- Linux-stable-mirror - lists.linaro.org

[patch 10/14] gcov: fix clang-11+ support

by Andrew Morton

From: Nick Desaulniers <ndesaulniers(a)google.com> Subject: gcov: fix clang-11+ support LLVM changed the expected function signatures for llvm_gcda_start_file() and llvm_gcda_emit_function() in the clang-11 release. Users of clang-11 or newer may have noticed their kernels failing to boot due to a panic when enabling CONFIG_GCOV_KERNEL=y +CONFIG_GCOV_PROFILE_ALL=y. Fix up the function signatures so calling these functions doesn't panic the kernel. Link: https://reviews.llvm.org/rGcdd683b516d147925212724b09ec6fb792a40041 Link: https://reviews.llvm.org/rG13a633b438b6500ecad9e4f936ebadf3411d0f44 Link: https://lkml.kernel.org/r/20210312224132.3413602-2-ndesaulniers@google.com Signed-off-by: Nick Desaulniers <ndesaulniers(a)google.com> Reported-by: Prasad Sodagudi <psodagud(a)quicinc.com> Suggested-by: Nathan Chancellor <nathan(a)kernel.org> Reviewed-by: Fangrui Song <maskray(a)google.com> Tested-by: Nathan Chancellor <nathan(a)kernel.org> Acked-by: Peter Oberparleiter <oberpar(a)linux.ibm.com> Reviewed-by: Nathan Chancellor <nathan(a)kernel.org> Cc: <stable(a)vger.kernel.org> [5.4+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- kernel/gcov/clang.c | 69 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) --- a/kernel/gcov/clang.c~gcov-fix-clang-11-support +++ a/kernel/gcov/clang.c @@ -75,7 +75,9 @@ struct gcov_fn_info { u32 num_counters; u64 *counters; +#if CONFIG_CLANG_VERSION < 110000 const char *function_name; +#endif }; static struct gcov_info *current_info; @@ -105,6 +107,7 @@ void llvm_gcov_init(llvm_gcov_callback w } EXPORT_SYMBOL(llvm_gcov_init); +#if CONFIG_CLANG_VERSION < 110000 void llvm_gcda_start_file(const char *orig_filename, const char version[4], u32 checksum) { @@ -113,7 +116,17 @@ void llvm_gcda_start_file(const char *or current_info->checksum = checksum; } EXPORT_SYMBOL(llvm_gcda_start_file); +#else +void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum) +{ + current_info->filename = orig_filename; + current_info->version = version; + current_info->checksum = checksum; +} +EXPORT_SYMBOL(llvm_gcda_start_file); +#endif +#if CONFIG_CLANG_VERSION < 110000 void llvm_gcda_emit_function(u32 ident, const char *function_name, u32 func_checksum, u8 use_extra_checksum, u32 cfg_checksum) { @@ -133,6 +146,24 @@ void llvm_gcda_emit_function(u32 ident, list_add_tail(&info->head, &current_info->functions); } EXPORT_SYMBOL(llvm_gcda_emit_function); +#else +void llvm_gcda_emit_function(u32 ident, u32 func_checksum, + u8 use_extra_checksum, u32 cfg_checksum) +{ + struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL); + + if (!info) + return; + + INIT_LIST_HEAD(&info->head); + info->ident = ident; + info->checksum = func_checksum; + info->use_extra_checksum = use_extra_checksum; + info->cfg_checksum = cfg_checksum; + list_add_tail(&info->head, &current_info->functions); +} +EXPORT_SYMBOL(llvm_gcda_emit_function); +#endif void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters) { @@ -295,6 +326,7 @@ void gcov_info_add(struct gcov_info *dst } } +#if CONFIG_CLANG_VERSION < 110000 static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) { size_t cv_size; /* counter values size */ @@ -322,6 +354,28 @@ err_name: kfree(fn_dup); return NULL; } +#else +static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) +{ + size_t cv_size; /* counter values size */ + struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn), + GFP_KERNEL); + if (!fn_dup) + return NULL; + INIT_LIST_HEAD(&fn_dup->head); + + cv_size = fn->num_counters * sizeof(fn->counters[0]); + fn_dup->counters = vmalloc(cv_size); + if (!fn_dup->counters) { + kfree(fn_dup); + return NULL; + } + + memcpy(fn_dup->counters, fn->counters, cv_size); + + return fn_dup; +} +#endif /** * gcov_info_dup - duplicate profiling data set @@ -362,6 +416,7 @@ err: * gcov_info_free - release memory for profiling data set duplicate * @info: profiling data set duplicate to free */ +#if CONFIG_CLANG_VERSION < 110000 void gcov_info_free(struct gcov_info *info) { struct gcov_fn_info *fn, *tmp; @@ -375,6 +430,20 @@ void gcov_info_free(struct gcov_info *in kfree(info->filename); kfree(info); } +#else +void gcov_info_free(struct gcov_info *info) +{ + struct gcov_fn_info *fn, *tmp; + + list_for_each_entry_safe(fn, tmp, &info->functions, head) { + vfree(fn->counters); + list_del(&fn->head); + kfree(fn); + } + kfree(info->filename); + kfree(info); +} +#endif #define ITER_STRIDE PAGE_SIZE _

