diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 2e24e765e6d3af5d6b7842d45d333d3061bfd1ca..3765135e598c6c919bc345be2d964149f02bb49c 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -231,14 +231,15 @@ vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned vma->vm_flags); } -static inline void -vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn) +static inline void vivt_flush_cache_pages(struct vm_area_struct *vma, + unsigned long user_addr, unsigned long pfn, unsigned int nr) { struct mm_struct *mm = vma->vm_mm; if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) { unsigned long addr = user_addr & PAGE_MASK; - __cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags); + __cpuc_flush_user_range(addr, addr + nr * PAGE_SIZE, + vma->vm_flags); } } @@ -247,15 +248,17 @@ vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig vivt_flush_cache_mm(mm) #define flush_cache_range(vma,start,end) \ vivt_flush_cache_range(vma,start,end) -#define flush_cache_page(vma,addr,pfn) \ - vivt_flush_cache_page(vma,addr,pfn) +#define flush_cache_pages(vma, addr, pfn, nr) \ + vivt_flush_cache_pages(vma, addr, pfn, nr) #else -extern void flush_cache_mm(struct mm_struct *mm); -extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn); +void flush_cache_mm(struct mm_struct *mm); +void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +void flush_cache_pages(struct vm_area_struct *vma, unsigned long user_addr, + unsigned long pfn, unsigned int nr); #endif #define flush_cache_dup_mm(mm) flush_cache_mm(mm) +#define flush_cache_page(vma, addr, pfn) flush_cache_pages(vma, addr, pfn, 1) /* * flush_icache_user_range is used when we want to ensure that the @@ -289,7 +292,9 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr * See update_mmu_cache for the user space part. */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 -extern void flush_dcache_page(struct page *); +void flush_dcache_page(struct page *); +void flush_dcache_folio(struct folio *folio); +#define flush_dcache_folio flush_dcache_folio static inline void flush_kernel_vmap_range(void *addr, int size) { @@ -323,6 +328,7 @@ extern void flush_kernel_dcache_page(struct page *); * duplicate cache flushing elsewhere performed by flush_dcache_page(). */ #define flush_icache_page(vma,page) do { } while (0) +#define flush_icache_pages(vma, page, nr) do { } while (0) /* * flush_cache_vmap() is used when creating mappings (eg, via vmap, diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 0ec157e955f7e3af12620f4d9b3ada65d5500800..b100a993130a148427150d2b844306d228dd7b20 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -222,8 +222,9 @@ static inline void __sync_icache_dcache(pte_t pteval) extern void __sync_icache_dcache(pte_t pteval); #endif -void set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval); +void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval, unsigned int nr); +#define set_ptes set_ptes static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 24cbfc112dfad539682ac42432d6395159464a0d..7e9847337c027f561deae5c7fcab51ea6548ee63 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -626,18 +626,22 @@ extern void flush_bp_all(void); * If PG_dcache_clean is not set for the page, we need to ensure that any * cache entries for the kernels virtual memory range are written * back to the page. On ARMv6 and later, the cache coherency is handled via - * the set_pte_at() function. + * the set_ptes() function. */ #if __LINUX_ARM_ARCH__ < 6 -extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep); +void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr); #else -static inline void update_mmu_cache(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + unsigned int nr) { } #endif +#define update_mmu_cache(vma, addr, ptep) \ + update_mmu_cache_range(NULL, vma, addr, ptep, 1) + #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) #endif diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c index 44f7292ec27be736934825a8462a93f0d607b6d1..9ae74b0eabfc15bb4db85bdc1a0daf6b8774897f 100644 --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -63,10 +63,11 @@ static void mc_copy_user_page(void *from, void *to) void v4_mc_copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { + struct folio *src = page_folio(from); void *kto = kmap_atomic(to); - if (!test_and_set_bit(PG_dcache_clean, &from->flags)) - __flush_dcache_page(page_mapping_file(from), from); + if (!test_and_set_bit(PG_dcache_clean, &src->flags)) + __flush_dcache_folio(folio_flush_mapping(src), src); raw_spin_lock(&minicache_lock); diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c index 6a769a6c314ef3c5c2d31c9ab7441e43a4d5808f..282f8ca1346198f66facc32a3702b286d2cd7bd7 