diff options
31 files changed, 258 insertions, 108 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index a2bc2bb91970..a5f17a58ffee 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11438,6 +11438,7 @@ F: drivers/tty/hvc/ HUNG TASK DETECTOR M: Andrew Morton <akpm@linux-foundation.org> R: Lance Yang <lance.yang@linux.dev> +R: Masami Hiramatsu <mhiramat@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: include/linux/hung_task.h diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index 916bac09b464..63e037e94e4c 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -106,5 +106,18 @@ void get_cpuflags(void) cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6], &cpu.flags[1]); } + + if (max_amd_level >= 0x8000001f) { + u32 ebx; + + /* + * The X86_FEATURE_COHERENCY_SFW_NO feature bit is in + * the virtualization flags entry (word 8) and set by + * scattered.c, so the bit needs to be explicitly set. + */ + cpuid(0x8000001f, &ignored, &ebx, &ignored, &ignored); + if (ebx & BIT(31)) + set_bit(X86_FEATURE_COHERENCY_SFW_NO, cpu.flags); + } } } diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c index 7a706db87b93..ac7dfd21ddd4 100644 --- a/arch/x86/boot/startup/sev-shared.c +++ b/arch/x86/boot/startup/sev-shared.c @@ -810,6 +810,13 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, if (ret) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); } + + /* + * If validating memory (making it private) and affected by the + * cache-coherency vulnerability, perform the cache eviction mitigation. + */ + if (validate && !has_cpuflag(X86_FEATURE_COHERENCY_SFW_NO)) + sev_evict_cache((void *)vaddr, 1); } /* diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index fc59ce78c477..400a6ab75d45 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -358,10 +358,31 @@ static void svsm_pval_pages(struct snp_psc_desc *desc) static void pvalidate_pages(struct snp_psc_desc *desc) { + struct psc_entry *e; + unsigned int i; + if (snp_vmpl) svsm_pval_pages(desc); else pval_pages(desc); + + /* + * If not affected by the cache-coherency vulnerability there is no need + * to perform the cache eviction mitigation. + */ + if (cpu_feature_enabled(X86_FEATURE_COHERENCY_SFW_NO)) + return; + + for (i = 0; i <= desc->hdr.end_entry; i++) { + e = &desc->entries[i]; + + /* + * If validating memory (making it private) perform the cache + * eviction mitigation. + */ + if (e->operation == SNP_PAGE_STATE_PRIVATE) + sev_evict_cache(pfn_to_kaddr(e->gfn), e->pagesize ? 512 : 1); + } } static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 602957dd2609..06fc0479a23f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -218,6 +218,7 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ +#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 89075ff19afa..02236962fdb1 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -619,6 +619,24 @@ int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); void kdump_sev_callback(void); void snp_fixup_e820_tables(void); + +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_rmptable_init(void) { return -ENOSYS; } @@ -634,6 +652,7 @@ static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} static inline void kdump_sev_callback(void) { } static inline void snp_fixup_e820_tables(void) {} +static inline void sev_evict_cache(void *va, int npages) {} #endif #endif diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index b4a1f6732a3a..6b868afb26c3 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -48,6 +48,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_AMD_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 }, { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 }, diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c index 601fdbe70179..61472a381904 100644 --- a/drivers/accel/habanalabs/common/memory.c +++ b/drivers/accel/habanalabs/common/memory.c @@ -1829,9 +1829,6 @@ static void hl_release_dmabuf(struct dma_buf *dmabuf) struct hl_dmabuf_priv *hl_dmabuf = dmabuf->priv; struct hl_ctx *ctx; - if (!hl_dmabuf) - return; - ctx = hl_dmabuf->ctx; if (hl_dmabuf->memhash_hnode) @@ -1859,7 +1856,12 @@ static int export_dmabuf(struct hl_ctx *ctx, { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); struct hl_device *hdev = ctx->hdev; - int rc, fd; + CLASS(get_unused_fd, fd)(flags); + + if (fd < 0) { + dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd); + return fd; + } exp_info.ops = &habanalabs_dmabuf_ops; exp_info.size = total_size; @@ -1872,13 +1874,6 @@ static int export_dmabuf(struct hl_ctx *ctx, return PTR_ERR(hl_dmabuf->dmabuf); } - fd = dma_buf_fd(hl_dmabuf->dmabuf, flags); - if (fd < 0) { - dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd); - rc = fd; - goto err_dma_buf_put; - } - hl_dmabuf->ctx = ctx; hl_ctx_get(hl_dmabuf->ctx); atomic_inc(&ctx->hdev->dmabuf_export_cnt); @@ -1890,13 +1885,9 @@ static int export_dmabuf(struct hl_ctx *ctx, get_file(ctx->hpriv->file_priv->filp); *dmabuf_fd = fd; + fd_install(take_fd(fd), hl_dmabuf->dmabuf->file); return 0; - -err_dma_buf_put: - hl_dmabuf->dmabuf->priv = NULL; - dma_buf_put(hl_dmabuf->dmabuf); - return rc; } static int validate_export_params_common(struct hl_device *hdev, u64 addr, u64 size, u64 offset) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 835b0deef9bb..f23d75986947 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4331,15 +4331,18 @@ static int try_release_subpage_extent_buffer(struct folio *folio) unsigned long end = index + (PAGE_SIZE >> fs_info->nodesize_bits) - 1; int ret; - xa_lock_irq(&fs_info->buffer_tree); + rcu_read_lock(); xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) { /* * The same as try_release_extent_buffer(), to ensure the eb * won't disappear out from under us. */ spin_lock(&eb->refs_lock); + rcu_read_unlock(); + if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); + rcu_read_lock(); continue; } @@ -4358,11 +4361,10 @@ static int try_release_subpage_extent_buffer(struct folio *folio) * check the folio private at the end. And * release_extent_buffer() will release the refs_lock. */ - xa_unlock_irq(&fs_info->buffer_tree); release_extent_buffer(eb); - xa_lock_irq(&fs_info->buffer_tree); + rcu_read_lock(); } - xa_unlock_irq(&fs_info->buffer_tree); + rcu_read_unlock(); /* * Finally to check if we have cleared folio private, as if we have @@ -4375,7 +4377,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio) ret = 0; spin_unlock(&folio->mapping->i_private_lock); return ret; - } int try_release_extent_buffer(struct folio *folio) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b77dd22b8cdb..d740910e071a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -401,10 +401,12 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, while (index <= end_index) { folio = filemap_get_folio(inode->vfs_inode.i_mapping, index); - index++; - if (IS_ERR(folio)) + if (IS_ERR(folio)) { + index++; continue; + } + index = folio_end(folio) >> PAGE_SHIFT; /* * Here we just clear all Ordered bits for every page in the * range, then btrfs_mark_ordered_io_finished() will handle @@ -2013,7 +2015,7 @@ static int nocow_one_range(struct btrfs_inode *inode, struct folio *locked_folio * cleaered by the caller. */ if (ret < 0) - btrfs_cleanup_ordered_extents(inode, file_pos, end); + btrfs_cleanup_ordered_extents(inode, file_pos, len); return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1a5972178b3a..ccaa9a3cf1ce 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1453,7 +1453,6 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup *src, int sign) { struct btrfs_qgroup *qgroup; - struct btrfs_qgroup *cur; LIST_HEAD(qgroup_list); u64 num_bytes = src->excl; int ret = 0; @@ -1463,7 +1462,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, goto out; qgroup_iterator_add(&qgroup_list, qgroup); - list_for_each_entry(cur, &qgroup_list, iterator) { + list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; qgroup->rfer += sign * num_bytes; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index e58151933844..7256f6748c8f 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -602,6 +602,25 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans, if (btrfs_root_id(root) == objectid) { u64 commit_root_gen; + /* + * Relocation will wait for cleaner thread, and any half-dropped + * subvolume will be fully cleaned up at mount time. + * So here we shouldn't hit a subvolume with non-zero drop_progress. + * + * If this isn't the case, error out since it can make us attempt to + * drop references for extents that were already dropped before. + */ + if (unlikely(btrfs_disk_key_objectid(&root->root_item.drop_progress))) { + struct btrfs_key cpu_key; + + btrfs_disk_key_to_cpu(&cpu_key, &root->root_item.drop_progress); + btrfs_err(fs_info, + "cannot relocate partially dropped subvolume %llu, drop progress key (%llu %u %llu)", + objectid, cpu_key.objectid, cpu_key.type, cpu_key.offset); + ret = -EUCLEAN; + goto fail; + } + /* called by btrfs_init_reloc_root */ ret = btrfs_copy_root(trans, root, root->commit_root, &eb, BTRFS_TREE_RELOC_OBJECTID); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2186e87fb61b..69e11557fd13 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2605,14 +2605,14 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, /* * Correctly adjust the reserved bytes occupied by a log tree extent buffer */ -static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) +static int unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, start); if (!cache) { btrfs_err(fs_info, "unable to find block group for %llu", start); - return; + return -ENOENT; } spin_lock(&cache->space_info->lock); @@ -2623,27 +2623,22 @@ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) spin_unlock(&cache->space_info->lock); btrfs_put_block_group(cache); + + return 0; } static int clean_log_buffer(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { - int ret; - btrfs_tree_lock(eb); btrfs_clear_buffer_dirty(trans, eb); wait_on_extent_buffer_writeback(eb); btrfs_tree_unlock(eb); - if (trans) { - ret = btrfs_pin_reserved_extent(trans, eb); - if (ret) - return ret; - } else { - unaccount_log_buffer(eb->fs_info, eb->start); - } + if (trans) + return btrfs_pin_reserved_extent(trans, eb); - return 0; + return unaccount_log_buffer(eb->fs_info, eb->start); } static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 245e813ecd78..db11b5b5f0e6 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2650,7 +2650,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info) spin_lock(&block_group->lock); if (block_group->reserved || block_group->alloc_offset == 0 || - (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) || + !(block_group->flags & BTRFS_BLOCK_GROUP_DATA) || test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) { spin_unlock(&block_group->lock); continue; diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 7b26efc271ee..d81f3318417d 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -3,8 +3,18 @@ config EROFS_FS tristate "EROFS filesystem support" depends on BLOCK + select CACHEFILES if EROFS_FS_ONDEMAND select CRC32 + select CRYPTO if EROFS_FS_ZIP_ACCEL + select CRYPTO_DEFLATE if EROFS_FS_ZIP_ACCEL select FS_IOMAP + select LZ4_DECOMPRESS if EROFS_FS_ZIP + select NETFS_SUPPORT if EROFS_FS_ONDEMAND + select XXHASH if EROFS_FS_XATTR + select XZ_DEC if EROFS_FS_ZIP_LZMA + select XZ_DEC_MICROLZMA if EROFS_FS_ZIP_LZMA + select ZLIB_INFLATE if EROFS_FS_ZIP_DEFLATE + select ZSTD_DECOMPRESS if EROFS_FS_ZIP_ZSTD help EROFS (Enhanced Read-Only File System) is a lightweight read-only file system with modern designs (e.g. no buffer heads, inline @@ -38,7 +48,6 @@ config EROFS_FS_DEBUG config EROFS_FS_XATTR bool "EROFS extended attributes" depends on EROFS_FS - select XXHASH default y help Extended attributes are name:value pairs associated with inodes by @@ -94,7 +103,6 @@ config EROFS_FS_BACKED_BY_FILE config EROFS_FS_ZIP bool "EROFS Data Compression Support" depends on EROFS_FS - select LZ4_DECOMPRESS default y help Enable transparent compression support for EROFS file systems. @@ -104,8 +112,6 @@ config EROFS_FS_ZIP config EROFS_FS_ZIP_LZMA bool "EROFS LZMA compressed data support" depends on EROFS_FS_ZIP - select XZ_DEC - select XZ_DEC_MICROLZMA help Saying Y here includes support for reading EROFS file systems containing LZMA compressed data, specifically called microLZMA. It @@ -117,7 +123,6 @@ config EROFS_FS_ZIP_LZMA config EROFS_FS_ZIP_DEFLATE bool "EROFS DEFLATE compressed data support" depends on EROFS_FS_ZIP - select ZLIB_INFLATE help Saying Y here includes support for reading EROFS file systems containing DEFLATE compressed data. It gives better compression @@ -132,7 +137,6 @@ config EROFS_FS_ZIP_DEFLATE config EROFS_FS_ZIP_ZSTD bool "EROFS Zstandard compressed data support" depends on EROFS_FS_ZIP - select ZSTD_DECOMPRESS help Saying Y here includes support for reading EROFS file systems containing Zstandard compressed data. It gives better compression @@ -147,8 +151,6 @@ config EROFS_FS_ZIP_ZSTD config EROFS_FS_ZIP_ACCEL bool "EROFS hardware decompression support" depends on EROFS_FS_ZIP - select CRYPTO - select CRYPTO_DEFLATE help Saying Y here includes hardware accelerator support for reading EROFS file systems