4 years, 7 months

1
0
0 0

[patch 07/14] squashfs: fix xattr id and id lookup sanity checks

by Andrew Morton

From: Phillip Lougher <phillip(a)squashfs.org.uk> Subject: squashfs: fix xattr id and id lookup sanity checks The checks for maximum metadata block size is missing SQUASHFS_BLOCK_OFFSET (the two byte length count). Link: https://lkml.kernel.org/r/2069685113.2081245.1614583677427@webmail.123-reg.… Fixes: f37aa4c7366e23f ("squashfs: add more sanity checks in id lookup") Signed-off-by: Phillip Lougher <phillip(a)squashfs.org.uk> Cc: Sean Nyekjaer <sean(a)geanix.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/squashfs/id.c | 6 ++++-- fs/squashfs/xattr_id.c | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) --- a/fs/squashfs/id.c~squashfs-fix-xattr-id-and-id-lookup-sanity-checks +++ a/fs/squashfs/id.c @@ -97,14 +97,16 @@ __le64 *squashfs_read_id_index_table(str start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= id_table_start || (id_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } --- a/fs/squashfs/xattr_id.c~squashfs-fix-xattr-id-and-id-lookup-sanity-checks +++ a/fs/squashfs/xattr_id.c @@ -109,14 +109,16 @@ __le64 *squashfs_read_xattr_id_table(str start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= table_start || (table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } _

4 years, 7 months

1
0
0 0

[patch 06/14] squashfs: fix inode lookup sanity checks

by Andrew Morton

From: Sean Nyekjaer <sean(a)geanix.com> Subject: squashfs: fix inode lookup sanity checks When mouting a squashfs image created without inode compression it fails with: "unable to read inode lookup table" It turns out that the BLOCK_OFFSET is missing when checking the SQUASHFS_METADATA_SIZE agaist the actual size. Link: https://lkml.kernel.org/r/20210226092903.1473545-1-sean@geanix.com Fixes: eabac19e40c0 ("squashfs: add more sanity checks in inode lookup") Signed-off-by: Sean Nyekjaer <sean(a)geanix.com> Acked-by: Phillip Lougher <phillip(a)squashfs.org.uk> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/squashfs/export.c | 8 ++++++-- fs/squashfs/squashfs_fs.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) --- a/fs/squashfs/export.c~squashfs-fix-inode-lookup-sanity-checks +++ a/fs/squashfs/export.c @@ -152,14 +152,18 @@ __le64 *squashfs_read_inode_lookup_table start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end + || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= lookup_table_start || + (lookup_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } --- a/fs/squashfs/squashfs_fs.h~squashfs-fix-inode-lookup-sanity-checks +++ a/fs/squashfs/squashfs_fs.h @@ -17,6 +17,7 @@ /* size of metadata (inode and directory) blocks */ #define SQUASHFS_METADATA_SIZE 8192 +#define SQUASHFS_BLOCK_OFFSET 2 /* default size of block device I/O */ #ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE _

4 years, 7 months

1
0
0 0

[patch 05/14] z3fold: prevent reclaim/free race for headless pages

by Andrew Morton

From: Thomas Hebb <tommyhebb(a)gmail.com> Subject: z3fold: prevent reclaim/free race for headless pages commit ca0246bb97c2 ("z3fold: fix possible reclaim races") introduced the PAGE_CLAIMED flag "to avoid racing on a z3fold 'headless' page release." By atomically testing and setting the bit in each of z3fold_free() and z3fold_reclaim_page(), a double-free was avoided. However, commit dcf5aedb24f8 ("z3fold: stricter locking and more careful reclaim") appears to have unintentionally broken this behavior by moving the PAGE_CLAIMED check in z3fold_reclaim_page() to after the page lock gets taken, which only happens for non-headless pages. For headless pages, the check is now skipped entirely and races can occur again. I have observed such a race on my system: page:00000000ffbd76b7 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x165316 flags: 0x2ffff0000000000() raw: 02ffff0000000000 ffffea0004535f48 ffff8881d553a170 0000000000000000 raw: 0000000000000000 0000000000000011 00000000ffffffff 0000000000000000 page dumped because: VM_BUG_ON_PAGE(page_ref_count(page) == 0) ------------[ cut here ]------------ kernel BUG at include/linux/mm.h:707! invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 2 PID: 291928 Comm: kworker/2:0 Tainted: G B 5.10.7-arch1-1-kasan #1 Hardware name: Gigabyte Technology Co., Ltd. H97N-WIFI/H97N-WIFI, BIOS F9b 03/03/2016 Workqueue: zswap-shrink shrink_worker RIP: 0010:__free_pages+0x10a/0x130 Code: c1 e7 06 48 01 ef 45 85 e4 74 d1 44 89 e6 31 d2 41 83 ec 01 e8 e7 b0 ff ff eb da 48 c7 c6 e0 32 91 88 48 89 ef e8 a6 89 f8 ff <0f> 0b 4c 89 e7 e8 fc 79 07 00 e9 33 ff ff ff 48 89 ef e8 ff 79 07 RSP: 0000:ffff88819a2ffb98 EFLAGS: 00010296 RAX: 0000000000000000 RBX: ffffea000594c5a8 RCX: 0000000000000000 RDX: 1ffffd4000b298b7 RSI: 0000000000000000 RDI: ffffea000594c5b8 RBP: ffffea000594c580 R08: 000000000000003e R09: ffff8881d5520bbb R10: ffffed103aaa4177 R11: 0000000000000001 R12: ffffea000594c5b4 R13: 0000000000000000 R14: ffff888165316000 R15: ffffea000594c588 FS: 0000000000000000(0000) GS:ffff8881d5500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7c8c3654d8 CR3: 0000000103f42004 CR4: 00000000001706e0 Call Trace: z3fold_zpool_shrink+0x9b6/0x1240 ? sugov_update_single+0x357/0x990 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0x18/0x180 ? z3fold_zpool_map+0x490/0x490 ? _raw_spin_lock_irq+0x88/0xe0 shrink_worker+0x35/0x90 process_one_work+0x70c/0x1210 ? pwq_dec_nr_in_flight+0x15b/0x2a0 worker_thread+0x539/0x1200 ? __kthread_parkme+0x73/0x120 ? rescuer_thread+0x1000/0x1000 kthread+0x330/0x400 ? __kthread_bind_mask+0x90/0x90 ret_from_fork+0x22/0x30 Modules linked in: rfcomm ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter ccm algif_aead des_generic libdes ecb algif_skcipher cmac bnep md4 algif_hash af_alg vfat fat intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel iwlmvm hid_logitech_hidpp kvm at24 mac80211 snd_hda_codec_realtek iTCO_wdt snd_hda_codec_generic intel_pmc_bxt snd_hda_codec_hdmi ledtrig_audio iTCO_vendor_support mei_wdt mei_hdcp snd_hda_intel snd_intel_dspcfg libarc4 soundwire_intel irqbypass iwlwifi soundwire_generic_allocation rapl soundwire_cadence intel_cstate snd_hda_codec intel_uncore btusb joydev mousedev snd_usb_audio pcspkr btrtl uvcvideo nouveau btbcm i2c_i801 btintel snd_hda_core videobuf2_vmalloc i2c_smbus snd_usbmidi_lib videobuf2_memops bluetooth snd_hwdep soundwire_bus snd_soc_rt5640 videobuf2_v4l2 cfg80211 snd_soc_rl6231 videobuf2_common snd_rawmidi lpc_ich alx videodev mdio snd_seq_device snd_soc_core mc ecdh_generic mxm_wmi mei_me hid_logitech_dj wmi snd_compress e1000e ac97_bus mei ttm rfkill snd_pcm_dmaengine ecc snd_pcm snd_timer snd soundcore mac_hid acpi_pad pkcs8_key_parser it87 hwmon_vid crypto_user fuse ip_tables x_tables ext4 crc32c_generic crc16 mbcache jbd2 dm_crypt cbc encrypted_keys trusted tpm rng_core usbhid dm_mod crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel aesni_intel crypto_simd cryptd glue_helper xhci_pci xhci_pci_renesas i915 video intel_gtt i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops cec drm agpgart ---[ end trace 126d646fc3dc0ad8 ]--- To fix the issue, re-add the earlier test and set in the case where we have a headless page. Link: https://lkml.kernel.org/r/c8106dbe6d8390b290cd1d7f873a2942e805349e.16154520… Fixes: dcf5aedb24f8 ("z3fold: stricter locking and more careful reclaim") Signed-off-by: Thomas Hebb <tommyhebb(a)gmail.com> Reviewed-by: Vitaly Wool <vitaly.wool(a)konsulko.com> Cc: Jongseok Kim <ks77sj(a)gmail.com> Cc: Snild Dolkow <snild(a)sony.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/z3fold.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) --- a/mm/z3fold.c~z3fold-prevent-reclaim-free-race-for-headless-pages +++ a/mm/z3fold.c @@ -1346,8 +1346,22 @@ static int z3fold_reclaim_page(struct z3 page = list_entry(pos, struct page, lru); zhdr = page_address(page); - if (test_bit(PAGE_HEADLESS, &page->private)) + if (test_bit(PAGE_HEADLESS, &page->private)) { + /* + * For non-headless pages, we wait to do this + * until we have the page lock to avoid racing + * with __z3fold_alloc(). Headless pages don't + * have a lock (and __z3fold_alloc() will never + * see them), but we still need to test and set + * PAGE_CLAIMED to avoid racing with + * z3fold_free(), so just do it now before + * leaving the loop. + */ + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + continue; + break; + } if (kref_get_unless_zero(&zhdr->refcount) == 0) { zhdr = NULL; _

4 years, 7 months

1
0
0 0

[patch 02/14] kasan: fix per-page tags for non-page_alloc pages

by Andrew Morton

From: Andrey Konovalov <andreyknvl(a)google.com> Subject: kasan: fix per-page tags for non-page_alloc pages To allow performing tag checks on page_alloc addresses obtained via page_address(), tag-based KASAN modes store tags for page_alloc allocations in page->flags. Currently, the default tag value stored in page->flags is 0x00. Therefore, page_address() returns a 0x00ffff... address for pages that were not allocated via page_alloc. This might cause problems. A particular case we encountered is a conflict with KFENCE. If a KFENCE-allocated slab object is being freed via kfree(page_address(page) + offset), the address passed to kfree() will get tagged with 0x00 (as slab pages keep the default per-page tags). This leads to is_kfence_address() check failing, and a KFENCE object ending up in normal slab freelist, which causes memory corruptions. This patch changes the way KASAN stores tag in page-flags: they are now stored xor'ed with 0xff. This way, KASAN doesn't need to initialize per-page flags for every created page, which might be slow. With this change, page_address() returns natively-tagged (with 0xff) pointers for pages that didn't have tags set explicitly. This patch fixes the encountered conflict with KFENCE and prevents more similar issues that can occur in the future. Link: https://lkml.kernel.org/r/1a41abb11c51b264511d9e71c303bb16d5cb367b.16154754… Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc") Signed-off-by: Andrey Konovalov <andreyknvl(a)google.com> Reviewed-by: Marco Elver <elver(a)google.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: Dmitry Vyukov <dvyukov(a)google.com> Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Peter Collingbourne <pcc(a)google.com> Cc: Evgenii Stepanov <eugenis(a)google.com> Cc: Branislav Rankov <Branislav.Rankov(a)arm.com> Cc: Kevin Brodsky <kevin.brodsky(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mm.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) --- a/include/linux/mm.h~kasan-fix-per-page-tags-for-non-page_alloc-pages +++ a/include/linux/mm.h @@ -1461,16 +1461,28 @@ static inline bool cpupid_match_pid(stru #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) +/* + * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid + * setting tags for all pages to native kernel tag value 0xff, as the default + * value 0x00 maps to 0xff. + */ + static inline u8 page_kasan_tag(const struct page *page) { - if (kasan_enabled()) - return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; - return 0xff; + u8 tag = 0xff; + + if (kasan_enabled()) { + tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; + tag ^= 0xff; + } + + return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { if (kasan_enabled()) { + tag ^= 0xff; page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } _

4 years, 7 months

1
0
0 0

[patch 01/14] hugetlb_cgroup: fix imbalanced css_get and css_put pair for shared mappings

by Andrew Morton

From: Miaohe Lin <linmiaohe(a)huawei.com> Subject: hugetlb_cgroup: fix imbalanced css_get and css_put pair for shared mappings The current implementation of hugetlb_cgroup for shared mappings could have different behavior. Consider the following two scenarios: 1.Assume initial css reference count of hugetlb_cgroup is 1: 1.1 Call hugetlb_reserve_pages with from = 1, to = 2. So css reference count is 2 associated with 1 file_region. 1.2 Call hugetlb_reserve_pages with from = 2, to = 3. So css reference count is 3 associated with 2 file_region. 1.3 coalesce_file_region will coalesce these two file_regions into one. So css reference count is 3 associated with 1 file_region now. 2.Assume initial css reference count of hugetlb_cgroup is 1 again: 2.1 Call hugetlb_reserve_pages with from = 1, to = 3. So css reference count is 2 associated with 1 file_region. Therefore, we might have one file_region while holding one or more css reference counts. This inconsistency could lead to imbalanced css_get() and css_put() pair. If we do css_put one by one (i.g. hole punch case), scenario 2 would put one more css reference. If we do css_put all together (i.g. truncate case), scenario 1 will leak one css reference. The imbalanced css_get() and css_put() pair would result in a non-zero reference when we try to destroy the hugetlb cgroup. The hugetlb cgroup directory is removed __but__ associated resource is not freed. This might result in OOM or can not create a new hugetlb cgroup in a busy workload ultimately. In order to fix this, we have to make sure that one file_region must hold exactly one css reference. So in coalesce_file_region case, we should release one css reference before coalescence. Also only put css reference when the entire file_region is removed. The last thing to note is that the caller of region_add() will only hold one reference to h_cg->css for the whole contiguous reservation region. But this area might be scattered when there are already some file_regions reside in it. As a result, many file_regions may share only one h_cg->css reference. In order to ensure that one file_region must hold exactly one css reference, we should do css_get() for each file_region and release the reference held by caller when they are done. [linmiaohe(a)huawei.com: fix imbalanced css_get and css_put pair for shared mappings] Link: https://lkml.kernel.org/r/20210316023002.53921-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210301120540.37076-1-linmiaohe@huawei.com Fixes: 075a61d07a8e ("hugetlb_cgroup: add accounting for shared mappings") Reported-by: kernel test robot <lkp(a)intel.com> (auto build test ERROR) Signed-off-by: Miaohe Lin <linmiaohe(a)huawei.com> Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.vnet.ibm.com> Cc: Wanpeng Li <liwp.linux(a)gmail.com> Cc: Mina Almasry <almasrymina(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/hugetlb_cgroup.h | 15 +++++++++-- mm/hugetlb.c | 41 +++++++++++++++++++++++++++---- mm/hugetlb_cgroup.c | 10 ++++++- 3 files changed, 58 insertions(+), 8 deletions(-) --- a/include/linux/hugetlb_cgroup.h~hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings +++ a/include/linux/hugetlb_cgroup.h @@ -113,6 +113,11 @@ static inline bool hugetlb_cgroup_disabl return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } +static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) +{ + css_put(&h_cg->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -138,7 +143,8 @@ extern void hugetlb_cgroup_uncharge_coun extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages); + unsigned long nr_pages, + bool region_del); extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct page *oldhpage, @@ -147,7 +153,8 @@ extern void hugetlb_cgroup_migrate(struc #else static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages) + unsigned long nr_pages, + bool region_del) { } @@ -185,6 +192,10 @@ static inline bool hugetlb_cgroup_disabl return true; } +static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { --- a/mm/hugetlb.c~hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings +++ a/mm/hugetlb.c @@ -280,6 +280,17 @@ static void record_hugetlb_cgroup_unchar nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; + /* + * The caller will hold exactly one h_cg->css reference for the + * whole contiguous reservation region. But this area might be + * scattered when there are already some file_regions reside in + * it. As a result, many file_regions may share only one css + * reference. In order to ensure that one file_region must hold + * exactly one h_cg->css reference, we should do css_get for + * each file_region and leave the reference held by caller + * untouched. + */ + css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in @@ -293,6 +304,14 @@ static void record_hugetlb_cgroup_unchar #endif } +static void put_uncharge_info(struct file_region *rg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (rg->css) + css_put(rg->css); +#endif +} + static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { @@ -316,6 +335,7 @@ static void coalesce_file_region(struct prg->to = rg->to; list_del(&rg->link); + put_uncharge_info(rg); kfree(rg); rg = prg; @@ -327,6 +347,7 @@ static void coalesce_file_region(struct nrg->from = rg->from; list_del(&rg->link); + put_uncharge_info(rg); kfree(rg); } } @@ -662,7 +683,7 @@ retry: del += t - f; hugetlb_cgroup_uncharge_file_region( - resv, rg, t - f); + resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; @@ -683,7 +704,7 @@ retry: if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, - rg->to - rg->from); + rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; @@ -691,13 +712,13 @@ retry: if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, - t - rg->from); + t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, - rg->to - f); + rg->to - f, false); del += rg->to - f; rg->to = f; @@ -5187,6 +5208,10 @@ bool hugetlb_reserve_pages(struct inode */ long rsv_adjust; + /* + * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the + * reference to h_cg->css. See comment below for detail. + */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); @@ -5194,6 +5219,14 @@ bool hugetlb_reserve_pages(struct inode rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); + } else if (h_cg) { + /* + * The file_regions will hold their own reference to + * h_cg->css. So we should release the reference held + * via hugetlb_cgroup_charge_cgroup_rsvd() when we are + * done. + */ + hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; --- a/mm/hugetlb_cgroup.c~hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings +++ a/mm/hugetlb_cgroup.c @@ -391,7 +391,8 @@ void hugetlb_cgroup_uncharge_counter(str void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages) + unsigned long nr_pages, + bool region_del) { if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages) return; @@ -400,7 +401,12 @@ void hugetlb_cgroup_uncharge_file_region !resv->reservation_counter) { page_counter_uncharge(rg->reservation_counter, nr_pages * resv->pages_per_hpage); - css_put(rg->css); + /* + * Only do css_put(rg->css) when we delete the entire region + * because one file_region must hold exactly one css reference. + */ + if (region_del) + css_put(rg->css); } } _