100644 --- a/arch/arm/mm/copypage-v6.c +++ b/arch/arm/mm/copypage-v6.c @@ -68,11 +68,12 @@ static void discard_old_kernel_data(void *kto) static void v6_copy_user_highpage_aliasing(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { + struct folio *src = page_folio(from); unsigned int offset = CACHE_COLOUR(vaddr); unsigned long kfrom, kto; - if (!test_and_set_bit(PG_dcache_clean, &from->flags)) - __flush_dcache_page(page_mapping_file(from), from); + if (!test_and_set_bit(PG_dcache_clean, &src->flags)) + __flush_dcache_folio(folio_flush_mapping(src), src); /* FIXME: not highmem safe */ discard_old_kernel_data(page_address(to)); diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c index eb5d338657d10e382de27dbe5521cdb5039eb507..7c8928bcb36551d9b2a3ff52631da8b9bf77d569 100644 --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -83,10 +83,11 @@ static void mc_copy_user_page(void *from, void *to) void xscale_mc_copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { + struct folio *src = page_folio(from); void *kto = kmap_atomic(to); - if (!test_and_set_bit(PG_dcache_clean, &from->flags)) - __flush_dcache_page(page_mapping_file(from), from); + if (!test_and_set_bit(PG_dcache_clean, &src->flags)) + __flush_dcache_folio(folio_flush_mapping(src), src); raw_spin_lock(&minicache_lock); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c4b8df2ad32850123386dec4a1b59e6aa4d05f7f..1baa3f8a39e3fd989c8fa5fe469a800b787103a5 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -942,19 +942,21 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, * Mark the D-cache clean for these pages to avoid extra flushing. */ if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) { - unsigned long pfn; - size_t left = size; - - pfn = page_to_pfn(page) + off / PAGE_SIZE; - off %= PAGE_SIZE; - if (off) { - pfn++; - left -= PAGE_SIZE - off; - } - while (left >= PAGE_SIZE) { - page = pfn_to_page(pfn++); - set_bit(PG_dcache_clean, &page->flags); - left -= PAGE_SIZE; + struct folio *folio = pfn_folio(paddr / PAGE_SIZE); + size_t offset = offset_in_folio(folio, paddr); + + for (;;) { + size_t sz = folio_size(folio) - offset; + + if (size < sz) + break; + if (!offset) + set_bit(PG_dcache_clean, &folio->flags); + offset = 0; + size -= sz; + if (!size) + break; + folio = folio_next(folio); } } } diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 0e49154454a6f9078870ca38c5bdddd68ab66d18..d1decf2a582e41c80d99dcde5c12fbae622e97d8 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -178,12 +178,12 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma, * * Note that the pte lock will be held. */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep) +void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr) { unsigned long pfn = pte_pfn(*ptep); struct address_space *mapping; - struct page *page; + struct folio *folio; if (!pfn_valid(pfn)) return; @@ -192,13 +192,13 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, * The zero page is never written to, so never has any dirty * cache lines, and therefore never needs to be flushed. */ - page = pfn_to_page(pfn); - if (page == ZERO_PAGE(0)) + if (is_zero_pfn(pfn)) return; - mapping = page_mapping_file(page); - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) - __flush_dcache_page(mapping, page); + folio = page_folio(pfn_to_page(pfn)); + mapping = folio_flush_mapping(folio); + if (!test_and_set_bit(PG_dcache_clean, &folio->flags)) + __flush_dcache_folio(mapping, folio); if (mapping) { if (cache_is_vivt()) make_coherent(mapping, vma, addr, ptep, pfn); diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 6d89db7895d14c85743c09e2c60d92f5410f3fbf..e5d7569dbb365728fd4bbeff421a3a533a50ea38 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -95,10 +95,10 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned __flush_icache_all(); } -void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn) +void flush_cache_pages(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn, unsigned int nr) { if (cache_is_vivt()) { - vivt_flush_cache_page(vma, user_addr, pfn); + vivt_flush_cache_pages(vma, user_addr, pfn, nr); return; } @@ -196,29 +196,31 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, #endif } -void __flush_dcache_page(struct address_space *mapping, struct page *page) +void __flush_dcache_folio(struct address_space *mapping, struct folio *folio) { /* * Writeback any data associated with the kernel mapping of this * page. This ensures that data in the physical page is mutually * coherent with the kernels mapping. */ - if (!PageHighMem(page)) { - __cpuc_flush_dcache_area(page_address(page), page_size(page)); + if (!folio_test_highmem(folio)) { + __cpuc_flush_dcache_area(folio_address(folio), + folio_size(folio)); } else { unsigned long i; if (cache_is_vipt_nonaliasing()) { - for (i = 0; i < compound_nr(page); i++) { - void *addr = kmap_atomic(page + i); + for (i = 0; i < folio_nr_pages(folio); i++) { + void *addr = kmap_local_folio(folio, + i * PAGE_SIZE); __cpuc_flush_dcache_area(addr, PAGE_SIZE); - kunmap_atomic(addr); + kunmap_local(addr); } } else { - for (i = 0; i < compound_nr(page); i++) { - void *addr = kmap_high_get(page + i); + for (i = 0; i < folio_nr_pages(folio); i++) { + void *addr = kmap_high_get(folio_page(folio, i)); if (addr) { __cpuc_flush_dcache_area(addr, PAGE_SIZE); - kunmap_high(page + i); + kunmap_high(folio_page(folio, i)); } } } @@ -230,15 +232,14 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) * userspace colour, which is congruent with page->index. */ if (mapping && cache_is_vipt_aliasing()) - flush_pfn_alias(page_to_pfn(page), - page->index << PAGE_SHIFT); + flush_pfn_alias(folio_pfn(folio), folio_pos(folio)); } -static void __flush_dcache_aliases(struct address_space *mapping, struct page *page) +static void __flush_dcache_aliases(struct address_space *mapping, struct folio *folio) { struct mm_struct *mm = current->active_mm; - struct vm_area_struct *mpnt; - pgoff_t pgoff; + struct vm_area_struct *vma; + pgoff_t pgoff, pgoff_end; /* * There are possible user space mappings of this page: @@ -246,21 +247,36 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p * data in the current VM view associated with this page. * - aliasing VIPT: we only need to find one mapping of this page. */ - pgoff = page->index; + pgoff = folio->index; + pgoff_end = pgoff + folio_nr_pages(folio) - 1; flush_dcache_mmap_lock(mapping); - vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { - unsigned long offset; + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff_end) { + unsigned long start, offset, pfn; + unsigned int nr; /* * If this VMA is not in our MM, we can ignore it. */ - if (mpnt->vm_mm != mm) + if (vma->vm_mm != mm) continue; - if (!(mpnt->vm_flags & VM_MAYSHARE)) + if (!(vma->vm_flags & VM_MAYSHARE)) continue; - offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; - flush_cache_page(mpnt, mpnt->vm_start + offset, page_to_pfn(page)); + + start = vma->vm_start; + pfn = folio_pfn(folio); + nr = folio_nr_pages(folio); + offset = pgoff - vma->vm_pgoff; + if (offset > -nr) { + pfn -= offset; + nr += offset; + } else { + start += offset * PAGE_SIZE; + } + if (start + nr * PAGE_SIZE > vma->vm_end) + nr = (vma->vm_end - start) / PAGE_SIZE; + + flush_cache_pages(vma, start, pfn, nr); } flush_dcache_mmap_unlock(mapping); } @@ -269,7 +285,7 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p void __sync_icache_dcache(pte_t pteval) { unsigned long pfn; - struct page *page; + struct folio *folio; struct address_space *mapping; if (cache_is_vipt_nonaliasing() && !pte_exec(pteval)) @@ -279,14 +295,17 @@ void __sync_icache_dcache(pte_t pteval) if (!pfn_valid(pfn)) return; - page = pfn_to_page(pfn); + folio = page_folio(pfn_to_page(pfn)); + if (folio_test_reserved(folio)) + return; + if (cache_is_vipt_aliasing()) - mapping = page_mapping_file(page); + mapping = folio_flush_mapping(folio); else mapping = NULL; - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) - __flush_dcache_page(mapping, page); + if (!test_and_set_bit(PG_dcache_clean, &folio->flags)) + __flush_dcache_folio(mapping, folio); if (pte_exec(pteval)) __flush_icache_all(); @@ -312,7 +331,7 @@ void __sync_icache_dcache(pte_t pteval) * Note that we disable the lazy flush for SMP configurations where * the cache maintenance operations are not automatically broadcasted. */ -void flush_dcache_page(struct page *page) +void flush_dcache_folio(struct folio *folio) { struct address_space *mapping; @@ -320,31 +339,36 @@ void flush_dcache_page(struct page *page) * The zero page is never written to, so never has any dirty * cache lines, and therefore never needs to be flushed. */ - if (page == ZERO_PAGE(0)) + if (is_zero_pfn(folio_pfn(folio))) return; if (!cache_ops_need_broadcast() && cache_is_vipt_nonaliasing()) { - if (test_bit(PG_dcache_clean, &page->flags)) - clear_bit(PG_dcache_clean, &page->flags); + if (test_bit(PG_dcache_clean, &folio->flags)) + clear_bit(PG_dcache_clean, &folio->flags); return; } - mapping = page_mapping_file(page); + mapping = folio_flush_mapping(folio); if (!cache_ops_need_broadcast() && - mapping && !page_mapcount(page)) - clear_bit(PG_dcache_clean, &page->flags); + mapping && !folio_mapped(folio)) + clear_bit(PG_dcache_clean, &folio->flags); else { - __flush_dcache_page(mapping, page); + __flush_dcache_folio(mapping, folio); if (mapping && cache_is_vivt()) - __flush_dcache_aliases(mapping, page); + __flush_dcache_aliases(mapping, folio); else if (mapping) __flush_icache_all(); - set_bit(PG_dcache_clean, &page->flags); + set_bit(PG_dcache_clean, &folio->flags); } } -EXPORT_SYMBOL(flush_dcache_page); +EXPORT_SYMBOL(flush_dcache_folio); +void flush_dcache_page(struct page *page) +{ + flush_dcache_folio(page_folio(page)); +} +EXPORT_SYMBOL(flush_dcache_page); /* * Ensure cache coherency for the kernel mapping of this page. We can * assume that the page is pinned via kmap. diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 9ff683612f2a8cfc3e59f198e2b806415878bf63..cc6c25b61b2baad0111a796a03770ed18d5569bb 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -45,7 +45,7 @@ struct mem_type { const struct mem_type *get_mem_type(unsigned int type); -extern void __flush_dcache_page(struct address_space *mapping, struct page *page); +void __flush_dcache_folio(struct address_space *mapping, struct folio *folio); /* * ARM specific vm_struct->flags bits. diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index c7fb68459332e9a4b92732a42d12c7d2e35c5dbb..2345c5d4131e1ecc8940d8f9b1dfc9ff08633832 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1682,7 +1682,7 @@ void __init paging_init(const struct machine_desc *mdesc) bootmem_init(); empty_zero_page = virt_to_page(zero_page); - __flush_dcache_page(NULL, empty_zero_page); + __flush_dcache_folio(NULL, page_folio(empty_zero_page)); } void __init early_mm_init(const struct machine_desc *mdesc) @@ -1691,8 +1691,8 @@ void __init early_mm_init(const struct machine_desc *mdesc) early_paging_init(mdesc); } -void set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval) +void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval, unsigned int nr) { unsigned long ext = 0; @@ -1702,5 +1702,11 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, ext |= PTE_EXT_NG; } - set_pte_ext(ptep, pteval, ext); + for (;;) { + set_pte_ext(ptep, pteval, ext); + if (--nr == 0) + break; + ptep++; + pte_val(pteval) += PAGE_SIZE; + } } diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index c4d5b3bacf6449c48836741d1a2cb6d51eb5c0c1..5dfd95d2e802f6f6b96706619dc315076c1439db 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -179,6 +179,12 @@ void setup_mm_for_reboot(void) { } +void flush_dcache_folio(struct folio *folio) +{ + __cpuc_flush_dcache_area(folio_address(folio), folio_size(folio)); +} +EXPORT_SYMBOL(flush_dcache_folio); + void flush_dcache_page(struct page *page) { __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 191bf0df146619332f3a2d403fc0451ab0c5a47f..d4c92b11e022e70f829d81569f08fa709ae11975 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2140,14 +2140,16 @@ static ssize_t tun_put_user(struct tun_struct *tun, tun_is_little_endian(tun), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); - pr_err("unexpected GSO type: " - "0x%x, gso_size %d, hdr_len %d\n", - sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), - tun16_to_cpu(tun, gso.hdr_len)); - print_hex_dump(KERN_ERR, "tun: ", - DUMP_PREFIX_NONE, - 16, 1, skb->head, - min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + + if (net_ratelimit()) { + netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), + tun16_to_cpu(tun, gso.hdr_len)); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + } WARN_ON_ONCE(1); return -EINVAL; } diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index a2ca38e25e0c33ab6a2c7aace36573068e3d9e36..19da72fe892d150b5ec14c5f315fb8a224e2dd7d 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -1190,14 +1190,24 @@ static ssize_t interface_authorized_store(struct device *dev, { struct usb_interface *intf = to_usb_interface(dev); bool val; + struct kernfs_node *kn; if (strtobool(buf, &val) != 0) return -EINVAL; - if (val) + if (val) { usb_authorize_interface(intf); - else - usb_deauthorize_interface(intf); + } else { + /* + * Prevent deadlock if another process is concurrently + * trying to unregister intf. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (kn) { + usb_deauthorize_interface(intf); + sysfs_unbreak_active_protection(kn); + } + } return count; } diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index af191371c3529beb3e84fb30484632b255de629a..bab63eeaf9cbc7cdb4f4cc5ebcb11ac1909824f3 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 5d86ffa72ceab2c2a82a686319021b8c44fd6351..499519f0f6ecd9f9469ad8d222936f58a375bb98 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -678,10 +678,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) LIST_HEAD(mds_list); nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_commit_begin(cinfo.mds); nfs_scan_commit(dreq->inode, &mds_list, &cinfo); res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); - if (res < 0) /* res == -ENOMEM */ - nfs_direct_write_reschedule(dreq); + if (res < 0) { /* res == -ENOMEM */ + spin_lock(&dreq->lock); + if (dreq->flags == 0) + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + } + if (nfs_commit_end(cinfo.mds)) + nfs_direct_write_complete(dreq); } static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index d3cd099ffb6e17702dd35a21cc317a2c70243e45..4cf0606919794f13bfa6e793b63c34544aeeadeb 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1637,7 +1637,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo) !atomic_read(&cinfo->rpcs_out)); } -static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) { atomic_inc(&cinfo->rpcs_out); } diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index bbf241a431f27c36d416ef1d259254fe395903db..c23f9eb3bcb5d7571dee56585c3583d9131481c9 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -312,7 +312,6 @@ int pstore_put_backend_records(struct pstore_info *psi) { struct pstore_private *pos, *tmp; struct dentry *root; - int rc = 0; root = psinfo_lock_root(); if (!root) @@ -322,11 +321,8 @@ int pstore_put_backend_records(struct pstore_info *psi) list_for_each_entry_safe(pos, tmp, &records_list, list) { if (pos->record->psi == psi) { list_del_init(&pos->list); - rc = simple_unlink(d_inode(root), pos->dentry); - if (WARN_ON(rc)) - break; - d_drop(pos->dentry); - dput(pos->dentry); + d_invalidate(pos->dentry); + simple_unlink(d_inode(root), pos->dentry); pos->dentry = NULL; } } @@ -334,7 +330,7 @@ int pstore_put_backend_records(struct pstore_info *psi) inode_unlock(d_inode(root)); - return rc; + return 0; } /* diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index 24463145b35135aeaa400eb51abb8aefed848453..9fb8e9fd4c001761c8c4e3369da17634b1db2b25 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -48,6 +48,10 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, gid_t i_gid; int err; + inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); + if (inode->i_ino == 0) + return -EINVAL; + err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &i_uid); if (err) return err; @@ -58,7 +62,6 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); - inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); inode->i_mtime.tv_sec = le32_to_cpu(sqsh_ino->mtime); inode->i_atime.tv_sec = inode->i_mtime.tv_sec; inode->i_ctime.tv_sec = inode->i_mtime.tv_sec; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 96d0da65e0887ce8192a7c4719aadfb9cd76d7c5..f51b2396830f4a87660a3c759afd28ed4e543395 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -429,6 +429,8 @@ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, kn = kernfs_find_and_get(kobj->sd, attr->name); if (kn) kernfs_break_active_protection(kn); + else + kobject_put(kobj); return kn; } EXPORT_SYMBOL_GPL(sysfs_break_active_protection); diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index ab54732c9c933add03cfb45db2117c947acaab55..6ccc465aa4265d3e021c3a1546a5b05a82ad46a9 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1127,6 +1127,8 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, dir_ui->ui_size = dir->i_size; mutex_unlock(&dir_ui->ui_mutex); out_inode: + /* Free inode->i_link before inode is marked as bad. */ + fscrypt_free_inode(inode); make_bad_inode(inode); iput(inode); out_fname: diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index e39342945a80ba88360de774cf28e9208cb77721..7488864589a7abf0a58d418741ea594da0f8e21e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -553,6 +553,7 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline int diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index f924468d84ec4150584c7ceb0d228842669d46fd..887072ba1d37eaea90e4a7a530e5476bb30f89cf 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -146,6 +146,66 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr) return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); } +/* + * A facility to provide lazy MMU batching. This allows PTE updates and + * page invalidations to be delayed until a call to leave lazy MMU mode + * is issued. Some architectures may benefit from doing this, and it is + * beneficial for both shadow and direct mode hypervisors, which may batch + * the PTE updates which happen during this window. Note that using this + * interface requires that read hazards be removed from the code. A read + * hazard could result in the direct mode hypervisor case, since the actual + * write to the page tables may not yet have taken place, so reads though + * a raw PTE pointer