloc -= nr_pfns; +} +#else +static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +{ + return 0; +} + +static inline void vmem_altmap_free(struct vmem_altmap *altmap, + unsigned long nr_pfns) +{ +} +#endif + #define VMEMMAP_RESERVE_NR 2 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 957ce38768b2..a66534c78c4d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -401,11 +401,11 @@ FOLIO_MATCH(compound_head, _head_2a); * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs. * @__page_mapping: Aliases with page->mapping. Unused for page tables. * @pt_mm: Used for x86 pgds. - * @pt_frag_refcount: For fragmented page table tracking. Powerpc and s390 only. + * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. - * @_refcount: Same as page refcount. Used for s390 page tables. + * @__page_refcount: Same as page refcount. * @pt_memcg_data: Memcg data. Tracked for page tables here. * * This struct overlays struct page for now. Do not modify without a good @@ -438,7 +438,7 @@ struct ptdesc { #endif }; unsigned int __page_type; - atomic_t _refcount; + atomic_t __page_refcount; #ifdef CONFIG_MEMCG unsigned long pt_memcg_data; #endif @@ -452,7 +452,7 @@ TABLE_MATCH(compound_head, _pt_pad_1); TABLE_MATCH(mapping, __page_mapping); TABLE_MATCH(rcu_head, pt_rcu_head); TABLE_MATCH(page_type, __page_type); -TABLE_MATCH(_refcount, _refcount); +TABLE_MATCH(_refcount, __page_refcount); #ifdef CONFIG_MEMCG TABLE_MATCH(memcg_data, pt_memcg_data); #endif @@ -1071,7 +1071,8 @@ struct vma_iterator { .mas = { \ .tree = &(__mm)->mm_mt, \ .index = __addr, \ - .node = MAS_START, \ + .node = NULL, \ + .status = ma_start, \ }, \ } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9db36e197712..ec73582e7d27 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -22,6 +22,7 @@ #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> +#include <linux/zswap.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ @@ -206,6 +207,10 @@ enum node_stat_item { #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ PGPROMOTE_CANDIDATE, /* candidate pages to promote */ + /* PGDEMOTE_*: pages demoted */ + PGDEMOTE_KSWAPD, + PGDEMOTE_DIRECT, + PGDEMOTE_KHUGEPAGED, #endif NR_VM_NODE_STAT_ITEMS }; @@ -641,6 +646,7 @@ struct lruvec { #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif + struct zswap_lruvec_state zswap_lruvec_state; }; /* Isolate for asynchronous migration */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a88e64acebfe..735cddc13d20 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -772,19 +772,14 @@ static __always_inline void SetPageUptodate(struct page *page) CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) -bool __folio_start_writeback(struct folio *folio, bool keep_write); -bool set_page_writeback(struct page *page); +void __folio_start_writeback(struct folio *folio, bool keep_write); +void set_page_writeback(struct page *page); #define folio_start_writeback(folio) \ __folio_start_writeback(folio, false) #define folio_start_writeback_keepwrite(folio) \ __folio_start_writeback(folio, true) -static inline bool test_set_page_writeback(struct page *page) -{ - return set_page_writeback(page); -} - static __always_inline bool folio_test_head(struct folio *folio) { return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY)); diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b26fe858fd44..3c2fc291b071 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -261,8 +261,8 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, * guarantee the pinned page won't be randomly replaced in the * future on write faults. */ - if (likely(!is_device_private_page(page) && - unlikely(page_needs_cow_for_dma(vma, page)))) + if (likely(!is_device_private_page(page)) && + unlikely(page_needs_cow_for_dma(vma, page))) return -EBUSY; ClearPageAnonExclusive(page); diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index e58306783d8e..a6796f178913 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -32,6 +32,18 @@ typedef u32 depot_stack_handle_t; */ #define STACK_DEPOT_EXTRA_BITS 5 +typedef u32 depot_flags_t; + +/* + * Flags that can be passed to stack_depot_save_flags(); see the comment next + * to its declaration for more details. + */ +#define STACK_DEPOT_FLAG_CAN_ALLOC ((depot_flags_t)0x0001) +#define STACK_DEPOT_FLAG_GET ((depot_flags_t)0x0002) + +#define STACK_DEPOT_FLAGS_NUM 2 +#define STACK_DEPOT_FLAGS_MASK ((depot_flags_t)((1 << STACK_DEPOT_FLAGS_NUM) - 1)) + /* * Using stack depot requires its initialization, which can be done in 3 ways: * @@ -69,31 +81,39 @@ static inline int stack_depot_early_init(void) { return 0; } #endif /** - * __stack_depot_save - Save a stack trace to stack depot + * stack_depot_save_flags - Save a stack trace to stack depot * * @entries: Pointer to the stack trace * @nr_entries: Number of frames in the stack * @alloc_flags: Allocation GFP flags - * @can_alloc: Allocate stack pools (increased chance of failure if false) + * @depot_flags: Stack depot flags + * + * Saves a stack trace from @entries array of size @nr_entries. + * + * If STACK_DEPOT_FLAG_CAN_ALLOC is set in @depot_flags, stack depot can + * replenish the stack pools in case no space is left (allocates using GFP + * flags of @alloc_flags). Otherwise, stack depot avoids any allocations and + * fails if no space is left to store the stack trace. * - * Saves a stack trace from @entries array of size @nr_entries. If @can_alloc is - * %true, stack depot can replenish the stack pools in case no space is left - * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids - * any allocations and fails if no space is left to store the stack trace. + * If STACK_DEPOT_FLAG_GET is set in @depot_flags, stack depot will increment + * the refcount on the saved stack trace if it already exists in stack depot. + * Users of this flag must also call stack_depot_put() when keeping the stack + * trace is no longer required to avoid overflowing the refcount. * * If the provided stack trace comes from the interrupt context, only the part * up to the interrupt entry is saved. * - * Context: Any context, but setting @can_alloc to %false is required if + * Context: Any context, but setting STACK_DEPOT_FLAG_CAN_ALLOC is required if * alloc_pages() cannot be used from the current context. Currently * this is the case for contexts where neither %GFP_ATOMIC nor * %GFP_NOWAIT can be used (NMI, raw_spin_lock). * * Return: Handle of the stack struct stored in depot, 0 on failure */ -depot_stack_handle_t __stack_depot_save(unsigned long *entries, - unsigned int nr_entries, - gfp_t gfp_flags, bool can_alloc); +depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, + unsigned int nr_entries, + gfp_t gfp_flags, + depot_flags_t depot_flags); /** * stack_depot_save - Save a stack trace to stack depot @@ -102,8 +122,11 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, * @nr_entries: Number of frames in the stack * @alloc_flags: Allocation GFP flags * - * Context: Contexts where allocations via alloc_pages() are allowed. - * See __stack_depot_save() for more details. + * Does not increment the refcount on the saved stack trace; see + * stack_depot_save_flags() for more details. + * + * Context: Contexts where allocations via alloc_pages() are allowed; + * see stack_depot_save_flags() for more details. * * Return: Handle of the stack trace stored in depot, 0 on failure */ @@ -142,6 +165,18 @@ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, int spaces); /** + * stack_depot_put - Drop a reference to a stack trace from stack depot + * + * @handle: Stack depot handle returned from stack_depot_save() + * + * The stack trace is evicted from stack depot once all references to it have + * been dropped (once the number of stack_depot_evict() calls matches the + * number of stack_depot_save_flags() calls with STACK_DEPOT_FLAG_GET set for + * this stack trace). + */ +void stack_depot_put(depot_stack_handle_t handle); + +/** * stack_depot_set_extra_bits - Set extra bits in a stack depot handle * * @handle: Stack depot handle returned from stack_depot_save() diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 8abfa1240040..747943bc8cc2 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -41,9 +41,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGSTEAL_KSWAPD, PGSTEAL_DIRECT, PGSTEAL_KHUGEPAGED, - PGDEMOTE_KSWAPD, - PGDEMOTE_DIRECT, - PGDEMOTE_KHUGEPAGED, PGSCAN_KSWAPD, PGSCAN_DIRECT, PGSCAN_KHUGEPAGED, @@ -145,6 +142,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_ZSWAP ZSWPIN, ZSWPOUT, + ZSWPWB, #endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 2a60ce39cfde..08c240e16a01 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -5,19 +5,40 @@ #include <linux/types.h> #include <linux/mm_types.h> +struct lruvec; + extern u64 zswap_pool_total_size; extern atomic_t zswap_stored_pages; #ifdef CONFIG_ZSWAP +struct zswap_lruvec_state { + /* + * Number of pages in zswap that should be protected from the shrinker. + * This number is an estimate of the following counts: + * + * a) Recent page faults. + * b) Recent insertion to the zswap LRU. This includes new zswap stores, + * as well as recent zswap LRU rotations. + * + * These pages are likely to be warm, and might incur IO if the are written + * to swap. + */ + atomic_long_t nr_zswap_protected; +}; + bool zswap_store(struct folio *folio); bool zswap_load(struct folio *folio); void zswap_invalidate(int type, pgoff_t offset); void zswap_swapon(int type); void zswap_swapoff(int type); - +void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg); +void zswap_lruvec_state_init(struct lruvec *lruvec); +void zswap_page_swapin(struct page *page); #else +struct zswap_lruvec_state {}; + static inline bool zswap_store(struct folio *folio) { return false; @@ -31,7 +52,9 @@ static inline bool zswap_load(struct folio *folio) static inline void zswap_invalidate(int type, pgoff_t offset) {} static inline void zswap_swapon(int type) {} static inline void zswap_swapoff(int type) {} - +static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {} +static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {} +static inline void zswap_page_swapin(struct page *page) {} #endif #endif /* _LINUX_ZSWAP_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index da43810b7485..48ad69f7722e 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -316,6 +316,7 @@ typedef int __bitwise __kernel_rwf_t; #define PAGE_IS_SWAPPED (1 << 4) #define PAGE_IS_PFNZERO (1 << 5) #define PAGE_IS_HUGE (1 << 6) +#define PAGE_IS_SOFT_DIRTY (1 << 7) /* * struct page_region - Page region with flags diff --git a/kernel/fork.c b/kernel/fork.c index 10917c3e1f03..93924392a5c3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -650,7 +650,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, int retval; unsigned long charge = 0; LIST_HEAD(uf); - VMA_ITERATOR(old_vmi, oldmm, 0); VMA_ITERATOR(vmi, mm, 0); uprobe_start_dup_mmap(); @@ -678,16 +677,22 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto out; khugepaged_fork(mm, oldmm); - retval = vma_iter_bulk_alloc(&vmi, oldmm->map_count); - if (retval) + /* Use __mt_dup() to efficiently build an identical maple tree. */ + retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); + if (unlikely(retval)) goto out; mt_clear_in_rcu(vmi.mas.tree); - for_each_vma(old_vmi, mpnt) { + for_each_vma(vmi, mpnt) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { + retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, + mpnt->vm_end, GFP_KERNEL); + if (retval) + goto loop_out; + vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } @@ -749,9 +754,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); - /* Link the vma into the MT */ - if (vma_iter_bulk_store(&vmi, tmp)) - goto fail_nomem_vmi_store; + /* + * Link the vma into the MT. After using __mt_dup(), memory + * allocation is not necessary here, so it cannot fail. + */ + vma_iter_bulk_store(&vmi, tmp); mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) @@ -760,15 +767,28 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); - if (retval) + if (retval) { + mpnt = vma_next(&vmi); goto loop_out; + } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); - if (!retval) + if (!retval) { mt_set_in_rcu(vmi.mas.tree); + } else if (mpnt) { + /* + * The entire maple tree has already been duplicated. If the + * mmap duplication fails, mark the failure point with + * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered, + * stop releasing VMAs that have not been duplicated after this + * point. + */ + mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); + mas_store(&vmi.mas, XA_ZERO_ENTRY); + } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); @@ -778,8 +798,6 @@ fail_uprobe_end: uprobe_end_dup_mmap(); return retval; -fail_nomem_vmi_store: - unlink_anon_vmas(tmp); fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: diff --git a/lib/Kconfig b/lib/Kconfig index 3ea1c830efab..5ddda7c2ed9b 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -713,10 +713,20 @@ config ARCH_STACKWALK config STACKDEPOT bool select STACKTRACE + help + Stack depot: stack trace storage that avoids duplication config STACKDEPOT_ALWAYS_INIT bool select STACKDEPOT + help + Always initialize stack depot during early boot + +config STACKDEPOT_MAX_FRAMES + int "Maximum number of frames in trace saved in stack depot" + range 1 256 + default 64 + depends on STACKDEPOT config REF_TRACKER bool diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index fdca89c05745..8653f5c38be7 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -134,7 +134,7 @@ endchoice choice prompt "Instrumentation type" depends on KASAN_GENERIC || KASAN_SW_TAGS - default KASAN_OUTLINE + default KASAN_INLINE if !ARCH_DISABLE_KASAN_INLINE config KASAN_OUTLINE bool "Outline instrumentation" @@ -207,4 +207,25 @@ config KASAN_MODULE_TEST A part of the KASAN test suite that is not integrated with KUnit. Incompatible with Hardware Tag-Based KASAN. +config KASAN_EXTRA_INFO + bool "Record and report more information" + depends on KASAN + help + Record and report more information to help us find the cause of the + bug and to help us correlate the error with other system events. + + Currently, the CPU number and timestamp are additionally + recorded for each heap block at allocation and free time, and + 8 bytes will be added to each metadata structure that records + allocation or free information. + + In Generic KASAN, each kmalloc-8 and kmalloc-16 object will add + 16 bytes of additional memory consumption, and each kmalloc-32 + object will add 8 bytes of additional memory consumption, not + affecting other larger objects. + + In SW_TAGS KASAN and HW_TAGS KASAN, depending on the stack_ring_size + boot parameter, it will add 8 * stack_ring_size bytes of additional + memory consumption. + endif # KASAN diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 684689457d77..d30815cbab80 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4,6 +4,8 @@ * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> * Matthew Wilcox <willy@infradead.org> + * Copyright (c) 2023 ByteDance + * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* @@ -165,6 +167,11 @@ static inline int mt_alloc_bulk(gfp_t gfp, size_t size, void **nodes) return kmem_cache_alloc_bulk(maple_node_cache, gfp, size, nodes); } +static inline void mt_free_one(struct maple_node *node) +{ + kmem_cache_free(maple_node_cache, node); +} + static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); @@ -205,23 +212,29 @@ static unsigned int mas_mt_height(struct ma_state *mas) return mt_height(mas->tree); } -static inline enum maple_type mte_node_type(const struct maple_enode *entry) +static inline unsigned int mt_attr(struct maple_tree *mt) +{ + return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; +} + +static __always_inline enum maple_type mte_node_type( + const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } -static inline bool ma_is_dense(const enum maple_type type) +static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } -static inline bool ma_is_leaf(const enum maple_type type) +static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } -static inline bool mte_is_leaf(const struct maple_enode *entry) +static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } @@ -230,60 +243,50 @@ static inline bool mte_is_leaf(const struct maple_enode *entry) * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ -static inline bool mt_is_reserved(const void *entry) +static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } -static inline void mas_set_err(struct ma_state *mas, long err) +static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); + mas->status = ma_error; } -static inline bool mas_is_ptr(const struct ma_state *mas) +static __always_inline bool mas_is_ptr(const struct ma_state *mas) { - return mas->node == MAS_ROOT; + return mas->status == ma_root; } -static inline bool mas_is_start(const struct ma_state *mas) +static __always_inline bool mas_is_start(const struct ma_state *mas) { - return mas->node == MAS_START; + return mas->status == ma_start; } -bool mas_is_err(struct ma_state *mas) +static __always_inline bool mas_is_none(const struct ma_state *mas) { - return xa_is_err(mas->node); + return mas->status == ma_none; } -static __always_inline bool mas_is_overflow(struct ma_state *mas) +static __always_inline bool mas_is_paused(const struct ma_state *mas) { - if (unlikely(mas->node == MAS_OVERFLOW)) - return true; - - return false; + return mas->status == ma_pause; } -static __always_inline bool mas_is_underflow(struct ma_state *mas) +static __always_inline bool mas_is_overflow(struct ma_state *mas) { - if (unlikely(mas->node == MAS_UNDERFLOW)) - return true; - - return false; + return mas->status == ma_overflow; } -static inline bool mas_searchable(struct ma_state *mas) +static inline bool mas_is_underflow(struct ma_state *mas) { - if (mas_is_none(mas)) - return false; - - if (mas_is_ptr(mas)) - return false; - - return true; + return mas->status == ma_underflow; } -static inline struct maple_node *mte_to_node(const struct maple_enode *entry) +static __always_inline struct maple_node *mte_to_node( + const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } @@ -360,12 +363,12 @@ static inline bool mte_has_null(const struct maple_enode *node) return (unsigned long)node & MAPLE_ENODE_NULL; } -static inline bool ma_is_root(struct maple_node *node) +static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } -static inline bool mte_is_root(const struct maple_enode *node) +static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } @@ -375,7 +378,7 @@ static inline bool mas_is_root_limits(const struct ma_state *mas) return !mas->min && mas->max == ULONG_MAX; } -static inline bool mt_is_alloc(struct maple_tree *mt) +static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } @@ -514,11 +517,12 @@ void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, * * Return: The slot in the parent node where @enode resides. */ -static inline unsigned int mte_parent_slot(const struct maple_enode *enode) +static __always_inline +unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; - if (val & MA_ROOT_PARENT) + if (unlikely(val & MA_ROOT_PARENT)) return 0; /* @@ -534,7 +538,8 @@ static inline unsigned int mte_parent_slot(const struct maple_enode *enode) * * Return: The parent maple node. */ -static inline struct maple_node *mte_parent(const struct maple_enode *enode) +static __always_inline +struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); @@ -546,7 +551,7 @@ static inline struct maple_node *mte_parent(const struct maple_enode *enode) * * Return: true if dead, false otherwise. */ -static inline bool ma_dead_node(const struct maple_node *node) +static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; @@ -562,7 +567,7 @@ static inline bool ma_dead_node(const struct maple_node *node) * * Return: true if dead, false otherwise. */ -static inline bool mte_dead_node(const struct maple_enode *enode) +static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *parent, *node; @@ -680,35 +685,6 @@ static inline unsigned long *ma_gaps(struct maple_node *node, } /* - * mas_pivot() - Get the pivot at @piv of the maple encoded node. - * @mas: The maple state. - * @piv: The pivot. - * - * Return: the pivot at @piv of @mn. - */ -static inline unsigned long mas_pivot(struct ma_state *mas, unsigned char piv) -{ - struct maple_node *node = mas_mn(mas); - enum maple_type type = mte_node_type(mas->node); - - if (MAS_WARN_ON(mas, piv >= mt_pivots[type])) { - mas_set_err(mas, -EIO); - return 0; - } - - switch (type) { - case maple_arange_64: - return node->ma64.pivot[piv]; - case maple_range_64: - case maple_leaf_64: - return node->mr64.pivot[piv]; - case maple_dense: - return 0; - } - return 0; -} - -/* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots @@ -718,7 +694,7 @@ static inline unsigned long mas_pivot(struct ma_state *mas, unsigned char piv) * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ -static inline unsigned long +static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { @@ -759,7 +735,6 @@ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, BUG_ON(piv >= mt_pivots[type]); switch (type) { - default: case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; @@ -783,7 +758,6 @@ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { - default: case maple_arange_64: return mn->ma64.slot; case maple_range_64: @@ -792,6 +766,8 @@ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) case maple_dense: return mn->slot; } + + return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) @@ -800,20 +776,20 @@ static inline bool mt_write_locked(const struct maple_tree *mt) lockdep_is_held(&mt->ma_lock); } -static inline bool mt_locked(const struct maple_tree *mt) +static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } -static inline void *mt_slot(const struct maple_tree *mt, +static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } -static inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, - unsigned char offset) +static __always_inline void *mt_slot_locked(struct maple_tree *mt, + void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } @@ -825,8 +801,8 @@ static inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, * * Return: The entry stored in @slots at the @offset. */ -static inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, - unsigned char offset) +static __always_inline void *mas_slot_locked(struct ma_state *mas, + void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } @@ -839,8 +815,8 @@ static inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, * * Return: The entry stored in @slots at the @offset */ -static inline void *mas_slot(struct ma_state *mas, void __rcu **slots, - unsigned char offset) +static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, + unsigned char offset) { return mt_slot(mas->tree, slots, offset); } @@ -851,7 +827,7 @@ static inline void *mas_slot(struct ma_state *mas, void __rcu **slots, * * Return: The pointer to the root of the tree */ -static inline void *mas_root(struct ma_state *mas) +static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } @@ -954,10 +930,8 @@ static inline unsigned char ma_meta_end(struct maple_node *mn, /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node - * @mt: The maple node type */ -static inline unsigned char ma_meta_gap(struct maple_node *mn, - enum maple_type mt) +static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } @@ -1112,14 +1086,16 @@ static int mas_ascend(struct ma_state *mas) return 0; } - if (!mas->min) + min = 0; + max = ULONG_MAX; + if (!mas->offset) { + min = mas->min; set_min = true; + } if (mas->max == ULONG_MAX) set_max = true; - min = 0; - max = ULONG_MAX; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); @@ -1258,6 +1234,7 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) if (mas->mas_flags & MA_STATE_PREALLOC) { if (allocated) return; + BUG_ON(!allocated); WARN_ON(!allocated); } @@ -1363,14 +1340,14 @@ static void mas_node_count(struct ma_state *mas, int count) * mas_start() - Sets up maple state for operations. * @mas: The maple state. * - * If mas->node == MAS_START, then set the min, max and depth to + * If mas->status == mas_start, then set the min, max and depth to * defaults. * * Return: - * - If mas->node is an error or not MAS_START, return NULL. - * - If it's an empty tree: NULL & mas->node == MAS_NONE - * - If it's a single entry: The entry & mas->node == MAS_ROOT - * - If it's a tree: NULL & mas->node == safe root node. + * - If mas->node is an error or not mas_start, return NULL. + * - If it's an empty tree: NULL & mas->status == ma_none + * - If it's a single entry: The entry & mas->status == mas_root + * - If it's a tree: NULL & mas->status == safe root node. */ static inline struct maple_enode *mas_start(struct ma_state *mas) { @@ -1386,6 +1363,7 @@ retry: /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; + mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) @@ -1396,13 +1374,14 @@ retry: /* empty tree */ if (unlikely(!root)) { - mas->node = MAS_NONE; + mas->node = NULL; + mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ - mas->node = MAS_ROOT; + mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ @@ -1425,10 +1404,8 @@ retry: * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ -static inline unsigned char ma_data_end(struct maple_node *node, - enum maple_type type, - unsigned long *pivots, - unsigned long max) +static __always_inline unsigned char ma_data_end(struct maple_node *node, + enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; @@ -1608,7 +1585,7 @@ static inline unsigned long mas_max_gap(struct ma_state *mas) node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); - offset = ma_meta_gap(node, mt); + offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } @@ -1639,7 +1616,7 @@ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); - meta_offset = ma_meta_gap(pnode, pmt); + meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; @@ -1987,27 +1964,13 @@ complete: /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. - * @mas: The maple state * @node: The maple node - * @pivots: pointer to the maple node pivots * @mt: The maple type - * @end: The assumed end - * - * Note, end may be incremented within this function but not modified at the - * source. This is fine since the metadata is the last thing to be stored in a - * node during a write. + * @end: The node end */ -static inline void mas_leaf_set_meta(struct ma_state *mas, - struct maple_node *node, unsigned long *pivots, +static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { - /* There is no room for metadata already */ - if (mt_pivots[mt] <= end) - return; - - if (pivots[end] && pivots[end] < mas->max) - end++; - if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } @@ -2064,7 +2027,7 @@ static inline void mab_mas_cp(struct maple_big_node *b_node, ma_set_meta(node, mt, offset, end); } else { - mas_leaf_set_meta(mas, node, pivots, mt, end); + mas_leaf_set_meta(node, mt, end); } } @@ -2152,11 +2115,11 @@ static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas, } slot = offset_end + 1; - if (slot > wr_mas->node_end) + if (slot > mas->end) goto b_end; /* Copy end data to the end of the node. */ - mas_mab_cp(mas, slot, wr_mas->node_end + 1, b_node, ++b_end); + mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end); b_node->b_end--; return; @@ -2211,19 +2174,21 @@ static inline bool mas_next_sibling(struct ma_state *mas) } /* - * mte_node_or_node() - Return the encoded node or MAS_NONE. + * mte_node_or_none() - Set the enode and state. * @enode: The encoded maple node. * - * Shorthand to avoid setting %NULLs in the tree or maple_subtree_state. - * - * Return: @enode or MAS_NONE + * Set the node to the enode and the status. */ -static inline struct maple_enode *mte_node_or_none(struct maple_enode *enode) +static inline void mas_node_or_none(struct ma_state *mas, + struct maple_enode *enode) { - if (enode) - return enode; - - return ma_enode_ptr(MAS_NONE); + if (enode) { + mas->node = enode; + mas->status = ma_active; + } else { + mas->node = NULL; + mas->status = ma_none; + } } /* @@ -2245,8 +2210,8 @@ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); - count = wr_mas->node_end = ma_data_end(wr_mas->node, wr_mas->type, - wr_mas->pivots, mas->max); + count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, + wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) @@ -2543,13 +2508,15 @@ static inline void mast_set_split_parents(struct maple_subtree_state *mast, * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, - struct maple_enode *enode, bool in_rcu) + struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; + struct maple_enode *enode; - if (enode == MAS_NONE) + if (mas_is_none(tmp_mas)) return; + enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); if (in_rcu) @@ -2589,8 +2556,8 @@ static inline void mas_topiary_replace(struct ma_state *mas, /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; - tmp[1].node = MAS_NONE; - tmp[2].node = MAS_NONE; + tmp[1].status = ma_none; + tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { @@ -2610,7 +2577,7 @@ static inline void mas_topiary_replace(struct ma_state *mas, break; while (n < 3) - tmp_next[n++].node = MAS_NONE; + tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; @@ -2623,8 +2590,8 @@ static inline void mas_topiary_replace(struct ma_state *mas, tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; - tmp[1].node = MAS_NONE; - tmp[2].node = MAS_NONE; + tmp[1].status = ma_none; + tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; @@ -2639,7 +2606,7 @@ static inline void mas_topiary_replace(struct ma_state *mas, if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); - tmp_next[n].node = MAS_NONE; + tmp_next[n].status = ma_none; } else { n++; } @@ -2650,16 +2617,16 @@ static inline void mas_topiary_replace(struct ma_state *mas, break; while (n < 3) - tmp_next[n++].node = MAS_NONE; + tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { - mas_topiary_node(mas, tmp[i].node, in_rcu); + mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) - mas_topiary_node(mas, tmp[i].node, in_rcu); + mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } @@ -2698,9 +2665,9 @@ static inline void mast_cp_to_nodes(struct maple_subtree_state *mast, { bool new_lmax = true; - mast->l->node = mte_node_or_none(left); - mast->m->node = mte_node_or_none(middle); - mast->r->node = mte_node_or_none(right); + mas_node_or_none(mast->l, left); + mas_node_or_none(mast->m, middle); + mas_node_or_none(mast->r, right); mast->l->min = mast->orig_l->min; if (split == mast->bn->b_end) { @@ -2796,32 +2763,29 @@ static inline void *mtree_range_walk(struct ma_state *mas) min = mas->min; max = mas->max; do { - offset = 0; last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); - if (unlikely(ma_dead_node(node))) - goto dead_node; - - if (pivots[offset] >= mas->index) { - prev_max = max; - prev_min = min; - max = pivots[offset]; + prev_min = min; + prev_max = max; + if (pivots[0] >= mas->index) { + offset = 0; + max = pivots[0]; goto next; } - do { + offset = 1; + while (offset < end) { + if (pivots[offset] >= mas->index) { + max = pivots[offset]; + break; + } offset++; - } while ((offset < end) && (pivots[offset] < mas->index)); + } - prev_min = min; min = pivots[offset - 1] + 1; - prev_max = max; - if (likely(offset < end && pivots[offset])) - max = pivots[offset]; - next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); @@ -2829,6 +2793,7 @@ next: goto dead_node; } while (!ma_is_leaf(type)); + mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; @@ -2879,7 +2844,7 @@ static int mas_spanning_rebalance(struct ma_state *mas, mast->l = &l_mas; mast->m = &m_mas; mast->r = &r_mas; - l_mas.node = r_mas.node = m_mas.node = MAS_NONE; + l_mas.status = r_mas.status = m_mas.status = ma_none; /* Check if this is not root and has sufficient data. */ if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) && @@ -3167,7 +3132,7 @@ done: * @mas: The maple state * @height: The height of the tree in case it's a new root. */ -static inline bool mas_split_final_node(struct maple_subtree_state *mast, +static inline void mas_split_final_node(struct maple_subtree_state *mast, struct ma_state *mas, int height) { struct maple_enode *ancestor; @@ -3191,7 +3156,6 @@ static inline bool mas_split_final_node(struct maple_subtree_state *mast, mast->l->node = ancestor; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, mast->l, true); mas->offset = mast->bn->b_end - 1; - return true; } /* @@ -3406,7 +3370,6 @@ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node) /* Try to push left. */ if (mas_push_data(mas, height, &mast, true)) break; - /* Try to push right. */ if (mas_push_data(mas, height, &mast, false)) break; @@ -3495,6 +3458,7 @@ static noinline_for_kasan int mas_commit_b_node(struct ma_wr_state *wr_mas, mas_replace_node(wr_mas->mas, old_enode); reuse_node: mas_update_gap(wr_mas->mas); + wr_mas->mas->end = b_end; return 1; } @@ -3521,6 +3485,7 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry) slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); + mas->status = ma_active; if (mas->index) { if (contents) { @@ -3553,7 +3518,7 @@ static inline void mas_store_root(struct ma_state *mas, void *entry) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); - mas->node = MAS_START; + mas->status = ma_start; } } @@ -3730,23 +3695,17 @@ static inline void *mtree_lookup_walk(struct ma_state *mas) enum maple_type type; void __rcu **slots; unsigned char end; - unsigned long max; next = mas->node; - max = ULONG_MAX; do { - offset = 0; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); - end = ma_data_end(node, type, pivots, max); - if (unlikely(ma_dead_node(node))) - goto dead_node; + end = mt_pivots[type]; + offset = 0; do { - if (pivots[offset] >= mas->index) { - max = pivots[offset]; + if (pivots[offset] >= mas->index) break; - } } while (++offset < end); slots = ma_slots(node, type); @@ -3785,7 +3744,7 @@ static inline int mas_new_root(struct ma_state *mas, void *entry) mas->depth = 0; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, entry); - mas->node = MAS_START; + mas->status = ma_start; goto done; } @@ -3798,6 +3757,7 @@ static inline int mas_new_root(struct ma_state *mas, void *entry) slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); + mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mas->depth = 1; @@ -3891,10 +3851,10 @@ static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas) memset(&b_node, 0, sizeof(struct maple_big_node)); /* Copy l_mas and store the value in b_node. */ - mas_store_b_node(&l_wr_mas, &b_node, l_wr_mas.node_end); + mas_store_b_node(&l_wr_mas, &b_node, l_mas.end); /* Copy r_mas into b_node. */ - if (r_mas.offset <= r_wr_mas.node_end) - mas_mab_cp(&r_mas, r_mas.offset, r_wr_mas.node_end, + if (r_mas.offset <= r_mas.end) + mas_mab_cp(&r_mas, r_mas.offset, r_mas.end, &b_node, b_node.b_end + 1); else b_node.b_end++; @@ -3936,7 +3896,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, if (mas->last == wr_mas->end_piv) offset_end++; /* don't copy this offset */ else if (unlikely(wr_mas->r_max == ULONG_MAX)) - mas_bulk_rebalance(mas, wr_mas->node_end, wr_mas->type); + mas_bulk_rebalance(mas, mas->end, wr_mas->type); /* set up node. */ if (in_rcu) { @@ -3972,12 +3932,12 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, * this range wrote to the end of the node or it overwrote the rest of * the data */ - if (offset_end > wr_mas->node_end) + if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ - copy_size = wr_mas->node_end - offset_end + 1; + copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, @@ -3987,7 +3947,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, dst_pivots[new_end] = mas->max; done: - mas_leaf_set_meta(mas, newnode, dst_pivots, maple_leaf_64, new_end); + mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; @@ -3998,6 +3958,7 @@ done: } trace_ma_write(__func__, mas, 0, wr_mas->entry); mas_update_gap(mas); + mas->end = new_end; return true; } @@ -4063,10 +4024,10 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && - (wr_mas->node_end != wr_mas->offset_end) && + (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; - if (wr_mas->offset_end == wr_mas->node_end) + if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; @@ -4091,11 +4052,11 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { - while ((wr_mas->offset_end < wr_mas->node_end) && + while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; - if (wr_mas->offset_end < wr_mas->node_end) + if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; @@ -4107,7 +4068,7 @@ static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; - unsigned char new_end = wr_mas->node_end + 2; + unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) @@ -4141,10 +4102,7 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas, if (mt_in_rcu(mas->tree)) return false; - if (mas->offset != wr_mas->node_end) - return false; - - end = wr_mas->node_end; + end = mas->end; if (mas->offset != end) return false; @@ -4178,6 +4136,7 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas, if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); + mas->end = new_end; trace_ma_write(__func__, mas, new_end, wr_mas->entry); return true; } @@ -4195,7 +4154,7 @@ static void mas_wr_bnode(struct ma_wr_state *wr_mas) trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); - mas_commit_b_node(wr_mas, &b_node, wr_mas->node_end); + mas_commit_b_node(wr_mas, &b_node, wr_mas->mas->end); } static inline void mas_wr_modify(struct ma_wr_state *wr_mas) @@ -4223,7 +4182,7 @@ static inline void mas_wr_modify(struct ma_wr_state *wr_mas) if (mas_wr_append(wr_mas, new_end)) return; - if (new_end == wr_mas->node_end && mas_wr_slot_store(wr_mas)) + if (new_end == mas->end && mas_wr_slot_store(wr_mas)) return; if (mas_wr_node_store(wr_mas, new_end)) @@ -4328,7 +4287,7 @@ exists: } -static inline void mas_rewalk(struct ma_state *mas, unsigned long index) +static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); @@ -4337,7 +4296,7 @@ retry: goto retry; } -static inline bool mas_rewalk_if_dead(struct ma_state *mas, +static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { @@ -4349,14 +4308,16 @@ static inline bool mas_rewalk_if_dead(struct ma_state *mas, /* * mas_prev_node() - Find the prev non-null entry at the same level in the - * tree. The prev value will be mas->node[mas->offset] or MAS_NONE. + * tree. The prev value will be mas->node[mas->offset] or the status will be + * ma_none. * @mas: The maple state * @min: The lower limit to search * - * The prev node value will be mas->node[mas->offset] or MAS_NONE. + * The prev node value will be mas->node[mas->offset] or the status will be + * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ -static inline int mas_prev_node(struct ma_state *mas, unsigned long min) +static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; @@ -4416,13 +4377,14 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min) if (unlikely(mte_dead_node(mas->node))) return 1; + mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; - mas->node = MAS_NONE; + mas->status = ma_underflow; return 0; } @@ -4436,8 +4398,7 @@ no_entry: * * Return: The entry in the previous slot which is possibly NULL */ -static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty, - bool set_underflow) +static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; @@ -4470,13 +4431,16 @@ again: mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { + if (mas->index <= min) + goto underflow; + if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } - if (mas_is_none(mas)) - goto underflow; + if (WARN_ON_ONCE(mas_is_underflow(mas))) + return NULL; mas->last = mas->max; node = mas_mn(mas); @@ -4490,12 +4454,15 @@ again: if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; + if (likely(entry)) return entry; if (!empty) { - if (mas->index <= min) - goto underflow; + if (mas->index <= min) { + mas->status = ma_underflow; + return NULL; + } goto again; } @@ -4503,8 +4470,7 @@ again: return entry; underflow: - if (set_underflow) - mas->node = MAS_UNDERFLOW; + mas->status = ma_underflow; return NULL; } @@ -4513,28 +4479,30 @@ underflow: * @mas: The maple state * @max: The maximum pivot value to check. * - * The next value will be mas->node[mas->offset] or MAS_NONE. + * The next value will be mas->node[mas->offset] or the status will have + * overflowed. * Return: 1 on dead node, 0 otherwise. */ -static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, - unsigned long max) +static int mas_next_node(struct ma_state *mas, struct maple_node *node, + unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; + struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) - goto no_entry; + goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) - goto no_entry; + goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) @@ -4574,6 +4542,10 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); + tmp = mte_to_node(enode); + mt = mte_node_type(enode); + pivots = ma_pivots(tmp, mt); + mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; @@ -4581,11 +4553,11 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, mas->min = min; return 0; -no_entry: +overflow: if (unlikely(ma_dead_node(node))) return 1; - mas->node = MAS_NONE; + mas->status = ma_overflow; return 0; } @@ -4600,15 +4572,13 @@ no_entry: * * Return: The entry in the next slot which is possibly NULL */ -static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty, - bool set_overflow) +static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; - unsigned char data_end; unsigned long save_point = mas->last; void *entry; @@ -4616,42 +4586,45 @@ retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); - data_end = ma_data_end(node, type, pivots, mas->max); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { - if (likely(mas->offset < data_end)) + if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else - goto overflow; + pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; - if (pivot >= max) - goto overflow; + if (pivot >= max) { /* Was at the limit, next will extend beyond */ + mas->status = ma_overflow; + return NULL; + } } - if (likely(mas->offset < data_end)) { + if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; - if (likely(mas->offset < data_end)) + if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { + if (mas->last >= max) { + mas->status = ma_overflow; + return NULL; + } + if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } - if (WARN_ON_ONCE(mas_is_none(mas))) { - mas->node = MAS_OVERFLOW; + if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; - goto overflow; - } mas->offset = 0; mas->index = mas->min; @@ -4669,21 +4642,18 @@ again: if (entry) return entry; + if (!empty) { - if (mas->last >= max) - goto overflow; + if (mas->last >= max) { + mas->status = ma_overflow; + return NULL; + } mas->index = mas->last + 1; - /* Node cannot end on NULL, so it's safe to short-cut here */ goto again; } return entry; - -overflow: - if (set_overflow) - mas->node = MAS_OVERFLOW; - return NULL; } /* @@ -4702,11 +4672,11 @@ overflow: static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) { if (mas->last >= limit) { - mas->node = MAS_OVERFLOW; + mas->status = ma_overflow; return NULL; } - return mas_next_slot(mas, limit, false, true); + return mas_next_slot(mas, limit, false); } /* @@ -4874,7 +4844,7 @@ done: * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If - * mas->node is MAS_NONE, reset to MAS_START. + * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ @@ -4883,7 +4853,7 @@ void *mas_walk(struct ma_state *mas) void *entry; if (!mas_is_active(mas) || !mas_is_start(mas)) - mas->node = MAS_START; + mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { @@ -4899,7 +4869,7 @@ retry: mas->index = 1; mas->last = ULONG_MAX; - mas->node = MAS_NONE; + mas->status = ma_none; return NULL; } @@ -5026,6 +4996,7 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned char offset; unsigned long *pivots; enum maple_type mt; + struct maple_node *node; if (min > max) return -EINVAL; @@ -5056,12 +5027,14 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, if (unlikely(offset == MAPLE_NODE_SLOTS)) return -EBUSY; + node = mas_mn(mas); mt = mte_node_type(mas->node); - pivots = ma_pivots(mas_mn(mas), mt); + pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; + mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); @@ -5122,6 +5095,7 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, mas->last = max; mas->index = mas->last - size + 1; + mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); @@ -5566,7 +5540,7 @@ void mas_destroy(struct ma_state *mas) mas_start(mas); mtree_range_walk(mas); - end = mas_data_end(mas) + 1; + end = mas->end + 1; if (end < mt_min_slot_count(mas->node) - 1) mas_destroy_rebalance(mas, end); @@ -5584,7 +5558,7 @@ void mas_destroy(struct ma_state *mas) mt_free_bulk(count, (void __rcu **)&node->slot[1]); total -= count; } - kmem_cache_free(maple_node_cache, node); + mt_free_one(ma_mnode_ptr(node)); total--; } @@ -5654,33 +5628,46 @@ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries) } EXPORT_SYMBOL_GPL(mas_expected_entries); -static inline bool mas_next_setup(struct ma_state *mas, unsigned long max, +static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { - mas->node = MAS_OVERFLOW; + mas->status = ma_overflow; return true; } - if (mas_is_active(mas)) + switch (mas->status) { + case ma_active: return false; - - if (mas_is_none(mas) || mas_is_paused(mas)) { - mas->node = MAS_START; - } else if (mas_is_overflow(mas)) { + case ma_none: + fallthrough; + case ma_pause: + mas->status = ma_start; + fallthrough; + case ma_start: + mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ + break; + case ma_overflow: /* Overflowed before, but the max changed */ - mas->node = MAS_START; - } else if (mas_is_underflow(mas)) { - mas->node = MAS_START; + mas->status = ma_active; + break; + case ma_underflow: + /* The user expects the mas to be one before where it is */ + mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; + break; + case ma_root: + break; + case ma_error: + return true; } - if (mas_is_start(mas)) - *entry = mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ + if (likely(mas_is_active(mas))) /* Fast path */ + return false; if (mas_is_ptr(mas)) { *entry = NULL; @@ -5690,7 +5677,7 @@ static inline bool mas_next_setup(struct ma_state *mas, unsigned long max, } mas->index = 1; mas->last = ULONG_MAX; - mas->node = MAS_NONE; + mas->status = ma_none; return true; } @@ -5719,7 +5706,7 @@ void *mas_next(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, false, true); + return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); @@ -5742,7 +5729,7 @@ void *mas_next_range(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, true, true); + return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); @@ -5770,37 +5757,48 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) } EXPORT_SYMBOL_GPL(mt_next); -static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min, - void **entry) +static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { - mas->node = MAS_UNDERFLOW; + mas->status = ma_underflow; return true; } - if (mas_is_active(mas)) + switch (mas->status) { + case ma_active: return false; - - if (mas_is_overflow(mas)) { - mas->node = MAS_START; + case ma_start: + break; + case ma_none: + fallthrough; + case ma_pause: + mas->status = ma_start; + break; + case ma_underflow: + /* underflowed before but the min changed */ + mas->status = ma_active; + break; + case ma_overflow: + /* User expects mas to be one after where it is */ + mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; - } - - if (mas_is_none(mas) || mas_is_paused(mas)) { - mas->node = MAS_START; - } else if (mas_is_underflow(mas)) { - /* underflowed before but the min changed */ - mas->node = MAS_START; + break; + case ma_root: + break; + case ma_error: + return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { - if (!mas->index) - goto none; + if (!mas->index) { + mas->status = ma_none; + return true; + } mas->index = mas->last = 0; *entry = mas_root(mas); return true; @@ -5810,7 +5808,7 @@ static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min, if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; - mas->node = MAS_ROOT; + mas->status = ma_root; *entry = mas_root(mas); return true; } @@ -5818,10 +5816,6 @@ static inline bool mas_prev_setup(struct ma_state *mas, unsigned long min, } return false; - -none: - mas->node = MAS_NONE; - return true; } /** @@ -5830,7 +5824,7 @@ none: * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. - * Will reset mas to MAS_START if the node is MAS_NONE. Will stop on not + * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. @@ -5842,7 +5836,7 @@ void *mas_prev(struct ma_state *mas, unsigned long min) if (mas_prev_setup(mas, min, &entry)) return entry; - return mas_prev_slot(mas, min, false, true); + return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); @@ -5853,7 +5847,7 @@ EXPORT_SYMBOL_GPL(mas_prev); * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. - * Will reset mas to MAS_START if the node is MAS_NONE. Will stop on not + * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. @@ -5865,7 +5859,7 @@ void *mas_prev_range(struct ma_state *mas, unsigned long min) if (mas_prev_setup(mas, min, &entry)) return entry; - return mas_prev_slot(mas, min, true, true); + return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); @@ -5908,7 +5902,8 @@ EXPORT_SYMBOL_GPL(mt_prev); */ void mas_pause(struct ma_state *mas) { - mas->node = MAS_PAUSE; + mas->status = ma_pause; + mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); @@ -5920,35 +5915,54 @@ EXPORT_SYMBOL_GPL(mas_pause); * * Returns: True if entry is the answer, false otherwise. */ -static inline bool mas_find_setup(struct ma_state *mas, unsigned long max, - void **entry) +static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { - if (mas_is_active(mas)) { + switch (mas->status) { + case ma_active: if (mas->last < max) return false; - return true; - } - - if (mas_is_paused(mas)) { + case ma_start: + break; + case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; - mas->node = MAS_START; - } else if (mas_is_none(mas)) { + mas->status = ma_start; + break; + case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; - mas->node = MAS_START; - } else if (mas_is_overflow(mas) || mas_is_underflow(mas)) { - if (mas->index > max) { - mas->node = MAS_OVERFLOW; + mas->status = ma_start; + break; + case ma_underflow: + /* mas is pointing at entry before unable to go lower */ + if (unlikely(mas->index >= max)) { + mas->status = ma_overflow; return true; } - mas->node = MAS_START; + mas->status = ma_active; + *entry = mas_walk(mas); + if (*entry) + return true; + break; + case ma_overflow: + if (unlikely(mas->last >= max)) + return true; + + mas->status = ma_active; + *entry = mas_walk(mas); + if (*entry) + return true; + break; + case ma_root: + break; + case ma_error: + return true; } if (mas_is_start(mas)) { @@ -5962,12 +5976,11 @@ static inline bool mas_find_setup(struct ma_state *mas, unsigned long max, } - if (unlikely(!mas_searchable(mas))) { - if (unlikely(mas_is_ptr(mas))) - goto ptr_out_of_range; + if (unlikely(mas_is_ptr(mas))) + goto ptr_out_of_range; + if (unlikely(mas_is_none(mas))) return true; - } if (mas->index == max) return true; @@ -5975,7 +5988,7 @@ static inline bool mas_find_setup(struct ma_state *mas, unsigned long max, return false; ptr_out_of_range: - mas->node = MAS_NONE; + mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; @@ -5989,7 +6002,7 @@ ptr_out_of_range: * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. - * May set @mas->node to MAS_NONE. + * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ @@ -6001,7 +6014,10 @@ void *mas_find(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, false, false); + entry = mas_next_slot(mas, max, false); + /* Ignore overflow */ + mas->status = ma_active; + return entry; } EXPORT_SYMBOL_GPL(mas_find); @@ -6013,7 +6029,7 @@ EXPORT_SYMBOL_GPL(mas_find); * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. - * May set @mas->node to MAS_NONE. + * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ @@ -6025,7 +6041,7 @@ void *mas_find_range(struct ma_state *mas, unsigned long max) return entry; /* Retries on dead nodes handled by mas_next_slot */ - return mas_next_slot(mas, max, true, false); + return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); @@ -6037,36 +6053,48 @@ EXPORT_SYMBOL_GPL(mas_find_range); * * Returns: True if entry is the answer, false otherwise. */ -static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, +static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { - if (mas_is_active(mas)) { - if (mas->index > min) - return false; - - return true; - } - if (mas_is_paused(mas)) { + switch (mas->status) { + case ma_active: + goto active; + case ma_start: + break; + case ma_pause: if (unlikely(mas->index <= min)) { - mas->node = MAS_NONE; + mas->status = ma_underflow; return true; } - mas->node = MAS_START; mas->last = --mas->index; - } else if (mas_is_none(mas)) { + mas->status = ma_start; + break; + case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; - mas->node = MAS_START; - } else if (mas_is_underflow(mas) || mas_is_overflow(mas)) { - if (mas->last <= min) { - mas->node = MAS_UNDERFLOW; + mas->status = ma_start; + break; + case ma_overflow: /* user expects the mas to be one after where it is */ + if (unlikely(mas->index <= min)) { + mas->status = ma_underflow; return true; } - mas->node = MAS_START; + mas->status = ma_active; + break; + case ma_underflow: /* user expects the mas to be one before where it is */ + if (unlikely(mas->index <= min)) + return true; + + mas->status = ma_active; + break; + case ma_root: + break; + case ma_error: + return true; } if (mas_is_start(mas)) { @@ -6079,29 +6107,28 @@ static inline bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, return true; } - if (unlikely(!mas_searchable(mas))) { - if (mas_is_ptr(mas)) - goto none; + if (unlikely(mas_is_ptr(mas))) + goto none; - if (mas_is_none(mas)) { - /* - * Walked to the location, and there was nothing so the - * previous location is 0. - */ - mas->last = mas->index = 0; - mas->node = MAS_ROOT; - *entry = mas_root(mas); - return true; - } + if (unlikely(mas_is_none(mas))) { + /* + * Walked to the location, and there was nothing so the previous + * location is 0. + */ + mas->last = mas->index = 0; + mas->status = ma_root; + *entry = mas_root(mas); + return true; } +active: if (mas->index < min) return true; return false; none: - mas->node = MAS_NONE; + mas->status = ma_none; return true; } @@ -6114,7 +6141,7 @@ none: * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. - * May set @mas->node to MAS_NONE. + * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ @@ -6126,7 +6153,7 @@ void *mas_find_rev(struct ma_state *mas, unsigned long min) return entry; /* Retries on dead nodes handled by mas_prev_slot */ - return mas_prev_slot(mas, min, false, false); + return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); @@ -6140,7 +6167,7 @@ EXPORT_SYMBOL_GPL(mas_find_rev); * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. - * May set @mas->node to MAS_NONE. + * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ @@ -6152,7 +6179,7 @@ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) return entry; /* Retries on dead nodes handled by mas_prev_slot */ - return mas_prev_slot(mas, min, true, false); + return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); @@ -6172,8 +6199,8 @@ void *mas_erase(struct ma_state *mas) void *entry; MA_WR_STATE(wr_mas, mas, NULL); - if (mas_is_none(mas) || mas_is_paused(mas)) - mas->node = MAS_START; + if (!mas_is_active(mas) || !mas_is_start(mas)) + mas->status = ma_start; /* Retry unnecessary when holding the write lock. */ entry = mas_state_walk(mas); @@ -6218,7 +6245,7 @@ bool mas_nomem(struct ma_state *mas, gfp_t gfp) if (!mas_allocated(mas)) return false; - mas->node = MAS_START; + mas->status = ma_start; return true; } @@ -6476,6 +6503,278 @@ void *mtree_erase(struct maple_tree *mt, unsigned long index) } EXPORT_SYMBOL(mtree_erase); +/* + * mas_dup_free() - Free an incomplete duplication of a tree. + * @mas: The maple state of a incomplete tree. + * + * The parameter @mas->node passed in indicates that the allocation failed on + * this node. This function frees all nodes starting from @mas->node in the + * reverse order of mas_dup_build(). There is no need to hold the source tree + * lock at this time. + */ +static void mas_dup_free(struct ma_state *mas) +{ + struct maple_node *node; + enum maple_type type; + void __rcu **slots; + unsigned char count, i; + + /* Maybe the first node allocation failed. */ + if (mas_is_none(mas)) + return; + + while (!mte_is_root(mas->node)) { + mas_ascend(mas); + if (mas->offset) { + mas->offset--; + do { + mas_descend(mas); + mas->offset = mas_data_end(mas); + } while (!mte_is_leaf(mas->node)); + + mas_ascend(mas); + } + + node = mte_to_node(mas->node); + type = mte_node_type(mas->node); + slots = ma_slots(node, type); + count = mas_data_end(mas) + 1; + for (i = 0; i < count; i++) + ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; + mt_free_bulk(count, slots); + } + + node = mte_to_node(mas->node); + mt_free_one(node); +} + +/* + * mas_copy_node() - Copy a maple node and replace the parent. + * @mas: The maple state of source tree. + * @new_mas: The maple state of new tree. + * @parent: The parent of the new node. + * + * Copy @mas->node to @new_mas->node, set @parent to be the parent of + * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. + */ +static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, + struct maple_pnode *parent) +{ + struct maple_node *node = mte_to_node(mas->node); + struct maple_node *new_node = mte_to_node(new_mas->node); + unsigned long val; + + /* Copy the node completely. */ + memcpy(new_node, node, sizeof(struct maple_node)); + /* Update the parent node pointer. */ + val = (unsigned long)node->parent & MAPLE_NODE_MASK; + new_node->parent = ma_parent_ptr(val | (unsigned long)parent); +} + +/* + * mas_dup_alloc() - Allocate child nodes for a maple node. + * @mas: The maple state of source tree. + * @new_mas: The maple state of new tree. + * @gfp: The GFP_FLAGS to use for allocations. + * + * This function allocates child nodes for @new_mas->node during the duplication + * process. If memory allocation fails, @mas is set to -ENOMEM. + */ +static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, + gfp_t gfp) +{ + struct maple_node *node = mte_to_node(mas->node); + struct maple_node *new_node = mte_to_node(new_mas->node); + enum maple_type type; + unsigned char request, count, i; + void __rcu **slots; + void __rcu **new_slots; + unsigned long val; + + /* Allocate memory for child nodes. */ + type = mte_node_type(mas->node); + new_slots = ma_slots(new_node, type); + request = mas_data_end(mas) + 1; + count = mt_alloc_bulk(gfp, request, (void **)new_slots); + if (unlikely(count < request)) { + memset(new_slots, 0, request * sizeof(void *)); + mas_set_err(mas, -ENOMEM); + return; + } + + /* Restore node type information in slots. */ + slots = ma_slots(node, type); + for (i = 0; i < count; i++) { + val = (unsigned long)mt_slot_locked(mas->tree, slots, i); + val &= MAPLE_NODE_MASK; + ((unsigned long *)new_slots)[i] |= val; + } +} + +/* + * mas_dup_build() - Build a new maple tree from a source tree + * @mas: The maple state of source tree, need to be in MAS_START state. + * @new_mas: The maple state of new tree, need to be in MAS_START state. + * @gfp: The GFP_FLAGS to use for allocations. + * + * This function builds a new tree in DFS preorder. If the memory allocation + * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the + * last node. mas_dup_free() will free the incomplete duplication of a tree. + * + * Note that the attributes of the two trees need to be exactly the same, and the + * new tree needs to be empty, otherwise -EINVAL will be set in @mas. + */ +static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, + gfp_t gfp) +{ + struct maple_node *node; + struct maple_pnode *parent = NULL; + struct maple_enode *root; + enum maple_type type; + + if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || + unlikely(!mtree_empty(new_mas->tree))) { + mas_set_err(mas, -EINVAL); + return; + } + + root = mas_start(mas); + if (mas_is_ptr(mas) || mas_is_none(mas)) + goto set_new_tree; + + node = mt_alloc_one(gfp); + if (!node) { + new_mas->status = ma_none; + mas_set_err(mas, -ENOMEM); + return; + } + + type = mte_node_type(mas->node); + root = mt_mk_node(node, type); + new_mas->node = root; + new_mas->min = 0; + new_mas->max = ULONG_MAX; + root = mte_mk_root(root); + while (1) { + mas_copy_node(mas, new_mas, parent); + if (!mte_is_leaf(mas->node)) { + /* Only allocate child nodes for non-leaf nodes. */ + mas_dup_alloc(mas, new_mas, gfp); + if (unlikely(mas_is_err(mas))) + return; + } else { + /* + * This is the last leaf node and duplication is + * completed. + */ + if (mas->max == ULONG_MAX) + goto done; + + /* This is not the last leaf node and needs to go up. */ + do { + mas_ascend(mas); + mas_ascend(new_mas); + } while (mas->offset == mas_data_end(mas)); + + /* Move to the next subtree. */ + mas->offset++; + new_mas->offset++; + } + + mas_descend(mas); + parent = ma_parent_ptr(mte_to_node(new_mas->node)); + mas_descend(new_mas); + mas->offset = 0; + new_mas->offset = 0; + } +done: + /* Specially handle the parent of the root node. */ + mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); +set_new_tree: + /* Make them the same height */ + new_mas->tree->ma_flags = mas->tree->ma_flags; + rcu_assign_pointer(new_mas->tree->ma_root, root); +} + +/** + * __mt_dup(): Duplicate an entire maple tree + * @mt: The source maple tree + * @new: The new maple tree + * @gfp: The GFP_FLAGS to use for allocations + * + * This function duplicates a maple tree in Depth-First Search (DFS) pre-order + * traversal. It uses memcpy() to copy nodes in the source tree and allocate + * new child nodes in non-leaf nodes. The new node is exactly the same as the + * source node except for all the addresses stored in it. It will be faster than + * traversing all elements in the source tree and inserting them one by one into + * the new tree. + * The user needs to ensure that the attributes of the source tree and the new + * tree are the same, and the new tree needs to be an empty tree, otherwise + * -EINVAL will be returned. + * Note that the user needs to manually lock the source tree and the new tree. + * + * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If + * the attributes of the two trees are different or the new tree is not an empty + * tree. + */ +int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) +{ + int ret = 0; + MA_STATE(mas, mt, 0, 0); + MA_STATE(new_mas, new, 0, 0); + + mas_dup_build(&mas, &new_mas, gfp); + if (unlikely(mas_is_err(&mas))) { + ret = xa_err(mas.node); + if (ret == -ENOMEM) + mas_dup_free(&new_mas); + } + + return ret; +} +EXPORT_SYMBOL(__mt_dup); + +/** + * mtree_dup(): Duplicate an entire maple tree + * @mt: The source maple tree + * @new: The new maple tree + * @gfp: The GFP_FLAGS to use for allocations + * + * This function duplicates a maple tree in Depth-First Search (DFS) pre-order + * traversal. It uses memcpy() to copy nodes in the source tree and allocate + * new child nodes in non-leaf nodes. The new node is exactly the same as the + * source node except for all the addresses stored in it. It will be faster than + * traversing all elements in the source tree and inserting them one by one into + * the new tree. + * The user needs to ensure that the attributes of the source tree and the new + * tree are the same, and the new tree needs to be an empty tree, otherwise + * -EINVAL will be returned. + * + * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If + * the attributes of the two trees are different or the new tree is not an empty + * tree. + */ +int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) +{ + int ret = 0; + MA_STATE(mas, mt, 0, 0); + MA_STATE(new_mas, new, 0, 0); + + mas_lock(&new_mas); + mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); + mas_dup_build(&mas, &new_mas, gfp); + mas_unlock(&mas); + if (unlikely(mas_is_err(&mas))) { + ret = xa_err(mas.node); + if (ret == -ENOMEM) + mas_dup_free(&new_mas); + } + + mas_unlock(&new_mas); + return ret; +} +EXPORT_SYMBOL(mtree_dup); + /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree @@ -6490,7 +6789,7 @@ void __mt_destroy(struct maple_tree *mt) if (xa_is_node(root)) mte_destroy_walk(root, mt); - mt->ma_flags = 0; + mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); @@ -6549,7 +6848,7 @@ retry: if (entry) goto unlock; - while (mas_searchable(&mas) && (mas.last < max)) { + while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_entry(&mas, max); if (likely(entry && !xa_is_zero(entry))) break; @@ -6631,26 +6930,6 @@ unsigned int mt_nr_allocated(void) return kmem_cache_nr_allocated(maple_node_cache); } -/* - * mas_dead_node() - Check if the maple state is pointing to a dead node. - * @mas: The maple state - * @index: The index to restore in @mas. - * - * Used in test code. - * Return: 1 if @mas has been reset to MAS_START, 0 otherwise. - */ -static inline int mas_dead_node(struct ma_state *mas, unsigned long index) -{ - if (unlikely(!mas_searchable(mas) || mas_is_start(mas))) - return 0; - - if (likely(!mte_dead_node(mas->node))) - return 0; - - mas_rewalk(mas, index); - return 1; -} - void mt_cache_shrink(void) { } @@ -6689,11 +6968,11 @@ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { - struct maple_enode *p = MAS_NONE, *mn = mas->node; + struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); - if (!mas_is_none(mas)) + if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) @@ -6706,7 +6985,7 @@ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); - } while (!mas_is_none(mas)); + } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; @@ -6729,7 +7008,6 @@ static void mt_dump_range(unsigned long min, unsigned long max, else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; - default: case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); @@ -6769,7 +7047,6 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry, case mt_dump_hex: pr_cont("%p %lX ", node->slot[i], node->pivot[i]); break; - default: case mt_dump_dec: pr_cont("%p %lu ", node->slot[i], node->pivot[i]); } @@ -6799,7 +7076,6 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry, pr_err("node %p last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; - default: case mt_dump_dec: pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); @@ -6824,7 +7100,6 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; - default: case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } @@ -6835,7 +7110,6 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, case mt_dump_hex: pr_cont("%p %lX ", node->slot[i], node->pivot[i]); break; - default: case mt_dump_dec: pr_cont("%p %lu ", node->slot[i], node->pivot[i]); } @@ -6976,7 +7250,8 @@ static void mas_validate_gaps(struct ma_state *mas) counted: if (mt == maple_arange_64) { - offset = ma_meta_gap(node, mt); + MT_BUG_ON(mas->tree, !gaps); + offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset %p[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); @@ -6988,7 +7263,6 @@ counted: MT_BUG_ON(mas->tree, 1); } - MT_BUG_ON(mas->tree, !gaps); for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap %p[%u] beyond node limit != 0\n", @@ -7166,7 +7440,7 @@ static void mt_validate_nulls(struct maple_tree *mt) MA_STATE(mas, mt, 0, 0); mas_start(&mas); - if (mas_is_none(&mas) || (mas.node == MAS_ROOT)) + if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) @@ -7183,7 +7457,7 @@ static void mt_validate_nulls(struct maple_tree *mt) last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); - if (mas_is_none(&mas)) + if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), @@ -7192,7 +7466,7 @@ static void mt_validate_nulls(struct maple_tree *mt) offset++; } - } while (!mas_is_none(&mas)); + } while (!mas_is_overflow(&mas)); } /* @@ -7207,13 +7481,13 @@ void mt_validate(struct maple_tree *mt) MA_STATE(mas, mt, 0, 0); rcu_read_lock(); mas_start(&mas); - if (!mas_searchable(&mas)) + if (!mas_is_active(&mas)) goto done; while (!mte_is_leaf(mas.node)) mas_descend(&mas); - while (!mas_is_none(&mas)) { + while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && @@ -7238,16 +7512,35 @@ EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=%p enode=%p ", mas->tree, mas->node); - if (mas_is_none(mas)) - pr_err("(MAS_NONE) "); - else if (mas_is_ptr(mas)) - pr_err("(MAS_ROOT) "); - else if (mas_is_start(mas)) - pr_err("(MAS_START) "); - else if (mas_is_paused(mas)) - pr_err("(MAS_PAUSED) "); - - pr_err("[%u] index=%lx last=%lx\n", mas->offset, mas->index, mas->last); + switch (mas->status) { + case ma_active: + pr_err("(ma_active)"); + break; + case ma_none: + pr_err("(ma_none)"); + break; + case ma_root: + pr_err("(ma_root)"); + break; + case ma_start: + pr_err("(ma_start) "); + break; + case ma_pause: + pr_err("(ma_pause) "); + break; + case ma_overflow: + pr_err("(ma_overflow) "); + break; + case ma_underflow: + pr_err("(ma_underflow) "); + break; + case ma_error: + pr_err("(ma_error) "); + break; + } + + pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, + mas->index, mas->last); pr_err(" min=%lx max=%lx alloc=%p, depth=%u, flags=%x\n", mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags); if (mas->index > mas->last) @@ -7260,7 +7553,7 @@ void mas_wr_dump(const struct ma_wr_state *wr_mas) pr_err("WR_MAS: node=%p r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", - wr_mas->type, wr_mas->offset_end, wr_mas->node_end, + wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 2f5aa851834e..870cce2f4cbd 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -18,11 +18,14 @@ #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/kmsan.h> +#include <linux/list.h> #include <linux/mm.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/printk.h> +#include <linux/refcount.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/stacktrace.h> #include <linux/stackdepot.h> #include <linux/string.h> @@ -32,14 +35,23 @@ #define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8) -#define DEPOT_VALID_BITS 1 #define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */ #define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER)) #define DEPOT_STACK_ALIGN 4 #define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN) -#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_VALID_BITS - \ - DEPOT_OFFSET_BITS - STACK_DEPOT_EXTRA_BITS) +#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \ + STACK_DEPOT_EXTRA_BITS) +#if IS_ENABLED(CONFIG_KMSAN) && CONFIG_STACKDEPOT_MAX_FRAMES >= 32 +/* + * KMSAN is frequently used in fuzzing scenarios and thus saves a lot of stack + * traces. As KMSAN does not support evicting stack traces from the stack + * depot, the stack depot capacity might be reached quickly with large stack + * records. Adjust the maximum number of stack depot pools for this case. + */ +#define DEPOT_POOLS_CAP (8192 * (CONFIG_STACKDEPOT_MAX_FRAMES / 16)) +#else #define DEPOT_POOLS_CAP 8192 +#endif #define DEPOT_MAX_POOLS \ (((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \ (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP) @@ -50,19 +62,22 @@ union handle_parts { struct { u32 pool_index : DEPOT_POOL_INDEX_BITS; u32 offset : DEPOT_OFFSET_BITS; - u32 valid : DEPOT_VALID_BITS; u32 extra : STACK_DEPOT_EXTRA_BITS; }; }; struct stack_record { - struct stack_record *next; /* Link in the hash table */ - u32 hash; /* Hash in the hash table */ + struct list_head list; /* Links in hash table or freelist */ + u32 hash; /* Hash in hash table */ u32 size; /* Number of stored frames */ union handle_parts handle; - unsigned long entries[]; /* Variable-sized array of frames */ + refcount_t count; + unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */ }; +#define DEPOT_STACK_RECORD_SIZE \ + ALIGN(sizeof(struct stack_record), 1 << DEPOT_STACK_ALIGN) + static bool stack_depot_disabled; static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT); static bool __stack_depot_early_init_passed __initdata; @@ -75,40 +90,34 @@ static bool __stack_depot_early_init_passed __initdata; /* Initial seed for jhash2. */ #define STACK_HASH_SEED 0x9747b28c -/* Hash table of pointers to stored stack traces. */ -static struct stack_record **stack_table; +/* Hash table of stored stack records. */ +static struct list_head *stack_table; /* Fixed order of the number of table buckets. Used when KASAN is enabled. */ static unsigned int stack_bucket_number_order; /* Hash mask for indexing the table. */ static unsigned int stack_hash_mask; -/* Array of memory regions that store stack traces. */ +/* Array of memory regions that store stack records. */ static void *stack_pools[DEPOT_MAX_POOLS]; -/* Currently used pool in stack_pools. */ -static int pool_index; -/* Offset to the unused space in the currently used pool. */ -static size_t pool_offset; -/* Lock that protects the variables above. */ -static DEFINE_RAW_SPINLOCK(pool_lock); +/* Newly allocated pool that is not yet added to stack_pools. */ +static void *new_pool; +/* Number of pools in stack_pools. */ +static int pools_num; +/* Freelist of stack records within stack_pools. */ +static LIST_HEAD(free_stacks); /* * Stack depot tries to keep an extra pool allocated even before it runs out - * of space in the currently used pool. - * This flag marks that this next extra pool needs to be allocated and - * initialized. It has the value 0 when either the next pool is not yet - * initialized or the limit on the number of pools is reached. + * of space in the currently used pool. This flag marks whether this extra pool + * needs to be allocated. It has the value 0 when either an extra pool is not + * yet allocated or if the limit on the number of pools is reached. */ -static int next_pool_required = 1; +static bool new_pool_required = true; +/* Lock that protects the variables above. */ +static DEFINE_RWLOCK(pool_rwlock); static int __init disable_stack_depot(char *str) { - int ret; - - ret = kstrtobool(str, &stack_depot_disabled); - if (!ret && stack_depot_disabled) { - pr_info("disabled\n"); - stack_table = NULL; - } - return 0; + return kstrtobool(str, &stack_depot_disabled); } early_param("stack_depot_disable", disable_stack_depot); @@ -120,6 +129,15 @@ void __init stack_depot_request_early_init(void) __stack_depot_early_init_requested = true; } +/* Initialize list_head's within the hash table. */ +static void init_stack_table(unsigned long entries) +{ + unsigned long i; + + for (i = 0; i < entries; i++) + INIT_LIST_HEAD(&stack_table[i]); +} + /* Allocates a hash table via memblock. Can only be used during early boot. */ int __init stack_depot_early_init(void) { @@ -131,6 +149,15 @@ int __init stack_depot_early_init(void) __stack_depot_early_init_passed = true; /* + * Print disabled message even if early init has not been requested: + * stack_depot_init() will not print one. + */ + if (stack_depot_disabled) { + pr_info("disabled\n"); + return 0; + } + + /* * If KASAN is enabled, use the maximum order: KASAN is frequently used * in fuzzing scenarios, which leads to a large number of different * stack traces being stored in stack depot. @@ -138,21 +165,25 @@ int __init stack_depot_early_init(void) if (kasan_enabled() && !stack_bucket_number_order) stack_bucket_number_order = STACK_BUCKET_NUMBER_ORDER_MAX; - if (!