4 years, 7 months

1
0
0 0

[patch 05/14] z3fold: prevent reclaim/free race for headless pages

by Andrew Morton

From: Thomas Hebb <tommyhebb(a)gmail.com> Subject: z3fold: prevent reclaim/free race for headless pages commit ca0246bb97c2 ("z3fold: fix possible reclaim races") introduced the PAGE_CLAIMED flag "to avoid racing on a z3fold 'headless' page release." By atomically testing and setting the bit in each of z3fold_free() and z3fold_reclaim_page(), a double-free was avoided. However, commit dcf5aedb24f8 ("z3fold: stricter locking and more careful reclaim") appears to have unintentionally broken this behavior by moving the PAGE_CLAIMED check in z3fold_reclaim_page() to after the page lock gets taken, which only happens for non-headless pages. For headless pages, the check is now skipped entirely and races can occur again. I have observed such a race on my system: page:00000000ffbd76b7 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x165316 flags: 0x2ffff0000000000() raw: 02ffff0000000000 ffffea0004535f48 ffff8881d553a170 0000000000000000 raw: 0000000000000000 0000000000000011 00000000ffffffff 0000000000000000 page dumped because: VM_BUG_ON_PAGE(page_ref_count(page) == 0) ------------[ cut here ]------------ kernel BUG at include/linux/mm.h:707! invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 2 PID: 291928 Comm: kworker/2:0 Tainted: G B 5.10.7-arch1-1-kasan #1 Hardware name: Gigabyte Technology Co., Ltd. H97N-WIFI/H97N-WIFI, BIOS F9b 03/03/2016 Workqueue: zswap-shrink shrink_worker RIP: 0010:__free_pages+0x10a/0x130 Code: c1 e7 06 48 01 ef 45 85 e4 74 d1 44 89 e6 31 d2 41 83 ec 01 e8 e7 b0 ff ff eb da 48 c7 c6 e0 32 91 88 48 89 ef e8 a6 89 f8 ff <0f> 0b 4c 89 e7 e8 fc 79 07 00 e9 33 ff ff ff 48 89 ef e8 ff 79 07 RSP: 0000:ffff88819a2ffb98 EFLAGS: 00010296 RAX: 0000000000000000 RBX: ffffea000594c5a8 RCX: 0000000000000000 RDX: 1ffffd4000b298b7 RSI: 0000000000000000 RDI: ffffea000594c5b8 RBP: ffffea000594c580 R08: 000000000000003e R09: ffff8881d5520bbb R10: ffffed103aaa4177 R11: 0000000000000001 R12: ffffea000594c5b4 R13: 0000000000000000 R14: ffff888165316000 R15: ffffea000594c588 FS: 0000000000000000(0000) GS:ffff8881d5500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7c8c3654d8 CR3: 0000000103f42004 CR4: 00000000001706e0 Call Trace: z3fold_zpool_shrink+0x9b6/0x1240 ? sugov_update_single+0x357/0x990 ? sched_clock+0x5/0x10 ? sched_clock_cpu+0x18/0x180 ? z3fold_zpool_map+0x490/0x490 ? _raw_spin_lock_irq+0x88/0xe0 shrink_worker+0x35/0x90 process_one_work+0x70c/0x1210 ? pwq_dec_nr_in_flight+0x15b/0x2a0 worker_thread+0x539/0x1200 ? __kthread_parkme+0x73/0x120 ? rescuer_thread+0x1000/0x1000 kthread+0x330/0x400 ? __kthread_bind_mask+0x90/0x90 ret_from_fork+0x22/0x30 Modules linked in: rfcomm ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter ccm algif_aead des_generic libdes ecb algif_skcipher cmac bnep md4 algif_hash af_alg vfat fat intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel iwlmvm hid_logitech_hidpp kvm at24 mac80211 snd_hda_codec_realtek iTCO_wdt snd_hda_codec_generic intel_pmc_bxt snd_hda_codec_hdmi ledtrig_audio iTCO_vendor_support mei_wdt mei_hdcp snd_hda_intel snd_intel_dspcfg libarc4 soundwire_intel irqbypass iwlwifi soundwire_generic_allocation rapl soundwire_cadence intel_cstate snd_hda_codec intel_uncore btusb joydev mousedev snd_usb_audio pcspkr btrtl uvcvideo nouveau btbcm i2c_i801 btintel snd_hda_core videobuf2_vmalloc i2c_smbus snd_usbmidi_lib videobuf2_memops bluetooth snd_hwdep soundwire_bus snd_soc_rt5640 videobuf2_v4l2 cfg80211 snd_soc_rl6231 videobuf2_common snd_rawmidi lpc_ich alx videodev mdio snd_seq_device snd_soc_core mc ecdh_generic mxm_wmi mei_me hid_logitech_dj wmi snd_compress e1000e ac97_bus mei ttm rfkill snd_pcm_dmaengine ecc snd_pcm snd_timer snd soundcore mac_hid acpi_pad pkcs8_key_parser it87 hwmon_vid crypto_user fuse ip_tables x_tables ext4 crc32c_generic crc16 mbcache jbd2 dm_crypt cbc encrypted_keys trusted tpm rng_core usbhid dm_mod crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel aesni_intel crypto_simd cryptd glue_helper xhci_pci xhci_pci_renesas i915 video intel_gtt i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops cec drm agpgart ---[ end trace 126d646fc3dc0ad8 ]--- To fix the issue, re-add the earlier test and set in the case where we have a headless page. Link: https://lkml.kernel.org/r/c8106dbe6d8390b290cd1d7f873a2942e805349e.16154520… Fixes: dcf5aedb24f8 ("z3fold: stricter locking and more careful reclaim") Signed-off-by: Thomas Hebb <tommyhebb(a)gmail.com> Reviewed-by: Vitaly Wool <vitaly.wool(a)konsulko.com> Cc: Jongseok Kim <ks77sj(a)gmail.com> Cc: Snild Dolkow <snild(a)sony.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/z3fold.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) --- a/mm/z3fold.c~z3fold-prevent-reclaim-free-race-for-headless-pages +++ a/mm/z3fold.c @@ -1346,8 +1346,22 @@ static int z3fold_reclaim_page(struct z3 page = list_entry(pos, struct page, lru); zhdr = page_address(page); - if (test_bit(PAGE_HEADLESS, &page->private)) + if (test_bit(PAGE_HEADLESS, &page->private)) { + /* + * For non-headless pages, we wait to do this + * until we have the page lock to avoid racing + * with __z3fold_alloc(). Headless pages don't + * have a lock (and __z3fold_alloc() will never + * see them), but we still need to test and set + * PAGE_CLAIMED to avoid racing with + * z3fold_free(), so just do it now before + * leaving the loop. + */ + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + continue; + break; + } if (kref_get_unless_zero(&zhdr->refcount) == 0) { zhdr = NULL; _

