diff options
214 files changed, 2473 insertions, 2111 deletions
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index ec3b5865c1be..7146da061693 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -1868,12 +1868,16 @@ There are some more advanced barrier functions: (*) smp_mb__before_atomic(); (*) smp_mb__after_atomic(); - These are for use with atomic (such as add, subtract, increment and - decrement) functions that don't return a value, especially when used for - reference counting. These functions do not imply memory barriers. - - These are also used for atomic bitop functions that do not return a - value (such as set_bit and clear_bit). + These are for use with atomic RMW functions that do not imply memory + barriers, but where the code needs a memory barrier. Examples for atomic + RMW functions that do not imply are memory barrier are e.g. add, + subtract, (failed) conditional operations, _relaxed functions, + but not atomic_read or atomic_set. A common example where a memory + barrier may be required is when atomic ops are used for reference + counting. + + These are also used for atomic RMW bitop functions that do not imply a + memory barrier (such as set_bit and clear_bit). As an example, consider a piece of code that marks an object as being dead and then decrements the object's reference count: diff --git a/arch/Kconfig b/arch/Kconfig index 48b5e103bdb0..98de654b79b3 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -393,18 +393,23 @@ config HAVE_ARCH_JUMP_LABEL config HAVE_ARCH_JUMP_LABEL_RELATIVE bool -config HAVE_RCU_TABLE_FREE +config MMU_GATHER_TABLE_FREE bool -config HAVE_RCU_TABLE_NO_INVALIDATE +config MMU_GATHER_RCU_TABLE_FREE bool + select MMU_GATHER_TABLE_FREE -config HAVE_MMU_GATHER_PAGE_SIZE +config MMU_GATHER_PAGE_SIZE bool -config HAVE_MMU_GATHER_NO_GATHER +config MMU_GATHER_NO_RANGE bool +config MMU_GATHER_NO_GATHER + bool + depends on MMU_GATHER_TABLE_FREE + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c index 7268222cf4e1..528d2be58182 100644 --- a/arch/alpha/kernel/srm_env.c +++ b/arch/alpha/kernel/srm_env.c @@ -119,13 +119,12 @@ static ssize_t srm_env_proc_write(struct file *file, const char __user *buffer, return res; } -static const struct file_operations srm_env_proc_fops = { - .owner = THIS_MODULE, - .open = srm_env_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = srm_env_proc_write, +static const struct proc_ops srm_env_proc_ops = { + .proc_open = srm_env_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = srm_env_proc_write, }; static int __init @@ -182,7 +181,7 @@ srm_env_init(void) entry = srm_named_entries; while (entry->name && entry->id) { if (!proc_create_data(entry->name, 0644, named_dir, - &srm_env_proc_fops, (void *)entry->id)) + &srm_env_proc_ops, (void *)entry->id)) goto cleanup; entry++; } @@ -194,7 +193,7 @@ srm_env_init(void) char name[4]; sprintf(name, "%ld", var_num); if (!proc_create_data(name, 0644, numbered_dir, - &srm_env_proc_fops, (void *)var_num)) + &srm_env_proc_ops, (void *)var_num)) goto cleanup; } diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 9019ed9f9c94..12be7e1b7cc0 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -273,6 +273,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pmd_none(x) (!pmd_val(x)) #define pmd_bad(x) ((pmd_val(x) & ~PAGE_MASK)) #define pmd_present(x) (pmd_val(x)) +#define pmd_leaf(x) (pmd_val(x) & _PAGE_HW_SZ) #define pmd_clear(xp) do { pmd_val(*(xp)) = 0; } while (0) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0b1b1c66bce9..497e0e4702b7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -102,7 +102,7 @@ config ARM select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_RCU_TABLE_FREE if SMP && ARM_LPAE + select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ select HAVE_STACKPROTECTOR diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 51beec41d48c..0d3ea35c97fe 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -189,6 +189,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) } #define pmd_large(pmd) (pmd_val(pmd) & 2) +#define pmd_leaf(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) #define pmd_present(pmd) (pmd_val(pmd)) diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 5b18295021a0..ad55ab068dbf 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -134,6 +134,7 @@ #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) #define pmd_large(pmd) pmd_sect(pmd) +#define pmd_leaf(pmd) pmd_sect(pmd) #define pud_clear(pudp) \ do { \ diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index 669474add486..4d4e7b6aabff 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -37,10 +37,6 @@ static inline void __tlb_remove_table(void *_table) #include <asm-generic/tlb.h> -#ifndef CONFIG_HAVE_RCU_TABLE_FREE -#define tlb_remove_table(tlb, entry) tlb_remove_page(tlb, entry) -#endif - static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c index 312cb89ec364..4247ebf4b893 100644 --- a/arch/arm/kernel/atags_proc.c +++ b/arch/arm/kernel/atags_proc.c @@ -17,9 +17,9 @@ static ssize_t atags_read(struct file *file, char __user *buf, return simple_read_from_buffer(buf, count, ppos, b->data, b->size); } -static const struct file_operations atags_fops = { - .read = atags_read, - .llseek = default_llseek, +static const struct proc_ops atags_proc_ops = { + .proc_read = atags_read, + .proc_lseek = default_llseek, }; #define BOOT_PARAMS_SIZE 1536 @@ -61,7 +61,7 @@ static int __init init_atags_procfs(void) b->size = size; memcpy(b->data, atags_copy, size); - tags_entry = proc_create_data("atags", 0400, NULL, &atags_fops, b); + tags_entry = proc_create_data("atags", 0400, NULL, &atags_proc_ops, b); if (!tags_entry) goto nomem; diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 788c5cf46de5..84718eddae60 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -162,12 +162,12 @@ static ssize_t alignment_proc_write(struct file *file, const char __user *buffer return count; } -static const struct file_operations alignment_proc_fops = { - .open = alignment_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = alignment_proc_write, +static const struct proc_ops alignment_proc_ops = { + .proc_open = alignment_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = alignment_proc_write, }; #endif /* CONFIG_PROC_FS */ @@ -1016,7 +1016,7 @@ static int __init alignment_init(void) struct proc_dir_entry *res; res = proc_create("cpu/alignment", S_IWUSR | S_IRUGO, NULL, - &alignment_proc_fops); + &alignment_proc_ops); if (!res) return -ENOMEM; #endif diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e822af0d9219..9414d72f664b 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -221,7 +221,7 @@ EXPORT_SYMBOL(arm_coherent_dma_ops); static int __dma_supported(struct device *dev, u64 mask, bool warn) { - unsigned long max_dma_pfn = min(max_pfn, arm_dma_pfn_limit); + unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit); /* * Translate the device's DMA mask to a PFN limit. This diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index de238b59d9eb..0b30e884e088 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -104,6 +104,7 @@ config ARM64 select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_PCI_IOMAP + select GENERIC_PTDUMP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_STRNCPY_FROM_USER @@ -164,7 +165,7 @@ config ARM64 select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUTEX_CMPXCHG if FUTEX - select HAVE_RCU_TABLE_FREE + select MMU_GATHER_RCU_TABLE_FREE select HAVE_RSEQ select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index cf09010d825f..1c906d932d6b 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -1,22 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -config ARM64_PTDUMP_CORE - def_bool n - -config ARM64_PTDUMP_DEBUGFS - bool "Export kernel pagetable layout to userspace via debugfs" - depends on DEBUG_KERNEL - select ARM64_PTDUMP_CORE - select DEBUG_FS - help - Say Y here if you want to show the kernel pagetable layout in a - debugfs file. This information is only useful for kernel developers - who are working in architecture specific areas of the kernel. - It is probably not a good idea to enable this feature in a production - kernel. - - If in doubt, say N. - config PID_IN_CONTEXTIDR bool "Write the current PID to the CONTEXTIDR register" help @@ -42,7 +25,7 @@ config ARM64_RANDOMIZE_TEXT_OFFSET config DEBUG_WX bool "Warn on W+X mappings at boot" - select ARM64_PTDUMP_CORE + select PTDUMP_CORE ---help--- Generate a warning if any W+X mappings are found at boot. diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index cd5de0e40bfa..538c85e62f86 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -441,6 +441,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) +#define pmd_leaf(pmd) pmd_sect(pmd) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 static inline bool pud_sect(pud_t pud) { return false; } @@ -525,6 +526,7 @@ static inline void pte_unmap(pte_t *pte) { } #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!(pud_val(pud) & PUD_TABLE_BIT)) #define pud_present(pud) pte_present(pud_pte(pud)) +#define pud_leaf(pud) pud_sect(pud) #define pud_valid(pud) pte_valid(pud_pte(pud)) static inline void set_pud(pud_t *pudp, pud_t pud) diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h index 0b8e7269ec82..38187f74e089 100644 --- a/arch/arm64/include/asm/ptdump.h +++ b/arch/arm64/include/asm/ptdump.h @@ -5,7 +5,7 @@ #ifndef __ASM_PTDUMP_H #define __ASM_PTDUMP_H -#ifdef CONFIG_ARM64_PTDUMP_CORE +#ifdef CONFIG_PTDUMP_CORE #include <linux/mm_types.h> #include <linux/seq_file.h> @@ -21,15 +21,15 @@ struct ptdump_info { unsigned long base_addr; }; -void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info); -#ifdef CONFIG_ARM64_PTDUMP_DEBUGFS +void ptdump_walk(struct seq_file *s, struct ptdump_info *info); +#ifdef CONFIG_PTDUMP_DEBUGFS void ptdump_debugfs_register(struct ptdump_info *info, const char *name); #else static inline void ptdump_debugfs_register(struct ptdump_info *info, const char *name) { } #endif void ptdump_check_wx(void); -#endif /* CONFIG_ARM64_PTDUMP_CORE */ +#endif /* CONFIG_PTDUMP_CORE */ #ifdef CONFIG_DEBUG_WX #define debug_checkwx() ptdump_check_wx() diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index 849c1df3d214..d91030f0ffee 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -4,8 +4,8 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ ioremap.o mmap.o pgd.o mmu.o \ context.o proc.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_ARM64_PTDUMP_CORE) += dump.o -obj-$(CONFIG_ARM64_PTDUMP_DEBUGFS) += ptdump_debugfs.o +obj-$(CONFIG_PTDUMP_CORE) += dump.o +obj-$(CONFIG_PTDUMP_DEBUGFS) += ptdump_debugfs.o obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o KASAN_SANITIZE_physaddr.o += n diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 0a920b538a89..860c00ec8bd3 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -15,6 +15,7 @@ #include <linux/io.h> #include <linux/init.h> #include <linux/mm.h> +#include <linux/ptdump.h> #include <linux/sched.h> #include <linux/seq_file.h> @@ -75,10 +76,11 @@ static struct addr_marker address_markers[] = { * dumps out a description of the range. */ struct pg_state { + struct ptdump_state ptdump; struct seq_file *seq; const struct addr_marker *marker; unsigned long start_address; - unsigned level; + int level; u64 current_prot; bool check_wx; unsigned long wx_pages; @@ -174,11 +176,14 @@ struct pg_level { }; static struct pg_level pg_level[] = { - { - }, { /* pgd */ + { /* pgd */ .name = "PGD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), + }, { /* p4d */ + .name = "P4D", + .bits = pte_bits, + .num = ARRAY_SIZE(pte_bits), }, { /* pud */ .name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD", .bits = pte_bits, @@ -241,13 +246,17 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr) st->wx_pages += (addr - st->start_address) / PAGE_SIZE; } -static void note_page(struct pg_state *st, unsigned long addr, unsigned level, - u64 val) +static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, + unsigned long val) { + struct pg_state *st = container_of(pt_st, struct pg_state, ptdump); static const char units[] = "KMGTPE"; - u64 prot = val & pg_level[level].mask; + u64 prot = 0; + + if (level >= 0) + prot = val & pg_level[level].mask; - if (!st->level) { + if (st->level == -1) { st->level = level; st->current_prot = prot; st->start_address = addr; @@ -260,21 +269,22 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, if (st->current_prot) { note_prot_uxn(st, addr); note_prot_wx(st, addr); - pt_dump_seq_printf(st->seq, "0x%016lx-0x%016lx ", + } + + pt_dump_seq_printf(st->seq, "0x%016lx-0x%016lx ", st->start_address, addr); - delta = (addr - st->start_address) >> 10; - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; - } - pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit, - pg_level[st->level].name); - if (pg_level[st->level].bits) - dump_prot(st, pg_level[st->level].bits, - pg_level[st->level].num); - pt_dump_seq_puts(st->seq, "\n"); + delta = (addr - st->start_address) >> 10; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; } + pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit, + pg_level[st->level].name); + if (st->current_prot && pg_level[st->level].bits) + dump_prot(st, pg_level[st->level].bits, + pg_level[st->level].num); + pt_dump_seq_puts(st->seq, "\n"); if (addr >= st->marker[1].start_address) { st->marker++; @@ -293,85 +303,27 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start, - unsigned long end) -{ - unsigned long addr = start; - pte_t *ptep = pte_offset_kernel(pmdp, start); - - do { - note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); - } while (ptep++, addr += PAGE_SIZE, addr != end); -} - -static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start, - unsigned long end) -{ - unsigned long next, addr = start; - pmd_t *pmdp = pmd_offset(pudp, start); - - do { - pmd_t pmd = READ_ONCE(*pmdp); - next = pmd_addr_end(addr, end); - - if (pmd_none(pmd) || pmd_sect(pmd)) { - note_page(st, addr, 3, pmd_val(pmd)); - } else { - BUG_ON(pmd_bad(pmd)); - walk_pte(st, pmdp, addr, next); - } - } while (pmdp++, addr = next, addr != end); -} - -static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start, - unsigned long end) +void ptdump_walk(struct seq_file *s, struct ptdump_info *info) { - unsigned long next, addr = start; - pud_t *pudp = pud_offset(pgdp, start); - - do { - pud_t pud = READ_ONCE(*pudp); - next = pud_addr_end(addr, end); - - if (pud_none(pud) || pud_sect(pud)) { - note_page(st, addr, 2, pud_val(pud)); - } else { - BUG_ON(pud_bad(pud)); - walk_pmd(st, pudp, addr, next); - } - } while (pudp++, addr = next, addr != end); -} + unsigned long end = ~0UL; + struct pg_state st; -static void walk_pgd(struct pg_state *st, struct mm_struct *mm, - unsigned long start) -{ - unsigned long end = (start < TASK_SIZE_64) ? TASK_SIZE_64 : 0; - unsigned long next, addr = start; - pgd_t *pgdp = pgd_offset(mm, start); - - do { - pgd_t pgd = READ_ONCE(*pgdp); - next = pgd_addr_end(addr, end); - - if (pgd_none(pgd)) { - note_page(st, addr, 1, pgd_val(pgd)); - } else { - BUG_ON(pgd_bad(pgd)); - walk_pud(st, pgdp, addr, next); - } - } while (pgdp++, addr = next, addr != end); -} + if (info->base_addr < TASK_SIZE_64) + end = TASK_SIZE_64; -void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info) -{ - struct pg_state st = { - .seq = m, + st = (struct pg_state){ + .seq = s, .marker = info->markers, + .ptdump = { + .note_page = note_page, + .range = (struct ptdump_range[]){ + {info->base_addr, end}, + {0, 0} + } + } }; - walk_pgd(&st, info->mm, info->base_addr); - - note_page(&st, 0, 0, 0); + ptdump_walk_pgd(&st.ptdump, info->mm, NULL); } static void ptdump_initialize(void) @@ -398,11 +350,19 @@ void ptdump_check_wx(void) { 0, NULL}, { -1, NULL}, }, + .level = -1, .check_wx = true, + .ptdump = { + .note_page = note_page, + .range = (struct ptdump_range[]) { + {PAGE_OFFSET, ~0UL}, + {0, 0} + } + } }; - walk_pgd(&st, &init_mm, PAGE_OFFSET); - note_page(&st, 0, 0, 0); + ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); + if (st.wx_pages || st.uxn_pages) pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n", st.wx_pages, st.uxn_pages); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 40797cbfba2d..128f70852bf3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -943,13 +943,13 @@ int __init arch_ioremap_pud_supported(void) * SW table walks can't handle removal of intermediate entries. */ return IS_ENABLED(CONFIG_ARM64_4K_PAGES) && - !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); + !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS); } int __init arch_ioremap_pmd_supported(void) { /* See arch_ioremap_pud_supported() */ - return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); + return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS); } int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c index 064163f25592..1f2eae3e988b 100644 --- a/arch/arm64/mm/ptdump_debugfs.c +++ b/arch/arm64/mm/ptdump_debugfs.c @@ -7,7 +7,7 @@ static int ptdump_show(struct seq_file *m, void *v) { struct ptdump_info *info = m->private; - ptdump_walk_pgd(m, info); + ptdump_walk(m, info); return 0; } DEFINE_SHOW_ATTRIBUTE(ptdump); diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index b392c0a50346..a25ab9b37953 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -331,10 +331,10 @@ retry: return size; } -static const struct file_operations salinfo_event_fops = { - .open = salinfo_event_open, - .read = salinfo_event_read, - .llseek = noop_llseek, +static const struct proc_ops salinfo_event_proc_ops = { + .proc_open = salinfo_event_open, + .proc_read = salinfo_event_read, + .proc_lseek = noop_llseek, }; static int @@ -534,12 +534,12 @@ salinfo_log_write(struct file *file, const char __user *buffer, size_t count, lo return count; } -static const struct file_operations salinfo_data_fops = { - .open = salinfo_log_open, - .release = salinfo_log_release, - .read = salinfo_log_read, - .write = salinfo_log_write, - .llseek = default_llseek, +static const struct proc_ops salinfo_data_proc_ops = { + .proc_open = salinfo_log_open, + .proc_release = salinfo_log_release, + .proc_read = salinfo_log_read, + .proc_write = salinfo_log_write, + .proc_lseek = default_llseek, }; static int salinfo_cpu_online(unsigned int cpu) @@ -617,13 +617,13 @@ salinfo_init(void) continue; entry = proc_create_data("event", S_IRUSR, dir, - &salinfo_event_fops, data); + &salinfo_event_proc_ops, data); if (!entry) continue; *sdir++ = entry; entry = proc_create_data("data", S_IRUSR | S_IWUSR, dir, - &salinfo_data_fops, data); + &salinfo_data_proc_ops, data); if (!entry) continue; *sdir++ = entry; diff --git a/arch/m68k/kernel/bootinfo_proc.c b/arch/m68k/kernel/bootinfo_proc.c index 3b9cab84917d..857fa2aaa748 100644 --- a/arch/m68k/kernel/bootinfo_proc.c +++ b/arch/m68k/kernel/bootinfo_proc.c @@ -26,9 +26,9 @@ static ssize_t bootinfo_read(struct file *file, char __user *buf, bootinfo_size); } -static const struct file_operations bootinfo_fops = { - .read = bootinfo_read, - .llseek = default_llseek, +static const struct proc_ops bootinfo_proc_ops = { + .proc_read = bootinfo_read, + .proc_lseek = default_llseek, }; void __init save_bootinfo(const struct bi_record *bi) @@ -67,7 +67,7 @@ static int __init init_bootinfo_procfs(void) if (!bootinfo_copy) return -ENOMEM; - pde = proc_create_data("bootinfo", 0400, NULL, &bootinfo_fops, NULL); + pde = proc_create_data("bootinfo", 0400, NULL, &bootinfo_proc_ops, NULL); if (!pde) { kfree(bootinfo_copy); return -ENOMEM; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 91b89aab1787..aef5378f909c 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -639,6 +639,11 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#ifdef _PAGE_HUGE +#define pmd_leaf(pmd) ((pmd_val(pmd) & _PAGE_HUGE) != 0) +#define pud_leaf(pud) ((pud_val(pud) & _PAGE_HUGE) != 0) +#endif + #define gup_fast_permitted(start, end) (!cpu_has_dc_aliases) #include <asm-generic/pgtable.h> diff --git a/arch/mips/lasat/picvue_proc.c b/arch/mips/lasat/picvue_proc.c index 8126f15b8e09..61c033494af5 100644 --- a/arch/mips/lasat/picvue_proc.c +++ b/arch/mips/lasat/picvue_proc.c @@ -89,13 +89,12 @@ static ssize_t pvc_line_proc_write(struct file *file, const char __user *buf, return count; } -static const struct file_operations pvc_line_proc_fops = { - .owner = THIS_MODULE, - .open = pvc_line_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = pvc_line_proc_write, +static const struct proc_ops pvc_line_proc_ops = { + .proc_open = pvc_line_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = pvc_line_proc_write, }; static ssize_t pvc_scroll_proc_write(struct file *file, const char __user *buf, @@ -148,13 +147,12 @@ static int pvc_scroll_proc_open(struct inode *inode, struct file *file) return single_open(file, pvc_scroll_proc_show, NULL); } -static const struct file_operations pvc_scroll_proc_fops = { - .owner = THIS_MODULE, - .open = pvc_scroll_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = pvc_scroll_proc_write, +static const struct proc_ops pvc_scroll_proc_ops = { + .proc_open = pvc_scroll_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = pvc_scroll_proc_write, }; void pvc_proc_timerfunc(struct timer_list *unused) @@ -189,12 +187,11 @@ static int __init pvc_proc_init(void) } for (i = 0; i < PVC_NLINES; i++) { proc_entry = proc_create_data(pvc_linename[i], 0644, dir, - &pvc_line_proc_fops, &pvc_linedata[i]); + &pvc_line_proc_ops, &pvc_linedata[i]); if (proc_entry == NULL) goto error; } - proc_entry = proc_create("scroll", 0644, dir, - &pvc_scroll_proc_fops); + proc_entry = proc_create("scroll", 0644, dir, &pvc_scroll_proc_ops); if (proc_entry == NULL) goto error; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c150a9d49343..bf2b538aba12 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -222,9 +222,8 @@ config PPC select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_RCU_TABLE_FREE if SMP - select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE - select HAVE_MMU_GATHER_PAGE_SIZE + select MMU_GATHER_RCU_TABLE_FREE + select MMU_GATHER_PAGE_SIZE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN select HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 998317702630..dc5c039eb28e 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -49,7 +49,6 @@ static inline void pgtable_free(void *table, unsigned index_size) #define get_hugepd_cache_index(x) (x) -#ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { @@ -66,13 +65,6 @@ static inline void __tlb_remove_table(void *_table) pgtable_free(table, shift); } -#else -static inline void pgtable_free_tlb(struct mmu_gather *tlb, - void *table, int shift) -{ - pgtable_free(table, shift); -} -#endif static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index f6968c811026..a41e91bd0580 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -19,9 +19,7 @@ extern struct vmemmap_backing *vmemmap_list; extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long); extern void pmd_fragment_free(unsigned long *); extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); -#ifdef CONFIG_SMP extern void __tlb_remove_table(void *_table); -#endif void pte_frag_destroy(void *pte_frag); static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index b01624e5c467..201a69e6a355 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1355,18 +1355,21 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va * Like pmd_huge() and pmd_large(), but works regardless of config options */ #define pmd_is_leaf pmd_is_leaf +#define pmd_leaf pmd_is_leaf static inline bool pmd_is_leaf(pmd_t pmd) { return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); } #define pud_is_leaf pud_is_leaf +#define pud_leaf pud_is_leaf static inline bool pud_is_leaf(pud_t pud) { return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); } #define pgd_is_leaf pgd_is_leaf +#define pgd_leaf pgd_is_leaf static inline bool pgd_is_leaf(pgd_t pgd) { return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE)); diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h index 332b13b4ecdb..29c43665a753 100644 --- a/arch/powerpc/include/asm/nohash/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/pgalloc.h @@ -46,7 +46,6 @@ static inline void pgtable_free(void *table, int shift) #define get_hugepd_cache_index(x) (x) -#ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { unsigned long pgf = (unsigned long)table; @@ -64,13 +63,6 @@ static inline void __tlb_remove_table(void *_table) pgtable_free(table, shift); } -#else -static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) -{ - pgtable_free(table, shift); -} -#endif - static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index b2c0be93929d..7f3a8b902325 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -26,6 +26,17 @@ #define tlb_flush tlb_flush extern void tlb_flush(struct mmu_gather *tlb); +/* + * book3s: + * Hash does not use the linux page-tables, so we can avoid + * the TLB invalidate for page-table freeing, Radix otoh does use the + * page-tables and needs the TLBI. + * + * nohash: + * We still do TLB invalidate in the __pte_free_tlb routine before we + * add the page table pages to mmu gather table batch. + */ +#define tlb_needs_table_invalidate() radix_enabled() /* Get the generic bits... */ #include <asm-generic/tlb.h> diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c index be3758d54e59..877817471e3c 100644 --- a/arch/powerpc/kernel/proc_powerpc.c +++ b/arch/powerpc/kernel/proc_powerpc.c @@ -39,10 +39,10 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) return 0; } -static const struct file_operations page_map_fops = { - .llseek = page_map_seek, - .read = page_map_read, - .mmap = page_map_mmap +static const struct proc_ops page_map_proc_ops = { + .proc_lseek = page_map_seek, + .proc_read = page_map_read, + .proc_mmap = page_map_mmap, }; @@ -51,7 +51,7 @@ static int __init proc_ppc64_init(void) struct proc_dir_entry *pde; pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL, - &page_map_fops, vdso_data); + &page_map_proc_ops, vdso_data); if (!pde) return 1; proc_set_size(pde, PAGE_SIZE); diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index 487dcd8da4de..2d33f342a293 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -159,12 +159,12 @@ static int poweron_open(struct inode *inode, struct file *file) return single_open(file, ppc_rtas_poweron_show, NULL); } -static const struct file_operations ppc_rtas_poweron_operations = { - .open = poweron_open, - .read = seq_read, - .llseek = seq_lseek, - .write = ppc_rtas_poweron_write, - .release = single_release, +static const struct proc_ops ppc_rtas_poweron_proc_ops = { + .proc_open = poweron_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = ppc_rtas_poweron_write, + .proc_release = single_release, }; static int progress_open(struct inode *inode, struct file *file) @@ -172,12 +172,12 @@ static int progress_open(struct inode *inode, struct file *file) return single_open(file, ppc_rtas_progress_show, NULL); } -static const struct file_operations ppc_rtas_progress_operations = { - .open = progress_open, - .read = seq_read, - .llseek = seq_lseek, - .write = ppc_rtas_progress_write, - .release = single_release, +static const struct proc_ops ppc_rtas_progress_proc_ops = { + .proc_open = progress_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = ppc_rtas_progress_write, + .proc_release = single_release, }; static int clock_open(struct inode *inode, struct file *file) @@ -185,12 +185,12 @@ static int clock_open(struct inode *inode, struct file *file) return single_open(file, ppc_rtas_clock_show, NULL); } -static const struct file_operations ppc_rtas_clock_operations = { - .open = clock_open, - .read = seq_read, - .llseek = seq_lseek, - .write = ppc_rtas_clock_write, - .release = single_release, +static const struct proc_ops ppc_rtas_clock_proc_ops = { + .proc_open = clock_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = ppc_rtas_clock_write, + .proc_release = single_release, }; static int tone_freq_open(struct inode *inode, struct file *file) @@ -198,12 +198,12 @@ static int tone_freq_open(struct inode *inode, struct file *file) return single_open(file, ppc_rtas_tone_freq_show, NULL); } -static const struct file_operations ppc_rtas_tone_freq_operations = { - .open = tone_freq_open, - .read = seq_read, - .llseek = seq_lseek, - .write = ppc_rtas_tone_freq_write, - .release = single_release, +static const struct proc_ops ppc_rtas_tone_freq_proc_ops = { + .proc_open = tone_freq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = ppc_rtas_tone_freq_write, + .proc_release = single_release, }; static int tone_volume_open(struct inode *inode, struct file *file) @@ -211,12 +211,12 @@ static int tone_volume_open(struct inode *inode, struct file *file) return single_open(file, ppc_rtas_tone_volume_show, NULL); } -static const struct file_operations ppc_rtas_tone_volume_operations = { - .open = tone_volume_open, - .read = seq_read, - .llseek = seq_lseek, - .write = ppc_rtas_tone_volume_write, - .release = single_release, +static const struct proc_ops ppc_rtas_tone_volume_proc_ops = { + .proc_open = tone_volume_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = ppc_rtas_tone_volume_write, + .proc_release = single_release, }; static int ppc_rtas_find_all_sensors(void); @@ -238,17 +238,17 @@ static int __init proc_rtas_init(void) return -ENODEV; proc_create("powerpc/rtas/progress", 0644, NULL, - &ppc_rtas_progress_operations); + &ppc_rtas_progress_proc_ops); proc_create("powerpc/rtas/clock", 0644, NULL, - &ppc_rtas_clock_operations); + &ppc_rtas_clock_proc_ops); proc_create("powerpc/rtas/poweron", 0644, NULL, - &ppc_rtas_poweron_operations); + &ppc_rtas_poweron_proc_ops); proc_create_single("powerpc/rtas/sensors", 0444, NULL, ppc_rtas_sensors_show); proc_create("powerpc/rtas/frequency", 0644, NULL, - &ppc_rtas_tone_freq_operations); + &ppc_rtas_tone_freq_proc_ops); proc_create("powerpc/rtas/volume", 0644, NULL, - &ppc_rtas_tone_volume_operations); + &ppc_rtas_tone_volume_proc_ops); proc_create_single("powerpc/rtas/rmo_buffer", 0400, NULL, ppc_rtas_rmo_buf_show); return 0; diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 84f794782c62..a99179d83538 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -655,7 +655,7 @@ struct rtas_flash_file { const char *filename; const char *rtas_call_name; int *status; - const struct file_operations fops; + const struct proc_ops ops; }; static const struct rtas_flash_file rtas_flash_files[] = { @@ -663,36 +663,36 @@ static const struct rtas_flash_file rtas_flash_files[] = { .filename = "powerpc/rtas/" FIRMWARE_FLASH_NAME, .rtas_call_name = "ibm,update-flash-64-and-reboot", .status = &rtas_update_flash_data.status, - .fops.read = rtas_flash_read_msg, - .fops.write = rtas_flash_write, - .fops.release = rtas_flash_release, - .fops.llseek = default_llseek, + .ops.proc_read = rtas_flash_read_msg, + .ops.proc_write = rtas_flash_write, + .ops.proc_release = rtas_flash_release, + .ops.proc_lseek = default_llseek, }, { .filename = "powerpc/rtas/" FIRMWARE_UPDATE_NAME, .rtas_call_name = "ibm,update-flash-64-and-reboot", .status = &rtas_update_flash_data.status, - .fops.read = rtas_flash_read_num, - .fops.write = rtas_flash_write, - .fops.release = rtas_flash_release, - .fops.llseek = default_llseek, + .ops.proc_read = rtas_flash_read_num, + .ops.proc_write = rtas_flash_write, + .ops.proc_release = rtas_flash_release, + .ops.proc_lseek = default_llseek, }, { .filename = "powerpc/rtas/" VALIDATE_FLASH_NAME, .rtas_call_name = "ibm,validate-flash-image", .status = &rtas_validate_flash_data.status, - .fops.read = validate_flash_read, - .fops.write = validate_flash_write, - .fops.release = validate_flash_release, - .fops.llseek = default_llseek, + .ops.proc_read = validate_flash_read, + .ops.proc_write = validate_flash_write, + .ops.proc_release = validate_flash_release, + .ops.proc_lseek = default_llseek, }, { .filename = "powerpc/rtas/" MANAGE_FLASH_NAME, .rtas_call_name = "ibm,manage-flash-image", .status = &rtas_manage_flash_data.status, - .fops.read = manage_flash_read, - .fops.write = manage_flash_write, - .fops.llseek = default_llseek, + .ops.proc_read = manage_flash_read, + .ops.proc_write = manage_flash_write, + .ops.proc_lseek = default_llseek, } }; @@ -723,7 +723,7 @@ static int __init rtas_flash_init(void) const struct rtas_flash_file *f = &rtas_flash_files[i]; int token; - if (!proc_create(f->filename, 0600, NULL, &f->fops)) + if (!proc_create(f->filename, 0600, NULL, &f->ops)) goto enomem; /* diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 8d02e047f96a..89b798f8f656 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -385,12 +385,12 @@ static __poll_t rtas_log_poll(struct file *file, poll_table * wait) return 0; } -static const struct file_operations proc_rtas_log_operations = { - .read = rtas_log_read, - .poll = rtas_log_poll, - .open = rtas_log_open, - .release = rtas_log_release, - .llseek = noop_llseek, +static const struct proc_ops rtas_log_proc_ops = { + .proc_read = rtas_log_read, + .proc_poll = rtas_log_poll, + .proc_open = rtas_log_open, + .proc_release = rtas_log_release, + .proc_lseek = noop_llseek, }; static int enable_surveillance(int timeout) @@ -572,7 +572,7 @@ static int __init rtas_init(void) return -ENODEV; entry = proc_create("powerpc/rtas/error_log", 0400, NULL, - &proc_rtas_log_operations); + &rtas_log_proc_ops); if (!entry) printk(KERN_ERR "Failed to create error_log proc entry\n"); diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 75483b40fcb1..2bf7e1b4fd82 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -378,7 +378,6 @@ static inline void pgtable_free(void *table, int index) } } -#ifdef CONFIG_SMP void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index) { unsigned long pgf = (unsigned long)table; @@ -395,12 +394,6 @@ void __tlb_remove_table(void *_table) return pgtable_free(table, index); } -#else -void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index) -{ - return pgtable_free(table, index); -} -#endif #ifdef CONFIG_PROC_FS atomic_long_t direct_pages_count[MMU_PAGE_COUNT]; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 50d68d21ddcc..3c7dec70cda0 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1616,11 +1616,11 @@ static ssize_t topology_write(struct file *file, const char __user *buf, return count; } -static const struct file_operations topology_ops = { - .read = seq_read, - .write = topology_write, - .open = topology_open, - .release = single_release +static const struct proc_ops topology_proc_ops = { + .proc_read = seq_read, + .proc_write = topology_write, + .proc_open = topology_open, + .proc_release = single_release, }; static int topology_update_init(void) @@ -1630,7 +1630,7 @@ static int topology_update_init(void) if (vphn_enabled) topology_schedule_update(); - if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops)) + if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_proc_ops)) return -ENOMEM; topology_inited = 1; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 60cb29ae4739..3c3da25b445c 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -582,12 +582,12 @@ static int vcpudispatch_stats_open(struct inode *inode, struct file *file) return single_open(file, vcpudispatch_stats_display, NULL); } -static