containing compressed data. It gives better @@ -163,9 +165,7 @@ config EROFS_FS_ZIP_ACCEL config EROFS_FS_ONDEMAND bool "EROFS fscache-based on-demand read support (deprecated)" depends on EROFS_FS - select NETFS_SUPPORT select FSCACHE - select CACHEFILES select CACHEFILES_ONDEMAND help This permits EROFS to use fscache-backed data blobs with on-demand diff --git a/fs/erofs/super.c b/fs/erofs/super.c index e1020aa60771..1b529ace4db0 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -174,6 +174,11 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, if (!erofs_is_fileio_mode(sbi)) { dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file), &dif->dax_part_off, NULL, NULL); + if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) { + erofs_info(sb, "DAX unsupported by %s. Turning off DAX.", + dif->path); + clear_opt(&sbi->opt, DAX_ALWAYS); + } } else if (!S_ISREG(file_inode(file)->i_mode)) { fput(file); return -EINVAL; @@ -210,8 +215,13 @@ static int erofs_scan_devices(struct super_block *sb, ondisk_extradevs, sbi->devs->extra_devices); return -EINVAL; } - if (!ondisk_extradevs) + if (!ondisk_extradevs) { + if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) { + erofs_info(sb, "DAX unsupported by block device. Turning off DAX."); + clear_opt(&sbi->opt, DAX_ALWAYS); + } return 0; + } if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb)) sbi->devs->flatdev = true; @@ -313,8 +323,8 @@ static int erofs_read_superblock(struct super_block *sb) sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact)); if (erofs_sb_has_48bit(sbi) && dsb->rootnid_8b) { sbi->root_nid = le64_to_cpu(dsb->rootnid_8b); - sbi->dif0.blocks = (sbi->dif0.blocks << 32) | - le16_to_cpu(dsb->rb.blocks_hi); + sbi->dif0.blocks = sbi->dif0.blocks | + ((u64)le16_to_cpu(dsb->rb.blocks_hi) << 32); } else { sbi->root_nid = le16_to_cpu(dsb->rb.rootnid_2b); } @@ -338,7 +348,6 @@ static int erofs_read_superblock(struct super_block *sb) if (ret < 0) goto out; - /* handle multiple devices */ ret = erofs_scan_devices(sb, dsb); if (erofs_sb_has_48bit(sbi)) @@ -671,14 +680,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return invalfc(fc, "cannot use fsoffset in fscache mode"); } - if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dif0.dax_dev) { - errorfc(fc, "DAX unsupported by block device. Turning off DAX."); - clear_opt(&sbi->opt, DAX_ALWAYS); - } else if (sbi->blkszbits != PAGE_SHIFT) { - errorfc(fc, "unsupported blocksize for DAX"); - clear_opt(&sbi->opt, DAX_ALWAYS); - } + if (test_opt(&sbi->opt, DAX_ALWAYS) && sbi->blkszbits != PAGE_SHIFT) { + erofs_info(sb, "unsupported blocksize for DAX"); + clear_opt(&sbi->opt, DAX_ALWAYS); } sb->s_time_gran = 1; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 792f20888a8f..2d73297003d2 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1432,6 +1432,16 @@ static void z_erofs_decompressqueue_kthread_work(struct kthread_work *work) } #endif +/* Use (kthread_)work in atomic contexts to minimize scheduling overhead */ +static inline bool z_erofs_in_atomic(void) +{ + if (IS_ENABLED(CONFIG_PREEMPTION) && rcu_preempt_depth()) + return true; + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return true; + return !preemptible(); +} + static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, int bios) { @@ -1446,8 +1456,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, if (atomic_add_return(bios, &io->pending_bios)) return; - /* Use (kthread_)work and sync decompression for atomic contexts only */ - if (!in_task() || irqs_disabled() || rcu_read_lock_any_held()) { + if (z_erofs_in_atomic()) { #ifdef CONFIG_EROFS_FS_PCPU_KTHREAD struct kthread_worker *worker; diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index 4f6468eb2adf..cb237f1b902a 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -103,10 +103,11 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, if (nfsd_file_get(new) == NULL) goto again; /* - * Drop the ref we were going to install and the - * one we were going to return. + * Drop the ref we were going to install (both file and + * net) and the one we were going to return (only file). */ nfsd_file_put(localio); + nfsd_net_put(net); nfsd_file_put(localio); localio = new; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 98ab55ba3ced..edf050766e57 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -470,7 +470,15 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) if (!iap->ia_valid) return 0; - iap->ia_valid |= ATTR_CTIME; + /* + * If ATTR_DELEG is set, then this is an update from a client that + * holds a delegation. If this is an update for only the atime, the + * ctime should not be changed. If the update contains the mtime + * too, then ATTR_CTIME should already be set. + */ + if (!