after it has been modified are not guaranteed to be + * up to date. This mode can only be entered and left under the protection of + * the page table locks for all page tables which may be modified. In the UP + * case, this is required so that preemption is disabled, and in the SMP case, + * it must synchronize the delayed page table writes properly on other CPUs. + */ +#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE +#define arch_enter_lazy_mmu_mode() do {} while (0) +#define arch_leave_lazy_mmu_mode() do {} while (0) +#define arch_flush_lazy_mmu_mode() do {} while (0) +#endif + +#ifndef set_ptes +#ifdef PFN_PTE_SHIFT +/** + * set_ptes - Map consecutive pages to a contiguous range of addresses. + * @mm: Address space to map the pages into. + * @addr: Address to map the first page at. + * @ptep: Page table pointer for the first entry. + * @pte: Page table entry for the first page. + * @nr: Number of pages to map. + * + * May be overridden by the architecture, or the architecture can define + * set_pte() and PFN_PTE_SHIFT. + * + * Context: The caller holds the page table lock. The pages all belong + * to the same folio. The PTEs are all in the same PMD. + */ +static inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned int nr) +{ + page_table_check_ptes_set(mm, ptep, pte, nr); + + arch_enter_lazy_mmu_mode(); + for (;;) { + set_pte(ptep, pte); + if (--nr == 0) + break; + ptep++; + pte = __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); + } + arch_leave_lazy_mmu_mode(); +} +#ifndef set_pte_at +#define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1) +#endif +#endif +#else +#define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1) +#endif + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, @@ -886,27 +946,6 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define pgprot_decrypted(prot) (prot) #endif -/* - * A facility to provide lazy MMU batching. This allows PTE updates and - * page invalidations to be delayed until a call to leave lazy MMU mode - * is issued. Some architectures may benefit from doing this, and it is - * beneficial for both shadow and direct mode hypervisors, which may batch - * the PTE updates which happen during this window. Note that using this - * interface requires that read hazards be removed from the code. A read - * hazard could result in the direct mode hypervisor case, since the actual - * write to the page tables may not yet have taken place, so reads though - * a raw PTE pointer after it has been modified are not guaranteed to be - * up to date. This mode can only be entered and left under the protection of - * the page table locks for all page tables which may be modified. In the UP - * case, this is required so that preemption is disabled, and in the SMP case, - * it must synchronize the delayed page table writes properly on other CPUs. - */ -#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE -#define arch_enter_lazy_mmu_mode() do {} while (0) -#define arch_leave_lazy_mmu_mode() do {} while (0) -#define arch_flush_lazy_mmu_mode() do {} while (0) -#endif - /* * A facility to provide batching of the reload of page tables and * other process state with the actual context switch code for diff --git a/init/main.c b/init/main.c index c8934546e764c351822eb8ddc82cd9cb983fa8f7..124d586f2cd9cdabd83704f5af0e73ffeffa9fc2 100644 --- a/init/main.c +++ b/init/main.c @@ -630,6 +630,8 @@ static void __init setup_command_line(char *command_line) if (!saved_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen); + len = xlen + strlen(command_line) + 1; + static_command_line = memblock_alloc(len, SMP_CACHE_BYTES); if (!static_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len); diff --git a/mm/swapfile.c b/mm/swapfile.c index d9c798405eb031aaa2902097df0c2b55ae4145d0..0a067a083116ad3a00d74dd397d1ff8e784bd526 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1272,6 +1272,11 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, } /* + * Note that when only holding the PTL, swapoff might succeed immediately + * after freeing a swap entry. Therefore, immediately after + * __swap_entry_free(), the swap info might become stale and should not + * be touched without a prior get_swap_device(). + * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until @@ -1798,13 +1803,19 @@ int free_swap_and_cache(swp_entry_t entry) if (non_swap_entry(entry)) return 1; - p = _swap_info_get(entry); + p = get_swap_device(entry); if (p) { + if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { + put_swap_device(p); + return 0; + } + count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); + put_swap_device(p); } return p != NULL; }