const struct file_operations vcpudispatch_stats_proc_ops = { - .open = vcpudispatch_stats_open, - .read = seq_read, - .write = vcpudispatch_stats_write, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops vcpudispatch_stats_proc_ops = { + .proc_open = vcpudispatch_stats_open, + .proc_read = seq_read, + .proc_write = vcpudispatch_stats_write, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; static ssize_t vcpudispatch_stats_freq_write(struct file *file, @@ -626,12 +626,12 @@ static int vcpudispatch_stats_freq_open(struct inode *inode, struct file *file) return single_open(file, vcpudispatch_stats_freq_display, NULL); } -static const struct file_operations vcpudispatch_stats_freq_proc_ops = { - .open = vcpudispatch_stats_freq_open, - .read = seq_read, - .write = vcpudispatch_stats_freq_write, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops vcpudispatch_stats_freq_proc_ops = { + .proc_open = vcpudispatch_stats_freq_open, + .proc_read = seq_read, + .proc_write = vcpudispatch_stats_freq_write, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; static int __init vcpudispatch_stats_procfs_init(void) diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index e33e8bc4b69b..f43e778dd7c8 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -698,12 +698,12 @@ static int lparcfg_open(struct inode *inode, struct file *file) return single_open(file, lparcfg_data, NULL); } -static const struct file_operations lparcfg_fops = { - .read = seq_read, - .write = lparcfg_write, - .open = lparcfg_open, - .release = single_release, - .llseek = seq_lseek, +static const struct proc_ops lparcfg_proc_ops = { + .proc_read = seq_read, + .proc_write = lparcfg_write, + .proc_open = lparcfg_open, + .proc_release = single_release, + .proc_lseek = seq_lseek, }; static int __init lparcfg_init(void) @@ -714,7 +714,7 @@ static int __init lparcfg_init(void) if (firmware_has_feature(FW_FEATURE_SPLPAR)) mode |= 0200; - if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops)) { + if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_proc_ops)) { printk(KERN_ERR "Failed to create powerpc/lparcfg\n"); return -EIO; } diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 8a9c4fb95b8b..7f7369fec46b 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -391,9 +391,9 @@ out: return rv ? rv : count; } -static const struct file_operations ofdt_fops = { - .write = ofdt_write, - .llseek = noop_llseek, +static const struct proc_ops ofdt_proc_ops = { + .proc_write = ofdt_write, + .proc_lseek = noop_llseek, }; /* create /proc/powerpc/ofdt write-only by root */ @@ -401,7 +401,7 @@ static int proc_ppc64_create_ofdt(void) { struct proc_dir_entry *ent; - ent = proc_create("powerpc/ofdt", 0200, NULL, &ofdt_fops); + ent = proc_create("powerpc/ofdt", 0200, NULL, &ofdt_proc_ops); if (ent) proc_set_size(ent, 0); diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c index a0001280503c..2879c4f0ceb7 100644 --- a/arch/powerpc/platforms/pseries/scanlog.c +++ b/arch/powerpc/platforms/pseries/scanlog.c @@ -152,13 +152,12 @@ static int scanlog_release(struct inode * inode, struct file * file) return 0; } -static const struct file_operations scanlog_fops = { - .owner = THIS_MODULE, - .read = scanlog_read, - .write = scanlog_write, - .open = scanlog_open, - .release = scanlog_release, - .llseek = noop_llseek, +static const struct proc_ops scanlog_proc_ops = { + .proc_read = scanlog_read, + .proc_write = scanlog_write, + .proc_open = scanlog_open, + .proc_release = scanlog_release, + .proc_lseek = noop_llseek, }; static int __init scanlog_init(void) @@ -176,7 +175,7 @@ static int __init scanlog_init(void) goto err; ent = proc_create("powerpc/rtas/scan-log-dump", 0400, NULL, - &scanlog_fops); + &scanlog_proc_ops); if (!ent) goto err; return 0; diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 36e638d1dfe4..b15f70a1fdfa 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -43,6 +43,13 @@ static inline int pud_bad(pud_t pud) return !pud_present(pud); } +#define pud_leaf pud_leaf +static inline int pud_leaf(pud_t pud) +{ + return pud_present(pud) && + (pud_val(pud) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)); +} + static inline void set_pud(pud_t *pudp, pud_t pud) { *pudp = pud; diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index f66b87314fa2..e43041519edd 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -130,6 +130,13 @@ static inline int pmd_bad(pmd_t pmd) return !pmd_present(pmd); } +#define pmd_leaf pmd_leaf +static inline int pmd_leaf(pmd_t pmd) +{ + return pmd_present(pmd) && + (pmd_val(pmd) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)); +} + static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { *pmdp = pmd; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 287714d51b47..734996784d03 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -163,13 +163,13 @@ config S390 select HAVE_PERF_USER_STACK_DUMP select HAVE_MEMBLOCK_NODE_MAP select HAVE_MEMBLOCK_PHYS_MAP - select HAVE_MMU_GATHER_NO_GATHER + select MMU_GATHER_NO_GATHER select HAVE_MOD_ARCH_SPECIFIC select HAVE_NOP_MCOUNT select HAVE_OPROFILE select HAVE_PCI select HAVE_PERF_EVENTS - select HAVE_RCU_TABLE_FREE + select MMU_GATHER_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 7b03037a8475..137a3920ca36 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -673,6 +673,7 @@ static inline int pud_none(pud_t pud) return pud_val(pud) == _REGION3_ENTRY_EMPTY; } +#define pud_leaf pud_large static inline int pud_large(pud_t pud) { if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) != _REGION_ENTRY_TYPE_R3) @@ -690,6 +691,7 @@ static inline unsigned long pud_pfn(pud_t pud) return (pud_val(pud) & origin_mask) >> PAGE_SHIFT; } +#define pmd_leaf pmd_large static inline int pmd_large(pmd_t pmd) { return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0; diff --git a/arch/sh/mm/alignment.c b/arch/sh/mm/alignment.c index ec2b25302427..fb517b82a87b 100644 --- a/arch/sh/mm/alignment.c +++ b/arch/sh/mm/alignment.c @@ -152,13 +152,12 @@ static ssize_t alignment_proc_write(struct file *file, return count; } -static const struct file_operations alignment_proc_fops = { - .owner = THIS_MODULE, - .open = alignment_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = alignment_proc_write, +static const struct proc_ops alignment_proc_ops = { + .proc_open = alignment_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = alignment_proc_write, }; /* @@ -176,12 +175,12 @@ static int __init alignment_init(void) return -ENOMEM; res = proc_create_data("alignment", S_IWUSR | S_IRUGO, dir, - &alignment_proc_fops, &se_usermode); + &alignment_proc_ops, &se_usermode); if (!res) return -ENOMEM; res = proc_create_data("kernel_alignment", S_IWUSR | S_IRUGO, dir, - &alignment_proc_fops, &se_kernmode_warn); + &alignment_proc_ops, &se_kernmode_warn); if (!res) return -ENOMEM; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index e8c3ea01c12f..c1dd6dd642f4 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -64,8 +64,7 @@ config SPARC64 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_KRETPROBES select HAVE_KPROBES - select HAVE_RCU_TABLE_FREE if SMP - select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE + select MMU_GATHER_RCU_TABLE_FREE if SMP select HAVE_MEMBLOCK_NODE_MAP select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_DYNAMIC_FTRACE diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 34ff3b43afbb..65494c3a420e 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -683,6 +683,7 @@ static inline unsigned long pte_special(pte_t pte) return pte_val(pte) & _PAGE_SPECIAL; } +#define pmd_leaf pmd_large static inline unsigned long pmd_large(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); @@ -867,6 +868,7 @@ static inline unsigned long pud_page_vaddr(pud_t pud) /* only used by the stubbed out hugetlb gup code, should never be called */ #define p4d_page(p4d) NULL +#define pud_leaf pud_large static inline unsigned long pud_large(pud_t pud) { pte_t pte = __pte(pud_val(pud)); diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h index a2f3fa61ee36..6820d357581c 100644 --- a/arch/sparc/include/asm/tlb_64.h +++ b/arch/sparc/include/asm/tlb_64.h @@ -28,6 +28,15 @@ void flush_tlb_pending(void); #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #define tlb_flush(tlb) flush_tlb_pending() +/* + * SPARC64's hardware TLB fill does not use the Linux page-tables + * and therefore we don't need a TLBI when freeing page-table pages. + */ + +#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE +#define tlb_needs_table_invalidate() (false) +#endif + #include <asm-generic/tlb.h> #endif /* _SPARC64_TLB_H */ diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c index a6292f8ed180..bd48575172c3 100644 --- a/arch/sparc/kernel/led.c +++ b/arch/sparc/kernel/led.c @@ -104,13 +104,12 @@ static ssize_t led_proc_write(struct file *file, const char __user *buffer, return count; } -static const struct file_operations led_proc_fops = { - .owner = THIS_MODULE, - .open = led_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = led_proc_write, +static const struct proc_ops led_proc_ops = { + .proc_open = led_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = led_proc_write, }; static struct proc_dir_entry *led; @@ -121,7 +120,7 @@ static int __init led_init(void) { timer_setup(&led_blink_timer, led_blink, 0); - led = proc_create("led", 0, NULL, &led_proc_fops); + led = proc_create("led", 0, NULL, &led_proc_ops); if (!led) return -ENOMEM; diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 0117489e9b30..b80a1d616e4e 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -752,10 +752,9 @@ static ssize_t mconsole_proc_write(struct file *file, return count; } -static const struct file_operations mconsole_proc_fops = { - .owner = THIS_MODULE, - .write = mconsole_proc_write, - .llseek = noop_llseek, +static const struct proc_ops mconsole_proc_ops = { + .proc_write = mconsole_proc_write, + .proc_lseek = noop_llseek, }; static int create_proc_mconsole(void) @@ -765,7 +764,7 @@ static int create_proc_mconsole(void) if (notify_socket == NULL) return 0; - ent = proc_create("mconsole", 0200, NULL, &mconsole_proc_fops); + ent = proc_create("mconsole", 0200, NULL, &mconsole_proc_ops); if (ent == NULL) { printk(KERN_INFO "create_proc_mconsole : proc_create failed\n"); return 0; diff --git a/arch/um/kernel/exitcode.c b/arch/um/kernel/exitcode.c index 369fd844e195..43edc2aa57e4 100644 --- a/arch/um/kernel/exitcode.c +++ b/arch/um/kernel/exitcode.c @@ -55,20 +55,19 @@ static ssize_t exitcode_proc_write(struct file *file, return count; } -static const struct file_operations exitcode_proc_fops = { - .owner = THIS_MODULE, - .open = exitcode_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = exitcode_proc_write, +static const struct proc_ops exitcode_proc_ops = { + .proc_open = exitcode_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = exitcode_proc_write, }; static int make_proc_exitcode(void) { struct proc_dir_entry *ent; - ent = proc_create("exitcode", 0600, NULL, &exitcode_proc_fops); + ent = proc_create("exitcode", 0600, NULL, &exitcode_proc_ops); if (ent == NULL) { printk(KERN_WARNING "make_proc_exitcode : Failed to register " "/proc/exitcode\n"); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 17045e7211bf..56a094182bf5 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -348,13 +348,12 @@ static ssize_t sysemu_proc_write(struct file *file, const char __user *buf, return count; } -static const struct file_operations sysemu_proc_fops = { - .owner = THIS_MODULE, - .open = sysemu_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = sysemu_proc_write, +static const struct proc_ops sysemu_proc_ops = { + .proc_open = sysemu_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = sysemu_proc_write, }; int __init make_proc_sysemu(void) @@ -363,7 +362,7 @@ int __init make_proc_sysemu(void) if (!sysemu_supported) return 0; - ent = proc_create("sysemu", 0600, NULL, &sysemu_proc_fops); + ent = proc_create("sysemu", 0600, NULL, &sysemu_proc_ops); if (ent == NULL) { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 44d279698c0f..beea77046f9b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -120,6 +120,7 @@ config X86 select GENERIC_IRQ_RESERVATION_MODE select GENERIC_IRQ_SHOW select GENERIC_PENDING_IRQ if SMP + select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER @@ -202,7 +203,7 @@ config X86 select HAVE_PCI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_RCU_TABLE_FREE if PARAVIRT + select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c4eab8ed33a3..2e74690b028a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -62,26 +62,10 @@ config EARLY_PRINTK_USB_XDBC config MCSAFE_TEST def_bool n -config X86_PTDUMP_CORE - def_bool n - -config X86_PTDUMP - tristate "Export kernel pagetable layout to userspace via debugfs" - depends on DEBUG_KERNEL - select DEBUG_FS - select X86_PTDUMP_CORE - ---help--- - Say Y here if you want to show the kernel pagetable layout in a - debugfs file. This information is only useful for kernel developers - who are working in architecture specific areas of the kernel. - It is probably not a good idea to enable this feature in a production - kernel. - If in doubt, say "N" - config EFI_PGT_DUMP bool "Dump the EFI pagetable" depends on EFI - select X86_PTDUMP_CORE + select PTDUMP_CORE ---help--- Enable this if you want to dump the EFI page table before enabling virtual mode. This can be used to debug miscellaneous @@ -90,7 +74,7 @@ config EFI_PGT_DUMP config DEBUG_WX bool "Warn on W+X mappings at boot" - select X86_PTDUMP_CORE + select PTDUMP_CORE ---help--- Generate a warning if any W+X mappings are found at boot. diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index ad97dc155195..7e118660bbd9 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -29,8 +29,9 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD]; int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); -void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); -void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user); +void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, + bool user); void ptdump_walk_pgd_level_checkwx(void); void ptdump_walk_user_pgd_level_checkwx(void); @@ -239,6 +240,7 @@ static inline unsigned long pgd_pfn(pgd_t pgd) return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } +#define p4d_leaf p4d_large static inline int p4d_large(p4d_t p4d) { /* No 512 GiB pages yet */ @@ -247,6 +249,7 @@ static inline int p4d_large(p4d_t p4d) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) +#define pmd_leaf pmd_large static inline int pmd_large(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; @@ -874,6 +877,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); } +#define pud_leaf pud_large static inline int pud_large(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) == @@ -885,6 +889,7 @@ static inline int pud_bad(pud_t pud) return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } #else +#define pud_leaf pud_large static inline int pud_large(pud_t pud) { return 0; @@ -1233,6 +1238,7 @@ static inline bool pgdp_maps_userspace(void *__ptr) return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } +#define pgd_leaf pgd_large static inline int pgd_large(pgd_t pgd) { return 0; } #ifdef CONFIG_PAGE_TABLE_ISOLATION diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index f23e7aaff4cd..820082bd6880 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -29,8 +29,8 @@ static inline void tlb_flush(struct mmu_gather *tlb) * shootdown, enablement code for several hypervisors overrides * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing * a hypercall. To keep software pagetable walkers safe in this case we - * switch to RCU based table free (HAVE_RCU_TABLE_FREE). See the comment - * below 'ifdef CONFIG_HAVE_RCU_TABLE_FREE' in include/asm-generic/tlb.h + * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment + * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h * for more details. */ static inline void __tlb_remove_table(void *table) diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index da532f656a7b..a5c506f6da7f 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -396,15 +396,16 @@ static int mtrr_open(struct inode *inode, struct file *file) return single_open(file, mtrr_seq_show, NULL); } -static const struct file_operations mtrr_fops = { - .owner = THIS_MODULE, - .open = mtrr_open, - .read = seq_read, - .llseek = seq_lseek, - .write = mtrr_write, - .unlocked_ioctl = mtrr_ioctl, - .compat_ioctl = mtrr_ioctl, - .release = mtrr_close, +static const struct proc_ops mtrr_proc_ops = { + .proc_open = mtrr_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = mtrr_write, + .proc_ioctl = mtrr_ioctl, +#ifdef CONFIG_COMPAT + .proc_compat_ioctl = mtrr_ioctl, +#endif + .proc_release = mtrr_close, }; static int __init mtrr_if_init(void) @@ -417,7 +418,7 @@ static int __init mtrr_if_init(void) (!cpu_has(c, X86_FEATURE_CENTAUR_MCR))) return -ENODEV; - proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops); + proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_proc_ops); return 0; } arch_initcall(mtrr_if_init); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 98aecb14fbcc..98f7c6fa2eaa 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -28,8 +28,8 @@ CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o -obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o +obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o +obj-$(CONFIG_PTDUMP_DEBUGFS) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index 39001a401eff..4a3b62f780b4 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -7,7 +7,7 @@ static int ptdump_show(struct seq_file *m, void *v) { - ptdump_walk_pgd_level_debugfs(m, NULL, false); + ptdump_walk_pgd_level_debugfs(m, &init_mm, false); return 0; } @@ -15,11 +15,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump); static int ptdump_curknl_show(struct seq_file *m, void *v) { - if (current->mm->pgd) { - down_read(¤t->mm->mmap_sem); - ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false); - up_read(¤t->mm->mmap_sem); - } + if (current->mm->pgd) + ptdump_walk_pgd_level_debugfs(m, current->mm, false); return 0; } @@ -28,11 +25,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curknl); #ifdef CONFIG_PAGE_TABLE_ISOLATION static int ptdump_curusr_show(struct seq_file *m, void *v) { - if (current->mm->pgd) { - down_read(¤t->mm->mmap_sem); - ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true); - up_read(¤t->mm->mmap_sem); - } + if (current->mm->pgd) + ptdump_walk_pgd_level_debugfs(m, current->mm, true); return 0; } @@ -43,7 +37,7 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curusr); static int ptdump_efi_show(struct seq_file *m, void *v) { if (efi_mm.pgd) - ptdump_walk_pgd_level_debugfs(m, efi_mm.pgd, false); + ptdump_walk_pgd_level_debugfs(m, &efi_mm, false); return 0; } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index ab67822fd2f4..64229dad7eab 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -16,6 +16,7 @@ #include <linux/seq_file.h> #include <linux/highmem.h> #include <linux/pci.h> +#include <linux/ptdump.h> #include <asm/e820/types.h> #include <asm/pgtable.h> @@ -26,16 +27,18 @@ * when a "break" in the continuity is found. */ struct pg_state { + struct ptdump_state ptdump; int level; - pgprot_t current_prot; + pgprotval_t current_prot; pgprotval_t effective_prot; + pgprotval_t prot_levels[5]; unsigned long start_address; - unsigned long current_address; const struct addr_marker *marker; unsigned long lines; bool to_dmesg; bool check_wx; unsigned long wx_pages; + struct seq_file *seq; }; struct addr_marker { @@ -174,11 +177,10 @@ static struct addr_marker address_markers[] = { /* * Print a readable form of a pgprot_t to the seq_file */ -static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) +static void printk_prot(struct seq_file *m, pgprotval_t pr, int level, bool dmsg) { - pgprotval_t pr = pgprot_val(prot); static const char * const level_name[] = - { "cr3", "pgd", "p4d", "pud", "pmd", "pte" }; + { "pgd", "p4d", "pud", "pmd", "pte" }; if (!(pr & _PAGE_PRESENT)) { /* Not present */ @@ -202,12 +204,12 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, " "); /* Bit 7 has a different meaning on level 3 vs 4 */ - if (level <= 4 && pr & _PAGE_PSE) + if (level <= 3 && pr & _PAGE_PSE) pt_dump_cont_printf(m, dmsg, "PSE "); else pt_dump_cont_printf(m, dmsg, " "); - if ((level == 5 && pr & _PAGE_PAT) || - ((level == 4 || level == 3) && pr & _PAGE_PAT_LARGE)) + if ((level == 4 && pr & _PAGE_PAT) || + ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE)) pt_dump_cont_printf(m, dmsg, "PAT "); else pt_dump_cont_printf(m, dmsg, " "); @@ -223,24 +225,11 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]); } -/* - * On 64 bits, sign-extend the 48 bit address to 64 bit - */ -static unsigned long normalize_addr(unsigned long u) -{ - int shift; - if (!IS_ENABLED(CONFIG_X86_64)) - return u; - - shift = 64 - (__VIRTUAL_MASK_SHIFT + 1); - return (signed long)(u << shift) >> shift; -} - -static void note_wx(struct pg_state *st) +static void note_wx(struct pg_state *st, unsigned long addr) { unsigned long npages; - npages = (st->current_address - st->start_address) / PAGE_SIZE; + npages = (addr - st->start_address) / PAGE_SIZE; #ifdef CONFIG_PCI_BIOS /* @@ -248,7 +237,7 @@ static void note_wx(struct pg_state *st) * Inform about it, but avoid the warning. */ if (pcibios_enabled && st->start_address >= PAGE_OFFSET + BIOS_BEGIN && - st->current_address <= PAGE_OFFSET + BIOS_END) { + addr <= PAGE_OFFSET + BIOS_END) { pr_warn_once("x86/mm: PCI BIOS W+X mapping %lu pages\n", npages); return; } @@ -260,27 +249,47 @@ static void note_wx(struct pg_state *st) (void *)st->start_address); } +static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2) +{ + return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) | + ((prot1 | prot2) & _PAGE_NX); +} + /* * This function gets called on a break in a continuous series * of PTE entries; the next one is different so we need to * print what we collected so far. */ -static void note_page(struct seq_file *m, struct pg_state *st, - pgprot_t new_prot, pgprotval_t new_eff, int level) +static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, + unsigned long val) { - pgprotval_t prot, cur, eff; + struct pg_state *st = container_of(pt_st, struct pg_state, ptdump); + pgprotval_t new_prot, new_eff; + pgprotval_t cur, eff; static const char units[] = "BKMGTPE"; + struct seq_file *m = st->seq; + + new_prot = val & PTE_FLAGS_MASK; + + if (level > 0) { + new_eff = effective_prot(st->prot_levels[level - 1], + new_prot); + } else { + new_eff = new_prot; + } + + if (level >= 0) + st->prot_levels[level] = new_eff; /* * If we have a "break" in the series, we need to flush the state that * we have now. "break" is either changing perms, levels or * address space marker. */ - prot = pgprot_val(new_prot); - cur = pgprot_val(st->current_prot); + cur = st->current_prot; eff = st->effective_prot; - if (!st->level) { + if (st->level == -1) { /* First entry */ st->current_prot = new_prot; st->effective_prot = new_eff; @@ -289,14 +298,14 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); - } else if (prot != cur || new_eff != eff || level != st->level || - st->current_address >= st->marker[1].start_address) { + } else if (new_prot != cur || new_eff != eff || level != st->level || + addr >= st->marker[1].start_address) { const char *unit = units; unsigned long delta; int width = sizeof(unsigned long) * 2; if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX)) - note_wx(st); + note_wx(st, addr); /* * Now print the actual finished series @@ -306,9 +315,9 @@ static void note_page(struct seq_file *m, struct pg_state *st, pt_dump_seq_printf(m, st->to_dmesg, "0x%0*lx-0x%0*lx ", width, st->start_address, - width, st->current_address); + width, addr); - delta = st->current_address - st->start_address; + delta = addr - st->start_address; while (!(delta & 1023) && unit[1]) { delta >>= 10; unit++; @@ -325,7 +334,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, * such as the start of vmalloc space etc. * This helps in the interpretation. */ - if (st->current_address >= st->marker[1].start_address) { + if (addr >= st->marker[1].start_address) { if (st->marker->max_lines && st->lines > st->marker->max_lines) { unsigned long nskip = @@ -341,222 +350,45 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->marker->name); } - st->start_address = st->current_address; + st->start_address = addr; st->current_prot = new_prot; st->effective_prot = new_eff; st->level = level; } } -static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2) -{ - return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) | - ((prot1 | prot2) & _PAGE_NX); -} - -static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, - pgprotval_t eff_in, unsigned long P) -{ - int i; - pte_t *pte; - pgprotval_t prot, eff; - - for (i = 0; i < PTRS_PER_PTE; i++) { - st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); - pte = pte_offset_map(&addr, st->current_address); - prot = pte_flags(*pte); - eff = effective_prot(eff_in, prot); - note_page(m, st, __pgprot(prot), eff, 5); - pte_unmap(pte); - } -} -#ifdef CONFIG_KASAN - -/* - * This is an optimization for KASAN=y case. Since all kasan page tables - * eventually point to the kasan_early_shadow_page we could call note_page() - * right away without walking through lower level page tables. This saves - * us dozens of seconds (minutes for 5-level config) while checking for - * W+X mapping or reading kernel_page_tables debugfs file. - */ -static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, - void *pt) -{ - if (__pa(pt) == __pa(kasan_early_shadow_pmd) || - (pgtable_l5_enabled() && - __pa(pt) == __pa(kasan_early_shadow_p4d)) || - __pa(pt) == __pa(kasan_early_shadow_pud)) { - pgprotval_t prot = pte_flags(kasan_early_shadow_pte[0]); - note_page(m, st, __pgprot(prot), 0, 5); - return true; - } - return false; -} -#else -static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, - void *pt) -{ - return false; -} -#endif - -#if PTRS_PER_PMD > 1 - -static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, - pgprotval_t eff_in, unsigned long P) -{ - int i; - pmd_t *start, *pmd_start; - pgprotval_t prot, eff; - - pmd_start = start = (pmd_t *)pud_page_vaddr(addr); - for (i = 0; i < PTRS_PER_PMD; i++) { - st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); - if (!pmd_none(*start)) { - prot = pmd_flags(*start); - eff = effective_prot(eff_in, prot); - if (pmd_large(*start) || !pmd_present(*start)) { - note_page(m, st, __pgprot(prot), eff, 4); - } else if (!kasan_page_table(m, st, pmd_start)) { - walk_pte_level(m, st, *start, eff, - P + i * PMD_LEVEL_MULT); - } - } else - note_page(m, st, __pgprot(0), 0, 4); - start++; - } -} - -#else -#define walk_pmd_level(m,s,a,e,p) walk_pte_level(m,s,__pmd(pud_val(a)),e,p) -#define pud_large(a) pmd_large(__pmd(pud_val(a))) -#define pud_none(a) pmd_none(__pmd(pud_val(a))) -#endif - -#if PTRS_PER_PUD > 1 - -static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, - pgprotval_t eff_in, unsigned long P) -{ - int i; - pud_t *start, *pud_start; - pgprotval_t prot, eff; - - pud_start = start = (pud_t *)p4d_page_vaddr(addr); - - for (i = 0; i < PTRS_PER_PUD; i++) { - st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); - if (!pud_none(*start)) { - prot = pud_flags(*start); - eff = effective_prot(eff_in, prot); - if (pud_large(*start) || !pud_present(*start)) { - note_page(m, st, __pgprot(prot), eff, 3); - } else if (!kasan_page_table(m, st, pud_start)) { - walk_pmd_level(m, st, *start, eff, - P + i * PUD_LEVEL_MULT); - } - } else - note_page(m, st, __pgprot(0), 0, 3); - - start++; - } -} - -#else -#define walk_pud_level(m,s,a,e,p) walk_pmd_level(m,s,__pud(p4d_val(a)),e,p) -#define p4d_large(a) pud_large(__pud(p4d_val(a))) -#define p4d_none(a) pud_none(__pud(p4d_val(a))) -#endif - -static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, - pgprotval_t eff_in, unsigned long P) -{ - int i; - p4d_t *start, *p4d_start; - pgprotval_t prot, eff; - - if (PTRS_PER_P4D == 1) - return walk_pud_level(m, st, __p4d(pgd_val(addr)), eff_in, P); - - p4d_start = start = (p4d_t *)pgd_page_vaddr(addr); - - for (i = 0; i < PTRS_PER_P4D; i++) { - st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT); - if (!p4d_none(*start)) { - prot = p4d_flags(*start); - eff = effective_prot(eff_in, prot); - if (p4d_large(*start) || !p4d_present(*start)) { - note_page(m, st, __pgprot(prot), eff, 2); - } else if (!kasan_page_table(m, st, p4d_start)) { - walk_pud_level(m, st, *start, eff, - P + i * P4D_LEVEL_MULT); - } - } else - note_page(m, st, __pgprot(0), 0, 2); - - start++; - } -} - -#define pgd_large(a) (pgtable_l5_enabled() ? pgd_large(a) : p4d_large(__p4d(pgd_val(a)))) -#define pgd_none(a) (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a)))) - -static inline bool is_hypervisor_range(int idx) -{ -#ifdef CONFIG_X86_64 - /* - * A hole in the beginning of kernel address space reserved - * for a hypervisor. - */ - return (idx >= pgd_index(GUARD_HOLE_BASE_ADDR)) && - (idx < pgd_index(GUARD_HOLE_END_ADDR)); -#else - return false; -#endif -} - -static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, +static void ptdump_walk_pgd_level_core(struct seq_file *m, + struct mm_struct *mm, pgd_t *pgd, bool checkwx, bool dmesg) { - pgd_t *start = INIT_PGD; - pgprotval_t prot, eff; - int i; - struct pg_state st = {}; - - if (pgd) { - start = pgd; - st.to_dmesg = dmesg; - } + const struct ptdump_range ptdump_ranges[] = { +#ifdef CONFIG_X86_64 - st.check_wx = checkwx; - if (checkwx) - st.wx_pages = 0; +#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1)) +#define normalize_addr(u) ((signed long)((u) << normalize_addr_shift) >> \ + normalize_addr_shift) - for (i = 0; i < PTRS_PER_PGD; i++) { - st.current_address = normalize_addr(i * PGD_LEVEL_MULT); - if (!pgd_none(*start) && !is_hypervisor_range(i)) { - prot = pgd_flags(*start); -#ifdef CONFIG_X86_PAE - eff = _PAGE_USER | _PAGE_RW; + {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2}, + {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL}, #else - eff = prot; + {0, ~0UL}, #endif - if (pgd_large(*start) || !pgd_present(*start)) { - note_page(m, &st, __pgprot(prot), eff, 1); - } else { - walk_p4d_level(m, &st, *start, eff, - i * PGD_LEVEL_MULT); - } - } else - note_page(m, &st, __pgprot(0), 0, 1); + {0, 0} +}; - cond_resched(); - start++; - } + struct pg_state st = { + .ptdump = { + .note_page = note_page, + .range = ptdump_ranges + }, + .level = -1, + .to_dmesg = dmesg, + .check_wx = checkwx, + .seq = m + }; + + ptdump_walk_pgd(&st.ptdump, mm, pgd); - /* Flush out the last page */ - st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT); - note_page(m, &st, __pgprot(0), 0, 0); if (!checkwx) return; if (st.wx_pages) @@ -566,18 +398,20 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n"); } -void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) +void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm) { - ptdump_walk_pgd_level_core(m, pgd, false, true); + ptdump_walk_pgd_level_core(m, mm, mm->pgd, false, true); } -void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user) +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, + bool user) { + pgd_t *pgd = mm->pgd; #ifdef CONFIG_PAGE_TABLE_ISOLATION if (user && boot_cpu_has(X86_FEATURE_PTI)) pgd = kernel_to_user_pgdp(pgd); #endif - ptdump_walk_pgd_level_core(m, pgd, false, false); + ptdump_walk_pgd_level_core(m, mm, pgd, false, false); } EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs); @@ -592,13 +426,13 @@ void ptdump_walk_user_pgd_level_checkwx(void) pr_info("x86/mm: Checking user space page tables\n"); pgd = kernel_to_user_pgdp(pgd); - ptdump_walk_pgd_level_core(NULL, pgd, true, false); + ptdump_walk_pgd_level_core(NULL, &init_mm, pgd, true, false); #endif } void ptdump_walk_pgd_level_checkwx(void) { - ptdump_walk_pgd_level_core(NULL, NULL, true, false); + ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false); } static int __init pt_dump_init(void) diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 71dddd1620f9..081d466002c9 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -49,7 +49,7 @@ void efi_sync_low_kernel_mappings(void) {} void __init efi_dump_pagetable(void) { #ifdef CONFIG_EFI_PGT_DUMP - ptdump_walk_pgd_level(NULL, swapper_pg_dir); + ptdump_walk_pgd_level(NULL, &init_mm); #endif } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index e2accfe636bd..fa8506e76bbe 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -471,9 +471,9 @@ void __init efi_dump_pagetable(void) { #ifdef CONFIG_EFI_PGT_DUMP if (efi_have_uv1_memmap()) - ptdump_walk_pgd_level(NULL, swapper_pg_dir); + ptdump_walk_pgd_level(NULL, &init_mm); else - ptdump_walk_pgd_level(NULL, efi_mm.pgd); + ptdump_walk_pgd_level(NULL, &efi_mm); #endif } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 5f0a96bf27a1..1fd321f37f1b 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1668,12 +1668,12 @@ static int tunables_open(struct inode *inode, struct file *file) return 0; } -static const struct file_operations proc_uv_ptc_operations = { - .open = ptc_proc_open, - .read = seq_read, - .write = ptc_proc_write, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops uv_ptc_proc_ops = { + .proc_open = ptc_proc_open, + .proc_read = seq_read, + .proc_write = ptc_proc_write, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static const struct file_operations tunables_fops = { @@ -1691,7 +1691,7 @@ static int __init uv_ptc_init(void) return 0; proc_uv_ptc = proc_create(UV_PTC_BASENAME, 0444, NULL, - &proc_uv_ptc_operations); + &uv_ptc_proc_ops); if (!proc_uv_ptc) { pr_err("unable to create %s proc entry\n", UV_PTC_BASENAME); diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index f9cd45860bee..833109880165 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -251,10 +251,10 @@ out_free: return err; } -static const struct file_operations fops = { - .read = proc_read_simdisk, - .write = proc_write_simdisk, - .llseek = default_llseek, +static const struct proc_ops simdisk_proc_ops = { + .proc_read = proc_read_simdisk, + .proc_write = proc_write_simdisk, + .proc_lseek = default_llseek, }; static int __init simdisk_setup(struct simdisk *dev, int which, @@ -290,7 +290,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which, set_capacity(dev->gd, 0); add_disk(dev->gd); - dev->procfile = proc_create_data(tmp, 0644, procdir, &fops, dev); + dev->procfile = proc_create_data(tmp, 0644, procdir, &simdisk_proc_ops, dev); return 0; out_alloc_disk: diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 3d8e53010cda..439367a8e95c 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -171,7 +171,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) sa->salg_name[sizeof(sa->salg_name) + addr_len - sizeof(*sa) - 1] = 0; type = alg_get_type(sa->salg_type); - if (IS_ERR(type) && PTR_ERR(type) == -ENOENT) { + if (PTR_ERR(type) == -ENOENT) { request_module("algif-%s", sa->salg_type); type = alg_get_type(sa->salg_type); } diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 15cc7d5a6185..111a407dcc77 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -1202,13 +1202,12 @@ static int acpi_battery_alarm_proc_open(struct inode *inode, struct file *file) return single_open(file, acpi_battery_alarm_proc_show, PDE_DATA(inode)); } -static const struct file_operations acpi_battery_alarm_fops = { - .owner = THIS_MODULE, - .open = acpi_battery_alarm_proc_open, - .read = seq_read, - .write = acpi_battery_write_alarm, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops acpi_battery_alarm_proc_ops = { + .proc_open = acpi_battery_alarm_proc_open, + .proc_read = seq_read, + .proc_write = acpi_battery_write_alarm, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; static int acpi_battery_add_fs(struct acpi_device *device) @@ -1228,7 +1227,7 @@ static int acpi_battery_add_fs(struct acpi_device *device) acpi_battery_state_proc_show, acpi_driver_data(device))) return -ENODEV; if (!proc_create_data("alarm", S_IFREG | S_IRUGO | S_IWUSR, - acpi_device_dir(device), &acpi_battery_alarm_fops, + acpi_device_dir(device), &acpi_battery_alarm_proc_ops, acpi_driver_data(device))) return -ENODEV; return 0; diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c index 652f19e6c541..0e62ef265ce4 100644 --- a/drivers/acpi/proc.c +++ b/drivers/acpi/proc.c @@ -136,18 +136,17 @@ acpi_system_wakeup_device_open_fs(struct inode *inode, struct file *file) PDE_DATA(inode)); } -static const struct file_operations acpi_system_wakeup_device_fops = { - .owner = THIS_MODULE, - .open = acpi_system_wakeup_device_open_fs, - .read = seq_read, - .write = acpi_system_write_wakeup_device, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops acpi_system_wakeup_device_proc_ops = { + .proc_open = acpi_system_wakeup_device_open_fs, + .proc_read = seq_read, + .proc_write = acpi_system_write_wakeup_device, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; void __init acpi_sleep_proc_init(void) { /* 'wakeup device' [R/W] */ proc_create("wakeup", S_IFREG | S_IRUGO | S_IWUSR, - acpi_root_dir, &acpi_system_wakeup_device_fops); + acpi_root_dir, &acpi_system_wakeup_device_proc_ops); } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 915650bf519f..6d3448895382 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1462,7 +1462,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) iort_dma_setup(dev, &dma_addr, &size); iommu = iort_iommu_configure(dev); - if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER) + if (PTR_ERR(iommu) == -EPROBE_DEFER) return -EPROBE_DEFER; arch_setup_dma_ops(dev, dma_addr, size, diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 15659306ad69..b9f474c11393 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -376,7 +376,6 @@ static ssize_t valid_zones_show(struct device *dev, struct memory_block *mem = to_memory_block(dev); unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; - unsigned long valid_start_pfn, valid_end_pfn; struct zone *default_zone; int nid; @@ -389,11 +388,11 @@ static ssize_t valid_zones_show(struct device *dev, * The block contains more than one zone can not be offlined. * This can happen e.g. for ZONE_DMA and ZONE_DMA32 */ - if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, - &valid_start_pfn, &valid_end_pfn)) + default_zone = test_pages_in_a_zone(start_pfn, + start_pfn + nr_pages); + if (!default_zone) return sprintf(buf, "none\n"); - start_pfn = valid_start_pfn; - strcat(buf, page_zone(pfn_to_page(start_pfn))->name); + strcat(buf, default_zone->name); goto out; } diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index ae8d4bc532b0..16510795e377 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -263,34 +263,34 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, } /* The following macro should only be used with TYPE = {uint, ulong, bool}. */ -#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY) \ -static ssize_t \ -nullb_device_##NAME##_show(struct config_item *item, char *page) \ -{ \ - return nullb_device_##TYPE##_attr_show( \ - to_nullb_device(item)->NAME, page); \ -} \ -static ssize_t \ -nullb_device_##NAME##_store(struct config_item *item, const char *page, \ - size_t count) \ -{ \ - int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY; \ - struct nullb_device *dev = to_nullb_device(item); \ - TYPE new_value; \ - int ret; \ - \ - ret = nullb_device_##TYPE##_attr_store(&new_value, page, count); \ - if (ret < 0) \ - return ret; \ - if (apply_fn) \ - ret = apply_fn(dev, new_value); \ - else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) \ - ret = -EBUSY; \ - if (ret < 0) \ - return ret; \ - dev->NAME = new_value; \ - return count; \ -} \ +#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY) \ +static ssize_t \ +nullb_device_##NAME##_show(struct config_item *item, char *page) \ +{ \ + return nullb_device_##TYPE##_attr_show( \ + to_nullb_device(item)->NAME, page); \ +} \ +static ssize_t \ +nullb_device_##NAME##_store(struct config_item *item, const char *page, \ + size_t count) \ +{ \ + int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;\ + struct nullb_device *dev = to_nullb_device(item); \ + TYPE uninitialized_var(new_value); \ + int ret; \ + \ + ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);\ + if (ret < 0) \ + return ret; \ + if (apply_fn) \ + ret = apply_fn(dev, new_value); \ + else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) \ + ret = -EBUSY; \ + if (ret < 0) \ + return ret; \ + dev->NAME = new_value; \ + return count; \ +} \ CONFIGFS_ATTR(nullb_device_, NAME); static int nullb_apply_submit_queues(struct nullb_device *dev, diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c index d2a5791eb49f..cbf5eaea662c 100644 --- a/drivers/char/hw_random/bcm2835-rng.c +++ b/drivers/char/hw_random/bcm2835-rng.c @@ -157,7 +157,7 @@ static int bcm2835_rng_probe(struct platform_device *pdev) /* Clock is optional on most platforms */ priv->clk = devm_clk_get(dev, NULL); - if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER) + if (PTR_ERR(priv->clk) == -EPROBE_DEFER) return -EPROBE_DEFER; priv->rng.name = pdev->name; diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c index 0ed07d16ec8e..65952393e1bb 100644 --- a/drivers/char/hw_random/omap-rng.c +++ b/drivers/char/hw_random/omap-rng.c @@ -476,7 +476,7 @@ static int omap_rng_probe(struct platform_device *pdev) } priv->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER) + if (PTR_ERR(priv->clk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(priv->clk)) { ret = clk_prepare_enable(priv->clk); @@ -488,7 +488,7 @@ static int omap_rng_probe(struct platform_device *pdev) } priv->clk_reg = devm_clk_get(&pdev->dev, "reg"); - if (IS_ERR(priv->clk_reg) && PTR_ERR(priv->clk_reg) == -EPROBE_DEFER) + if (PTR_ERR(priv->clk_reg) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(priv->clk_reg)) { ret = clk_prepare_enable(priv->clk_reg); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index d529ad67805c..f0f2b599fd7e 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -429,7 +429,7 @@ static void clk_core_fill_parent_index(struct clk_core *core, u8 index) parent = ERR_PTR(-EPROBE_DEFER); } else { parent = clk_core_get(core, index); - if (IS_ERR(parent) && PTR_ERR(parent) == -ENOENT && entry->name) + if (PTR_ERR(parent) == -ENOENT && entry->name) parent = clk_core_lookup(entry->name); } diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index e3850f04f676..157c959311ea 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -750,7 +750,7 @@ static int mv_xor_v2_probe(struct platform_device *pdev) } xor_dev->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { + if (PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { ret = EPROBE_DEFER; goto disable_reg_clk; } diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 899b803842bb..9dda2602c862 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -27,7 +27,7 @@ extern u64 efi_system_table; -#ifdef CONFIG_ARM64_PTDUMP_DEBUGFS +#if defined(CONFIG_PTDUMP_DEBUGFS) && defined(CONFIG_ARM64) #include <asm/ptdump.h> static struct ptdump_info efi_ptdump_info = { diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index 4421be09b960..72b6001c56ef 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -308,7 +308,7 @@ devm_gpiod_get_array_optional(struct device *dev, const char *con_id, struct gpio_descs *descs; descs = devm_gpiod_get_array(dev, con_id, flags); - if (IS_ERR(descs) && (PTR_ERR(descs) == -ENOENT)) + if (PTR_ERR(descs) == -ENOENT) return NULL; return descs; diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 1b3f217a35e2..c6d30f73df07 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -484,24 +484,24 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id, break; } - if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) { + if (PTR_ERR(desc) == -ENOENT) { /* Special handling for SPI GPIOs if used */ desc = of_find_spi_gpio(dev, con_id, &of_flags); } - if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) { + if (PTR_ERR(desc) == -ENOENT) { /* This quirk looks up flags and all */ desc = of_find_spi_cs_gpio(dev, con_id, idx, flags); if (!IS_ERR(desc)) return desc; } - if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) { + if (PTR_ERR(desc) == -ENOENT) { /* Special handling for regulator GPIOs if used */ desc = of_find_regulator_gpio(dev, con_id, &of_flags); } - if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) + if (PTR_ERR(desc) == -ENOENT) desc = of_find_arizona_gpio(dev, con_id, &of_flags); if (IS_ERR(desc)) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 99ac27a72e28..753283486037 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -5039,7 +5039,7 @@ struct gpio_descs *__must_check gpiod_get_array_optional(struct device *dev, struct gpio_descs *descs; descs = gpiod_get_array(dev, con_id, flags); - if (IS_ERR(descs) && (PTR_ERR(descs) == -ENOENT)) + if (PTR_ERR(descs) == -ENOENT) return NULL; return descs; diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index 17583bf8c2dc..d4c83009d625 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -595,19 +595,18 @@ static int i8k_open_fs(struct inode *inode, struct file *file) return single_open(file, i8k_proc_show, NULL); } -static const struct file_operations i8k_fops = { - .owner = THIS_MODULE, - .open = i8k_open_fs, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .unlocked_ioctl = i8k_ioctl, +static const struct proc_ops i8k_proc_ops = { + .proc_open = i8k_open_fs, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_ioctl = i8k_ioctl, }; static void __init i8k_init_procfs(void) { /* Register the proc entry */ - proc_create("i8k", 0, NULL, &i8k_fops); + proc_create("i8k", 0, NULL, &i8k_proc_ops); } static void __exit i8k_exit_procfs(void) diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index a5a95ea5b81a..febb7c7ea72b 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -901,14 +901,13 @@ mv64xxx_i2c_probe(struct platform_device *pd) /* Not all platforms have clocks */ drv_data->clk = devm_clk_get(&pd->dev, NULL); - if (IS_ERR(drv_data->clk) && PTR_ERR(drv_data->clk) == -EPROBE_DEFER) + if (PTR_ERR(drv_data->clk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(drv_data->clk)) clk_prepare_enable(drv_data->clk); drv_data->reg_clk = devm_clk_get(&pd->dev, "reg"); - if (IS_ERR(drv_data->reg_clk) && - PTR_ERR(drv_data->reg_clk) == -EPROBE_DEFER) + if (PTR_ERR(drv_data->reg_clk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(drv_data->reg_clk)) clk_prepare_enable(drv_data->reg_clk); diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c index 39762f0611b1..86026798b4f7 100644 --- a/drivers/i2c/busses/i2c-synquacer.c +++ b/drivers/i2c/busses/i2c-synquacer.c @@ -553,7 +553,7 @@ static int synquacer_i2c_probe(struct platform_device *pdev) &i2c->pclkrate); i2c->pclk = devm_clk_get(&pdev->dev, "pclk"); - if (IS_ERR(i2c->pclk) && PTR_ERR(i2c->pclk) == -EPROBE_DEFER) + if (PTR_ERR(i2c->pclk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR_OR_NULL(i2c->pclk)) { dev_dbg(&pdev->dev, "clock source %p\n", i2c->pclk); diff --git a/drivers/ide/ide-proc.c b/drivers/ide/ide-proc.c index e73016cbd406..15c17f3781ee 100644 --- a/drivers/ide/ide-proc.c +++ b/drivers/ide/ide-proc.c @@ -381,13 +381,12 @@ parse_error: return -EINVAL; } -static const struct file_operations ide_settings_proc_fops = { - .owner = THIS_MODULE, - .open = ide_settings_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = ide_settings_proc_write, +static const struct proc_ops ide_settings_proc_ops = { + .proc_open = ide_settings_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = ide_settings_proc_write, }; int ide_capacity_proc_show(struct seq_file *m, void *v) @@ -546,7 +545,7 @@ void ide_proc_port_register_devices(ide_hwif_t *hwif) if (drive->proc) { ide_add_proc_entries(drive->proc, generic_drive_entries, drive); proc_create_data("settings", S_IFREG|S_IRUSR|S_IWUSR, - drive->proc, &ide_settings_proc_fops, + drive->proc, &ide_settings_proc_ops, drive); } sprintf(name, "ide%d/%s", (drive->name[2]-'a')/2, drive->name); @@ -615,7 +614,7 @@ static int ide_drivers_show(struct seq_file *s, void *p) return 0; } -DEFINE_SHOW_ATTRIBUTE(ide_drivers); +DEFINE_PROC_SHOW_ATTRIBUTE(ide_drivers); void proc_ide_create(void) { @@ -624,7 +623,7 @@ void proc_ide_create(void) if (!proc_ide_root) return; - proc_create("drivers", 0, proc_ide_root, &ide_drivers_fops); + proc_create("drivers", 0, proc_ide_root, &ide_drivers_proc_ops); } void proc_ide_destroy(void) diff --git a/drivers/input/input.c b/drivers/input/input.c index ee6c3234df36..fce43e62dd45 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1216,13 +1216,12 @@ static int input_proc_devices_open(struct inode *inode, struct file *file) return seq_open(file, &input_devices_seq_ops); } -static const struct file_operations input_devices_fileops = { - .owner = THIS_MODULE, - .open = input_proc_devices_open, - .poll = input_proc_devices_poll, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops input_devices_proc_ops = { + .proc_open = input_proc_devices_open, + .proc_poll = input_proc_devices_poll, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static void *input_handlers_seq_start(struct seq_file *seq, loff_t *pos) @@ -1280,12 +1279,11 @@ static int input_proc_handlers_open(struct inode *inode, struct file *file) return seq_open(file, &input_handlers_seq_ops); } -static const struct file_operations input_handlers_fileops = { - .owner = THIS_MODULE, - .open = input_proc_handlers_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops input_handlers_proc_ops = { + .proc_open = input_proc_handlers_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static int __init input_proc_init(void) @@ -1297,12 +1295,12 @@ static int __init input_proc_init(void) return -ENOMEM; entry = proc_create("devices", 0, proc_bus_input_dir, - &input_devices_fileops); + &input_devices_proc_ops); if (!entry) goto fail1; entry = proc_create("handlers", 0, proc_bus_input_dir, - &input_handlers_fileops); + &input_handlers_proc_ops); if (!entry) goto fail2; diff --git a/drivers/isdn/capi/kcapi_proc.c b/drivers/isdn/capi/kcapi_proc.c index eadbe59b3753..b5ed4ea145cb 100644 --- a/drivers/isdn/capi/kcapi_proc.c +++ b/drivers/isdn/capi/kcapi_proc.c @@ -199,8 +199,8 @@ static ssize_t empty_read(struct file *file, char __user *buf, return 0; } -static const struct file_operations empty_fops = { - .read = empty_read, +static const struct proc_ops empty_proc_ops = { + .proc_read = empty_read, }; // --------------------------------------------------------------------------- @@ -214,7 +214,7 @@ kcapi_proc_init(void) proc_create_seq("capi/contrstats", 0, NULL, &seq_contrstats_ops); proc_create_seq("capi/applications", 0, NULL, &seq_applications_ops); proc_create_seq("capi/applstats", 0, NULL, &seq_applstats_ops); - proc_create("capi/driver", 0, NULL, &empty_fops); + proc_create("capi/driver", 0, NULL, &empty_proc_ops); } void diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index 21d532a78fa4..d38fb78a3b23 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -212,7 +212,7 @@ static int pmu_info_proc_show(struct seq_file *m, void *v); static int pmu_irqstats_proc_show(struct seq_file *m, void *v); static int pmu_battery_proc_show(struct seq_file *m, void *v); static void pmu_pass_intr(unsigned char *data, int len); -static const struct file_operations pmu_options_proc_fops; +static const struct proc_ops pmu_options_proc_ops; #ifdef CONFIG_ADB const struct adb_driver via_pmu_driver = { @@ -573,7 +573,7 @@ static int __init via_pmu_dev_init(void) proc_pmu_irqstats = proc_create_single("interrupts", 0, proc_pmu_root, pmu_irqstats_proc_show); proc_pmu_options = proc_create("options", 0600, proc_pmu_root, - &pmu_options_proc_fops); + &pmu_options_proc_ops); } return 0; } @@ -974,13 +974,12 @@ static ssize_t pmu_options_proc_write(struct file *file, return fcount; } -static const struct file_operations pmu_options_proc_fops = { - .owner = THIS_MODULE, - .open = pmu_options_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = pmu_options_proc_write, +static const struct proc_ops pmu_options_proc_ops = { + .proc_open = pmu_options_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = pmu_options_proc_write, }; #ifdef CONFIG_ADB diff --git a/drivers/md/md.c b/drivers/md/md.c index 4824d50526fa..469f551863be 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8279,13 +8279,12 @@ static __poll_t mdstat_poll(struct file *filp, poll_table *wait) return mask; } -static const struct file_operations md_seq_fops = { - .owner = THIS_MODULE, - .open = md_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, - .poll = mdstat_poll, +static const struct proc_ops mdstat_proc_ops = { + .proc_open = md_seq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, + .proc_poll = mdstat_poll, }; int register_md_personality(struct md_personality *p) @@ -9454,7 +9453,7 @@ static void md_geninit(void) { pr_debug("md: sizeof(mdp_super_t) = %d\n", (int)sizeof(mdp_super_t)); - proc_create("mdstat", S_IRUGO, NULL, &md_seq_fops); + proc_create("mdstat", S_IRUGO, NULL, &mdstat_proc_ops); } static int __init md_init(void) diff --git a/drivers/misc/sgi-gru/gruprocfs.c b/drivers/misc/sgi-gru/gruprocfs.c index 2817f4751306..97b8b38ab47d 100644 --- a/drivers/misc/sgi-gru/gruprocfs.c +++ b/drivers/misc/sgi-gru/gruprocfs.c @@ -255,28 +255,28 @@ static int options_open(struct inode *inode, struct file *file) } /* *INDENT-OFF* */ -static const struct file_operations statistics_fops = { - .open = statistics_open, - .read = seq_read, - .write = statistics_write, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops statistics_proc_ops = { + .proc_open = statistics_open, + .proc_read = seq_read, + .proc_write = statistics_write, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; -static const struct file_operations mcs_statistics_fops = { - .open = mcs_statistics_open, - .read = seq_read, - .write = mcs_statistics_write, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops mcs_statistics_proc_ops = { + .proc_open = mcs_statistics_open, + .proc_read = seq_read, + .proc_write = mcs_statistics_write, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; -static const struct file_operations options_fops = { - .open = options_open, - .read = seq_read, - .write = options_write, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops options_proc_ops = { + .proc_open = options_open, + .proc_read = seq_read, + .proc_write = options_write, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; static struct proc_dir_entry *proc_gru __read_mostly; @@ -286,11 +286,11 @@ int gru_proc_init(void) proc_gru = proc_mkdir("sgi_uv/gru", NULL); if (!proc_gru) return -1; - if (!proc_create("statistics", 0644, proc_gru, &statistics_fops)) + if (!proc_create("statistics", 0644, proc_gru, &statistics_proc_ops)) goto err; - if (!proc_create("mcs_statistics", 0644, proc_gru, &mcs_statistics_fops)) + if (!proc_create("mcs_statistics", 0644, proc_gru, &mcs_statistics_proc_ops)) goto err; - if (!proc_create("debug_options", 0644, proc_gru, &options_fops)) + if (!proc_create("debug_options", 0644, proc_gru, &options_proc_ops)) goto err; if (!proc_create_seq("cch_status", 0444, proc_gru, &cch_seq_ops)) goto err; diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 25fb72b2efa0..2f93c25bbaee 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1180,7 +1180,7 @@ static struct mtd_info * __init open_mtd_device(const char *mtd_dev) * MTD device name. */ mtd = get_mtd_device_nm(mtd_dev); - if (IS_ERR(mtd) && PTR_ERR(mtd) == -ENODEV) + if (PTR_ERR(mtd) == -ENODEV) /* Probably this is an MTD character device node path */ mtd = open_mtd_by_chdev(mtd_dev); } else diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index c4c8f1b62e1e..8363f91df7ea 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -4420,73 +4420,65 @@ static int proc_BSSList_open( struct inode *inode, struct file *file ); static int proc_config_open( struct inode *inode, struct file *file ); static int proc_wepkey_open( struct inode *inode, struct file *file ); -static const struct file_operations proc_statsdelta_ops = { - .owner = THIS_MODULE, - .read = proc_read, - .open = proc_statsdelta_open, - .release = proc_close, - .llseek = default_llseek, +static const struct proc_ops proc_statsdelta_ops = { + .proc_read = proc_read, + .proc_open = proc_statsdelta_open, + .proc_release = proc_close, + .proc_lseek = default_llseek, }; -static const struct file_operations proc_stats_ops = { - .owner = THIS_MODULE, - .read = proc_read, - .open = proc_stats_open, - .release = proc_close, - .llseek = default_llseek, +static const struct proc_ops proc_stats_ops = { + .proc_read = proc_read, + .proc_open = proc_stats_open, + .proc_release = proc_close, + .proc_lseek = default_llseek, }; -static const struct file_operations proc_status_ops = { - .owner = THIS_MODULE, - .read = proc_read, - .open = proc_status_open, - .release = proc_close, - .llseek = default_llseek, +static const struct proc_ops proc_status_ops = { + .proc_read = proc_read, + .proc_open = proc_status_open, + .proc_release = proc_close, + .proc_lseek = default_llseek, }; -static const struct file_operations proc_SSID_ops = { - .owner = THIS_MODULE, - .read = proc_read, - .write = proc_write, - .open = proc_SSID_open, - .release = proc_close, - .llseek = default_llseek, +static const struct proc_ops proc_SSID_ops = { + .proc_read = proc_read, + .proc_write = proc_write, + .proc_open = proc_SSID_open, + .proc_release = proc_close, + .proc_lseek = default_llseek, }; -static const struct file_operations proc_BSSList_ops = { - .owner = THIS_MODULE, - .read = proc_read, - .write = proc_write, - .open = proc_BSSList_open, - .release = proc_close, - .llseek = default_llseek, +static const struct proc_ops proc_BSSList_ops = { + .proc_read = proc_read, + .proc_write = proc_write, + .proc_open = proc_BSSList_open, + .proc_release = proc_close, + .proc_lseek = default_llseek, }; -static const struct file_operations proc_APList_ops = { - .owner = THIS_MODULE, - .read = proc_read, - .write = proc_write, - .open = proc_APList_open, - .release = proc_close, - .llseek = default_llseek, +static const struct proc_ops proc_APList_ops = { + .proc_read = proc_read, + .proc_write = proc_write, + .proc_open = proc_APList_open, + .proc_release = proc_close, + .proc_lseek = default_llseek, }; -static const struct file_operations proc_config_ops = { - .owner = THIS_MODULE, - .read = proc_read, - .write = proc_write, - .open = proc_config_open, - .release = proc_close, - .llseek = default_llseek, +static const struct proc_ops proc_config_ops = { + .proc_read = proc_read, + .proc_write = proc_write, + .proc_open = proc_config_open, + .proc_release = proc_close, + .proc_lseek = default_llseek, }; -static const struct file_operations proc_wepkey_ops = { - .owner = THIS_MODULE, - .read = proc_read, - .write = proc_write, - .open = proc_wepkey_open, - .release = proc_close, - .llseek = default_llseek, +static const struct proc_ops proc_wepkey_ops = { + .proc_read = proc_read, + .proc_write = proc_write, + .proc_open = proc_wepkey_open, + .proc_release = proc_close, + .proc_lseek = default_llseek, }; static struct proc_dir_entry *airo_entry; diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_module.c b/drivers/net/wireless/intel/ipw2x00/libipw_module.c index 436b819aeb36..43bab92a4148 100644 --- a/drivers/net/wireless/intel/ipw2x00/libipw_module.c +++ b/drivers/net/wireless/intel/ipw2x00/libipw_module.c @@ -240,13 +240,12 @@ static ssize_t debug_level_proc_write(struct file *file, return strnlen(buf, len); } -static const struct file_operations debug_level_proc_fops = { - .owner = THIS_MODULE, - .open = debug_level_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = debug_level_proc_write, +static const struct proc_ops debug_level_proc_ops = { + .proc_open = debug_level_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = debug_level_proc_write, }; #endif /* CONFIG_LIBIPW_DEBUG */ @@ -263,7 +262,7 @@ static int __init libipw_init(void) return -EIO; } e = proc_create("debug_level", 0644, libipw_proc, - &debug_level_proc_fops); + &debug_level_proc_ops); if (!e) { remove_proc_entry(DRV_PROCNAME, init_net.proc_net); libipw_proc = NULL; diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c index e323e9a5999f..58212c532c90 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_hw.c +++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c @@ -126,7 +126,7 @@ static void prism2_check_sta_fw_version(local_info_t *local); #ifdef PRISM2_DOWNLOAD_SUPPORT /* hostap_download.c */ -static const struct file_operations prism2_download_aux_dump_proc_fops; +static const struct proc_ops prism2_download_aux_dump_proc_ops; static u8 * prism2_read_pda(struct net_device *dev); static int prism2_download(local_info_t *local, struct prism2_download_param *param); @@ -3094,7 +3094,7 @@ prism2_init_local_data(struct prism2_helper_functions *funcs, int card_idx, local->func->reset_port = prism2_reset_port; local->func->schedule_reset = prism2_schedule_reset; #ifdef PRISM2_DOWNLOAD_SUPPORT - local->func->read_aux_fops = &prism2_download_aux_dump_proc_fops; + local->func->read_aux_proc_ops = &prism2_download_aux_dump_proc_ops; local->func->download = prism2_download; #endif /* PRISM2_DOWNLOAD_SUPPORT */ local->func->tx = prism2_tx_80211; diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c index 6151d8db5924..a2ee4693eaed 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_proc.c +++ b/drivers/net/wireless/intersil/hostap/hostap_proc.c @@ -211,9 +211,9 @@ static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf, return count; } -static const struct file_operations prism2_pda_proc_fops = { - .read = prism2_pda_proc_read, - .llseek = generic_file_llseek, +static const struct proc_ops prism2_pda_proc_ops = { + .proc_read = prism2_pda_proc_read, + .proc_lseek = generic_file_llseek, }; @@ -223,8 +223,8 @@ static ssize_t prism2_aux_dump_proc_no_read(struct file *file, char __user *buf, return 0; } -static const struct file_operations prism2_aux_dump_proc_fops = { - .read = prism2_aux_dump_proc_no_read, +static const struct proc_ops prism2_aux_dump_proc_ops = { + .proc_read = prism2_aux_dump_proc_no_read, }; @@ -379,9 +379,9 @@ void hostap_init_proc(local_info_t *local) proc_create_seq_data("wds", 0, local->proc, &prism2_wds_proc_seqops, local); proc_create_data("pda", 0, local->proc, - &prism2_pda_proc_fops, local); + &prism2_pda_proc_ops, local); proc_create_data("aux_dump", 0, local->proc, - local->func->read_aux_fops ?: &prism2_aux_dump_proc_fops, + local->func->read_aux_proc_ops ?: &prism2_aux_dump_proc_ops, local); proc_create_seq_data("bss_list", 0, local->proc, &prism2_bss_list_proc_seqops, local); diff --git a/drivers/net/wireless/intersil/hostap/hostap_wlan.h b/drivers/net/wireless/intersil/hostap/hostap_wlan.h index a8c4c1a8b29d..487883fbb58c 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_wlan.h +++ b/drivers/net/wireless/intersil/hostap/hostap_wlan.h @@ -599,7 +599,7 @@ struct prism2_helper_functions { struct prism2_download_param *param); int (*tx)(struct sk_buff *skb, struct net_device *dev); int (*set_tim)(struct net_device *dev, int aid, int set); - const struct file_operations *read_aux_fops; + const struct proc_ops *read_aux_proc_ops; int need_tx_headroom; /* number of bytes of headroom needed before * IEEE 802.11 header */ diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index cf372684b681..c1d542bfa530 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -2717,10 +2717,9 @@ static ssize_t ray_cs_essid_proc_write(struct file *file, return count; } -static const struct file_operations ray_cs_essid_proc_fops = { - .owner = THIS_MODULE, - .write = ray_cs_essid_proc_write, - .llseek = noop_llseek, +static const struct proc_ops ray_cs_essid_proc_ops = { + .proc_write = ray_cs_essid_proc_write, + .proc_lseek = noop_llseek, }; static ssize_t int_proc_write(struct file *file, const char __user *buffer, @@ -2751,10 +2750,9 @@ static ssize_t int_proc_write(struct file *file, const char __user *buffer, return count; } -static const struct file_operations int_proc_fops = { - .owner = THIS_MODULE, - .write = int_proc_write, - .llseek = noop_llseek, +static const struct proc_ops int_proc_ops = { + .proc_write = int_proc_write, + .proc_lseek = noop_llseek, }; #endif @@ -2790,10 +2788,10 @@ static int __init init_ray_cs(void) proc_mkdir("driver/ray_cs", NULL); proc_create_single("driver/ray_cs/ray_cs", 0, NULL, ray_cs_proc_show); - proc_create("driver/ray_cs/essid", 0200, NULL, &ray_cs_essid_proc_fops); - proc_create_data("driver/ray_cs/net_type", 0200, NULL, &int_proc_fops, + proc_create("driver/ray_cs/essid", 0200, NULL, &ray_cs_essid_proc_ops); + proc_create_data("driver/ray_cs/net_type", 0200, NULL, &int_proc_ops, &net_type); - proc_create_data("driver/ray_cs/translate", 0200, NULL, &int_proc_fops, + proc_create_data("driver/ray_cs/translate", 0200, NULL, &int_proc_ops, &translate); #endif if (translate != 0) diff --git a/drivers/of/device.c b/drivers/of/device.c index e9127db7b067..27203bfd0b22 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -161,7 +161,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) coherent ? " " : " not "); iommu = of_iommu_configure(dev, np); - if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER) + if (PTR_ERR(iommu) == -EPROBE_DEFER) return -EPROBE_DEFER; dev_dbg(dev, "device is%sbehind an iommu\n", diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index 73e37bb877a4..36c6613f7a36 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -230,13 +230,12 @@ parse_error: return -EINVAL; } -static const struct file_operations led_proc_fops = { - .owner = THIS_MODULE, - .open = led_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = led_proc_write, +static const struct proc_ops led_proc_ops = { + .proc_open = led_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = led_proc_write, }; static int __init led_create_procfs(void) @@ -252,14 +251,14 @@ static int __init led_create_procfs(void) if (!lcd_no_led_support) { ent = proc_create_data("led", S_IRUGO|S_IWUSR, proc_pdc_root, - &led_proc_fops, (void *)LED_NOLCD); /* LED */ + &led_proc_ops, (void *)LED_NOLCD); /* LED */ if (!ent) return -1; } if (led_type == LED_HASLCD) { ent = proc_create_data("lcd", S_IRUGO|S_IWUSR, proc_pdc_root, - &led_proc_fops, (void *)LED_HASLCD); /* LCD */ + &led_proc_ops, (void *)LED_HASLCD); /* LCD */ if (!ent) return -1; } diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c index ac93f5a0398e..0e03cef72840 100644 --- a/drivers/pci/controller/pci-tegra.c +++ b/drivers/pci/controller/pci-tegra.c @@ -1406,7 +1406,7 @@ static struct phy *devm_of_phy_optional_get_index(struct device *dev, phy = devm_of_phy_get(dev, np, name); kfree(name); - if (IS_ERR(phy) && PTR_ERR(phy) == -ENODEV) + if (PTR_ERR(phy) == -ENODEV) phy = NULL; return phy; diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index 6ef74bf5013f..bd2b691fa7a3 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -306,19 +306,20 @@ static int proc_bus_pci_release(struct inode *inode, struct file *file) } #endif /* HAVE_PCI_MMAP */ -static const struct file_operations proc_bus_pci_operations = { - .owner = THIS_MODULE, - .llseek = proc_bus_pci_lseek, - .read = proc_bus_pci_read, - .write = proc_bus_pci_write, - .unlocked_ioctl = proc_bus_pci_ioctl, - .compat_ioctl = proc_bus_pci_ioctl, +static const struct proc_ops proc_bus_pci_ops = { + .proc_lseek = proc_bus_pci_lseek, + .proc_read = proc_bus_pci_read, + .proc_write = proc_bus_pci_write, + .proc_ioctl = proc_bus_pci_ioctl, +#ifdef CONFIG_COMPAT + .proc_compat_ioctl = proc_bus_pci_ioctl, +#endif #ifdef HAVE_PCI_MMAP - .open = proc_bus_pci_open, - .release = proc_bus_pci_release, - .mmap = proc_bus_pci_mmap, + .proc_open = proc_bus_pci_open, + .proc_release = proc_bus_pci_release, + .proc_mmap = proc_bus_pci_mmap, #ifdef HAVE_ARCH_PCI_GET_UNMAPPED_AREA - .get_unmapped_area = get_pci_unmapped_area, + .proc_get_unmapped_area = get_pci_unmapped_area, #endif /* HAVE_ARCH_PCI_GET_UNMAPPED_AREA */ #endif /* HAVE_PCI_MMAP */ }; @@ -424,7 +425,7 @@ int pci_proc_attach_device(struct pci_dev *dev) sprintf(name, "%02x.