(iap->ia_valid & ATTR_DELEG)) + iap->ia_valid |= ATTR_CTIME; + return notify_change(&nop_mnt_idmap, dentry, iap, NULL); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3d6d8a9f13fc..29cca0e6d0ff 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -340,8 +340,8 @@ static int proc_maps_open(struct inode *inode, struct file *file, priv->inode = inode; priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR_OR_NULL(priv->mm)) { - int err = priv->mm ? PTR_ERR(priv->mm) : -ESRCH; + if (IS_ERR(priv->mm)) { + int err = PTR_ERR(priv->mm); seq_release_private(inode, file); return err; @@ -1148,10 +1148,13 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; - pte_t ptent = huge_ptep_get(walk->mm, addr, pte); struct folio *folio = NULL; bool present = false; + spinlock_t *ptl; + pte_t ptent; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); + ptent = huge_ptep_get(walk->mm, addr, pte); if (pte_present(ptent)) { folio = page_folio(pte_page(ptent)); present = true; @@ -1170,6 +1173,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); } + spin_unlock(ptl); return 0; } #else @@ -2017,12 +2021,14 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, struct pagemapread *pm = walk->private; struct vm_area_struct *vma = walk->vma; u64 flags = 0, frame = 0; + spinlock_t *ptl; int err = 0; pte_t pte; if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, ptep); pte = huge_ptep_get(walk->mm, addr, ptep); if (pte_present(pte)) { struct folio *folio = page_folio(pte_page(pte)); @@ -2050,11 +2056,12 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, err = add_to_pagemap(&pme, pm); if (err) - return err; + break; if (pm->show_pfn && (flags & PM_PRESENT)) frame++; } + spin_unlock(ptl); cond_resched(); return err; @@ -3128,17 +3135,22 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { - pte_t huge_pte = huge_ptep_get(walk->mm, addr, pte); + pte_t huge_pte; struct numa_maps *md; struct page *page; + spinlock_t *ptl; + ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); + huge_pte = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(huge_pte)) - return 0; + goto out; page = pte_page(huge_pte); md = walk->private; gather_stats(page, md, pte_dirty(huge_pte), 1); +out: + spin_unlock(ptl); return 0; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 174ee243b349..8eff357b0436 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4262,6 +4262,8 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->rcu_iw_gp_seq = rdp->gp_seq - 1; trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + + rcu_preempt_deferred_qs_init(rdp); rcu_spawn_rnp_kthreads(rnp); rcu_spawn_cpu_nocb_kthread(cpu); ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index de6ca13a7b5f..b8bbe7960cda 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -488,6 +488,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_flavor_sched_clock_irq(int user); static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck); +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static bool rcu_is_callbacks_kthread(struct rcu_data *rdp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index fc14adf15cbb..4cd170b2d655 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -763,8 +763,6 @@ static void rcu_read_unlock_special(struct task_struct *t) cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - rdp->defer_qs_iw = - IRQ_WORK_INIT_HARD(rcu_preempt_deferred_qs_handler); rdp->defer_qs_iw_pending = DEFER_QS_PENDING; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } @@ -904,6 +902,10 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) } } +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp) +{ + rdp->defer_qs_iw = IRQ_WORK_INIT_HARD(rcu_preempt_deferred_qs_handler); +} #else /* #ifdef CONFIG_PREEMPT_RCU */ /* @@ -1103,6 +1105,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks)); } +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp) { } + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index 2aa12dfa427a..e0968acc03aa 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -47,7 +47,7 @@ static struct { * Some