__stack_depot_early_init_requested || stack_depot_disabled) + /* + * Check if early init has been requested after setting + * stack_bucket_number_order: stack_depot_init() uses its value. + */ + if (!__stack_depot_early_init_requested) return 0; /* * If stack_bucket_number_order is not set, leave entries as 0 to rely - * on the automatic calculations performed by alloc_large_system_hash. + * on the automatic calculations performed by alloc_large_system_hash(). */ if (stack_bucket_number_order) entries = 1UL << stack_bucket_number_order; pr_info("allocating hash table via alloc_large_system_hash\n"); stack_table = alloc_large_system_hash("stackdepot", - sizeof(struct stack_record *), + sizeof(struct list_head), entries, STACK_HASH_TABLE_SCALE, - HASH_EARLY | HASH_ZERO, + HASH_EARLY, NULL, &stack_hash_mask, 1UL << STACK_BUCKET_NUMBER_ORDER_MIN, @@ -162,6 +193,14 @@ int __init stack_depot_early_init(void) stack_depot_disabled = true; return -ENOMEM; } + if (!entries) { + /* + * Obtain the number of entries that was calculated by + * alloc_large_system_hash(). + */ + entries = stack_hash_mask + 1; + } + init_stack_table(entries); return 0; } @@ -202,7 +241,7 @@ int stack_depot_init(void) entries = 1UL << STACK_BUCKET_NUMBER_ORDER_MAX; pr_info("allocating hash table of %lu entries via kvcalloc\n", entries); - stack_table = kvcalloc(entries, sizeof(struct stack_record *), GFP_KERNEL); + stack_table = kvcalloc(entries, sizeof(struct list_head), GFP_KERNEL); if (!stack_table) { pr_err("hash table allocation failed, disabling\n"); stack_depot_disabled = true; @@ -210,6 +249,7 @@ int stack_depot_init(void) goto out_unlock; } stack_hash_mask = entries - 1; + init_stack_table(entries); out_unlock: mutex_unlock(&stack_depot_init_mutex); @@ -218,41 +258,103 @@ out_unlock: } EXPORT_SYMBOL_GPL(stack_depot_init); -/* Uses preallocated memory to initialize a new stack depot pool. */ -static void depot_init_pool(void **prealloc) +/* Initializes a stack depol pool. */ +static void depot_init_pool(void *pool) { + int offset; + + lockdep_assert_held_write(&pool_rwlock); + + WARN_ON(!list_empty(&free_stacks)); + + /* Initialize handles and link stack records into the freelist. */ + for (offset = 0; offset <= DEPOT_POOL_SIZE - DEPOT_STACK_RECORD_SIZE; + offset += DEPOT_STACK_RECORD_SIZE) { + struct stack_record *stack = pool + offset; + + stack->handle.pool_index = pools_num; + stack->handle.offset = offset >> DEPOT_STACK_ALIGN; + stack->handle.extra = 0; + + list_add(&stack->list, &free_stacks); + } + + /* Save reference to the pool to be used by depot_fetch_stack(). */ + stack_pools[pools_num] = pool; + pools_num++; +} + +/* Keeps the preallocated memory to be used for a new stack depot pool. */ +static void depot_keep_new_pool(void **prealloc) +{ + lockdep_assert_held_write(&pool_rwlock); + /* - * If the next pool is already initialized or the maximum number of + * If a new pool is already saved or the maximum number of * pools is reached, do not use the preallocated memory. - * smp_load_acquire() here pairs with smp_store_release() below and - * in depot_alloc_stack(). */ - if (!smp_load_acquire(&next_pool_required)) + if (!new_pool_required) return; - /* Check if the current pool is not yet allocated. */ - if (stack_pools[pool_index] == NULL) { - /* Use the preallocated memory for the current pool. */ - stack_pools[pool_index] = *prealloc; + /* + * Use the preallocated memory for the new pool + * as long as we do not exceed the maximum number of pools. + */ + if (pools_num < DEPOT_MAX_POOLS) { + new_pool = *prealloc; *prealloc = NULL; - } else { - /* - * Otherwise, use the preallocated memory for the next pool - * as long as we do not exceed the maximum number of pools. - */ - if (pool_index + 1 < DEPOT_MAX_POOLS) { - stack_pools[pool_index + 1] = *prealloc; - *prealloc = NULL; - } - /* - * At this point, either the next pool is initialized or the - * maximum number of pools is reached. In either case, take - * note that initializing another pool is not required. - * This smp_store_release pairs with smp_load_acquire() above - * and in stack_depot_save(). - */ - smp_store_release(&next_pool_required, 0); } + + /* + * At this point, either a new pool is kept or the maximum + * number of pools is reached. In either case, take note that + * keeping another pool is not required. + */ + new_pool_required = false; +} + +/* Updates references to the current and the next stack depot pools. */ +static bool depot_update_pools(void **prealloc) +{ + lockdep_assert_held_write(&pool_rwlock); + + /* Check if we still have objects in the freelist. */ + if (!list_empty(&free_stacks)) + goto out_keep_prealloc; + + /* Check if we have a new pool saved and use it. */ + if (new_pool) { + depot_init_pool(new_pool); + new_pool = NULL; + + /* Take note that we might need a new new_pool. */ + if (pools_num < DEPOT_MAX_POOLS) + new_pool_required = true; + + /* Try keeping the preallocated memory for new_pool. */ + goto out_keep_prealloc; + } + + /* Bail out if we reached the pool limit. */ + if (unlikely(pools_num >= DEPOT_MAX_POOLS)) { + WARN_ONCE(1, "Stack depot reached limit capacity"); + return false; + } + + /* Check if we have preallocated memory and use it. */ + if (*prealloc) { + depot_init_pool(*prealloc); + *prealloc = NULL; + return true; + } + + return false; + +out_keep_prealloc: + /* Keep the preallocated memory for a new pool if required. */ + if (*prealloc) + depot_keep_new_pool(prealloc); + return true; } /* Allocates a new stack in a stack depot pool. */ @@ -260,62 +362,72 @@ static struct stack_record * depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc) { struct stack_record *stack; - size_t required_size = struct_size(stack, entries, size); - required_size = ALIGN(required_size, 1 << DEPOT_STACK_ALIGN); + lockdep_assert_held_write(&pool_rwlock); - /* Check if there is not enough space in the current pool. */ - if (unlikely(pool_offset + required_size > DEPOT_POOL_SIZE)) { - /* Bail out if we reached the pool limit. */ - if (unlikely(pool_index + 1 >= DEPOT_MAX_POOLS)) { - WARN_ONCE(1, "Stack depot reached limit capacity"); - return NULL; - } + /* Update current and new pools if required and possible. */ + if (!depot_update_pools(prealloc)) + return NULL; - /* - * Move on to the next pool. - * WRITE_ONCE pairs with potential concurrent read in - * stack_depot_fetch(). - */ - WRITE_ONCE(pool_index, pool_index + 1); - pool_offset = 0; - /* - * If the maximum number of pools is not reached, take note - * that the next pool needs to initialized. - * smp_store_release() here pairs with smp_load_acquire() in - * stack_depot_save() and depot_init_pool(). - */ - if (pool_index + 1 < DEPOT_MAX_POOLS) - smp_store_release(&next_pool_required, 1); - } + /* Check if we have a stack record to save the stack trace. */ + if (list_empty(&free_stacks)) + return NULL; - /* Assign the preallocated memory to a pool if required. */ - if (*prealloc) - depot_init_pool(prealloc); + /* Get and unlink the first entry from the freelist. */ + stack = list_first_entry(&free_stacks, struct stack_record, list); + list_del(&stack->list); - /* Check if we have a pool to save the stack trace. */ - if (stack_pools[pool_index] == NULL) - return NULL; + /* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */ + if (size > CONFIG_STACKDEPOT_MAX_FRAMES) + size = CONFIG_STACKDEPOT_MAX_FRAMES; /* Save the stack trace. */ - stack = stack_pools[pool_index] + pool_offset; stack->hash = hash; stack->size = size; - stack->handle.pool_index = pool_index; - stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN; - stack->handle.valid = 1; - stack->handle.extra = 0; + /* stack->handle is already filled in by depot_init_pool(). */ + refcount_set(&stack->count, 1); memcpy(stack->entries, entries, flex_array_size(stack, entries, size)); - pool_offset += required_size; + /* * Let KMSAN know the stored stack record is initialized. This shall * prevent false positive reports if instrumented code accesses it. */ - kmsan_unpoison_memory(stack, required_size); + kmsan_unpoison_memory(stack, DEPOT_STACK_RECORD_SIZE); return stack; } +static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle) +{ + union handle_parts parts = { .handle = handle }; + void *pool; + size_t offset = parts.offset << DEPOT_STACK_ALIGN; + struct stack_record *stack; + + lockdep_assert_held(&pool_rwlock); + + if (parts.pool_index > pools_num) { + WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n", + parts.pool_index, pools_num, handle); + return NULL; + } + + pool = stack_pools[parts.pool_index]; + if (!pool) + return NULL; + + stack = pool + offset; + return stack; +} + +/* Links stack into the freelist. */ +static void depot_free_stack(struct stack_record *stack) +{ + lockdep_assert_held_write(&pool_rwlock); + + list_add(&stack->list, &free_stacks); +} + /* Calculates the hash for a stack. */ static inline u32 hash_stack(unsigned long *entries, unsigned int size) { @@ -340,13 +452,17 @@ int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2, } /* Finds a stack in a bucket of the hash table. */ -static inline struct stack_record *find_stack(struct stack_record *bucket, +static inline struct stack_record *find_stack(struct list_head *bucket, unsigned long *entries, int size, u32 hash) { + struct list_head *pos; struct stack_record *found; - for (found = bucket; found; found = found->next) { + lockdep_assert_held(&pool_rwlock); + + list_for_each(pos, bucket) { + found = list_entry(pos, struct stack_record, list); if (found->hash == hash && found->size == size && !stackdepot_memcmp(entries, found->entries, size)) @@ -355,17 +471,24 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, return NULL; } -depot_stack_handle_t __stack_depot_save(unsigned long *entries, - unsigned int nr_entries, - gfp_t alloc_flags, bool can_alloc) +depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, + unsigned int nr_entries, + gfp_t alloc_flags, + depot_flags_t depot_flags) { - struct stack_record *found = NULL, **bucket; - union handle_parts retval = { .handle = 0 }; + struct list_head *bucket; + struct stack_record *found = NULL; + depot_stack_handle_t handle = 0; struct page *page = NULL; void *prealloc = NULL; + bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC; + bool need_alloc = false; unsigned long flags; u32 hash; + if (WARN_ON(depot_flags & ~STACK_DEPOT_FLAGS_MASK)) + return 0; + /* * If this stack trace is from an interrupt, including anything before * interrupt entry usually leads to unbounded stack depot growth. @@ -377,28 +500,33 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, nr_entries = filter_irq_stacks(entries, nr_entries); if (unlikely(nr_entries == 0) || stack_depot_disabled) - goto fast_exit; + return 0; hash = hash_stack(entries, nr_entries); bucket = &stack_table[hash & stack_hash_mask]; - /* - * Fast path: look the stack trace up without locking. - * The smp_load_acquire() here pairs with smp_store_release() to - * |bucket| below. - */ - found = find_stack(smp_load_acquire(bucket), entries, nr_entries, hash); - if (found) + read_lock_irqsave(&pool_rwlock, flags); + + /* Fast path: look the stack trace up without full locking. */ + found = find_stack(bucket, entries, nr_entries, hash); + if (found) { + if (depot_flags & STACK_DEPOT_FLAG_GET) + refcount_inc(&found->count); + read_unlock_irqrestore(&pool_rwlock, flags); goto exit; + } + + /* Take note if another stack pool needs to be allocated. */ + if (new_pool_required) + need_alloc = true; + + read_unlock_irqrestore(&pool_rwlock, flags); /* - * Check if another stack pool needs to be initialized. If so, allocate - * the memory now - we won't be able to do that under the lock. - * - * The smp_load_acquire() here pairs with smp_store_release() to - * |next_pool_inited| in depot_alloc_stack() and depot_init_pool(). + * Allocate memory for a new pool if required now: + * we won't be able to do that under the lock. */ - if (unlikely(can_alloc && smp_load_acquire(&next_pool_required))) { + if (unlikely(can_alloc && need_alloc)) { /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic @@ -412,63 +540,54 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, prealloc = page_address(page); } - raw_spin_lock_irqsave(&pool_lock, flags); + write_lock_irqsave(&pool_rwlock, flags); - found = find_stack(*bucket, entries, nr_entries, hash); + found = find_stack(bucket, entries, nr_entries, hash); if (!found) { struct stack_record *new = depot_alloc_stack(entries, nr_entries, hash, &prealloc); if (new) { - new->next = *bucket; - /* - * This smp_store_release() pairs with - * smp_load_acquire() from |bucket| above. - */ - smp_store_release(bucket, new); + list_add(&new->list, bucket); found = new; } - } else if (prealloc) { + } else { + if (depot_flags & STACK_DEPOT_FLAG_GET) + refcount_inc(&found->count); /* * Stack depot already contains this stack trace, but let's - * keep the preallocated memory for the future. + * keep the preallocated memory for future. */ - depot_init_pool(&prealloc); + if (prealloc) + depot_keep_new_pool(&prealloc); } - raw_spin_unlock_irqrestore(&pool_lock, flags); + write_unlock_irqrestore(&pool_rwlock, flags); exit: if (prealloc) { /* Stack depot didn't use this memory, free it. */ free_pages((unsigned long)prealloc, DEPOT_POOL_ORDER); } if (found) - retval.handle = found->handle.handle; -fast_exit: - return retval.handle; + handle = found->handle.handle; + return handle; } -EXPORT_SYMBOL_GPL(__stack_depot_save); +EXPORT_SYMBOL_GPL(stack_depot_save_flags); depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t alloc_flags) { - return __stack_depot_save(entries, nr_entries, alloc_flags, true); + return stack_depot_save_flags(entries, nr_entries, alloc_flags, + STACK_DEPOT_FLAG_CAN_ALLOC); } EXPORT_SYMBOL_GPL(stack_depot_save); unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries) { - union handle_parts parts = { .handle = handle }; - /* - * READ_ONCE pairs with potential concurrent write in - * depot_alloc_stack. - */ - int pool_index_cached = READ_ONCE(pool_index); - void *pool; - size_t offset = parts.offset << DEPOT_STACK_ALIGN; struct stack_record *stack; + unsigned long flags; *entries = NULL; /* @@ -477,24 +596,47 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, */ kmsan_unpoison_memory(entries, sizeof(*entries)); - if (!handle) + if (!handle || stack_depot_disabled) return 0; - if (parts.pool_index > pool_index_cached) { - WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n", - parts.pool_index, pool_index_cached, handle); - return 0; - } - pool = stack_pools[parts.pool_index]; - if (!pool) - return 0; - stack = pool + offset; + read_lock_irqsave(&pool_rwlock, flags); + + stack = depot_fetch_stack(handle); + + read_unlock_irqrestore(&pool_rwlock, flags); *entries = stack->entries; return stack->size; } EXPORT_SYMBOL_GPL(stack_depot_fetch); +void stack_depot_put(depot_stack_handle_t handle) +{ + struct stack_record *stack; + unsigned long flags; + + if (!handle || stack_depot_disabled) + return; + + write_lock_irqsave(&pool_rwlock, flags); + + stack = depot_fetch_stack(handle); + if (WARN_ON(!stack)) + goto out; + + if (refcount_dec_and_test(&stack->count)) { + /* Unlink stack from the hash table. */ + list_del(&stack->list); + + /* Free stack. */ + depot_free_stack(stack); + } + +out: + write_unlock_irqrestore(&pool_rwlock, flags); +} +EXPORT_SYMBOL_GPL(stack_depot_put); + void stack_depot_print(depot_stack_handle_t stack) { unsigned long *entries; diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 464eeb90d5ad..29185ac5c727 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -43,6 +43,7 @@ atomic_t maple_tree_tests_passed; /* #define BENCH_NODE_STORE */ /* #define BENCH_AWALK */ /* #define BENCH_WALK */ +/* #define BENCH_LOAD */ /* #define BENCH_MT_FOR_EACH */ /* #define BENCH_FORK */ /* #define BENCH_MAS_FOR_EACH */ @@ -54,6 +55,11 @@ atomic_t maple_tree_tests_passed; #else #define cond_resched() do {} while (0) #endif + +#define mas_is_none(x) ((x)->status == ma_none) +#define mas_is_overflow(x) ((x)->status == ma_overflow) +#define mas_is_underflow(x) ((x)->status == ma_underflow) + static int __init mtree_insert_index(struct maple_tree *mt, unsigned long index, gfp_t gfp) { @@ -582,7 +588,7 @@ static noinline void __init check_find(struct maple_tree *mt) MT_BUG_ON(mt, last != mas.last); - mas.node = MAS_NONE; + mas.status = ma_none; mas.index = ULONG_MAX; mas.last = ULONG_MAX; entry2 = mas_prev(&mas, 0); @@ -1749,6 +1755,19 @@ static noinline void __init bench_walk(struct maple_tree *mt) } #endif +#if defined(BENCH_LOAD) +static noinline void __init bench_load(struct maple_tree *mt) +{ + int i, max = 2500, count = 550000000; + + for (i = 0; i < max; i += 10) + mtree_store_range(mt, i, i + 5, xa_mk_value(i), GFP_KERNEL); + + for (i = 0; i < count; i++) + mtree_load(mt, 1470); +} +#endif + #if defined(BENCH_MT_FOR_EACH) static noinline void __init bench_mt_for_each(struct maple_tree *mt) { @@ -1834,47 +1853,48 @@ static noinline void __init bench_mas_prev(struct maple_tree *mt) } #endif /* check_forking - simulate the kernel forking sequence with the tree. */ -static noinline void __init check_forking(struct maple_tree *mt) +static noinline void __init check_forking(void) { - - struct maple_tree newmt; - int i, nr_entries = 134; + struct maple_tree mt, newmt; + int i, nr_entries = 134, ret; void *val; - MA_STATE(mas, mt, 0, 0); - MA_STATE(newmas, mt, 0, 0); - struct rw_semaphore newmt_lock; + MA_STATE(mas, &mt, 0, 0); + MA_STATE(newmas, &newmt, 0, 0); + struct rw_semaphore mt_lock, newmt_lock; + init_rwsem(&mt_lock); init_rwsem(&newmt_lock); - for (i = 0; i <= nr_entries; i++) - mtree_store_range(mt, i*10, i*10 + 5, - xa_mk_value(i), GFP_KERNEL); + mt_init_flags(&mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); + mt_set_external_lock(&mt, &mt_lock); - mt_set_non_kernel(99999); mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); mt_set_external_lock(&newmt, &newmt_lock); - newmas.tree = &newmt; - mas_reset(&newmas); - mas_reset(&mas); - down_write(&newmt_lock); - mas.index = 0; - mas.last = 0; - if (mas_expected_entries(&newmas, nr_entries)) { + + down_write(&mt_lock); + for (i = 0; i <= nr_entries; i++) { + mas_set_range(&mas, i*10, i*10 + 5); + mas_store_gfp(&mas, xa_mk_value(i), GFP_KERNEL); + } + + down_write_nested(&newmt_lock, SINGLE_DEPTH_NESTING); + ret = __mt_dup(&mt, &newmt, GFP_KERNEL); + if (ret) { pr_err("OOM!"); BUG_ON(1); } - rcu_read_lock(); - mas_for_each(&mas, val, ULONG_MAX) { - newmas.index = mas.index; - newmas.last = mas.last; + + mas_set(&newmas, 0); + mas_for_each(&newmas, val, ULONG_MAX) mas_store(&newmas, val); - } - rcu_read_unlock(); + mas_destroy(&newmas); + mas_destroy(&mas); mt_validate(&newmt); - mt_set_non_kernel(0); __mt_destroy(&newmt); + __mt_destroy(&mt); up_write(&newmt_lock); + up_write(&mt_lock); } static noinline void __init check_iteration(struct maple_tree *mt) @@ -1977,49 +1997,51 @@ static noinline void __init check_mas_store_gfp(struct maple_tree *mt) } #if defined(BENCH_FORK) -static noinline void __init bench_forking(struct maple_tree *mt) +static noinline void __init bench_forking(void) { - - struct maple_tree newmt; - int i, nr_entries = 134, nr_fork = 80000; + struct maple_tree mt, newmt; + int i, nr_entries = 134, nr_fork = 80000, ret; void *val; - MA_STATE(mas, mt, 0, 0); - MA_STATE(newmas, mt, 0, 0); - struct rw_semaphore newmt_lock; + MA_STATE(mas, &mt, 0, 0); + MA_STATE(newmas, &newmt, 0, 0); + struct rw_semaphore mt_lock, newmt_lock; + init_rwsem(&mt_lock); init_rwsem(&newmt_lock); - mt_set_external_lock(&newmt, &newmt_lock); - for (i = 0; i <= nr_entries; i++) - mtree_store_range(mt, i*10, i*10 + 5, - xa_mk_value(i), GFP_KERNEL); + mt_init_flags(&mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); + mt_set_external_lock(&mt, &mt_lock); + + down_write(&mt_lock); + for (i = 0; i <= nr_entries; i++) { + mas_set_range(&mas, i*10, i*10 + 5); + mas_store_gfp(&mas, xa_mk_value(i), GFP_KERNEL); + } for (i = 0; i < nr_fork; i++) { - mt_set_non_kernel(99999); - mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE); - newmas.tree = &newmt; - mas_reset(&newmas); - mas_reset(&mas); - mas.index = 0; - mas.last = 0; - rcu_read_lock(); - down_write(&newmt_lock); - if (mas_expected_entries(&newmas, nr_entries)) { - printk("OOM!"); + mt_init_flags(&newmt, + MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); + mt_set_external_lock(&newmt, &newmt_lock); + + down_write_nested(&newmt_lock, SINGLE_DEPTH_NESTING); + ret = __mt_dup(&mt, &newmt, GFP_KERNEL); + if (ret) { + pr_err("OOM!"); BUG_ON(1); } - mas_for_each(&mas, val, ULONG_MAX) { - newmas.index = mas.index; - newmas.last = mas.last; + + mas_set(&newmas, 0); + mas_for_each(&newmas, val, ULONG_MAX) mas_store(&newmas, val); - } + mas_destroy(&newmas); - rcu_read_unlock(); mt_validate(&newmt); - mt_set_non_kernel(0); __mt_destroy(&newmt); up_write(&newmt_lock); } + mas_destroy(&mas); + __mt_destroy(&mt); + up_write(&mt_lock); } #endif @@ -2175,7 +2197,7 @@ static noinline void __init next_prev_test(struct maple_tree *mt) MT_BUG_ON(mt, val != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 5); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); mas.index = 0; mas.last = 5; @@ -3039,10 +3061,6 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt) * DNE active active range of NULL */ -#define mas_active(x) (((x).node != MAS_ROOT) && \ - ((x).node != MAS_START) && \ - ((x).node != MAS_PAUSE) && \ - ((x).node != MAS_NONE)) static noinline void __init check_state_handling(struct maple_tree *mt) { MA_STATE(mas, mt, 0, 0); @@ -3057,7 +3075,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) /* prev: Start -> underflow*/ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, mas.status != ma_underflow); /* prev: Start -> root */ mas_set(&mas, 10); @@ -3065,7 +3083,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* prev: pause -> root */ mas_set(&mas, 10); @@ -3074,7 +3092,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* next: start -> none */ mas_set(&mas, 0); @@ -3082,7 +3100,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* next: start -> none*/ mas_set(&mas, 10); @@ -3090,7 +3108,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find: start -> root */ mas_set(&mas, 0); @@ -3098,21 +3116,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* find: root -> none */ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find: none -> none */ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find: start -> none */ mas_set(&mas, 10); @@ -3120,14 +3138,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find_rev: none -> root */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* find_rev: start -> root */ mas_set(&mas, 0); @@ -3135,21 +3153,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* find_rev: root -> none */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find_rev: none -> none */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* find_rev: start -> root */ mas_set(&mas, 10); @@ -3157,7 +3175,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: start -> none */ mas_set(&mas, 10); @@ -3165,7 +3183,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: pause -> none*/ mas_set(&mas, 10); @@ -3174,7 +3192,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: none -> none */ mas.index = mas.last = 10; @@ -3182,14 +3200,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: none -> none */ entry = mas_walk(&mas); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: start -> root */ mas_set(&mas, 0); @@ -3197,7 +3215,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: pause -> root */ mas_set(&mas, 0); @@ -3206,22 +3224,22 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: none -> root */ - mas.node = MAS_NONE; + mas.status = ma_none; entry = mas_walk(&mas); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: root -> root */ entry = mas_walk(&mas); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); /* walk: root -> none */ mas_set(&mas, 10); @@ -3229,7 +3247,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 1); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_NONE); + MT_BUG_ON(mt, mas.status != ma_none); /* walk: none -> root */ mas.index = mas.last = 0; @@ -3237,7 +3255,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0); - MT_BUG_ON(mt, mas.node != MAS_ROOT); + MT_BUG_ON(mt, mas.status != ma_root); mas_unlock(&mas); @@ -3255,7 +3273,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* next: pause ->active */ mas_set(&mas, 0); @@ -3264,126 +3282,132 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* next: none ->active */ mas.index = mas.last = 0; mas.offset = 0; - mas.node = MAS_NONE; + mas.status = ma_none; entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* next:active ->active */ - entry = mas_next(&mas, ULONG_MAX); + /* next:active ->active (spanning limit) */ + entry = mas_next(&mas, 0x2100); MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* next:active -> active beyond data */ + /* next:active -> overflow (limit reached) beyond data */ entry = mas_next(&mas, 0x2999); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x2501); MT_BUG_ON(mt, mas.last != 0x2fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_overflow(&mas)); - /* Continue after last range ends after max */ + /* next:overflow -> active (limit changed) */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); - MT_BUG_ON(mt, !mas_active(mas)); - - /* next:active -> active continued */ - entry = mas_next(&mas, ULONG_MAX); - MT_BUG_ON(mt, entry != NULL); - MT_BUG_ON(mt, mas.index != 0x3501); - MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* next:active -> overflow */ + /* next:active -> overflow (limit reached) */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x3501); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_OVERFLOW); + MT_BUG_ON(mt, !mas_is_overflow(&mas)); /* next:overflow -> overflow */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x3501); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, mas.node != MAS_OVERFLOW); + MT_BUG_ON(mt, !mas_is_overflow(&mas)); /* prev:overflow -> active */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* next: none -> active, skip value at location */ mas_set(&mas, 0); entry = mas_next(&mas, ULONG_MAX); - mas.node = MAS_NONE; + mas.status = ma_none; mas.offset = 0; entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* prev:active ->active */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* prev:active -> active spanning end range */ + /* prev:active -> underflow (span limit) */ + mas_next(&mas, ULONG_MAX); + entry = mas_prev(&mas, 0x1200); + MT_BUG_ON(mt, entry != ptr); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* spanning limit */ + entry = mas_prev(&mas, 0x1200); /* underflow */ + MT_BUG_ON(mt, entry != NULL); + MT_BUG_ON(mt, mas.index != 0x1000); + MT_BUG_ON(mt, mas.last != 0x1500); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); + + /* prev:underflow -> underflow (lower limit) spanning end range */ entry = mas_prev(&mas, 0x0100); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); - /* prev:active -> underflow */ + /* prev:underflow -> underflow */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* prev:underflow -> underflow */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* next:underflow -> active */ entry = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* prev:first value -> underflow */ entry = mas_prev(&mas, 0x1000); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* find:underflow -> first value */ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* prev: pause ->active */ mas_set(&mas, 0x3600); @@ -3394,21 +3418,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* prev:active -> active spanning min */ + /* prev:active -> underflow spanning min */ entry = mas_prev(&mas, 0x1600); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1FFF); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* prev: active ->active, continue */ entry = mas_prev(&mas, 0); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find: start ->active */ mas_set(&mas, 0); @@ -3416,7 +3440,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find: pause ->active */ mas_set(&mas, 0); @@ -3425,7 +3449,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find: start ->active on value */; mas_set(&mas, 1200); @@ -3433,14 +3457,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find:active ->active */ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find:active -> active (NULL)*/ @@ -3448,35 +3472,35 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x2501); MT_BUG_ON(mt, mas.last != 0x2FFF); - MT_BUG_ON(mt, !mas_active(mas)); + MAS_BUG_ON(&mas, !mas_is_active(&mas)); /* find: overflow ->active */ entry = mas_find(&mas, 0x5000); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find:active -> active (NULL) end*/ entry = mas_find(&mas, ULONG_MAX); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x3501); MT_BUG_ON(mt, mas.last != ULONG_MAX); - MT_BUG_ON(mt, !mas_active(mas)); + MAS_BUG_ON(&mas, !mas_is_active(&mas)); /* find_rev: active (END) ->active */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != ptr3); MT_BUG_ON(mt, mas.index != 0x3000); MT_BUG_ON(mt, mas.last != 0x3500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find_rev:active ->active */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != ptr2); MT_BUG_ON(mt, mas.index != 0x2000); MT_BUG_ON(mt, mas.last != 0x2500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* find_rev: pause ->active */ mas_pause(&mas); @@ -3484,14 +3508,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); - /* find_rev:active -> active */ + /* find_rev:active -> underflow */ entry = mas_find_rev(&mas, 0); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0); MT_BUG_ON(mt, mas.last != 0x0FFF); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_underflow(&mas)); /* find_rev: start ->active */ mas_set(&mas, 0x1200); @@ -3499,7 +3523,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk start ->active */ mas_set(&mas, 0x1200); @@ -3507,7 +3531,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk start ->active */ mas_set(&mas, 0x1600); @@ -3515,7 +3539,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk pause ->active */ mas_set(&mas, 0x1200); @@ -3524,7 +3548,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk pause -> active */ mas_set(&mas, 0x1600); @@ -3533,25 +3557,25 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk none -> active */ mas_set(&mas, 0x1200); - mas.node = MAS_NONE; + mas.status = ma_none; entry = mas_walk(&mas); MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk none -> active */ mas_set(&mas, 0x1600); - mas.node = MAS_NONE; + mas.status = ma_none; entry = mas_walk(&mas); MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk active -> active */ mas.index = 0x1200; @@ -3561,7 +3585,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != ptr); MT_BUG_ON(mt, mas.index != 0x1000); MT_BUG_ON(mt, mas.last != 0x1500); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); /* mas_walk active -> active */ mas.index = 0x1600; @@ -3570,7 +3594,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt) MT_BUG_ON(mt, entry != NULL); MT_BUG_ON(mt, mas.index != 0x1501); MT_BUG_ON(mt, mas.last != 0x1fff); - MT_BUG_ON(mt, !mas_active(mas)); + MT_BUG_ON(mt, !mas_is_active(&mas)); mas_unlock(&mas); } @@ -3585,10 +3609,6 @@ static int __init maple_tree_seed(void) pr_info("\nTEST STARTING\n\n"); - mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); - check_root_expand(&tree); - mtree_destroy(&tree); - #if defined(BENCH_SLOT_STORE) #define BENCH mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); @@ -3617,13 +3637,18 @@ static int __init maple_tree_seed(void) mtree_destroy(&tree); goto skip; #endif -#if defined(BENCH_FORK) +#if defined(BENCH_LOAD) #define BENCH mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); - bench_forking(&tree); + bench_load(&tree); mtree_destroy(&tree); goto skip; #endif +#if defined(BENCH_FORK) +#define BENCH + bench_forking(); + goto skip; +#endif #if defined(BENCH_MT_FOR_EACH) #define BENCH mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); @@ -3647,13 +3672,15 @@ static int __init maple_tree_seed(void) #endif mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); - check_iteration(&tree); + check_root_expand(&tree); mtree_destroy(&tree); mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); - check_forking(&tree); + check_iteration(&tree); mtree_destroy(&tree); + check_forking(); + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); check_mas_store_gfp(&tree); mtree_destroy(&tree); diff --git a/mm/Kconfig b/mm/Kconfig index 57cd378c73d6..8f8b02e9c136 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -61,6 +61,20 @@ config ZSWAP_EXCLUSIVE_LOADS_DEFAULT_ON The cost is that if the page was never dirtied and needs to be swapped out again, it will be re-compressed. +config ZSWAP_SHRINKER_DEFAULT_ON + bool "Shrink the zswap pool on memory pressure" + depends on ZSWAP + default n + help + If selected, the zswap shrinker will be enabled, and the pages + stored in the zswap pool will become available for reclaim (i.e + written back to the backing swap device) on memory pressure. + + This means that zswap writeback could happen even if the pool is + not yet full, or the cgroup zswap limit has not been reached, + reducing the chance that cold pages will reside in the zswap pool + and consume memory indefinitely. + choice prompt "Default compressor" depends on ZSWAP @@ -859,6 +873,12 @@ choice madvise(MADV_HUGEPAGE) but it won't risk to increase the memory footprint of applications without a guaranteed benefit. + + config TRANSPARENT_HUGEPAGE_NEVER + bool "never" + help + Disable Transparent Hugepage by default. It can still be + enabled at runtime via sysfs. endchoice config THP_SWAP @@ -244,7 +244,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, { phys_addr_t memblock_end = memblock_end_of_DRAM(); phys_addr_t highmem_start; - int ret = 0; + int ret; /* * We can't use __pa(high_memory) directly, since high_memory diff --git a/mm/compaction.c b/mm/compaction.c index 01ba298739dd..de15a2ef0af5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1611,6 +1611,9 @@ static void fast_isolate_freepages(struct compact_control *cc) min(pageblock_end_pfn(min_pfn), zone_end_pfn(cc->zone)), cc->zone); + if (page && !suitable_migration_target(cc, page)) + page = NULL; + cc->free_pfn = min_pfn; } } diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h index 649adf91ebc5..6e5e9502d648 100644 --- a/mm/damon/core-test.h +++ b/mm/damon/core-test.h @@ -122,18 +122,25 @@ static void damon_test_split_at(struct kunit *test) { struct damon_ctx *c = damon_new_ctx(); struct damon_target *t; - struct damon_region *r; + struct damon_region *r, *r_new; t = damon_new_target(); r = damon_new_region(0, 100); + r->nr_accesses_bp = 420000; + r->nr_accesses = 42; + r->last_nr_accesses = 15; damon_add_region(r, t); damon_split_region_at(t, r, 25); KUNIT_EXPECT_EQ(test, r->ar.start, 0ul); KUNIT_EXPECT_EQ(test, r->ar.end, 25ul); - r = damon_next_region(r); - KUNIT_EXPECT_EQ(test, r->ar.start, 25ul); - KUNIT_EXPECT_EQ(test, r->ar.end, 100ul); + r_new = damon_next_region(r); + KUNIT_EXPECT_EQ(test, r_new->ar.start, 25ul); + KUNIT_EXPECT_EQ(test, r_new->ar.end, 100ul); + + KUNIT_EXPECT_EQ(test, r->nr_accesses_bp, r_new->nr_accesses_bp); + KUNIT_EXPECT_EQ(test, r->nr_accesses, r_new->nr_accesses); + KUNIT_EXPECT_EQ(test, r->last_nr_accesses, r_new->last_nr_accesses); damon_free_target(t); damon_destroy_ctx(c); @@ -439,6 +446,37 @@ static void damos_test_filter_out(struct kunit *test) damos_free_filter(f); } +static void damon_test_feed_loop_next_input(struct kunit *test) +{ + unsigned long last_input = 900000, current_score = 200; + + /* + * If current score is lower than the goal, which is always 10,000 + * (read the comment on damon_feed_loop_next_input()'s comment), next + * input should be higher than the last input. + */ + KUNIT_EXPECT_GT(test, + damon_feed_loop_next_input(last_input, current_score), + last_input); + + /* + * If current score is higher than the goal, next input should be lower + * than the last input. + */ + current_score = 250000000; + KUNIT_EXPECT_LT(test, + damon_feed_loop_next_input(last_input, current_score), + last_input); + + /* + * The next input depends on the distance between the current score and + * the goal + */ + KUNIT_EXPECT_GT(test, + damon_feed_loop_next_input(last_input, 200), + damon_feed_loop_next_input(last_input, 2000)); +} + static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_test_target), KUNIT_CASE(damon_test_regions), @@ -454,6 +492,7 @@ static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_test_moving_sum), KUNIT_CASE(damos_test_new_filter), KUNIT_CASE(damos_test_filter_out), + KUNIT_CASE(damon_test_feed_loop_next_input), {}, }; diff --git a/mm/damon/core.c b/mm/damon/core.c index 3a05e71509b9..2c0cc65d041e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1043,26 +1043,76 @@ static void damon_do_apply_schemes(struct damon_ctx *c, } } -/* Shouldn't be called if quota->ms and quota->sz are zero */ +/* + * damon_feed_loop_next_input() - get next input to achieve a target score. + * @last_input The last input. + * @score Current score that made with @last_input. + * + * Calculate next input to achieve the target score, based on the last input + * and current score. Assuming the input and the score are positively + * proportional, calculate how much compensation should be added to or + * subtracted from the last input as a proportion of the last input. Avoid + * next input always being zero by setting it non-zero always. In short form + * (assuming support of float and signed calculations), the algorithm is as + * below. + * + * next_input = max(last_input * ((goal - current) / goal + 1), 1) + * + * For simple implementation, we assume the target score is always 10,000. The + * caller should adjust @score for this. + * + * Returns next input that assumed to achieve the target score. + */ +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; + + if (goal > score) + return last_input + compensation; + if (last_input > compensation + min_input) + return last_input - compensation; + return min_input; +} + +/* Shouldn't be called if quota->ms, quota->sz, and quota->get_score unset */ static void damos_set_effective_quota(struct damos_quota *quota) { unsigned long throughput; unsigned long esz; - if (!quota->ms) { + if (!quota->ms && !quota->get_score) { quota->esz = quota->sz; return; } - if (quota->total_charged_ns) - throughput = quota->total_charged_sz * 1000000 / - quota->total_charged_ns; - else - throughput = PAGE_SIZE * 1024; - esz = throughput * quota->ms; + if (quota->get_score) { + quota->esz_bp = damon_feed_loop_next_input( + max(quota->esz_bp, 10000UL), + quota->get_score(quota->get_score_arg)); + esz = quota->esz_bp / 10000; + } + + if (quota->ms) { + if (quota->total_charged_ns) + throughput = quota->total_charged_sz * 1000000 / + quota->total_charged_ns; + else + throughput = PAGE_SIZE * 1024; + if (quota->get_score) + esz = min(throughput * quota->ms, esz); + else + esz = throughput * quota->ms; + } if (quota->sz && quota->sz < esz) esz = quota->sz; + quota->esz = esz; } @@ -1074,7 +1124,7 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s) unsigned long cumulated_sz; unsigned int score, max_score = 0; - if (!quota->ms && !quota->sz) + if (!quota->ms && !quota->sz && !quota->get_score) return; /* New charge window starts */ diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h index 5ff081226e28..4c37a166eb81 100644 --- a/mm/damon/sysfs-common.h +++ b/mm/damon/sysfs-common.h @@ -56,3 +56,6 @@ int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx); int damon_sysfs_schemes_clear_regions( struct damon_sysfs_schemes *sysfs_schemes, struct damon_ctx *ctx); + +void damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index fe0fe2562000..8dbaac6e5c2d 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -821,6 +821,203 @@ static const struct kobj_type damon_sysfs_watermarks_ktype = { }; /* + * quota goal directory + */ + +struct damos_sysfs_quota_goal { + struct kobject kobj; + unsigned long target_value; + unsigned long current_value; +}; + +static struct damos_sysfs_quota_goal *damos_sysfs_quota_goal_alloc(void) +{ + return kzalloc(sizeof(struct damos_sysfs_quota_goal), GFP_KERNEL); +} + +static ssize_t target_value_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damos_sysfs_quota_goal *goal = container_of(kobj, struct + damos_sysfs_quota_goal, kobj); + + return sysfs_emit(buf, "%lu\n", goal->target_value); +} + +static ssize_t target_value_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damos_sysfs_quota_goal *goal = container_of(kobj, struct + damos_sysfs_quota_goal, kobj); + int err = kstrtoul(buf, 0, &goal->target_value); + + return err ? err : count; +} + +static ssize_t current_value_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damos_sysfs_quota_goal *goal = container_of(kobj, struct + damos_sysfs_quota_goal, kobj); + + return sysfs_emit(buf, "%lu\n", goal->current_value); +} + +static ssize_t current_value_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damos_sysfs_quota_goal *goal = container_of(kobj, struct + damos_sysfs_quota_goal, kobj); + int err = kstrtoul(buf, 0, &goal->current_value); + + /* feed callback should check existence of this file and read value */ + return err ? err : count; +} + +static void damos_sysfs_quota_goal_release(struct kobject *kobj) +{ + /* or, notify this release to the feed callback */ + kfree(container_of(kobj, struct damos_sysfs_quota_goal, kobj)); +} + +static struct kobj_attribute damos_sysfs_quota_goal_target_value_attr = + __ATTR_RW_MODE(target_value, 0600); + +static struct kobj_attribute damos_sysfs_quota_goal_current_value_attr = + __ATTR_RW_MODE(current_value, 0600); + +static struct attribute *damos_sysfs_quota_goal_attrs[] = { + &damos_sysfs_quota_goal_target_value_attr.attr, + &damos_sysfs_quota_goal_current_value_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damos_sysfs_quota_goal); + +static const struct kobj_type damos_sysfs_quota_goal_ktype = { + .release = damos_sysfs_quota_goal_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damos_sysfs_quota_goal_groups, +}; + +/* + * quota goals directory + */ + +struct damos_sysfs_quota_goals { + struct kobject kobj; + struct damos_sysfs_quota_goal **goals_arr; /* counted by nr */ + int nr; +}; + +static struct damos_sysfs_quota_goals *damos_sysfs_quota_goals_alloc(void) +{ + return kzalloc(sizeof(struct damos_sysfs_quota_goals), GFP_KERNEL); +} + +static void damos_sysfs_quota_goals_rm_dirs( + struct damos_sysfs_quota_goals *goals) +{ + struct damos_sysfs_quota_goal **goals_arr = goals->goals_arr; + int i; + + for (i = 0; i < goals->nr; i++) + kobject_put(&goals_arr[i]->kobj); + goals->nr = 0; + kfree(goals_arr); + goals->goals_arr = NULL; +} + +static int damos_sysfs_quota_goals_add_dirs( + struct damos_sysfs_quota_goals *goals, int nr_goals) +{ + struct damos_sysfs_quota_goal **goals_arr, *goal; + int err, i; + + damos_sysfs_quota_goals_rm_dirs(goals); + if (!nr_goals) + return 0; + + goals_arr = kmalloc_array(nr_goals, sizeof(*goals_arr), + GFP_KERNEL | __GFP_NOWARN); + if (!goals_arr) + return -ENOMEM; + goals->goals_arr = goals_arr; + + for (i = 0; i < nr_goals; i++) { + goal = damos_sysfs_quota_goal_alloc(); + if (!goal) { + damos_sysfs_quota_goals_rm_dirs(goals); + return -ENOMEM; + } + + err = kobject_init_and_add(&goal->kobj, + &damos_sysfs_quota_goal_ktype, &goals->kobj, + "%d", i); + if (err) { + kobject_put(&goal->kobj); + damos_sysfs_quota_goals_rm_dirs(goals); + return err; + } + + goals_arr[i] = goal; + goals->nr++; + } + return 0; +} + +static ssize_t nr_goals_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damos_sysfs_quota_goals *goals = container_of(kobj, + struct damos_sysfs_quota_goals, kobj); + + return sysfs_emit(buf, "%d\n", goals->nr); +} + +static ssize_t nr_goals_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damos_sysfs_quota_goals *goals; + int nr, err = kstrtoint(buf, 0, &nr); + + if (err) + return err; + if (nr < 0) + return -EINVAL; + + goals = container_of(kobj, struct damos_sysfs_quota_goals, kobj); + + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + err = damos_sysfs_quota_goals_add_dirs(goals, nr); + mutex_unlock(&damon_sysfs_lock); + if (err) + return err; + + return count; +} + +static void damos_sysfs_quota_goals_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damos_sysfs_quota_goals, kobj)); +} + +static struct kobj_attribute damos_sysfs_quota_goals_nr_attr = + __ATTR_RW_MODE(nr_goals, 0600); + +static struct attribute *damos_sysfs_quota_goals_attrs[] = { + &damos_sysfs_quota_goals_nr_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damos_sysfs_quota_goals); + +static const struct kobj_type damos_sysfs_quota_goals_ktype = { + .release = damos_sysfs_quota_goals_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damos_sysfs_quota_goals_groups, +}; + +/* * scheme/weights directory */ @@ -938,6 +1135,7 @@ static const struct kobj_type damon_sysfs_weights_ktype = { struct damon_sysfs_quotas { struct kobject kobj; struct damon_sysfs_weights *weights; + struct damos_sysfs_quota_goals *goals; unsigned long ms; unsigned long sz; unsigned long reset_interval_ms; @@ -951,6 +1149,7 @@ static struct damon_sysfs_quotas *damon_sysfs_quotas_alloc(void) static int damon_sysfs_quotas_add_dirs(struct damon_sysfs_quotas *quotas) { struct damon_sysfs_weights *weights; + struct damos_sysfs_quota_goals *goals; int err; weights = damon_sysfs_weights_alloc(0, 0, 0); @@ -959,16 +1158,35 @@ static int damon_sysfs_quotas_add_dirs(struct damon_sysfs_quotas *quotas) err = kobject_init_and_add(&weights->kobj, &damon_sysfs_weights_ktype, "as->kobj, "weights"); - if (err) + if (err) { kobject_put(&weights->kobj); - else - quotas->weights = weights; + return err; + } + quotas->weights = weights; + + goals = damos_sysfs_quota_goals_alloc(); + if (!goals) { + kobject_put(&weights->kobj); + return -ENOMEM; + } + err = kobject_init_and_add(&goals->kobj, + &damos_sysfs_quota_goals_ktype, "as->kobj, + "goals"); + if (err) { + kobject_put(&weights->kobj); + kobject_put(&goals->kobj); + } else { + quotas->goals = goals; + } + return err; } static void damon_sysfs_quotas_rm_dirs(struct damon_sysfs_quotas *quotas) { kobject_put("as->weights->kobj); + damos_sysfs_quota_goals_rm_dirs(quotas->goals); + kobject_put("as->goals->kobj); } static ssize_t ms_show(struct kobject *kobj, struct kobj_attribute *attr, @@ -1650,6 +1868,50 @@ static int damon_sysfs_set_scheme_filters(struct damos *scheme, return 0; } +static unsigned long damos_sysfs_get_quota_score(void *arg) +{ + return (unsigned long)arg; +} + +static void damos_sysfs_set_quota_score( + struct damos_sysfs_quota_goals *sysfs_goals, + struct damos_quota *quota) +{ + struct damos_sysfs_quota_goal *sysfs_goal; + int i; + + quota->get_score = NULL; + quota->get_score_arg = (void *)0; + for (i = 0; i < sysfs_goals->nr; i++) { + sysfs_goal = sysfs_goals->goals_arr[i]; + if (!sysfs_goal->target_value) + continue; + + /* Higher score makes scheme less aggressive */ + quota->get_score_arg = (void *)max( + (unsigned long)quota->get_score_arg, + sysfs_goal->current_value * 10000 / + sysfs_goal->target_value); + quota->get_score = damos_sysfs_get_quota_score; + } +} + +void damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx) +{ + struct damos *scheme; + int i = 0; + + damon_for_each_scheme(scheme, ctx) { + struct damon_sysfs_scheme *sysfs_scheme; + + sysfs_scheme = sysfs_schemes->schemes_arr[i]; + damos_sysfs_set_quota_score(sysfs_scheme->quotas->goals, + &scheme->quota); + i++; + } +} + static struct damos *damon_sysfs_mk_scheme( struct damon_sysfs_scheme *sysfs_scheme) { @@ -1687,6 +1949,8 @@ static struct damos *damon_sysfs_mk_scheme( .low = sysfs_wmarks->low, }; + damos_sysfs_set_quota_score(sysfs_quotas->goals, "a); + scheme = damon_new_scheme(&pattern, sysfs_scheme->action, sysfs_scheme->apply_interval_us, "a, &wmarks); if (!scheme) @@ -1727,6 +1991,8 @@ static void damon_sysfs_update_scheme(struct damos *scheme, scheme->quota.weight_nr_accesses = sysfs_weights->nr_accesses; scheme->quota.weight_age = sysfs_weights->age; + damos_sysfs_set_quota_score(sysfs_quotas->goals, &scheme->quota); + scheme->wmarks.metric = sysfs_wmarks->metric; scheme->wmarks.interval = sysfs_wmarks->interval_us; scheme->wmarks.high = sysfs_wmarks->high; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 7472404456aa..1f891e18b4ee 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -995,6 +995,11 @@ enum damon_sysfs_cmd { /* @DAMON_SYSFS_CMD_COMMIT: Update kdamond inputs. */ DAMON_SYSFS_CMD_COMMIT, /* + * @DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS: Commit the quota goals + * to DAMON. + */ + DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS, + /* * @DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS: Update scheme stats sysfs * files. */ @@ -1025,6 +1030,7 @@ static const char * const damon_sysfs_cmd_strs[] = { "on", "off", "commit", + "commit_schemes_quota_goals", "update_schemes_stats", "update_schemes_tried_bytes", "update_schemes_tried_regions", @@ -1351,6 +1357,24 @@ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond) kdamond->contexts->contexts_arr[0]); } +static int damon_sysfs_commit_schemes_quota_goals( + struct damon_sysfs_kdamond *sysfs_kdamond) +{ + struct damon_ctx *ctx; + struct damon_sysfs_context *sysfs_ctx; + + if (!damon_sysfs_kdamond_running(sysfs_kdamond)) + return -EINVAL; + /* TODO: Support multiple contexts per kdamond */ + if (sysfs_kdamond->contexts->nr != 1) + return -EINVAL; + + ctx = sysfs_kdamond->damon_ctx; + sysfs_ctx = sysfs_kdamond->contexts->contexts_arr[0]; + damos_sysfs_set_quota_scores(sysfs_ctx->schemes, ctx); + return 0; +} + /* * damon_sysfs_cmd_request_callback() - DAMON callback for handling requests. * @c: The DAMON context of the callback. @@ -1379,6 +1403,9 @@ static int damon_sysfs_cmd_request_callback(struct damon_ctx *c, bool active) case DAMON_SYSFS_CMD_COMMIT: err = damon_sysfs_commit_input(kdamond); break; + case DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS: + err = damon_sysfs_commit_schemes_quota_goals(kdamond); + break; case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES: total_bytes_only = true; fallthrough; diff --git a/mm/filemap.c b/mm/filemap.c index ad5b4aa049a3..67ba56ecdd32 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1623,7 +1623,7 @@ EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { struct wait_queue_head *q = folio_waitqueue(folio); - int ret = 0; + int ret; wait->folio = folio; wait->bit_nr = PG_locked; @@ -2173,7 +2173,7 @@ update_start: if (nr) { folio = fbatch->folios[nr - 1]; - *start = folio->index + folio_nr_pages(folio); + *start = folio_next_index(folio); } out: rcu_read_unlock(); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 10c3247542cb..aee3b9a16828 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -46,9 +46,9 @@ void mark_page_accessed(struct page *page) } EXPORT_SYMBOL(mark_page_accessed); -bool set_page_writeback(struct page *page) +void set_page_writeback(struct page *page) { - return folio_start_writeback(page_folio(page)); + folio_start_writeback(page_folio(page)); } EXPORT_SYMBOL(set_page_writeback); @@ -710,6 +710,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, spin_unlock(ptl); if (page) return page; + return no_page_table(vma, flags); } if (likely(!pmd_trans_huge(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); @@ -758,6 +759,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, spin_unlock(ptl); if (page) return page; + return no_page_table(vma, flags); } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4f542444a91f..c848ea97ab02 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2379,7 +2379,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void unmap_folio(struct folio *folio) { enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | - TTU_SYNC; + TTU_SYNC | TTU_BATCH_FLUSH; VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); @@ -2392,6 +2392,8 @@ static void unmap_folio(struct folio *folio) try_to_migrate(folio, ttu_flags); else try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); + + try_to_unmap_flush(); } static void remap_page(struct folio *folio, unsigned long nr) @@ -2507,13 +2509,13 @@ static void __split_huge_page_tail(struct folio *folio, int tail, clear_compound_head(page_tail); /* Finally unfreeze refcount. Additional reference from page cache. */ - page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) || - PageSwapCache(head))); + page_ref_unfreeze(page_tail, 1 + (!folio_test_anon(folio) || + folio_test_swapcache(folio))); - if (page_is_young(head)) - set_page_young(page_tail); - if (page_is_idle(head)) - set_page_idle(page_tail); + if (folio_test_young(folio)) + folio_set_young(new_folio); + if (folio_test_idle(folio)) + folio_set_idle(new_folio); folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio)); diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 87818ee7f01d..da177e49d956 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -14,6 +14,7 @@ #include <linux/moduleparam.h> #include <linux/bootmem_info.h> #include <linux/mmdebug.h> +#include <linux/pagewalk.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "hugetlb_vmemmap.h" @@ -45,21 +46,14 @@ struct vmemmap_remap_walk { unsigned long flags; }; -static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush) +static int vmemmap_split_pmd(pmd_t *pmd, struct page *head, unsigned long start, + struct vmemmap_remap_walk *walk) { pmd_t __pmd; int i; unsigned long addr = start; - struct page *head; pte_t *pgtable; - spin_lock(&init_mm.page_table_lock); - head = pmd_leaf(*pmd) ? pmd_page(*pmd) : NULL; - spin_unlock(&init_mm.page_table_lock); - - if (!head) - return 0; - pgtable = pte_alloc_one_kernel(&init_mm); if (!pgtable) return -ENOMEM; @@ -88,7 +82,7 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush) /* Make pte visible before pmd. See comment in pmd_install(). */ smp_wmb(); pmd_populate_kernel(&init_mm, pmd, pgtable); - if (flush) + if (!(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH)) flush_tlb_kernel_range(start, start + PMD_SIZE); } else { pte_free_kernel(&init_mm, pgtable); @@ -98,123 +92,83 @@ static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, bool flush) return 0; } -static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr, - unsigned long end, - struct vmemmap_remap_walk *walk) +static int vmemmap_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) { - pte_t *pte = pte_offset_kernel(pmd, addr); + int ret = 0; + struct page *head; + struct vmemmap_remap_walk *vmemmap_walk = walk->private; + + /* Only splitting, not remapping the vmemmap pages. */ + if (!vmemmap_walk->remap_pte) + walk->action = ACTION_CONTINUE; + spin_lock(&init_mm.page_table_lock); + head = pmd_leaf(*pmd) ? pmd_page(*pmd) : NULL; /* - * The reuse_page is found 'first' in table walk before we start - * remapping (which is calling @walk->remap_pte). + * Due to HugeTLB alignment requirements and the vmemmap + * pages being at the start of the hotplugged memory + * region in memory_hotplug.memmap_on_memory case. Checking + * the vmemmap page associated with the first vmemmap page + * if it is self-hosted is sufficient. + * + * [ hotplugged memory ] + * [ section ][...][ section ] + * [ vmemmap ][ usable memory ] + * ^ | ^ | + * +--+ | | + * +------------------------+ */ - if (!walk->reuse_page) { - walk->reuse_page = pte_page(ptep_get(pte)); - /* - * Because the reuse address is part of the range that we are - * walking, skip the reuse address range. - */ - addr += PAGE_SIZE; - pte++; - walk->nr_walked++; - } + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && unlikely(!vmemmap_walk->nr_walked)) { + struct page *page = head ? head + pte_index(addr) : + pte_page(ptep_get(pte_offset_kernel(pmd, addr))); - for (; addr != end; addr += PAGE_SIZE, pte++) { - walk->remap_pte(pte, addr, walk); - walk->nr_walked++; + if (PageVmemmapSelfHosted(page)) + ret = -ENOTSUPP; } -} - -static int vmemmap_pmd_range(pud_t *pud, unsigned long addr, - unsigned long end, - struct vmemmap_remap_walk *walk) -{ - pmd_t *pmd; - unsigned long next; - - pmd = pmd_offset(pud, addr); - do { - int ret; - - ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK, - !(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH)); - if (ret) - return ret; - - next = pmd_addr_end(addr, end); - - /* - * We are only splitting, not remapping the hugetlb vmemmap - * pages. - */ - if (!walk->remap_pte) - continue; - - vmemmap_pte_range(pmd, addr, next, walk); - } while (pmd++, addr = next, addr != end); + spin_unlock(&init_mm.page_table_lock); + if (!head || ret) + return ret; - return 0; + return vmemmap_split_pmd(pmd, head, addr & PMD_MASK, vmemmap_walk); } -static int vmemmap_pud_range(p4d_t *p4d, unsigned long addr, - unsigned long end, - struct vmemmap_remap_walk *walk) +static int vmemmap_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) { - pud_t *pud; - unsigned long next; + struct vmemmap_remap_walk *vmemmap_walk = walk->private; - pud = pud_offset(p4d, addr); - do { - int ret; - - next = pud_addr_end(addr, end); - ret = vmemmap_pmd_range(pud, addr, next, walk); - if (ret) - return ret; - } while (pud++, addr = next, addr != end); + /* + * The reuse_page is found 'first' in page table walking before + * starting remapping. + */ + if (!vmemmap_walk->reuse_page) + vmemmap_walk->reuse_page = pte_page(ptep_get(pte)); + else + vmemmap_walk->remap_pte(pte, addr, vmemmap_walk); + vmemmap_walk->nr_walked++; return 0; } -static int vmemmap_p4d_range(pgd_t *pgd, unsigned long addr, - unsigned long end, - struct vmemmap_remap_walk *walk) -{ - p4d_t *p4d; - unsigned long next; - - p4d = p4d_offset(pgd, addr); - do { - int ret; - - next = p4d_addr_end(addr, end); - ret = vmemmap_pud_range(p4d, addr, next, walk); - if (ret) - return ret; - } while (p4d++, addr = next, addr != end); - - return 0; -} +static const struct mm_walk_ops vmemmap_remap_ops = { + .pmd_entry = vmemmap_pmd_entry, + .pte_entry = vmemmap_pte_entry, +}; static int vmemmap_remap_range(unsigned long start, unsigned long end, struct vmemmap_remap_walk *walk) { - unsigned long addr = start; - unsigned long next; - pgd_t *pgd; - - VM_BUG_ON(!PAGE_ALIGNED(start)); - VM_BUG_ON(!PAGE_ALIGNED(end)); + int ret; - pgd = pgd_offset_k(addr); - do { - int ret; + VM_BUG_ON(!PAGE_ALIGNED(start | end)); - next = pgd_addr_end(addr, end); - ret = vmemmap_p4d_range(pgd, addr, next, walk); - if (ret) - return ret; - } while (pgd++, addr = next, addr != end); + mmap_read_lock(&init_mm); + ret = walk_page_range_novma(&init_mm, start, end, &vmemmap_remap_ops, + NULL, walk); + mmap_read_unlock(&init_mm); + if (ret) + return ret; if (walk->remap_pte && !(walk->flags & VMEMMAP_REMAP_NO_TLB_FLUSH)) flush_tlb_kernel_range(start, end); @@ -328,9 +282,8 @@ static void vmemmap_restore_pte(pte_t *pte, unsigned long addr, * Return: %0 on success, negative error code otherwise. */ static int vmemmap_remap_split(unsigned long start, unsigned long end, - unsigned long reuse) + unsigned long reuse) { - int ret; struct vmemmap_remap_walk walk = { .remap_pte = NULL, .flags = VMEMMAP_SPLIT_NO_TLB_FLUSH, @@ -339,11 +292,7 @@ static int vmemmap_remap_split(unsigned long start, unsigned long end, /* See the comment in the vmemmap_remap_free(). */ BUG_ON(start - reuse != PAGE_SIZE); - mmap_read_lock(&init_mm); - ret = vmemmap_remap_range(reuse, end, &walk); - mmap_read_unlock(&init_mm); - - return ret; + return vmemmap_remap_range(reuse, end, &walk); } /** @@ -406,7 +355,6 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, */ BUG_ON(start - reuse != PAGE_SIZE); - mmap_read_lock(&init_mm); ret = vmemmap_remap_range(reuse, end, &walk); if (ret && walk.nr_walked) { end = reuse + walk.nr_walked * PAGE_SIZE; @@ -425,7 +373,6 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, vmemmap_remap_range(reuse, end, &walk); } - mmap_read_unlock(&init_mm); return ret; } @@ -482,11 +429,7 @@ static int vmemmap_remap_alloc(unsigned long start, unsigned long end, if (alloc_vmemmap_page_list(start, end, &vmemmap_pages)) return -ENOMEM; - mmap_read_lock(&init_mm); - vmemmap_remap_range(reuse, end, &walk); - mmap_read_unlock(&init_mm); - - return 0; + return vmemmap_remap_range(reuse, end, &walk); } DEFINE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key); @@ -495,14 +438,14 @@ EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key); static bool vmemmap_optimize_enabled = IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON); core_param(hugetlb_free_vmemmap, vmemmap_optimize_enabled, bool, 0); -static int __hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio, unsigned long flags) +static int __hugetlb_vmemmap_restore_folio(const struct hstate *h, + struct folio *folio, unsigned long flags) { int ret; - struct page *head = &folio->page; - unsigned long vmemmap_start = (unsigned long)head, vmemmap_end; + unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end; unsigned long vmemmap_reuse; - VM_WARN_ON_ONCE(!PageHuge(head)); + VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio); if (!folio_test_hugetlb_vmemmap_optimized(folio)) return 0; @@ -565,7 +508,7 @@ long hugetlb_vmemmap_restore_folios(const struct hstate *h, list_for_each_entry_safe(folio, t_folio, folio_list, lru) { if (folio_test_hugetlb_vmemmap_optimized(folio)) { ret = __hugetlb_vmemmap_restore_folio(h, folio, - VMEMMAP_REMAP_NO_TLB_FLUSH); + VMEMMAP_REMAP_NO_TLB_FLUSH); if (ret) break; restored++; @@ -583,9 +526,9 @@ long hugetlb_vmemmap_restore_folios(const struct hstate *h, } /* Return true iff a HugeTLB whose vmemmap should and can be optimized. */ -static bool vmemmap_should_optimize(const struct hstate *h, const struct page *head) +static bool vmemmap_should_optimize_folio(const struct hstate *h, struct folio *folio) { - if (HPageVmemmapOptimized((struct page *)head)) + if (folio_test_hugetlb_vmemmap_optimized(folio)) return false; if (!READ_ONCE(vmemmap_optimize_enabled)) @@ -594,65 +537,20 @@ static bool vmemmap_should_optimize(const struct hstate *h, const struct page *h if (!hugetlb_vmemmap_optimizable(h)) return false; - if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { - pmd_t *pmdp, pmd; - struct page *vmemmap_page; - unsigned long vaddr = (unsigned long)head; - - /* - * Only the vmemmap page's vmemmap page can be self-hosted. - * Walking the page tables to find the backing page of the - * vmemmap page. - */ - pmdp = pmd_off_k(vaddr); - /* - * The READ_ONCE() is used to stabilize *pmdp in a register or - * on the stack so that it will stop changing under the code. - * The only concurrent operation where it can be changed is - * split_vmemmap_huge_pmd() (*pmdp will be stable after this - * operation). - */ - pmd = READ_ONCE(*pmdp); - if (pmd_leaf(pmd)) - vmemmap_page = pmd_page(pmd) + pte_index(vaddr); - else - vmemmap_page = pte_page(*pte_offset_kernel(pmdp, vaddr)); - /* - * Due to HugeTLB alignment requirements and the vmemmap pages - * being at the start of the hotplugged memory region in - * memory_hotplug.memmap_on_memory case. Checking any vmemmap - * page's vmemmap page if it is marked as VmemmapSelfHosted is - * sufficient. - * - * [ hotplugged memory ] - * [ section ][...][ section ] - * [ vmemmap ][ usable memory ] - * ^ | | | - * +---+ | | - * ^ | | - * +-------+ | - * ^ | - * +-------------------------------------------+ - */ - if (PageVmemmapSelfHosted(vmemmap_page)) - return false; - } - return true; } static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h, - struct folio *folio, - struct list_head *vmemmap_pages, - unsigned long flags) + struct folio *folio, + struct list_head *vmemmap_pages, + unsigned long flags) { int ret = 0; - struct page *head = &folio->page; - unsigned long vmemmap_start = (unsigned long)head, vmemmap_end; + unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end; unsigned long vmemmap_reuse; - VM_WARN_ON_ONCE(!PageHuge(head)); - if (!vmemmap_should_optimize(h, head)) + VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio); + if (!vmemmap_should_optimize_folio(h, folio)) return ret; static_branch_inc(&hugetlb_optimize_vmemmap_key); @@ -680,7 +578,7 @@ static int __hugetlb_vmemmap_optimize_folio(const struct hstate *h, * the caller. */ ret = vmemmap_remap_free(vmemmap_start, vmemmap_end, vmemmap_reuse, - vmemmap_pages, flags); + vmemmap_pages, flags); if (ret) { static_branch_dec(&hugetlb_optimize_vmemmap_key); folio_clear_hugetlb_vmemmap_optimized(folio); @@ -707,12 +605,12 @@ void hugetlb_vmemmap_optimize_folio(const struct hstate *h, struct folio *folio) free_vmemmap_page_list(&vmemmap_pages); } -static int hugetlb_vmemmap_split(const struct hstate *h, struct page *head) +static int hugetlb_vmemmap_split_folio(const struct hstate *h, struct folio *folio) { - unsigned long vmemmap_start = (unsigned long)head, vmemmap_end; + unsigned long vmemmap_start = (unsigned long)&folio->page, vmemmap_end; unsigned long vmemmap_reuse; - if (!vmemmap_should_optimize(h, head)) + if (!vmemmap_should_optimize_folio(h, folio)) return 0; vmemmap_end = vmemmap_start + hugetlb_vmemmap_size(h); @@ -732,7 +630,7 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l LIST_HEAD(vmemmap_pages); list_for_each_entry(folio, folio_list, lru) { - int ret = hugetlb_vmemmap_split(h, &folio->page); + int ret = hugetlb_vmemmap_split_folio(h, folio); /* * Spliting the PMD requires allocating a page, thus lets fail @@ -747,9 +645,10 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l flush_tlb_all(); list_for_each_entry(folio, folio_list, lru) { - int ret = __hugetlb_vmemmap_optimize_folio(h, folio, - &vmemmap_pages, - VMEMMAP_REMAP_NO_TLB_FLUSH); + int ret; + + ret = __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, + VMEMMAP_REMAP_NO_TLB_FLUSH); /* * Pages to be freed may have been accumulated. If we @@ -763,9 +662,8 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l flush_tlb_all(); free_vmemmap_page_list(&vmemmap_pages); INIT_LIST_HEAD(&vmemmap_pages); - __hugetlb_vmemmap_optimize_folio(h, folio, - &vmemmap_pages, - VMEMMAP_REMAP_NO_TLB_FLUSH); + __hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, + VMEMMAP_REMAP_NO_TLB_FLUSH); } } diff --git a/mm/internal.h b/mm/internal.h index b61034bd50f5..222e63b2dea4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -138,7 +138,7 @@ void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); -long invalidate_inode_page(struct page *page); +long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); @@ -616,7 +616,7 @@ folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; - unsigned long vma_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) @@ -1135,8 +1135,6 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) static inline void vma_iter_config(struct vma_iterator *vmi, unsigned long index, unsigned long last) { - MAS_BUG_ON(&vmi->mas, vmi->mas.node != MAS_START && - (vmi->mas.index > index || vmi->mas.last < index)); __mas_set_range(&vmi->mas, index, last - 1); } @@ -1154,17 +1152,6 @@ static inline void vma_iter_clear(struct vma_iterator *vmi) mas_store_prealloc(&vmi->mas, NULL); } -static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, - unsigned long start, unsigned long end, gfp_t gfp) -{ - __mas_set_range(&vmi->mas, start, end - 1); - mas_store_gfp(&vmi->mas, NULL, gfp); - if (unlikely(mas_is_err(&vmi->mas))) - return -ENOMEM; - - return 0; -} - static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi) { return mas_walk(&vmi->mas); @@ -1176,13 +1163,13 @@ static inline void vma_iter_store(struct vma_iterator *vmi, { #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) - if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START && + if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.index > vma->vm_start)) { pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n", vmi->mas.index, vma->vm_start, vma->vm_start, vma->vm_end, vmi->mas.index, vmi->mas.last); } - if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START && + if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start && vmi->mas.last < vma->vm_start)) { pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n", vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end, @@ -1190,7 +1177,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi, } #endif - if (vmi->mas.node != MAS_START && + if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); @@ -1201,7 +1188,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi, static inline int vma_iter_store_gfp(struct vma_iterator *vmi, struct vm_area_struct *vma, gfp_t gfp) { - if (vmi->mas.node != MAS_START && + if (vmi->mas.status != ma_start && ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start))) vma_iter_invalidate(vmi); diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 256930da578a..fe6c4b43ad9f 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -20,8 +20,10 @@ #include <linux/module.h> #include <linux/printk.h> #include <linux/sched.h> +#include <linux/sched/clock.h> #include <linux/sched/task_stack.h> #include <linux/slab.h> +#include <linux/stackdepot.h> #include <linux/stacktrace.h> #include <linux/string.h> #include <linux/types.h> @@ -37,19 +39,27 @@ struct slab *kasan_addr_to_slab(const void *addr) return NULL; } -depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc) +depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags) { unsigned long entries[KASAN_STACK_DEPTH]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); - return __stack_depot_save(entries, nr_entries, flags, can_alloc); + return stack_depot_save_flags(entries, nr_entries, flags, depot_flags); } void kasan_set_track(struct kasan_track *track, gfp_t flags) { +#ifdef CONFIG_KASAN_EXTRA_INFO + u32 cpu = raw_smp_processor_id(); + u64 ts_nsec = local_clock(); + + track->cpu = cpu; + track->timestamp = ts_nsec >> 3; +#endif /* CONFIG_KASAN_EXTRA_INFO */ track->pid = current->pid; - track->stack = kasan_save_stack(flags, true); + track->stack = kasan_save_stack(flags, + STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET); } #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 4d837ab83f08..54e20b2bc3e1 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -25,6 +25,7 @@ #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/slab.h> +#include <linux/stackdepot.h> #include <linux/stacktrace.h> #include <linux/string.h> #include <linux/types.h> @@ -361,6 +362,8 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, { unsigned int ok_size; unsigned int optimal_size; + unsigned int rem_free_meta_size; + unsigned int orig_alloc_meta_offset; if (!kasan_requires_meta()) return; @@ -394,6 +397,9 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, /* Continue, since free meta might still fit. */ } + ok_size = *size; + orig_alloc_meta_offset = cache->kasan_info.alloc_meta_offset; + /* * Add free meta into redzone when it's not possible to store * it in the object. This is the case when: @@ -401,23 +407,37 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, * be touched after it was freed, or * 2. Object has a constructor, which means it's expected to * retain its content until the next allocation, or - * 3. Object is too small. + * 3. Object is too small and SLUB DEBUG is enabled. Avoid + * free meta that exceeds the object size corrupts the + * SLUB DEBUG metadata. * Otherwise cache->kasan_info.free_meta_offset = 0 is implied. + * If the object is smaller than the free meta and SLUB DEBUG + * is not enabled, it is still possible to store part of the + * free meta in the object. */ - if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor || - cache->object_size < sizeof(struct kasan_free_meta)) { - ok_size = *size; - + if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor) { cache->kasan_info.free_meta_offset = *size; *size += sizeof(struct kasan_free_meta); - - /* If free meta doesn't fit, don't add it. */ - if (*size > KMALLOC_MAX_SIZE) { - cache->kasan_info.free_meta_offset = KASAN_NO_FREE_META; - *size = ok_size; + } else if (cache->object_size < sizeof(struct kasan_free_meta)) { + if (__slub_debug_enabled()) { + cache->kasan_info.free_meta_offset = *size; + *size += sizeof(struct kasan_free_meta); + } else { + rem_free_meta_size = sizeof(struct kasan_free_meta) - + cache->object_size; + *size += rem_free_meta_size; + if (cache->kasan_info.alloc_meta_offset != 0) + cache->kasan_info.alloc_meta_offset += rem_free_meta_size; } } + /* If free meta doesn't fit, don't add it. */ + if (*size > KMALLOC_MAX_SIZE) { + cache->kasan_info.free_meta_offset = KASAN_NO_FREE_META; + cache->kasan_info.alloc_meta_offset = orig_alloc_meta_offset; + *size = ok_size; + } + /* Calculate size with optimal redzone. */ optimal_size = cache->object_size + optimal_redzone(cache->object_size); /* Limit it with KMALLOC_MAX_SIZE (relevant for SLAB only). */ @@ -448,10 +468,14 @@ struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache, void kasan_init_object_meta(struct kmem_cache *cache, const void *object) { struct kasan_alloc_meta *alloc_meta; + struct kasan_free_meta *free_meta; alloc_meta = kasan_get_alloc_meta(cache, object); if (alloc_meta) __memset(alloc_meta, 0, sizeof(*alloc_meta)); + free_meta = kasan_get_free_meta(cache, object); + if (free_meta) + __memset(free_meta, 0, sizeof(*free_meta)); } size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object) @@ -472,7 +496,7 @@ size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object) sizeof(struct kasan_free_meta) : 0); } -static void __kasan_record_aux_stack(void *addr, bool can_alloc) +static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags) { struct slab *slab = kasan_addr_to_slab(addr); struct kmem_cache *cache; @@ -488,18 +512,20 @@ static void __kasan_record_aux_stack(void *addr, bool can_alloc) if (!alloc_meta) return; + stack_depot_put(alloc_meta->aux_stack[1]); alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0]; - alloc_meta->aux_stack[0] = kasan_save_stack(0, can_alloc); + alloc_meta->aux_stack[0] = kasan_save_stack(0, depot_flags); } void kasan_record_aux_stack(void *addr) { - return __kasan_record_aux_stack(addr, true); + return __kasan_record_aux_stack(addr, + STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET); } void kasan_record_aux_stack_noalloc(void *addr) { - return __kasan_record_aux_stack(addr, false); + return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_GET); } void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags) @@ -507,8 +533,16 @@ void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags) struct kasan_alloc_meta *alloc_meta; alloc_meta = kasan_get_alloc_meta(cache, object); - if (alloc_meta) - kasan_set_track(&alloc_meta->alloc_track, flags); + if (!alloc_meta) + return; + + /* Evict previous stack traces (might exist for krealloc). */ + stack_depot_put(alloc_meta->alloc_track.stack); + stack_depot_put(alloc_meta->aux_stack[0]); + stack_depot_put(alloc_meta->aux_stack[1]); + __memset(alloc_meta, 0, sizeof(*alloc_meta)); + + kasan_set_track(&alloc_meta->alloc_track, flags); } void kasan_save_free_info(struct kmem_cache *cache, void *object) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 8b06bab5c406..5e298e3ac909 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -187,6 +187,10 @@ static inline bool kasan_requires_meta(void) struct kasan_track { u32 pid; depot_stack_handle_t stack; +#ifdef CONFIG_KASAN_EXTRA_INFO + u64 cpu:20; + u64 timestamp:44; +#endif /* CONFIG_KASAN_EXTRA_INFO */ }; enum kasan_report_type { @@ -278,6 +282,10 @@ struct kasan_stack_ring_entry { u32 pid; depot_stack_handle_t stack; bool is_free; +#ifdef CONFIG_KASAN_EXTRA_INFO + u64 cpu:20; + u64 timestamp:44; +#endif /* CONFIG_KASAN_EXTRA_INFO */ }; struct kasan_stack_ring { @@ -368,7 +376,7 @@ static inline void kasan_init_cache_meta(struct kmem_cache *cache, unsigned int static inline void kasan_init_object_meta(struct kmem_cache *cache, const void *object) { } #endif -depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc); +depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags); void kasan_set_track(struct kasan_track *track, gfp_t flags); void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags); void kasan_save_free_info(struct kmem_cache *cache, void *object); diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index ca4529156735..265ca2bbe2dd 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -143,11 +143,22 @@ static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache) static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache) { void *object = qlink_to_object(qlink, cache); - struct kasan_free_meta *meta = kasan_get_free_meta(cache, object); + struct kasan_alloc_meta *alloc_meta = kasan_get_alloc_meta(cache, object); + struct kasan_free_meta *free_meta = kasan_get_free_meta(cache, object); unsigned long flags; - if (IS_ENABLED(CONFIG_SLAB)) - local_irq_save(flags); + if (alloc_meta) { + stack_depot_put(alloc_meta->alloc_track.stack); + stack_depot_put(alloc_meta->aux_stack[0]); + stack_depot_put(alloc_meta->aux_stack[1]); + __memset(alloc_meta, 0, sizeof(*alloc_meta)); + } + + if (free_meta && + *(u8 *)kasan_mem_to_shadow(object) == KASAN_SLAB_FREETRACK) { + stack_depot_put(free_meta->free_track.stack); + free_meta->free_track.stack = 0; + } /* * If init_on_free is enabled and KASAN's free metadata is stored in @@ -157,14 +168,17 @@ static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache) */ if (slab_want_init_on_free(cache) && cache->kasan_info.free_meta_offset == 0) - memzero_explicit(meta, sizeof(*meta)); + memzero_explicit(free_meta, sizeof(*free_meta)); /* - * As the object now gets freed from the quarantine, assume that its - * free track is no longer valid. + * As the object now gets freed from the quarantine, + * take note that its free track is no longer exists. */ *(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREE; + if (IS_ENABLED(CONFIG_SLAB)) + local_irq_save(flags); + ___cache_free(cache, object, _THIS_IP_); if (IS_ENABLED(CONFIG_SLAB)) diff --git a/mm/kasan/report.c b/mm/kasan/report.c index e77facb62900..a938237f6882 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -262,7 +262,19 @@ static void print_error_description(struct kasan_report_info *info) static void print_track(struct kasan_track *track, const char *prefix) { +#ifdef CONFIG_KASAN_EXTRA_INFO + u64 ts_nsec = track->timestamp; + unsigned long rem_usec; + + ts_nsec <<= 3; + rem_usec = do_div(ts_nsec, NSEC_PER_SEC) / 1000; + + pr_err("%s by task %u on cpu %d at %lu.%06lus:\n", + prefix, track->pid, track->cpu, + (unsigned long)ts_nsec, rem_usec); +#else pr_err("%s by task %u:\n", prefix, track->pid); +#endif /* CONFIG_KASAN_EXTRA_INFO */ if (track->stack) stack_depot_print(track->stack); else diff --git a/mm/kasan/report_tags.c b/mm/kasan/report_tags.c index 8b8bfdb3cfdb..979f284c2497 100644 --- a/mm/kasan/report_tags.c +++ b/mm/kasan/report_tags.c @@ -7,6 +7,7 @@ #include <linux/atomic.h> #include "kasan.h" +#include "../slab.h" extern struct kasan_stack_ring stack_ring; @@ -26,15 +27,20 @@ static const char *get_common_bug_type(struct kasan_report_info *info) return "invalid-access"; } +#ifdef CONFIG_KASAN_EXTRA_INFO +static void kasan_complete_extra_report_info(struct kasan_track *track, + struct kasan_stack_ring_entry *entry) +{ + track->cpu = entry->cpu; + track->timestamp = entry->timestamp; +} +#endif /* CONFIG_KASAN_EXTRA_INFO */ + void kasan_complete_mode_report_info(struct kasan_report_info *info) { unsigned long flags; u64 pos; struct kasan_stack_ring_entry *entry; - void *ptr; - u32 pid; - depot_stack_handle_t stack; - bool is_free; bool alloc_found = false, free_found = false; if ((!info->cache || !info->object) && !info->bug_type) { @@ -61,18 +67,12 @@ void kasan_complete_mode_report_info(struct kasan_report_info *info) entry = &stack_ring.entries[i % stack_ring.size]; - /* Paired with smp_store_release() in save_stack_info(). */ - ptr = (void *)smp_load_acquire(&entry->ptr); - - if (kasan_reset_tag(ptr) != info->object || - get_tag(ptr) != get_tag(info->access_addr)) + if (kasan_reset_tag(entry->ptr) != info->object || + get_tag(entry->ptr) != get_tag(info->access_addr) || + info->cache->object_size != entry->size) continue; - pid = READ_ONCE(entry->pid); - stack = READ_ONCE(entry->stack); - is_free = READ_ONCE(entry->is_free); - - if (is_free) { + if (entry->is_free) { /* * Second free of the same object. * Give up on trying to find the alloc entry. @@ -80,8 +80,11 @@ void kasan_complete_mode_report_info(struct kasan_report_info *info) if (free_found) break; - info->free_track.pid = pid; - info->free_track.stack = stack; + info->free_track.pid = entry->pid; + info->free_track.stack = entry->stack; +#ifdef CONFIG_KASAN_EXTRA_INFO + kasan_complete_extra_report_info(&info->free_track, entry); +#endif /* CONFIG_KASAN_EXTRA_INFO */ free_found = true; /* @@ -95,8 +98,11 @@ void kasan_complete_mode_report_info(struct kasan_report_info *info) if (alloc_found) break; - info->alloc_track.pid = pid; - info->alloc_track.stack = stack; + info->alloc_track.pid = entry->pid; + info->alloc_track.stack = entry->stack; +#ifdef CONFIG_KASAN_EXTRA_INFO + kasan_complete_extra_report_info(&info->alloc_track, entry); +#endif /* CONFIG_KASAN_EXTRA_INFO */ alloc_found = true; /* diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c index 7dcfe341d48e..c13b198b8302 100644 --- a/mm/kasan/tags.c +++ b/mm/kasan/tags.c @@ -13,6 +13,8 @@ #include <linux/memblock.h> #include <linux/memory.h> #include <linux/mm.h> +#include <linux/sched/clock.h> +#include <linux/stackdepot.h> #include <linux/static_key.h> #include <linux/string.h> #include <linux/types.h> @@ -92,16 +94,28 @@ void __init kasan_init_tags(void) } } +#ifdef CONFIG_KASAN_EXTRA_INFO +static void save_extra_info(struct kasan_stack_ring_entry *entry) +{ + u32 cpu = raw_smp_processor_id(); + u64 ts_nsec = local_clock(); + + entry->cpu = cpu; + entry->timestamp = ts_nsec >> 3; +} +#endif /* CONFIG_KASAN_EXTRA_INFO */ + static void save_stack_info(struct kmem_cache *cache, void *object, gfp_t gfp_flags, bool is_free) { unsigned long flags; - depot_stack_handle_t stack; + depot_stack_handle_t stack, old_stack; u64 pos; struct kasan_stack_ring_entry *entry; void *old_ptr; - stack = kasan_save_stack(gfp_flags, true); + stack = kasan_save_stack(gfp_flags, + STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET); /* * Prevent save_stack_info() from modifying stack ring @@ -120,17 +134,22 @@ next: if (!try_cmpxchg(&entry->ptr, &old_ptr, STACK_RING_BUSY_PTR)) goto next; /* Busy slot. */ - WRITE_ONCE(entry->size, cache->object_size); - WRITE_ONCE(entry->pid, current->pid); - WRITE_ONCE(entry->stack, stack); - WRITE_ONCE(entry->is_free, is_free); + old_stack = entry->stack; - /* - * Paired with smp_load_acquire() in kasan_complete_mode_report_info(). - */ - smp_store_release(&entry->ptr, (s64)object); + entry->size = cache->object_size; + entry->pid = current->pid; + entry->stack = stack; + entry->is_free = is_free; +#ifdef CONFIG_KASAN_EXTRA_INFO + save_extra_info(entry); +#endif /* CONFIG_KASAN_EXTRA_INFO */ + + entry->ptr = object; read_unlock_irqrestore(&stack_ring.lock, flags); + + if (old_stack) + stack_depot_put(old_stack); } void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 5501363d6b31..6a540c2b27c5 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -14,17 +14,15 @@ * The following locks and mutexes are used by kmemleak: * * - kmemleak_lock (raw_spinlock_t): protects the object_list as well as - * del_state modifications and accesses to the object_tree_root (or - * object_phys_tree_root). The object_list is the main list holding the - * metadata (struct kmemleak_object) for the allocated memory blocks. - * The object_tree_root and object_phys_tree_root are red - * black trees used to look-up metadata based on a pointer to the - * corresponding memory block. The object_phys_tree_root is for objects - * allocated with physical address. The kmemleak_object structures are - * added to the object_list and object_tree_root (or object_phys_tree_root) - * in the create_object() function called from the kmemleak_alloc() (or - * kmemleak_alloc_phys()) callback and removed in delete_object() called from - * the kmemleak_free() callback + * del_state modifications and accesses to the object trees + * (object_tree_root, object_phys_tree_root, object_percpu_tree_root). The + * object_list is the main list holding the metadata (struct + * kmemleak_object) for the allocated memory blocks. The object trees are + * red black trees used to look-up metadata based on a pointer to the + * corresponding memory block. The kmemleak_object structures are added to + * the object_list and the object tree root in the create_object() function + * called from the kmemleak_alloc{,_phys,_percpu}() callback and removed in + * delete_object() called from the kmemleak_free{,_phys,_percpu}() callback * - kmemleak_object.lock (raw_spinlock_t): protects a kmemleak_object. * Accesses to the metadata (e.g. count) are protected by this lock. Note * that some members of this structure may be protected by other means @@ -178,6 +176,8 @@ struct kmemleak_object { #define OBJECT_FULL_SCAN (1 << 3) /* flag set for object allocated with physical address */ #define OBJECT_PHYS (1 << 4) +/* flag set for per-CPU pointers */ +#define OBJECT_PERCPU (1 << 5) /* set when __remove_object() called */ #define DELSTATE_REMOVED (1 << 0) @@ -206,6 +206,8 @@ static LIST_HEAD(mem_pool_free_list); static struct rb_root object_tree_root = RB_ROOT; /* search tree for object (with OBJECT_PHYS flag) boundaries */ static struct rb_root object_phys_tree_root = RB_ROOT; +/* search tree for object (with OBJECT_PERCPU flag) boundaries */ +static struct rb_root object_percpu_tree_root = RB_ROOT; /* protecting the access to object_list, object_tree_root (or object_phys_tree_root) */ static DEFINE_RAW_SPINLOCK(kmemleak_lock); @@ -298,7 +300,7 @@ static void hex_dump_object(struct seq_file *seq, const u8 *ptr = (const u8 *)object->pointer; size_t len; - if (WARN_ON_ONCE(object->flags & OBJECT_PHYS)) + if (WARN_ON_ONCE(object->flags & (OBJECT_PHYS | OBJECT_PERCPU))) return; /* limit the number of lines to HEX_MAX_LINES */ @@ -355,16 +357,14 @@ static void print_unreferenced(struct seq_file *seq, int i; unsigned long *entries; unsigned int nr_entries; - unsigned int msecs_age = jiffies_to_msecs(jiffies - object->jiffies); nr_entries = stack_depot_fetch(object->trace_handle, &entries); warn_or_seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n", object->pointer, object->size); - warn_or_seq_printf(seq, " comm \"%s\", pid %d, jiffies %lu (age %d.%03ds)\n", - object->comm, object->pid, object->jiffies, - msecs_age / 1000, msecs_age % 1000); + warn_or_seq_printf(seq, " comm \"%s\", pid %d, jiffies %lu\n", + object->comm, object->pid, object->jiffies); hex_dump_object(seq, object); - warn_or_seq_printf(seq, " backtrace:\n"); + warn_or_seq_printf(seq, " backtrace (crc %x):\n", object->checksum); for (i = 0; i < nr_entries; i++) { void *ptr = (void *)entries[i]; @@ -392,6 +392,15 @@ static void dump_object_info(struct kmemleak_object *object) stack_depot_print(object->trace_handle); } +static struct rb_root *object_tree(unsigned long objflags) +{ + if (objflags & OBJECT_PHYS) + return &object_phys_tree_root; + if (objflags & OBJECT_PERCPU) + return &object_percpu_tree_root; + return &object_tree_root; +} + /* * Look-up a memory block metadata (kmemleak_object) in the object search * tree based on a pointer value. If alias is 0, only values pointing to the @@ -399,10 +408,9 @@ static void dump_object_info(struct kmemleak_object *object) * when calling this function. */ static struct kmemleak_object *__lookup_object(unsigned long ptr, int alias, - bool is_phys) + unsigned int objflags) { - struct rb_node *rb = is_phys ? object_phys_tree_root.rb_node : - object_tree_root.rb_node; + struct rb_node *rb = object_tree(objflags)->rb_node; unsigned long untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); while (rb) { @@ -431,7 +439,7 @@ static struct kmemleak_object *__lookup_object(unsigned long ptr, int alias, /* Look-up a kmemleak object which allocated with virtual address. */ static struct kmemleak_object *lookup_object(unsigned long ptr, int alias) { - return __lookup_object(ptr, alias, false); + return __lookup_object(ptr, alias, 0); } /* @@ -544,14 +552,14 @@ static void put_object(struct kmemleak_object *object) * Look up an object in the object search tree and increase its use_count. */ static struct kmemleak_object *__find_and_get_object(unsigned long ptr, int alias, - bool is_phys) + unsigned int objflags) { unsigned long flags; struct kmemleak_object *object; rcu_read_lock(); raw_spin_lock_irqsave(&kmemleak_lock, flags); - object = __lookup_object(ptr, alias, is_phys); + object = __lookup_object(ptr, alias, objflags); raw_spin_unlock_irqrestore(&kmemleak_lock, flags); /* check whether the object is still available */ @@ -565,19 +573,16 @@ static struct kmemleak_object *__find_and_get_object(unsigned long ptr, int alia /* Look up and get an object which allocated with virtual address. */ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) { - return __find_and_get_object(ptr, alias, false); + return __find_and_get_object(ptr, alias, 0); } /* - * Remove an object from the object_tree_root (or object_phys_tree_root) - * and object_list. Must be called with the kmemleak_lock held _if_ kmemleak - * is still enabled. + * Remove an object from its object tree and object_list. Must be called with + * the kmemleak_lock held _if_ kmemleak is still enabled. */ static void __remove_object(struct kmemleak_object *object) { - rb_erase(&object->rb_node, object->flags & OBJECT_PHYS ? - &object_phys_tree_root : - &object_tree_root); + rb_erase(&object->rb_node, object_tree(object->flags)); if (!(object->del_state & DELSTATE_NO_DELETE)) list_del_rcu(&object->object_list); object->del_state |= DELSTATE_REMOVED; @@ -585,11 +590,11 @@ static void __remove_object(struct kmemleak_object *object) static struct kmemleak_object *__find_and_remove_object(unsigned long ptr, int alias, - bool is_phys) + unsigned int objflags) { struct kmemleak_object *object; - object = __lookup_object(ptr, alias, is_phys); + object = __lookup_object(ptr, alias, objflags); if (object) __remove_object(object); @@ -597,19 +602,18 @@ static struct kmemleak_object *__find_and_remove_object(unsigned long ptr, } /* - * Look up an object in the object search tree and remove it from both - * object_tree_root (or object_phys_tree_root) and object_list. The - * returned object's use_count should be at least 1, as initially set - * by create_object(). + * Look up an object in the object search tree and remove it from both object + * tree root and object_list. The returned object's use_count should be at + * least 1, as initially set by create_object(). */ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int alias, - bool is_phys) + unsigned int objflags) { unsigned long flags; struct kmemleak_object *object; raw_spin_lock_irqsave(&kmemleak_lock, flags); - object = __find_and_remove_object(ptr, alias, is_phys); + object = __find_and_remove_object(ptr, alias, objflags); raw_spin_unlock_irqrestore(&kmemleak_lock, flags); return object; @@ -680,7 +684,7 @@ static struct kmemleak_object *__alloc_object(gfp_t gfp) } static int __link_object(struct kmemleak_object *object, unsigned long ptr, - size_t size, int min_count, bool is_phys) + size_t size, int min_count, unsigned int objflags) { struct kmemleak_object *parent; @@ -688,7 +692,7 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr, unsigned long untagged_ptr; unsigned long untagged_objp; - object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0); + object->flags = OBJECT_ALLOCATED | objflags; object->pointer = ptr; object->size = kfence_ksize((void *)ptr) ?: size; object->min_count = min_count; @@ -699,12 +703,11 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr, * Only update min_addr and max_addr with object * storing virtual address. */ - if (!is_phys) { + if (!(objflags & (OBJECT_PHYS | OBJECT_PERCPU))) { min_addr = min(min_addr, untagged_ptr); max_addr = max(max_addr, untagged_ptr + size); } - link = is_phys ? &object_phys_tree_root.rb_node : - &object_tree_root.rb_node; + link = &object_tree(objflags)->rb_node; rb_parent = NULL; while (*link) { rb_parent = *link; @@ -726,8 +729,7 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr, } } rb_link_node(&object->rb_node, rb_parent, link); - rb_insert_color(&object->rb_node, is_phys ? &object_phys_tree_root : - &object_tree_root); + rb_insert_color(&object->rb_node, object_tree(objflags)); list_add_tail_rcu(&object->object_list, &object_list); return 0; @@ -735,11 +737,10 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr, /* * Create the metadata (struct kmemleak_object) corresponding to an allocated - * memory block and add it to the object_list and object_tree_root (or - * object_phys_tree_root). + * memory block and add it to the object_list and object tree. */ static void __create_object(unsigned long ptr, size_t size, - int min_count, gfp_t gfp, bool is_phys) + int min_count, gfp_t gfp, unsigned int objflags) { struct kmemleak_object *object; unsigned long flags; @@ -750,7 +751,7 @@ static void __create_object(unsigned long ptr, size_t size, return; raw_spin_lock_irqsave(&kmemleak_lock, flags); - ret = __link_object(object, ptr, size, min_count, is_phys); + ret = __link_object(object, ptr, size, min_count, objflags); raw_spin_unlock_irqrestore(&kmemleak_lock, flags); if (ret) mem_pool_free(object); @@ -760,14 +761,21 @@ static void __create_object(unsigned long ptr, size_t size, static void create_object(unsigned long ptr, size_t size, int min_count, gfp_t gfp) { - __create_object(ptr, size, min_count, gfp, false); + __create_object(ptr, size, min_count, gfp, 0); } /* Create kmemleak object which allocated with physical address. */ static void create_object_phys(unsigned long ptr, size_t size, int min_count, gfp_t gfp) { - __create_object(ptr, size, min_count, gfp, true); + __create_object(ptr, size, min_count, gfp, OBJECT_PHYS); +} + +/* Create kmemleak object corresponding to a per-CPU allocation. */ +static void create_object_percpu(unsigned long ptr, size_t size, + int min_count, gfp_t gfp) +{ + __create_object(ptr, size, min_count, gfp, OBJECT_PERCPU); } /* @@ -794,11 +802,11 @@ static void __delete_object(struct kmemleak_object *object) * Look up the metadata (struct kmemleak_object) corresponding to ptr and * delete it. */ -static void delete_object_full(unsigned long ptr) +static void delete_object_full(unsigned long ptr, unsigned int objflags) { struct kmemleak_object *object; - object = find_and_remove_object(ptr, 0, false); + object = find_and_remove_object(ptr, 0, objflags); if (!object) { #ifdef DEBUG kmemleak_warn("Freeing unknown object at 0x%08lx\n", @@ -814,7 +822,8 @@ static void delete_object_full(unsigned long ptr) * delete it. If the memory block is partially freed, the function may create * additional metadata for the remaining parts of the block. */ -static void delete_object_part(unsigned long ptr, size_t size, bool is_phys) +static void delete_object_part(unsigned long ptr, size_t size, + unsigned int objflags) { struct kmemleak_object *object, *object_l, *object_r; unsigned long start, end, flags; @@ -828,7 +837,7 @@ static void delete_object_part(unsigned long ptr, size_t size, bool is_phys) goto out; raw_spin_lock_irqsave(&kmemleak_lock, flags); - object = __find_and_remove_object(ptr, 1, is_phys); + object = __find_and_remove_object(ptr, 1, objflags); if (!object) { #ifdef DEBUG kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n", @@ -846,11 +855,11 @@ static void delete_object_part(unsigned long ptr, size_t size, bool is_phys) end = object->pointer + object->size; if ((ptr > start) && !__link_object(object_l, start, ptr - start, - object->min_count, is_phys)) + object->min_count, objflags)) object_l = NULL; if ((ptr + size < end) && !__link_object(object_r, ptr + size, end - ptr - size, - object->min_count, is_phys)) + object->min_count, objflags)) object_r = NULL; unlock: @@ -881,11 +890,11 @@ static void paint_it(struct kmemleak_object *object, int color) raw_spin_unlock_irqrestore(&object->lock, flags); } -static void paint_ptr(unsigned long ptr, int color, bool is_phys) +static void paint_ptr(unsigned long ptr, int color, unsigned int objflags) { struct kmemleak_object *object; - object = __find_and_get_object(ptr, 0, is_phys); + object = __find_and_get_object(ptr, 0, objflags); if (!object) { kmemleak_warn("Trying to color unknown object at 0x%08lx as %s\n", ptr, @@ -903,16 +912,16 @@ static void paint_ptr(unsigned long ptr, int color, bool is_phys) */ static void make_gray_object(unsigned long ptr) { - paint_ptr(ptr, KMEMLEAK_GREY, false); + paint_ptr(ptr, KMEMLEAK_GREY, 0); } /* * Mark the object as black-colored so that it is ignored from scans and * reporting. */ -static void make_black_object(unsigned long ptr, bool is_phys) +static void make_black_object(unsigned long ptr, unsigned int objflags) { - paint_ptr(ptr, KMEMLEAK_BLACK, is_phys); + paint_ptr(ptr, KMEMLEAK_BLACK, objflags); } /* @@ -1048,8 +1057,6 @@ EXPORT_SYMBOL_GPL(kmemleak_alloc); void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, gfp_t gfp) { - unsigned int cpu; - pr_debug("%s(0x%px, %zu)\n", __func__, ptr, size); /* @@ -1057,9 +1064,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, * (min_count is set to 0). */ if (kmemleak_enabled && ptr && !IS_ERR(ptr)) - for_each_possible_cpu(cpu) - create_object((unsigned long)per_cpu_ptr(ptr, cpu), - size, 0, gfp); + create_object_percpu((unsigned long)ptr, size, 0, gfp); } EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); @@ -1100,7 +1105,7 @@ void __ref kmemleak_free(const void *ptr) pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_free_enabled && ptr && !IS_ERR(ptr)) - delete_object_full((unsigned long)ptr); + delete_object_full((unsigned long)ptr, 0); } EXPORT_SYMBOL_GPL(kmemleak_free); @@ -1118,7 +1123,7 @@ void __ref kmemleak_free_part(const void *ptr, size_t size) pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) - delete_object_part((unsigned long)ptr, size, false); + delete_object_part((unsigned long)ptr, size, 0); } EXPORT_SYMBOL_GPL(kmemleak_free_part); @@ -1131,14 +1136,10 @@ EXPORT_SYMBOL_GPL(kmemleak_free_part); */ void __ref kmemleak_free_percpu(const void __percpu *ptr) { - unsigned int cpu; - pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_free_enabled && ptr && !IS_ERR(ptr)) - for_each_possible_cpu(cpu) - delete_object_full((unsigned long)per_cpu_ptr(ptr, - cpu)); + delete_object_full((unsigned long)ptr, OBJECT_PERCPU); } EXPORT_SYMBOL_GPL(kmemleak_free_percpu); @@ -1208,7 +1209,7 @@ void __ref kmemleak_ignore(const void *ptr) pr_debug("%s(0x%px)\n", __func__, ptr); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) - make_black_object((unsigned long)ptr, false); + make_black_object((unsigned long)ptr, 0); } EXPORT_SYMBOL(kmemleak_ignore); @@ -1282,7 +1283,7 @@ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) pr_debug("%s(0x%px)\n", __func__, &phys); if (kmemleak_enabled) - delete_object_part((unsigned long)phys, size, true); + delete_object_part((unsigned long)phys, size, OBJECT_PHYS); } EXPORT_SYMBOL(kmemleak_free_part_phys); @@ -1296,7 +1297,7 @@ void __ref kmemleak_ignore_phys(phys_addr_t phys) pr_debug("%s(0x%px)\n", __func__, &phys); if (kmemleak_enabled) - make_black_object((unsigned long)phys, true); + make_black_object((unsigned long)phys, OBJECT_PHYS); } EXPORT_SYMBOL(kmemleak_ignore_phys); @@ -1307,7 +1308,7 @@ static bool update_checksum(struct kmemleak_object *object) { u32 old_csum = object->checksum; - if (WARN_ON_ONCE(object->flags & OBJECT_PHYS)) + if (WARN_ON_ONCE(object->flags & (OBJECT_PHYS | OBJECT_PERCPU))) return false; kasan_disable_current(); @@ -1463,7 +1464,6 @@ static void scan_object(struct kmemleak_object *object) { struct kmemleak_scan_area *area; unsigned long flags; - void *obj_ptr; /* * Once the object->lock is acquired, the corresponding memory block @@ -1476,14 +1476,27 @@ static void scan_object(struct kmemleak_object *object) /* already freed object */ goto out; - obj_ptr = object->flags & OBJECT_PHYS ? - __va((phys_addr_t)object->pointer) : - (void *)object->pointer; + if (object->flags & OBJECT_PERCPU) { + unsigned int cpu; + + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr((void __percpu *)object->pointer, cpu); + void *end = start + object->size; - if (hlist_empty(&object->area_list) || + scan_block(start, end, object); + + raw_spin_unlock_irqrestore(&object->lock, flags); + cond_resched(); + raw_spin_lock_irqsave(&object->lock, flags); + if (!(object->flags & OBJECT_ALLOCATED)) + break; + } + } else if (hlist_empty(&object->area_list) || object->flags & OBJECT_FULL_SCAN) { - void *start = obj_ptr; - void *end = obj_ptr + object->size; + void *start = object->flags & OBJECT_PHYS ? + __va((phys_addr_t)object->pointer) : + (void *)object->pointer; + void *end = start + object->size; void *next; do { @@ -1498,11 +1511,12 @@ static void scan_object(struct kmemleak_object *object) cond_resched(); raw_spin_lock_irqsave(&object->lock, flags); } while (object->flags & OBJECT_ALLOCATED); - } else + } else { hlist_for_each_entry(area, &object->area_list, node) scan_block((void *)area->start, (void *)(area->start + area->size), object); + } out: raw_spin_unlock_irqrestore(&object->lock, flags); } diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index c19f47af0424..cf2d70e9c9a5 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -76,7 +76,7 @@ depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags, /* Don't sleep. */ flags &= ~(__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM); - handle = __stack_depot_save(entries, nr_entries, flags, true); + handle = stack_depot_save(entries, nr_entries, flags); return stack_depot_set_extra_bits(handle, extra); } @@ -185,11 +185,10 @@ depot_stack_handle_t kmsan_internal_chain_origin(depot_stack_handle_t id) /* * @entries is a local var in non-instrumented code, so KMSAN does not * know it is initialized. Explicitly unpoison it to avoid false - * positives when __stack_depot_save() passes it to instrumented code. + * positives when stack_depot_save() passes it to instrumented code. */ kmsan_internal_unpoison_memory(entries, sizeof(entries), false); - handle = __stack_depot_save(entries, ARRAY_SIZE(entries), __GFP_HIGH, - true); + handle = stack_depot_save(entries, ARRAY_SIZE(entries), __GFP_HIGH); return stack_depot_set_extra_bits(handle, extra_bits); } @@ -1099,9 +1099,9 @@ error: static u32 calc_checksum(struct page *page) { u32 checksum; - void *addr = kmap_atomic(page); + void *addr = kmap_local_page(page); checksum = xxhash(addr, PAGE_SIZE, 0); - kunmap_atomic(addr); + kunmap_local(addr); return checksum; } @@ -2876,48 +2876,51 @@ void __ksm_exit(struct mm_struct *mm) } struct page *ksm_might_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address) + struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = page_folio(page); struct anon_vma *anon_vma = folio_anon_vma(folio); - struct page *new_page; + struct folio *new_folio; - if (PageKsm(page)) { - if (page_stable_node(page) && + if (folio_test_large(folio)) + return page; + + if (folio_test_ksm(folio)) { + if (folio_stable_node(folio) && !