%x", PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn)); e = proc_create_data(name, S_IFREG | S_IRUGO | S_IWUSR, bus->procdir, - &proc_bus_pci_operations, dev); + &proc_bus_pci_ops, dev); if (!e) return -ENOMEM; proc_set_size(e, dev->cfg_size); diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 2eb28cc2d2dc..cd5a6c95dbdc 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -712,7 +712,7 @@ struct phy *phy_optional_get(struct device *dev, const char *string) { struct phy *phy = phy_get(dev, string); - if (IS_ERR(phy) && (PTR_ERR(phy) == -ENODEV)) + if (PTR_ERR(phy) == -ENODEV) phy = NULL; return phy; @@ -766,7 +766,7 @@ struct phy *devm_phy_optional_get(struct device *dev, const char *string) { struct phy *phy = devm_phy_get(dev, string); - if (IS_ERR(phy) && (PTR_ERR(phy) == -ENODEV)) + if (PTR_ERR(phy) == -ENODEV) phy = NULL; return phy; diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c index 21c370dbbfba..bddf2c5dd3bf 100644 --- a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c +++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c @@ -10,6 +10,7 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/module.h> +#include <linux/pinctrl/machine.h> #include <linux/pinctrl/pinconf.h> #include <linux/pinctrl/pinconf-generic.h> #include <linux/pinctrl/pinmux.h> diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index da794dcfdd92..8eaadbaf8ffa 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -907,13 +907,12 @@ static ssize_t dispatch_proc_write(struct file *file, return ret; } -static const struct file_operations dispatch_proc_fops = { - .owner = THIS_MODULE, - .open = dispatch_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = dispatch_proc_write, +static const struct proc_ops dispatch_proc_ops = { + .proc_open = dispatch_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = dispatch_proc_write, }; static char *next_cmd(char **cmds) @@ -9984,7 +9983,7 @@ static int __init ibm_init(struct ibm_init_struct *iibm) if (ibm->write) mode |= S_IWUSR; entry = proc_create_data(ibm->name, mode, proc_dir, - &dispatch_proc_fops, ibm); + &dispatch_proc_ops, ibm); if (!entry) { pr_err("unable to create proc entry %s\n", ibm->name); ret = -ENODEV; diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index a1e6569427c3..808944546739 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -1432,13 +1432,12 @@ static ssize_t lcd_proc_write(struct file *file, const char __user *buf, return count; } -static const struct file_operations lcd_proc_fops = { - .owner = THIS_MODULE, - .open = lcd_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = lcd_proc_write, +static const struct proc_ops lcd_proc_ops = { + .proc_open = lcd_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = lcd_proc_write, }; /* Video-Out */ @@ -1539,13 +1538,12 @@ static ssize_t video_proc_write(struct file *file, const char __user *buf, return ret ? -EIO : count; } -static const struct file_operations video_proc_fops = { - .owner = THIS_MODULE, - .open = video_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = video_proc_write, +static const struct proc_ops video_proc_ops = { + .proc_open = video_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = video_proc_write, }; /* Fan status */ @@ -1617,13 +1615,12 @@ static ssize_t fan_proc_write(struct file *file, const char __user *buf, return count; } -static const struct file_operations fan_proc_fops = { - .owner = THIS_MODULE, - .open = fan_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = fan_proc_write, +static const struct proc_ops fan_proc_ops = { + .proc_open = fan_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = fan_proc_write, }; static int keys_proc_show(struct seq_file *m, void *v) @@ -1662,13 +1659,12 @@ static ssize_t keys_proc_write(struct file *file, const char __user *buf, return count; } -static const struct file_operations keys_proc_fops = { - .owner = THIS_MODULE, - .open = keys_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = keys_proc_write, +static const struct proc_ops keys_proc_ops = { + .proc_open = keys_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = keys_proc_write, }; static int __maybe_unused version_proc_show(struct seq_file *m, void *v) @@ -1688,16 +1684,16 @@ static void create_toshiba_proc_entries(struct toshiba_acpi_dev *dev) { if (dev->backlight_dev) proc_create_data("lcd", S_IRUGO | S_IWUSR, toshiba_proc_dir, - &lcd_proc_fops, dev); + &lcd_proc_ops, dev); if (dev->video_supported) proc_create_data("video", S_IRUGO | S_IWUSR, toshiba_proc_dir, - &video_proc_fops, dev); + &video_proc_ops, dev); if (dev->fan_supported) proc_create_data("fan", S_IRUGO | S_IWUSR, toshiba_proc_dir, - &fan_proc_fops, dev); + &fan_proc_ops, dev); if (dev->hotkey_dev) proc_create_data("keys", S_IRUGO | S_IWUSR, toshiba_proc_dir, - &keys_proc_fops, dev); + &keys_proc_ops, dev); proc_create_single_data("version", S_IRUGO, toshiba_proc_dir, version_proc_show, dev); } diff --git a/drivers/pnp/isapnp/proc.c b/drivers/pnp/isapnp/proc.c index 36820979bd1c..785a796430fa 100644 --- a/drivers/pnp/isapnp/proc.c +++ b/drivers/pnp/isapnp/proc.c @@ -49,10 +49,9 @@ static ssize_t isapnp_proc_bus_read(struct file *file, char __user * buf, return nbytes; } -static const struct file_operations isapnp_proc_bus_file_operations = { - .owner = THIS_MODULE, - .llseek = isapnp_proc_bus_lseek, - .read = isapnp_proc_bus_read, +static const struct proc_ops isapnp_proc_bus_proc_ops = { + .proc_lseek = isapnp_proc_bus_lseek, + .proc_read = isapnp_proc_bus_read, }; static int isapnp_proc_attach_device(struct pnp_dev *dev) @@ -69,7 +68,7 @@ static int isapnp_proc_attach_device(struct pnp_dev *dev) } sprintf(name, "%02x", dev->number); e = dev->procent = proc_create_data(name, S_IFREG | S_IRUGO, de, - &isapnp_proc_bus_file_operations, dev); + &isapnp_proc_bus_proc_ops, dev); if (!e) return -ENOMEM; proc_set_size(e, 256); diff --git a/drivers/pnp/pnpbios/proc.c b/drivers/pnp/pnpbios/proc.c index fe1c8f5d9af0..a806830e3a40 100644 --- a/drivers/pnp/pnpbios/proc.c +++ b/drivers/pnp/pnpbios/proc.c @@ -210,13 +210,12 @@ out: return ret; } -static const struct file_operations pnpbios_proc_fops = { - .owner = THIS_MODULE, - .open = pnpbios_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = pnpbios_proc_write, +static const struct proc_ops pnpbios_proc_ops = { + .proc_open = pnpbios_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = pnpbios_proc_write, }; int pnpbios_interface_attach_device(struct pnp_bios_node *node) @@ -228,13 +227,13 @@ int pnpbios_interface_attach_device(struct pnp_bios_node *node) if (!proc_pnp) return -EIO; if (!pnpbios_dont_use_current_config) { - proc_create_data(name, 0644, proc_pnp, &pnpbios_proc_fops, + proc_create_data(name, 0644, proc_pnp, &pnpbios_proc_ops, (void *)(long)(node->handle)); } if (!proc_pnp_boot) return -EIO; - if (proc_create_data(name, 0644, proc_pnp_boot, &pnpbios_proc_fops, + if (proc_create_data(name, 0644, proc_pnp_boot, &pnpbios_proc_ops, (void *)(long)(node->handle + 0x100))) return 0; return -EIO; diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c index 8d4d69ea5baf..62a859ea67f8 100644 --- a/drivers/s390/block/dasd_proc.c +++ b/drivers/s390/block/dasd_proc.c @@ -320,13 +320,12 @@ out_error: #endif /* CONFIG_DASD_PROFILE */ } -static const struct file_operations dasd_stats_proc_fops = { - .owner = THIS_MODULE, - .open = dasd_stats_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = dasd_stats_proc_write, +static const struct proc_ops dasd_stats_proc_ops = { + .proc_open = dasd_stats_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = dasd_stats_proc_write, }; /* @@ -347,7 +346,7 @@ dasd_proc_init(void) dasd_statistics_entry = proc_create("statistics", S_IFREG | S_IRUGO | S_IWUSR, dasd_proc_root_entry, - &dasd_stats_proc_fops); + &dasd_stats_proc_ops); if (!dasd_statistics_entry) goto out_nostatistics; return 0; diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c index 2a3f874a21d5..da642e811f7f 100644 --- a/drivers/s390/cio/blacklist.c +++ b/drivers/s390/cio/blacklist.c @@ -398,12 +398,12 @@ cio_ignore_proc_open(struct inode *inode, struct file *file) sizeof(struct ccwdev_iter)); } -static const struct file_operations cio_ignore_proc_fops = { - .open = cio_ignore_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, - .write = cio_ignore_write, +static const struct proc_ops cio_ignore_proc_ops = { + .proc_open = cio_ignore_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release_private, + .proc_write = cio_ignore_write, }; static int @@ -412,7 +412,7 @@ cio_ignore_proc_init (void) struct proc_dir_entry *entry; entry = proc_create("cio_ignore", S_IFREG | S_IRUGO | S_IWUSR, NULL, - &cio_ignore_proc_fops); + &cio_ignore_proc_ops); if (!entry) return -ENOENT; return 0; diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 831850435c23..94edbb33d0d1 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1372,18 +1372,17 @@ static ssize_t cio_settle_write(struct file *file, const char __user *buf, return ret ? ret : count; } -static const struct file_operations cio_settle_proc_fops = { - .open = nonseekable_open, - .write = cio_settle_write, - .llseek = no_llseek, +static const struct proc_ops cio_settle_proc_ops = { + .proc_open = nonseekable_open, + .proc_write = cio_settle_write, + .proc_lseek = no_llseek, }; static int __init cio_settle_init(void) { struct proc_dir_entry *entry; - entry = proc_create("cio_settle", S_IWUSR, NULL, - &cio_settle_proc_fops); + entry = proc_create("cio_settle", S_IWUSR, NULL, &cio_settle_proc_ops); if (!entry) return -ENOMEM; return 0; diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c index 80c5a235d193..7b49e2e9fcde 100644 --- a/drivers/scsi/esas2r/esas2r_main.c +++ b/drivers/scsi/esas2r/esas2r_main.c @@ -617,6 +617,13 @@ static const struct file_operations esas2r_proc_fops = { .unlocked_ioctl = esas2r_proc_ioctl, }; +static const struct proc_ops esas2r_proc_ops = { + .proc_ioctl = esas2r_proc_ioctl, +#ifdef CONFIG_COMPAT + .proc_compat_ioctl = compat_ptr_ioctl, +#endif +}; + static struct Scsi_Host *esas2r_proc_host; static int esas2r_proc_major; @@ -728,7 +735,7 @@ const char *esas2r_info(struct Scsi_Host *sh) pde = proc_create(ATTONODE_NAME, 0, sh->hostt->proc_dir, - &esas2r_proc_fops); + &esas2r_proc_ops); if (!pde) { esas2r_log_dev(ESAS2R_LOG_WARN, diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index df14597752ec..eed31021e788 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -736,13 +736,12 @@ out: return err; } -static const struct file_operations scsi_devinfo_proc_fops = { - .owner = THIS_MODULE, - .open = proc_scsi_devinfo_open, - .read = seq_read, - .write = proc_scsi_devinfo_write, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops scsi_devinfo_proc_ops = { + .proc_open = proc_scsi_devinfo_open, + .proc_read = seq_read, + .proc_write = proc_scsi_devinfo_write, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; #endif /* CONFIG_SCSI_PROC_FS */ @@ -867,7 +866,7 @@ int __init scsi_init_devinfo(void) } #ifdef CONFIG_SCSI_PROC_FS - p = proc_create("scsi/device_info", 0, NULL, &scsi_devinfo_proc_fops); + p = proc_create("scsi/device_info", 0, NULL, &scsi_devinfo_proc_ops); if (!p) { error = -ENOMEM; goto out; diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c index 5b313226f11c..d6982d355739 100644 --- a/drivers/scsi/scsi_proc.c +++ b/drivers/scsi/scsi_proc.c @@ -83,12 +83,12 @@ static int proc_scsi_host_open(struct inode *inode, struct file *file) 4 * PAGE_SIZE); } -static const struct file_operations proc_scsi_fops = { - .open = proc_scsi_host_open, - .release = single_release, - .read = seq_read, - .llseek = seq_lseek, - .write = proc_scsi_host_write +static const struct proc_ops proc_scsi_ops = { + .proc_open = proc_scsi_host_open, + .proc_release = single_release, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = proc_scsi_host_write }; /** @@ -146,7 +146,7 @@ void scsi_proc_host_add(struct Scsi_Host *shost) sprintf(name,"%d", shost->host_no); p = proc_create_data(name, S_IRUGO | S_IWUSR, - sht->proc_dir, &proc_scsi_fops, shost); + sht->proc_dir, &proc_scsi_ops, shost); if (!p) printk(KERN_ERR "%s: Failed to register host %d in" "%s\n", __func__, shost->host_no, @@ -436,13 +436,12 @@ static int proc_scsi_open(struct inode *inode, struct file *file) return seq_open(file, &scsi_seq_ops); } -static const struct file_operations proc_scsi_operations = { - .owner = THIS_MODULE, - .open = proc_scsi_open, - .read = seq_read, - .write = proc_scsi_write, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops scsi_scsi_proc_ops = { + .proc_open = proc_scsi_open, + .proc_read = seq_read, + .proc_write = proc_scsi_write, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; /** @@ -456,7 +455,7 @@ int __init scsi_init_procfs(void) if (!proc_scsi) goto err1; - pde = proc_create("scsi/scsi", 0, NULL, &proc_scsi_operations); + pde = proc_create("scsi/scsi", 0, NULL, &scsi_scsi_proc_ops); if (!pde) goto err2; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index bafeaf7b9ad8..4e6af592f018 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -2322,25 +2322,23 @@ static int sg_proc_seq_show_int(struct seq_file *s, void *v); static int sg_proc_single_open_adio(struct inode *inode, struct file *file); static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer, size_t count, loff_t *off); -static const struct file_operations adio_fops = { - .owner = THIS_MODULE, - .open = sg_proc_single_open_adio, - .read = seq_read, - .llseek = seq_lseek, - .write = sg_proc_write_adio, - .release = single_release, +static const struct proc_ops adio_proc_ops = { + .proc_open = sg_proc_single_open_adio, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = sg_proc_write_adio, + .proc_release = single_release, }; static int sg_proc_single_open_dressz(struct inode *inode, struct file *file); static ssize_t sg_proc_write_dressz(struct file *filp, const char __user *buffer, size_t count, loff_t *off); -static const struct file_operations dressz_fops = { - .owner = THIS_MODULE, - .open = sg_proc_single_open_dressz, - .read = seq_read, - .llseek = seq_lseek, - .write = sg_proc_write_dressz, - .release = single_release, +static const struct proc_ops dressz_proc_ops = { + .proc_open = sg_proc_single_open_dressz, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = sg_proc_write_dressz, + .proc_release = single_release, }; static int sg_proc_seq_show_version(struct seq_file *s, void *v); @@ -2381,9 +2379,9 @@ sg_proc_init(void) if (!p) return 1; - proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_fops); + proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_proc_ops); proc_create_seq("debug", S_IRUGO, p, &debug_seq_ops); - proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_fops); + proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_proc_ops); proc_create_single("device_hdr", S_IRUGO, p, sg_proc_seq_show_devhdr); proc_create_seq("devices", S_IRUGO, p, &dev_seq_ops); proc_create_seq("device_strs", S_IRUGO, p, &devstrs_seq_ops); diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index c7266ef295fd..1f59beb7d27e 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -646,8 +646,7 @@ static int orion_spi_probe(struct platform_device *pdev) /* The following clock is only used by some SoCs */ spi->axi_clk = devm_clk_get(&pdev->dev, "axi"); - if (IS_ERR(spi->axi_clk) && - PTR_ERR(spi->axi_clk) == -EPROBE_DEFER) { + if (PTR_ERR(spi->axi_clk) == -EPROBE_DEFER) { status = -EPROBE_DEFER; goto out_rel_clk; } diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_module.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_module.c index 4a6c3f674431..aa9dab8a4ae8 100644 --- a/drivers/staging/rtl8192u/ieee80211/ieee80211_module.c +++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_module.c @@ -264,12 +264,12 @@ static int open_debug_level(struct inode *inode, struct file *file) return single_open(file, show_debug_level, NULL); } -static const struct file_operations fops = { - .open = open_debug_level, - .read = seq_read, - .llseek = seq_lseek, - .write = write_debug_level, - .release = single_release, +static const struct proc_ops debug_level_proc_ops = { + .proc_open = open_debug_level, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = write_debug_level, + .proc_release = single_release, }; int __init ieee80211_debug_init(void) @@ -284,7 +284,7 @@ int __init ieee80211_debug_init(void) " proc directory\n"); return -EIO; } - e = proc_create("debug_level", 0644, ieee80211_proc, &fops); + e = proc_create("debug_level", 0644, ieee80211_proc, &debug_level_proc_ops); if (!e) { remove_proc_entry(DRV_NAME, init_net.proc_net); ieee80211_proc = NULL; diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 1d4f317a0e42..f724962a5906 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -1101,15 +1101,15 @@ static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf, return count; } -static const struct file_operations proc_sysrq_trigger_operations = { - .write = write_sysrq_trigger, - .llseek = noop_llseek, +static const struct proc_ops sysrq_trigger_proc_ops = { + .proc_write = write_sysrq_trigger, + .proc_lseek = noop_llseek, }; static void sysrq_init_procfs(void) { if (!proc_create("sysrq-trigger", S_IWUSR, NULL, - &proc_sysrq_trigger_operations)) + &sysrq_trigger_proc_ops)) pr_err("Failed to register proc interface\n"); } diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 04c142c13075..64de9f1b874c 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -72,7 +72,7 @@ static rndis_resp_t *rndis_add_response(struct rndis_params *params, #ifdef CONFIG_USB_GADGET_DEBUG_FILES -static const struct file_operations rndis_proc_fops; +static const struct proc_ops rndis_proc_ops; #endif /* CONFIG_USB_GADGET_DEBUG_FILES */ @@ -902,7 +902,7 @@ struct rndis_params *rndis_register(void (*resp_avail)(void *v), void *v) sprintf(name, NAME_TEMPLATE, i); proc_entry = proc_create_data(name, 0660, NULL, - &rndis_proc_fops, params); + &rndis_proc_ops, params); if (!proc_entry) { kfree(params); rndis_put_nr(i); @@ -1164,13 +1164,12 @@ static int rndis_proc_open(struct inode *inode, struct file *file) return single_open(file, rndis_proc_show, PDE_DATA(inode)); } -static const struct file_operations rndis_proc_fops = { - .owner = THIS_MODULE, - .open = rndis_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = rndis_proc_write, +static const struct proc_ops rndis_proc_ops = { + .proc_open = rndis_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = rndis_proc_write, }; #define NAME_TEMPLATE "driver/rndis-%03d" diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index 08a17eb2a5c7..370bf2553d43 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -1017,7 +1017,7 @@ static int imxfb_probe(struct platform_device *pdev) } fbi->lcd_pwr = devm_regulator_get(&pdev->dev, "lcd"); - if (IS_ERR(fbi->lcd_pwr) && (PTR_ERR(fbi->lcd_pwr) == -EPROBE_DEFER)) { + if (PTR_ERR(fbi->lcd_pwr) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; goto failed_lcd; } diff --git a/drivers/video/fbdev/via/viafbdev.c b/drivers/video/fbdev/via/viafbdev.c index f815f98190bc..852673c40a2f 100644 --- a/drivers/video/fbdev/via/viafbdev.c +++ b/drivers/video/fbdev/via/viafbdev.c @@ -1173,13 +1173,12 @@ static ssize_t viafb_dvp0_proc_write(struct file *file, return count; } -static const struct file_operations viafb_dvp0_proc_fops = { - .owner = THIS_MODULE, - .open = viafb_dvp0_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = viafb_dvp0_proc_write, +static const struct proc_ops viafb_dvp0_proc_ops = { + .proc_open = viafb_dvp0_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = viafb_dvp0_proc_write, }; static int viafb_dvp1_proc_show(struct seq_file *m, void *v) @@ -1238,13 +1237,12 @@ static ssize_t viafb_dvp1_proc_write(struct file *file, return count; } -static const struct file_operations viafb_dvp1_proc_fops = { - .owner = THIS_MODULE, - .open = viafb_dvp1_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = viafb_dvp1_proc_write, +static const struct proc_ops viafb_dvp1_proc_ops = { + .proc_open = viafb_dvp1_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = viafb_dvp1_proc_write, }; static int viafb_dfph_proc_show(struct seq_file *m, void *v) @@ -1273,13 +1271,12 @@ static ssize_t viafb_dfph_proc_write(struct file *file, return count; } -static const struct file_operations viafb_dfph_proc_fops = { - .owner = THIS_MODULE, - .open = viafb_dfph_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = viafb_dfph_proc_write, +static const struct proc_ops viafb_dfph_proc_ops = { + .proc_open = viafb_dfph_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = viafb_dfph_proc_write, }; static int viafb_dfpl_proc_show(struct seq_file *m, void *v) @@ -1308,13 +1305,12 @@ static ssize_t viafb_dfpl_proc_write(struct file *file, return count; } -static const struct file_operations viafb_dfpl_proc_fops = { - .owner = THIS_MODULE, - .open = viafb_dfpl_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = viafb_dfpl_proc_write, +static const struct proc_ops viafb_dfpl_proc_ops = { + .proc_open = viafb_dfpl_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = viafb_dfpl_proc_write, }; static int viafb_vt1636_proc_show(struct seq_file *m, void *v) @@ -1444,13 +1440,12 @@ static ssize_t viafb_vt1636_proc_write(struct file *file, return count; } -static const struct file_operations viafb_vt1636_proc_fops = { - .owner = THIS_MODULE, - .open = viafb_vt1636_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = viafb_vt1636_proc_write, +static const struct proc_ops viafb_vt1636_proc_ops = { + .proc_open = viafb_vt1636_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = viafb_vt1636_proc_write, }; #endif /* CONFIG_FB_VIA_DIRECT_PROCFS */ @@ -1522,13 +1517,12 @@ static ssize_t viafb_iga1_odev_proc_write(struct file *file, return res; } -static const struct file_operations viafb_iga1_odev_proc_fops = { - .owner = THIS_MODULE, - .open = viafb_iga1_odev_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = viafb_iga1_odev_proc_write, +static const struct proc_ops viafb_iga1_odev_proc_ops = { + .proc_open = viafb_iga1_odev_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = viafb_iga1_odev_proc_write, }; static int viafb_iga2_odev_proc_show(struct seq_file *m, void *v) @@ -1562,13 +1556,12 @@ static ssize_t viafb_iga2_odev_proc_write(struct file *file, return res; } -static const struct file_operations viafb_iga2_odev_proc_fops = { - .owner = THIS_MODULE, - .open = viafb_iga2_odev_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = viafb_iga2_odev_proc_write, +static const struct proc_ops viafb_iga2_odev_proc_ops = { + .proc_open = viafb_iga2_odev_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = viafb_iga2_odev_proc_write, }; #define IS_VT1636(lvds_chip) ((lvds_chip).lvds_chip_name == VT1636_LVDS) @@ -1580,14 +1573,14 @@ static void viafb_init_proc(struct viafb_shared *shared) shared->proc_entry = viafb_entry; if (viafb_entry) { #ifdef CONFIG_FB_VIA_DIRECT_PROCFS - proc_create("dvp0", 0, viafb_entry, &viafb_dvp0_proc_fops); - proc_create("dvp1", 0, viafb_entry, &viafb_dvp1_proc_fops); - proc_create("dfph", 0, viafb_entry, &viafb_dfph_proc_fops); - proc_create("dfpl", 0, viafb_entry, &viafb_dfpl_proc_fops); + proc_create("dvp0", 0, viafb_entry, &viafb_dvp0_proc_ops); + proc_create("dvp1", 0, viafb_entry, &viafb_dvp1_proc_ops); + proc_create("dfph", 0, viafb_entry, &viafb_dfph_proc_ops); + proc_create("dfpl", 0, viafb_entry, &viafb_dfpl_proc_ops); if (IS_VT1636(shared->chip_info.lvds_chip_info) || IS_VT1636(shared->chip_info.lvds_chip_info2)) proc_create("vt1636", 0, viafb_entry, - &viafb_vt1636_proc_fops); + &viafb_vt1636_proc_ops); #endif /* CONFIG_FB_VIA_DIRECT_PROCFS */ proc_create_single("supported_output_devices", 0, viafb_entry, @@ -1595,11 +1588,11 @@ static void viafb_init_proc(struct viafb_shared *shared) iga1_entry = proc_mkdir("iga1", viafb_entry); shared->iga1_proc_entry = iga1_entry; proc_create("output_devices", 0, iga1_entry, - &viafb_iga1_odev_proc_fops); + &viafb_iga1_odev_proc_ops); iga2_entry = proc_mkdir("iga2", viafb_entry); shared->iga2_proc_entry = iga2_entry; proc_create("output_devices", 0, iga2_entry, - &viafb_iga2_odev_proc_fops); + &viafb_iga2_odev_proc_ops); } } static void viafb_remove_proc(struct viafb_shared *shared) diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c index 2e4ca4dc0960..1c9ae08225d8 100644 --- a/drivers/zorro/proc.c +++ b/drivers/zorro/proc.c @@ -56,10 +56,9 @@ proc_bus_zorro_read(struct file *file, char __user *buf, size_t nbytes, loff_t * return nbytes; } -static const struct file_operations proc_bus_zorro_operations = { - .owner = THIS_MODULE, - .llseek = proc_bus_zorro_lseek, - .read = proc_bus_zorro_read, +static const struct proc_ops bus_zorro_proc_ops = { + .proc_lseek = proc_bus_zorro_lseek, + .proc_read = proc_bus_zorro_read, }; static void * zorro_seq_start(struct seq_file *m, loff_t *pos) @@ -105,7 +104,7 @@ static int __init zorro_proc_attach_device(unsigned int slot) sprintf(name, "%02x", slot); entry = proc_create_data(name, 0, proc_bus_zorro_dir, - &proc_bus_zorro_operations, + &bus_zorro_proc_ops, &zorro_autocon[slot]); if (!entry) return -ENOMEM; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 19f6e592b941..276e4b5ea8e0 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -611,12 +611,12 @@ static int cifs_stats_proc_open(struct inode *inode, struct file *file) return single_open(file, cifs_stats_proc_show, NULL); } -static const struct file_operations cifs_stats_proc_fops = { - .open = cifs_stats_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_stats_proc_write, +static const struct proc_ops cifs_stats_proc_ops = { + .proc_open = cifs_stats_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifs_stats_proc_write, }; #ifdef CONFIG_CIFS_SMB_DIRECT @@ -640,12 +640,12 @@ static int name##_open(struct inode *inode, struct file *file) \ return single_open(file, name##_proc_show, NULL); \ } \ \ -static const struct file_operations cifs_##name##_proc_fops = { \ - .open = name##_open, \ - .read = seq_read, \ - .llseek = seq_lseek, \ - .release = single_release, \ - .write = name##_write, \ +static const struct proc_ops cifs_##name##_proc_fops = { \ + .proc_open = name##_open, \ + .proc_read = seq_read, \ + .proc_lseek = seq_lseek, \ + .proc_release = single_release, \ + .proc_write = name##_write, \ } PROC_FILE_DEFINE(rdma_readwrite_threshold); @@ -659,11 +659,11 @@ PROC_FILE_DEFINE(smbd_receive_credit_max); #endif static struct proc_dir_entry *proc_fs_cifs; -static const struct file_operations cifsFYI_proc_fops; -static const struct file_operations cifs_lookup_cache_proc_fops; -static const struct file_operations traceSMB_proc_fops; -static const struct file_operations cifs_security_flags_proc_fops; -static const struct file_operations cifs_linux_ext_proc_fops; +static const struct proc_ops cifsFYI_proc_ops; +static const struct proc_ops cifs_lookup_cache_proc_ops; +static const struct proc_ops traceSMB_proc_ops; +static const struct proc_ops cifs_security_flags_proc_ops; +static const struct proc_ops cifs_linux_ext_proc_ops; void cifs_proc_init(void) @@ -678,18 +678,18 @@ cifs_proc_init(void) proc_create_single("open_files", 0400, proc_fs_cifs, cifs_debug_files_proc_show); - proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops); - proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops); - proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops); + proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_ops); + proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_ops); + proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_ops); proc_create("LinuxExtensionsEnabled", 0644, proc_fs_cifs, - &cifs_linux_ext_proc_fops); + &cifs_linux_ext_proc_ops); proc_create("SecurityFlags", 0644, proc_fs_cifs, - &cifs_security_flags_proc_fops); + &cifs_security_flags_proc_ops); proc_create("LookupCacheEnabled", 0644, proc_fs_cifs, - &cifs_lookup_cache_proc_fops); + &cifs_lookup_cache_proc_ops); #ifdef CONFIG_CIFS_DFS_UPCALL - proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_fops); + proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_ops); #endif #ifdef CONFIG_CIFS_SMB_DIRECT @@ -774,12 +774,12 @@ static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer, return count; } -static const struct file_operations cifsFYI_proc_fops = { - .open = cifsFYI_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifsFYI_proc_write, +static const struct proc_ops cifsFYI_proc_ops = { + .proc_open = cifsFYI_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifsFYI_proc_write, }; static int cifs_linux_ext_proc_show(struct seq_file *m, void *v) @@ -805,12 +805,12 @@ static ssize_t cifs_linux_ext_proc_write(struct file *file, return count; } -static const struct file_operations cifs_linux_ext_proc_fops = { - .open = cifs_linux_ext_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_linux_ext_proc_write, +static const struct proc_ops cifs_linux_ext_proc_ops = { + .proc_open = cifs_linux_ext_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifs_linux_ext_proc_write, }; static int cifs_lookup_cache_proc_show(struct seq_file *m, void *v) @@ -836,12 +836,12 @@ static ssize_t cifs_lookup_cache_proc_write(struct file *file, return count; } -static const struct file_operations cifs_lookup_cache_proc_fops = { - .open = cifs_lookup_cache_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_lookup_cache_proc_write, +static const struct proc_ops cifs_lookup_cache_proc_ops = { + .proc_open = cifs_lookup_cache_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifs_lookup_cache_proc_write, }; static int traceSMB_proc_show(struct seq_file *m, void *v) @@ -867,12 +867,12 @@ static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer, return count; } -static const struct file_operations traceSMB_proc_fops = { - .open = traceSMB_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = traceSMB_proc_write, +static const struct proc_ops traceSMB_proc_ops = { + .proc_open = traceSMB_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = traceSMB_proc_write, }; static int cifs_security_flags_proc_show(struct seq_file *m, void *v) @@ -978,12 +978,12 @@ static ssize_t cifs_security_flags_proc_write(struct file *file, return count; } -static const struct file_operations cifs_security_flags_proc_fops = { - .open = cifs_security_flags_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_security_flags_proc_write, +static const struct proc_ops cifs_security_flags_proc_ops = { + .proc_open = cifs_security_flags_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = cifs_security_flags_proc_write, }; #else inline void cifs_proc_init(void) diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 9a384d1e27b4..43c1b43a07ec 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -8,6 +8,7 @@ #include <linux/jhash.h> #include <linux/ktime.h> #include <linux/slab.h> +#include <linux/proc_fs.h> #include <linux/nls.h> #include <linux/workqueue.h> #include "cifsglob.h" @@ -211,12 +212,12 @@ static int dfscache_proc_open(struct inode *inode, struct file *file) return single_open(file, dfscache_proc_show, NULL); } -const struct file_operations dfscache_proc_fops = { - .open = dfscache_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = dfscache_proc_write, +const struct proc_ops dfscache_proc_ops = { + .proc_open = dfscache_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = dfscache_proc_write, }; #ifdef CONFIG_CIFS_DEBUG2 diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h index 76c732943f5f..99ee44f8ad07 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -24,7 +24,7 @@ struct dfs_cache_tgt_iterator { extern int dfs_cache_init(void); extern void dfs_cache_destroy(void); -extern const struct file_operations dfscache_proc_fops; +extern const struct proc_ops dfscache_proc_ops; extern int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nls_table *nls_codepage, int remap, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 88b213bd32bc..8434217549b3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6043,7 +6043,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, bh = ext4_bread(handle, inode, blk, EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL); - } while (IS_ERR(bh) && (PTR_ERR(bh) == -ENOSPC) && + } while (PTR_ERR(bh) == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); if (IS_ERR(bh)) return PTR_ERR(bh); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3314a0f3405e..9d02cdcdbb07 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -875,7 +875,7 @@ static int truncate_dnode(struct dnode_of_data *dn) /* get direct node */ page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); - if (IS_ERR(page) && PTR_ERR(page) == -ENOENT) + if (PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) return PTR_ERR(page); diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 9616af3768e1..08e91efbce53 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -111,7 +111,7 @@ extern void fscache_enqueue_object(struct fscache_object *); * object-list.c */ #ifdef CONFIG_FSCACHE_OBJECT_LIST -extern const struct file_operations fscache_objlist_fops; +extern const struct proc_ops fscache_objlist_proc_ops; extern void fscache_objlist_add(struct fscache_object *); extern void fscache_objlist_remove(struct fscache_object *); diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index 72ebfe578f40..e106a1a1600d 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -7,6 +7,7 @@ #define FSCACHE_DEBUG_LEVEL COOKIE #include <linux/module.h> +#include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/key.h> @@ -405,9 +406,9 @@ static int fscache_objlist_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -const struct file_operations fscache_objlist_fops = { - .open = fscache_objlist_open, - .read = seq_read, - .llseek = seq_lseek, - .release = fscache_objlist_release, +const struct proc_ops fscache_objlist_proc_ops = { + .proc_open = fscache_objlist_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = fscache_objlist_release, }; diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 5523446e2952..90a7bc22f7e1 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -35,7 +35,7 @@ int __init fscache_proc_init(void) #ifdef CONFIG_FSCACHE_OBJECT_LIST if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL, - &fscache_objlist_fops)) + &fscache_objlist_proc_ops)) goto error_objects; #endif diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 60bf8ff78913..eb8ca446d1ab 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1074,12 +1074,11 @@ static int jbd2_seq_info_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static const struct file_operations jbd2_seq_info_fops = { - .owner = THIS_MODULE, - .open = jbd2_seq_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = jbd2_seq_info_release, +static const struct proc_ops jbd2_info_proc_ops = { + .proc_open = jbd2_seq_info_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = jbd2_seq_info_release, }; static struct proc_dir_entry *proc_jbd2_stats; @@ -1089,7 +1088,7 @@ static void jbd2_stats_proc_init(journal_t *journal) journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { proc_create_data("info", S_IRUGO, journal->j_proc_entry, - &jbd2_seq_info_fops, journal); + &jbd2_info_proc_ops, journal); } } diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c index 888cdd685a1e..44b62b3c322e 100644 --- a/fs/jfs/jfs_debug.c +++ b/fs/jfs/jfs_debug.c @@ -43,12 +43,12 @@ static ssize_t jfs_loglevel_proc_write(struct file *file, return count; } -static const struct file_operations jfs_loglevel_proc_fops = { - .open = jfs_loglevel_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = jfs_loglevel_proc_write, +static const struct proc_ops jfs_loglevel_proc_ops = { + .proc_open = jfs_loglevel_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = jfs_loglevel_proc_write, }; #endif @@ -68,7 +68,7 @@ void jfs_proc_init(void) #endif #ifdef CONFIG_JFS_DEBUG proc_create_single("TxAnchor", 0, base, jfs_txanchor_proc_show); - proc_create("loglevel", 0, base, &jfs_loglevel_proc_fops); + proc_create("loglevel", 0, base, &jfs_loglevel_proc_ops); #endif } diff --git a/fs/lockd/procfs.c b/fs/lockd/procfs.c index ca9228a56d65..a01f08c8c2f3 100644 --- a/fs/lockd/procfs.c +++ b/fs/lockd/procfs.c @@ -60,11 +60,11 @@ nlm_end_grace_read(struct file *file, char __user *buf, size_t size, return simple_read_from_buffer(buf, size, pos, resp, sizeof(resp)); } -static const struct file_operations lockd_end_grace_operations = { - .write = nlm_end_grace_write, - .read = nlm_end_grace_read, - .llseek = default_llseek, - .release = simple_transaction_release, +static const struct proc_ops lockd_end_grace_proc_ops = { + .proc_write = nlm_end_grace_write, + .proc_read = nlm_end_grace_read, + .proc_lseek = default_llseek, + .proc_release = simple_transaction_release, }; int __init @@ -76,7 +76,7 @@ lockd_create_procfs(void) if (!entry) return -ENOMEM; entry = proc_create("nlm_end_grace", S_IRUGO|S_IWUSR, entry, - &lockd_end_grace_operations); + &lockd_end_grace_proc_ops); if (!entry) { remove_proc_entry("fs/lockd", NULL); return -ENOMEM; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 11b42c523f04..7eb919f1b13f 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -157,11 +157,11 @@ static int exports_proc_open(struct inode *inode, struct file *file) return exports_net_open(current->nsproxy->net_ns, file); } -static const struct file_operations exports_proc_operations = { - .open = exports_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops exports_proc_ops = { + .proc_open = exports_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static int exports_nfsd_open(struct inode *inode, struct file *file) @@ -1431,8 +1431,7 @@ static int create_proc_exports_entry(void) entry = proc_mkdir("fs/nfs", NULL); if (!entry) return -ENOMEM; - entry = proc_create("exports", 0, entry, - &exports_proc_operations); + entry = proc_create("exports", 0, entry, &exports_proc_ops); if (!entry) { remove_proc_entry("fs/nfs", NULL); return -ENOMEM; diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 9bce3b913189..b1bc582b0493 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -84,17 +84,17 @@ static int nfsd_proc_open(struct inode *inode, struct file *file) return single_open(file, nfsd_proc_show, NULL); } -static const struct file_operations nfsd_proc_fops = { - .open = nfsd_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops nfsd_proc_ops = { + .proc_open = nfsd_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; void nfsd_stat_init(void) { - svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_fops); + svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_ops); } void diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9876db52913a..6cd5e4924e4d 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2101,17 +2101,15 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos) static int ocfs2_inode_lock_for_extent_tree(struct inode *inode, struct buffer_head **di_bh, int meta_level, - int overwrite_io, int write_sem, int wait) { int ret = 0; if (wait) - ret = ocfs2_inode_lock(inode, NULL, meta_level); + ret = ocfs2_inode_lock(inode, di_bh, meta_level); else - ret = ocfs2_try_inode_lock(inode, - overwrite_io ? NULL : di_bh, meta_level); + ret = ocfs2_try_inode_lock(inode, di_bh, meta_level); if (ret < 0) goto out; @@ -2136,6 +2134,7 @@ static int ocfs2_inode_lock_for_extent_tree(struct inode *inode, out_unlock: brelse(*di_bh); + *di_bh = NULL; ocfs2_inode_unlock(inode, meta_level); out: return ret; @@ -2177,7 +2176,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file, ret = ocfs2_inode_lock_for_extent_tree(inode, &di_bh, meta_level, - overwrite_io, write_sem, wait); if (ret < 0) { @@ -2233,13 +2231,13 @@ static int ocfs2_prepare_inode_for_write(struct file *file, &di_bh, meta_level, write_sem); + meta_level = 1; + write_sem = 1; ret = ocfs2_inode_lock_for_extent_tree(inode, &di_bh, meta_level, - overwrite_io, - 1, + write_sem, wait); - write_sem = 1; if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 4180c3ef0a68..939df99d2dec 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -696,7 +696,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode, ac, cl); - if (IS_ERR(bg_bh) && (PTR_ERR(bg_bh) == -ENOSPC)) + if (PTR_ERR(bg_bh) == -ENOSPC) bg_bh = ocfs2_block_group_alloc_discontig(handle, alloc_inode, ac, cl); diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c index 96f1087e372c..c1dea9b8222e 100644 --- a/fs/proc/cpuinfo.c +++ b/fs/proc/cpuinfo.c @@ -16,16 +16,16 @@ static int cpuinfo_open(struct inode *inode, struct file *file) return seq_open(file, &cpuinfo_op); } -static const struct file_operations proc_cpuinfo_operations = { - .open = cpuinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops cpuinfo_proc_ops = { + .proc_open = cpuinfo_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static int __init proc_cpuinfo_init(void) { - proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations); + proc_create("cpuinfo", 0, NULL, &cpuinfo_proc_ops); return 0; } fs_initcall(proc_cpuinfo_init); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 074e9585c699..3faed94e4b65 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -473,7 +473,7 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, ent = __proc_create(&parent, name, S_IFDIR | mode, 2); if (ent) { ent->data = data; - ent->proc_fops = &proc_dir_operations; + ent->proc_dir_ops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; ent = proc_register(parent, ent); } @@ -503,7 +503,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) ent = __proc_create(&parent, name, mode, 2); if (ent) { ent->data = NULL; - ent->proc_fops = NULL; + ent->proc_dir_ops = NULL; ent->proc_iops = NULL; ent = proc_register(parent, ent); } @@ -533,25 +533,23 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, - const struct file_operations *proc_fops, void *data) + const struct proc_ops *proc_ops, void *data) { struct proc_dir_entry *p; - BUG_ON(proc_fops == NULL); - p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; - p->proc_fops = proc_fops; + p->proc_ops = proc_ops; return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_data); struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, - const struct file_operations *proc_fops) + const struct proc_ops *proc_ops) { - return proc_create_data(name, mode, parent, proc_fops, NULL); + return proc_create_data(name, mode, parent, proc_ops, NULL); } EXPORT_SYMBOL(proc_create); @@ -573,11 +571,11 @@ static int proc_seq_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static const struct file_operations proc_seq_fops = { - .open = proc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = proc_seq_release, +static const struct proc_ops proc_seq_ops = { + .proc_open = proc_seq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = proc_seq_release, }; struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, @@ -589,7 +587,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; - p->proc_fops = &proc_seq_fops; + p->proc_ops = &proc_seq_ops; p->seq_ops = ops; p->state_size = state_size; return proc_register(parent, p); @@ -603,11 +601,11 @@ static int proc_single_open(struct inode *inode, struct file *file) return single_open(file, de->single_show, de->data); } -static const struct file_operations proc_single_fops = { - .open = proc_single_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops proc_single_ops = { + .proc_open = proc_single_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, @@ -619,7 +617,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; - p->proc_fops = &proc_single_fops; + p->proc_ops = &proc_single_ops; p->single_show = show; return proc_register(parent, p); } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index dbe43a50caf2..6da18316d209 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -163,7 +163,7 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); file = pdeo->file; - pde->proc_fops->release(file_inode(file), file); + pde->proc_ops->proc_release(file_inode(file), file); spin_lock(&pde->pde_unload_lock); /* After ->release. */ list_del(&pdeo->lh); @@ -200,12 +200,12 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) struct proc_dir_entry *pde = PDE(file_inode(file)); loff_t rv = -EINVAL; if (use_pde(pde)) { - typeof_member(struct file_operations, llseek) llseek; + typeof_member(struct proc_ops, proc_lseek) lseek; - llseek = pde->proc_fops->llseek; - if (!llseek) - llseek = default_llseek; - rv = llseek(file, offset, whence); + lseek = pde->proc_ops->proc_lseek; + if (!lseek) + lseek = default_llseek; + rv = lseek(file, offset, whence); unuse_pde(pde); } return rv; @@ -216,9 +216,9 @@ static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (use_pde(pde)) { - typeof_member(struct file_operations, read) read; + typeof_member(struct proc_ops, proc_read) read; - read = pde->proc_fops->read; + read = pde->proc_ops->proc_read; if (read) rv = read(file, buf, count, ppos); unuse_pde(pde); @@ -231,9 +231,9 @@ static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (use_pde(pde)) { - typeof_member(struct file_operations, write) write; + typeof_member(struct proc_ops, proc_write) write; - write = pde->proc_fops->write; + write = pde->proc_ops->proc_write; if (write) rv = write(file, buf, count, ppos); unuse_pde(pde); @@ -246,9 +246,9 @@ static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts) struct proc_dir_entry *pde = PDE(file_inode(file)); __poll_t rv = DEFAULT_POLLMASK; if (use_pde(pde)) { - typeof_member(struct file_operations, poll) poll; + typeof_member(struct proc_ops, proc_poll) poll; - poll = pde->proc_fops->poll; + poll = pde->proc_ops->proc_poll; if (poll) rv = poll(file, pts); unuse_pde(pde); @@ -261,9 +261,9 @@ static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigne struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; if (use_pde(pde)) { - typeof_member(struct file_operations, unlocked_ioctl) ioctl; + typeof_member(struct proc_ops, proc_ioctl) ioctl; - ioctl = pde->proc_fops->unlocked_ioctl; + ioctl = pde->proc_ops->proc_ioctl; if (ioctl) rv = ioctl(file, cmd, arg); unuse_pde(pde); @@ -277,9 +277,9 @@ static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; if (use_pde(pde)) { - typeof_member(struct file_operations, compat_ioctl) compat_ioctl; + typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl; - compat_ioctl = pde->proc_fops->compat_ioctl; + compat_ioctl = pde->proc_ops->proc_compat_ioctl; if (compat_ioctl) rv = compat_ioctl(file, cmd, arg); unuse_pde(pde); @@ -293,9 +293,9 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) struct proc_dir_entry *pde = PDE(file_inode(file)); int rv = -EIO; if (use_pde(pde)) { - typeof_member(struct file_operations, mmap) mmap; + typeof_member(struct proc_ops, proc_mmap) mmap; - mmap = pde->proc_fops->mmap; + mmap = pde->proc_ops->proc_mmap; if (mmap) rv = mmap(file, vma); unuse_pde(pde); @@ -312,9 +312,9 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long rv = -EIO; if (use_pde(pde)) { - typeof_member(struct file_operations, get_unmapped_area) get_area; + typeof_member(struct proc_ops, proc_get_unmapped_area) get_area; - get_area = pde->proc_fops->get_unmapped_area; + get_area = pde->proc_ops->proc_get_unmapped_area; #ifdef CONFIG_MMU if (!get_area) get_area = current->mm->get_unmapped_area; @@ -333,8 +333,8 @@ static int proc_reg_open(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); int rv = 0; - typeof_member(struct file_operations, open) open; - typeof_member(struct file_operations, release) release; + typeof_member(struct proc_ops, proc_open) open; + typeof_member(struct proc_ops, proc_release) release; struct pde_opener *pdeo; /* @@ -351,7 +351,7 @@ static int proc_reg_open(struct inode *inode, struct file *file) if (!use_pde(pde)) return -ENOENT; - release = pde->proc_fops->release; + release = pde->proc_ops->proc_release; if (release) { pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); if (!pdeo) { @@ -360,7 +360,7 @@ static int proc_reg_open(struct inode *inode, struct file *file) } } - open = pde->proc_fops->open; + open = pde->proc_ops->proc_open; if (open) rv = open(inode, file); @@ -468,21 +468,23 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) inode->i_size = de->size; if (de->nlink) set_nlink(inode, de->nlink); - WARN_ON(!de->proc_iops); - inode->i_op = de->proc_iops; - if (de->proc_fops) { - if (S_ISREG(inode->i_mode)) { + + if (S_ISREG(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = &proc_reg_file_ops; #ifdef CONFIG_COMPAT - if (!de->proc_fops->compat_ioctl) - inode->i_fop = - &proc_reg_file_ops_no_compat; - else -#endif - inode->i_fop = &proc_reg_file_ops; - } else { - inode->i_fop = de->proc_fops; + if (!de->proc_ops->proc_compat_ioctl) { + inode->i_fop = &proc_reg_file_ops_no_compat; } - } +#endif + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = de->proc_dir_ops; + } else if (S_ISLNK(inode->i_mode)) { + inode->i_op = de->proc_iops; + inode->i_fop = NULL; + } else + BUG(); } else pde_put(de); return inode; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 0f3b557c9b77..41587276798e 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -39,7 +39,10 @@ struct proc_dir_entry { spinlock_t pde_unload_lock; struct completion *pde_unload_completion; const struct inode_operations *proc_iops; - const struct file_operations *proc_fops; + union { + const struct proc_ops *proc_ops; + const struct file_operations *proc_dir_ops; + }; const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index e2ed8e08cc7a..8ba492d44e68 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -574,11 +574,11 @@ static int release_kcore(struct inode *inode, struct file *file) return 0; } -static const struct file_operations proc_kcore_operations = { - .read = read_kcore, - .open = open_kcore, - .release = release_kcore, - .llseek = default_llseek, +static const struct proc_ops kcore_proc_ops = { + .proc_read = read_kcore, + .proc_open = open_kcore, + .proc_release = release_kcore, + .proc_lseek = default_llseek, }; /* just remember that we have to update kcore */ @@ -637,8 +637,7 @@ static void __init add_modules_range(void) static int __init proc_kcore_init(void) { - proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, - &proc_kcore_operations); + proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &kcore_proc_ops); if (!proc_root_kcore) { pr_err("couldn't create /proc/kcore\n"); return 0; /* Always returns 0. */ diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index 4f4a2abb225e..ec1b7d2fb773 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -49,17 +49,17 @@ static __poll_t kmsg_poll(struct file *file, poll_table *wait) } -static const struct file_operations proc_kmsg_operations = { - .read = kmsg_read, - .poll = kmsg_poll, - .open = kmsg_open, - .release = kmsg_release, - .llseek = generic_file_llseek, +static const struct proc_ops kmsg_proc_ops = { + .proc_read = kmsg_read, + .proc_poll = kmsg_poll, + .proc_open = kmsg_open, + .proc_release = kmsg_release, + .proc_lseek = generic_file_llseek, }; static int __init proc_kmsg_init(void) { - proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations); + proc_create("kmsg", S_IRUSR, NULL, &kmsg_proc_ops); return 0; } fs_initcall(proc_kmsg_init); diff --git a/fs/proc/page.c b/fs/proc/page.c index 7c952ee732e6..f909243d4a66 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -21,6 +21,21 @@ #define KPMMASK (KPMSIZE - 1) #define KPMBITS (KPMSIZE * BITS_PER_BYTE) +static inline unsigned long get_max_dump_pfn(void) +{ +#ifdef CONFIG_SPARSEMEM + /* + * The memmap of early sections is completely populated and marked + * online even if max_pfn does not fall on a section boundary - + * pfn_to_online_page() will succeed on all pages. Allow inspecting + * these memmaps. + */ + return round_up(max_pfn, PAGES_PER_SECTION); +#else + return max_pfn; +#endif +} + /* /proc/kpagecount - an array exposing page counts * * Each entry is a u64 representing the corresponding @@ -29,6 +44,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { + const unsigned long max_dump_pfn = get_max_dump_pfn(); u64 __user *out = (u64 __user *)buf; struct page *ppage; unsigned long src = *ppos; @@ -37,9 +53,11 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, u64 pcount; pfn = src / KPMSIZE; - count = min_t(size_t, count, (max_pfn * KPMSIZE) - src); if (src & KPMMASK || count & KPMMASK) return -EINVAL; + if (src >= max_dump_pfn * KPMSIZE) + return 0; + count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src); while (count > 0) { /* @@ -71,9 +89,9 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, return ret; } -static const struct file_operations proc_kpagecount_operations = { - .llseek = mem_lseek, - .read = kpagecount_read, +static const struct proc_ops kpagecount_proc_ops = { + .proc_lseek = mem_lseek, + .proc_read = kpagecount_read, }; /* /proc/kpageflags - an array exposing page flags @@ -206,6 +224,7 @@ u64 stable_page_flags(struct page *page) static ssize_t kpageflags_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { + const unsigned long max_dump_pfn = get_max_dump_pfn(); u64 __user *out = (u64 __user *)buf; struct page *ppage; unsigned long src = *ppos; @@ -213,9 +232,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, ssize_t ret = 0; pfn = src / KPMSIZE; - count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); if (src & KPMMASK || count & KPMMASK) return -EINVAL; + if (src >= max_dump_pfn * KPMSIZE) + return 0; + count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src); while (count > 0) { /* @@ -242,15 +263,16 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, return ret; } -static const struct file_operations proc_kpageflags_operations = { - .llseek = mem_lseek, - .read = kpageflags_read, +static const struct proc_ops kpageflags_proc_ops = { + .proc_lseek = mem_lseek, + .proc_read = kpageflags_read, }; #ifdef CONFIG_MEMCG static ssize_t kpagecgroup_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { + const unsigned long max_dump_pfn = get_max_dump_pfn(); u64 __user *out = (u64 __user *)buf; struct page *ppage; unsigned long src = *ppos; @@ -259,9 +281,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, u64 ino; pfn = src / KPMSIZE; - count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); if (src & KPMMASK || count & KPMMASK) return -EINVAL; + if (src >= max_dump_pfn * KPMSIZE) + return 0; + count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src); while (count > 0) { /* @@ -293,18 +317,18 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, return ret; } -static const struct file_operations proc_kpagecgroup_operations = { - .llseek = mem_lseek, - .read = kpagecgroup_read, +static const struct proc_ops kpagecgroup_proc_ops = { + .proc_lseek = mem_lseek, + .proc_read = kpagecgroup_read, }; #endif /* CONFIG_MEMCG */ static int __init proc_page_init(void) { - proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations); - proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations); + proc_create("kpagecount", S_IRUSR, NULL, &kpagecount_proc_ops); + proc_create("kpageflags", S_IRUSR, NULL, &kpageflags_proc_ops); #ifdef CONFIG_MEMCG - proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations); + proc_create("kpagecgroup", S_IRUSR, NULL, &kpagecgroup_proc_ops); #endif return 0; } diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 76ae278df1c4..4888c5224442 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -90,12 +90,12 @@ static int seq_release_net(struct inode *ino, struct file *f) return 0; } -static const struct file_operations proc_net_seq_fops = { - .open = seq_open_net, - .read = seq_read, - .write = proc_simple_write, - .llseek = seq_lseek, - .release = seq_release_net, +static const struct proc_ops proc_net_seq_ops = { + .proc_open = seq_open_net, + .proc_read = seq_read, + .proc_write = proc_simple_write, + .proc_lseek = seq_lseek, + .proc_release = seq_release_net, }; struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, @@ -108,7 +108,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, if (!p) return NULL; pde_force_lookup(p); - p->proc_fops = &proc_net_seq_fops; + p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; return proc_register(parent, p); @@ -152,7 +152,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode if (!p) return NULL; pde_force_lookup(p); - p->proc_fops = &proc_net_seq_fops; + p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; p->write = write; @@ -183,12 +183,12 @@ static int single_release_net(struct inode *ino, struct file *f) return single_release(ino, f); } -static const struct file_operations proc_net_single_fops = { - .open = single_open_net, - .read = seq_read, - .write = proc_simple_write, - .llseek = seq_lseek, - .release = single_release_net, +static const struct proc_ops proc_net_single_ops = { + .proc_open = single_open_net, + .proc_read = seq_read, + .proc_write = proc_simple_write, + .proc_lseek = seq_lseek, + .proc_release = single_release_net, }; struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, @@ -201,7 +201,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, if (!p) return NULL; pde_force_lookup(p); - p->proc_fops = &proc_net_single_fops; + p->proc_ops = &proc_net_single_ops; p->single_show = show; return proc_register(parent, p); } @@ -244,7 +244,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo if (!p) return NULL; pde_force_lookup(p); - p->proc_fops = &proc_net_single_fops; + p->proc_ops = &proc_net_single_ops; p->single_show = show; p->write = write; return proc_register(parent, p); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d80989b6c344..c75bb4632ed1 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1720,7 +1720,7 @@ int __init proc_sys_init(void) proc_sys_root = proc_mkdir("sys", NULL); proc_sys_root->proc_iops = &proc_sys_dir_operations; - proc_sys_root->proc_fops = &proc_sys_dir_file_operations; + proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations; proc_sys_root->nlink = 0; return sysctl_init(); diff --git a/fs/proc/root.c b/fs/proc/root.c index 0b7c8dffc9ae..72c07a34cff0 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -292,7 +292,7 @@ struct proc_dir_entry proc_root = { .nlink = 2, .refcnt = REFCOUNT_INIT(1), .proc_iops = &proc_root_inode_operations, - .proc_fops = &proc_root_operations, + .proc_dir_ops = &proc_root_operations, .parent = &proc_root, .subdir = RB_ROOT, .name = "/proc", diff --git a/fs/proc/stat.c b/fs/proc/stat.c index fd931d3e77be..0449edf460f5 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -223,16 +223,16 @@ static int stat_open(struct inode *inode, struct file *file) return single_open_size(file, show_stat, NULL, size); } -static const struct file_operations proc_stat_operations = { - .open = stat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops stat_proc_ops = { + .proc_open = stat_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; static int __init proc_stat_init(void) { - proc_create("stat", 0, NULL, &proc_stat_operations); + proc_create("stat", 0, NULL, &stat_proc_ops); return 0; } fs_initcall(proc_stat_init); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 9442631fd4af..3ba9ae83bff5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -505,7 +505,7 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, #ifdef CONFIG_SHMEM static int smaps_pte_hole(unsigned long addr, unsigned long end, - struct mm_walk *walk) + __always_unused int depth, struct mm_walk *walk) { struct mem_size_stats *mss = walk->private; @@ -1282,7 +1282,7 @@ static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme, } static int pagemap_pte_hole(unsigned long start, unsigned long end, - struct mm_walk *walk) + __always_unused int depth, struct mm_walk *walk) { struct pagemapread *pm = walk->private; unsigned long addr = start; diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 7b13988796e1..7dc800cce354 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -667,10 +667,10 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) } #endif -static const struct file_operations proc_vmcore_operations = { - .read = read_vmcore, - .llseek = default_llseek, - .mmap = mmap_vmcore, +static const struct proc_ops vmcore_proc_ops = { + .proc_read = read_vmcore, + .proc_lseek = default_llseek, + .proc_mmap = mmap_vmcore, }; static struct vmcore* __init get_new_element(void) @@ -1555,7 +1555,7 @@ static int __init vmcore_init(void) elfcorehdr_free(elfcorehdr_addr); elfcorehdr_addr = ELFCORE_ADDR_ERR; - proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations); + proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &vmcore_proc_ops); if (proc_vmcore) proc_vmcore->size = vmcore_size; return 0; diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index d41c21fef138..c4ab045926b7 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -449,7 +449,7 @@ int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, } link = kernfs_create_link(kobj->sd, target_name, entry); - if (IS_ERR(link) && PTR_ERR(link) == -EEXIST) + if (PTR_ERR(link) == -EEXIST) sysfs_warn_dup(kobj->sd, target_name); kernfs_put(entry); diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 798ea36a0549..e2e2bef07dd2 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1238,4 +1238,24 @@ static inline bool arch_has_pfn_modify_check(void) #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif +/* + * p?d_leaf() - true if this entry is a final mapping to a physical address. + * This differs from p?d_huge() by the fact that they are always available (if + * the architecture supports large pages at the appropriate level) even + * if CONFIG_HUGETLB_PAGE is not defined. + * Only meaningful when called on a valid entry. + */ +#ifndef pgd_leaf +#define pgd_leaf(x) 0 +#endif +#ifndef p4d_leaf +#define p4d_leaf(x) 0 +#endif +#ifndef pud_leaf +#define pud_leaf(x) 0 +#endif +#ifndef pmd_leaf +#define pmd_leaf(x) 0 +#endif + #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 2b10036fefd0..f391f6b500b4 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -56,6 +56,15 @@ * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * + * - tlb_remove_table() + * + * tlb_remove_table() is the basic primitive to free page-table directories + * (__p*_free_tlb()). In it's most primitive form it is an alias for + * tlb_remove_page() below, for when page directories are pages and have no + * additional constraints. + * + * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. + * * - tlb_remove_page() / __tlb_remove_page() * - tlb_remove_page_size() / __tlb_remove_page_size() * @@ -121,65 +130,53 @@ * * Additionally there are a few opt-in features: * - * HAVE_MMU_GATHER_PAGE_SIZE + * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * - * HAVE_RCU_TABLE_FREE + * This might be useful if your architecture has size specific TLB + * invalidation instructions. + * + * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() - * for page directores (__p*_free_tlb()). This provides separate freeing of - * the page-table pages themselves in a semi-RCU fashion (see comment below). - * Useful if your architecture doesn't use IPIs for remote TLB invalidates - * and therefore doesn't naturally serialize with software page-table walkers. + * for page directores (__p*_free_tlb()). + * + * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() * which does the actual freeing of these pages. * - * HAVE_RCU_TABLE_NO_INVALIDATE + * MMU_GATHER_RCU_TABLE_FREE * - * This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before - * freeing the page-table pages. This can be avoided if you use - * HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux - * page-tables natively. + * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see + * comment below). + * + * Useful if your architecture doesn't use IPIs for remote TLB invalidates + * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). - */ - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -/* - * Semi RCU freeing of the page directories. - * - * This is needed by some architectures to implement software pagetable walkers. * - * gup_fast() and other software pagetable walkers do a lockless page-table - * walk and therefore needs some synchronization with the freeing of the page - * directories. The chosen means to accomplish that is by disabling IRQs over - * the walk. + * MMU_GATHER_NO_GATHER * - * Architectures that use IPIs to flush TLBs will then automagically DTRT, - * since we unlink the page, flush TLBs, free the page. Since the disabling of - * IRQs delays the completion of the TLB flush we can never observe an already - * freed page. - * - * Architectures that do not have this (PPC) need to delay the freeing by some - * other means, this is that means. - * - * What we do is batch the freed directory pages (tables) and RCU free them. - * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling - * holds off grace periods. - * - * However, in order to batch these pages we need to allocate storage, this - * allocation is deep inside the MM code and can thus easily fail on memory - * pressure. To guarantee progress we fall back to single table freeing, see - * the implementation of tlb_remove_table_one(). + * If the option is set the mmu_gather will not track individual pages for + * delayed page free anymore. A platform that enables the option needs to + * provide its own implementation of the __tlb_remove_page_size() function to + * free pages. * + * This is useful if your architecture already flushes TLB entries in the + * various ptep_get_and_clear() functions. */ + +#ifdef CONFIG_MMU_GATHER_TABLE_FREE + struct mmu_table_batch { +#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; +#endif unsigned int nr; void *tables[0]; }; @@ -189,9 +186,35 @@ struct mmu_table_batch { extern void tlb_remove_table(struct mmu_gather *tlb, void *table); +#else /* !CONFIG_MMU_GATHER_HAVE_TABLE_FREE */ + +/* + * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based + * page directories and we can use the normal page batching to free them. + */ +#define tlb_remove_table(tlb, page) tlb_remove_page((tlb), (page)) + +#endif /* CONFIG_MMU_GATHER_TABLE_FREE */ + +#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE +/* + * This allows an architecture that does not use the linux page-tables for + * hardware to skip the TLBI when freeing page tables. + */ +#ifndef tlb_needs_table_invalidate +#define tlb_needs_table_invalidate() (true) #endif -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER +#else + +#ifdef tlb_needs_table_invalidate +#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE +#endif + +#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ + + +#ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. @@ -227,7 +250,7 @@ extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, struct mmu_gather { struct mm_struct *mm; -#ifdef CONFIG_HAVE_RCU_TABLE_FREE +#ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; #endif @@ -266,22 +289,18 @@ struct mmu_gather { unsigned int batch_count; -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER +#ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; -#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE +#ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif #endif }; -void arch_tlb_gather_mmu(struct mmu_gather *tlb, - struct mm_struct *mm, unsigned long start, unsigned long end); void tlb_flush_mmu(struct mmu_gather *tlb); -void arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end, bool force); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, @@ -394,7 +413,12 @@ tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { - if (!tlb->end) + /* + * Anything calling __tlb_adjust_range() also sets at least one of + * these bits. + */ + if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || + tlb->cleared_puds || tlb->cleared_p4ds)) return; tlb_flush(tlb); @@ -426,7 +450,7 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { -#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE +#ifdef CONFIG_MMU_GATHER_PAGE_SIZE if (tlb->page_size && tlb->page_size != page_size) { if (!tlb->fullmm && !tlb->need_flush_all) tlb_flush_mmu(tlb); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 80ad521116d7..e52ceb1a73d3 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -186,7 +186,7 @@ bitmap_find_next_zero_area(unsigned long *map, align_mask, 0); } -extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, +extern int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits); extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); @@ -454,12 +454,6 @@ static inline void bitmap_replace(unsigned long *dst, __bitmap_replace(dst, old, new, mask, nbits); } -static inline int bitmap_parse(const char *buf, unsigned int buflen, - unsigned long *maskp, int nmaskbits) -{ - return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits); -} - static inline void bitmap_next_clear_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 6c7c4133c25c..47f54b459c26 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -11,8 +11,10 @@ # define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) #endif -#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) +#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) +#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) extern unsigned int __sw_hweight8(unsigned int w); diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 78a73eba64dd..d5cc88514aee 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -663,9 +663,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, */ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) { - unsigned int len = strchrnul(buf, '\n') - buf; - - return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits); + return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ffa6ad12d84a..f4d59155f3d4 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -96,8 +96,8 @@ extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); /* VM interface that may be used by firmware interface */ extern int online_pages(unsigned long pfn, unsigned long nr_pages, int online_type, int nid); -extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, - unsigned long *valid_start, unsigned long *valid_end); +extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, + unsigned long end_pfn); extern unsigned long __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn); diff --git a/include/linux/mm.h b/include/linux/mm.h index faa3bb5fe633..52269e56c514 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2182,12 +2182,6 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#if !defined(CONFIG_FLAT_NODE_MEM_MAP) -void zero_resv_unavail(void); -#else -static inline void zero_resv_unavail(void) {} -#endif - extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context, struct vmem_altmap *); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c2bc309d1634..462f6873905a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1379,6 +1379,16 @@ static inline int pfn_present(unsigned long pfn) return present_section(__nr_to_section(pfn_to_section_nr(pfn))); } +static inline unsigned long next_present_section_nr(unsigned long section_nr) +{ + while (++section_nr <= __highest_present_section_nr) { + if (present_section_nr(section_nr)) + return section_nr; + } + + return -1; +} + /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 6ec82e92c87f..b1cb6b753abb 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -8,16 +8,19 @@ struct mm_walk; /** * mm_walk_ops - callbacks for walk_page_range - * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry - * this handler should only handle pud_trans_huge() puds. - * the pmd_entry or pte_entry callbacks will be used for - * regular PUDs. - * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry + * @pgd_entry: if set, called for each non-empty PGD (top-level) entry + * @p4d_entry: if set, called for each non-empty P4D entry + * @pud_entry: if set, called for each non-empty PUD entry + * @pmd_entry: if set, called for each non-empty PMD entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each non-empty PTE (4th-level) entry - * @pte_hole: if set, called for each hole at all levels + * @pte_entry: if set, called for each non-empty PTE (lowest-level) + * entry + * @pte_hole: if set, called for each hole at all levels, + * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD + * 4:PTE. Any folded depths (where PTRS_PER_P?D is equal + * to 1) are skipped. * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether * we walk over the current vma or not. Returning 0 means @@ -27,8 +30,15 @@ struct mm_walk; * @pre_vma: if set, called before starting walk on a non-null vma. * @post_vma: if set, called after a walk on a non-null vma, provided * that @pre_vma and the vma walk succeeded. + * + * p?d_entry callbacks are called even if those levels are folded on a + * particular architecture/configuration. */ struct mm_walk_ops { + int (*pgd_entry)(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*p4d_entry)(p4d_t *p4d, unsigned long addr, + unsigned long next, struct mm_walk *walk); int (*pud_entry)(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr, @@ -36,7 +46,7 @@ struct mm_walk_ops { int (*pte_entry)(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pte_hole)(unsigned long addr, unsigned long next, - struct mm_walk *walk); + int depth, struct mm_walk *walk); int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long next, struct mm_walk *walk); @@ -47,11 +57,27 @@ struct mm_walk_ops { void (*post_vma)(struct mm_walk *walk); }; +/* + * Action for pud_entry / pmd_entry callbacks. + * ACTION_SUBTREE is the default + */ +enum page_walk_action { + /* Descend to next level, splitting huge pages if needed and possible */ + ACTION_SUBTREE = 0, + /* Continue to next entry at this level (ignoring any subtree) */ + ACTION_CONTINUE = 1, + /* Call again for this entry */ + ACTION_AGAIN = 2 +}; + /** * mm_walk - walk_page_range data * @ops: operation to call during the walk * @mm: mm_struct representing the target process of page table walk + * @pgd: pointer to PGD; only valid with no_vma (otherwise set to NULL) * @vma: vma currently walked (NULL if walking outside vmas) + * @action: next action to perform (see enum page_walk_action) + * @no_vma: walk ignoring vmas (vma will always be NULL) * @private: private data for callbacks' usage * * (see the comment on walk_page_range() for more details) @@ -59,13 +85,20 @@ struct mm_walk_ops { struct mm_walk { const struct mm_walk_ops *ops; struct mm_struct *mm; + pgd_t *pgd; struct vm_area_struct *vma; + enum page_walk_action action; + bool no_vma; void *private; }; int walk_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); +int walk_page_range_novma(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + pgd_t *pgd, + void *private); int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private); int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0640be56dcbd..3dfa92633af3 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -12,6 +12,21 @@ struct proc_dir_entry; struct seq_file; struct seq_operations; +struct proc_ops { + int (*proc_open)(struct inode *, struct file *); + ssize_t (*proc_read)(struct file *, char __user *, size_t, loff_t *); + ssize_t (*proc_write)(struct file *, const char __user *, size_t, loff_t *); + loff_t (*proc_lseek)(struct file *, loff_t, int); + int (*proc_release)(struct inode *, struct file *); + __poll_t (*proc_poll)(struct file *, struct poll_table_struct *); + long (*proc_ioctl)(struct file *, unsigned int, unsigned long); +#ifdef CONFIG_COMPAT + long (*proc_compat_ioctl)(struct file *, unsigned int, unsigned long); +#endif + int (*proc_mmap)(struct file *, struct vm_area_struct *); + unsigned long (*proc_get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); +}; + #ifdef CONFIG_PROC_FS typedef int (*proc_write_t)(struct file *, char *, size_t); @@ -43,10 +58,10 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *, - const struct file_operations *, + const struct proc_ops *, void *); -struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops); +struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); extern void *PDE_DATA(const struct inode *); @@ -108,8 +123,8 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, #define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create_single(name, mode, parent, show) ({NULL;}) #define proc_create_single_data(name, mode, parent, show, data) ({NULL;}) -#define proc_create(name, mode, parent, proc_fops) ({NULL;}) -#define proc_create_data(name, mode, parent, proc_fops, data) ({NULL;}) +#define proc_create(name, mode, parent, proc_ops) ({NULL;}) +#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;}) static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h new file mode 100644 index 000000000000..a67065c403c3 --- /dev/null +++ b/include/linux/ptdump.