tests use these global variables to store return values from function * calls that could otherwise be eliminated by the compiler as dead code. */ -static volatile void *kasan_ptr_result; +static void *volatile kasan_ptr_result; static volatile int kasan_int_result; /* Probe for console output: obtains test_status lines of interest. */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 374a6a5193a7..6b40bdfd224c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1172,11 +1172,11 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ + vma_start_write(vma); result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; - vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 8d588e685311..84265983f239 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -470,6 +470,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) { unsigned long flags; struct kmemleak_object *object; + bool warn = false; /* try the slab allocator first */ if (object_cache) { @@ -488,8 +489,10 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) else if (mem_pool_free_count) object = &mem_pool[--mem_pool_free_count]; else - pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); + warn = true; raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + if (warn) + pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); return object; } @@ -2181,6 +2184,7 @@ static const struct file_operations kmemleak_fops = { static void __kmemleak_do_cleanup(void) { struct kmemleak_object *object, *tmp; + unsigned int cnt = 0; /* * Kmemleak has already been disabled, no need for RCU list traversal @@ -2189,6 +2193,10 @@ static void __kmemleak_do_cleanup(void) list_for_each_entry_safe(object, tmp, &object_list, object_list) { __remove_object(object); __delete_object(object); + + /* Call cond_resched() once per 64 iterations to avoid soft lockup */ + if (!(++cnt & 0x3f)) + cond_resched(); } } diff --git a/mm/mprotect.c b/mm/mprotect.c index 78bded7acf79..113b48985834 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -120,9 +120,8 @@ static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep, static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, pte_t oldpte, pte_t *pte, int target_node, - struct folio **foliop) + struct folio *folio) { - struct folio *folio = NULL; bool ret = true; bool toptier; int nid; @@ -131,7 +130,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, if (pte_protnone(oldpte)) goto skip; - folio = vm_normal_folio(vma, addr, oldpte); if (!folio) goto skip; @@ -173,7 +171,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); skip: - *foliop = folio; return ret; } @@ -231,10 +228,9 @@ static int page_anon_exclusive_sub_batch(int start_idx, int max_len, * retrieve sub-batches. */ static void commit_anon_folio_batch(struct vm_area_struct *vma, - struct folio *folio, unsigned long addr, pte_t *ptep, + struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb) { - struct page *first_page = folio_page(folio, 0); bool expected_anon_exclusive; int sub_batch_idx = 0; int len; @@ -251,7 +247,7 @@ static void commit_anon_folio_batch(struct vm_area_struct *vma, } static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma, - struct folio *folio, unsigned long addr, pte_t *ptep, + struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb) { bool set_write; @@ -270,7 +266,7 @@ static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma, /* idx = */ 0, set_write, tlb); return; } - commit_anon_folio_batch(vma, folio, addr, ptep, oldpte, ptent, nr_ptes, tlb); + commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb); } static long change_pte_range(struct mmu_gather *tlb, @@ -305,15 +301,19 @@ static long change_pte_range(struct mmu_gather *tlb, const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE; int max_nr_ptes = (end - addr) >> PAGE_SHIFT; struct folio *folio = NULL; + struct page *page; pte_t ptent; + page = vm_normal_page(vma, addr, oldpte); + if (page) + folio = page_folio(page); /* * Avoid trapping faults against the zero or KSM * pages. See similar comment in change_huge_pmd. */ if (prot_numa) { int ret = prot_numa_skip(vma, addr, oldpte, pte, - target_node, &folio); + target_node, folio); if (ret) { /* determine batch to skip */ @@ -323,9 +323,6 @@ static long change_pte_range(struct mmu_gather *tlb, } } - if (!folio) - folio = vm_normal_folio(vma, addr, oldpte); - nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags); oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes); @@ -351,7 +348,7 @@ static long change_pte_range(struct mmu_gather *tlb, */ if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pte_write(ptent)) - set_write_prot_commit_flush_ptes(vma, folio, + set_write_prot_commit_flush_ptes(vma, folio, page, addr, pte, oldpte, ptent, nr_ptes, tlb); else prot_commit_flush_ptes(vma, addr, pte, oldpte, ptent, diff --git a/mm/mremap.c b/mm/mremap.c index 677a4d744df9..9afa8cd524f5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -179,6 +179,10 @@ static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr if (max_nr == 1) return 1; + /* Avoid expensive folio lookup if we stand no chance of benefit. */ + if (pte_batch_hint(ptep, pte) == 1) + return 1; + folio = vm_normal_folio(vma, addr, pte); if (!folio || !folio_test_large(folio)) return 1; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index cbed91b09640..45e6290e2e8b 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1821,13 +1821,16 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, /* Check if we can move the pmd without splitting it. */ if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || !pmd_none(dst_pmdval)) { - struct folio *folio = pmd_folio(*src_pmd); - - if (!folio || (!is_huge_zero_folio(folio) && - !PageAnonExclusive(&folio->page))) { - spin_unlock(ptl); - err = -EBUSY; - break; + /* Can be a migration entry */ + if (pmd_present(*src_pmd)) { + struct folio *folio = pmd_folio(*src_pmd); + + if (!is_huge_zero_folio(folio) && + !PageAnonExclusive(&folio->page)) { + spin_unlock(ptl); + err = -EBUSY; + break; + } } spin_unlock(ptl); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 46c156b121db..e2c5e0e626f9 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -257,20 +257,47 @@ svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg, } static int -svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg) +svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags) { union { struct cmsghdr cmsg; u8 buf[CMSG_SPACE(sizeof(u8))]; } u; - struct socket *sock = svsk->sk_sock; + u8 alert[2]; + struct kvec alert_kvec = { + .iov_base = alert, + .iov_len = sizeof(alert), + }; + struct msghdr msg = { + .msg_flags = *msg_flags, + .msg_control = &u, + .msg_controllen = sizeof(u), + }; + int ret; + + iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, + alert_kvec.iov_len); + ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT); + if (ret > 0 && + tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { + iov_iter_revert(&msg.msg_iter, ret); + ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN); + } + return ret; +} + +static int +svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg) +{ int ret; + struct socket *sock = svsk->sk_sock; - msg->msg_control = &u; - msg->msg_controllen = sizeof(u); ret = sock_recvmsg(sock, msg, MSG_DONTWAIT); - if (unlikely(msg->msg_controllen != sizeof(u))) - ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret); + if (msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR); + if (ret == 0 || ret == -EIO) + ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags); + } return ret; } @@ -321,7 +348,7 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen, iov_iter_advance(&msg.msg_iter, seek); buflen -= seek; } - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len > 0) svc_flush_bvec(bvec, len, seek); @@ -1018,7 +1045,7 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk, iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen; iov.iov_len = want; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want); - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len < 0) return len; svsk->sk_tcplen += len; diff --git a/tools/testing/selftests/proc/proc-maps-race.c b/tools/testing/selftests/proc/proc-maps-race.c index 66773685a047..94bba4553130 100644 --- a/tools/testing/selftests/proc/proc-maps-race.c +++ b/tools/testing/selftests/proc/proc-maps-race.c @@ -202,11 +202,11 @@ static void print_first_lines(char *text, int nr) int offs = end - text; text[offs] = '\0'; - printf(text); + printf("%s", text); text[offs] = '\n'; printf("\n"); } else { - printf(text); + printf("%s", text); } } @@ -221,7 +221,7 @@ static void print_last_lines(char *text, int nr) nr--; start--; } - printf(start); + printf("%s", start); } static void print_boundaries(const char *title, FIXTURE_DATA(proc_maps_race) *self) |