(ksm_run & KSM_RUN_UNMERGE)) return page; /* no need to copy it */ } else if (!anon_vma) { return page; /* no need to copy it */ - } else if (page->index == linear_page_index(vma, address) && + } else if (folio->index == linear_page_index(vma, addr) && anon_vma->root == vma->anon_vma->root) { return page; /* still no need to copy it */ } if (PageHWPoison(page)) return ERR_PTR(-EHWPOISON); - if (!PageUptodate(page)) + if (!folio_test_uptodate(folio)) return page; /* let do_swap_page report the error */ - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (new_page && - mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) { - put_page(new_page); - new_page = NULL; + new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false); + if (new_folio && + mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) { + folio_put(new_folio); + new_folio = NULL; } - if (new_page) { - if (copy_mc_user_highpage(new_page, page, address, vma)) { - put_page(new_page); + if (new_folio) { + if (copy_mc_user_highpage(&new_folio->page, page, addr, vma)) { + folio_put(new_folio); memory_failure_queue(page_to_pfn(page), 0); return ERR_PTR(-EHWPOISON); } - SetPageDirty(new_page); - __SetPageUptodate(new_page); - __SetPageLocked(new_page); + folio_set_dirty(new_folio); + __folio_mark_uptodate(new_folio); + __folio_set_locked(new_folio); #ifdef CONFIG_SWAP count_vm_event(KSM_SWPIN_COPY); #endif } - return new_page; + return new_folio ? &new_folio->page : NULL; } void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) diff --git a/mm/list_lru.c b/mm/list_lru.c index a05e5bef3b40..fcca67ac26ec 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -116,21 +116,19 @@ list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr, } #endif /* CONFIG_MEMCG_KMEM */ -bool list_lru_add(struct list_lru *lru, struct list_head *item) +bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, + struct mem_cgroup *memcg) { - int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; - struct mem_cgroup *memcg; struct list_lru_one *l; spin_lock(&nlru->lock); if (list_empty(item)) { - l = list_lru_from_kmem(lru, nid, item, &memcg); + l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) - set_shrinker_bit(memcg, nid, - lru_shrinker_id(lru)); + set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); nlru->nr_items++; spin_unlock(&nlru->lock); return true; @@ -140,15 +138,25 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item) } EXPORT_SYMBOL_GPL(list_lru_add); -bool list_lru_del(struct list_lru *lru, struct list_head *item) +bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); + struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ? + mem_cgroup_from_slab_obj(item) : NULL; + + return list_lru_add(lru, item, nid, memcg); +} +EXPORT_SYMBOL_GPL(list_lru_add_obj); + +bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, + struct mem_cgroup *memcg) +{ struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; spin_lock(&nlru->lock); if (!list_empty(item)) { - l = list_lru_from_kmem(lru, nid, item, NULL); + l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); list_del_init(item); l->nr_items--; nlru->nr_items--; @@ -160,6 +168,16 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item) } EXPORT_SYMBOL_GPL(list_lru_del); +bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) +{ + int nid = page_to_nid(virt_to_page(item)); + struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ? + mem_cgroup_from_slab_obj(item) : NULL; + + return list_lru_del(lru, item, nid, memcg); +} +EXPORT_SYMBOL_GPL(list_lru_del_obj); + void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); @@ -175,6 +193,20 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, } EXPORT_SYMBOL_GPL(list_lru_isolate_move); +void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid, + struct mem_cgroup *memcg) +{ + struct list_lru_one *list = + list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); + + if (list_empty(item)) { + list_add_tail(item, &list->list); + if (!list->nr_items++) + set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); + } +} +EXPORT_SYMBOL_GPL(list_lru_putback); + unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { diff --git a/mm/memblock.c b/mm/memblock.c index 5a88d6d24d79..4a62f7774b65 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -735,6 +735,40 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) } /** + * memblock_validate_numa_coverage - check if amount of memory with + * no node ID assigned is less than a threshold + * @threshold_bytes: maximal number of pages that can have unassigned node + * ID (in bytes). + * + * A buggy firmware may report memory that does not belong to any node. + * Check if amount of such memory is below @threshold_bytes. + * + * Return: true on success, false on failure. + */ +bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes) +{ + unsigned long nr_pages = 0; + unsigned long start_pfn, end_pfn, mem_size_mb; + int nid, i; + + /* calculate lose page */ + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + if (nid == NUMA_NO_NODE) + nr_pages += end_pfn - start_pfn; + } + + if ((nr_pages << PAGE_SHIFT) >= threshold_bytes) { + mem_size_mb = memblock_phys_mem_size() >> 20; + pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n", + (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb); + return false; + } + + return true; +} + + +/** * memblock_isolate_range - isolate given range into disjoint memblocks * @type: memblock type to isolate range for * @base: base of range to isolate diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b226090fd906..69b0ad455242 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -703,6 +703,7 @@ static const unsigned int memcg_vm_event_stat[] = { #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) ZSWPIN, ZSWPOUT, + ZSWPWB, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE THP_FAULT_ALLOC, @@ -5614,6 +5615,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) page_counter_set_min(&memcg->memory, 0); page_counter_set_low(&memcg->memory, 0); + zswap_memcg_offline_cleanup(memcg); + memcg_offline_kmem(memcg); reparent_shrinker_deferred(memcg); wb_memcg_offline(memcg); @@ -6783,6 +6786,10 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, return nbytes; } +/* + * Note: don't forget to update the 'samples/cgroup/memcg_event_listener' + * if any new events become available. + */ static void __memory_events_show(struct seq_file *m, atomic_long_t *events) { seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW])); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 455093f73a70..5a23da5eb8c1 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -901,39 +901,38 @@ static const char * const action_page_types[] = { * The page count will stop it from being freed by unpoison. * Stress tests should be aware of this memory leak problem. */ -static int delete_from_lru_cache(struct page *p) +static int delete_from_lru_cache(struct folio *folio) { - if (isolate_lru_page(p)) { + if (folio_isolate_lru(folio)) { /* * Clear sensible page flags, so that the buddy system won't - * complain when the page is unpoison-and-freed. + * complain when the folio is unpoison-and-freed. */ - ClearPageActive(p); - ClearPageUnevictable(p); + folio_clear_active(folio); + folio_clear_unevictable(folio); /* * Poisoned page might never drop its ref count to 0 so we have * to uncharge it manually from its memcg. */ - mem_cgroup_uncharge(page_folio(p)); + mem_cgroup_uncharge(folio); /* - * drop the page count elevated by isolate_lru_page() + * drop the refcount elevated by folio_isolate_lru() */ - put_page(p); + folio_put(folio); return 0; } return -EIO; } -static int truncate_error_page(struct page *p, unsigned long pfn, +static int truncate_error_folio(struct folio *folio, unsigned long pfn, struct address_space *mapping) { int ret = MF_FAILED; - if (mapping->a_ops->error_remove_page) { - struct folio *folio = page_folio(p); - int err = mapping->a_ops->error_remove_page(mapping, p); + if (mapping->a_ops->error_remove_folio) { + int err = mapping->a_ops->error_remove_folio(mapping, folio); if (err != 0) pr_info("%#lx: Failed to punch page: %d\n", pfn, err); @@ -946,7 +945,7 @@ static int truncate_error_page(struct page *p, unsigned long pfn, * If the file system doesn't support it just invalidate * This fails on dirty or anything with private pages */ - if (invalidate_inode_page(p)) + if (mapping_evict_folio(mapping, folio)) ret = MF_RECOVERED; else pr_info("%#lx: Failed to invalidate\n", pfn); @@ -1013,17 +1012,18 @@ static int me_unknown(struct page_state *ps, struct page *p) */ static int me_pagecache_clean(struct page_state *ps, struct page *p) { + struct folio *folio = page_folio(p); int ret; struct address_space *mapping; bool extra_pins; - delete_from_lru_cache(p); + delete_from_lru_cache(folio); /* - * For anonymous pages we're done the only reference left + * For anonymous folios the only reference left * should be the one m_f() holds. */ - if (PageAnon(p)) { + if (folio_test_anon(folio)) { ret = MF_RECOVERED; goto out; } @@ -1035,11 +1035,9 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p) * has a reference, because it could be file system metadata * and that's not safe to truncate. */ - mapping = page_mapping(p); + mapping = folio_mapping(folio); if (!mapping) { - /* - * Page has been teared down in the meanwhile - */ + /* Folio has been torn down in the meantime */ ret = MF_FAILED; goto out; } @@ -1055,12 +1053,12 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p) * * Open: to take i_rwsem or not for this? Right now we don't. */ - ret = truncate_error_page(p, page_to_pfn(p), mapping); + ret = truncate_error_folio(folio, page_to_pfn(p), mapping); if (has_extra_refcount(ps, p, extra_pins)) ret = MF_FAILED; out: - unlock_page(p); + folio_unlock(folio); return ret; } @@ -1138,15 +1136,16 @@ static int me_pagecache_dirty(struct page_state *ps, struct page *p) */ static int me_swapcache_dirty(struct page_state *ps, struct page *p) { + struct folio *folio = page_folio(p); int ret; bool extra_pins = false; - ClearPageDirty(p); + folio_clear_dirty(folio); /* Trigger EIO in shmem: */ - ClearPageUptodate(p); + folio_clear_uptodate(folio); - ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; - unlock_page(p); + ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_DELAYED; + folio_unlock(folio); if (ret == MF_DELAYED) extra_pins = true; @@ -1164,7 +1163,7 @@ static int me_swapcache_clean(struct page_state *ps, struct page *p) delete_from_swap_cache(folio); - ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; + ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_RECOVERED; folio_unlock(folio); if (has_extra_refcount(ps, p, false)) @@ -1181,25 +1180,25 @@ static int me_swapcache_clean(struct page_state *ps, struct page *p) */ static int me_huge_page(struct page_state *ps, struct page *p) { + struct folio *folio = page_folio(p); int res; - struct page *hpage = compound_head(p); struct address_space *mapping; bool extra_pins = false; - mapping = page_mapping(hpage); + mapping = folio_mapping(folio); if (mapping) { - res = truncate_error_page(hpage, page_to_pfn(p), mapping); + res = truncate_error_folio(folio, page_to_pfn(p), mapping); /* The page is kept in page cache. */ extra_pins = true; - unlock_page(hpage); + folio_unlock(folio); } else { - unlock_page(hpage); + folio_unlock(folio); /* * migration entry prevents later access on error hugepage, * so we can free and dissolve it into buddy to save healthy * subpages. */ - put_page(hpage); + folio_put(folio); if (__page_handle_poison(p) >= 0) { page_ref_inc(p); res = MF_RECOVERED; @@ -2601,37 +2600,37 @@ unlock_mutex: } EXPORT_SYMBOL(unpoison_memory); -static bool isolate_page(struct page *page, struct list_head *pagelist) +static bool mf_isolate_folio(struct folio *folio, struct list_head *pagelist) { bool isolated = false; - if (PageHuge(page)) { - isolated = isolate_hugetlb(page_folio(page), pagelist); + if (folio_test_hugetlb(folio)) { + isolated = isolate_hugetlb(folio, pagelist); } else { - bool lru = !__PageMovable(page); + bool lru = !__folio_test_movable(folio); if (lru) - isolated = isolate_lru_page(page); + isolated = folio_isolate_lru(folio); else - isolated = isolate_movable_page(page, + isolated = isolate_movable_page(&folio->page, ISOLATE_UNEVICTABLE); if (isolated) { - list_add(&page->lru, pagelist); + list_add(&folio->lru, pagelist); if (lru) - inc_node_page_state(page, NR_ISOLATED_ANON + - page_is_file_lru(page)); + node_stat_add_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio)); } } /* - * If we succeed to isolate the page, we grabbed another refcount on - * the page, so we can safely drop the one we got from get_any_page(). - * If we failed to isolate the page, it means that we cannot go further + * If we succeed to isolate the folio, we grabbed another refcount on + * the folio, so we can safely drop the one we got from get_any_page(). + * If we failed to isolate the folio, it means that we cannot go further * and we will return an error, so drop the reference we got from * get_any_page() as well. */ - put_page(page); + folio_put(folio); return isolated; } @@ -2644,40 +2643,40 @@ static int soft_offline_in_use_page(struct page *page) { long ret = 0; unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_head(page); + struct folio *folio = page_folio(page); char const *msg_page[] = {"page", "hugepage"}; - bool huge = PageHuge(page); + bool huge = folio_test_hugetlb(folio); LIST_HEAD(pagelist); struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, }; - if (!huge && PageTransHuge(hpage)) { + if (!huge && folio_test_large(folio)) { if (try_to_split_thp_page(page)) { pr_info("soft offline: %#lx: thp split failed\n", pfn); return -EBUSY; } - hpage = page; + folio = page_folio(page); } - lock_page(page); + folio_lock(folio); if (!huge) - wait_on_page_writeback(page); + folio_wait_writeback(folio); if (PageHWPoison(page)) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); pr_info("soft offline: %#lx page already poisoned\n", pfn); return 0; } - if (!huge && PageLRU(page) && !PageSwapCache(page)) + if (!huge && folio_test_lru(folio) && !folio_test_swapcache(folio)) /* * Try to invalidate first. This should work for * non dirty unmapped page cache pages. */ - ret = invalidate_inode_page(page); - unlock_page(page); + ret = mapping_evict_folio(folio_mapping(folio), folio); + folio_unlock(folio); if (ret) { pr_info("soft_offline: %#lx: invalidated\n", pfn); @@ -2685,7 +2684,7 @@ static int soft_offline_in_use_page(struct page *page) return 0; } - if (isolate_page(hpage, &pagelist)) { + if (mf_isolate_folio(folio, &pagelist)) { ret = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL); if (!ret) { diff --git a/mm/memory.c b/mm/memory.c index 5c757fba8858..99582b188ed2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -374,6 +374,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, * be 0. This will underflow and is okay. */ next = mas_find(mas, ceiling - 1); + if (unlikely(xa_is_zero(next))) + next = NULL; /* * Hide vma from rmap and truncate_pagecache before freeing @@ -395,6 +397,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, && !is_vm_hugetlb_page(next)) { vma = next; next = mas_find(mas, ceiling - 1); + if (unlikely(xa_is_zero(next))) + next = NULL; if (mm_wr_locked) vma_start_write(vma); unlink_anon_vmas(vma); @@ -988,12 +992,17 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, return 0; } -static inline struct folio *page_copy_prealloc(struct mm_struct *src_mm, - struct vm_area_struct *vma, unsigned long addr) +static inline struct folio *folio_prealloc(struct mm_struct *src_mm, + struct vm_area_struct *vma, unsigned long addr, bool need_zero) { struct folio *new_folio; - new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false); + if (need_zero) + new_folio = vma_alloc_zeroed_movable_folio(vma, addr); + else + new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, + addr, false); + if (!new_folio) return NULL; @@ -1125,7 +1134,7 @@ again: } else if (ret == -EBUSY) { goto out; } else if (ret == -EAGAIN) { - prealloc = page_copy_prealloc(src_mm, src_vma, addr); + prealloc = folio_prealloc(src_mm, src_vma, addr, false); if (!prealloc) return -ENOMEM; } else if (ret) { @@ -1744,7 +1753,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, unmap_single_vma(tlb, vma, start, end, &details, mm_wr_locked); hugetlb_zap_end(vma, &details); - } while ((vma = mas_find(mas, tree_end - 1)) != NULL); + vma = mas_find(mas, tree_end - 1); + } while (vma && likely(!xa_is_zero(vma))); mmu_notifier_invalidate_range_end(&range); } @@ -1837,9 +1847,12 @@ pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, static int validate_page_before_insert(struct page *page) { - if (PageAnon(page) || PageSlab(page) || page_has_type(page)) + struct folio *folio = page_folio(page); + + if (folio_test_anon(folio) || folio_test_slab(folio) || + page_has_type(page)) return -EINVAL; - flush_dcache_page(page); + flush_dcache_folio(folio); return 0; } @@ -2836,7 +2849,8 @@ static inline int __wp_page_copy_user(struct page *dst, struct page *src, * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ - kaddr = kmap_atomic(dst); + kaddr = kmap_local_page(dst); + pagefault_disable(); uaddr = (void __user *)(addr & PAGE_MASK); /* @@ -2904,7 +2918,8 @@ warn: pte_unlock: if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); - kunmap_atomic(kaddr); + pagefault_enable(); + kunmap_local(kaddr); flush_dcache_page(dst); return ret; @@ -3102,6 +3117,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) int page_copied = 0; struct mmu_notifier_range range; vm_fault_t ret; + bool pfn_is_zero; delayacct_wpcopy_start(); @@ -3111,16 +3127,13 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) if (unlikely(ret)) goto out; - if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { - new_folio = vma_alloc_zeroed_movable_folio(vma, vmf->address); - if (!new_folio) - goto oom; - } else { + pfn_is_zero = is_zero_pfn(pte_pfn(vmf->orig_pte)); + new_folio = folio_prealloc(mm, vma, vmf->address, pfn_is_zero); + if (!new_folio) + goto oom; + + if (!pfn_is_zero) { int err; - new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, - vmf->address, false); - if (!new_folio) - goto oom; err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf); if (err) { @@ -3141,10 +3154,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) kmsan_copy_page_meta(&new_folio->page, vmf->page); } - if (mem_cgroup_charge(new_folio, mm, GFP_KERNEL)) - goto oom_free_new; - folio_throttle_swaprate(new_folio, GFP_KERNEL); - __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, @@ -3243,8 +3252,6 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) delayacct_wpcopy_end(); return 0; -oom_free_new: - folio_put(new_folio); oom: ret = VM_FAULT_OOM; out: @@ -4240,6 +4247,7 @@ oom: static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; + struct folio *folio; vm_fault_t ret; /* @@ -4268,27 +4276,26 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) VM_FAULT_DONE_COW))) return ret; + folio = page_folio(vmf->page); if (unlikely(PageHWPoison(vmf->page))) { - struct page *page = vmf->page; vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { - if (page_mapped(page)) - unmap_mapping_pages(page_mapping(page), - page->index, 1, false); - /* Retry if a clean page was removed from the cache. */ - if (invalidate_inode_page(page)) + if (page_mapped(vmf->page)) + unmap_mapping_folio(folio); + /* Retry if a clean folio was removed from the cache. */ + if (mapping_evict_folio(folio->mapping, folio)) poisonret = VM_FAULT_NOPAGE; - unlock_page(page); + folio_unlock(folio); } - put_page(page); + folio_put(folio); vmf->page = NULL; return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) - lock_page(vmf->page); + folio_lock(folio); else - VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); + VM_BUG_ON_PAGE(!folio_test_locked(folio), vmf->page); return ret; } @@ -4641,6 +4648,7 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf) static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; + struct folio *folio; vm_fault_t ret; ret = vmf_can_call_fault(vmf); @@ -4649,16 +4657,11 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (ret) return ret; - vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); - if (!vmf->cow_page) + folio = folio_prealloc(vma->vm_mm, vma, vmf->address, false); + if (!folio) return VM_FAULT_OOM; - if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm, - GFP_KERNEL)) { - put_page(vmf->cow_page); - return VM_FAULT_OOM; - } - folio_throttle_swaprate(page_folio(vmf->cow_page), GFP_KERNEL); + vmf->cow_page = &folio->page; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) @@ -4667,7 +4670,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) return ret; copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma); - __SetPageUptodate(vmf->cow_page); + __folio_mark_uptodate(folio); ret |= finish_fault(vmf); unlock_page(vmf->page); @@ -4676,7 +4679,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) goto uncharge_out; return ret; uncharge_out: - put_page(vmf->cow_page); + folio_put(folio); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 7a5fc89a8652..926e1cfb10e9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1380,6 +1380,85 @@ static bool mhp_supports_memmap_on_memory(unsigned long size) return arch_supports_memmap_on_memory(vmemmap_size); } +static void __ref remove_memory_blocks_and_altmaps(u64 start, u64 size) +{ + unsigned long memblock_size = memory_block_size_bytes(); + u64 cur_start; + + /* + * For memmap_on_memory, the altmaps were added on a per-memblock + * basis; we have to process each individual memory block. + */ + for (cur_start = start; cur_start < start + size; + cur_start += memblock_size) { + struct vmem_altmap *altmap = NULL; + struct memory_block *mem; + + mem = find_memory_block(pfn_to_section_nr(PFN_DOWN(cur_start))); + if (WARN_ON_ONCE(!mem)) + continue; + + altmap = mem->altmap; + mem->altmap = NULL; + + remove_memory_block_devices(cur_start, memblock_size); + + arch_remove_memory(cur_start, memblock_size, altmap); + + /* Verify that all vmemmap pages have actually been freed. */ + WARN(altmap->alloc, "Altmap not fully unmapped"); + kfree(altmap); + } +} + +static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group, + u64 start, u64 size) +{ + unsigned long memblock_size = memory_block_size_bytes(); + u64 cur_start; + int ret; + + for (cur_start = start; cur_start < start + size; + cur_start += memblock_size) { + struct mhp_params params = { .pgprot = + pgprot_mhp(PAGE_KERNEL) }; + struct vmem_altmap mhp_altmap = { + .base_pfn = PHYS_PFN(cur_start), + .end_pfn = PHYS_PFN(cur_start + memblock_size - 1), + }; + + mhp_altmap.free = memory_block_memmap_on_memory_pages(); + params.altmap = kmemdup(&mhp_altmap, sizeof(struct vmem_altmap), + GFP_KERNEL); + if (!params.altmap) { + ret = -ENOMEM; + goto out; + } + + /* call arch's memory hotadd */ + ret = arch_add_memory(nid, cur_start, memblock_size, ¶ms); + if (ret < 0) { + kfree(params.altmap); + goto out; + } + + /* create memory block devices after memory was added */ + ret = create_memory_block_devices(cur_start, memblock_size, + params.altmap, group); + if (ret) { + arch_remove_memory(cur_start, memblock_size, NULL); + kfree(params.altmap); + goto out; + } + } + + return 0; +out: + if (ret && cur_start != start) + remove_memory_blocks_and_altmaps(start, cur_start - start); + return ret; +} + /* * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations (triggered e.g. by sysfs). @@ -1390,10 +1469,6 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; enum memblock_flags memblock_flags = MEMBLOCK_NONE; - struct vmem_altmap mhp_altmap = { - .base_pfn = PHYS_PFN(res->start), - .end_pfn = PHYS_PFN(res->end), - }; struct memory_group *group = NULL; u64 start, size; bool new_node = false; @@ -1436,30 +1511,22 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) /* * Self hosted memmap array */ - if (mhp_flags & MHP_MEMMAP_ON_MEMORY) { - if (mhp_supports_memmap_on_memory(size)) { - mhp_altmap.free = memory_block_memmap_on_memory_pages(); - params.altmap = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL); - if (!params.altmap) { - ret = -ENOMEM; - goto error; - } + if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) && + mhp_supports_memmap_on_memory(memory_block_size_bytes())) { + ret = create_altmaps_and_memory_blocks(nid, group, start, size); + if (ret) + goto error; + } else { + ret = arch_add_memory(nid, start, size, ¶ms); + if (ret < 0) + goto error; - memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap)); + /* create memory block devices after memory was added */ + ret = create_memory_block_devices(start, size, NULL, group); + if (ret) { + arch_remove_memory(start, size, params.altmap); + goto error; } - /* fallback to not using altmap */ - } - - /* call arch's memory hotadd */ - ret = arch_add_memory(nid, start, size, ¶ms); - if (ret < 0) - goto error_free; - - /* create memory block devices after memory was added */ - ret = create_memory_block_devices(start, size, params.altmap, group); - if (ret) { - arch_remove_memory(start, size, params.altmap); - goto error_free; } if (new_node) { @@ -1496,8 +1563,6 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) walk_memory_blocks(start, size, NULL, online_memory_block); return ret; -error_free: - kfree(params.altmap); error: if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) memblock_remove(start, size); @@ -2067,17 +2132,13 @@ static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) return 0; } -static int test_has_altmap_cb(struct memory_block *mem, void *arg) +static int count_memory_range_altmaps_cb(struct memory_block *mem, void *arg) { - struct memory_block **mem_ptr = (struct memory_block **)arg; - /* - * return the memblock if we have altmap - * and break callback. - */ - if (mem->altmap) { - *mem_ptr = mem; - return 1; - } + u64 *num_altmaps = (u64 *)arg; + + if (mem->altmap) + *num_altmaps += 1; + return 0; } @@ -2151,11 +2212,29 @@ void try_offline_node(int nid) } EXPORT_SYMBOL(try_offline_node); +static int memory_blocks_have_altmaps(u64 start, u64 size) +{ + u64 num_memblocks = size / memory_block_size_bytes(); + u64 num_altmaps = 0; + + if (!mhp_memmap_on_memory()) + return 0; + + walk_memory_blocks(start, size, &num_altmaps, + count_memory_range_altmaps_cb); + + if (num_altmaps == 0) + return 0; + + if (WARN_ON_ONCE(num_memblocks != num_altmaps)) + return -EINVAL; + + return 1; +} + static int __ref try_remove_memory(u64 start, u64 size) { - struct memory_block *mem; - int rc = 0, nid = NUMA_NO_NODE; - struct vmem_altmap *altmap = NULL; + int rc, nid = NUMA_NO_NODE; BUG_ON(check_hotplug_memory_range(start, size)); @@ -2172,45 +2251,26 @@ static int __ref try_remove_memory(u64 start, u64 size) if (rc) return rc; - /* - * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in - * the same granularity it was added - a single memory block. - */ - if (mhp_memmap_on_memory()) { - rc = walk_memory_blocks(start, size, &mem, test_has_altmap_cb); - if (rc) { - if (size != memory_block_size_bytes()) { - pr_warn("Refuse to remove %#llx - %#llx," - "wrong granularity\n", - start, start + size); - return -EINVAL; - } - altmap = mem->altmap; - /* - * Mark altmap NULL so that we can add a debug - * check on memblock free. - */ - mem->altmap = NULL; - } - } - /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); - /* - * Memory block device removal under the device_hotplug_lock is - * a barrier against racing online attempts. - */ - remove_memory_block_devices(start, size); - mem_hotplug_begin(); - arch_remove_memory(start, size, altmap); - - /* Verify that all vmemmap pages have actually been freed. */ - if (altmap) { - WARN(altmap->alloc, "Altmap not fully unmapped"); - kfree(altmap); + rc = memory_blocks_have_altmaps(start, size); + if (rc < 0) { + mem_hotplug_done(); + return rc; + } else if (!rc) { + /* + * Memory block device removal under the device_hotplug_lock is + * a barrier against racing online attempts. + * No altmaps present, do the removal directly + */ + remove_memory_block_devices(start, size); + arch_remove_memory(start, size, NULL); + } else { + /* all memblocks in the range have altmaps */ + remove_memory_blocks_and_altmaps(start, size); } if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { diff --git a/mm/mempool.c b/mm/mempool.c index 734bcf5afbb7..b3d2084fd989 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -64,10 +64,10 @@ static void check_element(mempool_t *pool, void *element) } else if (pool->free == mempool_free_pages) { /* Mempools backed by page allocator */ int order = (int)(long)pool->pool_data; - void *addr = kmap_atomic((struct page *)element); + void *addr = kmap_local_page((struct page *)element); __check_element(pool, addr, 1UL << (PAGE_SHIFT + order)); - kunmap_atomic(addr); + kunmap_local(addr); } } @@ -89,10 +89,10 @@ static void poison_element(mempool_t *pool, void *element) } else if (pool->alloc == mempool_alloc_pages) { /* Mempools backed by page allocator */ int order = (int)(long)pool->pool_data; - void *addr = kmap_atomic((struct page *)element); + void *addr = kmap_local_page((struct page *)element); __poison_element(addr, 1UL << (PAGE_SHIFT + order)); - kunmap_atomic(addr); + kunmap_local(addr); } } #else /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ diff --git a/mm/memremap.c b/mm/memremap.c index bee85560a243..9531faa92a7c 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -7,6 +7,7 @@ #include <linux/memremap.h> #include <linux/pfn_t.h> #include <linux/swap.h> +#include <linux/mm.h> #include <linux/mmzone.h> #include <linux/swapops.h> #include <linux/types.h> @@ -422,19 +423,6 @@ void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) } EXPORT_SYMBOL_GPL(devm_memunmap_pages); -unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) -{ - /* number of pfns from base where pfn_to_page() is valid */ - if (altmap) - return altmap->reserve + altmap->free; - return 0; -} - -void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) -{ - altmap->alloc -= nr_pfns; -} - /** * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn * @pfn: page frame number to lookup page_map diff --git a/mm/mm_init.c b/mm/mm_init.c index 077bfe393b5e..a5f91eba4f8d 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -796,6 +796,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) * - physical memory bank size is not necessarily the exact multiple of the * arbitrary section size * - early reserved memory may not be listed in memblock.memory + * - non-memory regions covered by the contigious flatmem mapping * - memory layouts defined with memmap= kernel parameter may not align * nicely with memmap sections * @@ -826,7 +827,7 @@ static void __init init_unavailable_range(unsigned long spfn, } if (pgcnt) - pr_info("On node %d, zone %s: %lld pages in unavailable ranges", + pr_info("On node %d, zone %s: %lld pages in unavailable ranges\n", node, zone_names[zone], pgcnt); } diff --git a/mm/mmap.c b/mm/mmap.c index 1971bfffcc03..e8470b6b678c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2207,42 +2207,7 @@ struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned lon } #endif -/* - * IA64 has some horrid mapping rules: it can expand both up and down, - * but with various special rules. - * - * We'll get rid of this architecture eventually, so the ugliness is - * temporary. - */ -#ifdef CONFIG_IA64 -static inline bool vma_expand_ok(struct vm_area_struct *vma, unsigned long addr) -{ - return REGION_NUMBER(addr) == REGION_NUMBER(vma->vm_start) && - REGION_OFFSET(addr) < RGN_MAP_LIMIT; -} - -/* - * IA64 stacks grow down, but there's a special register backing store - * that can grow up. Only sequentially, though, so the new address must - * match vm_end. - */ -static inline int vma_expand_up(struct vm_area_struct *vma, unsigned long addr) -{ - if (!vma_expand_ok(vma, addr)) - return -EFAULT; - if (vma->vm_end != (addr & PAGE_MASK)) - return -EFAULT; - return expand_upwards(vma, addr); -} - -static inline bool vma_expand_down(struct vm_area_struct *vma, unsigned long addr) -{ - if (!vma_expand_ok(vma, addr)) - return -EFAULT; - return expand_downwards(vma, addr); -} - -#elif defined(CONFIG_STACK_GROWSUP) +#if defined(CONFIG_STACK_GROWSUP) #define vma_expand_up(vma,addr) expand_upwards(vma, addr) #define vma_expand_down(vma, addr) (-EFAULT) @@ -3294,10 +3259,11 @@ void exit_mmap(struct mm_struct *mm) arch_exit_mmap(mm); vma = mas_find(&mas, ULONG_MAX); - if (!vma) { + if (!vma || unlikely(xa_is_zero(vma))) { /* Can happen if dup_mmap() received an OOM */ mmap_read_unlock(mm); - return; + mmap_write_lock(mm); + goto destroy; } lru_add_drain(); @@ -3332,11 +3298,13 @@ void exit_mmap(struct mm_struct *mm) remove_vma(vma, true); count++; cond_resched(); - } while ((vma = mas_find(&mas, ULONG_MAX)) != NULL); + vma = mas_find(&mas, ULONG_MAX); + } while (vma && likely(!xa_is_zero(vma))); BUG_ON(count != mm->map_count); trace_exit_mmap(mm); +destroy: __mt_destroy(&mm->mm_mt); mmap_write_unlock(mm); vm_unacct_memory(nr_accounted); diff --git a/mm/mmzone.c b/mm/mmzone.c index b594d3f268fe..c01896eca736 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -78,6 +78,7 @@ void lruvec_init(struct lruvec *lruvec) memset(lruvec, 0, sizeof(struct lruvec)); spin_lock_init(&lruvec->lru_lock); + zswap_lruvec_state_init(lruvec); for_each_lru(lru) INIT_LIST_HEAD(&lruvec->lists[lru]); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 9e6071fde34a..91ccd82097c2 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -399,10 +399,11 @@ static int dump_task(struct task_struct *p, void *arg) return 0; } - pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n", + pr_info("[%7d] %5d %5d %8lu %8lu %8lu %8lu %9lu %8ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), - mm_pgtables_bytes(task->mm), + get_mm_counter(task->mm, MM_ANONPAGES), get_mm_counter(task->mm, MM_FILEPAGES), + get_mm_counter(task->mm, MM_SHMEMPAGES), mm_pgtables_bytes(task->mm), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); @@ -423,7 +424,7 @@ static int dump_task(struct task_struct *p, void *arg) static void dump_tasks(struct oom_control *oc) { pr_info("Tasks state (memory values in pages):\n"); - pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n"); + pr_info("[ pid ] uid tgid total_vm rss rss_anon rss_file rss_shmem pgtables_bytes swapents oom_score_adj name\n"); if (is_memcg_oom(oc)) mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ee2fd6a6af40..ca64bd513fa2 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2982,67 +2982,63 @@ bool __folio_end_writeback(struct folio *folio) return ret; } -bool __folio_start_writeback(struct folio *folio, bool keep_write) +void __folio_start_writeback(struct folio *folio, bool keep_write) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); - bool ret; int access_ret; + VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); + folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; + bool on_wblist; xas_lock_irqsave(&xas, flags); xas_load(&xas); - ret = folio_test_set_writeback(folio); - if (!ret) { - bool on_wblist; + folio_test_set_writeback(folio); - on_wblist = mapping_tagged(mapping, - PAGECACHE_TAG_WRITEBACK); + on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); - xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); - if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { - struct bdi_writeback *wb = inode_to_wb(inode); - - wb_stat_mod(wb, WB_WRITEBACK, nr); - if (!on_wblist) - wb_inode_writeback_start(wb); - } + xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); + if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { + struct bdi_writeback *wb = inode_to_wb(inode); - /* - * We can come through here when swapping - * anonymous folios, so we don't necessarily - * have an inode to track for sync. - */ - if (mapping->host && !on_wblist) - sb_mark_inode_writeback(mapping->host); + wb_stat_mod(wb, WB_WRITEBACK, nr); + if (!on_wblist) + wb_inode_writeback_start(wb); } + + /* + * We can come through here when swapping anonymous + * folios, so we don't necessarily have an inode to + * track for sync. + */ + if (mapping->host && !on_wblist) + sb_mark_inode_writeback(mapping->host); if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { - ret = folio_test_set_writeback(folio); - } - if (!ret) { - lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); - zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); + folio_test_set_writeback(folio); } + + lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); folio_memcg_unlock(folio); + access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_FOLIO(access_ret != 0, folio); - - return ret; } EXPORT_SYMBOL(__folio_start_writeback); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 733732e7e0ba..7ea9c33320bf 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1086,13 +1086,11 @@ static __always_inline bool free_pages_prepare(struct page *page, trace_mm_page_free(page, order); kmsan_free_page(page, order); + if (memcg_kmem_online() && PageMemcgKmem(page)) + __memcg_kmem_uncharge_page(page, order); + if (unlikely(PageHWPoison(page)) && !order) { - /* - * Do not let hwpoison pages hit pcplists/buddy - * Untie memcg state and reset page's owner - */ - if (memcg_kmem_online() && PageMemcgKmem(page)) - __memcg_kmem_uncharge_page(page, order); + /* Do not let hwpoison pages hit pcplists/buddy */ reset_page_owner(page, order); page_table_check_free(page, order); return false; @@ -1123,8 +1121,6 @@ static __always_inline bool free_pages_prepare(struct page *page, } if (PageMappingFlags(page)) page->mapping = NULL; - if (memcg_kmem_online() && PageMemcgKmem(page)) - __memcg_kmem_uncharge_page(page, order); if (is_check_pages_enabled()) { if (free_page_is_bad(page)) bad++; @@ -1884,10 +1880,14 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone) unsigned long max_managed, flags; /* - * Limit the number reserved to 1 pageblock or roughly 1% of a zone. + * The number reserved as: minimum is 1 pageblock, maximum is + * roughly 1% of a zone. But if 1% of a zone falls below a + * pageblock size, then don't reserve any pageblocks. * Check is race-prone but harmless. */ - max_managed = (zone_managed_pages(zone) / 100) + pageblock_nr_pages; + if ((zone_managed_pages(zone) / 100) < pageblock_nr_pages) + return; + max_managed = ALIGN((zone_managed_pages(zone) / 100), pageblock_nr_pages); if (zone->nr_reserved_highatomic >= max_managed) return; @@ -3951,14 +3951,9 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, else (*no_progress_loops)++; - /* - * Make sure we converge to OOM if we cannot make any progress - * several times in the row. - */ - if (*no_progress_loops > MAX_RECLAIM_RETRIES) { - /* Before OOM, exhaust highatomic_reserve */ - return unreserve_highatomic_pageblock(ac, true); - } + if (*no_progress_loops > MAX_RECLAIM_RETRIES) + goto out; + /* * Keep reclaiming pages while there is a chance this will lead @@ -4001,6 +3996,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, schedule_timeout_uninterruptible(1); else cond_resched(); +out: + /* Before OOM, exhaust highatomic_reserve */ + if (!ret) + return unreserve_highatomic_pageblock(ac, true); + return ret; } diff --git a/mm/page_owner.c b/mm/page_owner.c index 4f13ce7d2452..e7eba7688881 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -32,6 +32,8 @@ struct page_owner { char comm[TASK_COMM_LEN]; pid_t pid; pid_t tgid; + pid_t free_pid; + pid_t free_tgid; }; static bool page_owner_enabled __initdata; @@ -152,6 +154,8 @@ void __reset_page_owner(struct page *page, unsigned short order) page_owner = get_page_owner(page_ext); page_owner->free_handle = handle; page_owner->free_ts_nsec = free_ts_nsec; + page_owner->free_pid = current->pid; + page_owner->free_tgid = current->tgid; page_ext = page_ext_next(page_ext); } page_ext_put(page_ext); @@ -253,6 +257,8 @@ void __folio_copy_owner(struct folio *newfolio, struct folio *old) new_page_owner->handle = old_page_owner->handle; new_page_owner->pid = old_page_owner->pid; new_page_owner->tgid = old_page_owner->tgid; + new_page_owner->free_pid = old_page_owner->free_pid; + new_page_owner->free_tgid = old_page_owner->free_tgid; new_page_owner->ts_nsec = old_page_owner->ts_nsec; new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; strcpy(new_page_owner->comm, old_page_owner->comm); @@ -495,7 +501,8 @@ void __dump_page_owner(const struct page *page) if (!handle) { pr_alert("page_owner free stack trace missing\n"); } else { - pr_alert("page last free stack trace:\n"); + pr_alert("page last free pid %d tgid %d stack trace:\n", + page_owner->free_pid, page_owner->free_tgid); stack_depot_print(handle); } diff --git a/mm/page_poison.c b/mm/page_poison.c index b4f456437b7e..3e9037363cf9 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -21,13 +21,13 @@ early_param("page_poison", early_page_poison_param); static void poison_page(struct page *page) { - void *addr = kmap_atomic(page); + void *addr = kmap_local_page(page); /* KASAN still think the page is in-use, so skip it. */ kasan_disable_current(); memset(kasan_reset_tag(addr), PAGE_POISON, PAGE_SIZE); kasan_enable_current(); - kunmap_atomic(addr); + kunmap_local(addr); } void __kernel_poison_pages(struct page *page, int n) @@ -77,7 +77,7 @@ static void unpoison_page(struct page *page) { void *addr; - addr = kmap_atomic(page); + addr = kmap_local_page(page); kasan_disable_current(); /* * Page poisoning when enabled poisons each and every page @@ -86,7 +86,7 @@ static void unpoison_page(struct page *page) */ check_poison_mem(page, kasan_reset_tag(addr), PAGE_SIZE); kasan_enable_current(); - kunmap_atomic(addr); + kunmap_local(addr); } void __kernel_unpoison_pages(struct page *page, int n) diff --git a/mm/pagewalk.c b/mm/pagewalk.c index b7d7e4fcfad7..f46c80b18ce4 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -539,6 +539,11 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, * not backed by VMAs. Because 'unusual' entries may be walked this function * will also not lock the PTEs for the pte_entry() callback. This is useful for * walking the kernel pages tables or page tables for firmware. + * + * Note: Be careful to walk the kernel pages tables, the caller may be need to + * take other effective approache (mmap lock may be insufficient) to prevent + * the intermediate kernel page tables belonging to the specified address range + * from being freed (e.g. memory hot-remove). */ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, @@ -556,7 +561,29 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, if (start >= end || !walk.mm) return -EINVAL; - mmap_assert_write_locked(walk.mm); + /* + * 1) For walking the user virtual address space: + * + * The mmap lock protects the page walker from changes to the page + * tables during the walk. However a read lock is insufficient to + * protect those areas which don't have a VMA as munmap() detaches + * the VMAs before downgrading to a read lock and actually tearing + * down PTEs/page tables. In which case, the mmap write lock should + * be hold. + * + * 2) For walking the kernel virtual address space: + * + * The kernel intermediate page tables usually do not be freed, so + * the mmap map read lock is sufficient. But there are some exceptions. + * E.g. memory hot-remove. In which case, the mmap lock is insufficient + * to prevent the intermediate kernel pages tables belonging to the + * specified address range from being freed. The caller should take + * other actions to prevent this race. + */ + if (mm == &init_mm) + mmap_assert_locked(walk.mm); + else + mmap_assert_write_locked(walk.mm); return walk_pgd_range(start, end, &walk); } diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 0523edab03a6..b308e96cd05a 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -53,7 +53,10 @@ static int process_vm_rw_pages(struct page **pages, } /* Maximum number of pages kmalloc'd to hold struct page's during copy */ -#define PVM_MAX_KMALLOC_PAGES (PAGE_SIZE * 2) +#define PVM_MAX_KMALLOC_PAGES 2 + +/* Maximum number of pages that can be stored at a time */ +#define PVM_MAX_USER_PAGES (PVM_MAX_KMALLOC_PAGES * PAGE_SIZE / sizeof(struct page *)) /** * process_vm_rw_single_vec - read/write pages from task specified @@ -79,8 +82,6 @@ static int process_vm_rw_single_vec(unsigned long addr, unsigned long start_offset = addr - pa; unsigned long nr_pages; ssize_t rc = 0; - unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES - / sizeof(struct pages *); unsigned int flags = 0; /* Work out address and page range required */ @@ -92,7 +93,7 @@ static int process_vm_rw_single_vec(unsigned long addr, flags |= FOLL_WRITE; while (!rc && nr_pages && iov_iter_count(iter)) { - int pinned_pages = min(nr_pages, max_pages_per_loop); + int pinned_pages = min_t(unsigned long, nr_pages, PVM_MAX_USER_PAGES); int locked = 1; size_t bytes; @@ -171,7 +172,7 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, iov_len = rvec[i].iov_len; if (iov_len > 0) { nr_pages_iov = ((unsigned long)rvec[i].iov_base - + iov_len) + + iov_len - 1) / PAGE_SIZE - (unsigned long)rvec[i].iov_base / PAGE_SIZE + 1; nr_pages = max(nr_pages, nr_pages_iov); @@ -184,8 +185,8 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, if (nr_pages > PVM_MAX_PP_ARRAY_COUNT) { /* For reliability don't try to kmalloc more than 2 pages worth */ - process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES, - sizeof(struct pages *)*nr_pages), + process_pages = kmalloc(min_t(size_t, PVM_MAX_KMALLOC_PAGES * PAGE_SIZE, + sizeof(struct page *)*nr_pages), GFP_KERNEL); if (!process_pages) diff --git a/mm/readahead.c b/mm/readahead.c index 6925e6959fd3..23620c57c122 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -511,16 +511,14 @@ void page_cache_ra_order(struct readahead_control *ractl, unsigned int order = new_order; /* Align with smaller pages if needed */ - if (index & ((1UL << order) - 1)) { + if (index & ((1UL << order) - 1)) order = __ffs(index); - if (order == 1) - order = 0; - } /* Don't allocate pages past EOF */ - while (index + (1UL << order) - 1 > limit) { - if (--order == 1) - order = 0; - } + while (index + (1UL << order) - 1 > limit) + order--; + /* THP machinery does not support order-1 */ + if (order == 1) + order = 0; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; diff --git a/mm/shmem.c b/mm/shmem.c index 0d1ce70bce38..c62f904ba1ca 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4462,8 +4462,8 @@ static void __init shmem_destroy_inodecache(void) } /* Keep the page in page cache instead of truncating it */ -static int shmem_error_remove_page(struct address_space *mapping, - struct page *page) +static int shmem_error_remove_folio(struct address_space *mapping, + struct folio *folio) { return 0; } @@ -4478,7 +4478,7 @@ const struct address_space_operations shmem_aops = { #ifdef CONFIG_MIGRATION .migrate_folio = migrate_folio, #endif - .error_remove_page = shmem_error_remove_page, + .error_remove_folio = shmem_error_remove_folio, }; EXPORT_SYMBOL(shmem_aops); diff --git a/mm/slub.c b/mm/slub.c index 63d281dfacdb..782bd8a6bd34 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -870,20 +870,20 @@ static inline void set_orig_size(struct kmem_cache *s, void *object, unsigned int orig_size) { void *p = kasan_reset_tag(object); + unsigned int kasan_meta_size; if (!slub_debug_orig_size(s)) return; -#ifdef CONFIG_KASAN_GENERIC /* - * KASAN could save its free meta data in object's data area at - * offset 0, if the size is larger than 'orig_size', it will - * overlap the data redzone in [orig_size+1, object_size], and - * the check should be skipped. + * KASAN can save its free meta data inside of the object at offset 0. + * If this meta data size is larger than 'orig_size', it will overlap + * the data redzone in [orig_size+1, object_size]. Thus, we adjust + * 'orig_size' to be as at least as big as KASAN's meta data. */ - if (kasan_metadata_size(s, true) > orig_size) - orig_size = s->object_size; -#endif + kasan_meta_size = kasan_metadata_size(s, true); + if (kasan_meta_size > orig_size) + orig_size = kasan_meta_size; p += get_info_end(s); p += sizeof(struct track) * 2; @@ -1192,7 +1192,7 @@ static int check_object(struct kmem_cache *s, struct slab *slab, { u8 *p = object; u8 *endobject = object + s->object_size; - unsigned int orig_size; + unsigned int orig_size, kasan_meta_size; if (s->flags & SLAB_RED_ZONE) { if (!check_bytes_and_report(s, slab, object, "Left Redzone", @@ -1222,12 +1222,23 @@ static int check_object(struct kmem_cache *s, struct slab *slab, } if (s->flags & SLAB_POISON) { - if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && - (!check_bytes_and_report(s, slab, p, "Poison", p, - POISON_FREE, s->object_size - 1) || - !check_bytes_and_report(s, slab, p, "End Poison", - p + s->object_size - 1, POISON_END, 1))) - return 0; + if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON)) { + /* + * KASAN can save its free meta data inside of the + * object at offset 0. Thus, skip checking the part of + * the redzone that overlaps with the meta data. + */ + kasan_meta_size = kasan_metadata_size(s, true); + if (kasan_meta_size < s->object_size - 1 && + !check_bytes_and_report(s, slab, p, "Poison", + p + kasan_meta_size, POISON_FREE, + s->object_size - kasan_meta_size - 1)) + return 0; + if (kasan_meta_size < s->object_size && + !check_bytes_and_report(s, slab, p, "End Poison", + p + s->object_size - 1, POISON_END, 1)) + return 0; + } /* * check_pad_bytes cleans up on its own. */ diff --git a/mm/swap.h b/mm/swap.h index 73c332ee4d91..c0dc73e10e91 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -51,7 +51,8 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct swap_iocb **plug); struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx, - bool *new_page_allocated); + bool *new_page_allocated, + bool skip_if_exists); struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, struct mempolicy *mpol, pgoff_t ilx); struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, diff --git a/mm/swap_state.c b/mm/swap_state.c index 85d9e5806a6a..c597cec606e4 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -412,7 +412,8 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping, struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx, - bool *new_page_allocated) + bool *new_page_allocated, + bool skip_if_exists) { struct swap_info_struct *si; struct folio *folio; @@ -471,6 +472,17 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, goto fail_put_swap; /* + * Protect against a recursive call to __read_swap_cache_async() + * on the same entry waiting forever here because SWAP_HAS_CACHE + * is set but the folio is not the swap cache yet. This can + * happen today if mem_cgroup_swapin_charge_folio() below + * triggers reclaim through zswap, which may call + * __read_swap_cache_async() in the writeback path. + */ + if (skip_if_exists) + goto fail_put_swap; + + /* * We might race against __delete_from_swap_cache(), and * stumble across a swap_map entry whose SWAP_HAS_CACHE * has not yet been cleared. Or race against another @@ -537,7 +549,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, mpol = get_vma_policy(vma, addr, 0, &ilx); page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); mpol_cond_put(mpol); if (page_allocated) @@ -654,7 +666,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, /* Ok, do the async read-ahead now */ page = __read_swap_cache_async( swp_entry(swp_type(entry), offset), - gfp_mask, mpol, ilx, &page_allocated); + gfp_mask, mpol, ilx, &page_allocated, false); if (!page) continue; if (page_allocated) { @@ -672,9 +684,10 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, skip: /* The page was likely read above, so no need for plugging here */ page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); if (unlikely(page_allocated)) swap_readpage(page, false, NULL); + zswap_page_swapin(page); return page; } @@ -827,7 +840,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, pte_unmap(pte); pte = NULL; page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, - &page_allocated); + &page_allocated, false); if (!page) continue; if (page_allocated) { @@ -847,9 +860,10 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, skip: /* The page was likely read above, so no need for plugging here */ page = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx, - &page_allocated); + &page_allocated, false); if (unlikely(page_allocated)) swap_readpage(page, false, NULL); + zswap_page_swapin(page); return page; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 4bc70f459164..8be70912e298 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1495,9 +1495,9 @@ int swp_swapcount(swp_entry_t entry) do { page = list_next_entry(page, lru); - map = kmap_atomic(page); + map = kmap_local_page(page); tmp_count = map[offset]; - kunmap_atomic(map); + kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); @@ -3477,9 +3477,9 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; - map = kmap_atomic(list_page) + offset; + map = kmap_local_page(list_page) + offset; count = *map; - kunmap_atomic(map); + kunmap_local(map); /* * If this continuation count now has some space in it, @@ -3529,7 +3529,7 @@ static bool swap_count_continued(struct swap_info_struct *si, spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); - map = kmap_atomic(page) + offset; + map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ @@ -3539,27 +3539,27 @@ static bool swap_count_continued(struct swap_info_struct *si, * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { - kunmap_atomic(map); + kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); - map = kmap_atomic(page) + offset; + map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { - kunmap_atomic(map); + kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } - map = kmap_atomic(page) + offset; + map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; - kunmap_atomic(map); + kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { - map = kmap_atomic(page) + offset; + map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; - kunmap_atomic(map); + kunmap_local(map); } ret = true; /* incremented */ @@ -3569,21 +3569,21 @@ init_map: *map = 0; /* we didn't zero the page */ */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { - kunmap_atomic(map); + kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); - map = kmap_atomic(page) + offset; + map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; - kunmap_atomic(map); + kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { - map = kmap_atomic(page) + offset; + map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; - kunmap_atomic(map); + kunmap_local(map); } ret = count == COUNT_CONTINUED; } diff --git a/mm/truncate.c b/mm/truncate.c index 8e3aa9e8618e..725b150e47ac 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -250,10 +250,9 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) /* * Used to get rid of pages on hardware memory corruption. */ -int generic_error_remove_page(struct address_space *mapping, struct page *page) +int generic_error_remove_folio(struct address_space *mapping, + struct folio *folio) { - VM_BUG_ON_PAGE(PageTail(page), page); - if (!mapping) return -EINVAL; /* @@ -262,13 +261,26 @@ int generic_error_remove_page(struct address_space *mapping, struct page *page) */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; - return truncate_inode_folio(mapping, page_folio(page)); + return truncate_inode_folio(mapping, folio); } -EXPORT_SYMBOL(generic_error_remove_page); +EXPORT_SYMBOL(generic_error_remove_folio); -static long mapping_evict_folio(struct address_space *mapping, - struct folio *folio) +/** + * mapping_evict_folio() - Remove an unused folio from the page-cache. + * @mapping: The mapping this folio belongs to. + * @folio: The folio to remove. + * + * Safely remove one folio from the page cache. + * It only drops clean, unused folios. + * + * Context: Folio must be locked. + * Return: The number of pages successfully removed. + */ +long mapping_evict_folio(struct address_space *mapping, struct folio *folio) { + /* The page may have been truncated before it was locked */ + if (!mapping) + return 0; if (folio_test_dirty(folio) || folio_test_writeback(folio)) return 0; /* The refcount will be elevated if any page in the folio is mapped */ @@ -282,27 +294,6 @@ static long mapping_evict_folio(struct address_space *mapping, } /** - * invalidate_inode_page() - Remove an unused page from the pagecache. - * @page: The page to remove. - * - * Safely invalidate one page from its pagecache mapping. - * It only drops clean, unused pages. - * - * Context: Page must be locked. - * Return: The number of pages successfully removed. - */ -long invalidate_inode_page(struct page *page) -{ - struct folio *folio = page_folio(page); - struct address_space *mapping = folio_mapping(folio); - - /* The page may have been truncated before it was locked */ - if (!mapping) - return 0; - return mapping_evict_folio(mapping, folio); -} - -/** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate @@ -560,9 +551,9 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, EXPORT_SYMBOL(invalidate_mapping_pages); /* - * This is like invalidate_inode_page(), except it ignores the page's + * This is like mapping_evict_folio(), except it ignores the folio's * refcount. We do this because invalidate_inode_pages2() needs stronger - * invalidation guarantees, and cannot afford to leave pages behind because + * invalidation guarantees, and cannot afford to leave folios behind because * shrink_page_list() has a temp ref on them, or because they're transiently * sitting in the folio_add_lru() caches. */ diff --git a/mm/util.c b/mm/util.c index 744b4d7e3fae..5a6a9802583b 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1047,11 +1047,11 @@ int __weak memcmp_pages(struct page *page1, struct page *page2) char *addr1, *addr2; int ret; - addr1 = kmap_atomic(page1); - addr2 = kmap_atomic(page2); + addr1 = kmap_local_page(page1); + addr2 = kmap_local_page(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); - kunmap_atomic(addr2); - kunmap_atomic(addr1); + kunmap_local(addr2); + kunmap_local(addr1); return ret; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 9dd8977de5a2..f0eba9ef3332 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -409,12 +409,14 @@ void drop_slab(void) static int reclaimer_offset(void) { +#ifdef CONFIG_NUMA_BALANCING BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD); - BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != - PGSCAN_DIRECT - PGSCAN_KSWAPD); BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD); +#endif + BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != + PGSCAN_DIRECT - PGSCAN_KSWAPD); BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD); @@ -976,8 +978,10 @@ static unsigned int demote_folio_list(struct list_head *demote_folios, migrate_pages(demote_folios, alloc_demote_folio, NULL, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); - - __count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded); +#ifdef CONFIG_NUMA_BALANCING + mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(), + nr_succeeded); +#endif return nr_succeeded; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 359460deb377..cfd8d8256f8e 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1248,6 +1248,9 @@ const char * const vmstat_text[] = { #ifdef CONFIG_NUMA_BALANCING "pgpromote_success", "pgpromote_candidate", + "pgdemote_kswapd", + "pgdemote_direct", + "pgdemote_khugepaged", #endif /* enum writeback_stat_item counters */ @@ -1279,9 +1282,6 @@ const char * const vmstat_text[] = { "pgsteal_kswapd", "pgsteal_direct", "pgsteal_khugepaged", - "pgdemote_kswapd", - "pgdemote_direct", - "pgdemote_khugepaged", "pgscan_kswapd", "pgscan_direct", "pgscan_khugepaged", @@ -1401,6 +1401,7 @@ const char * const vmstat_text[] = { #ifdef CONFIG_ZSWAP "zswpin", "zswpout", + "zswpwb", #endif #ifdef CONFIG_X86 "direct_map_level2_splits", diff --git a/mm/workingset.c b/mm/workingset.c index 33baad203277..3ea2ccb8e57d 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -615,12 +615,12 @@ void workingset_update_node(struct xa_node *node) if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) { - list_lru_add(&shadow_nodes, &node->private_list); + list_lru_add_obj(&shadow_nodes, &node->private_list); __inc_lruvec_kmem_state(node, WORKINGSET_NODES); } } else { if (!list_empty(&node->private_list)) { - list_lru_del(&shadow_nodes, &node->private_list); + list_lru_del_obj(&shadow_nodes, &node->private_list); __dec_lruvec_kmem_state(node, WORKINGSET_NODES); } } diff --git a/mm/zswap.c b/mm/zswap.c index 74411dfdad92..015425ed9003 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -35,6 +35,7 @@ #include <linux/writeback.h> #include <linux/pagemap.h> #include <linux/workqueue.h> +#include <linux/list_lru.h> #include "swap.h" #include "internal.h" @@ -147,6 +148,11 @@ module_param_named(exclusive_loads, zswap_exclusive_loads_enabled, bool, 0644); /* Number of zpools in zswap_pool (empirically determined for scalability) */ #define ZSWAP_NR_ZPOOLS 32 +/* Enable/disable memory pressure-based shrinker. */ +static bool zswap_shrinker_enabled = IS_ENABLED( + CONFIG_ZSWAP_SHRINKER_DEFAULT_ON); +module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644); + /********************************* * data structures **********************************/ @@ -174,8 +180,10 @@ struct zswap_pool { struct work_struct shrink_work; struct hlist_node node; char tfm_name[CRYPTO_MAX_ALG_NAME]; - struct list_head lru; - spinlock_t lru_lock; + struct list_lru list_lru; + struct mem_cgroup *next_shrink; + struct shrinker *shrinker; + atomic_t nr_stored; }; /* @@ -274,32 +282,72 @@ static bool zswap_can_accept(void) DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE); } +static u64 get_zswap_pool_size(struct zswap_pool *pool) +{ + u64 pool_size = 0; + int i; + + for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) + pool_size += zpool_get_total_size(pool->zpools[i]); + + return pool_size; +} + static void zswap_update_total_size(void) { struct zswap_pool *pool; u64 total = 0; - int i; rcu_read_lock(); list_for_each_entry_rcu(pool, &zswap_pools, list) - for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) - total += zpool_get_total_size(pool->zpools[i]); + total += get_zswap_pool_size(pool); rcu_read_unlock(); zswap_pool_total_size = total; } +/* should be called under RCU */ +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) +{ + return entry->objcg ? obj_cgroup_memcg(entry->objcg) : NULL; +} +#else +static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) +{ + return NULL; +} +#endif + +static inline int entry_to_nid(struct zswap_entry *entry) +{ + return page_to_nid(virt_to_page(entry)); +} + +void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) +{ + struct zswap_pool *pool; + + /* lock out zswap pools list modification */ + spin_lock(&zswap_pools_lock); + list_for_each_entry(pool, &zswap_pools, list) { + if (pool->next_shrink == memcg) + pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL); + } + spin_unlock(&zswap_pools_lock); +} + /********************************* * zswap entry functions **********************************/ static struct kmem_cache *zswap_entry_cache; -static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp) +static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid) { struct zswap_entry *entry; - entry = kmem_cache_alloc(zswap_entry_cache, gfp); + entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid); if (!entry) return NULL; entry->refcount = 1; @@ -313,6 +361,100 @@ static void zswap_entry_cache_free(struct zswap_entry *entry) } /********************************* +* zswap lruvec functions +**********************************/ +void zswap_lruvec_state_init(struct lruvec *lruvec) +{ + atomic_long_set(&lruvec->zswap_lruvec_state.nr_zswap_protected, 0); +} + +void zswap_page_swapin(struct page *page) +{ + struct lruvec *lruvec; + + if (page) { + lruvec = folio_lruvec(page_folio(page)); + atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected); + } +} + +/********************************* +* lru functions +**********************************/ +static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) +{ + atomic_long_t *nr_zswap_protected; + unsigned long lru_size, old, new; + int nid = entry_to_nid(entry); + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + /* + * Note that it is safe to use rcu_read_lock() here, even in the face of + * concurrent memcg offlining. Thanks to the memcg->kmemcg_id indirection + * used in list_lru lookup, only two scenarios are possible: + * + * 1. list_lru_add() is called before memcg->kmemcg_id is updated. The + * new entry will be reparented to memcg's parent's list_lru. + * 2. list_lru_add() is called after memcg->kmemcg_id is updated. The + * new entry will be added directly to memcg's parent's list_lru. + * + * Similar reasoning holds for list_lru_del() and list_lru_putback(). + */ + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + /* will always succeed */ + list_lru_add(list_lru, &entry->lru, nid, memcg); + + /* Update the protection area */ + lru_size = list_lru_count_one(list_lru, nid, memcg); + lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); + nr_zswap_protected = &lruvec->zswap_lruvec_state.nr_zswap_protected; + old = atomic_long_inc_return(nr_zswap_protected); + /* + * Decay to avoid overflow and adapt to changing workloads. + * This is based on LRU reclaim cost decaying heuristics. + */ + do { + new = old > lru_size / 4 ? old / 2 : old; + } while (!atomic_long_try_cmpxchg(nr_zswap_protected, &old, new)); + rcu_read_unlock(); +} + +static void zswap_lru_del(struct list_lru *list_lru, struct zswap_entry *entry) +{ + int nid = entry_to_nid(entry); + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + /* will always succeed */ + list_lru_del(list_lru, &entry->lru, nid, memcg); + rcu_read_unlock(); +} + +static void zswap_lru_putback(struct list_lru *list_lru, + struct zswap_entry *entry) +{ + int nid = entry_to_nid(entry); + spinlock_t *lock = &list_lru->node[nid].lock; + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = mem_cgroup_from_entry(entry); + spin_lock(lock); + /* we cannot use list_lru_add here, because it increments node's lru count */ + list_lru_putback(list_lru, &entry->lru, nid, memcg); + spin_unlock(lock); + + lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(entry_to_nid(entry))); + /* increment the protection area to account for the LRU rotation. */ + atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected); + rcu_read_unlock(); +} + +/********************************* * rbtree functions **********************************/ static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset) @@ -396,10 +538,9 @@ static void zswap_free_entry(struct zswap_entry *entry) if (!entry->length) atomic_dec(&zswap_same_filled_pages); else { - spin_lock(&entry->pool->lru_lock); - list_del(&entry->lru); - spin_unlock(&entry->pool->lru_lock); + zswap_lru_del(&entry->pool->list_lru, entry); zpool_free(zswap_find_zpool(entry), entry->handle); + atomic_dec(&entry->pool->nr_stored); zswap_pool_put(entry->pool); } zswap_entry_cache_free(entry); @@ -442,6 +583,109 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root, } /********************************* +* shrinker functions +**********************************/ +static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, + spinlock_t *lock, void *arg); + +static unsigned long zswap_shrinker_scan(struct shrinker *shrinker, + struct shrink_control *sc) +{ + struct lruvec *lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); + unsigned long shrink_ret, nr_protected, lru_size; + struct zswap_pool *pool = shrinker->private_data; + bool encountered_page_in_swapcache = false; + + if (!zswap_shrinker_enabled) { + sc->nr_scanned = 0; + return SHRINK_STOP; + } + + nr_protected = + atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected); + lru_size = list_lru_shrink_count(&pool->list_lru, sc); + + /* + * Abort if we are shrinking into the protected region. + * + * This short-circuiting is necessary because if we have too many multiple + * concurrent reclaimers getting the freeable zswap object counts at the + * same time (before any of them made reasonable progress), the total + * number of reclaimed objects might be more than the number of unprotected + * objects (i.e the reclaimers will reclaim into the protected area of the + * zswap LRU). + */ + if (nr_protected >= lru_size - sc->nr_to_scan) { + sc->nr_scanned = 0; + return SHRINK_STOP; + } + + shrink_ret = list_lru_shrink_walk(&pool->list_lru, sc, &shrink_memcg_cb, + &encountered_page_in_swapcache); + + if (encountered_page_in_swapcache) + return SHRINK_STOP; + + return shrink_ret ? shrink_ret : SHRINK_STOP; +} + +static unsigned long zswap_shrinker_count(struct shrinker *shrinker, + struct shrink_control *sc) +{ + struct zswap_pool *pool = shrinker->private_data; + struct mem_cgroup *memcg = sc->memcg; + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid)); + unsigned long nr_backing, nr_stored, nr_freeable, nr_protected; + + if (!zswap_shrinker_enabled) + return 0; + +#ifdef CONFIG_MEMCG_KMEM + mem_cgroup_flush_stats(); + nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; + nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); +#else + /* use pool stats instead of memcg stats */ + nr_backing = get_zswap_pool_size(pool) >> PAGE_SHIFT; + nr_stored = atomic_read(&pool->nr_stored); +#endif + + if (!nr_stored) + return 0; + + nr_protected = + atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected); + nr_freeable = list_lru_shrink_count(&pool->list_lru, sc); + /* + * Subtract the lru size by an estimate of the number of pages + * that should be protected. + */ + nr_freeable = nr_freeable > nr_protected ? nr_freeable - nr_protected : 0; + + /* + * Scale the number of freeable pages by the memory saving factor. + * This ensures that the better zswap compresses memory, the fewer + * pages we will evict to swap (as it will otherwise incur IO for + * relatively small memory saving). + */ + return mult_frac(nr_freeable, nr_backing, nr_stored); +} + +static void zswap_alloc_shrinker(struct zswap_pool *pool) +{ + pool->shrinker = + shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-zswap"); + if (!pool->shrinker) + return; + + pool->shrinker->private_data = pool; + pool->shrinker->scan_objects = zswap_shrinker_scan; + pool->shrinker->count_objects = zswap_shrinker_count; + pool->shrinker->batch = 0; + pool->shrinker->seeks = DEFAULT_SEEKS; +} + +/********************************* * per-cpu code **********************************/ static DEFINE_PER_CPU(u8 *, zswap_dstmem); @@ -632,21 +876,16 @@ static void zswap_invalidate_entry(struct zswap_tree *tree, zswap_entry_put(tree, entry); } -static int zswap_reclaim_entry(struct zswap_pool *pool) +static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, + spinlock_t *lock, void *arg) { - struct zswap_entry *entry; + struct zswap_entry *entry = container_of(item, struct zswap_entry, lru); + bool *encountered_page_in_swapcache = (bool *)arg; struct zswap_tree *tree; pgoff_t swpoffset; - int ret; + enum lru_status ret = LRU_REMOVED_RETRY; + int writeback_result; - /* Get an entry off the LRU */ - spin_lock(&pool->lru_lock); - if (list_empty(&pool->lru)) { - spin_unlock(&pool->lru_lock); - return -EINVAL; - } - entry = list_last_entry(&pool->lru, struct zswap_entry, lru); - list_del_init(&entry->lru); /* * Once the lru lock is dropped, the entry might get freed. The * swpoffset is copied to the stack, and entry isn't deref'd again @@ -654,29 +893,48 @@ static int zswap_reclaim_entry(struct zswap_pool *pool) */ swpoffset = swp_offset(entry->swpentry); tree = zswap_trees[swp_type(entry->swpentry)]; - spin_unlock(&pool->lru_lock); + list_lru_isolate(l, item); + /* + * It's safe to drop the lock here because we return either + * LRU_REMOVED_RETRY or LRU_RETRY. + */ + spin_unlock(lock); /* Check for invalidate() race */ spin_lock(&tree->lock); - if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) { - ret = -EAGAIN; + if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) goto unlock; - } + /* Hold a reference to prevent a free during writeback */ zswap_entry_get(entry); spin_unlock(&tree->lock); - ret = zswap_writeback_entry(entry, tree); + writeback_result = zswap_writeback_entry(entry, tree); spin_lock(&tree->lock); - if (ret) { - /* Writeback failed, put entry back on LRU */ - spin_lock(&pool->lru_lock); - list_move(&entry->lru, &pool->lru); - spin_unlock(&pool->lru_lock); + if (writeback_result) { + zswap_reject_reclaim_fail++; + zswap_lru_putback(&entry->pool->list_lru, entry); + ret = LRU_RETRY; + + /* + * Encountering a page already in swap cache is a sign that we are shrinking + * into the warmer region. We should terminate shrinking (if we're in the dynamic + * shrinker context). + */ + if (writeback_result == -EEXIST && encountered_page_in_swapcache) { + ret = LRU_SKIP; + *encountered_page_in_swapcache = true; + } + goto put_unlock; } + zswap_written_back_pages++; + + if (entry->objcg) + count_objcg_event(entry->objcg, ZSWPWB); + count_vm_event(ZSWPWB); /* * Writeback started successfully, the page now belongs to the * swapcache. Drop the entry from zswap - unless invalidate already @@ -689,24 +947,91 @@ put_unlock: zswap_entry_put(tree, entry); unlock: spin_unlock(&tree->lock); - return ret ? -EAGAIN : 0; + spin_lock(lock); + return ret; +} + +static int shrink_memcg(struct mem_cgroup *memcg) +{ + struct zswap_pool *pool; + int nid, shrunk = 0; + + /* + * Skip zombies because their LRUs are reparented and we would be + * reclaiming from the parent instead of the dead memcg. + */ + if (memcg && !mem_cgroup_online(memcg)) + return -ENOENT; + + pool = zswap_pool_current_get(); + if (!pool) + return -EINVAL; + + for_each_node_state(nid, N_NORMAL_MEMORY) { + unsigned long nr_to_walk = 1; + + shrunk += list_lru_walk_one(&pool->list_lru, nid, memcg, + &shrink_memcg_cb, NULL, &nr_to_walk); + } + zswap_pool_put(pool); + return shrunk ? 0 : -EAGAIN; } static void shrink_worker(struct work_struct *w) { struct zswap_pool *pool = container_of(w, typeof(*pool), shrink_work); + struct mem_cgroup *memcg; int ret, failures = 0; + /* global reclaim will select cgroup in a round-robin fashion. */ do { - ret = zswap_reclaim_entry(pool); - if (ret) { - zswap_reject_reclaim_fail++; - if (ret != -EAGAIN) + spin_lock(&zswap_pools_lock); + pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL); + memcg = pool->next_shrink; + + /* + * We need to retry if we have gone through a full round trip, or if we + * got an offline memcg (or else we risk undoing the effect of the + * zswap memcg offlining cleanup callback). This is not catastrophic + * per se, but it will keep the now offlined memcg hostage for a while. + * + * Note that if we got an online memcg, we will keep the extra + * reference in case the original reference obtained by mem_cgroup_iter + * is dropped by the zswap memcg offlining callback, ensuring that the + * memcg is not killed when we are reclaiming. + */ + if (!memcg) { + spin_unlock(&zswap_pools_lock); + if (++failures == MAX_RECLAIM_RETRIES) break; + + goto resched; + } + + if (!mem_cgroup_tryget_online(memcg)) { + /* drop the reference from mem_cgroup_iter() */ + mem_cgroup_iter_break(NULL, memcg); + pool->next_shrink = NULL; + spin_unlock(&zswap_pools_lock); + if (++failures == MAX_RECLAIM_RETRIES) break; + + goto resched; } + spin_unlock(&zswap_pools_lock); + + ret = shrink_memcg(memcg); + /* drop the extra reference */ + mem_cgroup_put(memcg); + + if (ret == -EINVAL) + break; + if (ret && ++failures == MAX_RECLAIM_RETRIES) + break; + +resched: cond_resched(); } while (!zswap_can_accept()); zswap_pool_put(pool); @@ -760,6 +1085,11 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) &pool->node); if (ret) goto error; + + zswap_alloc_shrinker(pool); + if (!pool->shrinker) + goto error; + pr_debug("using %s compressor\n", pool->tfm_name); /* being the current pool takes 1 ref; this func expects the @@ -767,14 +1097,19 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) */ kref_init(&pool->kref); INIT_LIST_HEAD(&pool->list); - INIT_LIST_HEAD(&pool->lru); - spin_lock_init(&pool->lru_lock); + if (list_lru_init_memcg(&pool->list_lru, pool->shrinker)) + goto lru_fail; + shrinker_register(pool->shrinker); INIT_WORK(&pool->shrink_work, shrink_worker); + atomic_set(&pool->nr_stored, 0); zswap_pool_debug("created", pool); return pool; +lru_fail: + list_lru_destroy(&pool->list_lru); + shrinker_free(pool->shrinker); error: if (pool->acomp_ctx) free_percpu(pool->acomp_ctx); @@ -832,8 +1167,16 @@ static void zswap_pool_destroy(struct zswap_pool *pool) zswap_pool_debug("destroying", pool); + shrinker_free(pool->shrinker); cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); free_percpu(pool->acomp_ctx); + list_lru_destroy(&pool->list_lru); + + spin_lock(&zswap_pools_lock); + mem_cgroup_iter_break(NULL, pool->next_shrink); + pool->next_shrink = NULL; + spin_unlock(&zswap_pools_lock); + for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) zpool_destroy_pool(pool->zpools[i]); kfree(pool); @@ -1081,7 +1424,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry, /* try to allocate swap cache page */ mpol = get_task_policy(current); page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol, - NO_INTERLEAVE_INDEX, &page_was_allocated); + NO_INTERLEAVE_INDEX, &page_was_allocated, true); if (!page) { ret = -ENOMEM; goto fail; @@ -1147,7 +1490,6 @@ static int zswap_writeback_entry(struct zswap_entry *entry, /* start writeback */ __swap_writepage(page, &wbc); put_page(page); - zswap_written_back_pages++; return ret; @@ -1204,6 +1546,7 @@ bool zswap_store(struct folio *folio) struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; struct obj_cgroup *objcg = NULL; + struct mem_cgroup *memcg = NULL; struct zswap_pool *pool; struct zpool *zpool; unsigned int dlen = PAGE_SIZE; @@ -1235,15 +1578,15 @@ bool zswap_store(struct folio *folio) zswap_invalidate_entry(tree, dupentry); } spin_unlock(&tree->lock); - - /* - * XXX: zswap reclaim does not work with cgroups yet. Without a - * cgroup-aware entry LRU, we will push out entries system-wide based on - * local cgroup limits. - */ objcg = get_obj_cgroup_from_folio(folio); - if (objcg && !obj_cgroup_may_zswap(objcg)) - goto reject; + if (objcg && !obj_cgroup_may_zswap(objcg)) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (shrink_memcg(memcg)) { + mem_cgroup_put(memcg); + goto reject; + } + mem_cgroup_put(memcg); + } /* reclaim space if needed */ if (zswap_is_full()) { @@ -1260,23 +1603,23 @@ bool zswap_store(struct folio *folio) } /* allocate entry */ - entry = zswap_entry_cache_alloc(GFP_KERNEL); + entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page)); if (!entry) { zswap_reject_kmemcache_fail++; goto reject; } if (zswap_same_filled_pages_enabled) { - src = kmap_atomic(page); + src = kmap_local_page(page); if (zswap_is_page_same_filled(src, &value)) { - kunmap_atomic(src); + kunmap_local(src); entry->swpentry = swp_entry(type, offset); entry->length = 0; entry->value = value; atomic_inc(&zswap_same_filled_pages); goto insert_entry; } - kunmap_atomic(src); + kunmap_local(src); } if (!zswap_non_same_filled_pages_enabled) @@ -1287,6 +1630,15 @@ bool zswap_store(struct folio *folio) if (!entry->pool) goto freepage; + if (objcg) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (memcg_list_lru_alloc(memcg, &entry->pool->list_lru, GFP_KERNEL)) { + mem_cgroup_put(memcg); + goto put_pool; + } + mem_cgroup_put(memcg); + } + /* compress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); @@ -1365,9 +1717,9 @@ insert_entry: zswap_invalidate_entry(tree, dupentry); } if (entry->length) { - spin_lock(&entry->pool->lru_lock); - list_add(&entry->lru, &entry->pool->lru); - spin_unlock(&entry->pool->lru_lock); + INIT_LIST_HEAD(&entry->lru); + zswap_lru_add(&entry->pool->list_lru, entry); + atomic_inc(&entry->pool->nr_stored); } spin_unlock(&tree->lock); @@ -1380,6 +1732,7 @@ insert_entry: put_dstmem: mutex_unlock(acomp_ctx->mutex); +put_pool: zswap_pool_put(entry->pool); freepage: zswap_entry_cache_free(entry); @@ -1422,9 +1775,9 @@ bool zswap_load(struct folio *folio) spin_unlock(&tree->lock); if (!entry->length) { - dst = kmap_atomic(page); + dst = kmap_local_page(page); zswap_fill_page(dst, entry->value); - kunmap_atomic(dst); + kunmap_local(dst); ret = true; goto stats; } @@ -1474,9 +1827,8 @@ freeentry: zswap_invalidate_entry(tree, entry); folio_mark_dirty(folio); } else if (entry->length) { - spin_lock(&entry->pool->lru_lock); - list_move(&entry->lru, &entry->pool->lru); - spin_unlock(&entry->pool->lru_lock); + zswap_lru_del(&entry->pool->list_lru, entry); + zswap_lru_add(&entry->pool->list_lru, entry); } zswap_entry_put(tree, entry); spin_unlock(&tree->lock); diff --git a/samples/Kconfig b/samples/Kconfig index b0ddf5f36738..b288d9991d27 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -285,6 +285,12 @@ config SAMPLE_KMEMLEAK Build a sample program which have explicitly leaks memory to test kmemleak +config SAMPLE_CGROUP + bool "Build cgroup sample code" + depends on CGROUPS && CC_CAN_LINK && HEADERS_INSTALL + help + Build samples that demonstrate the usage of the cgroup API. + source "samples/rust/Kconfig" endif # SAMPLES diff --git a/samples/Makefile b/samples/Makefile index 0a551c2b33f4..b85fa64390c5 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -3,6 +3,7 @@ subdir-$(CONFIG_SAMPLE_AUXDISPLAY) += auxdisplay subdir-$(CONFIG_SAMPLE_ANDROID_BINDERFS) += binderfs +subdir-$(CONFIG_SAMPLE_CGROUP) += cgroup obj-$(CONFIG_SAMPLE_CONFIGFS) += configfs/ obj-$(CONFIG_SAMPLE_CONNECTOR) += connector/ obj-$(CONFIG_SAMPLE_FANOTIFY_ERROR) += fanotify/ diff --git a/samples/cgroup/Makefile b/samples/cgroup/Makefile new file mode 100644 index 000000000000..526c8569707c --- /dev/null +++ b/samples/cgroup/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +userprogs-always-y += cgroup_event_listener memcg_event_listener + +userccflags += -I usr/include diff --git a/tools/cgroup/cgroup_event_listener.c b/samples/cgroup/cgroup_event_listener.c index 3d70dc831a76..3d70dc831a76 100644 --- a/tools/cgroup/cgroup_event_listener.c +++ b/samples/cgroup/cgroup_event_listener.c diff --git a/samples/cgroup/memcg_event_listener.c b/samples/cgroup/memcg_event_listener.c new file mode 100644 index 000000000000..a1667fe2489a --- /dev/null +++ b/samples/cgroup/memcg_event_listener.c @@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * memcg_event_listener.c - Simple listener of memcg memory.events + * + * Copyright (c) 2023, SaluteDevices. All Rights Reserved. + * + * Author: Dmitry Rokosov <ddrokosov@salutedevices.com> + */ + +#include <err.h> +#include <errno.h> +#include <limits.h> +#include <poll.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/inotify.h> +#include <unistd.h> + +#define MEMCG_EVENTS "memory.events" + +/* Size of buffer to use when reading inotify events */ +#define INOTIFY_BUFFER_SIZE 8192 + +#define INOTIFY_EVENT_NEXT(event, length) ({ \ + (length) -= sizeof(*(event)) + (event)->len; \ + (event)++; \ +}) + +#define INOTIFY_EVENT_OK(event, length) ((length) >= (ssize_t)sizeof(*(event))) + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0])) + +struct memcg_counters { + long low; + long high; + long max; + long oom; + long oom_kill; + long oom_group_kill; +}; + +struct memcg_events { + struct memcg_counters counters; + char path[PATH_MAX]; + int inotify_fd; + int inotify_wd; +}; + +static void print_memcg_counters(const struct memcg_counters *counters) +{ + printf("MEMCG events:\n"); + printf("\tlow: %ld\n", counters->low); + printf("\thigh: %ld\n", counters->high); + printf("\tmax: %ld\n", counters->max); + printf("\toom: %ld\n", counters->oom); + printf("\toom_kill: %ld\n", counters->oom_kill); + printf("\toom_group_kill: %ld\n", counters->oom_group_kill); +} + +static int get_memcg_counter(char *line, const char *name, long *counter) +{ + size_t len = strlen(name); + char *endptr; + long tmp; + + if (memcmp(line, name, len)) { + warnx("Counter line %s has wrong name, %s is expected", + line, name); + return -EINVAL; + } + + /* skip the whitespace delimiter */ + len += 1; + + errno = 0; + tmp = strtol(&line[len], &endptr, 10); + if (((tmp == LONG_MAX || tmp == LONG_MIN) && errno == ERANGE) || + (errno && !tmp)) { + warnx("Failed to parse: %s", &line[len]); + return -ERANGE; + } + + if (endptr == &line[len]) { + warnx("Not digits were found in line %s", &line[len]); + return -EINVAL; + } + + if (!(*endptr == '\0' || (*endptr == '\n' && *++endptr == '\0'))) { + warnx("Further characters after number: %s", endptr); + return -EINVAL; + } + + *counter = tmp; + + return 0; +} + +static int read_memcg_events(struct memcg_events *events, bool show_diff) +{ + FILE *fp = fopen(events->path, "re"); + size_t i; + int ret = 0; + bool any_new_events = false; + char *line = NULL; + size_t len = 0; + struct memcg_counters new_counters; + struct memcg_counters *counters = &events->counters; + struct { + const char *name; + long *new; + long *old; + } map[] = { + { + .name = "low", + .new = &new_counters.low, + .old = &counters->low, + }, + { + .name = "high", + .new = &new_counters.high, + .old = &counters->high, + }, + { + .name = "max", + .new = &new_counters.max, + .old = &counters->max, + }, + { + .name = "oom", + .new = &new_counters.oom, + .old = &counters->oom, + }, + { + .name = "oom_kill", + .new = &new_counters.oom_kill, + .old = &counters->oom_kill, + }, + { + .name = "oom_group_kill", + .new = &new_counters.oom_group_kill, + .old = &counters->oom_group_kill, + }, + }; + + if (!fp) { + warn("Failed to open memcg events file %s", events->path); + return -EBADF; + } + + /* Read new values for memcg counters */ + for (i = 0; i < ARRAY_SIZE(map); ++i) { + ssize_t nread; + + errno = 0; + nread = getline(&line, &len, fp); + if (nread == -1) { + if (errno) { + warn("Failed to read line for counter %s", + map[i].name); + ret = -EIO; + goto exit; + } + + break; + } + + ret = get_memcg_counter(line, map[i].name, map[i].new); + if (ret) { + warnx("Failed to get counter value from line %s", line); + goto exit; + } + } + + for (i = 0; i < ARRAY_SIZE(map); ++i) { + long diff; + + if (*map[i].new > *map[i].old) { + diff = *map[i].new - *map[i].old; + + if (show_diff) + printf("*** %ld MEMCG %s event%s, " + "change counter %ld => %ld\n", + diff, map[i].name, + (diff == 1) ? "" : "s", + *map[i].old, *map[i].new); + + *map[i].old += diff; + any_new_events = true; + } + } + + if (show_diff && !any_new_events) + printf("*** No new untracked memcg events available\n"); + +exit: + free(line); + fclose(fp); + + return ret; +} + +static void process_memcg_events(struct memcg_events *events, + struct inotify_event *event) +{ + int ret; + + if (events->inotify_wd != event->wd) { + warnx("Unknown inotify event %d, should be %d", event->wd, + events->inotify_wd); + return; + } + + printf("Received event in %s:\n", events->path); + + if (!(event->mask & IN_MODIFY)) { + warnx("No IN_MODIFY event, skip it"); + return; + } + + ret = read_memcg_events(events, /* show_diff = */true); + if (ret) + warnx("Can't read memcg events"); +} + +static void monitor_events(struct memcg_events *events) +{ + struct pollfd fds[1]; + int ret; + + printf("Started monitoring memory events from '%s'...\n", events->path); + + fds[0].fd = events->inotify_fd; + fds[0].events = POLLIN; + + for (;;) { + ret = poll(fds, ARRAY_SIZE(fds), -1); + if (ret < 0 && errno != EAGAIN) + err(EXIT_FAILURE, "Can't poll memcg events (%d)", ret); + + if (fds[0].revents & POLLERR) + err(EXIT_FAILURE, "Got POLLERR during monitor events"); + + if (fds[0].revents & POLLIN) { + struct inotify_event *event; + char buffer[INOTIFY_BUFFER_SIZE]; + ssize_t length; + + length = read(fds[0].fd, buffer, INOTIFY_BUFFER_SIZE); + if (length <= 0) + continue; + + event = (struct inotify_event *)buffer; + while (INOTIFY_EVENT_OK(event, length)) { + process_memcg_events(events, event); + event = INOTIFY_EVENT_NEXT(event, length); + } + } + } +} + +static int initialize_memcg_events(struct memcg_events *events, + const char *cgroup) +{ + int ret; + + memset(events, 0, sizeof(struct memcg_events)); + + ret = snprintf(events->path, PATH_MAX, + "/sys/fs/cgroup/%s/memory.events", cgroup); + if (ret >= PATH_MAX) { + warnx("Path to cgroup memory.events is too long"); + return -EMSGSIZE; + } else if (ret < 0) { + warn("Can't generate cgroup event full name"); + return ret; + } + + ret = read_memcg_events(events, /* show_diff = */false); + if (ret) { + warnx("Failed to read initial memcg events state (%d)", ret); + return ret; + } + + events->inotify_fd = inotify_init(); + if (events->inotify_fd < 0) { + warn("Failed to setup new inotify device"); + return -EMFILE; + } + + events->inotify_wd = inotify_add_watch(events->inotify_fd, + events->path, IN_MODIFY); + if (events->inotify_wd < 0) { + warn("Couldn't add monitor in dir %s", events->path); + return -EIO; + } + + printf("Initialized MEMCG events with counters:\n"); + print_memcg_counters(&events->counters); + + return 0; +} + +static void cleanup_memcg_events(struct memcg_events *events) +{ + inotify_rm_watch(events->inotify_fd, events->inotify_wd); + close(events->inotify_fd); +} + +int main(int argc, const char **argv) +{ + struct memcg_events events; + ssize_t ret; + + if (argc != 2) + errx(EXIT_FAILURE, "Usage: %s <cgroup>", argv[0]); + + ret = initialize_memcg_events(&events, argv[1]); + if (ret) + errx(EXIT_FAILURE, "Can't initialize memcg events (%zd)", ret); + + monitor_events(&events); + + cleanup_memcg_events(&events); + + printf("Exiting memcg event listener...\n"); + + return EXIT_SUCCESS; +} diff --git a/tools/cgroup/Makefile b/tools/cgroup/Makefile deleted file mode 100644 index ffca068e4a76..000000000000 --- a/tools/cgroup/Makefile +++ /dev/null @@ -1,11 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Makefile for cgroup tools - -CFLAGS = -Wall -Wextra - -all: cgroup_event_listener -%: %.c - $(CC) $(CFLAGS) -o $@ $^ - -clean: - $(RM) cgroup_event_listener diff --git a/tools/include/linux/rwsem.h b/tools/include/linux/rwsem.h index 83971b3cbfce..f8bffd4a987c 100644 --- a/tools/include/linux/rwsem.h +++ b/tools/include/linux/rwsem.h @@ -37,4 +37,8 @@ static inline int up_write(struct rw_semaphore *sem) { return pthread_rwlock_unlock(&sem->lock); } + +#define down_read_nested(sem, subclass) down_read(sem) +#define down_write_nested(sem, subclass) down_write(sem) + #endif /* _TOOLS_RWSEM_H */ diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index 622266b197d0..a6cdf25b6b9d 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -11,6 +11,7 @@ #define spin_lock_init(x) pthread_mutex_init(x, NULL) #define spin_lock(x) pthread_mutex_lock(x) +#define spin_lock_nested(x, subclass) pthread_mutex_lock(x) #define spin_unlock(x) pthread_mutex_unlock(x) #define spin_lock_bh(x) pthread_mutex_lock(x) #define spin_unlock_bh(x) pthread_mutex_unlock(x) diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index da43810b7485..48ad69f7722e 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -316,6 +316,7 @@ typedef int __bitwise __kernel_rwf_t; #define PAGE_IS_SWAPPED (1 << 4) #define PAGE_IS_PFNZERO (1 << 5) #define PAGE_IS_HUGE (1 << 6) +#define PAGE_IS_SOFT_DIRTY (1 << 7) /* * struct page_region - Page region with flags diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 61fe2601cb3a..4eb442206d01 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -93,13 +93,9 @@ void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru, return p; } -void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp) +void __kmem_cache_free_locked(struct kmem_cache *cachep, void *objp) { assert(objp); - uatomic_dec(&nr_allocated); - uatomic_dec(&cachep->nr_allocated); - if (kmalloc_verbose) - printf("Freeing %p to slab\n", objp); if (cachep->nr_objs > 10 || cachep->align) { memset(objp, POISON_FREE, cachep->size); free(objp); @@ -111,6 +107,15 @@ void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp) } } +void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp) +{ + uatomic_dec(&nr_allocated); + uatomic_dec(&cachep->nr_allocated); + if (kmalloc_verbose) + printf("Freeing %p to slab\n", objp); + __kmem_cache_free_locked(cachep, objp); +} + void kmem_cache_free(struct kmem_cache *cachep, void *objp) { pthread_mutex_lock(&cachep->lock); @@ -141,18 +146,17 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size, if (kmalloc_verbose) pr_debug("Bulk alloc %lu\n", size); - if (!(gfp & __GFP_DIRECT_RECLAIM)) { - if (cachep->non_kernel < size) - return 0; - - cachep->non_kernel -= size; - } - pthread_mutex_lock(&cachep->lock); if (cachep->nr_objs >= size) { struct radix_tree_node *node; for (i = 0; i < size; i++) { + if (!(gfp & __GFP_DIRECT_RECLAIM)) { + if (!cachep->non_kernel) + break; + cachep->non_kernel--; + } + node = cachep->objs; cachep->nr_objs--; cachep->objs = node->parent; @@ -163,11 +167,19 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size, } else { pthread_mutex_unlock(&cachep->lock); for (i = 0; i < size; i++) { + if (!(gfp & __GFP_DIRECT_RECLAIM)) { + if (!cachep->non_kernel) + break; + cachep->non_kernel--; + } + if (cachep->align) { posix_memalign(&p[i], cachep->align, cachep->size); } else { p[i] = malloc(cachep->size); + if (!p[i]) + break; } if (cachep->ctor) cachep->ctor(p[i]); @@ -176,6 +188,15 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size, } } + if (i < size) { + size = i; + pthread_mutex_lock(&cachep->lock); + for (i = 0; i < size; i++) + __kmem_cache_free_locked(cachep, p[i]); + pthread_mutex_unlock(&cachep->lock); + return 0; + } + for (i = 0; i < size; i++) { uatomic_inc(&nr_allocated); uatomic_inc(&cachep->nr_allocated); diff --git a/tools/testing/radix-tree/linux/maple_tree.h b/tools/testing/radix-tree/linux/maple_tree.h index 7d8d1f445b89..06c89bdcc515 100644 --- a/tools/testing/radix-tree/linux/maple_tree.h +++ b/tools/testing/radix-tree/linux/maple_tree.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0+ */ #define atomic_t int32_t -#include "../../../../include/linux/maple_tree.h" #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) #define atomic_set(x, y) do {} while (0) #define U8_MAX UCHAR_MAX +#include "../../../../include/linux/maple_tree.h" diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 76a8990bb14e..35cc8c2a10f4 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -118,6 +118,7 @@ static noinline void __init check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas.alloc == NULL); MT_BUG_ON(mt, mas.alloc->slot[0] == NULL); mas_push_node(&mas, mn); + mas_reset(&mas); mas_nomem(&mas, GFP_KERNEL); /* free */ mtree_unlock(mt); @@ -141,7 +142,7 @@ static noinline void __init check_new_node(struct maple_tree *mt) mn->parent = ma_parent_ptr(mn); ma_free_rcu(mn); - mas.node = MAS_START; + mas.status = ma_start; mas_nomem(&mas, GFP_KERNEL); /* Allocate 3 nodes, will fail. */ mas_node_count(&mas, 3); @@ -158,6 +159,7 @@ static noinline void __init check_new_node(struct maple_tree *mt) /* Ensure we counted 3. */ MT_BUG_ON(mt, mas_allocated(&mas) != 3); /* Free. */ + mas_reset(&mas); mas_nomem(&mas, GFP_KERNEL); /* Set allocation request to 1. */ @@ -272,6 +274,7 @@ static noinline void __init check_new_node(struct maple_tree *mt) ma_free_rcu(mn); MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1); } + mas_reset(&mas); MT_BUG_ON(mt, mas_nomem(&mas, GFP_KERNEL)); } @@ -294,6 +297,7 @@ static noinline void __init check_new_node(struct maple_tree *mt) smn = smn->slot[0]; /* next. */ } MT_BUG_ON(mt, mas_allocated(&mas) != total); + mas_reset(&mas); mas_nomem(&mas, GFP_KERNEL); /* Free. */ MT_BUG_ON(mt, mas_allocated(&mas) != 0); @@ -441,7 +445,7 @@ static noinline void __init check_new_node(struct maple_tree *mt) mas.node = MA_ERROR(-ENOMEM); mas_node_count(&mas, 10); /* Request */ mas_nomem(&mas, GFP_KERNEL); /* Fill request */ - mas.node = MAS_START; + mas.status = ma_start; MT_BUG_ON(mt, mas_allocated(&mas) != 10); mas_destroy(&mas); @@ -452,7 +456,7 @@ static noinline void __init check_new_node(struct maple_tree *mt) mas.node = MA_ERROR(-ENOMEM); mas_node_count(&mas, 10 + MAPLE_ALLOC_SLOTS - 1); /* Request */ mas_nomem(&mas, GFP_KERNEL); /* Fill request */ - mas.node = MAS_START; + mas.status = ma_start; MT_BUG_ON(mt, mas_allocated(&mas) != 10 + MAPLE_ALLOC_SLOTS - 1); mas_destroy(&mas); @@ -941,10 +945,11 @@ retry: ret = mas_descend_walk(mas, range_min, range_max); if (unlikely(mte_dead_node(mas->node))) { - mas->node = MAS_START; + mas->status = ma_start; goto retry; } + mas->end = mas_data_end(mas); return ret; not_found: @@ -960,17 +965,19 @@ static inline void *mas_range_load(struct ma_state *mas, unsigned long index = mas->index; if (mas_is_none(mas) || mas_is_paused(mas)) - mas->node = MAS_START; + mas->status = ma_start; retry: if (mas_tree_walk(mas, range_min, range_max)) - if (unlikely(mas->node == MAS_ROOT)) + if (unlikely(mas->status == ma_root)) return mas_root(mas); if (likely(mas->offset != MAPLE_NODE_SLOTS)) entry = mas_get_slot(mas, mas->offset); - if (mas_dead_node(mas, index)) + if (mas_is_active(mas) && mte_dead_node(mas->node)) { + mas_set(mas, index); goto retry; + } return entry; } @@ -35336,7 +35343,7 @@ static void mas_dfs_preorder(struct ma_state *mas) unsigned char end, slot = 0; unsigned long *pivots; - if (mas->node == MAS_START) { + if (mas->status == ma_start) { mas_start(mas); return; } @@ -35373,7 +35380,7 @@ walk_up: return; done: - mas->node = MAS_NONE; + mas->status = ma_none; } @@ -35832,7 +35839,7 @@ static noinline void __init check_nomem(struct maple_tree *mt) mas_store(&ms, &ms); /* insert 1 -> &ms, fails. */ MT_BUG_ON(mt, ms.node != MA_ERROR(-ENOMEM)); mas_nomem(&ms, GFP_KERNEL); /* Node allocated in here. */ - MT_BUG_ON(mt, ms.node != MAS_START); + MT_BUG_ON(mt, ms.status != ma_start); mtree_unlock(mt); MT_BUG_ON(mt, mtree_insert(mt, 2, mt, GFP_KERNEL) != 0); mtree_lock(mt); @@ -35857,6 +35864,363 @@ static noinline void __init check_locky(struct maple_tree *mt) mt_clear_in_rcu(mt); } +/* + * Compares two nodes except for the addresses stored in the nodes. + * Returns zero if they are the same, otherwise returns non-zero. + */ +static int __init compare_node(struct maple_enode *enode_a, + struct maple_enode *enode_b) +{ + struct maple_node *node_a, *node_b; + struct maple_node a, b; + void **slots_a, **slots_b; /* Do not use the rcu tag. */ + enum maple_type type; + int i; + + if (((unsigned long)enode_a & MAPLE_NODE_MASK) != + ((unsigned long)enode_b & MAPLE_NODE_MASK)) { + pr_err("The lower 8 bits of enode are different.\n"); + return -1; + } + + type = mte_node_type(enode_a); + node_a = mte_to_node(enode_a); + node_b = mte_to_node(enode_b); + a = *node_a; + b = *node_b; + + /* Do not compare addresses. */ + if (ma_is_root(node_a) || ma_is_root(node_b)) { + a.parent = (struct maple_pnode *)((unsigned long)a.parent & + MA_ROOT_PARENT); + b.parent = (struct maple_pnode *)((unsigned long)b.parent & + MA_ROOT_PARENT); + } else { + a.parent = (struct maple_pnode *)((unsigned long)a.parent & + MAPLE_NODE_MASK); + b.parent = (struct maple_pnode *)((unsigned long)b.parent & + MAPLE_NODE_MASK); + } + + if (a.parent != b.parent) { + pr_err("The lower 8 bits of parents are different. %p %p\n", + a.parent, b.parent); + return -1; + } + + /* + * If it is a leaf node, the slots do not contain the node address, and + * no special processing of slots is required. + */ + if (ma_is_leaf(type)) + goto cmp; + + slots_a = ma_slots(&a, type); + slots_b = ma_slots(&b, type); + + for (i = 0; i < mt_slots[type]; i++) { + if (!slots_a[i] && !slots_b[i]) + break; + + if (!slots_a[i] || !slots_b[i]) { + pr_err("The number of slots is different.\n"); + return -1; + } + + /* Do not compare addresses in slots. */ + ((unsigned long *)slots_a)[i] &= MAPLE_NODE_MASK; + ((unsigned long *)slots_b)[i] &= MAPLE_NODE_MASK; + } + +cmp: + /* + * Compare all contents of two nodes, including parent (except address), + * slots (except address), pivots, gaps and metadata. + */ + return memcmp(&a, &b, sizeof(struct maple_node)); +} + +/* + * Compare two trees and return 0 if they are the same, non-zero otherwise. + */ +static int __init compare_tree(struct maple_tree *mt_a, struct maple_tree *mt_b) +{ + MA_STATE(mas_a, mt_a, 0, 0); + MA_STATE(mas_b, mt_b, 0, 0); + + if (mt_a->ma_flags != mt_b->ma_flags) { + pr_err("The flags of the two trees are different.\n"); + return -1; + } + + mas_dfs_preorder(&mas_a); + mas_dfs_preorder(&mas_b); + + if (mas_is_ptr(&mas_a) || mas_is_ptr(&mas_b)) { + if (!(mas_is_ptr(&mas_a) && mas_is_ptr(&mas_b))) { + pr_err("One is ma_root and the other is not.\n"); + return -1; + } + return 0; + } + + while (!mas_is_none(&mas_a) || !mas_is_none(&mas_b)) { + + if (mas_is_none(&mas_a) || mas_is_none(&mas_b)) { + pr_err("One is ma_none and the other is not.\n"); + return -1; + } + + if (mas_a.min != mas_b.min || + mas_a.max != mas_b.max) { + pr_err("mas->min, mas->max do not match.\n"); + return -1; + } + + if (compare_node(mas_a.node, mas_b.node)) { + pr_err("The contents of nodes %p and %p are different.\n", + mas_a.node, mas_b.node); + mt_dump(mt_a, mt_dump_dec); + mt_dump(mt_b, mt_dump_dec); + return -1; + } + + mas_dfs_preorder(&mas_a); + mas_dfs_preorder(&mas_b); + } + + return 0; +} + +static __init void mas_subtree_max_range(struct ma_state *mas) +{ + unsigned long limit = mas->max; + MA_STATE(newmas, mas->tree, 0, 0); + void *entry; + + mas_for_each(mas, entry, limit) { + if (mas->last - mas->index >= + newmas.last - newmas.index) { + newmas = *mas; + } + } + + *mas = newmas; +} + +/* + * build_full_tree() - Build a full tree. + * @mt: The tree to build. + * @flags: Use @flags to build the tree. + * @height: The height of the tree to build. + * + * Build a tree with full leaf nodes and internal nodes. Note that the height + * should not exceed 3, otherwise it will take a long time to build. + * Return: zero if the build is successful, non-zero if it fails. + */ +static __init int build_full_tree(struct maple_tree *mt, unsigned int flags, + int height) +{ + MA_STATE(mas, mt, 0, 0); + unsigned long step; + int ret = 0, cnt = 1; + enum maple_type type; + + mt_init_flags(mt, flags); + mtree_insert_range(mt, 0, ULONG_MAX, xa_mk_value(5), GFP_KERNEL); + + mtree_lock(mt); + + while (1) { + mas_set(&mas, 0); + if (mt_height(mt) < height) { + mas.max = ULONG_MAX; + goto store; + } + + while (1) { + mas_dfs_preorder(&mas); + if (mas_is_none(&mas)) + goto unlock; + + type = mte_node_type(mas.node); + if (mas_data_end(&mas) + 1 < mt_slots[type]) { + mas_set(&mas, mas.min); + goto store; + } + } +store: + mas_subtree_max_range(&mas); + step = mas.last - mas.index; + if (step < 1) { + ret = -1; + goto unlock; + } + + step /= 2; + mas.last = mas.index + step; + mas_store_gfp(&mas, xa_mk_value(5), + GFP_KERNEL); + ++cnt; + } +unlock: + mtree_unlock(mt); + + MT_BUG_ON(mt, mt_height(mt) != height); + /* pr_info("height:%u number of elements:%d\n", mt_height(mt), cnt); */ + return ret; +} + +static noinline void __init check_mtree_dup(struct maple_tree *mt) +{ + DEFINE_MTREE(new); + int i, j, ret, count = 0; + unsigned int rand_seed = 17, rand; + + /* store a value at [0, 0] */ + mt_init_flags(mt, 0); + mtree_store_range(mt, 0, 0, xa_mk_value(0), GFP_KERNEL); + ret = mtree_dup(mt, &new, GFP_KERNEL); + MT_BUG_ON(&new, ret); + mt_validate(&new); + if (compare_tree(mt, &new)) + MT_BUG_ON(&new, 1); + + mtree_destroy(mt); + mtree_destroy(&new); + + /* The two trees have different attributes. */ + mt_init_flags(mt, 0); + mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE); + ret = mtree_dup(mt, &new, GFP_KERNEL); + MT_BUG_ON(&new, ret != -EINVAL); + mtree_destroy(mt); + mtree_destroy(&new); + + /* The new tree is not empty */ + mt_init_flags(mt, 0); + mt_init_flags(&new, 0); + mtree_store(&new, 5, xa_mk_value(5), GFP_KERNEL); + ret = mtree_dup(mt, &new, GFP_KERNEL); + MT_BUG_ON(&new, ret != -EINVAL); + mtree_destroy(mt); + mtree_destroy(&new); + + /* Test for duplicating full trees. */ + for (i = 1; i <= 3; i++) { + ret = build_full_tree(mt, 0, i); + MT_BUG_ON(mt, ret); + mt_init_flags(&new, 0); + + ret = mtree_dup(mt, &new, GFP_KERNEL); + MT_BUG_ON(&new, ret); + mt_validate(&new); + if (compare_tree(mt, &new)) + MT_BUG_ON(&new, 1); + + mtree_destroy(mt); + mtree_destroy(&new); + } + + for (i = 1; i <= 3; i++) { + ret = build_full_tree(mt, MT_FLAGS_ALLOC_RANGE, i); + MT_BUG_ON(mt, ret); + mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE); + + ret = mtree_dup(mt, &new, GFP_KERNEL); + MT_BUG_ON(&new, ret); + mt_validate(&new); + if (compare_tree(mt, &new)) + MT_BUG_ON(&new, 1); + + mtree_destroy(mt); + mtree_destroy(&new); + } + + /* Test for normal duplicating. */ + for (i = 0; i < 1000; i += 3) { + if (i & 1) { + mt_init_flags(mt, 0); + mt_init_flags(&new, 0); + } else { + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE); + } + + for (j = 0; j < i; j++) { + mtree_store_range(mt, j * 10, j * 10 + 5, + xa_mk_value(j), GFP_KERNEL); + } + + ret = mtree_dup(mt, &new, GFP_KERNEL); + MT_BUG_ON(&new, ret); + mt_validate(&new); + if (compare_tree(mt, &new)) + MT_BUG_ON(&new, 1); + + mtree_destroy(mt); + mtree_destroy(&new); + } + + /* Test memory allocation failed. */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + for (i = 0; i < 30; i += 3) { + mtree_store_range(mt, j * 10, j * 10 + 5, + xa_mk_value(j), GFP_KERNEL); + } + + /* Failed at the first node. */ + mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE); + mt_set_non_kernel(0); + ret = mtree_dup(mt, &new, GFP_NOWAIT); + mt_set_non_kernel(0); + MT_BUG_ON(&new, ret != -ENOMEM); + mtree_destroy(mt); + mtree_destroy(&new); + + /* Random maple tree fails at a random node. */ + for (i = 0; i < 1000; i += 3) { + if (i & 1) { + mt_init_flags(mt, 0); + mt_init_flags(&new, 0); + } else { + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mt_init_flags(&new, MT_FLAGS_ALLOC_RANGE); + } + + for (j = 0; j < i; j++) { + mtree_store_range(mt, j * 10, j * 10 + 5, + xa_mk_value(j), GFP_KERNEL); + } + /* + * The rand() library function is not used, so we can generate + * the same random numbers on any platform. + */ + rand_seed = rand_seed * 1103515245 + 12345; + rand = rand_seed / 65536 % 128; + mt_set_non_kernel(rand); + + ret = mtree_dup(mt, &new, GFP_NOWAIT); + mt_set_non_kernel(0); + if (ret != 0) { + MT_BUG_ON(&new, ret != -ENOMEM); + count++; + mtree_destroy(mt); + continue; + } + + mt_validate(&new); + if (compare_tree(mt, &new)) + MT_BUG_ON(&new, 1); + + mtree_destroy(mt); + mtree_destroy(&new); + } + + /* pr_info("mtree_dup() fail %d times\n", count); */ + BUG_ON(!count); +} + extern void test_kmem_cache_bulk(void); void farmer_tests(void) @@ -35904,6 +36268,10 @@ void farmer_tests(void) check_null_expand(&tree); mtree_destroy(&tree); + mt_init_flags(&tree, 0); + check_mtree_dup(&tree); + mtree_destroy(&tree); + /* RCU testing */ mt_init_flags(&tree, 0); check_erase_testset(&tree); @@ -35938,7 +36306,9 @@ void farmer_tests(void) void maple_tree_tests(void) { +#if !defined(BENCH) farmer_tests(); +#endif maple_tree_seed(); maple_tree_harvest(); } diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index c99d2adaca3f..47fdaa146443 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -50,9 +50,9 @@ static int get_zswap_stored_pages(size_t *value) return read_int("/sys/kernel/debug/zswap/stored_pages", value); } -static int get_zswap_written_back_pages(size_t *value) +static int get_cg_wb_count(const char *cg) { - return read_int("/sys/kernel/debug/zswap/written_back_pages", value); + return cg_read_key_long(cg, "memory.stat", "zswp_wb"); } static long get_zswpout(const char *cgroup) @@ -73,6 +73,24 @@ static int allocate_bytes(const char *cgroup, void *arg) return 0; } +static char *setup_test_group_1M(const char *root, const char *name) +{ + char *group_name = cg_name(root, name); + + if (!group_name) + return NULL; + if (cg_create(group_name)) + goto fail; + if (cg_write(group_name, "memory.max", "1M")) { + cg_destroy(group_name); + goto fail; + } + return group_name; +fail: + free(group_name); + return NULL; +} + /* * Sanity test to check that pages are written into zswap. */ @@ -117,43 +135,51 @@ out: /* * When trying to store a memcg page in zswap, if the memcg hits its memory - * limit in zswap, writeback should not be triggered. - * - * This was fixed with commit 0bdf0efa180a("zswap: do not shrink if cgroup may - * not zswap"). Needs to be revised when a per memcg writeback mechanism is - * implemented. + * limit in zswap, writeback should affect only the zswapped pages of that + * memcg. */ static int test_no_invasive_cgroup_shrink(const char *root) { - size_t written_back_before, written_back_after; int ret = KSFT_FAIL; - char *test_group; + size_t control_allocation_size = MB(10); + char *control_allocation, *wb_group = NULL, *control_group = NULL; /* Set up */ - test_group = cg_name(root, "no_shrink_test"); - if (!test_group) - goto out; - if (cg_create(test_group)) + wb_group = setup_test_group_1M(root, "per_memcg_wb_test1"); + if (!wb_group) + return KSFT_FAIL; + if (cg_write(wb_group, "memory.zswap.max", "10K")) goto out; - if (cg_write(test_group, "memory.max", "1M")) + control_group = setup_test_group_1M(root, "per_memcg_wb_test2"); + if (!control_group) goto out; - if (cg_write(test_group, "memory.zswap.max", "10K")) + + /* Push some test_group2 memory into zswap */ + if (cg_enter_current(control_group)) goto out; - if (get_zswap_written_back_pages(&written_back_before)) + control_allocation = malloc(control_allocation_size); + for (int i = 0; i < control_allocation_size; i += 4095) + control_allocation[i] = 'a'; + if (cg_read_key_long(control_group, "memory.stat", "zswapped") < 1) goto out; - /* Allocate 10x memory.max to push memory into zswap */ - if (cg_run(test_group, allocate_bytes, (void *)MB(10))) + /* Allocate 10x memory.max to push wb_group memory into zswap and trigger wb */ + if (cg_run(wb_group, allocate_bytes, (void *)MB(10))) goto out; - /* Verify that no writeback happened because of the memcg allocation */ - if (get_zswap_written_back_pages(&written_back_after)) - goto out; - if (written_back_after == written_back_before) + /* Verify that only zswapped memory from gwb_group has been written back */ + if (get_cg_wb_count(wb_group) > 0 && get_cg_wb_count(control_group) == 0) ret = KSFT_PASS; out: - cg_destroy(test_group); - free(test_group); + cg_enter_current(root); + if (control_group) { + cg_destroy(control_group); + free(control_group); + } + cg_destroy(wb_group); + free(wb_group); + if (control_allocation) + free(control_allocation); return ret; } diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh index 56f0230a8b92..e9a976d296e2 100755 --- a/tools/testing/selftests/damon/sysfs.sh +++ b/tools/testing/selftests/damon/sysfs.sh @@ -150,6 +150,32 @@ test_weights() ensure_file "$weights_dir/age_permil" "exist" "600" } +test_goal() +{ + goal_dir=$1 + ensure_dir "$goal_dir" "exist" + ensure_file "$goal_dir/target_value" "exist" "600" + ensure_file "$goal_dir/current_value" "exist" "600" +} + +test_goals() +{ + goals_dir=$1 + ensure_dir "$goals_dir" "exist" + ensure_file "$goals_dir/nr_goals" "exist" "600" + + ensure_write_succ "$goals_dir/nr_goals" "1" "valid input" + test_goal "$goals_dir/0" + + ensure_write_succ "$goals_dir/nr_goals" "2" "valid input" + test_goal "$goals_dir/0" + test_goal "$goals_dir/1" + + ensure_write_succ "$goals_dir/nr_goals" "0" "valid input" + ensure_dir "$goals_dir/0" "not_exist" + ensure_dir "$goals_dir/1" "not_exist" +} + test_quotas() { quotas_dir=$1 @@ -158,6 +184,7 @@ test_quotas() ensure_file "$quotas_dir/bytes" "exist" 600 ensure_file "$quotas_dir/reset_interval_ms" "exist" 600 test_weights "$quotas_dir/weights" + test_goals "$quotas_dir/goals" } test_access_pattern() diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 00757445278e..c0212258b852 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -334,8 +334,6 @@ CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 0 CATEGORY="ksm" run_test ./ksm_functional_tests -run_test ./ksm_functional_tests - # protection_keys tests if [ -x ./protection_keys_32 ] then diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 3082b40492dd..05736c615734 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -4,6 +4,7 @@ #include <dirent.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h> +#include <linux/fs.h> #include <sys/syscall.h> #include <unistd.h> #include "../kselftest.h" @@ -28,19 +29,92 @@ uint64_t pagemap_get_entry(int fd, char *start) return entry; } +static uint64_t __pagemap_scan_get_categories(int fd, char *start, struct page_region *r) +{ + struct pm_scan_arg arg; + + arg.start = (uintptr_t)start; + arg.end = (uintptr_t)(start + psize()); + arg.vec = (uintptr_t)r; + arg.vec_len = 1; + arg.flags = 0; + arg.size = sizeof(struct pm_scan_arg); + arg.max_pages = 0; + arg.category_inverted = 0; + arg.category_mask = 0; + arg.category_anyof_mask = PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | PAGE_IS_FILE | + PAGE_IS_PRESENT | PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | + PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY; + arg.return_mask = arg.category_anyof_mask; + + return ioctl(fd, PAGEMAP_SCAN, &arg); +} + +static uint64_t pagemap_scan_get_categories(int fd, char *start) +{ + struct page_region r; + long ret; + + ret = __pagemap_scan_get_categories(fd, start, &r); + if (ret < 0) + ksft_exit_fail_msg("PAGEMAP_SCAN failed: %s\n", strerror(errno)); + if (ret == 0) + return 0; + return r.categories; +} + +/* `start` is any valid address. */ +static bool pagemap_scan_supported(int fd, char *start) +{ + static int supported = -1; + int ret; + + if (supported != -1) + return supported; + + /* Provide an invalid address in order to trigger EFAULT. */ + ret = __pagemap_scan_get_categories(fd, start, (struct page_region *) ~0UL); + if (ret == 0) + ksft_exit_fail_msg("PAGEMAP_SCAN succeeded unexpectedly\n"); + + supported = errno == EFAULT; + + return supported; +} + +static bool page_entry_is(int fd, char *start, char *desc, + uint64_t pagemap_flags, uint64_t pagescan_flags) +{ + bool m = pagemap_get_entry(fd, start) & pagemap_flags; + + if (pagemap_scan_supported(fd, start)) { + bool s = pagemap_scan_get_categories(fd, start) & pagescan_flags; + + if (m == s) + return m; + + ksft_exit_fail_msg( + "read and ioctl return unmatched results for %s: %d %d", desc, m, s); + } + return m; +} + bool pagemap_is_softdirty(int fd, char *start) { - return pagemap_get_entry(fd, start) & PM_SOFT_DIRTY; + return page_entry_is(fd, start, "soft-dirty", + PM_SOFT_DIRTY, PAGE_IS_SOFT_DIRTY); } bool pagemap_is_swapped(int fd, char *start) { - return pagemap_get_entry(fd, start) & PM_SWAP; + return page_entry_is(fd, start, "swap", PM_SWAP, PAGE_IS_SWAPPED); } bool pagemap_is_populated(int fd, char *start) { - return pagemap_get_entry(fd, start) & (PM_PRESENT | PM_SWAP); + return page_entry_is(fd, start, "populated", + PM_PRESENT | PM_SWAP, + PAGE_IS_PRESENT | PAGE_IS_SWAPPED); } unsigned long pagemap_get_pfn(int fd, char *start) |