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PTDUMP_H +#define _LINUX_PTDUMP_H + +#include <linux/mm_types.h> + +struct ptdump_range { + unsigned long start; + unsigned long end; +}; + +struct ptdump_state { + /* level is 0:PGD to 4:PTE, or -1 if unknown */ + void (*note_page)(struct ptdump_state *st, unsigned long addr, + int level, unsigned long val); + const struct ptdump_range *range; +}; + +void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd); + +#endif /* _LINUX_PTDUMP_H */ diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 5998e1f4ff06..770c2bf3aa43 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -160,6 +160,19 @@ static const struct file_operations __name ## _fops = { \ .release = single_release, \ } +#define DEFINE_PROC_SHOW_ATTRIBUTE(__name) \ +static int __name ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, __name ## _show, inode->i_private); \ +} \ + \ +static const struct proc_ops __name ## _proc_ops = { \ + .proc_open = __name ## _open, \ + .proc_read = seq_read, \ + .proc_lseek = seq_lseek, \ + .proc_release = single_release, \ +} + static inline struct user_namespace *seq_user_ns(struct seq_file *seq) { #ifdef CONFIG_USER_NS diff --git a/include/linux/slab.h b/include/linux/slab.h index 877a95c6a2d2..03a389358562 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -184,7 +184,6 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *); /* * Common kmalloc functions provided by all allocators */ -void * __must_check __krealloc(const void *, size_t, gfp_t); void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kzfree(const void *); diff --git a/include/linux/string.h b/include/linux/string.h index 02894e417565..6dfbb2efa815 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -62,6 +62,7 @@ extern char * strchr(const char *,int); #ifndef __HAVE_ARCH_STRCHRNUL extern char * strchrnul(const char *,int); #endif +extern char * strnchrnul(const char *, size_t, int); #ifndef __HAVE_ARCH_STRNCHR extern char * strnchr(const char *, size_t, int); #endif diff --git a/include/linux/sunrpc/stats.h b/include/linux/sunrpc/stats.h index 84b92b4ad1c0..d94d4f410507 100644 --- a/include/linux/sunrpc/stats.h +++ b/include/linux/sunrpc/stats.h @@ -63,7 +63,7 @@ struct proc_dir_entry * rpc_proc_register(struct net *,struct rpc_stat *); void rpc_proc_unregister(struct net *,const char *); void rpc_proc_zero(const struct rpc_program *); struct proc_dir_entry * svc_proc_register(struct net *, struct svc_stat *, - const struct file_operations *); + const struct proc_ops *); void svc_proc_unregister(struct net *, const char *); void svc_seq_show(struct seq_file *, @@ -75,7 +75,7 @@ static inline void rpc_proc_unregister(struct net *net, const char *p) {} static inline void rpc_proc_zero(const struct rpc_program *p) {} static inline struct proc_dir_entry *svc_proc_register(struct net *net, struct svc_stat *s, - const struct file_operations *f) { return NULL; } + const struct proc_ops *proc_ops) { return NULL; } static inline void svc_proc_unregister(struct net *net, const char *p) {} static inline void svc_seq_show(struct seq_file *seq, diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 3d920ff15c80..49a05ba3000d 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -63,6 +63,66 @@ struct posix_msg_tree_node { int priority; }; +/* + * Locking: + * + * Accesses to a message queue are synchronized by acquiring info->lock. + * + * There are two notable exceptions: + * - The actual wakeup of a sleeping task is performed using the wake_q + * framework. info->lock is already released when wake_up_q is called. + * - The exit codepaths after sleeping check ext_wait_queue->state without + * any locks. If it is STATE_READY, then the syscall is completed without + * acquiring info->lock. + * + * MQ_BARRIER: + * To achieve proper release/acquire memory barrier pairing, the state is set to + * STATE_READY with smp_store_release(), and it is read with READ_ONCE followed + * by smp_acquire__after_ctrl_dep(). In addition, wake_q_add_safe() is used. + * + * This prevents the following races: + * + * 1) With the simple wake_q_add(), the task could be gone already before + * the increase of the reference happens + * Thread A + * Thread B + * WRITE_ONCE(wait.state, STATE_NONE); + * schedule_hrtimeout() + * wake_q_add(A) + * if (cmpxchg()) // success + * ->state = STATE_READY (reordered) + * <timeout returns> + * if (wait.state == STATE_READY) return; + * sysret to user space + * sys_exit() + * get_task_struct() // UaF + * + * Solution: Use wake_q_add_safe() and perform the get_task_struct() before + * the smp_store_release() that does ->state = STATE_READY. + * + * 2) Without proper _release/_acquire barriers, the woken up task + * could read stale data + * + * Thread A + * Thread B + * do_mq_timedreceive + * WRITE_ONCE(wait.state, STATE_NONE); + * schedule_hrtimeout() + * state = STATE_READY; + * <timeout returns> + * if (wait.state == STATE_READY) return; + * msg_ptr = wait.msg; // Access to stale data! + * receiver->msg = message; (reordered) + * + * Solution: use _release and _acquire barriers. + * + * 3) There is intentionally no barrier when setting current->state + * to TASK_INTERRUPTIBLE: spin_unlock(&info->lock) provides the + * release memory barrier, and the wakeup is triggered when holding + * info->lock, i.e. spin_lock(&info->lock) provided a pairing + * acquire memory barrier. + */ + struct ext_wait_queue { /* queue of sleeping tasks */ struct task_struct *task; struct list_head list; @@ -646,18 +706,23 @@ static int wq_sleep(struct mqueue_inode_info *info, int sr, wq_add(info, sr, ewp); for (;;) { + /* memory barrier not required, we hold info->lock */ __set_current_state(TASK_INTERRUPTIBLE); spin_unlock(&info->lock); time = schedule_hrtimeout_range_clock(timeout, 0, HRTIMER_MODE_ABS, CLOCK_REALTIME); - if (ewp->state == STATE_READY) { + if (READ_ONCE(ewp->state) == STATE_READY) { + /* see MQ_BARRIER for purpose/pairing */ + smp_acquire__after_ctrl_dep(); retval = 0; goto out; } spin_lock(&info->lock); - if (ewp->state == STATE_READY) { + + /* we hold info->lock, so no memory barrier required */ + if (READ_ONCE(ewp->state) == STATE_READY) { retval = 0; goto out_unlock; } @@ -918,6 +983,18 @@ out_name: * The same algorithm is used for senders. */ +static inline void __pipelined_op(struct wake_q_head *wake_q, + struct mqueue_inode_info *info, + struct ext_wait_queue *this) +{ + list_del(&this->list); + get_task_struct(this->task); + + /* see MQ_BARRIER for purpose/pairing */ + smp_store_release(&this->state, STATE_READY); + wake_q_add_safe(wake_q, this->task); +} + /* pipelined_send() - send a message directly to the task waiting in * sys_mq_timedreceive() (without inserting message into a queue). */ @@ -927,17 +1004,7 @@ static inline void pipelined_send(struct wake_q_head *wake_q, struct ext_wait_queue *receiver) { receiver->msg = message; - list_del(&receiver->list); - wake_q_add(wake_q, receiver->task); - /* - * Rely on the implicit cmpxchg barrier from wake_q_add such - * that we can ensure that updating receiver->state is the last - * write operation: As once set, the receiver can continue, - * and if we don't have the reference count from the wake_q, - * yet, at that point we can later have a use-after-free - * condition and bogus wakeup. - */ - receiver->state = STATE_READY; + __pipelined_op(wake_q, info, receiver); } /* pipelined_receive() - if there is task waiting in sys_mq_timedsend() @@ -955,9 +1022,7 @@ static inline void pipelined_receive(struct wake_q_head *wake_q, if (msg_insert(sender->msg, info)) return; - list_del(&sender->list); - wake_q_add(wake_q, sender->task); - sender->state = STATE_READY; + __pipelined_op(wake_q, info, sender); } static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, @@ -1044,7 +1109,9 @@ static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, } else { wait.task = current; wait.msg = (void *) msg_ptr; - wait.state = STATE_NONE; + + /* memory barrier not required, we hold info->lock */ + WRITE_ONCE(wait.state, STATE_NONE); ret = wq_sleep(info, SEND, timeout, &wait); /* * wq_sleep must be called with info->lock held, and @@ -1147,7 +1214,9 @@ static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, ret = -EAGAIN; } else { wait.task = current; - wait.state = STATE_NONE; + + /* memory barrier not required, we hold info->lock */ + WRITE_ONCE(wait.state, STATE_NONE); ret = wq_sleep(info, RECV, timeout, &wait); msg_ptr = wait.msg; } diff --git a/ipc/msg.c b/ipc/msg.c index 8dec945fa030..caca67368cb5 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -61,6 +61,16 @@ struct msg_queue { struct list_head q_senders; } __randomize_layout; +/* + * MSG_BARRIER Locking: + * + * Similar to the optimization used in ipc/mqueue.c, one syscall return path + * does not acquire any locks when it sees that a message exists in + * msg_receiver.r_msg. Therefore r_msg is set using smp_store_release() + * and accessed using READ_ONCE()+smp_acquire__after_ctrl_dep(). In addition, + * wake_q_add_safe() is used. See ipc/mqueue.c for more details + */ + /* one msg_receiver structure for each sleeping receiver */ struct msg_receiver { struct list_head r_list; @@ -184,6 +194,10 @@ static inline void ss_add(struct msg_queue *msq, { mss->tsk = current; mss->msgsz = msgsz; + /* + * No memory barrier required: we did ipc_lock_object(), + * and the waker obtains that lock before calling wake_q_add(). + */ __set_current_state(TASK_INTERRUPTIBLE); list_add_tail(&mss->list, &msq->q_senders); } @@ -237,8 +251,11 @@ static void expunge_all(struct msg_queue *msq, int res, struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { - wake_q_add(wake_q, msr->r_tsk); - WRITE_ONCE(msr->r_msg, ERR_PTR(res)); + get_task_struct(msr->r_tsk); + + /* see MSG_BARRIER for purpose/pairing */ + smp_store_release(&msr->r_msg, ERR_PTR(res)); + wake_q_add_safe(wake_q, msr->r_tsk); } } @@ -377,7 +394,7 @@ copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, - struct msqid64_ds *msqid64) + struct ipc64_perm *perm, int msg_qbytes) { struct kern_ipc_perm *ipcp; struct msg_queue *msq; @@ -387,7 +404,7 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &msg_ids(ns), msqid, cmd, - &msqid64->msg_perm, msqid64->msg_qbytes); + perm, msg_qbytes); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; @@ -409,18 +426,18 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, { DEFINE_WAKE_Q(wake_q); - if (msqid64->msg_qbytes > ns->msg_ctlmnb && + if (msg_qbytes > ns->msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) { err = -EPERM; goto out_unlock1; } ipc_lock_object(&msq->q_perm); - err = ipc_update_perm(&msqid64->msg_perm, ipcp); + err = ipc_update_perm(perm, ipcp); if (err) goto out_unlock0; - msq->q_qbytes = msqid64->msg_qbytes; + msq->q_qbytes = msg_qbytes; msq->q_ctime = ktime_get_real_seconds(); /* @@ -601,9 +618,10 @@ static long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf, int ver case IPC_SET: if (copy_msqid_from_user(&msqid64, buf, version)) return -EFAULT; - /* fallthru */ + return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, + msqid64.msg_qbytes); case IPC_RMID: - return msgctl_down(ns, msqid, cmd, &msqid64); + return msgctl_down(ns, msqid, cmd, NULL, 0); default: return -EINVAL; } @@ -735,9 +753,9 @@ static long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr, int versio case IPC_SET: if (copy_compat_msqid_from_user(&msqid64, uptr, version)) return -EFAULT; - /* fallthru */ + return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); case IPC_RMID: - return msgctl_down(ns, msqid, cmd, &msqid64); + return msgctl_down(ns, msqid, cmd, NULL, 0); default: return -EINVAL; } @@ -798,13 +816,17 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, list_del(&msr->r_list); if (msr->r_maxsize < msg->m_ts) { wake_q_add(wake_q, msr->r_tsk); - WRITE_ONCE(msr->r_msg, ERR_PTR(-E2BIG)); + + /* See expunge_all regarding memory barrier */ + smp_store_release(&msr->r_msg, ERR_PTR(-E2BIG)); } else { ipc_update_pid(&msq->q_lrpid, task_pid(msr->r_tsk)); msq->q_rtime = ktime_get_real_seconds(); wake_q_add(wake_q, msr->r_tsk); - WRITE_ONCE(msr->r_msg, msg); + + /* See expunge_all regarding memory barrier */ + smp_store_release(&msr->r_msg, msg); return 1; } } @@ -1154,7 +1176,11 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in msr_d.r_maxsize = INT_MAX; else msr_d.r_maxsize = bufsz; - msr_d.r_msg = ERR_PTR(-EAGAIN); + + /* memory barrier not require due to ipc_lock_object() */ + WRITE_ONCE(msr_d.r_msg, ERR_PTR(-EAGAIN)); + + /* memory barrier not required, we own ipc_lock_object() */ __set_current_state(TASK_INTERRUPTIBLE); ipc_unlock_object(&msq->q_perm); @@ -1183,8 +1209,12 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in * signal) it will either see the message and continue ... */ msg = READ_ONCE(msr_d.r_msg); - if (msg != ERR_PTR(-EAGAIN)) + if (msg != ERR_PTR(-EAGAIN)) { + /* see MSG_BARRIER for purpose/pairing */ + smp_acquire__after_ctrl_dep(); + goto out_unlock1; + } /* * ... or see -EAGAIN, acquire the lock to check the message @@ -1192,7 +1222,7 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in */ ipc_lock_object(&msq->q_perm); - msg = msr_d.r_msg; + msg = READ_ONCE(msr_d.r_msg); if (msg != ERR_PTR(-EAGAIN)) goto out_unlock0; diff --git a/ipc/sem.c b/ipc/sem.c index ec97a7072413..4f4303f32077 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -205,15 +205,38 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); * * Memory ordering: * Most ordering is enforced by using spin_lock() and spin_unlock(). - * The special case is use_global_lock: + * + * Exceptions: + * 1) use_global_lock: (SEM_BARRIER_1) * Setting it from non-zero to 0 is a RELEASE, this is ensured by - * using smp_store_release(). + * using smp_store_release(): Immediately after setting it to 0, + * a simple op can start. * Testing if it is non-zero is an ACQUIRE, this is ensured by using * smp_load_acquire(). * Setting it from 0 to non-zero must be ordered with regards to * this smp_load_acquire(), this is guaranteed because the smp_load_acquire() * is inside a spin_lock() and after a write from 0 to non-zero a * spin_lock()+spin_unlock() is done. + * + * 2) queue.status: (SEM_BARRIER_2) + * Initialization is done while holding sem_lock(), so no further barrier is + * required. + * Setting it to a result code is a RELEASE, this is ensured by both a + * smp_store_release() (for case a) and while holding sem_lock() + * (for case b). + * The AQUIRE when reading the result code without holding sem_lock() is + * achieved by using READ_ONCE() + smp_acquire__after_ctrl_dep(). + * (case a above). + * Reading the result code while holding sem_lock() needs no further barriers, + * the locks inside sem_lock() enforce ordering (case b above) + * + * 3) current->state: + * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock(). + * The wakeup is handled using the wake_q infrastructure. wake_q wakeups may + * happen immediately after calling wake_q_add. As wake_q_add_safe() is called + * when holding sem_lock(), no further barriers are required. + * + * See also ipc/mqueue.c for more details on the covered races. */ #define sc_semmsl sem_ctls[0] @@ -344,12 +367,8 @@ static void complexmode_tryleave(struct sem_array *sma) return; } if (sma->use_global_lock == 1) { - /* - * Immediately after setting use_global_lock to 0, - * a simple op can start. Thus: all memory writes - * performed by the current operation must be visible - * before we set use_global_lock to 0. - */ + + /* See SEM_BARRIER_1 for purpose/pairing */ smp_store_release(&sma->use_global_lock, 0); } else { sma->use_global_lock--; @@ -400,7 +419,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, */ spin_lock(&sem->lock); - /* pairs with smp_store_release() */ + /* see SEM_BARRIER_1 for purpose/pairing */ if (!smp_load_acquire(&sma->use_global_lock)) { /* fast path successful! */ return sops->sem_num; @@ -766,15 +785,12 @@ would_block: static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error, struct wake_q_head *wake_q) { - wake_q_add(wake_q, q->sleeper); - /* - * Rely on the above implicit barrier, such that we can - * ensure that we hold reference to the task before setting - * q->status. Otherwise we could race with do_exit if the - * task is awoken by an external event before calling - * wake_up_process(). - */ - WRITE_ONCE(q->status, error); + get_task_struct(q->sleeper); + + /* see SEM_BARRIER_2 for purpuse/pairing */ + smp_store_release(&q->status, error); + + wake_q_add_safe(wake_q, q->sleeper); } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) @@ -2148,9 +2164,11 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, } do { + /* memory ordering ensured by the lock in sem_lock() */ WRITE_ONCE(queue.status, -EINTR); queue.sleeper = current; + /* memory ordering is ensured by the lock in sem_lock() */ __set_current_state(TASK_INTERRUPTIBLE); sem_unlock(sma, locknum); rcu_read_unlock(); @@ -2173,13 +2191,8 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, */ error = READ_ONCE(queue.status); if (error != -EINTR) { - /* - * User space could assume that semop() is a memory - * barrier: Without the mb(), the cpu could - * speculatively read in userspace stale data that was - * overwritten by the previous owner of the semaphore. - */ - smp_mb(); + /* see SEM_BARRIER_2 for purpose/pairing */ + smp_acquire__after_ctrl_dep(); goto out_free; } @@ -2189,6 +2202,9 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, if (!ipc_valid_object(&sma->sem_perm)) goto out_unlock_free; + /* + * No necessity for any barrier: We are protect by sem_lock() + */ error = READ_ONCE(queue.status); /* diff --git a/ipc/util.c b/ipc/util.c index 915eacb9c059..fe61df53775a 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -126,7 +126,7 @@ void ipc_init_ids(struct ipc_ids *ids) } #ifdef CONFIG_PROC_FS -static const struct file_operations sysvipc_proc_fops; +static const struct proc_ops sysvipc_proc_ops; /** * ipc_init_proc_interface - create a proc interface for sysipc types using a seq_file interface. * @path: Path in procfs @@ -151,7 +151,7 @@ void __init ipc_init_proc_interface(const char *path, const char *header, pde = proc_create_data(path, S_IRUGO, /* world readable */ NULL, /* parent dir */ - &sysvipc_proc_fops, + &sysvipc_proc_ops, iface); if (!pde) kfree(iface); @@ -884,10 +884,10 @@ static int sysvipc_proc_release(struct inode *inode, struct file *file) return seq_release_private(inode, file); } -static const struct file_operations sysvipc_proc_fops = { - .open = sysvipc_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = sysvipc_proc_release, +static const struct proc_ops sysvipc_proc_ops = { + .proc_open = sysvipc_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = sysvipc_proc_release, }; #endif /* CONFIG_PROC_FS */ diff --git a/kernel/configs.c b/kernel/configs.c index c09ea4c995e1..a28c79c5f713 100644 --- a/kernel/configs.c +++ b/kernel/configs.c @@ -47,10 +47,9 @@ ikconfig_read_current(struct file *file, char __user *buf, &kernel_config_data); } -static const struct file_operations ikconfig_file_ops = { - .owner = THIS_MODULE, - .read = ikconfig_read_current, - .llseek = default_llseek, +static const struct proc_ops config_gz_proc_ops = { + .proc_read = ikconfig_read_current, + .proc_lseek = default_llseek, }; static int __init ikconfig_init(void) @@ -59,7 +58,7 @@ static int __init ikconfig_init(void) /* create the current config file */ entry = proc_create("config.gz", S_IFREG | S_IRUGO, NULL, - &ikconfig_file_ops); + &config_gz_proc_ops); if (!entry) return -ENOMEM; diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index cfc4f088a0e7..9e5783d98033 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -176,20 +176,20 @@ static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode)); } -static const struct file_operations irq_affinity_proc_fops = { - .open = irq_affinity_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = irq_affinity_proc_write, +static const struct proc_ops irq_affinity_proc_ops = { + .proc_open = irq_affinity_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = irq_affinity_proc_write, }; -static const struct file_operations irq_affinity_list_proc_fops = { - .open = irq_affinity_list_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = irq_affinity_list_proc_write, +static const struct proc_ops irq_affinity_list_proc_ops = { + .proc_open = irq_affinity_list_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = irq_affinity_list_proc_write, }; #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK @@ -246,12 +246,12 @@ static int default_affinity_open(struct inode *inode, struct file *file) return single_open(file, default_affinity_show, PDE_DATA(inode)); } -static const struct file_operations default_affinity_proc_fops = { - .open = default_affinity_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = default_affinity_write, +static const struct proc_ops default_affinity_proc_ops = { + .proc_open = default_affinity_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = default_affinity_write, }; static int irq_node_proc_show(struct seq_file *m, void *v) @@ -342,7 +342,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) #ifdef CONFIG_SMP /* create /proc/irq/<irq>/smp_affinity */ proc_create_data("smp_affinity", 0644, desc->dir, - &irq_affinity_proc_fops, irqp); + &irq_affinity_proc_ops, irqp); /* create /proc/irq/<irq>/affinity_hint */ proc_create_single_data("affinity_hint", 0444, desc->dir, @@ -350,7 +350,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) /* create /proc/irq/<irq>/smp_affinity_list */ proc_create_data("smp_affinity_list", 0644, desc->dir, - &irq_affinity_list_proc_fops, irqp); + &irq_affinity_list_proc_ops, irqp); proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show, irqp); @@ -401,7 +401,7 @@ static void register_default_affinity_proc(void) { #ifdef CONFIG_SMP proc_create("irq/default_smp_affinity", 0644, NULL, - &default_affinity_proc_fops); + &default_affinity_proc_ops); #endif } diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 136ce049c4ad..d812b90f4c86 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -698,16 +698,16 @@ const char *kdb_walk_kallsyms(loff_t *pos) } #endif /* CONFIG_KGDB_KDB */ -static const struct file_operations kallsyms_operations = { - .open = kallsyms_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, +static const struct proc_ops kallsyms_proc_ops = { + .proc_open = kallsyms_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release_private, }; static int __init kallsyms_init(void) { - proc_create("kallsyms", 0444, NULL, &kallsyms_operations); + proc_create("kallsyms", 0444, NULL, &kallsyms_proc_ops); return 0; } device_initcall(kallsyms_init); diff --git a/kernel/latencytop.c b/kernel/latencytop.c index e3acead004e6..8d1c15832e55 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -255,17 +255,17 @@ static int lstats_open(struct inode *inode, struct file *filp) return single_open(filp, lstats_show, NULL); } -static const struct file_operations lstats_fops = { - .open = lstats_open, - .read = seq_read, - .write = lstats_write, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops lstats_proc_ops = { + .proc_open = lstats_open, + .proc_read = seq_read, + .proc_write = lstats_write, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; static int __init init_lstats_procfs(void) { - proc_create("latency_stats", 0644, NULL, &lstats_fops); + proc_create("latency_stats", 0644, NULL, &lstats_proc_ops); return 0; } diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 9bb6d2497b04..231684cfc5ae 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -643,12 +643,12 @@ static int lock_stat_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static const struct file_operations proc_lock_stat_operations = { - .open = lock_stat_open, - .write = lock_stat_write, - .read = seq_read, - .llseek = seq_lseek, - .release = lock_stat_release, +static const struct proc_ops lock_stat_proc_ops = { + .proc_open = lock_stat_open, + .proc_write = lock_stat_write, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = lock_stat_release, }; #endif /* CONFIG_LOCK_STAT */ @@ -660,8 +660,7 @@ static int __init lockdep_proc_init(void) #endif proc_create_single("lockdep_stats", S_IRUSR, NULL, lockdep_stats_show); #ifdef CONFIG_LOCK_STAT - proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, - &proc_lock_stat_operations); + proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, &lock_stat_proc_ops); #endif return 0; diff --git a/kernel/module.c b/kernel/module.c index 90ec5ab60255..33569a01d6e1 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -4354,16 +4354,16 @@ static int modules_open(struct inode *inode, struct file *file) return err; } -static const struct file_operations proc_modules_operations = { - .open = modules_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops modules_proc_ops = { + .proc_open = modules_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static int __init proc_modules_init(void) { - proc_create("modules", 0, NULL, &proc_modules_operations); + proc_create("modules", 0, NULL, &modules_proc_ops); return 0; } module_init(proc_modules_init); diff --git a/kernel/profile.c b/kernel/profile.c index 4b144b02ca5d..6f69a4195d56 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -442,18 +442,18 @@ static ssize_t prof_cpu_mask_proc_write(struct file *file, return err; } -static const struct file_operations prof_cpu_mask_proc_fops = { - .open = prof_cpu_mask_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = prof_cpu_mask_proc_write, +static const struct proc_ops prof_cpu_mask_proc_ops = { + .proc_open = prof_cpu_mask_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = prof_cpu_mask_proc_write, }; void create_prof_cpu_mask(void) { /* create /proc/irq/prof_cpu_mask */ - proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_fops); + proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops); } /* @@ -517,10 +517,10 @@ static ssize_t write_profile(struct file *file, const char __user *buf, return count; } -static const struct file_operations proc_profile_operations = { - .read = read_profile, - .write = write_profile, - .llseek = default_llseek, +static const struct proc_ops profile_proc_ops = { + .proc_read = read_profile, + .proc_write = write_profile, + .proc_lseek = default_llseek, }; int __ref create_proc_profile(void) @@ -548,7 +548,7 @@ int __ref create_proc_profile(void) err = 0; #endif entry = proc_create("profile", S_IWUSR | S_IRUGO, - NULL, &proc_profile_operations); + NULL, &profile_proc_ops); if (!entry) goto err_state_onl; proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index db7b50bba3f1..ac4bd0ca11cc 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1251,40 +1251,40 @@ static int psi_fop_release(struct inode *inode, struct file *file) return single_release(inode, file); } -static const struct file_operations psi_io_fops = { - .open = psi_io_open, - .read = seq_read, - .llseek = seq_lseek, - .write = psi_io_write, - .poll = psi_fop_poll, - .release = psi_fop_release, +static const struct proc_ops psi_io_proc_ops = { + .proc_open = psi_io_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_io_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_release, }; -static const struct file_operations psi_memory_fops = { - .open = psi_memory_open, - .read = seq_read, - .llseek = seq_lseek, - .write = psi_memory_write, - .poll = psi_fop_poll, - .release = psi_fop_release, +static const struct proc_ops psi_memory_proc_ops = { + .proc_open = psi_memory_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_memory_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_release, }; -static const struct file_operations psi_cpu_fops = { - .open = psi_cpu_open, - .read = seq_read, - .llseek = seq_lseek, - .write = psi_cpu_write, - .poll = psi_fop_poll, - .release = psi_fop_release, +static const struct proc_ops psi_cpu_proc_ops = { + .proc_open = psi_cpu_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_cpu_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_release, }; static int __init psi_proc_init(void) { if (psi_enable) { proc_mkdir("pressure", NULL); - proc_create("pressure/io", 0, NULL, &psi_io_fops); - proc_create("pressure/memory", 0, NULL, &psi_memory_fops); - proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops); + proc_create("pressure/io", 0, NULL, &psi_io_proc_ops); + proc_create("pressure/memory", 0, NULL, &psi_memory_proc_ops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_proc_ops); } return 0; } diff --git a/lib/bitmap.c b/lib/bitmap.c index 6e175fbd69a9..89260aa342d6 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -431,97 +431,6 @@ EXPORT_SYMBOL(bitmap_find_next_zero_area_off); * second version by Paul Jackson, third by Joe Korty. */ -#define CHUNKSZ 32 -#define nbits_to_hold_value(val) fls(val) -#define BASEDEC 10 /* fancier cpuset lists input in decimal */ - -/** - * __bitmap_parse - convert an ASCII hex string into a bitmap. - * @buf: pointer to buffer containing string. - * @buflen: buffer size in bytes. If string is smaller than this - * then it must be terminated with a \0. - * @is_user: location of buffer, 0 indicates kernel space - * @maskp: pointer to bitmap array that will contain result. - * @nmaskbits: size of bitmap, in bits. - * - * Commas group hex digits into chunks. Each chunk defines exactly 32 - * bits of the resultant bitmask. No chunk may specify a value larger - * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value - * then leading 0-bits are prepended. %-EINVAL is returned for illegal - * characters and for grouping errors such as "1,,5", ",44", "," and "". - * Leading and trailing whitespace accepted, but not embedded whitespace. - */ -int __bitmap_parse(const char *buf, unsigned int buflen, - int is_user, unsigned long *maskp, - int nmaskbits) -{ - int c, old_c, totaldigits, ndigits, nchunks, nbits; - u32 chunk; - const char __user __force *ubuf = (const char __user __force *)buf; - - bitmap_zero(maskp, nmaskbits); - - nchunks = nbits = totaldigits = c = 0; - do { - chunk = 0; - ndigits = totaldigits; - - /* Get the next chunk of the bitmap */ - while (buflen) { - old_c = c; - if (is_user) { - if (__get_user(c, ubuf++)) - return -EFAULT; - } - else - c = *buf++; - buflen--; - if (isspace(c)) - continue; - - /* - * If the last character was a space and the current - * character isn't '\0', we've got embedded whitespace. - * This is a no-no, so throw an error. - */ - if (totaldigits && c && isspace(old_c)) - return -EINVAL; - - /* A '\0' or a ',' signal the end of the chunk */ - if (c == '\0' || c == ',') - break; - - if (!isxdigit(c)) - return -EINVAL; - - /* - * Make sure there are at least 4 free bits in 'chunk'. - * If not, this hexdigit will overflow 'chunk', so - * throw an error. - */ - if (chunk & ~((1UL << (CHUNKSZ - 4)) - 1)) - return -EOVERFLOW; - - chunk = (chunk << 4) | hex_to_bin(c); - totaldigits++; - } - if (ndigits == totaldigits) - return -EINVAL; - if (nchunks == 0 && chunk == 0) - continue; - - __bitmap_shift_left(maskp, maskp, CHUNKSZ, nmaskbits); - *maskp |= chunk; - nchunks++; - nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ; - if (nbits > nmaskbits) - return -EOVERFLOW; - } while (buflen && c == ','); - - return 