4 years, 7 months

1
0
0 0

[patch 02/14] kasan: fix per-page tags for non-page_alloc pages

by Andrew Morton

From: Andrey Konovalov <andreyknvl(a)google.com> Subject: kasan: fix per-page tags for non-page_alloc pages To allow performing tag checks on page_alloc addresses obtained via page_address(), tag-based KASAN modes store tags for page_alloc allocations in page->flags. Currently, the default tag value stored in page->flags is 0x00. Therefore, page_address() returns a 0x00ffff... address for pages that were not allocated via page_alloc. This might cause problems. A particular case we encountered is a conflict with KFENCE. If a KFENCE-allocated slab object is being freed via kfree(page_address(page) + offset), the address passed to kfree() will get tagged with 0x00 (as slab pages keep the default per-page tags). This leads to is_kfence_address() check failing, and a KFENCE object ending up in normal slab freelist, which causes memory corruptions. This patch changes the way KASAN stores tag in page-flags: they are now stored xor'ed with 0xff. This way, KASAN doesn't need to initialize per-page flags for every created page, which might be slow. With this change, page_address() returns natively-tagged (with 0xff) pointers for pages that didn't have tags set explicitly. This patch fixes the encountered conflict with KFENCE and prevents more similar issues that can occur in the future. Link: https://lkml.kernel.org/r/1a41abb11c51b264511d9e71c303bb16d5cb367b.16154754… Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc") Signed-off-by: Andrey Konovalov <andreyknvl(a)google.com> Reviewed-by: Marco Elver <elver(a)google.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Vincenzo Frascino <vincenzo.frascino(a)arm.com> Cc: Dmitry Vyukov <dvyukov(a)google.com> Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Peter Collingbourne <pcc(a)google.com> Cc: Evgenii Stepanov <eugenis(a)google.com> Cc: Branislav Rankov <Branislav.Rankov(a)arm.com> Cc: Kevin Brodsky <kevin.brodsky(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mm.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) --- a/include/linux/mm.h~kasan-fix-per-page-tags-for-non-page_alloc-pages +++ a/include/linux/mm.h @@ -1461,16 +1461,28 @@ static inline bool cpupid_match_pid(stru #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) +/* + * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid + * setting tags for all pages to native kernel tag value 0xff, as the default + * value 0x00 maps to 0xff. + */ + static inline u8 page_kasan_tag(const struct page *page) { - if (kasan_enabled()) - return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; - return 0xff; + u8 tag = 0xff; + + if (kasan_enabled()) { + tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; + tag ^= 0xff; + } + + return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { if (kasan_enabled()) { + tag ^= 0xff; page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } _

4 years, 7 months

1
0
0 0

[patch 01/14] hugetlb_cgroup: fix imbalanced css_get and css_put pair for shared mappings

by Andrew Morton

From: Miaohe Lin <linmiaohe(a)huawei.com> Subject: hugetlb_cgroup: fix imbalanced css_get and css_put pair for shared mappings The current implementation of hugetlb_cgroup for shared mappings could have different behavior. Consider the following two scenarios: 1.Assume initial css reference count of hugetlb_cgroup is 1: 1.1 Call hugetlb_reserve_pages with from = 1, to = 2. So css reference count is 2 associated with 1 file_region. 1.2 Call hugetlb_reserve_pages with from = 2, to = 3. So css reference count is 3 associated with 2 file_region. 1.3 coalesce_file_region will coalesce these two file_regions into one. So css reference count is 3 associated with 1 file_region now. 2.Assume initial css reference count of hugetlb_cgroup is 1 again: 2.1 Call hugetlb_reserve_pages with from = 1, to = 3. So css reference count is 2 associated with 1 file_region. Therefore, we might have one file_region while holding one or more css reference counts. This inconsistency could lead to imbalanced css_get() and css_put() pair. If we do css_put one by one (i.g. hole punch case), scenario 2 would put one more css reference. If we do css_put all together (i.g. truncate case), scenario 1 will leak one css reference. The imbalanced css_get() and css_put() pair would result in a non-zero reference when we try to destroy the hugetlb cgroup. The hugetlb cgroup directory is removed __but__ associated resource is not freed. This might result in OOM or can not create a new hugetlb cgroup in a busy workload ultimately. In order to fix this, we have to make sure that one file_region must hold exactly one css reference. So in coalesce_file_region case, we should release one css reference before coalescence. Also only put css reference when the entire file_region is removed. The last thing to note is that the caller of region_add() will only hold one reference to h_cg->css for the whole contiguous reservation region. But this area might be scattered when there are already some file_regions reside in it. As a result, many file_regions may share only one h_cg->css reference. In order to ensure that one file_region must hold exactly one css reference, we should do css_get() for each file_region and release the reference held by caller when they are done. [linmiaohe(a)huawei.com: fix imbalanced css_get and css_put pair for shared mappings] Link: https://lkml.kernel.org/r/20210316023002.53921-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210301120540.37076-1-linmiaohe@huawei.com Fixes: 075a61d07a8e ("hugetlb_cgroup: add accounting for shared mappings") Reported-by: kernel test robot <lkp(a)intel.com> (auto build test ERROR) Signed-off-by: Miaohe Lin <linmiaohe(a)huawei.com> Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.vnet.ibm.com> Cc: Wanpeng Li <liwp.linux(a)gmail.com> Cc: Mina Almasry <almasrymina(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/hugetlb_cgroup.h | 15 +++++++++-- mm/hugetlb.c | 41 +++++++++++++++++++++++++++---- mm/hugetlb_cgroup.c | 10 ++++++- 3 files changed, 58 insertions(+), 8 deletions(-) --- a/include/linux/hugetlb_cgroup.h~hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings +++ a/include/linux/hugetlb_cgroup.h @@ -113,6 +113,11 @@ static inline bool hugetlb_cgroup_disabl return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } +static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) +{ + css_put(&h_cg->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -138,7 +143,8 @@ extern void hugetlb_cgroup_uncharge_coun extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages); + unsigned long nr_pages, + bool region_del); extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct page *oldhpage, @@ -147,7 +153,8 @@ extern void hugetlb_cgroup_migrate(struc #else static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages) + unsigned long nr_pages, + bool region_del) { } @@ -185,6 +192,10 @@ static inline bool hugetlb_cgroup_disabl return true; } +static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { --- a/mm/hugetlb.c~hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings +++ a/mm/hugetlb.c @@ -280,6 +280,17 @@ static void record_hugetlb_cgroup_unchar nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; + /* + * The caller will hold exactly one h_cg->css reference for the + * whole contiguous reservation region. But this area might be + * scattered when there are already some file_regions reside in + * it. As a result, many file_regions may share only one css + * reference. In order to ensure that one file_region must hold + * exactly one h_cg->css reference, we should do css_get for + * each file_region and leave the reference held by caller + * untouched. + */ + css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in @@ -293,6 +304,14 @@ static void record_hugetlb_cgroup_unchar #endif } +static void put_uncharge_info(struct file_region *rg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (rg->css) + css_put(rg->css); +#endif +} + static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { @@ -316,6 +335,7 @@ static void coalesce_file_region(struct prg->to = rg->to; list_del(&rg->link); + put_uncharge_info(rg); kfree(rg); rg = prg; @@ -327,6 +347,7 @@ static void coalesce_file_region(struct nrg->from = rg->from; list_del(&rg->link); + put_uncharge_info(rg); kfree(rg); } } @@ -662,7 +683,7 @@ retry: del += t - f; hugetlb_cgroup_uncharge_file_region( - resv, rg, t - f); + resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; @@ -683,7 +704,7 @@ retry: if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, - rg->to - rg->from); + rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; @@ -691,13 +712,13 @@ retry: if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, - t - rg->from); + t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, - rg->to - f); + rg->to - f, false); del += rg->to - f; rg->to = f; @@ -5187,6 +5208,10 @@ bool hugetlb_reserve_pages(struct inode */ long rsv_adjust; + /* + * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the + * reference to h_cg->css. See comment below for detail. + */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); @@ -5194,6 +5219,14 @@ bool hugetlb_reserve_pages(struct inode rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); + } else if (h_cg) { + /* + * The file_regions will hold their own reference to + * h_cg->css. So we should release the reference held + * via hugetlb_cgroup_charge_cgroup_rsvd() when we are + * done. + */ + hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; --- a/mm/hugetlb_cgroup.c~hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings +++ a/mm/hugetlb_cgroup.c @@ -391,7 +391,8 @@ void hugetlb_cgroup_uncharge_counter(str void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages) + unsigned long nr_pages, + bool region_del) { if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages) return; @@ -400,7 +401,12 @@ void hugetlb_cgroup_uncharge_file_region !resv->reservation_counter) { page_counter_uncharge(rg->reservation_counter, nr_pages * resv->pages_per_hpage); - css_put(rg->css); + /* + * Only do css_put(rg->css) when we delete the entire region + * because one file_region must hold exactly one css reference. + */ + if (region_del) + css_put(rg->css); } } _