0; -} -EXPORT_SYMBOL(__bitmap_parse); - /** * bitmap_parse_user - convert an ASCII hex string in a user buffer into a bitmap * @@ -530,22 +439,22 @@ EXPORT_SYMBOL(__bitmap_parse); * then it must be terminated with a \0. * @maskp: pointer to bitmap array that will contain result. * @nmaskbits: size of bitmap, in bits. - * - * Wrapper for __bitmap_parse(), providing it with user buffer. - * - * We cannot have this as an inline function in bitmap.h because it needs - * linux/uaccess.h to get the access_ok() declaration and this causes - * cyclic dependencies. */ int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *maskp, int nmaskbits) { - if (!access_ok(ubuf, ulen)) - return -EFAULT; - return __bitmap_parse((const char __force *)ubuf, - ulen, 1, maskp, nmaskbits); + char *buf; + int ret; + buf = memdup_user_nul(ubuf, ulen); + if (IS_ERR(buf)) + return PTR_ERR(buf); + + ret = bitmap_parse(buf, UINT_MAX, maskp, nmaskbits); + + kfree(buf); + return ret; } EXPORT_SYMBOL(bitmap_parse_user); @@ -653,6 +562,14 @@ static const char *bitmap_find_region(const char *str) return end_of_str(*str) ? NULL : str; } +static const char *bitmap_find_region_reverse(const char *start, const char *end) +{ + while (start <= end && __end_of_region(*end)) + end--; + + return end; +} + static const char *bitmap_parse_region(const char *str, struct region *r) { str = bitmap_getnum(str, &r->start); @@ -776,6 +693,80 @@ int bitmap_parselist_user(const char __user *ubuf, } EXPORT_SYMBOL(bitmap_parselist_user); +static const char *bitmap_get_x32_reverse(const char *start, + const char *end, u32 *num) +{ + u32 ret = 0; + int c, i; + + for (i = 0; i < 32; i += 4) { + c = hex_to_bin(*end--); + if (c < 0) + return ERR_PTR(-EINVAL); + + ret |= c << i; + + if (start > end || __end_of_region(*end)) + goto out; + } + + if (hex_to_bin(*end--) >= 0) + return ERR_PTR(-EOVERFLOW); +out: + *num = ret; + return end; +} + +/** + * bitmap_parse - convert an ASCII hex string into a bitmap. + * @start: pointer to buffer containing string. + * @buflen: buffer size in bytes. If string is smaller than this + * then it must be terminated with a \0 or \n. In that case, + * UINT_MAX may be provided instead of string length. + * @maskp: pointer to bitmap array that will contain result. + * @nmaskbits: size of bitmap, in bits. + * + * Commas group hex digits into chunks. Each chunk defines exactly 32 + * bits of the resultant bitmask. No chunk may specify a value larger + * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value + * then leading 0-bits are prepended. %-EINVAL is returned for illegal + * characters. Grouping such as "1,,5", ",44", "," or "" is allowed. + * Leading, embedded and trailing whitespace accepted. + */ +int bitmap_parse(const char *start, unsigned int buflen, + unsigned long *maskp, int nmaskbits) +{ + const char *end = strnchrnul(start, buflen, '\n') - 1; + int chunks = BITS_TO_U32(nmaskbits); + u32 *bitmap = (u32 *)maskp; + int unset_bit; + + while (1) { + end = bitmap_find_region_reverse(start, end); + if (start > end) + break; + + if (!chunks--) + return -EOVERFLOW; + + end = bitmap_get_x32_reverse(start, end, bitmap++); + if (IS_ERR(end)) + return PTR_ERR(end); + } + + unset_bit = (BITS_TO_U32(nmaskbits) - chunks) * 32; + if (unset_bit < nmaskbits) { + bitmap_clear(maskp, unset_bit, nmaskbits - unset_bit); + return 0; + } + + if (find_next_bit(maskp, unset_bit, nmaskbits) != unset_bit) + return -EOVERFLOW; + + return 0; +} +EXPORT_SYMBOL(bitmap_parse); + #ifdef CONFIG_NUMA /** diff --git a/lib/string.c b/lib/string.c index 08ec58cc673b..f607b967d978 100644 --- a/lib/string.c +++ b/lib/string.c @@ -434,6 +434,23 @@ char *strchrnul(const char *s, int c) EXPORT_SYMBOL(strchrnul); #endif +/** + * strnchrnul - Find and return a character in a length limited string, + * or end of string + * @s: The string to be searched + * @count: The number of characters to be searched + * @c: The character to search for + * + * Returns pointer to the first occurrence of 'c' in s. If c is not found, + * then return a pointer to the last character of the string. + */ +char *strnchrnul(const char *s, size_t count, int c) +{ + while (count-- && *s && *s != (char)c) + s++; + return (char *)s; +} + #ifndef __HAVE_ARCH_STRRCHR /** * strrchr - Find the last occurrence of a character in a string diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 71ec3afe1681..61ed71c1daba 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -295,7 +295,8 @@ static void __init test_replace(void) expect_eq_bitmap(bmap, exp3_1_0, nbits); } -#define PARSE_TIME 0x1 +#define PARSE_TIME 0x1 +#define NO_LEN 0x2 struct test_bitmap_parselist{ const int errno; @@ -349,7 +350,6 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = { {-EINVAL, "0-31:a/1", NULL, 8, 0}, {-EINVAL, "0-\n", NULL, 8, 0}, -#undef step }; static void __init __test_bitmap_parselist(int is_user) @@ -401,6 +401,95 @@ static void __init __test_bitmap_parselist(int is_user) } } +static const unsigned long parse_test[] __initconst = { + BITMAP_FROM_U64(0), + BITMAP_FROM_U64(1), + BITMAP_FROM_U64(0xdeadbeef), + BITMAP_FROM_U64(0x100000000ULL), +}; + +static const unsigned long parse_test2[] __initconst = { + BITMAP_FROM_U64(0x100000000ULL), BITMAP_FROM_U64(0xdeadbeef), + BITMAP_FROM_U64(0x100000000ULL), BITMAP_FROM_U64(0xbaadf00ddeadbeef), + BITMAP_FROM_U64(0x100000000ULL), BITMAP_FROM_U64(0x0badf00ddeadbeef), +}; + +static const struct test_bitmap_parselist parse_tests[] __initconst = { + {0, "", &parse_test[0 * step], 32, 0}, + {0, " ", &parse_test[0 * step], 32, 0}, + {0, "0", &parse_test[0 * step], 32, 0}, + {0, "0\n", &parse_test[0 * step], 32, 0}, + {0, "1", &parse_test[1 * step], 32, 0}, + {0, "deadbeef", &parse_test[2 * step], 32, 0}, + {0, "1,0", &parse_test[3 * step], 33, 0}, + {0, "deadbeef,\n,0,1", &parse_test[2 * step], 96, 0}, + + {0, "deadbeef,1,0", &parse_test2[0 * 2 * step], 96, 0}, + {0, "baadf00d,deadbeef,1,0", &parse_test2[1 * 2 * step], 128, 0}, + {0, "badf00d,deadbeef,1,0", &parse_test2[2 * 2 * step], 124, 0}, + {0, "badf00d,deadbeef,1,0", &parse_test2[2 * 2 * step], 124, NO_LEN}, + {0, " badf00d,deadbeef,1,0 ", &parse_test2[2 * 2 * step], 124, 0}, + {0, " , badf00d,deadbeef,1,0 , ", &parse_test2[2 * 2 * step], 124, 0}, + {0, " , badf00d, ,, ,,deadbeef,1,0 , ", &parse_test2[2 * 2 * step], 124, 0}, + + {-EINVAL, "goodfood,deadbeef,1,0", NULL, 128, 0}, + {-EOVERFLOW, "3,0", NULL, 33, 0}, + {-EOVERFLOW, "123badf00d,deadbeef,1,0", NULL, 128, 0}, + {-EOVERFLOW, "badf00d,deadbeef,1,0", NULL, 90, 0}, + {-EOVERFLOW, "fbadf00d,deadbeef,1,0", NULL, 95, 0}, + {-EOVERFLOW, "badf00d,deadbeef,1,0", NULL, 100, 0}, +#undef step +}; + +static void __init __test_bitmap_parse(int is_user) +{ + int i; + int err; + ktime_t time; + DECLARE_BITMAP(bmap, 2048); + char *mode = is_user ? "_user" : ""; + + for (i = 0; i < ARRAY_SIZE(parse_tests); i++) { + struct test_bitmap_parselist test = parse_tests[i]; + + if (is_user) { + size_t len = strlen(test.in); + mm_segment_t orig_fs = get_fs(); + + set_fs(KERNEL_DS); + time = ktime_get(); + err = bitmap_parse_user((__force const char __user *)test.in, len, + bmap, test.nbits); + time = ktime_get() - time; + set_fs(orig_fs); + } else { + size_t len = test.flags & NO_LEN ? + UINT_MAX : strlen(test.in); + time = ktime_get(); + err = bitmap_parse(test.in, len, bmap, test.nbits); + time = ktime_get() - time; + } + + if (err != test.errno) { + pr_err("parse%s: %d: input is %s, errno is %d, expected %d\n", + mode, i, test.in, err, test.errno); + continue; + } + + if (!err && test.expected + && !__bitmap_equal(bmap, test.expected, test.nbits)) { + pr_err("parse%s: %d: input is %s, result is 0x%lx, expected 0x%lx\n", + mode, i, test.in, bmap[0], + *test.expected); + continue; + } + + if (test.flags & PARSE_TIME) + pr_err("parse%s: %d: input is '%s' OK, Time: %llu\n", + mode, i, test.in, time); + } +} + static void __init test_bitmap_parselist(void) { __test_bitmap_parselist(0); @@ -411,6 +500,16 @@ static void __init test_bitmap_parselist_user(void) __test_bitmap_parselist(1); } +static void __init test_bitmap_parse(void) +{ + __test_bitmap_parse(0); +} + +static void __init test_bitmap_parse_user(void) +{ + __test_bitmap_parse(1); +} + #define EXP1_IN_BITS (sizeof(exp1) * 8) static void __init test_bitmap_arr32(void) @@ -516,6 +615,8 @@ static void __init selftest(void) test_copy(); test_replace(); test_bitmap_arr32(); + test_bitmap_parse(); + test_bitmap_parse_user(); test_bitmap_parselist(); test_bitmap_parselist_user(); test_mem_optimisations(); diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 327b3ebf23bf..0271b22e063f 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -117,3 +117,24 @@ config DEBUG_RODATA_TEST depends on STRICT_KERNEL_RWX ---help--- This option enables a testcase for the setting rodata read-only. + +config GENERIC_PTDUMP + bool + +config PTDUMP_CORE + bool + +config PTDUMP_DEBUGFS + bool "Export kernel pagetable layout to userspace via debugfs" + depends on DEBUG_KERNEL + depends on DEBUG_FS + depends on GENERIC_PTDUMP + select PTDUMP_CORE + help + Say Y here if you want to show the kernel pagetable layout in a + debugfs file. This information is only useful for kernel developers + who are working in architecture specific areas of the kernel. + It is probably not a good idea to enable this feature in a production + kernel. + + If in doubt, say N. diff --git a/mm/Makefile b/mm/Makefile index 32f08e22e824..272e66039e70 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -109,3 +109,4 @@ obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o +obj-$(CONFIG_PTDUMP_CORE) += ptdump.o @@ -1792,7 +1792,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * Before activating this code, please be aware that the following assumptions * are currently made: * - * *) Either HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to + * *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to * free pages containing page tables or TLB flushing requires IPI broadcast. * * *) ptes can be read atomically by the architecture. @@ -186,7 +186,7 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk, } static int hmm_vma_walk_hole(unsigned long addr, unsigned long end, - struct mm_walk *walk) + __always_unused int depth, struct mm_walk *walk) { struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; @@ -380,7 +380,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp, again: pmd = READ_ONCE(*pmdp); if (pmd_none(pmd)) - return hmm_vma_walk_hole(start, end, walk); + return hmm_vma_walk_hole(start, end, -1, walk); if (thp_migration_supported() && is_pmd_migration_entry(pmd)) { bool fault, write_fault; @@ -474,23 +474,32 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end, { struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; - unsigned long addr = start, next; - pmd_t *pmdp; + unsigned long addr = start; pud_t pud; - int ret; + int ret = 0; + spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma); + + if (!ptl) + return 0; + + /* Normally we don't want to split the huge page */ + walk->action = ACTION_CONTINUE; -again: pud = READ_ONCE(*pudp); - if (pud_none(pud)) - return hmm_vma_walk_hole(start, end, walk); + if (pud_none(pud)) { + ret = hmm_vma_walk_hole(start, end, -1, walk); + goto out_unlock; + } if (pud_huge(pud) && pud_devmap(pud)) { unsigned long i, npages, pfn; uint64_t *pfns, cpu_flags; bool fault, write_fault; - if (!pud_present(pud)) - return hmm_vma_walk_hole(start, end, walk); + if (!pud_present(pud)) { + ret = hmm_vma_walk_hole(start, end, -1, walk); + goto out_unlock; + } i = (addr - range->start) >> PAGE_SHIFT; npages = (end - addr) >> PAGE_SHIFT; @@ -499,16 +508,20 @@ again: cpu_flags = pud_to_hmm_pfn_flags(range, pud); hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags, &fault, &write_fault); - if (fault || write_fault) - return hmm_vma_walk_hole_(addr, end, fault, - write_fault, walk); + if (fault || write_fault) { + ret = hmm_vma_walk_hole_(addr, end, fault, + write_fault, walk); + goto out_unlock; + } pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); for (i = 0; i < npages; ++i, ++pfn) { hmm_vma_walk->pgmap = get_dev_pagemap(pfn, hmm_vma_walk->pgmap); - if (unlikely(!hmm_vma_walk->pgmap)) - return -EBUSY; + if (unlikely(!hmm_vma_walk->pgmap)) { + ret = -EBUSY; + goto out_unlock; + } pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags; } @@ -517,22 +530,15 @@ again: hmm_vma_walk->pgmap = NULL; } hmm_vma_walk->last = end; - return 0; + goto out_unlock; } - split_huge_pud(walk->vma, pudp, addr); - if (pud_none(*pudp)) - goto again; + /* Ask for the PUD to be split */ + walk->action = ACTION_SUBTREE; - pmdp = pmd_offset(pudp, addr); - do { - next = pmd_addr_end(addr, end); - ret = hmm_vma_walk_pmd(pmdp, addr, next, walk); - if (ret) - return ret; - } while (pmdp++, addr = next, addr != end); - - return 0; +out_unlock: + spin_unlock(ptl); + return ret; } #else #define hmm_vma_walk_pud NULL diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 36d80915ddc2..0a54ffac8c68 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -355,7 +355,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, if (unlikely(pfn_to_nid(start_pfn) != nid)) continue; - if (zone && zone != page_zone(pfn_to_page(start_pfn))) + if (zone != page_zone(pfn_to_page(start_pfn))) continue; return start_pfn; @@ -380,7 +380,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, if (unlikely(pfn_to_nid(pfn) != nid)) continue; - if (zone && zone != page_zone(pfn_to_page(pfn))) + if (zone != page_zone(pfn_to_page(pfn))) continue; return pfn; @@ -392,14 +392,11 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long zone_start_pfn = zone->zone_start_pfn; - unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */ - unsigned long zone_end_pfn = z; unsigned long pfn; int nid = zone_to_nid(zone); zone_span_writelock(zone); - if (zone_start_pfn == start_pfn) { + if (zone->zone_start_pfn == start_pfn) { /* * If the section is smallest section in the zone, it need * shrink zone->zone_start_pfn and zone->zone_spanned_pages. @@ -407,50 +404,30 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, * for shrinking zone. */ pfn = find_smallest_section_pfn(nid, zone, end_pfn, - zone_end_pfn); + zone_end_pfn(zone)); if (pfn) { + zone->spanned_pages = zone_end_pfn(zone) - pfn; zone->zone_start_pfn = pfn; - zone->spanned_pages = zone_end_pfn - pfn; + } else { + zone->zone_start_pfn = 0; + zone->spanned_pages = 0; } - } else if (zone_end_pfn == end_pfn) { + } else if (zone_end_pfn(zone) == end_pfn) { /* * If the section is biggest section in the zone, it need * shrink zone->spanned_pages. * In this case, we find second biggest valid mem_section for * shrinking zone. */ - pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn, + pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn, start_pfn); if (pfn) - zone->spanned_pages = pfn - zone_start_pfn + 1; - } - - /* - * The section is not biggest or smallest mem_section in the zone, it - * only creates a hole in the zone. So in this case, we need not - * change the zone. But perhaps, the zone has only hole data. Thus - * it check the zone has only hole or not. - */ - pfn = zone_start_pfn; - for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_to_online_page(pfn))) - continue; - - if (page_zone(pfn_to_page(pfn)) != zone) - continue; - - /* Skip range to be removed */ - if (pfn >= start_pfn && pfn < end_pfn) - continue; - - /* If we find valid section, we have nothing to do */ - zone_span_writeunlock(zone); - return; + zone->spanned_pages = pfn - zone->zone_start_pfn + 1; + else { + zone->zone_start_pfn = 0; + zone->spanned_pages = 0; + } } - - /* The zone has no valid section */ - zone->zone_start_pfn = 0; - zone->spanned_pages = 0; zone_span_writeunlock(zone); } @@ -490,6 +467,9 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; + /* Poison struct pages because they are now uninitialized again. */ + page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages); + #ifdef CONFIG_ZONE_DEVICE /* * Zone shrinking code cannot properly deal with ZONE_DEVICE. So @@ -536,25 +516,20 @@ static void __remove_section(unsigned long pfn, unsigned long nr_pages, void __remove_pages(unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap) { + const unsigned long end_pfn = pfn + nr_pages; + unsigned long cur_nr_pages; unsigned long map_offset = 0; - unsigned long nr, start_sec, end_sec; map_offset = vmem_altmap_offset(altmap); if (check_pfn_span(pfn, nr_pages, "remove")) return; - start_sec = pfn_to_section_nr(pfn); - end_sec = pfn_to_section_nr(pfn + nr_pages - 1); - for (nr = start_sec; nr <= end_sec; nr++) { - unsigned long pfns; - + for (; pfn < end_pfn; pfn += cur_nr_pages) { cond_resched(); - pfns = min(nr_pages, PAGES_PER_SECTION - - (pfn & ~PAGE_SECTION_MASK)); - __remove_section(pfn, pfns, map_offset, altmap); - pfn += pfns; - nr_pages -= pfns; + /* Select all remaining pages up to the next section boundary */ + cur_nr_pages = min(end_pfn - pfn, -(pfn | PAGE_SECTION_MASK)); + __remove_section(pfn, cur_nr_pages, map_offset, altmap); map_offset = 0; } } @@ -1197,14 +1172,13 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) } /* - * Confirm all pages in a range [start, end) belong to the same zone. - * When true, return its valid [start, end). + * Confirm all pages in a range [start, end) belong to the same zone (skipping + * memory holes). When true, return the zone. */ -int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, - unsigned long *valid_start, unsigned long *valid_end) +struct zone *test_pages_in_a_zone(unsigned long start_pfn, + unsigned long end_pfn) { unsigned long pfn, sec_end_pfn; - unsigned long start, end; struct zone *zone = NULL; struct page *page; int i; @@ -1225,24 +1199,15 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, continue; /* Check if we got outside of the zone */ if (zone && !zone_spans_pfn(zone, pfn + i)) - return 0; + return NULL; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) - return 0; - if (!zone) - start = pfn + i; + return NULL; zone = page_zone(page); - end = pfn + MAX_ORDER_NR_PAGES; } } - if (zone) { - *valid_start = start; - *valid_end = min(end, end_pfn); - return 1; - } else { - return 0; - } + return zone; } /* @@ -1487,7 +1452,6 @@ static int __ref __offline_pages(unsigned long start_pfn, unsigned long offlined_pages = 0; int ret, node, nr_isolate_pageblock; unsigned long flags; - unsigned long valid_start, valid_end; struct zone *zone; struct memory_notify arg; char *reason; @@ -1512,14 +1476,12 @@ static int __ref __offline_pages(unsigned long start_pfn, /* This makes hotplug much easier...and readable. we assume this for now. .*/ - if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, - &valid_end)) { + zone = test_pages_in_a_zone(start_pfn, end_pfn); + if (!zone) { ret = -EINVAL; reason = "multizone range"; goto failed_removal; } - - zone = page_zone(pfn_to_page(valid_start)); node = zone_to_nid(zone); /* set above range as isolated */ diff --git a/mm/memremap.c b/mm/memremap.c index 4c723d2049d5..09b5b7adc773 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -120,6 +120,8 @@ void memunmap_pages(struct dev_pagemap *pgmap) nid = page_to_nid(first_page); mem_hotplug_begin(); + remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(res->start), + PHYS_PFN(resource_size(res))); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { __remove_pages(PHYS_PFN(res->start), PHYS_PFN(resource_size(res)), NULL); diff --git a/mm/migrate.c b/mm/migrate.c index edf42ed90030..b1092876e537 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2151,6 +2151,7 @@ out_unlock: #ifdef CONFIG_DEVICE_PRIVATE static int migrate_vma_collect_hole(unsigned long start, unsigned long end, + __always_unused int depth, struct mm_walk *walk) { struct migrate_vma *migrate = walk->private; @@ -2195,7 +2196,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, again: if (pmd_none(*pmdp)) - return migrate_vma_collect_hole(start, end, walk); + return migrate_vma_collect_hole(start, end, -1, walk); if (pmd_trans_huge(*pmdp)) { struct page *page; @@ -2228,7 +2229,7 @@ again: return migrate_vma_collect_skip(start, end, walk); if (pmd_none(*pmdp)) - return migrate_vma_collect_hole(start, end, + return migrate_vma_collect_hole(start, end, -1, walk); } } diff --git a/mm/mincore.c b/mm/mincore.c index 49b6fa2f6aa1..0e6dd9948f1a 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -112,6 +112,7 @@ static int __mincore_unmapped_range(unsigned long addr, unsigned long end, } static int mincore_unmapped_range(unsigned long addr, unsigned long end, + __always_unused int depth, struct mm_walk *walk) { walk->private += __mincore_unmapped_range(addr, end, diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 7d70e5c78f97..a3538cb2bcbe 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -11,7 +11,7 @@ #include <asm/pgalloc.h> #include <asm/tlb.h> -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER +#ifndef CONFIG_MMU_GATHER_NO_GATHER static bool tlb_next_batch(struct mmu_gather *tlb) { @@ -69,7 +69,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ VM_BUG_ON(!tlb->end); -#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE +#ifdef CONFIG_MMU_GATHER_PAGE_SIZE VM_WARN_ON(tlb->page_size != page_size); #endif @@ -89,58 +89,108 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ return false; } -#endif /* HAVE_MMU_GATHER_NO_GATHER */ +#endif /* MMU_GATHER_NO_GATHER */ -#ifdef CONFIG_HAVE_RCU_TABLE_FREE +#ifdef CONFIG_MMU_GATHER_TABLE_FREE -/* - * See the comment near struct mmu_table_batch. - */ +static void __tlb_remove_table_free(struct mmu_table_batch *batch) +{ + int i; + + for (i = 0; i < batch->nr; i++) + __tlb_remove_table(batch->tables[i]); + + free_page((unsigned long)batch); +} + +#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* - * If we want tlb_remove_table() to imply TLB invalidates. + * Semi RCU freeing of the page directories. + * + * This is needed by some architectures to implement software pagetable walkers. + * + * gup_fast() and other software pagetable walkers do a lockless page-table + * walk and therefore needs some synchronization with the freeing of the page + * directories. The chosen means to accomplish that is by disabling IRQs over + * the walk. + * + * Architectures that use IPIs to flush TLBs will then automagically DTRT, + * since we unlink the page, flush TLBs, free the page. Since the disabling of + * IRQs delays the completion of the TLB flush we can never observe an already + * freed page. + * + * Architectures that do not have this (PPC) need to delay the freeing by some + * other means, this is that means. + * + * What we do is batch the freed directory pages (tables) and RCU free them. + * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling + * holds off grace periods. + * + * However, in order to batch these pages we need to allocate storage, this + * allocation is deep inside the MM code and can thus easily fail on memory + * pressure. To guarantee progress we fall back to single table freeing, see + * the implementation of tlb_remove_table_one(). + * */ -static inline void tlb_table_invalidate(struct mmu_gather *tlb) -{ -#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE - /* - * Invalidate page-table caches used by hardware walkers. Then we still - * need to RCU-sched wait while freeing the pages because software - * walkers can still be in-flight. - */ - tlb_flush_mmu_tlbonly(tlb); -#endif -} static void tlb_remove_table_smp_sync(void *arg) { /* Simply deliver the interrupt */ } -static void tlb_remove_table_one(void *table) +static void tlb_remove_table_sync_one(void) { /* * This isn't an RCU grace period and hence the page-tables cannot be * assumed to be actually RCU-freed. * * It is however sufficient for software page-table walkers that rely on - * IRQ disabling. See the comment near struct mmu_table_batch. + * IRQ disabling. */ smp_call_function(tlb_remove_table_smp_sync, NULL, 1); - __tlb_remove_table(table); } static void tlb_remove_table_rcu(struct rcu_head *head) { - struct mmu_table_batch *batch; - int i; + __tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu)); +} + +static void tlb_remove_table_free(struct mmu_table_batch *batch) +{ + call_rcu(&batch->rcu, tlb_remove_table_rcu); +} - batch = container_of(head, struct mmu_table_batch, rcu); +#else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */ - for (i = 0; i < batch->nr; i++) - __tlb_remove_table(batch->tables[i]); +static void tlb_remove_table_sync_one(void) { } - free_page((unsigned long)batch); +static void tlb_remove_table_free(struct mmu_table_batch *batch) +{ + __tlb_remove_table_free(batch); +} + +#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ + +/* + * If we want tlb_remove_table() to imply TLB invalidates. + */ +static inline void tlb_table_invalidate(struct mmu_gather *tlb) +{ + if (tlb_needs_table_invalidate()) { + /* + * Invalidate page-table caches used by hardware walkers. Then + * we still need to RCU-sched wait while freeing the pages + * because software walkers can still be in-flight. + */ + tlb_flush_mmu_tlbonly(tlb); + } +} + +static void tlb_remove_table_one(void *table) +{ + tlb_remove_table_sync_one(); + __tlb_remove_table(table); } static void tlb_table_flush(struct mmu_gather *tlb) @@ -149,7 +199,7 @@ static void tlb_table_flush(struct mmu_gather *tlb) if (*batch) { tlb_table_invalidate(tlb); - call_rcu(&(*batch)->rcu, tlb_remove_table_rcu); + tlb_remove_table_free(*batch); *batch = NULL; } } @@ -173,14 +223,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) tlb_table_flush(tlb); } -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ +static inline void tlb_table_init(struct mmu_gather *tlb) +{ + tlb->batch = NULL; +} + +#else /* !CONFIG_MMU_GATHER_TABLE_FREE */ + +static inline void tlb_table_flush(struct mmu_gather *tlb) { } +static inline void tlb_table_init(struct mmu_gather *tlb) { } + +#endif /* CONFIG_MMU_GATHER_TABLE_FREE */ static void tlb_flush_mmu_free(struct mmu_gather *tlb) { -#ifdef CONFIG_HAVE_RCU_TABLE_FREE tlb_table_flush(tlb); -#endif -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER +#ifndef CONFIG_MMU_GATHER_NO_GATHER tlb_batch_pages_flush(tlb); #endif } @@ -211,7 +269,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, /* Is it from 0 to ~0? */ tlb->fullmm = !(start | (end+1)); -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER +#ifndef CONFIG_MMU_GATHER_NO_GATHER tlb->need_flush_all = 0; tlb->local.next = NULL; tlb->local.nr = 0; @@ -220,10 +278,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, tlb->batch_count = 0; #endif -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb->batch = NULL; -#endif -#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE + tlb_table_init(tlb); +#ifdef CONFIG_MMU_GATHER_PAGE_SIZE tlb->page_size = 0; #endif @@ -271,7 +327,7 @@ void tlb_finish_mmu(struct mmu_gather *tlb, tlb_flush_mmu(tlb); -#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER +#ifndef CONFIG_MMU_GATHER_NO_GATHER tlb_batch_list_free(tlb); #endif dec_tlb_flush_pending(tlb->mm); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 15e908ad933b..3c4eb750a199 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5852,18 +5852,11 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) /* Skip PFNs that belong to non-present sections */ static inline __meminit unsigned long next_pfn(unsigned long pfn) { - unsigned long section_nr; + const unsigned long section_nr = pfn_to_section_nr(++pfn); - section_nr = pfn_to_section_nr(++pfn); if (present_section_nr(section_nr)) return pfn; - - while (++section_nr <= __highest_present_section_nr) { - if (present_section_nr(section_nr)) - return section_nr_to_pfn(section_nr); - } - - return -1; + return section_nr_to_pfn(next_present_section_nr(section_nr)); } #else static inline __meminit unsigned long next_pfn(unsigned long pfn) @@ -5905,18 +5898,20 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, } #endif - for (pfn = start_pfn; pfn < end_pfn; pfn++) { + for (pfn = start_pfn; pfn < end_pfn; ) { /* * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ if (context == MEMMAP_EARLY) { if (!early_pfn_valid(pfn)) { - pfn = next_pfn(pfn) - 1; + pfn = next_pfn(pfn); continue; } - if (!early_pfn_in_nid(pfn, nid)) + if (!early_pfn_in_nid(pfn, nid)) { + pfn++; continue; + } if (overlap_memmap_init(zone, &pfn)) continue; if (defer_init(nid, pfn, end_pfn)) @@ -5944,16 +5939,17 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, set_pageblock_migratetype(page, MIGRATE_MOVABLE); cond_resched(); } + pfn++; } } #ifdef CONFIG_ZONE_DEVICE void __ref memmap_init_zone_device(struct zone *zone, unsigned long start_pfn, - unsigned long size, + unsigned long nr_pages, struct dev_pagemap *pgmap) { - unsigned long pfn, end_pfn = start_pfn + size; + unsigned long pfn, end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; struct vmem_altmap *altmap = pgmap_altmap(pgmap); unsigned long zone_idx = zone_idx(zone); @@ -5970,7 +5966,7 @@ void __ref memmap_init_zone_device(struct zone *zone, */ if (altmap) { start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); - size = end_pfn - start_pfn; + nr_pages = end_pfn - start_pfn; } for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -6017,7 +6013,7 @@ void __ref memmap_init_zone_device(struct zone *zone, } pr_info("%s initialised %lu pages in %ums\n", __func__, - size, jiffies_to_msecs(jiffies - start)); + nr_pages, jiffies_to_msecs(jiffies - start)); } #endif @@ -6916,10 +6912,10 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, #if !defined(CONFIG_FLAT_NODE_MEM_MAP) /* - * Zero all valid struct pages in range [spfn, epfn), return number of struct - * pages zeroed + * Initialize all valid struct pages in the range [spfn, epfn) and mark them + * PageReserved(). Return the number of struct pages that were initialized. */ -static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) +static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) { unsigned long pfn; u64 pgcnt = 0; @@ -6930,7 +6926,13 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) + pageblock_nr_pages - 1; continue; } - mm_zero_struct_page(pfn_to_page(pfn)); + /* + * Use a fake node/zone (0) for now. Some of these pages + * (in memblock.reserved but not in memblock.memory) will + * get re-initialized via reserve_bootmem_region() later. + */ + __init_single_page(pfn_to_page(pfn), pfn, 0, 0); + __SetPageReserved(pfn_to_page(pfn)); pgcnt++; } @@ -6942,14 +6944,15 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) * initialized by going through __init_single_page(). But, there are some * struct pages which are reserved in memblock allocator and their fields * may be accessed (for example page_to_pfn() on some configuration accesses - * flags). We must explicitly zero those struct pages. + * flags). We must explicitly initialize those struct pages. * * This function also addresses a similar issue where struct pages are left * uninitialized because the physical address range is not covered by * memblock.memory or memblock.reserved. That could happen when memblock - * layout is manually configured via memmap=. + * layout is manually configured via memmap=, or when the highest physical + * address (max_pfn) does not end on a section boundary. */ -void __init zero_resv_unavail(void) +static void __init init_unavailable_mem(void) { phys_addr_t start, end; u64 i, pgcnt; @@ -6962,10 +6965,20 @@ void __init zero_resv_unavail(void) for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { if (next < start) - pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start)); + pgcnt += init_unavailable_range(PFN_DOWN(next), + PFN_UP(start)); next = end; } - pgcnt += zero_pfn_range(PFN_DOWN(next), max_pfn); + + /* + * Early sections always have a fully populated memmap for the whole + * section - see pfn_valid(). If the last section has holes at the + * end and that section is marked "online", the memmap will be + * considered initialized. Make sure that memmap has a well defined + * state. + */ + pgcnt += init_unavailable_range(PFN_DOWN(next), + round_up(max_pfn, PAGES_PER_SECTION)); /* * Struct pages that do not have backing memory. This could be because @@ -6974,6 +6987,10 @@ void __init zero_resv_unavail(void) if (pgcnt) pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); } +#else +static inline void __init init_unavailable_mem(void) +{ +} #endif /* !CONFIG_FLAT_NODE_MEM_MAP */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -7403,7 +7420,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Initialise every node */ mminit_verify_pageflags_layout(); setup_nr_node_ids(); - zero_resv_unavail(); + init_unavailable_mem(); for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); free_area_init_node(nid, NULL, @@ -7598,7 +7615,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) void __init free_area_init(unsigned long *zones_size) { - zero_resv_unavail(); + init_unavailable_mem(); free_area_init_node(0, zones_size, __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index ea0b9e606ad1..928df1638c30 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -4,26 +4,57 @@ #include <linux/sched.h> #include <linux/hugetlb.h> -static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, - struct mm_walk *walk) +/* + * We want to know the real level where a entry is located ignoring any + * folding of levels which may be happening. For example if p4d is folded then + * a missing entry found at level 1 (p4d) is actually at level 0 (pgd). + */ +static int real_depth(int depth) +{ + if (depth == 3 && PTRS_PER_PMD == 1) + depth = 2; + if (depth == 2 && PTRS_PER_PUD == 1) + depth = 1; + if (depth == 1 && PTRS_PER_P4D == 1) + depth = 0; + return depth; +} + +static int walk_pte_range_inner(pte_t *pte, unsigned long addr, + unsigned long end, struct mm_walk *walk) { - pte_t *pte; - int err = 0; const struct mm_walk_ops *ops = walk->ops; - spinlock_t *ptl; + int err = 0; - pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (;;) { err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) break; - addr += PAGE_SIZE; - if (addr == end) + if (addr >= end - PAGE_SIZE) break; + addr += PAGE_SIZE; pte++; } + return err; +} + +static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pte_t *pte; + int err = 0; + spinlock_t *ptl; + + if (walk->no_vma) { + pte = pte_offset_map(pmd, addr); + err = walk_pte_range_inner(pte, addr, end, walk); + pte_unmap(pte); + } else { + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + err = walk_pte_range_inner(pte, addr, end, walk); + pte_unmap_unlock(pte, ptl); + } - pte_unmap_unlock(pte, ptl); return err; } @@ -34,18 +65,22 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, unsigned long next; const struct mm_walk_ops *ops = walk->ops; int err = 0; + int depth = real_depth(3); pmd = pmd_offset(pud, addr); do { again: next = pmd_addr_end(addr, end); - if (pmd_none(*pmd) || !walk->vma) { + if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) { if (ops->pte_hole) - err = ops->pte_hole(addr, next, walk); + err = ops->pte_hole(addr, next, depth, walk); if (err) break; continue; } + + walk->action = ACTION_SUBTREE; + /* * This implies that each ->pmd_entry() handler * needs to know about pmd_trans_huge() pmds @@ -55,16 +90,24 @@ again: if (err) break; + if (walk->action == ACTION_AGAIN) + goto again; + /* * Check this here so we only break down trans_huge * pages when we _need_ to */ - if (!ops->pte_entry) + if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) || + walk->action == ACTION_CONTINUE || + !(ops->pte_entry)) continue; - split_huge_pmd(walk->vma, pmd, addr); - if (pmd_trans_unstable(pmd)) - goto again; + if (walk->vma) { + split_huge_pmd(walk->vma, pmd, addr); + if (pmd_trans_unstable(pmd)) + goto again; + } + err = walk_pte_range(pmd, addr, next, walk); if (err) break; @@ -80,37 +123,41 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long next; const struct mm_walk_ops *ops = walk->ops; int err = 0; + int depth = real_depth(2); pud = pud_offset(p4d, addr); do { again: next = pud_addr_end(addr, end); - if (pud_none(*pud) || !walk->vma) { + if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) { if (ops->pte_hole) - err = ops->pte_hole(addr, next, walk); + err = ops->pte_hole(addr, next, depth, walk); if (err) break; continue; } - if (ops->pud_entry) { - spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma); + walk->action = ACTION_SUBTREE; - if (ptl) { - err = ops->pud_entry(pud, addr, next, walk); - spin_unlock(ptl); - if (err) - break; - continue; - } - } + if (ops->pud_entry) + err = ops->pud_entry(pud, addr, next, walk); + if (err) + break; + + if (walk->action == ACTION_AGAIN) + goto again; - split_huge_pud(walk->vma, pud, addr); + if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) || + walk->action == ACTION_CONTINUE || + !(ops->pmd_entry || ops->pte_entry)) + continue; + + if (walk->vma) + split_huge_pud(walk->vma, pud, addr); if (pud_none(*pud)) goto again; - if (ops->pmd_entry || ops->pte_entry) - err = walk_pmd_range(pud, addr, next, walk); + err = walk_pmd_range(pud, addr, next, walk); if (err) break; } while (pud++, addr = next, addr != end); @@ -125,18 +172,24 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long next; const struct mm_walk_ops *ops = walk->ops; int err = 0; + int depth = real_depth(1); p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) { if (ops->pte_hole) - err = ops->pte_hole(addr, next, walk); + err = ops->pte_hole(addr, next, depth, walk); if (err) break; continue; } - if (ops->pmd_entry || ops->pte_entry) + if (ops->p4d_entry) { + err = ops->p4d_entry(p4d, addr, next, walk); + if (err) + break; + } + if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -153,17 +206,26 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, const struct mm_walk_ops *ops = walk->ops; int err = 0; - pgd = pgd_offset(walk->mm, addr); + if (walk->pgd) + pgd = walk->pgd + pgd_index(addr); + else + pgd = pgd_offset(walk->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) { if (ops->pte_hole) - err = ops->pte_hole(addr, next, walk); + err = ops->pte_hole(addr, next, 0, walk); if (err) break; continue; } - if (ops->pmd_entry || ops->pte_entry) + if (ops->pgd_entry) { + err = ops->pgd_entry(pgd, addr, next, walk); + if (err) + break; + } + if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || + ops->pte_entry) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; @@ -199,7 +261,7 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, if (pte) err = ops->hugetlb_entry(pte, hmask, addr, next, walk); else if (ops->pte_hole) - err = ops->pte_hole(addr, next, walk); + err = ops->pte_hole(addr, next, -1, walk); if (err) break; @@ -243,7 +305,7 @@ static int walk_page_test(unsigned long start, unsigned long end, if (vma->vm_flags & VM_PFNMAP) { int err = 1; if (ops->pte_hole) - err = ops->pte_hole(start, end, walk); + err = ops->pte_hole(start, end, -1, walk); return err ? err : 1; } return 0; @@ -369,6 +431,33 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, return err; } +/* + * Similar to walk_page_range() but can walk any page tables even if they are + * not backed by VMAs. Because 'unusual' entries may be walked this function + * will also not lock the PTEs for the pte_entry() callback. This is useful for + * walking the kernel pages tables or page tables for firmware. + */ +int walk_page_range_novma(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + pgd_t *pgd, + void *private) +{ + struct mm_walk walk = { + .ops = ops, + .mm = mm, + .pgd = pgd, + .private = private, + .no_vma = true + }; + + if (start >= end || !walk.mm) + return -EINVAL; + + lockdep_assert_held(&walk.mm->mmap_sem); + + return __walk_page_range(start, end, &walk); +} + int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private) { diff --git a/mm/ptdump.c b/mm/ptdump.c new file mode 100644 index 000000000000..26208d0d03b7 --- /dev/null +++ b/mm/ptdump.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/pagewalk.h> +#include <linux/ptdump.h> +#include <linux/kasan.h> + +#ifdef CONFIG_KASAN +/* + * This is an optimization for KASAN=y case. Since all kasan page tables + * eventually point to the kasan_early_shadow_page we could call note_page() + * right away without walking through lower level page tables. This saves + * us dozens of seconds (minutes for 5-level config) while checking for + * W+X mapping or reading kernel_page_tables debugfs file. + */ +static inline int note_kasan_page_table(struct mm_walk *walk, + unsigned long addr) +{ + struct ptdump_state *st = walk->private; + + st->note_page(st, addr, 4, pte_val(kasan_early_shadow_pte[0])); + + walk->action = ACTION_CONTINUE; + + return 0; +} +#endif + +static int ptdump_pgd_entry(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + pgd_t val = READ_ONCE(*pgd); + +#if CONFIG_PGTABLE_LEVELS > 4 && defined(CONFIG_KASAN) + if (pgd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_p4d))) + return note_kasan_page_table(walk, addr); +#endif + + if (pgd_leaf(val)) + st->note_page(st, addr, 0, pgd_val(val)); + + return 0; +} + +static int ptdump_p4d_entry(p4d_t *p4d, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + p4d_t val = READ_ONCE(*p4d); + +#if CONFIG_PGTABLE_LEVELS > 3 && defined(CONFIG_KASAN) + if (p4d_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pud))) + return note_kasan_page_table(walk, addr); +#endif + + if (p4d_leaf(val)) + st->note_page(st, addr, 1, p4d_val(val)); + + return 0; +} + +static int ptdump_pud_entry(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + pud_t val = READ_ONCE(*pud); + +#if CONFIG_PGTABLE_LEVELS > 2 && defined(CONFIG_KASAN) + if (pud_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pmd))) + return note_kasan_page_table(walk, addr); +#endif + + if (pud_leaf(val)) + st->note_page(st, addr, 2, pud_val(val)); + + return 0; +} + +static int ptdump_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + pmd_t val = READ_ONCE(*pmd); + +#if defined(CONFIG_KASAN) + if (pmd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pte))) + return note_kasan_page_table(walk, addr); +#endif + + if (pmd_leaf(val)) + st->note_page(st, addr, 3, pmd_val(val)); + + return 0; +} + +static int ptdump_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + + st->note_page(st, addr, 4, pte_val(READ_ONCE(*pte))); + + return 0; +} + +static int ptdump_hole(unsigned long addr, unsigned long next, + int depth, struct mm_walk *walk) +{ + struct ptdump_state *st = walk->private; + + st->note_page(st, addr, depth, 0); + + return 0; +} + +static const struct mm_walk_ops ptdump_ops = { + .pgd_entry = ptdump_pgd_entry, + .p4d_entry = ptdump_p4d_entry, + .pud_entry = ptdump_pud_entry, + .pmd_entry = ptdump_pmd_entry, + .pte_entry = ptdump_pte_entry, + .pte_hole = ptdump_hole, +}; + +void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd) +{ + const struct ptdump_range *range = st->range; + + down_read(&mm->mmap_sem); + while (range->start != range->end) { + walk_page_range_novma(mm, range->start, range->end, + &ptdump_ops, pgd, st); + range++; + } + up_read(&mm->mmap_sem); + + /* Flush out the last page */ + st->note_page(st, 0, -1, 0); +} diff --git a/mm/slab_common.c b/mm/slab_common.c index 0d95ddea13b0..1907cb2903c7 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1580,18 +1580,17 @@ static int slabinfo_open(struct inode *inode, struct file *file) return seq_open(file, &slabinfo_op); } -static const struct file_operations proc_slabinfo_operations = { - .open = slabinfo_open, - .read = seq_read, - .write = slabinfo_write, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops slabinfo_proc_ops = { + .proc_open = slabinfo_open, + .proc_read = seq_read, + .proc_write = slabinfo_write, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static int __init slab_proc_init(void) { - proc_create("slabinfo", SLABINFO_RIGHTS, NULL, - &proc_slabinfo_operations); + proc_create("slabinfo", SLABINFO_RIGHTS, NULL, &slabinfo_proc_ops); return 0; } module_init(slab_proc_init); @@ -1677,28 +1676,6 @@ static __always_inline void *__do_krealloc(const void *p, size_t new_size, } /** - * __krealloc - like krealloc() but don't free @p. - * @p: object to reallocate memory for. - * @new_size: how many bytes of memory are required. - * @flags: the type of memory to allocate. - * - * This function is like krealloc() except it never frees the originally - * allocated buffer. Use this if you don't want to free the buffer immediately - * like, for example, with RCU. - * - * Return: pointer to the allocated memory or %NULL in case of error - */ -void *__krealloc(const void *p, size_t new_size, gfp_t flags) -{ - if (unlikely(!new_size)) - return ZERO_SIZE_PTR; - - return __do_krealloc(p, new_size, flags); - -} -EXPORT_SYMBOL(__krealloc); - -/** * krealloc - reallocate memory. The contents will remain unchanged. * @p: object to reallocate memory for. * @new_size: how many bytes of memory are required. diff --git a/mm/sparse.c b/mm/sparse.c index 3918fc3eaef1..c184b69460b7 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -198,16 +198,6 @@ static void section_mark_present(struct mem_section *ms) ms->section_mem_map |= SECTION_MARKED_PRESENT; } -static inline unsigned long next_present_section_nr(unsigned long section_nr) -{ - do { - section_nr++; - if (present_section_nr(section_nr)) - return section_nr; - } while ((section_nr <= __highest_present_section_nr)); - - return -1; -} #define for_each_present_section_nr(start, section_nr) \ for (section_nr = next_present_section_nr(start-1); \ ((section_nr != -1) && \ diff --git a/mm/swapfile.c b/mm/swapfile.c index 6febae9ad3cd..2c33ff456ed5 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2796,17 +2796,17 @@ static int swaps_open(struct inode *inode, struct file *file) return 0; } -static const struct file_operations proc_swaps_operations = { - .open = swaps_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, - .poll = swaps_poll, +static const struct proc_ops swaps_proc_ops = { + .proc_open = swaps_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, + .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { - proc_create("swaps", 0, NULL, &proc_swaps_operations); + proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 46d6cd9a36ae..829db9eba0cb 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -53,15 +53,12 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff, static int parse_qos(const char *buff); -/* - * Define allowed FILE OPERATIONS - */ -static const struct file_operations mpc_file_operations = { - .open = proc_mpc_open, - .read = seq_read, - .llseek = seq_lseek, - .write = proc_mpc_write, - .release = seq_release, +static const struct proc_ops mpc_proc_ops = { + .proc_open = proc_mpc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = proc_mpc_write, + .proc_release = seq_release, }; /* @@ -290,7 +287,7 @@ int mpc_proc_init(void) { struct proc_dir_entry *p; - p = proc_create(STAT_FILE_NAME, 0, atm_proc_root, &mpc_file_operations); + p = proc_create(STAT_FILE_NAME, 0, atm_proc_root, &mpc_proc_ops); if (!p) { pr_err("Unable to initialize /proc/atm/%s\n", STAT_FILE_NAME); return -ENOMEM; diff --git a/net/atm/proc.c b/net/atm/proc.c index c31896707313..4369ffa3302a 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -36,9 +36,9 @@ static ssize_t proc_dev_atm_read(struct file *file, char __user *buf, size_t count, loff_t *pos); -static const struct file_operations proc_atm_dev_ops = { - .read = proc_dev_atm_read, - .llseek = noop_llseek, +static const struct proc_ops atm_dev_proc_ops = { + .proc_read = proc_dev_atm_read, + .proc_lseek = noop_llseek, }; static void add_stats(struct seq_file *seq, const char *aal, @@ -359,7 +359,7 @@ int atm_proc_dev_register(struct atm_dev *dev) goto err_out; dev->proc_entry = proc_create_data(dev->proc_name, 0, atm_proc_root, - &proc_atm_dev_ops, dev); + &atm_dev_proc_ops, dev); if (!dev->proc_entry) goto err_free_name; return 0; diff --git a/net/core/dev.c b/net/core/dev.c index 17529d49faec..a69e8bd7ed74 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5792,7 +5792,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (&ptype->list == head) goto normal; - if (IS_ERR(pp) && PTR_ERR(pp) == -EINPROGRESS) { + if (PTR_ERR(pp) == -EINPROGRESS) { ret = GRO_CONSUMED; goto ok; } diff --git a/net/core/filter.c b/net/core/filter.c index 792e3744b915..c180871e606d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1573,7 +1573,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) return -EPERM; prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); - if (IS_ERR(prog) && PTR_ERR(prog) == -EINVAL) + if (PTR_ERR(prog) == -EINVAL) prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT); if (IS_ERR(prog)) return PTR_ERR(prog); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 294bfcf0ce0e..acc849df60b5 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -535,12 +535,12 @@ static int pgctrl_open(struct inode *inode, struct file *file) return single_open(file, pgctrl_show, PDE_DATA(inode)); } -static const struct file_operations pktgen_fops = { - .open = pgctrl_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pgctrl_write, - .release = single_release, +static const struct proc_ops pktgen_proc_ops = { + .proc_open = pgctrl_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = pgctrl_write, + .proc_release = single_release, }; static int pktgen_if_show(struct seq_file *seq, void *v) @@ -1707,12 +1707,12 @@ static int pktgen_if_open(struct inode *inode, struct file *file) return single_open(file, pktgen_if_show, PDE_DATA(inode)); } -static const struct file_operations pktgen_if_fops = { - .open = pktgen_if_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pktgen_if_write, - .release = single_release, +static const struct proc_ops pktgen_if_proc_ops = { + .proc_open = pktgen_if_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = pktgen_if_write, + .proc_release = single_release, }; static int pktgen_thread_show(struct seq_file *seq, void *v) @@ -1844,12 +1844,12 @@ static int pktgen_thread_open(struct inode *inode, struct file *file) return single_open(file, pktgen_thread_show, PDE_DATA(inode)); } -static const struct file_operations pktgen_thread_fops = { - .open = pktgen_thread_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pktgen_thread_write, - .release = single_release, +static const struct proc_ops pktgen_thread_proc_ops = { + .proc_open = pktgen_thread_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = pktgen_thread_write, + .proc_release = single_release, }; /* Think find or remove for NN */ @@ -1926,7 +1926,7 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d pkt_dev->entry = proc_create_data(dev->name, 0600, pn->proc_dir, - &pktgen_if_fops, + &pktgen_if_proc_ops, pkt_dev); if (!pkt_dev->entry) pr_err("can't move proc entry for '%s'\n", @@ -3638,7 +3638,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->clone_skb = pg_clone_skb_d; pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir, - &pktgen_if_fops, pkt_dev); + &pktgen_if_proc_ops, pkt_dev); if (!pkt_dev->entry) { pr_err("cannot create %s/%s procfs entry\n", PG_PROC_DIR, ifname); @@ -3708,7 +3708,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) t->tsk = p; pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir, - &pktgen_thread_fops, t); + &pktgen_thread_proc_ops, t); if (!pe) { pr_err("cannot create %s/%s procfs entry\n", PG_PROC_DIR, t->tsk->comm); @@ -3793,7 +3793,7 @@ static int __net_init pg_net_init(struct net *net) pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR); return -ENODEV; } - pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops); + pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_proc_ops); if (pe == NULL) { pr_err("cannot create %s procfs entry\n", PGCTRL); ret = -EINVAL; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index f35308ff84c3..4438f6b12335 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1334,7 +1334,7 @@ static int __init ipconfig_proc_net_init(void) /* Create a new file under /proc/net/ipconfig */ static int ipconfig_proc_net_create(const char *name, - const struct file_operations *fops) + const struct proc_ops *proc_ops) { char *pname; struct proc_dir_entry *p; @@ -1346,7 +1346,7 @@ static int ipconfig_proc_net_create(const char *name, if (!pname) return -ENOMEM; - p = proc_create(pname, 0444, init_net.proc_net, fops); + p = proc_create(pname, 0444, init_net.proc_net, proc_ops); kfree(pname); if (!p) return -ENOMEM; @@ -1355,7 +1355,7 @@ static int ipconfig_proc_net_create(const char *name, } /* Write NTP server IP addresses to /proc/net/ipconfig/ntp_servers */ -static int ntp_servers_seq_show(struct seq_file *seq, void *v) +static int ntp_servers_show(struct seq_file *seq, void *v) { int i; @@ -1365,7 +1365,7 @@ static int ntp_servers_seq_show(struct seq_file *seq, void *v) } return 0; } -DEFINE_SHOW_ATTRIBUTE(ntp_servers_seq); +DEFINE_PROC_SHOW_ATTRIBUTE(ntp_servers); #endif /* CONFIG_PROC_FS */ /* @@ -1456,7 +1456,7 @@ static int __init ip_auto_config(void) proc_create_single("pnp", 0444, init_net.proc_net, pnp_seq_show); if (ipconfig_proc_net_init() == 0) - ipconfig_proc_net_create("ntp_servers", &ntp_servers_seq_fops); + ipconfig_proc_net_create("ntp_servers", &ntp_servers_proc_ops); #endif /* CONFIG_PROC_FS */ if (!ic_enable) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 6bdb1ab8af61..f8755a4ae9d4 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -58,7 +58,7 @@ struct clusterip_config { }; #ifdef CONFIG_PROC_FS -static const struct file_operations clusterip_proc_fops; +static const struct proc_ops clusterip_proc_ops; #endif struct clusterip_net { @@ -280,7 +280,7 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, mutex_lock(&cn->mutex); c->pde = proc_create_data(buffer, 0600, cn->procdir, - &clusterip_proc_fops, c); + &clusterip_proc_ops, c); mutex_unlock(&cn->mutex); if (!c->pde) { err = -ENOMEM; @@ -804,12 +804,12 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input, return size; } -static const struct file_operations clusterip_proc_fops = { - .open = clusterip_proc_open, - .read = seq_read, - .write = clusterip_proc_write, - .llseek = seq_lseek, - .release = clusterip_proc_release, +static const struct proc_ops clusterip_proc_ops = { + .proc_open = clusterip_proc_open, + .proc_read = seq_read, + .proc_write = clusterip_proc_write, + .proc_lseek = seq_lseek, + .proc_release = clusterip_proc_release, }; #endif /* CONFIG_PROC_FS */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d5c57b3f77d5..ebe7060d0fc9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -237,11 +237,11 @@ static int rt_cache_seq_open(struct inode *inode, struct file *file) return seq_open(file, &rt_cache_seq_ops); } -static const struct file_operations rt_cache_seq_fops = { - .open = rt_cache_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops rt_cache_proc_ops = { + .proc_open = rt_cache_seq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; @@ -328,11 +328,11 @@ static int rt_cpu_seq_open(struct inode *inode, struct file *file) return seq_open(file, &rt_cpu_seq_ops); } -static const struct file_operations rt_cpu_seq_fops = { - .open = rt_cpu_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops rt_cpu_proc_ops = { + .proc_open = rt_cpu_seq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; #ifdef CONFIG_IP_ROUTE_CLASSID @@ -366,12 +366,12 @@ static int __net_init ip_rt_do_proc_init(struct net *net) struct proc_dir_entry *pde; pde = proc_create("rt_cache", 0444, net->proc_net, - &rt_cache_seq_fops); + &rt_cache_proc_ops); if (!pde) goto err1; pde = proc_create("rt_cache", 0444, - net->proc_net_stat, &rt_cpu_seq_fops); + net->proc_net_stat, &rt_cpu_proc_ops); if (!pde) goto err2; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 781e0b482189..0a9708004e20 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -103,7 +103,7 @@ static DEFINE_SPINLOCK(recent_lock); static DEFINE_MUTEX(recent_mutex); #ifdef CONFIG_PROC_FS -static const struct file_operations recent_mt_fops; +static const struct proc_ops recent_mt_proc_ops; #endif static u_int32_t hash_rnd __read_mostly; @@ -405,7 +405,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par, goto out; } pde = proc_create_data(t->name, ip_list_perms, recent_net->xt_recent, - &recent_mt_fops, t); + &recent_mt_proc_ops, t); if (pde == NULL) { recent_table_free(t); ret = -ENOMEM; @@ -616,13 +616,12 @@ recent_mt_proc_write(struct file *file, const char __user *input, return size + 1; } -static const struct file_operations recent_mt_fops = { - .open = recent_seq_open, - .read = seq_read, - .write = recent_mt_proc_write, - .release = seq_release_private, - .owner = THIS_MODULE, - .llseek = seq_lseek, +static const struct proc_ops recent_mt_proc_ops = { + .proc_open = recent_seq_open, + .proc_read = seq_read, + .proc_write = recent_mt_proc_write, + .proc_release = seq_release_private, + .proc_lseek = seq_lseek, }; static int __net_init recent_proc_net_init(struct net *net) diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 311181720d79..7511a68aadf0 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1428,10 +1428,10 @@ static ssize_t read_gssp(struct file *file, char __user *buf, return len; } -static const struct file_operations use_gss_proxy_ops = { - .open = nonseekable_open, - .write = write_gssp, - .read = read_gssp, +static const struct proc_ops use_gss_proxy_proc_ops = { + .proc_open = nonseekable_open, + .proc_write = write_gssp, + .proc_read = read_gssp, }; static int create_use_gss_proxy_proc_entry(struct net *net) @@ -1442,7 +1442,7 @@ static int create_use_gss_proxy_proc_entry(struct net *net) sn->use_gss_proxy = -1; *p = proc_create_data("use-gss-proxy", S_IFREG | 0600, sn->proc_net_rpc, - &use_gss_proxy_ops, net); + &use_gss_proxy_proc_ops, net); if (!*p) return -ENOMEM; init_gssp_clnt(sn); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index d996bf872a7c..375914c7a7b1 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1571,15 +1571,14 @@ static int cache_release_procfs(struct inode *inode, struct file *filp) return cache_release(inode, filp, cd); } -static const struct file_operations cache_file_operations_procfs = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .read = cache_read_procfs, - .write = cache_write_procfs, - .poll = cache_poll_procfs, - .unlocked_ioctl = cache_ioctl_procfs, /* for FIONREAD */ - .open = cache_open_procfs, - .release = cache_release_procfs, +static const struct proc_ops cache_channel_proc_ops = { + .proc_lseek = no_llseek, + .proc_read = cache_read_procfs, + .proc_write = cache_write_procfs, + .proc_poll = cache_poll_procfs, + .proc_ioctl = cache_ioctl_procfs, /* for FIONREAD */ + .proc_open = cache_open_procfs, + .proc_release = cache_release_procfs, }; static int content_open_procfs(struct inode *inode, struct file *filp) @@ -1596,11 +1595,11 @@ static int content_release_procfs(struct inode *inode, struct file *filp) return content_release(inode, filp, cd); } -static const struct file_operations content_file_operations_procfs = { - .open = content_open_procfs, - .read = seq_read, - .llseek = seq_lseek, - .release = content_release_procfs, +static const struct proc_ops content_proc_ops = { + .proc_open = content_open_procfs, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = content_release_procfs, }; static int open_flush_procfs(struct inode *inode, struct file *filp) @@ -1634,12 +1633,12 @@ static ssize_t write_flush_procfs(struct file *filp, return write_flush(filp, buf, count, ppos, cd); } -static const struct file_operations cache_flush_operations_procfs = { - .open = open_flush_procfs, - .read = read_flush_procfs, - .write = write_flush_procfs, - .release = release_flush_procfs, - .llseek = no_llseek, +static const struct proc_ops cache_flush_proc_ops = { + .proc_open = open_flush_procfs, + .proc_read = read_flush_procfs, + .proc_write = write_flush_procfs, + .proc_release = release_flush_procfs, + .proc_lseek = no_llseek, }; static void remove_cache_proc_entries(struct cache_detail *cd) @@ -1662,19 +1661,19 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) goto out_nomem; p = proc_create_data("flush", S_IFREG | 0600, - cd->procfs, &cache_flush_operations_procfs, cd); + cd->procfs, &cache_flush_proc_ops, cd); if (p == NULL) goto out_nomem; if (cd->cache_request || cd->cache_parse) { p = proc_create_data("channel", S_IFREG | 0600, cd->procfs, - &cache_file_operations_procfs, cd); + &cache_channel_proc_ops, cd); if (p == NULL) goto out_nomem; } if (cd->cache_show) { p = proc_create_data("content", S_IFREG | 0400, cd->procfs, - &content_file_operations_procfs, cd); + &content_proc_ops, cd); if (p == NULL) goto out_nomem; } diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 7c74197c2ecf..c964b48eaaba 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -69,12 +69,11 @@ static int rpc_proc_open(struct inode *inode, struct file *file) return single_open(file, rpc_proc_show, PDE_DATA(inode)); } -static const struct file_operations rpc_proc_fops = { - .owner = THIS_MODULE, - .open = rpc_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops rpc_proc_ops = { + .proc_open = rpc_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; /* @@ -281,19 +280,19 @@ EXPORT_SYMBOL_GPL(rpc_clnt_show_stats); */ static inline struct proc_dir_entry * do_register(struct net *net, const char *name, void *data, - const struct file_operations *fops) + const struct proc_ops *proc_ops) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc/%s\n", name); sn = net_generic(net, sunrpc_net_id); - return proc_create_data(name, 0, sn->proc_net_rpc, fops, data); + return proc_create_data(name, 0, sn->proc_net_rpc, proc_ops, data); } struct proc_dir_entry * rpc_proc_register(struct net *net, struct rpc_stat *statp) { - return do_register(net, statp->program->name, statp, &rpc_proc_fops); + return do_register(net, statp->program->name, statp, &rpc_proc_ops); } EXPORT_SYMBOL_GPL(rpc_proc_register); @@ -308,9 +307,9 @@ rpc_proc_unregister(struct net *net, const char *name) EXPORT_SYMBOL_GPL(rpc_proc_unregister); struct proc_dir_entry * -svc_proc_register(struct net *net, struct svc_stat *statp, const struct file_operations *fops) +svc_proc_register(struct net *net, struct svc_stat *statp, const struct proc_ops *proc_ops) { - return do_register(net, statp->program->pg_name, statp, fops); + return do_register(net, statp->program->pg_name, statp, proc_ops); } EXPORT_SYMBOL_GPL(svc_proc_register); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 297d1eb79e5c..dbda08ec566e 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3189,7 +3189,7 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, flags | XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_KEEP_DST_REF); - if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) + if (PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); if (IS_ERR(dst)) diff --git a/samples/kfifo/bytestream-example.c b/samples/kfifo/bytestream-example.c index 9ca3e4400c98..c406f03ee551 100644 --- a/samples/kfifo/bytestream-example.c +++ b/samples/kfifo/bytestream-example.c @@ -142,11 +142,10 @@ static ssize_t fifo_read(struct file *file, char __user *buf, return ret ? ret : copied; } -static const struct file_operations fifo_fops = { - .owner = THIS_MODULE, - .read = fifo_read, - .write = fifo_write, - .llseek = noop_llseek, +static const struct proc_ops fifo_proc_ops = { + .proc_read = fifo_read, + .proc_write = fifo_write, + .proc_lseek = noop_llseek, }; static int __init example_init(void) @@ -169,7 +168,7 @@ static int __init example_init(void) return -EIO; } - if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) { + if (proc_create(PROC_FIFO, 0, NULL, &fifo_proc_ops) == NULL) { #ifdef DYNAMIC kfifo_free(&test); #endif diff --git a/samples/kfifo/inttype-example.c b/samples/kfifo/inttype-example.c index 6cdeb72f83f1..78977fc4a23f 100644 --- a/samples/kfifo/inttype-example.c +++ b/samples/kfifo/inttype-example.c @@ -135,11 +135,10 @@ static ssize_t fifo_read(struct file *file, char __user *buf, return ret ? ret : copied; } -static const struct file_operations fifo_fops = { - .owner = THIS_MODULE, - .read = fifo_read, - .write = fifo_write, - .llseek = noop_llseek, +static const struct proc_ops fifo_proc_ops = { + .proc_read = fifo_read, + .proc_write = fifo_write, + .proc_lseek = noop_llseek, }; static int __init example_init(void) @@ -160,7 +159,7 @@ static int __init example_init(void) return -EIO; } - if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) { + if (proc_create(PROC_FIFO, 0, NULL, &fifo_proc_ops) == NULL) { #ifdef DYNAMIC kfifo_free(&test); #endif diff --git a/samples/kfifo/record-example.c b/samples/kfifo/record-example.c index 79ae8bb04120..c507998a2617 100644 --- a/samples/kfifo/record-example.c +++ b/samples/kfifo/record-example.c @@ -149,11 +149,10 @@ static ssize_t fifo_read(struct file *file, char __user *buf, return ret ? ret : copied; } -static const struct file_operations fifo_fops = { - .owner = THIS_MODULE, - .read = fifo_read, - .write = fifo_write, - .llseek = noop_llseek, +static const struct proc_ops fifo_proc_ops = { + .proc_read = fifo_read, + .proc_write = fifo_write, + .proc_lseek = noop_llseek, }; static int __init example_init(void) @@ -176,7 +175,7 @@ static int __init example_init(void) return -EIO; } - if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) { + if (proc_create(PROC_FIFO, 0, NULL, &fifo_proc_ops) == NULL) { #ifdef DYNAMIC kfifo_free(&test); #endif diff --git a/scripts/coccinelle/free/devm_free.cocci b/scripts/coccinelle/free/devm_free.cocci index 9330d4294b74..3357bf4dbd7c 100644 --- a/scripts/coccinelle/free/devm_free.cocci +++ b/scripts/coccinelle/free/devm_free.cocci @@ -91,8 +91,6 @@ position p; | kzfree@p(x) | - __krealloc@p(x, ...) -| krealloc@p(x, ...) | free_pages@p(x, ...) @@ -116,8 +114,6 @@ position p != safe.p; | * kzfree@p(x) | -* __krealloc@p(x, ...) -| * krealloc@p(x, ...) | * free_pages@p(x, ...) diff --git a/sound/core/info.c b/sound/core/info.c index 6801d8160866..ca87ae4c30ba 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -282,17 +282,16 @@ static int snd_info_entry_release(struct inode *inode, struct file *file) return 0; } -static const struct file_operations snd_info_entry_operations = -{ - .owner = THIS_MODULE, - .llseek = snd_info_entry_llseek, - .read = snd_info_entry_read, - .write = snd_info_entry_write, - .poll = snd_info_entry_poll, - .unlocked_ioctl = snd_info_entry_ioctl, - .mmap = snd_info_entry_mmap, - .open = snd_info_entry_open, - .release = snd_info_entry_release, +static const struct proc_ops snd_info_entry_operations = +{ + .proc_lseek = snd_info_entry_llseek, + .proc_read = snd_info_entry_read, + .proc_write = snd_info_entry_write, + .proc_poll = snd_info_entry_poll, + .proc_ioctl = snd_info_entry_ioctl, + .proc_mmap = snd_info_entry_mmap, + .proc_open = snd_info_entry_open, + .proc_release = snd_info_entry_release, }; /* @@ -421,14 +420,13 @@ static int snd_info_text_entry_release(struct inode *inode, struct file *file) return 0; } -static const struct file_operations snd_info_text_entry_ops = +static const struct proc_ops snd_info_text_entry_ops = { - .owner = THIS_MODULE, - .open = snd_info_text_entry_open, - .release = snd_info_text_entry_release, - .write = snd_info_text_entry_write, - .llseek = seq_lseek, - .read = seq_read, + .proc_open = snd_info_text_entry_open, + .proc_release = snd_info_text_entry_release, + .proc_write = snd_info_text_entry_write, + .proc_lseek = seq_lseek, + .proc_read = seq_read, }; static struct snd_info_entry *create_subdir(struct module *mod, @@ -810,7 +808,7 @@ static int __snd_info_register(struct snd_info_entry *entry) return -ENOMEM; } } else { - const struct file_operations *ops; + const struct proc_ops *ops; if (entry->content == SNDRV_INFO_CONTENT_DATA) ops = &snd_info_entry_operations; else diff --git a/sound/soc/codecs/ak4104.c b/sound/soc/codecs/ak4104.c index e8c5fda82e08..979cfb165eed 100644 --- a/sound/soc/codecs/ak4104.c +++ b/sound/soc/codecs/ak4104.c @@ -295,8 +295,7 @@ static int ak4104_spi_probe(struct spi_device *spi) reset_gpiod = devm_gpiod_get_optional(&spi->dev, "reset", GPIOD_OUT_HIGH); - if (IS_ERR(reset_gpiod) && - PTR_ERR(reset_gpiod) == -EPROBE_DEFER) + if (PTR_ERR(reset_gpiod) == -EPROBE_DEFER) return -EPROBE_DEFER; /* read the 'reserved' register - according to the datasheet, it diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c index 793a14d58667..5f25b9f872bd 100644 --- a/sound/soc/codecs/cs4270.c +++ b/sound/soc/codecs/cs4270.c @@ -681,8 +681,7 @@ static int cs4270_i2c_probe(struct i2c_client *i2c_client, reset_gpiod = devm_gpiod_get_optional(&i2c_client->dev, "reset", GPIOD_OUT_HIGH); - if (IS_ERR(reset_gpiod) && - PTR_ERR(reset_gpiod) == -EPROBE_DEFER) + if (PTR_ERR(reset_gpiod) == -EPROBE_DEFER) return -EPROBE_DEFER; cs4270->regmap = devm_regmap_init_i2c(i2c_client, &cs4270_regmap); diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c index b4e9a6c73f90..d087f3b20b1d 100644 --- a/sound/soc/codecs/tlv320aic32x4.c +++ b/sound/soc/codecs/tlv320aic32x4.c @@ -1098,11 +1098,9 @@ static int aic32x4_setup_regulators(struct device *dev, return PTR_ERR(aic32x4->supply_av); } } else { - if (IS_ERR(aic32x4->supply_dv) && - PTR_ERR(aic32x4->supply_dv) == -EPROBE_DEFER) + if (PTR_ERR(aic32x4->supply_dv) == -EPROBE_DEFER) return -EPROBE_DEFER; - if (IS_ERR(aic32x4->supply_av) && - PTR_ERR(aic32x4->supply_av) == -EPROBE_DEFER) + if (PTR_ERR(aic32x4->supply_av) == -EPROBE_DEFER) return -EPROBE_DEFER; } diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c index cbe598b0fb10..98a9fe645521 100644 --- a/sound/soc/sunxi/sun4i-spdif.c +++ b/sound/soc/sunxi/sun4i-spdif.c @@ -555,7 +555,7 @@ static int sun4i_spdif_probe(struct platform_device *pdev) if (quirks->has_reset) { host->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL); - if (IS_ERR(host->rst) && PTR_ERR(host->rst) == -EPROBE_DEFER) { + if (PTR_ERR(host->rst) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; dev_err(&pdev->dev, "Failed to get reset: %d\n", ret); return ret; diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 140c8362f113..5fca38fe1ba8 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -14,10 +14,11 @@ #include <linux/bits.h> #include <linux/compiler.h> -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) -#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) -#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) +#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) +#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) +#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); |