4 years, 7 months

1
0
0 0

[folded-merged] hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings-v3.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: hugetlb_cgroup: fix imbalanced css_get and css_put pair for shared mappings has been removed from the -mm tree. Its filename was hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings-v3.patch This patch was dropped because it was folded into hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings.patch ------------------------------------------------------ From: Miaohe Lin <linmiaohe(a)huawei.com> Subject: hugetlb_cgroup: fix imbalanced css_get and css_put pair for shared mappings reshape some comments, per Mike Link: https://lkml.kernel.org/r/20210316023002.53921-1-linmiaohe@huawei.com Fixes: 075a61d07a8e ("hugetlb_cgroup: add accounting for shared mappings") Signed-off-by: Miaohe Lin <linmiaohe(a)huawei.com> Reported-by: kernel test robot <lkp(a)intel.com> (auto build test ERROR) Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.vnet.ibm.com> Cc: Wanpeng Li <liwp.linux(a)gmail.com> Cc: Mina Almasry <almasrymina(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/hugetlb.c | 13 ++++++------- mm/hugetlb_cgroup.c | 3 +-- 2 files changed, 7 insertions(+), 9 deletions(-) --- a/mm/hugetlb.c~hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings-v3 +++ a/mm/hugetlb.c @@ -281,13 +281,12 @@ static void record_hugetlb_cgroup_unchar &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* - * The caller (hugetlb_reserve_pages now) will only hold one - * h_cg->css reference for the whole contiguous reservation - * region. But this area might be scattered when there are - * already some file_regions reside in it. As a result, many - * file_regions may share only one h_cg->css reference. In - * order to ensure that one file_region must hold and only - * hold one h_cg->css reference, we should do css_get for + * The caller will hold exactly one h_cg->css reference for the + * whole contiguous reservation region. But this area might be + * scattered when there are already some file_regions reside in + * it. As a result, many file_regions may share only one css + * reference. In order to ensure that one file_region must hold + * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ --- a/mm/hugetlb_cgroup.c~hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings-v3 +++ a/mm/hugetlb_cgroup.c @@ -403,8 +403,7 @@ void hugetlb_cgroup_uncharge_file_region nr_pages * resv->pages_per_hpage); /* * Only do css_put(rg->css) when we delete the entire region - * because one file_region must hold and only hold one rg->css - * reference. + * because one file_region must hold exactly one css reference. */ if (region_del) css_put(rg->css); _ Patches currently in -mm which might be from linmiaohe(a)huawei.com are hugetlb_cgroup-fix-imbalanced-css_get-and-css_put-pair-for-shared-mappings.patch mm-hugetlb-remove-redundant-reservation-check-condition-in-alloc_huge_page.patch mm-hugetlb-use-some-helper-functions-to-cleanup-code.patch mm-hugetlb-optimize-the-surplus-state-transfer-code-in-move_hugetlb_state.patch hugetlb_cgroup-remove-unnecessary-vm_bug_on_page-in-hugetlb_cgroup_migrate.patch mm-hugetlb-simplify-the-code-when-alloc_huge_page-failed-in-hugetlb_no_page.patch mm-hugetlb-avoid-calculating-fault_mutex_hash-in-truncate_op-case.patch khugepaged-remove-unneeded-return-value-of-khugepaged_collapse_pte_mapped_thps.patch khugepaged-reuse-the-smp_wmb-inside-__setpageuptodate.patch khugepaged-use-helper-khugepaged_test_exit-in-__khugepaged_enter.patch khugepaged-fix-wrong-result-value-for-trace_mm_collapse_huge_page_isolate.patch mm-huge_memoryc-remove-unnecessary-local-variable-ret2.patch mm-huge_memoryc-rework-the-function-vma_adjust_trans_huge.patch mm-huge_memoryc-make-get_huge_zero_page-return-bool.patch mm-huge_memoryc-rework-the-function-do_huge_pmd_numa_page-slightly.patch mm-huge_memoryc-remove-redundant-pagecompound-check.patch mm-huge_memoryc-remove-unused-macro-transparent_hugepage_debug_cow_flag.patch mm-huge_memoryc-use-helper-function-migration_entry_to_page.patch

4 years, 7 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror