diff options
Diffstat (limited to 'fs')
114 files changed, 1978 insertions, 1603 deletions
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 21e154516bf2..f14478643b91 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -142,39 +142,6 @@ config BINFMT_ZFLAT help Support FLAT format compressed binaries -config HAVE_AOUT - def_bool n - -config BINFMT_AOUT - tristate "Kernel support for a.out and ECOFF binaries" - depends on HAVE_AOUT - help - A.out (Assembler.OUTput) is a set of formats for libraries and - executables used in the earliest versions of UNIX. Linux used - the a.out formats QMAGIC and ZMAGIC until they were replaced - with the ELF format. - - The conversion to ELF started in 1995. This option is primarily - provided for historical interest and for the benefit of those - who need to run binaries from that era. - - Most people should answer N here. If you think you may have - occasional use for this format, enable module support above - and answer M here to compile this support as a module called - binfmt_aout. - - If any crucial components of your system (such as /sbin/init - or /lib/ld.so) are still in a.out format, you will have to - say Y here. - -config OSF4_COMPAT - bool "OSF/1 v4 readv/writev compatibility" - depends on ALPHA && BINFMT_AOUT - help - Say Y if you are using OSF/1 binaries (like Netscape and Acrobat) - with v4 shared libraries freely available from Compaq. If you're - going to use shared libraries from Tru64 version 5.0 or later, say N. - config BINFMT_MISC tristate "Kernel support for MISC binaries" help diff --git a/fs/Makefile b/fs/Makefile index 93b80529f8e8..4dea17840761 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -38,7 +38,6 @@ obj-$(CONFIG_FS_DAX) += dax.o obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ obj-$(CONFIG_FILE_LOCKING) += locks.o -obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o diff --git a/fs/afs/flock.c b/fs/afs/flock.c index c4210a3964d8..bbcc5afd1576 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call) if (call->error == 0) { spin_lock(&vnode->lock); trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0); - vnode->locked_at = call->reply_time; + vnode->locked_at = call->issue_time; afs_schedule_lock_extension(vnode); spin_unlock(&vnode->lock); } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 4943413d9c5f..7d37f63ef0f0 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -131,7 +131,7 @@ bad: static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry) { - return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry; + return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry; } static void xdr_decode_AFSCallBack(const __be32 **_bp, diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 64ad55494349..723d162078a3 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -137,7 +137,6 @@ struct afs_call { bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ bool upgrade; /* T to request service upgrade */ - bool have_reply_time; /* T if have got reply_time */ bool intr; /* T if interruptible */ bool unmarshalling_error; /* T if an unmarshalling error occurred */ u16 service_id; /* Actual service ID (after upgrade) */ @@ -151,7 +150,7 @@ struct afs_call { } __attribute__((packed)); __be64 tmp64; }; - ktime_t reply_time; /* Time of first reply packet */ + ktime_t issue_time; /* Time of issue of operation */ }; struct afs_call_type { diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 933e67fcdab1..805328ca5428 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -69,6 +69,7 @@ int afs_abort_to_error(u32 abort_code) /* Unified AFS error table */ case UAEPERM: return -EPERM; case UAENOENT: return -ENOENT; + case UAEAGAIN: return -EAGAIN; case UAEACCES: return -EACCES; case UAEBUSY: return -EBUSY; case UAEEXIST: return -EEXIST; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index d5c4785c862d..eccc3cd0cb70 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -351,6 +351,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) if (call->max_lifespan) rxrpc_kernel_set_max_life(call->net->socket, rxcall, call->max_lifespan); + call->issue_time = ktime_get_real(); /* send the request */ iov[0].iov_base = call->request; @@ -501,12 +502,6 @@ static void afs_deliver_to_call(struct afs_call *call) return; } - if (!call->have_reply_time && - rxrpc_kernel_get_reply_time(call->net->socket, - call->rxcall, - &call->reply_time)) - call->have_reply_time = true; - ret = call->type->deliver(call); state = READ_ONCE(call->state); if (ret == 0 && call->unmarshalling_error) diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index fdc7d675b4b0..11571cca86c1 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -232,8 +232,7 @@ static void xdr_decode_YFSCallBack(const __be32 **_bp, struct afs_callback *cb = &scb->callback; ktime_t cb_expiry; - cb_expiry = call->reply_time; - cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100); + cb_expiry = ktime_add(call->issue_time, xdr_to_u64(x->expiration_time) * 100); cb->expires_at = ktime_divns(cb_expiry, NSEC_PER_SEC); scb->have_cb = true; *_bp += xdr_size(x); diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c deleted file mode 100644 index 0dcfc691e7e2..000000000000 --- a/fs/binfmt_aout.c +++ /dev/null @@ -1,342 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * linux/fs/binfmt_aout.c - * - * Copyright (C) 1991, 1992, 1996 Linus Torvalds - */ - -#include <linux/module.h> - -#include <linux/time.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/mman.h> -#include <linux/a.out.h> -#include <linux/errno.h> -#include <linux/signal.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/file.h> -#include <linux/stat.h> -#include <linux/fcntl.h> -#include <linux/ptrace.h> -#include <linux/user.h> -#include <linux/binfmts.h> -#include <linux/personality.h> -#include <linux/init.h> -#include <linux/coredump.h> -#include <linux/slab.h> -#include <linux/sched/task_stack.h> - -#include <linux/uaccess.h> -#include <asm/cacheflush.h> - -static int load_aout_binary(struct linux_binprm *); -static int load_aout_library(struct file*); - -static struct linux_binfmt aout_format = { - .module = THIS_MODULE, - .load_binary = load_aout_binary, - .load_shlib = load_aout_library, -}; - -#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE) - -static int set_brk(unsigned long start, unsigned long end) -{ - start = PAGE_ALIGN(start); - end = PAGE_ALIGN(end); - if (end > start) - return vm_brk(start, end - start); - return 0; -} - -/* - * create_aout_tables() parses the env- and arg-strings in new user - * memory and creates the pointer tables from them, and puts their - * addresses on the "stack", returning the new stack pointer value. - */ -static unsigned long __user *create_aout_tables(char __user *p, struct linux_binprm * bprm) -{ - char __user * __user *argv; - char __user * __user *envp; - unsigned long __user *sp; - int argc = bprm->argc; - int envc = bprm->envc; - - sp = (void __user *)((-(unsigned long)sizeof(char *)) & (unsigned long) p); -#ifdef __alpha__ -/* whee.. test-programs are so much fun. */ - put_user(0, --sp); - put_user(0, --sp); - if (bprm->loader) { - put_user(0, --sp); - put_user(1003, --sp); - put_user(bprm->loader, --sp); - put_user(1002, --sp); - } - put_user(bprm->exec, --sp); - put_user(1001, --sp); -#endif - sp -= envc+1; - envp = (char __user * __user *) sp; - sp -= argc+1; - argv = (char __user * __user *) sp; -#ifndef __alpha__ - put_user((unsigned long) envp,--sp); - put_user((unsigned long) argv,--sp); -#endif - put_user(argc,--sp); - current->mm->arg_start = (unsigned long) p; - while (argc-->0) { - char c; - put_user(p,argv++); - do { - get_user(c,p++); - } while (c); - } - put_user(NULL,argv); - current->mm->arg_end = current->mm->env_start = (unsigned long) p; - while (envc-->0) { - char c; - put_user(p,envp++); - do { - get_user(c,p++); - } while (c); - } - put_user(NULL,envp); - current->mm->env_end = (unsigned long) p; - return sp; -} - -/* - * These are the functions used to load a.out style executables and shared - * libraries. There is no binary dependent code anywhere else. - */ - -static int load_aout_binary(struct linux_binprm * bprm) -{ - struct pt_regs *regs = current_pt_regs(); - struct exec ex; - unsigned long error; - unsigned long fd_offset; - unsigned long rlim; - int retval; - - ex = *((struct exec *) bprm->buf); /* exec-header */ - if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC && - N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) || - N_TRSIZE(ex) || N_DRSIZE(ex) || - i_size_read(file_inode(bprm->file)) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) { - return -ENOEXEC; - } - - /* - * Requires a mmap handler. This prevents people from using a.out - * as part of an exploit attack against /proc-related vulnerabilities. - */ - if (!bprm->file->f_op->mmap) - return -ENOEXEC; - - fd_offset = N_TXTOFF(ex); - - /* Check initial limits. This avoids letting people circumvent - * size limits imposed on them by creating programs with large - * arrays in the data or bss. - */ - rlim = rlimit(RLIMIT_DATA); - if (rlim >= RLIM_INFINITY) - rlim = ~0; - if (ex.a_data + ex.a_bss > rlim) - return -ENOMEM; - - /* Flush all traces of the currently running executable */ - retval = begin_new_exec(bprm); - if (retval) - return retval; - - /* OK, This is the point of no return */ -#ifdef __alpha__ - SET_AOUT_PERSONALITY(bprm, ex); -#else - set_personality(PER_LINUX); -#endif - setup_new_exec(bprm); - - current->mm->end_code = ex.a_text + - (current->mm->start_code = N_TXTADDR(ex)); - current->mm->end_data = ex.a_data + - (current->mm->start_data = N_DATADDR(ex)); - current->mm->brk = ex.a_bss + - (current->mm->start_brk = N_BSSADDR(ex)); - - retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT); - if (retval < 0) - return retval; - - - if (N_MAGIC(ex) == OMAGIC) { - unsigned long text_addr, map_size; - loff_t pos; - - text_addr = N_TXTADDR(ex); - -#ifdef __alpha__ - pos = fd_offset; - map_size = ex.a_text+ex.a_data + PAGE_SIZE - 1; -#else - pos = 32; - map_size = ex.a_text+ex.a_data; -#endif - error = vm_brk(text_addr & PAGE_MASK, map_size); - if (error) - return error; - - error = read_code(bprm->file, text_addr, pos, - ex.a_text+ex.a_data); - if ((signed long)error < 0) - return error; - } else { - if ((ex.a_text & 0xfff || ex.a_data & 0xfff) && - (N_MAGIC(ex) != NMAGIC) && printk_ratelimit()) - { - printk(KERN_NOTICE "executable not page aligned\n"); - } - - if ((fd_offset & ~PAGE_MASK) != 0 && printk_ratelimit()) - { - printk(KERN_WARNING - "fd_offset is not page aligned. Please convert program: %pD\n", - bprm->file); - } - - if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) { - error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); - if (error) - return error; - - read_code(bprm->file, N_TXTADDR(ex), fd_offset, - ex.a_text + ex.a_data); - goto beyond_if; - } - - error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, - PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE, - fd_offset); - - if (error != N_TXTADDR(ex)) - return error; - - error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE, - fd_offset + ex.a_text); - if (error != N_DATADDR(ex)) - return error; - } -beyond_if: - set_binfmt(&aout_format); - - retval = set_brk(current->mm->start_brk, current->mm->brk); - if (retval < 0) - return retval; - - current->mm->start_stack = - (unsigned long) create_aout_tables((char __user *) bprm->p, bprm); -#ifdef __alpha__ - regs->gp = ex.a_gpvalue; -#endif - finalize_exec(bprm); - start_thread(regs, ex.a_entry, current->mm->start_stack); - return 0; -} - -static int load_aout_library(struct file *file) -{ - struct inode * inode; - unsigned long bss, start_addr, len; - unsigned long error; - int retval; - struct exec ex; - loff_t pos = 0; - - inode = file_inode(file); - - retval = -ENOEXEC; - error = kernel_read(file, &ex, sizeof(ex), &pos); - if (error != sizeof(ex)) - goto out; - - /* We come in here for the regular a.out style of shared libraries */ - if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) || - N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) || - i_size_read(inode) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) { - goto out; - } - - /* - * Requires a mmap handler. This prevents people from using a.out - * as part of an exploit attack against /proc-related vulnerabilities. - */ - if (!file->f_op->mmap) - goto out; - - if (N_FLAGS(ex)) - goto out; - - /* For QMAGIC, the starting address is 0x20 into the page. We mask - this off to get the starting address for the page */ - - start_addr = ex.a_entry & 0xfffff000; - - if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) { - if (printk_ratelimit()) - { - printk(KERN_WARNING - "N_TXTOFF is not page aligned. Please convert library: %pD\n", - file); - } - retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); - if (retval) - goto out; - - read_code(file, start_addr, N_TXTOFF(ex), - ex.a_text + ex.a_data); - retval = 0; - goto out; - } - /* Now use mmap to map the library into memory. */ - error = vm_mmap(file, start_addr, ex.a_text + ex.a_data, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE, - N_TXTOFF(ex)); - retval = error; - if (error != start_addr) - goto out; - - len = PAGE_ALIGN(ex.a_text + ex.a_data); - bss = ex.a_text + ex.a_data + ex.a_bss; - if (bss > len) { - retval = vm_brk(start_addr + len, bss - len); - if (retval) - goto out; - } - retval = 0; -out: - return retval; -} - -static int __init init_aout_binfmt(void) -{ - register_binfmt(&aout_format); - return 0; -} - -static void __exit exit_aout_binfmt(void) -{ - unregister_binfmt(&aout_format); -} - -core_initcall(init_aout_binfmt); -module_exit(exit_aout_binfmt); -MODULE_LICENSE("GPL"); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c3aecfb0a71d..e0375ba9d0fe 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -440,39 +440,26 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, btrfs_put_caching_control(caching_ctl); } -int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) +static int btrfs_caching_ctl_wait_done(struct btrfs_block_group *cache, + struct btrfs_caching_control *caching_ctl) +{ + wait_event(caching_ctl->wait, btrfs_block_group_done(cache)); + return cache->cached == BTRFS_CACHE_ERROR ? -EIO : 0; +} + +static int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) { struct btrfs_caching_control *caching_ctl; - int ret = 0; + int ret; caching_ctl = btrfs_get_caching_control(cache); if (!caching_ctl) return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0; - - wait_event(caching_ctl->wait, btrfs_block_group_done(cache)); - if (cache->cached == BTRFS_CACHE_ERROR) - ret = -EIO; + ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); btrfs_put_caching_control(caching_ctl); return ret; } -static bool space_cache_v1_done(struct btrfs_block_group *cache) -{ - bool ret; - - spin_lock(&cache->lock); - ret = cache->cached != BTRFS_CACHE_FAST; - spin_unlock(&cache->lock); - - return ret; -} - -void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache, - struct btrfs_caching_control *caching_ctl) -{ - wait_event(caching_ctl->wait, space_cache_v1_done(cache)); -} - #ifdef CONFIG_BTRFS_DEBUG static void fragment_free_space(struct btrfs_block_group *block_group) { @@ -750,9 +737,8 @@ done: btrfs_put_block_group(block_group); } -int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only) +int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) { - DEFINE_WAIT(wait); struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_caching_control *caching_ctl = NULL; int ret = 0; @@ -785,10 +771,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only } WARN_ON(cache->caching_ctl); cache->caching_ctl = caching_ctl; - if (btrfs_test_opt(fs_info, SPACE_CACHE)) - cache->cached = BTRFS_CACHE_FAST; - else - cache->cached = BTRFS_CACHE_STARTED; + cache->cached = BTRFS_CACHE_STARTED; cache->has_caching_ctl = 1; spin_unlock(&cache->lock); @@ -801,8 +784,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work); out: - if (load_cache_only && caching_ctl) - btrfs_wait_space_cache_v1_finished(cache, caching_ctl); + if (wait && caching_ctl) + ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); if (caching_ctl) btrfs_put_caching_control(caching_ctl); @@ -1640,9 +1623,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) div64_u64(zone_unusable * 100, bg->length)); trace_btrfs_reclaim_block_group(bg); ret = btrfs_relocate_chunk(fs_info, bg->start); - if (ret) + if (ret) { + btrfs_dec_block_group_ro(bg); btrfs_err(fs_info, "error relocating chunk %llu", bg->start); + } next: btrfs_put_block_group(bg); @@ -3310,7 +3295,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, * space back to the block group, otherwise we will leak space. */ if (!alloc && !btrfs_block_group_done(cache)) - btrfs_cache_block_group(cache, 1); + btrfs_cache_block_group(cache, true); byte_in_group = bytenr - cache->start; WARN_ON(byte_in_group > cache->length); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 35e0e860cc0b..6b3cdc4cbc41 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -263,9 +263,7 @@ void btrfs_dec_nocow_writers(struct btrfs_block_group *bg); void btrfs_wait_nocow_writers(struct btrfs_block_group *bg); void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache, u64 num_bytes); -int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache); -int btrfs_cache_block_group(struct btrfs_block_group *cache, - int load_cache_only); +int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait); void btrfs_put_caching_control(struct btrfs_caching_control *ctl); struct btrfs_caching_control *btrfs_get_caching_control( struct btrfs_block_group *cache); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 6e556031a8f3..ebfa35fe1c38 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2075,6 +2075,9 @@ cow_done: if (!p->skip_locking) { level = btrfs_header_level(b); + + btrfs_maybe_reset_lockdep_class(root, b); + if (level <= write_lock_level) { btrfs_tree_lock(b); p->locks[level] = BTRFS_WRITE_LOCK; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4db85b9dc7ed..df8c99c99df9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -505,7 +505,6 @@ struct btrfs_free_cluster { enum btrfs_caching_type { BTRFS_CACHE_NO, BTRFS_CACHE_STARTED, - BTRFS_CACHE_FAST, BTRFS_CACHE_FINISHED, BTRFS_CACHE_ERROR, }; @@ -1089,8 +1088,6 @@ struct btrfs_fs_info { spinlock_t zone_active_bgs_lock; struct list_head zone_active_bgs; - /* Waiters when BTRFS_FS_NEED_ZONE_FINISH is set */ - wait_queue_head_t zone_finish_wait; /* Updates are not protected by any lock */ struct btrfs_commit_stats commit_stats; @@ -1173,6 +1170,8 @@ enum { BTRFS_ROOT_ORPHAN_CLEANUP, /* This root has a drop operation that was started previously. */ BTRFS_ROOT_UNFINISHED_DROP, + /* This reloc root needs to have its buffers lockdep class reset. */ + BTRFS_ROOT_RESET_LOCKDEP_CLASS, }; static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index f43196a893ca..41cddd3ff059 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -165,7 +165,7 @@ no_valid_dev_replace_entry_found: */ if (btrfs_find_device(fs_info->fs_devices, &args)) { btrfs_err(fs_info, - "replace devid present without an active replace item"); +"replace without active item, run 'device scan --forget' on the target device"); ret = -EUCLEAN; } else { dev_replace->srcdev = NULL; @@ -1129,8 +1129,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info) up_write(&dev_replace->rwsem); /* Scrub for replace must not be running in suspended state */ - ret = btrfs_scrub_cancel(fs_info); - ASSERT(ret != -ENOTCONN); + btrfs_scrub_cancel(fs_info); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4c3166f3c725..2633137c3e9f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -87,88 +87,6 @@ struct async_submit_bio { }; /* - * Lockdep class keys for extent_buffer->lock's in this root. For a given - * eb, the lockdep key is determined by the btrfs_root it belongs to and - * the level the eb occupies in the tree. - * - * Different roots are used for different purposes and may nest inside each - * other and they require separate keysets. As lockdep keys should be - * static, assign keysets according to the purpose of the root as indicated - * by btrfs_root->root_key.objectid. This ensures that all special purpose - * roots have separate keysets. - * - * Lock-nesting across peer nodes is always done with the immediate parent - * node locked thus preventing deadlock. As lockdep doesn't know this, use - * subclass to avoid triggering lockdep warning in such cases. - * - * The key is set by the readpage_end_io_hook after the buffer has passed - * csum validation but before the pages are unlocked. It is also set by - * btrfs_init_new_buffer on freshly allocated blocks. - * - * We also add a check to make sure the highest level of the tree is the - * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code - * needs update as well. - */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# if BTRFS_MAX_LEVEL != 8 -# error -# endif - -#define DEFINE_LEVEL(stem, level) \ - .names[level] = "btrfs-" stem "-0" #level, - -#define DEFINE_NAME(stem) \ - DEFINE_LEVEL(stem, 0) \ - DEFINE_LEVEL(stem, 1) \ - DEFINE_LEVEL(stem, 2) \ - DEFINE_LEVEL(stem, 3) \ - DEFINE_LEVEL(stem, 4) \ - DEFINE_LEVEL(stem, 5) \ - DEFINE_LEVEL(stem, 6) \ - DEFINE_LEVEL(stem, 7) - -static struct btrfs_lockdep_keyset { - u64 id; /* root objectid */ - /* Longest entry: btrfs-free-space-00 */ - char names[BTRFS_MAX_LEVEL][20]; - struct lock_class_key keys[BTRFS_MAX_LEVEL]; -} btrfs_lockdep_keysets[] = { - { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") }, - { .id = BTRFS_EXTENT_TREE_OBJECTID, DEFINE_NAME("extent") }, - { .id = BTRFS_CHUNK_TREE_OBJECTID, DEFINE_NAME("chunk") }, - { .id = BTRFS_DEV_TREE_OBJECTID, DEFINE_NAME("dev") }, - { .id = BTRFS_CSUM_TREE_OBJECTID, DEFINE_NAME("csum") }, - { .id = BTRFS_QUOTA_TREE_OBJECTID, DEFINE_NAME("quota") }, - { .id = BTRFS_TREE_LOG_OBJECTID, DEFINE_NAME("log") }, - { .id = BTRFS_TREE_RELOC_OBJECTID, DEFINE_NAME("treloc") }, - { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") }, - { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") }, - { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") }, - { .id = 0, DEFINE_NAME("tree") }, -}; - -#undef DEFINE_LEVEL -#undef DEFINE_NAME - -void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, - int level) -{ - struct btrfs_lockdep_keyset *ks; - - BUG_ON(level >= ARRAY_SIZE(ks->keys)); - - /* find the matching keyset, id 0 is the default entry */ - for (ks = btrfs_lockdep_keysets; ks->id; ks++) - if (ks->id == objectid) - break; - - lockdep_set_class_and_name(&eb->lock, - &ks->keys[level], ks->names[level]); -} - -#endif - -/* * Compute the csum of a btree block and store the result to provided buffer. */ static void csum_tree_block(struct extent_buffer *buf, u8 *result) @@ -3150,7 +3068,6 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); init_waitqueue_head(&fs_info->delayed_iputs_wait); - init_waitqueue_head(&fs_info->zone_finish_wait); /* Usable values until the real ones are cached from the superblock */ fs_info->nodesize = 4096; @@ -4558,6 +4475,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); /* + * If we had UNFINISHED_DROPS we could still be processing them, so + * clear that bit and wake up relocation so it can stop. + * We must do this before stopping the block group reclaim task, because + * at btrfs_relocate_block_group() we wait for this bit, and after the + * wait we stop with -EINTR if btrfs_fs_closing() returns non-zero - we + * have just set BTRFS_FS_CLOSING_START, so btrfs_fs_closing() will + * return 1. + */ + btrfs_wake_unfinished_drop(fs_info); + + /* * We may have the reclaim task running and relocating a data block group, * in which case it may create delayed iputs. So stop it before we park * the cleaner kthread otherwise we can get new delayed iputs after @@ -4575,12 +4503,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) */ kthread_park(fs_info->cleaner_kthread); - /* - * If we had UNFINISHED_DROPS we could still be processing them, so - * clear that bit and wake up relocation so it can stop. - */ - btrfs_wake_unfinished_drop(fs_info); - /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -4603,6 +4525,31 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); + /* + * After we parked the cleaner kthread, ordered extents may have + * completed and created new delayed iputs. If one of the async reclaim + * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we + * can hang forever trying to stop it, because if a delayed iput is + * added after it ran btrfs_run_delayed_iputs() and before it called + * btrfs_wait_on_delayed_iputs(), it will hang forever since there is + * no one else to run iputs. + * + * So wait for all ongoing ordered extents to complete and then run + * delayed iputs. This works because once we reach this point no one + * can either create new ordered extents nor create delayed iputs + * through some other means. + * + * Also note that btrfs_wait_ordered_roots() is not safe here, because + * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent, + * but the delayed iput for the respective inode is made only when doing + * the final btrfs_put_ordered_extent() (which must happen at + * btrfs_finish_ordered_io() when we are unmounting). + */ + btrfs_flush_workqueue(fs_info->endio_write_workers); + /* Ordered extents for free space inodes. */ + btrfs_flush_workqueue(fs_info->endio_freespace_worker); + btrfs_run_delayed_iputs(fs_info); + cancel_work_sync(&fs_info->async_reclaim_work); cancel_work_sync(&fs_info->async_data_reclaim_work); cancel_work_sync(&fs_info->preempt_reclaim_work); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 8993b428e09c..47ad8e0a2d33 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -137,14 +137,4 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags); int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid); int btrfs_init_root_free_objectid(struct btrfs_root *root); -#ifdef CONFIG_DEBUG_LOCK_ALLOC -void btrfs_set_buffer_lockdep_class(u64 objectid, - struct extent_buffer *eb, int level); -#else -static inline void btrfs_set_buffer_lockdep_class(u64 objectid, - struct extent_buffer *eb, int level) -{ -} -#endif - #endif diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index ea3ec1e761e8..6914cd8024ba 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2551,17 +2551,10 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, return -EINVAL; /* - * pull in the free space cache (if any) so that our pin - * removes the free space from the cache. We have load_only set - * to one because the slow code to read in the free extents does check - * the pinned extents. + * Fully cache the free space first so that our pin removes the free space + * from the cache. */ - btrfs_cache_block_group(cache, 1); - /* - * Make sure we wait until the cache is completely built in case it is - * missing or is invalid and therefore needs to be rebuilt. - */ - ret = btrfs_wait_block_group_cache_done(cache); + ret = btrfs_cache_block_group(cache, true); if (ret) goto out; @@ -2584,12 +2577,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, if (!block_group) return -EINVAL; - btrfs_cache_block_group(block_group, 1); - /* - * Make sure we wait until the cache is completely built in case it is - * missing or is invalid and therefore needs to be rebuilt. - */ - ret = btrfs_wait_block_group_cache_done(block_group); + ret = btrfs_cache_block_group(block_group, true); if (ret) goto out; @@ -4399,7 +4387,7 @@ have_block_group: ffe_ctl->cached = btrfs_block_group_done(block_group); if (unlikely(!ffe_ctl->cached)) { ffe_ctl->have_caching_bg = true; - ret = btrfs_cache_block_group(block_group, 0); + ret = btrfs_cache_block_group(block_group, false); /* * If we get ENOMEM here or something else we want to @@ -4867,6 +4855,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *buf; + u64 lockdep_owner = owner; buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level); if (IS_ERR(buf)) @@ -4886,11 +4875,26 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, } /* + * The reloc trees are just snapshots, so we need them to appear to be + * just like any other fs tree WRT lockdep. + * + * The exception however is in replace_path() in relocation, where we + * hold the lock on the original fs root and then search for the reloc + * root. At that point we need to make sure any reloc root buffers are + * set to the BTRFS_TREE_RELOC_OBJECTID lockdep class in order to make + * lockdep happy. + */ + if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID && + !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)) + lockdep_owner = BTRFS_FS_TREE_OBJECTID; + + /* * This needs to stay, because we could allocate a freed block from an * old tree into a new tree, so we need to make sure this new block is * set to the appropriate level and owner. */ - btrfs_set_buffer_lockdep_class(owner, buf, level); + btrfs_set_buffer_lockdep_class(lockdep_owner, buf, level); + __btrfs_tree_lock(buf, nest); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); @@ -6153,13 +6157,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) if (end - start >= range->minlen) { if (!btrfs_block_group_done(cache)) { - ret = btrfs_cache_block_group(cache, 0); - if (ret) { - bg_failed++; - bg_ret = ret; - continue; - } - ret = btrfs_wait_block_group_cache_done(cache); + ret = btrfs_cache_block_group(cache, true); if (ret) { bg_failed++; bg_ret = ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index bfae67c593c5..cf4f19e80e2f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3233,7 +3233,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl, u32 bio_size = bio->bi_iter.bi_size; u32 real_size; const sector_t sector = disk_bytenr >> SECTOR_SHIFT; - bool contig; + bool contig = false; int ret; ASSERT(bio); @@ -3242,10 +3242,35 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl, if (bio_ctrl->compress_type != compress_type) return 0; - if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) + + if (bio->bi_iter.bi_size == 0) { + /* We can always add a page into an empty bio. */ + contig = true; + } else if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE) { + struct bio_vec *bvec = bio_last_bvec_all(bio); + + /* + * The contig check requires the following conditions to be met: + * 1) The pages are belonging to the same inode + * This is implied by the call chain. + * + * 2) The range has adjacent logical bytenr + * + * 3) The range has adjacent file offset + * This is required for the usage of btrfs_bio->file_offset. + */ + if (bio_end_sector(bio) == sector && + page_offset(bvec->bv_page) + bvec->bv_offset + + bvec->bv_len == page_offset(page) + pg_offset) + contig = true; + } else { + /* + * For compression, all IO should have its logical bytenr + * set to the starting bytenr of the compressed extent. + */ contig = bio->bi_iter.bi_sector == sector; - else - contig = bio_end_sector(bio) == sector; + } + if (!contig) return 0; @@ -6140,6 +6165,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, struct extent_buffer *exists = NULL; struct page *p; struct address_space *mapping = fs_info->btree_inode->i_mapping; + u64 lockdep_owner = owner_root; int uptodate = 1; int ret; @@ -6164,7 +6190,15 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, eb = __alloc_extent_buffer(fs_info, start, len); if (!eb) return ERR_PTR(-ENOMEM); - btrfs_set_buffer_lockdep_class(owner_root, eb, level); + + /* + * The reloc trees are just snapshots, so we need them to appear to be + * just like any other fs tree WRT lockdep. + */ + if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID) + lockdep_owner = BTRFS_FS_TREE_OBJECTID; + + btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++, index++) { diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 66c822182ecc..5a3f6e0d9688 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2482,6 +2482,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); + btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); goto out; } @@ -2498,6 +2499,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); + btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_mark_buffer_dirty(leaf); goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f0c97d25b4a0..1372210869b1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1644,10 +1644,9 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode, done_offset = end; if (done_offset == start) { - struct btrfs_fs_info *info = inode->root->fs_info; - - wait_var_event(&info->zone_finish_wait, - !test_bit(BTRFS_FS_NEED_ZONE_FINISH, &info->flags)); + wait_on_bit_io(&inode->root->fs_info->flags, + BTRFS_FS_NEED_ZONE_FINISH, + TASK_UNINTERRUPTIBLE); continue; } @@ -7694,6 +7693,20 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, bool unlock_extents = false; /* + * We could potentially fault if we have a buffer > PAGE_SIZE, and if + * we're NOWAIT we may submit a bio for a partial range and return + * EIOCBQUEUED, which would result in an errant short read. + * + * The best way to handle this would be to allow for partial completions + * of iocb's, so we could submit the partial bio, return and fault in + * the rest of the pages, and then submit the io for the rest of the + * range. However we don't have that currently, so simply return + * -EAGAIN at this point so that the normal path is used. + */ + if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE) + return -EAGAIN; + + /* * Cap the size of reads to that usually seen in buffered I/O as we need * to allocate a contiguous array for the checksums. */ diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 33461b4f9c8b..9063072b399b 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -14,6 +14,93 @@ #include "locking.h" /* + * Lockdep class keys for extent_buffer->lock's in this root. For a given + * eb, the lockdep key is determined by the btrfs_root it belongs to and + * the level the eb occupies in the tree. + * + * Different roots are used for different purposes and may nest inside each + * other and they require separate keysets. As lockdep keys should be + * static, assign keysets according to the purpose of the root as indicated + * by btrfs_root->root_key.objectid. This ensures that all special purpose + * roots have separate keysets. + * + * Lock-nesting across peer nodes is always done with the immediate parent + * node locked thus preventing deadlock. As lockdep doesn't know this, use + * subclass to avoid triggering lockdep warning in such cases. + * + * The key is set by the readpage_end_io_hook after the buffer has passed + * csum validation but before the pages are unlocked. It is also set by + * btrfs_init_new_buffer on freshly allocated blocks. + * + * We also add a check to make sure the highest level of the tree is the + * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code + * needs update as well. + */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#if BTRFS_MAX_LEVEL != 8 +#error +#endif + +#define DEFINE_LEVEL(stem, level) \ + .names[level] = "btrfs-" stem "-0" #level, + +#define DEFINE_NAME(stem) \ + DEFINE_LEVEL(stem, 0) \ + DEFINE_LEVEL(stem, 1) \ + DEFINE_LEVEL(stem, 2) \ + DEFINE_LEVEL(stem, 3) \ + DEFINE_LEVEL(stem, 4) \ + DEFINE_LEVEL(stem, 5) \ + DEFINE_LEVEL(stem, 6) \ + DEFINE_LEVEL(stem, 7) + +static struct btrfs_lockdep_keyset { + u64 id; /* root objectid */ + /* Longest entry: btrfs-free-space-00 */ + char names[BTRFS_MAX_LEVEL][20]; + struct lock_class_key keys[BTRFS_MAX_LEVEL]; +} btrfs_lockdep_keysets[] = { + { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") }, + { .id = BTRFS_EXTENT_TREE_OBJECTID, DEFINE_NAME("extent") }, + { .id = BTRFS_CHUNK_TREE_OBJECTID, DEFINE_NAME("chunk") }, + { .id = BTRFS_DEV_TREE_OBJECTID, DEFINE_NAME("dev") }, + { .id = BTRFS_CSUM_TREE_OBJECTID, DEFINE_NAME("csum") }, + { .id = BTRFS_QUOTA_TREE_OBJECTID, DEFINE_NAME("quota") }, + { .id = BTRFS_TREE_LOG_OBJECTID, DEFINE_NAME("log") }, + { .id = BTRFS_TREE_RELOC_OBJECTID, DEFINE_NAME("treloc") }, + { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") }, + { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") }, + { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") }, + { .id = 0, DEFINE_NAME("tree") }, +}; + +#undef DEFINE_LEVEL +#undef DEFINE_NAME + +void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level) +{ + struct btrfs_lockdep_keyset *ks; + + BUG_ON(level >= ARRAY_SIZE(ks->keys)); + + /* Find the matching keyset, id 0 is the default entry */ + for (ks = btrfs_lockdep_keysets; ks->id; ks++) + if (ks->id == objectid) + break; + + lockdep_set_class_and_name(&eb->lock, &ks->keys[level], ks->names[level]); +} + +void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb) +{ + if (test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)) + btrfs_set_buffer_lockdep_class(root->root_key.objectid, + eb, btrfs_header_level(eb)); +} + +#endif + +/* * Extent buffer locking * ===================== * @@ -164,6 +251,8 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root) while (1) { eb = btrfs_root_node(root); + + btrfs_maybe_reset_lockdep_class(root, eb); btrfs_tree_lock(eb); if (eb == root->node) break; @@ -185,6 +274,8 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root) while (1) { eb = btrfs_root_node(root); + + btrfs_maybe_reset_lockdep_class(root, eb); btrfs_tree_read_lock(eb); if (eb == root->node) break; diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index bbc45534ae9a..ab268be09bb5 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -131,4 +131,18 @@ void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock); void btrfs_drew_read_lock(struct btrfs_drew_lock *lock); void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level); +void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb); +#else +static inline void btrfs_set_buffer_lockdep_class(u64 objectid, + struct extent_buffer *eb, int level) +{ +} +static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, + struct extent_buffer *eb) +{ +} +#endif + #endif diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index a6dc827e75af..45c02aba2492 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1326,7 +1326,9 @@ again: btrfs_release_path(path); path->lowest_level = level; + set_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state); ret = btrfs_search_slot(trans, src, &key, path, 0, 1); + clear_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state); path->lowest_level = 0; if (ret) { if (ret > 0) @@ -3573,7 +3575,12 @@ int prepare_to_relocate(struct reloc_control *rc) */ return PTR_ERR(trans); } - return btrfs_commit_transaction(trans); + + ret = btrfs_commit_transaction(trans); + if (ret) + unset_reloc_control(rc); + + return ret; } static noinline_for_stack int relocate_block_group(struct reloc_control *rc) diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index a64b26b16904..d647cb2938c0 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -349,9 +349,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, key.offset = ref_id; again: ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); - if (ret < 0) + if (ret < 0) { + err = ret; goto out; - if (ret == 0) { + } else if (ret == 0) { leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index d0cbeb7ae81c..435559ba94fa 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -199,7 +199,7 @@ static u64 calc_chunk_size(const struct btrfs_fs_info *fs_info, u64 flags) ASSERT(flags & BTRFS_BLOCK_GROUP_TYPE_MASK); if (flags & BTRFS_BLOCK_GROUP_DATA) - return SZ_1G; + return BTRFS_MAX_DATA_CHUNK_SIZE; else if (flags & BTRFS_BLOCK_GROUP_SYSTEM) return SZ_32M; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 9e0e0ae2288c..43f905ab0a18 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1233,7 +1233,8 @@ static void extent_err(const struct extent_buffer *eb, int slot, } static int check_extent_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot) + struct btrfs_key *key, int slot, + struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_extent_item *ei; @@ -1453,6 +1454,26 @@ static int check_extent_item(struct extent_buffer *leaf, total_refs, inline_refs); return -EUCLEAN; } + + if ((prev_key->type == BTRFS_EXTENT_ITEM_KEY) || + (prev_key->type == BTRFS_METADATA_ITEM_KEY)) { + u64 prev_end = prev_key->objectid; + + if (prev_key->type == BTRFS_METADATA_ITEM_KEY) + prev_end += fs_info->nodesize; + else + prev_end += prev_key->offset; + + if (unlikely(prev_end > key->objectid)) { + extent_err(leaf, slot, + "previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]", + prev_key->objectid, prev_key->type, + prev_key->offset, key->objectid, key->type, + key->offset); + return -EUCLEAN; + } + } + return 0; } @@ -1621,7 +1642,7 @@ static int check_leaf_item(struct extent_buffer *leaf, break; case BTRFS_EXTENT_ITEM_KEY: case BTRFS_METADATA_ITEM_KEY: - ret = check_extent_item(leaf, key, slot); + ret = check_extent_item(leaf, key, slot, prev_key); break; case BTRFS_TREE_BLOCK_REF_KEY: case BTRFS_SHARED_DATA_REF_KEY: diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index dcf75a8daa20..9205c4a5ca81 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1146,7 +1146,9 @@ again: extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen, inode_objectid, parent_objectid, 0, 0); - if (!IS_ERR_OR_NULL(extref)) { + if (IS_ERR(extref)) { + return PTR_ERR(extref); + } else if (extref) { u32 item_size; u32 cur_offset = 0; unsigned long base; @@ -1457,7 +1459,7 @@ static int add_link(struct btrfs_trans_handle *trans, * on the inode will not free it. We will fixup the link count later. */ if (other_inode->i_nlink == 0) - inc_nlink(other_inode); + set_nlink(other_inode, 1); add_link: ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name, namelen, 0, ref_index); @@ -1600,7 +1602,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, * free it. We will fixup the link count later. */ if (!ret && inode->i_nlink == 0) - inc_nlink(inode); + set_nlink(inode, 1); } if (ret < 0) goto out; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 272901514b0c..f63ff91e2883 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2345,8 +2345,11 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0, &bdev, &disk_super); - if (ret) + if (ret) { + btrfs_put_dev_args_from_path(args); return ret; + } + args->devid = btrfs_stack_device_id(&disk_super->dev_item); memcpy(args->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE); if (btrfs_fs_incompat(fs_info, METADATA_UUID)) @@ -5264,6 +5267,9 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl, ctl->stripe_size); } + /* Stripe size should not go beyond 1G. */ + ctl->stripe_size = min_t(u64, ctl->stripe_size, SZ_1G); + /* Align to BTRFS_STRIPE_LEN */ ctl->stripe_size = round_down(ctl->stripe_size, BTRFS_STRIPE_LEN); ctl->chunk_size = ctl->stripe_size * data_stripes; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 7421abcf325a..5bb8d8c86311 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -371,6 +371,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler, const char *name, const void *buffer, size_t size, int flags) { + if (btrfs_root_readonly(BTRFS_I(inode)->root)) + return -EROFS; + name = xattr_full_name(handler, name); return btrfs_setxattr_trans(inode, name, buffer, size, flags); } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b150b07ba1a7..73c6929f7be6 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -421,10 +421,19 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) * since btrfs adds the pages one by one to a bio, and btrfs cannot * increase the metadata reservation even if it increases the number of * extents, it is safe to stick with the limit. + * + * With the zoned emulation, we can have non-zoned device on the zoned + * mode. In this case, we don't have a valid max zone append size. So, + * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size. */ - zone_info->max_zone_append_size = - min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, - (u64)bdev_max_segments(bdev) << PAGE_SHIFT); + if (bdev_is_zoned(bdev)) { + zone_info->max_zone_append_size = min_t(u64, + (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, + (u64)bdev_max_segments(bdev) << PAGE_SHIFT); + } else { + zone_info->max_zone_append_size = + (u64)bdev_max_segments(bdev) << PAGE_SHIFT; + } if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++; @@ -1178,7 +1187,7 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) * offset. */ static int calculate_alloc_pointer(struct btrfs_block_group *cache, - u64 *offset_ret) + u64 *offset_ret, bool new) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_root *root; @@ -1188,6 +1197,21 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache, int ret; u64 length; + /* + * Avoid tree lookups for a new block group, there's no use for it. + * It must always be 0. + * + * Also, we have a lock chain of extent buffer lock -> chunk mutex. + * For new a block group, this function is called from + * btrfs_make_block_group() which is already taking the chunk mutex. + * Thus, we cannot call calculate_alloc_pointer() which takes extent + * buffer locks to avoid deadlock. + */ + if (new) { + *offset_ret = 0; + return 0; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -1323,6 +1347,13 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) else num_conventional++; + /* + * Consider a zone as active if we can allow any number of + * active zones. + */ + if (!device->zone_info->max_active_zones) + __set_bit(i, active); + if (!is_sequential) { alloc_offsets[i] = WP_CONVENTIONAL; continue; @@ -1389,45 +1420,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) __set_bit(i, active); break; } - - /* - * Consider a zone as active if we can allow any number of - * active zones. - */ - if (!device->zone_info->max_active_zones) - __set_bit(i, active); } if (num_sequential > 0) cache->seq_zone = true; if (num_conventional > 0) { - /* - * Avoid calling calculate_alloc_pointer() for new BG. It - * is no use for new BG. It must be always 0. - * - * Also, we have a lock chain of extent buffer lock -> - * chunk mutex. For new BG, this function is called from - * btrfs_make_block_group() which is already taking the - * chunk mutex. Thus, we cannot call - * calculate_alloc_pointer() which takes extent buffer - * locks to avoid deadlock. - */ - /* Zone capacity is always zone size in emulation */ cache->zone_capacity = cache->length; - if (new) { - cache->alloc_offset = 0; - goto out; - } - ret = calculate_alloc_pointer(cache, &last_alloc); - if (ret || map->num_stripes == num_conventional) { - if (!ret) - cache->alloc_offset = last_alloc; - else - btrfs_err(fs_info, + ret = calculate_alloc_pointer(cache, &last_alloc, new); + if (ret) { + btrfs_err(fs_info, "zoned: failed to determine allocation offset of bg %llu", - cache->start); + cache->start); + goto out; + } else if (map->num_stripes == num_conventional) { + cache->alloc_offset = last_alloc; + cache->zone_is_active = 1; goto out; } } @@ -1495,13 +1504,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } - if (cache->zone_is_active) { - btrfs_get_block_group(cache); - spin_lock(&fs_info->zone_active_bgs_lock); - list_add_tail(&cache->active_bg_list, &fs_info->zone_active_bgs); - spin_unlock(&fs_info->zone_active_bgs_lock); - } - out: if (cache->alloc_offset > fs_info->zone_size) { btrfs_err(fs_info, @@ -1526,10 +1528,16 @@ out: ret = -EIO; } - if (!ret) + if (!ret) { cache->meta_write_pointer = cache->alloc_offset + cache->start; - - if (ret) { + if (cache->zone_is_active) { + btrfs_get_block_group(cache); + spin_lock(&fs_info->zone_active_bgs_lock); + list_add_tail(&cache->active_bg_list, + &fs_info->zone_active_bgs); + spin_unlock(&fs_info->zone_active_bgs_lock); + } + } else { kfree(cache->physical_map); cache->physical_map = NULL; } @@ -1910,10 +1918,44 @@ out_unlock: return ret; } +static void wait_eb_writebacks(struct btrfs_block_group *block_group) +{ + struct btrfs_fs_info *fs_info = block_group->fs_info; + const u64 end = block_group->start + block_group->length; + struct radix_tree_iter iter; + struct extent_buffer *eb; + void __rcu **slot; + + rcu_read_lock(); + radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, + block_group->start >> fs_info->sectorsize_bits) { + eb = radix_tree_deref_slot(slot); + if (!eb) + continue; + if (radix_tree_deref_retry(eb)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (eb->start < block_group->start) + continue; + if (eb->start >= end) + break; + + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); + wait_on_extent_buffer_writeback(eb); + rcu_read_lock(); + } + rcu_read_unlock(); +} + static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct map_lookup *map; + const bool is_metadata = (block_group->flags & + (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)); int ret = 0; int i; @@ -1924,8 +1966,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ } /* Check if we have unwritten allocated space */ - if ((block_group->flags & - (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) && + if (is_metadata && block_group->start + block_group->alloc_offset > block_group->meta_write_pointer) { spin_unlock(&block_group->lock); return -EAGAIN; @@ -1950,6 +1991,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ /* No need to wait for NOCOW writers. Zoned mode does not allow that */ btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start, block_group->length); + /* Wait for extent buffers to be written. */ + if (is_metadata) + wait_eb_writebacks(block_group); spin_lock(&block_group->lock); @@ -2007,8 +2051,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ /* For active_bg_list */ btrfs_put_block_group(block_group); - clear_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); - wake_up_all(&fs_info->zone_finish_wait); + clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); return 0; } diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 6cba2c6de2f9..2ad58c465208 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -111,6 +111,7 @@ struct cachefiles_cache { char *tag; /* cache binding tag */ refcount_t unbind_pincount;/* refcount to do daemon unbind */ struct xarray reqs; /* xarray of pending on-demand requests */ + unsigned long req_id_next; struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ u32 ondemand_id_next; }; diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 1fee702d5529..0254ed39f68c 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -158,9 +158,13 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) /* fail OPEN request if daemon reports an error */ if (size < 0) { - if (!IS_ERR_VALUE(size)) - size = -EINVAL; - req->error = size; + if (!IS_ERR_VALUE(size)) { + req->error = -EINVAL; + ret = -EINVAL; + } else { + req->error = size; + ret = 0; + } goto out; } @@ -238,14 +242,19 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, unsigned long id = 0; size_t n; int ret = 0; - XA_STATE(xas, &cache->reqs, 0); + XA_STATE(xas, &cache->reqs, cache->req_id_next); /* - * Search for a request that has not ever been processed, to prevent - * requests from being processed repeatedly. + * Cyclically search for a request that has not ever been processed, + * to prevent requests from being processed repeatedly, and make + * request distribution fair. */ xa_lock(&cache->reqs); req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW); + if (!req && cache->req_id_next > 0) { + xas_set(&xas, 0); + req = xas_find_marked(&xas, cache->req_id_next - 1, CACHEFILES_REQ_NEW); + } if (!req) { xa_unlock(&cache->reqs); return 0; @@ -260,6 +269,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, } xas_clear_mark(&xas, CACHEFILES_REQ_NEW); + cache->req_id_next = xas.xa_index + 1; xa_unlock(&cache->reqs); id = xas.xa_index; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 11fd85de7217..c05477e28cff 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -42,7 +42,7 @@ void cifs_dump_detail(void *buf, struct TCP_Server_Info *server) smb->Command, smb->Status.CifsError, smb->Flags, smb->Flags2, smb->Mid, smb->Pid); cifs_dbg(VFS, "smb buf %p len %u\n", smb, - server->ops->calc_smb_size(smb, server)); + server->ops->calc_smb_size(smb)); #endif /* CONFIG_CIFS_DEBUG2 */ } diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 8f7835ccbca1..46f5718754f9 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -32,10 +32,9 @@ int __cifs_calc_signature(struct smb_rqst *rqst, int rc; struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; - int is_smb2 = server->vals->header_preamble_size == 0; /* iov[0] is actual data and not the rfc1002 length for SMB2+ */ - if (is_smb2) { + if (!is_smb1(server)) { if (iov[0].iov_len <= 4) return -EIO; i = 0; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f54d8bf2732a..8042d7280dec 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1248,6 +1248,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, lock_two_nondirectories(target_inode, src_inode); cifs_dbg(FYI, "about to flush pages\n"); + + rc = filemap_write_and_wait_range(src_inode->i_mapping, off, + off + len - 1); + if (rc) + goto out; + /* should we flush first and last page first */ truncate_inode_pages(&target_inode->i_data, 0); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 81f4c15936d0..5b4a7a32bdc5 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -153,6 +153,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 38 -#define CIFS_VERSION "2.38" +#define SMB3_PRODUCT_BUILD 39 +#define CIFS_VERSION "2.39" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index bc0ee2d4b47b..ae7f571a7dba 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -417,7 +417,7 @@ struct smb_version_operations { int (*close_dir)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* calculate a size of SMB message */ - unsigned int (*calc_smb_size)(void *buf, struct TCP_Server_Info *ptcpi); + unsigned int (*calc_smb_size)(void *buf); /* check for STATUS_PENDING and process the response if yes */ bool (*is_status_pending)(char *buf, struct TCP_Server_Info *server); /* check for STATUS_NETWORK_SESSION_EXPIRED */ @@ -557,6 +557,8 @@ struct smb_version_values { #define HEADER_SIZE(server) (server->vals->header_size) #define MAX_HEADER_SIZE(server) (server->vals->max_header_size) +#define HEADER_PREAMBLE_SIZE(server) (server->vals->header_preamble_size) +#define MID_HEADER_SIZE(server) (HEADER_SIZE(server) - 1 - HEADER_PREAMBLE_SIZE(server)) /** * CIFS superblock mount flags (mnt_cifs_flags) to consider when @@ -750,6 +752,11 @@ struct TCP_Server_Info { #endif }; +static inline bool is_smb1(struct TCP_Server_Info *server) +{ + return HEADER_PREAMBLE_SIZE(server) != 0; +} + static inline void cifs_server_lock(struct TCP_Server_Info *server) { unsigned int nofs_flag = memalloc_nofs_save(); diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 87a77a684339..3bc94bcc7177 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -151,7 +151,7 @@ extern int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool); extern int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, struct cifsFileInfo **ret_file); -extern unsigned int smbCalcSize(void *buf, struct TCP_Server_Info *server); +extern unsigned int smbCalcSize(void *buf); extern int decode_negTokenInit(unsigned char *security_blob, int length, struct TCP_Server_Info *server); extern int cifs_convert_address(struct sockaddr *dst, const char *src, int len); diff --git a/fs/cifs/cifsroot.c b/fs/cifs/cifsroot.c index 9e91a5a40aae..56ec1b233f52 100644 --- a/fs/cifs/cifsroot.c +++ b/fs/cifs/cifsroot.c @@ -59,7 +59,7 @@ static int __init cifs_root_setup(char *line) pr_err("Root-CIFS: UNC path too long\n"); return 1; } - strlcpy(root_dev, line, len); + strscpy(root_dev, line, len); srvaddr = parse_srvaddr(&line[2], s); if (*s) { int n = snprintf(root_opts, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9111c025bcb8..7ae6f2c08153 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -702,9 +702,6 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg) int length = 0; int total_read; - smb_msg->msg_control = NULL; - smb_msg->msg_controllen = 0; - for (total_read = 0; msg_data_left(smb_msg); total_read += length) { try_to_freeze(); @@ -760,7 +757,7 @@ int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, unsigned int to_read) { - struct msghdr smb_msg; + struct msghdr smb_msg = {}; struct kvec iov = {.iov_base = buf, .iov_len = to_read}; iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read); @@ -770,15 +767,13 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, ssize_t cifs_discard_from_socket(struct TCP_Server_Info *server, size_t to_read) { - struct msghdr smb_msg; + struct msghdr smb_msg = {}; /* * iov_iter_discard already sets smb_msg.type and count and iov_offset * and cifs_readv_from_socket sets msg_control and msg_controllen * so little to initialize in struct msghdr */ - smb_msg.msg_name = NULL; - smb_msg.msg_namelen = 0; iov_iter_discard(&smb_msg.msg_iter, READ, to_read); return cifs_readv_from_socket(server, &smb_msg); @@ -788,7 +783,7 @@ int cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page, unsigned int page_offset, unsigned int to_read) { - struct msghdr smb_msg; + struct msghdr smb_msg = {}; struct bio_vec bv = { .bv_page = page, .bv_len = to_read, .bv_offset = page_offset}; iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read); @@ -871,7 +866,7 @@ smb2_get_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) /* * SMB1 does not use credits. */ - if (server->vals->header_preamble_size) + if (is_smb1(server)) return 0; return le16_to_cpu(shdr->CreditRequest); @@ -1050,7 +1045,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) /* make sure this will fit in a large buffer */ if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server) - - server->vals->header_preamble_size) { + HEADER_PREAMBLE_SIZE(server)) { cifs_server_dbg(VFS, "SMB response too long (%u bytes)\n", pdu_length); cifs_reconnect(server, true); return -ECONNABORTED; @@ -1065,8 +1060,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) /* now read the rest */ length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1, - pdu_length - HEADER_SIZE(server) + 1 - + server->vals->header_preamble_size); + pdu_length - MID_HEADER_SIZE(server)); if (length < 0) return length; @@ -1122,7 +1116,7 @@ smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) /* * SMB1 does not use credits. */ - if (server->vals->header_preamble_size) + if (is_smb1(server)) return; if (shdr->CreditRequest) { @@ -1180,10 +1174,10 @@ cifs_demultiplex_thread(void *p) if (length < 0) continue; - if (server->vals->header_preamble_size == 0) - server->total_read = 0; - else + if (is_smb1(server)) server->total_read = length; + else + server->total_read = 0; /* * The right amount was read from socket - 4 bytes, @@ -1198,8 +1192,7 @@ next_pdu: server->pdu_size = pdu_length; /* make sure we have enough to get to the MID */ - if (server->pdu_size < HEADER_SIZE(server) - 1 - - server->vals->header_preamble_size) { + if (server->pdu_size < MID_HEADER_SIZE(server)) { cifs_server_dbg(VFS, "SMB response too short (%u bytes)\n", server->pdu_size); cifs_reconnect(server, true); @@ -1208,9 +1201,8 @@ next_pdu: /* read down to the MID */ length = cifs_read_from_socket(server, - buf + server->vals->header_preamble_size, - HEADER_SIZE(server) - 1 - - server->vals->header_preamble_size); + buf + HEADER_PREAMBLE_SIZE(server), + MID_HEADER_SIZE(server)); if (length < 0) continue; server->total_read += length; @@ -2353,7 +2345,9 @@ cifs_put_tcon(struct cifs_tcon *tcon) ses = tcon->ses; cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count); spin_lock(&cifs_tcp_ses_lock); + spin_lock(&tcon->tc_lock); if (--tcon->tc_count > 0) { + spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); return; } @@ -2362,6 +2356,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) WARN_ON(tcon->tc_count < 0); list_del_init(&tcon->tcon_list); + spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); /* cancel polling of interfaces */ @@ -3994,7 +3989,7 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, } bcc_ptr += length + 1; bytes_left -= (length + 1); - strlcpy(tcon->treeName, tree, sizeof(tcon->treeName)); + strscpy(tcon->treeName, tree, sizeof(tcon->treeName)); /* mostly informational -- no need to fail on error here */ kfree(tcon->nativeFileSystem); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fa738adc031f..6f38b134a346 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3575,6 +3575,9 @@ static ssize_t __cifs_writev( ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from) { + struct file *file = iocb->ki_filp; + + cifs_revalidate_mapping(file->f_inode); return __cifs_writev(iocb, from, true); } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 34d990f06fd6..87f60f736731 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -354,7 +354,7 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server) /* otherwise, there is enough to get to the BCC */ if (check_smb_hdr(smb)) return -EIO; - clc_len = smbCalcSize(smb, server); + clc_len = smbCalcSize(smb); if (4 + rfclen != total_read) { cifs_dbg(VFS, "Length read does not match RFC1001 length %d\n", @@ -737,6 +737,8 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) list_for_each_entry(cfile, &cifs_inode->openFileList, flist) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + cifs_del_deferred_close(cfile); + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) break; @@ -766,6 +768,8 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) list_for_each_entry(cfile, &tcon->openFileList, tlist) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + cifs_del_deferred_close(cfile); + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) break; @@ -799,6 +803,8 @@ cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) if (strstr(full_path, path)) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + cifs_del_deferred_close(cfile); + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) break; diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 28caae7aed1b..1b52e6ac431c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -909,7 +909,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr) * portion, the number of word parameters and the data portion of the message */ unsigned int -smbCalcSize(void *buf, struct TCP_Server_Info *server) +smbCalcSize(void *buf) { struct smb_hdr *ptr = buf; return (sizeof(struct smb_hdr) + (2 * ptr->WordCount) + diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 2eece8a07c11..8e060c00c969 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -806,8 +806,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, end_of_smb = cfile->srch_inf.ntwrk_buf_start + server->ops->calc_smb_size( - cfile->srch_inf.ntwrk_buf_start, - server); + cfile->srch_inf.ntwrk_buf_start); cur_ent = cfile->srch_inf.srch_entries_start; first_entry_in_buffer = cfile->srch_inf.index_of_last_entry @@ -1161,8 +1160,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) cifs_dbg(FYI, "loop through %d times filling dir for net buf %p\n", num_to_fill, cifsFile->srch_inf.ntwrk_buf_start); max_len = tcon->ses->server->ops->calc_smb_size( - cifsFile->srch_inf.ntwrk_buf_start, - tcon->ses->server); + cifsFile->srch_inf.ntwrk_buf_start); end_of_smb = cifsFile->srch_inf.ntwrk_buf_start + max_len; tmp_buf = kmalloc(UNICODE_NAME_MAX, GFP_KERNEL); diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index f5dcc4940b6d..9dfd2dd612c2 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -61,7 +61,6 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, nr_ioctl_req.Reserved = 0; rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, - true /* is_fsctl */, (char *)&nr_ioctl_req, sizeof(nr_ioctl_req), CIFSMaxBufSize, NULL, NULL /* no return info */); if (rc == -EOPNOTSUPP) { diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 6a6ec6efb45a..d73e5672aac4 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -222,7 +222,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) } } - calc_len = smb2_calc_size(buf, server); + calc_len = smb2_calc_size(buf); /* For SMB2_IOCTL, OutputOffset and OutputLength are optional, so might * be 0, and not a real miscalculation */ @@ -410,7 +410,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) * portion, the number of word parameters and the data portion of the message. */ unsigned int -smb2_calc_size(void *buf, struct TCP_Server_Info *srvr) +smb2_calc_size(void *buf) { struct smb2_pdu *pdu = buf; struct smb2_hdr *shdr = &pdu->hdr; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index f406af596887..421be43af425 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -387,7 +387,7 @@ smb2_dump_detail(void *buf, struct TCP_Server_Info *server) shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId, shdr->Id.SyncId.ProcessId); cifs_server_dbg(VFS, "smb buf %p len %u\n", buf, - server->ops->calc_smb_size(buf, server)); + server->ops->calc_smb_size(buf)); #endif } @@ -681,7 +681,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) struct cifs_ses *ses = tcon->ses; rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, - FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */, + FSCTL_QUERY_NETWORK_INTERFACE_INFO, NULL /* no data input */, 0 /* no data input */, CIFSMaxBufSize, (char **)&out_buf, &ret_data_len); if (rc == -EOPNOTSUPP) { @@ -1323,9 +1323,8 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon, struct resume_key_req *res_key; rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, - FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */, - NULL, 0 /* no input */, CIFSMaxBufSize, - (char **)&res_key, &ret_data_len); + FSCTL_SRV_REQUEST_RESUME_KEY, NULL, 0 /* no input */, + CIFSMaxBufSize, (char **)&res_key, &ret_data_len); if (rc == -EOPNOTSUPP) { pr_warn_once("Server share %s does not support copy range\n", tcon->treeName); @@ -1467,7 +1466,7 @@ smb2_ioctl_query_info(const unsigned int xid, rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE; rc = SMB2_ioctl_init(tcon, server, &rqst[1], COMPOUND_FID, COMPOUND_FID, - qi.info_type, true, buffer, qi.output_buffer_length, + qi.info_type, buffer, qi.output_buffer_length, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); free_req1_func = SMB2_ioctl_free; @@ -1601,17 +1600,8 @@ smb2_copychunk_range(const unsigned int xid, int chunks_copied = 0; bool chunk_sizes_updated = false; ssize_t bytes_written, total_bytes_written = 0; - struct inode *inode; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); - - /* - * We need to flush all unwritten data before we can send the - * copychunk ioctl to the server. - */ - inode = d_inode(trgtfile->dentry); - filemap_write_and_wait(inode->i_mapping); - if (pcchunk == NULL) return -ENOMEM; @@ -1643,9 +1633,8 @@ smb2_copychunk_range(const unsigned int xid, retbuf = NULL; rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, - true /* is_fsctl */, (char *)pcchunk, - sizeof(struct copychunk_ioctl), CIFSMaxBufSize, - (char **)&retbuf, &ret_data_len); + (char *)pcchunk, sizeof(struct copychunk_ioctl), + CIFSMaxBufSize, (char **)&retbuf, &ret_data_len); if (rc == 0) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) { @@ -1805,7 +1794,6 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_SPARSE, - true /* is_fctl */, &setsparse, 1, CIFSMaxBufSize, NULL, NULL); if (rc) { tcon->broken_sparse_sup = true; @@ -1888,7 +1876,6 @@ smb2_duplicate_extents(const unsigned int xid, rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_DUPLICATE_EXTENTS_TO_FILE, - true /* is_fsctl */, (char *)&dup_ext_buf, sizeof(struct duplicate_extents_to_file), CIFSMaxBufSize, NULL, @@ -1923,7 +1910,6 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_INTEGRITY_INFORMATION, - true /* is_fsctl */, (char *)&integr_info, sizeof(struct fsctl_set_integrity_information_req), CIFSMaxBufSize, NULL, @@ -1976,7 +1962,6 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SRV_ENUMERATE_SNAPSHOTS, - true /* is_fsctl */, NULL, 0 /* no input data */, max_response_size, (char **)&retbuf, &ret_data_len); @@ -2699,7 +2684,6 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, do { rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_DFS_GET_REFERRALS, - true /* is_fsctl */, (char *)dfs_req, dfs_req_size, CIFSMaxBufSize, (char **)&dfs_rsp, &dfs_rsp_size); if (!is_retryable_error(rc)) @@ -2906,8 +2890,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl_init(tcon, server, &rqst[1], fid.persistent_fid, - fid.volatile_fid, FSCTL_GET_REPARSE_POINT, - true /* is_fctl */, NULL, 0, + fid.volatile_fid, FSCTL_GET_REPARSE_POINT, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); @@ -3087,8 +3070,7 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl_init(tcon, server, &rqst[1], COMPOUND_FID, - COMPOUND_FID, FSCTL_GET_REPARSE_POINT, - true /* is_fctl */, NULL, 0, + COMPOUND_FID, FSCTL_GET_REPARSE_POINT, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); @@ -3316,26 +3298,43 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb, return pntsd; } +static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon, + loff_t offset, loff_t len, unsigned int xid) +{ + struct cifsFileInfo *cfile = file->private_data; + struct file_zero_data_information fsctl_buf; + + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); + + fsctl_buf.FileOffset = cpu_to_le64(offset); + fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); + + return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, + (char *)&fsctl_buf, + sizeof(struct file_zero_data_information), + 0, NULL, NULL); +} + static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len, bool keep_size) { struct cifs_ses *ses = tcon->ses; - struct inode *inode; - struct cifsInodeInfo *cifsi; + struct inode *inode = file_inode(file); + struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; - struct file_zero_data_information fsctl_buf; long rc; unsigned int xid; __le64 eof; xid = get_xid(); - inode = d_inode(cfile->dentry); - cifsi = CIFS_I(inode); - trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); + inode_lock(inode); + filemap_invalidate_lock(inode->i_mapping); + /* * We zero the range through ioctl, so we need remove the page caches * first, otherwise the data may be inconsistent with the server. @@ -3343,26 +3342,12 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, truncate_pagecache_range(inode, offset, offset + len - 1); /* if file not oplocked can't be sure whether asking to extend size */ - if (!CIFS_CACHE_READ(cifsi)) - if (keep_size == false) { - rc = -EOPNOTSUPP; - trace_smb3_zero_err(xid, cfile->fid.persistent_fid, - tcon->tid, ses->Suid, offset, len, rc); - free_xid(xid); - return rc; - } - - cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); - - fsctl_buf.FileOffset = cpu_to_le64(offset); - fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); + rc = -EOPNOTSUPP; + if (keep_size == false && !CIFS_CACHE_READ(cifsi)) + goto zero_range_exit; - rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, - cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true, - (char *)&fsctl_buf, - sizeof(struct file_zero_data_information), - 0, NULL, NULL); - if (rc) + rc = smb3_zero_data(file, tcon, offset, len, xid); + if (rc < 0) goto zero_range_exit; /* @@ -3375,6 +3360,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, } zero_range_exit: + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3388,7 +3375,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len) { - struct inode *inode; + struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; struct file_zero_data_information fsctl_buf; long rc; @@ -3397,14 +3384,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode = d_inode(cfile->dentry); - + inode_lock(inode); /* Need to make file sparse, if not already, before freeing range. */ /* Consider adding equivalent for compressed since it could also work */ if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) { rc = -EOPNOTSUPP; - free_xid(xid); - return rc; + goto out; } filemap_invalidate_lock(inode->i_mapping); @@ -3421,11 +3406,13 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, - true /* is_fctl */, (char *)&fsctl_buf, + (char *)&fsctl_buf, sizeof(struct file_zero_data_information), CIFSMaxBufSize, NULL, NULL); - free_xid(xid); filemap_invalidate_unlock(inode->i_mapping); +out: + inode_unlock(inode); + free_xid(xid); return rc; } @@ -3481,7 +3468,7 @@ static int smb3_simple_fallocate_range(unsigned int xid, in_data.length = cpu_to_le64(len); rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), 1024 * sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); @@ -3682,39 +3669,50 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, { int rc; unsigned int xid; - struct inode *inode; + struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; - struct cifsInodeInfo *cifsi; + struct cifsInodeInfo *cifsi = CIFS_I(inode); __le64 eof; + loff_t old_eof; xid = get_xid(); - inode = d_inode(cfile->dentry); - cifsi = CIFS_I(inode); + inode_lock(inode); - if (off >= i_size_read(inode) || - off + len >= i_size_read(inode)) { + old_eof = i_size_read(inode); + if ((off >= old_eof) || + off + len >= old_eof) { rc = -EINVAL; goto out; } + filemap_invalidate_lock(inode->i_mapping); + rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1); + if (rc < 0) + goto out_2; + + truncate_pagecache_range(inode, off, old_eof); + rc = smb2_copychunk_range(xid, cfile, cfile, off + len, - i_size_read(inode) - off - len, off); + old_eof - off - len, off); if (rc < 0) - goto out; + goto out_2; - eof = cpu_to_le64(i_size_read(inode) - len); + eof = cpu_to_le64(old_eof - len); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, &eof); if (rc < 0) - goto out; + goto out_2; rc = 0; cifsi->server_eof = i_size_read(inode) - len; truncate_setsize(inode, cifsi->server_eof); fscache_resize_cookie(cifs_inode_cookie(inode), cifsi->server_eof); +out_2: + filemap_invalidate_unlock(inode->i_mapping); out: + inode_unlock(inode); free_xid(xid); return rc; } @@ -3725,34 +3723,47 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, int rc; unsigned int xid; struct cifsFileInfo *cfile = file->private_data; + struct inode *inode = file_inode(file); __le64 eof; - __u64 count; + __u64 count, old_eof; xid = get_xid(); - if (off >= i_size_read(file->f_inode)) { + inode_lock(inode); + + old_eof = i_size_read(inode); + if (off >= old_eof) { rc = -EINVAL; goto out; } - count = i_size_read(file->f_inode) - off; - eof = cpu_to_le64(i_size_read(file->f_inode) + len); + count = old_eof - off; + eof = cpu_to_le64(old_eof + len); + + filemap_invalidate_lock(inode->i_mapping); + rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof + len - 1); + if (rc < 0) + goto out_2; + truncate_pagecache_range(inode, off, old_eof); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, &eof); if (rc < 0) - goto out; + goto out_2; rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); if (rc < 0) - goto out; + goto out_2; - rc = smb3_zero_range(file, tcon, off, len, 1); + rc = smb3_zero_data(file, tcon, off, len, xid); if (rc < 0) - goto out; + goto out_2; rc = 0; +out_2: + filemap_invalidate_unlock(inode->i_mapping); out: + inode_unlock(inode); free_xid(xid); return rc; } @@ -3802,7 +3813,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); @@ -3862,7 +3873,7 @@ static int smb3_fiemap(struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), 1024 * sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 9b31ea946d45..6352ab32c7e7 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -965,16 +965,17 @@ SMB2_negotiate(const unsigned int xid, } else if (rc != 0) goto neg_exit; + rc = -EIO; if (strcmp(server->vals->version_string, SMB3ANY_VERSION_STRING) == 0) { if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) { cifs_server_dbg(VFS, "SMB2 dialect returned but not requested\n"); - return -EIO; + goto neg_exit; } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { cifs_server_dbg(VFS, "SMB2.1 dialect returned but not requested\n"); - return -EIO; + goto neg_exit; } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) { /* ops set to 3.0 by default for default so update */ server->ops = &smb311_operations; @@ -985,7 +986,7 @@ SMB2_negotiate(const unsigned int xid, if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) { cifs_server_dbg(VFS, "SMB2 dialect returned but not requested\n"); - return -EIO; + goto neg_exit; } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { /* ops set to 3.0 by default for default so update */ server->ops = &smb21_operations; @@ -999,7 +1000,7 @@ SMB2_negotiate(const unsigned int xid, /* if requested single dialect ensure returned dialect matched */ cifs_server_dbg(VFS, "Invalid 0x%x dialect returned: not requested\n", le16_to_cpu(rsp->DialectRevision)); - return -EIO; + goto neg_exit; } cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode); @@ -1017,9 +1018,10 @@ SMB2_negotiate(const unsigned int xid, else { cifs_server_dbg(VFS, "Invalid dialect returned by server 0x%x\n", le16_to_cpu(rsp->DialectRevision)); - rc = -EIO; goto neg_exit; } + + rc = 0; server->dialect = le16_to_cpu(rsp->DialectRevision); /* @@ -1173,7 +1175,7 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) } rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, - FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, + FSCTL_VALIDATE_NEGOTIATE_INFO, (char *)pneg_inbuf, inbuflen, CIFSMaxBufSize, (char **)&pneg_rsp, &rsplen); if (rc == -EOPNOTSUPP) { @@ -1928,7 +1930,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, tcon->capabilities = rsp->Capabilities; /* we keep caps little endian */ tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess); tcon->tid = le32_to_cpu(rsp->hdr.Id.SyncId.TreeId); - strlcpy(tcon->treeName, tree, sizeof(tcon->treeName)); + strscpy(tcon->treeName, tree, sizeof(tcon->treeName)); if ((rsp->Capabilities & SMB2_SHARE_CAP_DFS) && ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0)) @@ -2572,19 +2574,15 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len, path_len = UniStrnlen((wchar_t *)path, PATH_MAX); - /* - * make room for one path separator between the treename and - * path - */ - *out_len = treename_len + 1 + path_len; + /* make room for one path separator only if @path isn't empty */ + *out_len = treename_len + (path[0] ? 1 : 0) + path_len; /* - * final path needs to be null-terminated UTF16 with a - * size aligned to 8 + * final path needs to be 8-byte aligned as specified in + * MS-SMB2 2.2.13 SMB2 CREATE Request. */ - - *out_size = roundup((*out_len+1)*2, 8); - *out_path = kzalloc(*out_size, GFP_KERNEL); + *out_size = roundup(*out_len * sizeof(__le16), 8); + *out_path = kzalloc(*out_size + sizeof(__le16) /* null */, GFP_KERNEL); if (!*out_path) return -ENOMEM; @@ -3056,7 +3054,7 @@ int SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + char *in_data, u32 indatalen, __u32 max_response_size) { struct smb2_ioctl_req *req; @@ -3131,10 +3129,8 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(max(indatalen, max_response_size), SMB2_MAX_BUFFER_SIZE)); - if (is_fsctl) - req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); - else - req->Flags = 0; + /* always an FSCTL (for now) */ + req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); /* validate negotiate request must be signed - see MS-SMB2 3.2.5.5 */ if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) @@ -3161,9 +3157,9 @@ SMB2_ioctl_free(struct smb_rqst *rqst) */ int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, - u64 volatile_fid, u32 opcode, bool is_fsctl, - char *in_data, u32 indatalen, u32 max_out_data_len, - char **out_data, u32 *plen /* returned data len */) + u64 volatile_fid, u32 opcode, char *in_data, u32 indatalen, + u32 max_out_data_len, char **out_data, + u32 *plen /* returned data len */) { struct smb_rqst rqst; struct smb2_ioctl_rsp *rsp = NULL; @@ -3205,7 +3201,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rc = SMB2_ioctl_init(tcon, server, &rqst, persistent_fid, volatile_fid, opcode, - is_fsctl, in_data, indatalen, max_out_data_len); + in_data, indatalen, max_out_data_len); if (rc) goto ioctl_exit; @@ -3297,7 +3293,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, cpu_to_le16(COMPRESSION_FORMAT_DEFAULT); rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, - FSCTL_SET_COMPRESSION, true /* is_fsctl */, + FSCTL_SET_COMPRESSION, (char *)&fsctl_input /* data input */, 2 /* in data len */, CIFSMaxBufSize /* max out data */, &ret_data /* out data */, NULL); diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 51c5bf4a338a..3f740f24b96a 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -23,7 +23,7 @@ struct smb_rqst; extern int map_smb2_to_linux_error(char *buf, bool log_err); extern int smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *server); -extern unsigned int smb2_calc_size(void *buf, struct TCP_Server_Info *server); +extern unsigned int smb2_calc_size(void *buf); extern char *smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr); extern __le16 *cifs_convert_path_to_utf16(const char *from, @@ -137,13 +137,13 @@ extern int SMB2_open_init(struct cifs_tcon *tcon, extern void SMB2_open_free(struct smb_rqst *rqst); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen, + char *in_data, u32 indatalen, u32 maxoutlen, char **out_data, u32 *plen /* returned data len */); extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + char *in_data, u32 indatalen, __u32 max_response_size); extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index de7aeced7e16..9a2753e21170 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -194,10 +194,6 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, *sent = 0; - smb_msg->msg_name = (struct sockaddr *) &server->dstaddr; - smb_msg->msg_namelen = sizeof(struct sockaddr); - smb_msg->msg_control = NULL; - smb_msg->msg_controllen = 0; if (server->noblocksnd) smb_msg->msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; else @@ -261,8 +257,8 @@ smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst) int nvec; unsigned long buflen = 0; - if (server->vals->header_preamble_size == 0 && - rqst->rq_nvec >= 2 && rqst->rq_iov[0].iov_len == 4) { + if (!is_smb1(server) && rqst->rq_nvec >= 2 && + rqst->rq_iov[0].iov_len == 4) { iov = &rqst->rq_iov[1]; nvec = rqst->rq_nvec - 1; } else { @@ -309,7 +305,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, sigset_t mask, oldmask; size_t total_len = 0, sent, size; struct socket *ssocket = server->ssocket; - struct msghdr smb_msg; + struct msghdr smb_msg = {}; __be32 rfc1002_marker; if (cifs_rdma_enabled(server)) { @@ -346,7 +342,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, sigprocmask(SIG_BLOCK, &mask, &oldmask); /* Generate a rfc1002 marker for SMB2+ */ - if (server->vals->header_preamble_size == 0) { + if (!is_smb1(server)) { struct kvec hiov = { .iov_base = &rfc1002_marker, .iov_len = 4 @@ -1238,7 +1234,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, buf = (char *)midQ[i]->resp_buf; resp_iov[i].iov_base = buf; resp_iov[i].iov_len = midQ[i]->resp_buf_size + - server->vals->header_preamble_size; + HEADER_PREAMBLE_SIZE(server); if (midQ[i]->large_buf) resp_buf_type[i] = CIFS_LARGE_BUFFER; @@ -1643,7 +1639,7 @@ int cifs_discard_remaining_data(struct TCP_Server_Info *server) { unsigned int rfclen = server->pdu_size; - int remaining = rfclen + server->vals->header_preamble_size - + int remaining = rfclen + HEADER_PREAMBLE_SIZE(server) - server->total_read; while (remaining > 0) { @@ -1689,8 +1685,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) unsigned int data_offset, data_len; struct cifs_readdata *rdata = mid->callback_data; char *buf = server->smallbuf; - unsigned int buflen = server->pdu_size + - server->vals->header_preamble_size; + unsigned int buflen = server->pdu_size + HEADER_PREAMBLE_SIZE(server); bool use_rdma_mr = false; cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%u\n", @@ -1724,10 +1719,10 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) /* set up first two iov for signature check and to get credits */ rdata->iov[0].iov_base = buf; - rdata->iov[0].iov_len = server->vals->header_preamble_size; - rdata->iov[1].iov_base = buf + server->vals->header_preamble_size; + rdata->iov[0].iov_len = HEADER_PREAMBLE_SIZE(server); + rdata->iov[1].iov_base = buf + HEADER_PREAMBLE_SIZE(server); rdata->iov[1].iov_len = - server->total_read - server->vals->header_preamble_size; + server->total_read - HEADER_PREAMBLE_SIZE(server); cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n", rdata->iov[0].iov_base, rdata->iov[0].iov_len); cifs_dbg(FYI, "1: iov_base=%p iov_len=%zu\n", @@ -1752,7 +1747,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) } data_offset = server->ops->read_data_offset(buf) + - server->vals->header_preamble_size; + HEADER_PREAMBLE_SIZE(server); if (data_offset < server->total_read) { /* * win2k8 sometimes sends an offset of 0 when the read diff --git a/fs/coredump.c b/fs/coredump.c index 9f4aae202109..1ab4f5b76a1e 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -832,6 +832,38 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr) } } +static int dump_emit_page(struct coredump_params *cprm, struct page *page) +{ + struct bio_vec bvec = { + .bv_page = page, + .bv_offset = 0, + .bv_len = PAGE_SIZE, + }; + struct iov_iter iter; + struct file *file = cprm->file; + loff_t pos = file->f_pos; + ssize_t n; + + if (cprm->to_skip) { + if (!__dump_skip(cprm, cprm->to_skip)) + return 0; + cprm->to_skip = 0; + } + if (cprm->written + PAGE_SIZE > cprm->limit) + return 0; + if (dump_interrupted()) + return 0; + iov_iter_bvec(&iter, WRITE, &bvec, 1, PAGE_SIZE); + n = __kernel_write_iter(cprm->file, &iter, &pos); + if (n != PAGE_SIZE) + return 0; + file->f_pos = pos; + cprm->written += PAGE_SIZE; + cprm->pos += PAGE_SIZE; + + return 1; +} + int dump_emit(struct coredump_params *cprm, const void *addr, int nr) { if (cprm->to_skip) { @@ -863,7 +895,6 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start, for (addr = start; addr < start + len; addr += PAGE_SIZE) { struct page *page; - int stop; /* * To avoid having to allocate page tables for virtual address @@ -874,10 +905,7 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start, */ page = get_dump_page(addr); if (page) { - void *kaddr = kmap_local_page(page); - - stop = !dump_emit(cprm, kaddr, PAGE_SIZE); - kunmap_local(kaddr); + int stop = !dump_emit_page(cprm, page); put_page(page); if (stop) return 0; @@ -1445,6 +1445,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t done = 0; int ret; + if (!iomi.len) + return 0; + if (iov_iter_rw(iter) == WRITE) { lockdep_assert_held_write(&iomi.inode->i_rwsem); iomi.flags |= IOMAP_WRITE; diff --git a/fs/dcache.c b/fs/dcache.c index c5dc32a59c76..bb0c4d0038db 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2270,6 +2270,48 @@ bool d_same_name(const struct dentry *dentry, const struct dentry *parent, } EXPORT_SYMBOL_GPL(d_same_name); +/* + * This is __d_lookup_rcu() when the parent dentry has + * DCACHE_OP_COMPARE, which makes things much nastier. + */ +static noinline struct dentry *__d_lookup_rcu_op_compare( + const struct dentry *parent, + const struct qstr *name, + unsigned *seqp) +{ + u64 hashlen = name->hash_len; + struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); + struct hlist_bl_node *node; + struct dentry *dentry; + + hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { + int tlen; + const char *tname; + unsigned seq; + +seqretry: + seq = raw_seqcount_begin(&dentry->d_seq); + if (dentry->d_parent != parent) + continue; + if (d_unhashed(dentry)) + continue; + if (dentry->d_name.hash != hashlen_hash(hashlen)) + continue; + tlen = dentry->d_name.len; + tname = dentry->d_name.name; + /* we want a consistent (name,len) pair */ + if (read_seqcount_retry(&dentry->d_seq, seq)) { + cpu_relax(); + goto seqretry; + } + if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) + continue; + *seqp = seq; + return dentry; + } + return NULL; +} + /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry @@ -2316,6 +2358,9 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent, * Keep the two functions in sync. */ + if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) + return __d_lookup_rcu_op_compare(parent, name, seqp); + /* * The hash list is protected using RCU. * @@ -2332,7 +2377,6 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent, hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; -seqretry: /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. @@ -2355,28 +2399,10 @@ seqretry: continue; if (d_unhashed(dentry)) continue; - - if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { - int tlen; - const char *tname; - if (dentry->d_name.hash != hashlen_hash(hashlen)) - continue; - tlen = dentry->d_name.len; - tname = dentry->d_name.name; - /* we want a consistent (name,len) pair */ - if (read_seqcount_retry(&dentry->d_seq, seq)) { - cpu_relax(); - goto seqretry; - } - if (parent->d_op->d_compare(dentry, - tlen, tname, name) != 0) - continue; - } else { - if (dentry->d_name.hash_len != hashlen) - continue; - if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) - continue; - } + if (dentry->d_name.hash_len != hashlen) + continue; + if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) + continue; *seqp = seq; return dentry; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 3dcf0b8b4e93..232cfdf095ae 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -745,6 +745,28 @@ void debugfs_remove(struct dentry *dentry) EXPORT_SYMBOL_GPL(debugfs_remove); /** + * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it + * @name: a pointer to a string containing the name of the item to look up. + * @parent: a pointer to the parent dentry of the item. + * + * This is the equlivant of doing something like + * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting + * handled for the directory being looked up. + */ +void debugfs_lookup_and_remove(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + + dentry = debugfs_lookup(name, parent); + if (!dentry) + return; + + debugfs_remove(dentry); + dput(dentry); +} +EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); + +/** * debugfs_rename - rename a file/directory in the debugfs filesystem * @old_dir: a pointer to the parent dentry for the renamed object. This * should be a directory dentry. diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 8e01d89c3319..b5fd9d71e67f 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -222,8 +222,10 @@ static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) rreq = erofs_fscache_alloc_request(folio_mapping(folio), folio_pos(folio), folio_size(folio)); - if (IS_ERR(rreq)) + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); goto out; + } return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, rreq, mdev.m_pa); @@ -301,8 +303,10 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio) rreq = erofs_fscache_alloc_request(folio_mapping(folio), folio_pos(folio), folio_size(folio)); - if (IS_ERR(rreq)) + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); goto out_unlock; + } pstart = mdev.m_pa + (pos - map.m_la); return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index cfee49d33b95..a01cc82795a2 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -195,7 +195,6 @@ struct erofs_workgroup { atomic_t refcount; }; -#if defined(CONFIG_SMP) static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, int val) { @@ -224,34 +223,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) return atomic_cond_read_relaxed(&grp->refcount, VAL != EROFS_LOCKED_MAGIC); } -#else -static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, - int val) -{ - preempt_disable(); - /* no need to spin on UP platforms, let's just disable preemption. */ - if (val != atomic_read(&grp->refcount)) { - preempt_enable(); - return false; - } - return true; -} - -static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp, - int orig_val) -{ - preempt_enable(); -} - -static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) -{ - int v = atomic_read(&grp->refcount); - - /* workgroup is never freezed on uniprocessor systems */ - DBG_BUGON(v == EROFS_LOCKED_MAGIC); - return v; -} -#endif /* !CONFIG_SMP */ #endif /* !CONFIG_EROFS_FS_ZIP */ /* we strictly follow PAGE_SIZE and no buffer head yet */ diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 572f0b8151ba..d58549ca1df9 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -141,7 +141,7 @@ struct z_erofs_maprecorder { u8 type, headtype; u16 clusterofs; u16 delta[2]; - erofs_blk_t pblk, compressedlcs; + erofs_blk_t pblk, compressedblks; erofs_off_t nextpackoff; }; @@ -192,7 +192,7 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, DBG_BUGON(1); return -EFSCORRUPTED; } - m->compressedlcs = m->delta[0] & + m->compressedblks = m->delta[0] & ~Z_EROFS_VLE_DI_D0_CBLKCNT; m->delta[0] = 1; } @@ -293,7 +293,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, DBG_BUGON(1); return -EFSCORRUPTED; } - m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; m->delta[0] = 1; return 0; } else if (i + 1 != (int)vcnt) { @@ -497,7 +497,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, return 0; } lcn = m->lcn + 1; - if (m->compressedlcs) + if (m->compressedblks) goto out; err = z_erofs_load_cluster_from_disk(m, lcn, false); @@ -506,7 +506,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, /* * If the 1st NONHEAD lcluster has already been handled initially w/o - * valid compressedlcs, which means at least it mustn't be CBLKCNT, or + * valid compressedblks, which means at least it mustn't be CBLKCNT, or * an internal implemenatation error is detected. * * The following code can also handle it properly anyway, but let's @@ -523,12 +523,12 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. */ - m->compressedlcs = 1; + m->compressedblks = 1 << (lclusterbits - LOG_BLOCK_SIZE); break; case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) goto err_bonus_cblkcnt; - if (m->compressedlcs) + if (m->compressedblks) break; fallthrough; default: @@ -539,7 +539,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, return -EFSCORRUPTED; } out: - map->m_plen = (u64)m->compressedlcs << lclusterbits; + map->m_plen = (u64)m->compressedblks << LOG_BLOCK_SIZE; return 0; err_bonus_cblkcnt: erofs_err(m->inode->i_sb, diff --git a/fs/exec.c b/fs/exec.c index f793221f4eb6..69a572fc57db 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -65,7 +65,6 @@ #include <linux/io_uring.h> #include <linux/syscall_user_dispatch.h> #include <linux/coredump.h> -#include <linux/time_namespace.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -584,11 +583,11 @@ static int copy_strings(int argc, struct user_arg_ptr argv, if (kmapped_page) { flush_dcache_page(kmapped_page); - kunmap(kmapped_page); + kunmap_local(kaddr); put_arg_page(kmapped_page); } kmapped_page = page; - kaddr = kmap(kmapped_page); + kaddr = kmap_local_page(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } @@ -602,7 +601,7 @@ static int copy_strings(int argc, struct user_arg_ptr argv, out: if (kmapped_page) { flush_dcache_page(kmapped_page); - kunmap(kmapped_page); + kunmap_local(kaddr); put_arg_page(kmapped_page); } return ret; @@ -880,11 +879,11 @@ int transfer_args_to_stack(struct linux_binprm *bprm, for (index = MAX_ARG_PAGES - 1; index >= stop; index--) { unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0; - char *src = kmap(bprm->page[index]) + offset; + char *src = kmap_local_page(bprm->page[index]) + offset; sp -= PAGE_SIZE - offset; if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0) ret = -EFAULT; - kunmap(bprm->page[index]); + kunmap_local(src); if (ret) goto out; } @@ -958,8 +957,7 @@ struct file *open_exec(const char *name) } EXPORT_SYMBOL(open_exec); -#if defined(CONFIG_HAVE_AOUT) || defined(CONFIG_BINFMT_FLAT) || \ - defined(CONFIG_BINFMT_ELF_FDPIC) +#if defined(CONFIG_BINFMT_FLAT) || defined(CONFIG_BINFMT_ELF_FDPIC) ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len) { ssize_t res = vfs_read(file, (void __user *)addr, len, &pos); @@ -979,12 +977,10 @@ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; - bool vfork; int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; - vfork = !!tsk->vfork_done; old_mm = current->mm; exec_mm_release(tsk, old_mm); if (old_mm) @@ -1029,10 +1025,6 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm->vmacache_seqnum = 0; vmacache_flush(tsk); task_unlock(tsk); - - if (vfork) - timens_on_fork(tsk->nsproxy, tsk); - if (old_mm) { mmap_read_unlock(old_mm); BUG_ON(active_mm != old_mm); @@ -1686,13 +1678,13 @@ int remove_arg_zero(struct linux_binprm *bprm) ret = -EFAULT; goto out; } - kaddr = kmap_atomic(page); + kaddr = kmap_local_page(page); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; - kunmap_atomic(kaddr); + kunmap_local(kaddr); put_arg_page(page); } while (offset == PAGE_SIZE); diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index ee0b7cf51157..41ae4cce1f42 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -270,8 +270,7 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu) struct super_block *sb = dir->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct buffer_head *bh; - sector_t blknr, last_blknr; - int i; + sector_t blknr, last_blknr, i; blknr = exfat_cluster_to_sector(sbi, clu); last_blknr = blknr + sbi->sect_per_clus; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9bca5565547b..3bf9a6926798 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -167,8 +167,6 @@ enum SHIFT_DIRECTION { #define EXT4_MB_CR0_OPTIMIZED 0x8000 /* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */ #define EXT4_MB_CR1_OPTIMIZED 0x00010000 -/* Perform linear traversal for one group */ -#define EXT4_MB_SEARCH_NEXT_LINEAR 0x00020000 struct ext4_allocation_request { /* target inode for block we're allocating */ struct inode *inode; @@ -1600,8 +1598,8 @@ struct ext4_sb_info { struct list_head s_discard_list; struct work_struct s_discard_work; atomic_t s_retry_alloc_pending; - struct rb_root s_mb_avg_fragment_size_root; - rwlock_t s_mb_rb_lock; + struct list_head *s_mb_avg_fragment_size; + rwlock_t *s_mb_avg_fragment_size_locks; struct list_head *s_mb_largest_free_orders; rwlock_t *s_mb_largest_free_orders_locks; @@ -3413,6 +3411,8 @@ struct ext4_group_info { ext4_grpblk_t bb_first_free; /* first free block */ ext4_grpblk_t bb_free; /* total free blocks */ ext4_grpblk_t bb_fragments; /* nr of freespace fragments */ + int bb_avg_fragment_size_order; /* order of average + fragment in BG */ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */ ext4_group_t bb_group; /* Group number */ struct list_head bb_prealloc_list; @@ -3420,7 +3420,7 @@ struct ext4_group_info { void *bb_bitmap; #endif struct rw_semaphore alloc_sem; - struct rb_node bb_avg_fragment_size_rb; + struct list_head bb_avg_fragment_size_node; struct list_head bb_largest_free_order_node; ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block * regions, index is order. diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c148bb97b527..5235974126bd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -460,6 +460,10 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid eh_entries"; goto corrupted; } + if (unlikely((eh->eh_entries == 0) && (depth > 0))) { + error_msg = "eh_entries is 0 but eh_depth is > 0"; + goto corrupted; + } if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f73e5eb43eae..208b87ce8858 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -510,7 +510,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, goto fallback; } - max_dirs = ndirs / ngroups + inodes_per_group / 16; + max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16; min_inodes = avefreei - inodes_per_group*flex_size / 4; if (min_inodes < 1) min_inodes = 1; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index bd8f8b5c3d30..9dad93059945 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -140,13 +140,15 @@ * number of buddy bitmap orders possible) number of lists. Group-infos are * placed in appropriate lists. * - * 2) Average fragment size rb tree (sbi->s_mb_avg_fragment_size_root) + * 2) Average fragment size lists (sbi->s_mb_avg_fragment_size) * - * Locking: sbi->s_mb_rb_lock (rwlock) + * Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks) * - * This is a red black tree consisting of group infos and the tree is sorted - * by average fragment sizes (which is calculated as ext4_group_info->bb_free - * / ext4_group_info->bb_fragments). + * This is an array of lists where in the i-th list there are groups with + * average fragment size >= 2^i and < 2^(i+1). The average fragment size + * is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments. + * Note that we don't bother with a special list for completely empty groups + * so we only have MB_NUM_ORDERS(sb) lists. * * When "mb_optimize_scan" mount option is set, mballoc consults the above data * structures to decide the order in which groups are to be traversed for @@ -160,7 +162,8 @@ * * At CR = 1, we only consider groups where average fragment size > request * size. So, we lookup a group which has average fragment size just above or - * equal to request size using our rb tree (data structure 2) in O(log N) time. + * equal to request size using our average fragment size group lists (data + * structure 2) in O(1) time. * * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in * linear order which requires O(N) search time for each CR 0 and CR 1 phase. @@ -802,65 +805,51 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, } } -static void ext4_mb_rb_insert(struct rb_root *root, struct rb_node *new, - int (*cmp)(struct rb_node *, struct rb_node *)) +static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) { - struct rb_node **iter = &root->rb_node, *parent = NULL; + int order; - while (*iter) { - parent = *iter; - if (cmp(new, *iter) > 0) - iter = &((*iter)->rb_left); - else - iter = &((*iter)->rb_right); - } - - rb_link_node(new, parent, iter); - rb_insert_color(new, root); -} - -static int -ext4_mb_avg_fragment_size_cmp(struct rb_node *rb1, struct rb_node *rb2) -{ - struct ext4_group_info *grp1 = rb_entry(rb1, - struct ext4_group_info, - bb_avg_fragment_size_rb); - struct ext4_group_info *grp2 = rb_entry(rb2, - struct ext4_group_info, - bb_avg_fragment_size_rb); - int num_frags_1, num_frags_2; - - num_frags_1 = grp1->bb_fragments ? - grp1->bb_free / grp1->bb_fragments : 0; - num_frags_2 = grp2->bb_fragments ? - grp2->bb_free / grp2->bb_fragments : 0; - - return (num_frags_2 - num_frags_1); + /* + * We don't bother with a special lists groups with only 1 block free + * extents and for completely empty groups. + */ + order = fls(len) - 2; + if (order < 0) + return 0; + if (order == MB_NUM_ORDERS(sb)) + order--; + return order; } -/* - * Reinsert grpinfo into the avg_fragment_size tree with new average - * fragment size. - */ +/* Move group to appropriate avg_fragment_size list */ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); + int new_order; if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) return; - write_lock(&sbi->s_mb_rb_lock); - if (!RB_EMPTY_NODE(&grp->bb_avg_fragment_size_rb)) { - rb_erase(&grp->bb_avg_fragment_size_rb, - &sbi->s_mb_avg_fragment_size_root); - RB_CLEAR_NODE(&grp->bb_avg_fragment_size_rb); - } + new_order = mb_avg_fragment_size_order(sb, + grp->bb_free / grp->bb_fragments); + if (new_order == grp->bb_avg_fragment_size_order) + return; - ext4_mb_rb_insert(&sbi->s_mb_avg_fragment_size_root, - &grp->bb_avg_fragment_size_rb, - ext4_mb_avg_fragment_size_cmp); - write_unlock(&sbi->s_mb_rb_lock); + if (grp->bb_avg_fragment_size_order != -1) { + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_del(&grp->bb_avg_fragment_size_node); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + } + grp->bb_avg_fragment_size_order = new_order; + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_add_tail(&grp->bb_avg_fragment_size_node, + &sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); } /* @@ -909,86 +898,55 @@ static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac, *new_cr = 1; } else { *group = grp->bb_group; - ac->ac_last_optimal_group = *group; ac->ac_flags |= EXT4_MB_CR0_OPTIMIZED; } } /* - * Choose next group by traversing average fragment size tree. Updates *new_cr - * if cr lvel needs an update. Sets EXT4_MB_SEARCH_NEXT_LINEAR to indicate that - * the linear search should continue for one iteration since there's lock - * contention on the rb tree lock. + * Choose next group by traversing average fragment size list of suitable + * order. Updates *new_cr if cr level needs an update. */ static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac, int *new_cr, ext4_group_t *group, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - int avg_fragment_size, best_so_far; - struct rb_node *node, *found; - struct ext4_group_info *grp; - - /* - * If there is contention on the lock, instead of waiting for the lock - * to become available, just continue searching lineraly. We'll resume - * our rb tree search later starting at ac->ac_last_optimal_group. - */ - if (!read_trylock(&sbi->s_mb_rb_lock)) { - ac->ac_flags |= EXT4_MB_SEARCH_NEXT_LINEAR; - return; - } + struct ext4_group_info *grp = NULL, *iter; + int i; if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) { if (sbi->s_mb_stats) atomic_inc(&sbi->s_bal_cr1_bad_suggestions); - /* We have found something at CR 1 in the past */ - grp = ext4_get_group_info(ac->ac_sb, ac->ac_last_optimal_group); - for (found = rb_next(&grp->bb_avg_fragment_size_rb); found != NULL; - found = rb_next(found)) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + } + + for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); + i < MB_NUM_ORDERS(ac->ac_sb); i++) { + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) + continue; + read_lock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) { + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + continue; + } + list_for_each_entry(iter, &sbi->s_mb_avg_fragment_size[i], + bb_avg_fragment_size_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[1]); - if (likely(ext4_mb_good_group(ac, grp->bb_group, 1))) + if (likely(ext4_mb_good_group(ac, iter->bb_group, 1))) { + grp = iter; break; - } - goto done; - } - - node = sbi->s_mb_avg_fragment_size_root.rb_node; - best_so_far = 0; - found = NULL; - - while (node) { - grp = rb_entry(node, struct ext4_group_info, - bb_avg_fragment_size_rb); - avg_fragment_size = 0; - if (ext4_mb_good_group(ac, grp->bb_group, 1)) { - avg_fragment_size = grp->bb_fragments ? - grp->bb_free / grp->bb_fragments : 0; - if (!best_so_far || avg_fragment_size < best_so_far) { - best_so_far = avg_fragment_size; - found = node; } } - if (avg_fragment_size > ac->ac_g_ex.fe_len) - node = node->rb_right; - else - node = node->rb_left; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (grp) + break; } -done: - if (found) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + if (grp) { *group = grp->bb_group; ac->ac_flags |= EXT4_MB_CR1_OPTIMIZED; } else { *new_cr = 2; } - - read_unlock(&sbi->s_mb_rb_lock); - ac->ac_last_optimal_group = *group; } static inline int should_optimize_scan(struct ext4_allocation_context *ac) @@ -1017,11 +975,6 @@ next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) goto inc_and_return; } - if (ac->ac_flags & EXT4_MB_SEARCH_NEXT_LINEAR) { - ac->ac_flags &= ~EXT4_MB_SEARCH_NEXT_LINEAR; - goto inc_and_return; - } - return group; inc_and_return: /* @@ -1049,8 +1002,10 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, { *new_cr = ac->ac_criteria; - if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) + if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) { + *group = next_linear_group(ac, *group, ngroups); return; + } if (*new_cr == 0) { ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups); @@ -1075,23 +1030,25 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int i; - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) { + for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) + if (grp->bb_counters[i] > 0) + break; + /* No need to move between order lists? */ + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || + i == grp->bb_largest_free_order) { + grp->bb_largest_free_order = i; + return; + } + + if (grp->bb_largest_free_order >= 0) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_del_init(&grp->bb_largest_free_order_node); write_unlock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); } - grp->bb_largest_free_order = -1; /* uninit */ - - for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) { - if (grp->bb_counters[i] > 0) { - grp->bb_largest_free_order = i; - break; - } - } - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && - grp->bb_largest_free_order >= 0 && grp->bb_free) { + grp->bb_largest_free_order = i; + if (grp->bb_largest_free_order >= 0 && grp->bb_free) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_add_tail(&grp->bb_largest_free_order_node, @@ -1148,13 +1105,13 @@ void ext4_mb_generate_buddy(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); + mb_update_avg_fragment_size(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; atomic_inc(&sbi->s_mb_buddies_generated); atomic64_add(period, &sbi->s_mb_generation_time); - mb_update_avg_fragment_size(sb, grp); } /* The buddy information is attached the buddy cache inode @@ -2636,7 +2593,7 @@ static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; - int cr = -1; + int cr = -1, new_cr; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; @@ -2707,17 +2664,14 @@ repeat: * from the goal value specified */ group = ac->ac_g_ex.fe_group; - ac->ac_last_optimal_group = group; ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups; prefetch_grp = group; - for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups), - i++) { - int ret = 0, new_cr; + for (i = 0, new_cr = cr; i < ngroups; i++, + ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) { + int ret = 0; cond_resched(); - - ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups); if (new_cr != cr) { cr = new_cr; goto repeat; @@ -2991,9 +2945,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock) struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; - read_lock(&EXT4_SB(sb)->s_mb_rb_lock); - - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -3005,7 +2957,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof unsigned long position; ++*pos; - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -3017,29 +2969,22 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; - struct rb_node *n; - unsigned int count, min, max; + unsigned int count; position--; if (position >= MB_NUM_ORDERS(sb)) { - seq_puts(seq, "fragment_size_tree:\n"); - n = rb_first(&sbi->s_mb_avg_fragment_size_root); - if (!n) { - seq_puts(seq, "\ttree_min: 0\n\ttree_max: 0\n\ttree_nodes: 0\n"); - return 0; - } - grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); - min = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; - count = 1; - while (rb_next(n)) { - count++; - n = rb_next(n); - } - grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); - max = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; + position -= MB_NUM_ORDERS(sb); + if (position == 0) + seq_puts(seq, "avg_fragment_size_lists:\n"); - seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n", - min, max, count); + count = 0; + read_lock(&sbi->s_mb_avg_fragment_size_locks[position]); + list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position], + bb_avg_fragment_size_node) + count++; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]); + seq_printf(seq, "\tlist_order_%u_groups: %u\n", + (unsigned int)position, count); return 0; } @@ -3049,9 +2994,11 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) seq_puts(seq, "max_free_order_lists:\n"); } count = 0; + read_lock(&sbi->s_mb_largest_free_orders_locks[position]); list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position], bb_largest_free_order_node) count++; + read_unlock(&sbi->s_mb_largest_free_orders_locks[position]); seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); @@ -3059,11 +3006,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) } static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) -__releases(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = pde_data(file_inode(seq->file)); - - read_unlock(&EXT4_SB(sb)->s_mb_rb_lock); } const struct seq_operations ext4_mb_seq_structs_summary_ops = { @@ -3176,8 +3119,9 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node); - RB_CLEAR_NODE(&meta_group_info[i]->bb_avg_fragment_size_rb); + INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node); meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ + meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); @@ -3426,7 +3370,24 @@ int ext4_mb_init(struct super_block *sb) i++; } while (i < MB_NUM_ORDERS(sb)); - sbi->s_mb_avg_fragment_size_root = RB_ROOT; + sbi->s_mb_avg_fragment_size = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size) { + ret = -ENOMEM; + goto out; + } + sbi->s_mb_avg_fragment_size_locks = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size_locks) { + ret = -ENOMEM; + goto out; + } + for (i = 0; i < MB_NUM_ORDERS(sb); i++) { + INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]); + rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]); + } sbi->s_mb_largest_free_orders = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), GFP_KERNEL); @@ -3445,7 +3406,6 @@ int ext4_mb_init(struct super_block *sb) INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]); rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]); } - rwlock_init(&sbi->s_mb_rb_lock); spin_lock_init(&sbi->s_md_lock); sbi->s_mb_free_pending = 0; @@ -3516,6 +3476,8 @@ out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -3582,6 +3544,8 @@ int ext4_mb_release(struct super_block *sb) kvfree(group_info); rcu_read_unlock(); } + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -5193,6 +5157,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; + bool inode_pa_eligible, group_pa_eligible; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; @@ -5200,25 +5165,27 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; + group_pa_eligible = sbi->s_mb_group_prealloc > 0; + inode_pa_eligible = true; size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; + /* No point in using inode preallocation for closed files */ if ((size == isize) && !ext4_fs_is_busy(sbi) && - !inode_is_open_for_write(ac->ac_inode)) { - ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; - return; - } + !inode_is_open_for_write(ac->ac_inode)) + inode_pa_eligible = false; - if (sbi->s_mb_group_prealloc <= 0) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; - return; - } - - /* don't use group allocation for large files */ size = max(size, isize); - if (size > sbi->s_mb_stream_request) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + /* Don't use group allocation for large files */ + if (size > sbi->s_mb_stream_request) + group_pa_eligible = false; + + if (!group_pa_eligible) { + if (inode_pa_eligible) + ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + else + ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } @@ -5565,6 +5532,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; + int retries = 0; u64 seq; might_sleep(); @@ -5667,7 +5635,8 @@ repeat: ar->len = ac->ac_b_ex.fe_len; } } else { - if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) + if (++retries < 3 && + ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 39da92ceabf8..dcda2a943cee 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -178,7 +178,6 @@ struct ext4_allocation_context { /* copy of the best found extent taken before preallocation efforts */ struct ext4_free_extent ac_f_ex; - ext4_group_t ac_last_optimal_group; __u32 ac_groups_considered; __u32 ac_flags; /* allocation hints */ __u16 ac_groups_scanned; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 05221366a16d..08a1993ab7fd 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -134,10 +134,10 @@ static bool inode_io_list_move_locked(struct inode *inode, static void wb_wakeup(struct bdi_writeback *wb) { - spin_lock_bh(&wb->work_lock); + spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); - spin_unlock_bh(&wb->work_lock); + spin_unlock_irq(&wb->work_lock); } static void finish_writeback_work(struct bdi_writeback *wb, @@ -164,7 +164,7 @@ static void wb_queue_work(struct bdi_writeback *wb, if (work->done) atomic_inc(&work->done->cnt); - spin_lock_bh(&wb->work_lock); + spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); @@ -172,7 +172,7 @@ static void wb_queue_work(struct bdi_writeback *wb, } else finish_writeback_work(wb, work); - spin_unlock_bh(&wb->work_lock); + spin_unlock_irq(&wb->work_lock); } /** @@ -2082,13 +2082,13 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; - spin_lock_bh(&wb->work_lock); + spin_lock_irq(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } - spin_unlock_bh(&wb->work_lock); + spin_unlock_irq(&wb->work_lock); return work; } diff --git a/fs/inode.c b/fs/inode.c index 6462276dfdf0..ba1de23c13c1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2018,23 +2018,25 @@ static int __file_remove_privs(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); - int error; + int error = 0; int kill; if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); - if (kill <= 0) + if (kill < 0) return kill; - if (flags & IOCB_NOWAIT) - return -EAGAIN; + if (kill) { + if (flags & IOCB_NOWAIT) + return -EAGAIN; + + error = __remove_privs(file_mnt_user_ns(file), dentry, kill); + } - error = __remove_privs(file_mnt_user_ns(file), dentry, kill); if (!error) inode_has_no_xattr(inode); - return error; } diff --git a/fs/internal.h b/fs/internal.h index 87e96b9024ce..3e206d3e317c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -16,6 +16,7 @@ struct shrink_control; struct fs_context; struct user_namespace; struct pipe_inode_info; +struct iov_iter; /* * block/bdev.c @@ -221,3 +222,5 @@ ssize_t do_getxattr(struct user_namespace *mnt_userns, int setxattr_copy(const char __user *name, struct xattr_ctx *ctx); int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct xattr_ctx *ctx); + +ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos); diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h index 52aa0adeb951..e0cbcfa98c7e 100644 --- a/fs/ksmbd/ksmbd_netlink.h +++ b/fs/ksmbd/ksmbd_netlink.h @@ -349,6 +349,7 @@ enum KSMBD_TREE_CONN_STATUS { #define KSMBD_SHARE_FLAG_STREAMS BIT(11) #define KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS BIT(12) #define KSMBD_SHARE_FLAG_ACL_XATTR BIT(13) +#define KSMBD_SHARE_FLAG_UPDATE BIT(14) /* * Tree connect request flags. @@ -364,6 +365,7 @@ enum KSMBD_TREE_CONN_STATUS { #define KSMBD_TREE_CONN_FLAG_READ_ONLY BIT(1) #define KSMBD_TREE_CONN_FLAG_WRITABLE BIT(2) #define KSMBD_TREE_CONN_FLAG_ADMIN_ACCOUNT BIT(3) +#define KSMBD_TREE_CONN_FLAG_UPDATE BIT(4) /* * RPC over IPC. diff --git a/fs/ksmbd/mgmt/share_config.c b/fs/ksmbd/mgmt/share_config.c index 70655af93b44..c9bca1c2c834 100644 --- a/fs/ksmbd/mgmt/share_config.c +++ b/fs/ksmbd/mgmt/share_config.c @@ -51,12 +51,16 @@ static void kill_share(struct ksmbd_share_config *share) kfree(share); } -void __ksmbd_share_config_put(struct ksmbd_share_config *share) +void ksmbd_share_config_del(struct ksmbd_share_config *share) { down_write(&shares_table_lock); hash_del(&share->hlist); up_write(&shares_table_lock); +} +void __ksmbd_share_config_put(struct ksmbd_share_config *share) +{ + ksmbd_share_config_del(share); kill_share(share); } diff --git a/fs/ksmbd/mgmt/share_config.h b/fs/ksmbd/mgmt/share_config.h index 28bf3511763f..902f2cb1963a 100644 --- a/fs/ksmbd/mgmt/share_config.h +++ b/fs/ksmbd/mgmt/share_config.h @@ -64,6 +64,7 @@ static inline int test_share_config_flag(struct ksmbd_share_config *share, return share->flags & flag; } +void ksmbd_share_config_del(struct ksmbd_share_config *share); void __ksmbd_share_config_put(struct ksmbd_share_config *share); static inline void ksmbd_share_config_put(struct ksmbd_share_config *share) diff --git a/fs/ksmbd/mgmt/tree_connect.c b/fs/ksmbd/mgmt/tree_connect.c index b35ea6a6abc5..97ab7987df6e 100644 --- a/fs/ksmbd/mgmt/tree_connect.c +++ b/fs/ksmbd/mgmt/tree_connect.c @@ -19,7 +19,7 @@ struct ksmbd_tree_conn_status ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, char *share_name) { - struct ksmbd_tree_conn_status status = {-EINVAL, NULL}; + struct ksmbd_tree_conn_status status = {-ENOENT, NULL}; struct ksmbd_tree_connect_response *resp = NULL; struct ksmbd_share_config *sc; struct ksmbd_tree_connect *tree_conn = NULL; @@ -57,6 +57,20 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, goto out_error; tree_conn->flags = resp->connection_flags; + if (test_tree_conn_flag(tree_conn, KSMBD_TREE_CONN_FLAG_UPDATE)) { + struct ksmbd_share_config *new_sc; + + ksmbd_share_config_del(sc); + new_sc = ksmbd_share_config_get(share_name); + if (!new_sc) { + pr_err("Failed to update stale share config\n"); + status.ret = -ESTALE; + goto out_error; + } + ksmbd_share_config_put(sc); + sc = new_sc; + } + tree_conn->user = sess->user; tree_conn->share_conf = sc; status.tree_conn = tree_conn; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 9751cc92c111..19412ac701a6 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1944,8 +1944,10 @@ out_err1: rsp->hdr.Status = STATUS_SUCCESS; rc = 0; break; + case -ESTALE: + case -ENOENT: case KSMBD_TREE_CONN_STATUS_NO_SHARE: - rsp->hdr.Status = STATUS_BAD_NETWORK_PATH; + rsp->hdr.Status = STATUS_BAD_NETWORK_NAME; break; case -ENOMEM: case KSMBD_TREE_CONN_STATUS_NOMEM: @@ -2328,15 +2330,15 @@ static int smb2_remove_smb_xattrs(struct path *path) name += strlen(name) + 1) { ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); - if (strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && - strncmp(&name[XATTR_USER_PREFIX_LEN], DOS_ATTRIBUTE_PREFIX, - DOS_ATTRIBUTE_PREFIX_LEN) && - strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) - continue; - - err = ksmbd_vfs_remove_xattr(user_ns, path->dentry, name); - if (err) - ksmbd_debug(SMB, "remove xattr failed : %s\n", name); + if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && + !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, + STREAM_PREFIX_LEN)) { + err = ksmbd_vfs_remove_xattr(user_ns, path->dentry, + name); + if (err) + ksmbd_debug(SMB, "remove xattr failed : %s\n", + name); + } } out: kvfree(xattr_list); @@ -3042,12 +3044,6 @@ int smb2_open(struct ksmbd_work *work) list_add(&fp->node, &fp->f_ci->m_fp_list); write_unlock(&fp->f_ci->m_lock); - rc = ksmbd_vfs_getattr(&path, &stat); - if (rc) { - generic_fillattr(user_ns, d_inode(path.dentry), &stat); - rc = 0; - } - /* Check delete pending among previous fp before oplock break */ if (ksmbd_inode_pending_delete(fp)) { rc = -EBUSY; @@ -3134,6 +3130,10 @@ int smb2_open(struct ksmbd_work *work) } } + rc = ksmbd_vfs_getattr(&path, &stat); + if (rc) + goto err_out; + if (stat.result_mask & STATX_BTIME) fp->create_time = ksmbd_UnixTimeToNT(stat.btime); else @@ -3149,9 +3149,6 @@ int smb2_open(struct ksmbd_work *work) memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); - generic_fillattr(user_ns, file_inode(fp->filp), - &stat); - rsp->StructureSize = cpu_to_le16(89); rcu_read_lock(); opinfo = rcu_dereference(fp->f_opinfo); diff --git a/fs/locks.c b/fs/locks.c index c266cfdc3291..607f94a0e789 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2129,6 +2129,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) else error = locks_lock_file_wait(f.file, &fl); + locks_release_private(&fl); out_putf: fdput(f); diff --git a/fs/namespace.c b/fs/namespace.c index 68789f896f08..df137ba19d37 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4238,6 +4238,13 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, err = -EPERM; goto out_fput; } + + /* We're not controlling the target namespace. */ + if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) { + err = -EPERM; + goto out_fput; + } + kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index dbab3caa15ed..5d6c2ddc7ea6 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2382,7 +2382,8 @@ static void nfs_dentry_remove_handle_error(struct inode *dir, { switch (error) { case -ENOENT: - d_delete(dentry); + if (d_really_is_positive(dentry)) + d_delete(dentry); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; case 0: @@ -2484,8 +2485,10 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) */ error = -ETXTBSY; if (WARN_ON(dentry->d_flags & DCACHE_NFSFS_RENAMED) || - WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) + WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) { + spin_unlock(&dentry->d_lock); goto out; + } if (dentry->d_fsdata) /* old devname */ kfree(dentry->d_fsdata); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d2bcd4834c0e..e032fe201a36 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -221,8 +221,10 @@ nfs_file_fsync_commit(struct file *file, int datasync) int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); + struct nfs_inode *nfsi = NFS_I(inode); + long save_nredirtied = atomic_long_read(&nfsi->redirtied_pages); + long nredirtied; int ret; trace_nfs_fsync_enter(inode); @@ -237,15 +239,10 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) ret = pnfs_sync_inode(inode, !!datasync); if (ret != 0) break; - if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags)) + nredirtied = atomic_long_read(&nfsi->redirtied_pages); + if (nredirtied == save_nredirtied) break; - /* - * If nfs_file_fsync_commit detected a server reboot, then - * resend all dirty pages that might have been covered by - * the NFS_CONTEXT_RESEND_WRITES flag - */ - start = 0; - end = LLONG_MAX; + save_nredirtied = nredirtied; } trace_nfs_fsync_exit(inode, ret); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b4e46b0ffa2d..bea7c005119c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -426,6 +426,7 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 27c720d71b4e..898dd95bc7a7 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -606,6 +606,31 @@ static inline gfp_t nfs_io_gfp_mask(void) return GFP_KERNEL; } +/* + * Special version of should_remove_suid() that ignores capabilities. + */ +static inline int nfs_should_remove_suid(const struct inode *inode) +{ + umode_t mode = inode->i_mode; + int kill = 0; + + /* suid always must be killed */ + if (unlikely(mode & S_ISUID)) + kill = ATTR_KILL_SUID; + + /* + * sgid without any exec bits is just a mandatory locking mark; leave + * it alone. If some exec bits are set, it's a real sgid; kill it. + */ + if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) + kill |= ATTR_KILL_SGID; + + if (unlikely(kill && S_ISREG(mode))) + return kill; + + return 0; +} + /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 068c45b3bc1a..6dab9e408372 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -78,10 +78,15 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, status = nfs4_call_sync(server->client, server, msg, &args.seq_args, &res.seq_res, 0); - if (status == 0) + if (status == 0) { + if (nfs_should_remove_suid(inode)) { + spin_lock(&inode->i_lock); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); + spin_unlock(&inode->i_lock); + } status = nfs_post_op_update_inode_force_wcc(inode, res.falloc_fattr); - + } if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE]) trace_nfs4_fallocate(inode, &args, status); else diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index e88f6b18445e..9eb181287879 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -340,6 +340,11 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out; } + if (!S_ISREG(fattr->mode)) { + res = ERR_PTR(-EBADF); + goto out; + } + res = ERR_PTR(-ENOMEM); len = strlen(SSC_READ_NAME_BODY) + 16; read_name = kzalloc(len, GFP_KERNEL); @@ -357,6 +362,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, r_ino->i_fop); if (IS_ERR(filep)) { res = ERR_CAST(filep); + iput(r_ino); goto out_free_name; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 41a9b6b58fb9..2613b7e36eb9 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2817,7 +2817,6 @@ int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr) /* Resend all requests through the MDS */ nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true, hdr->completion_ops); - set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags); return nfs_pageio_resend(&pgio, hdr); } EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 82944e14fcea..ee66ffdb985e 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1051,22 +1051,31 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx) if (ctx->bsize) sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits); - if (server->nfs_client->rpc_ops->version != 2) { - /* The VFS shouldn't apply the umask to mode bits. We will do - * so ourselves when necessary. + switch (server->nfs_client->rpc_ops->version) { + case 2: + sb->s_time_gran = 1000; + sb->s_time_min = 0; + sb->s_time_max = U32_MAX; + break; + case 3: + /* + * The VFS shouldn't apply the umask to mode bits. + * We will do so ourselves when necessary. */ sb->s_flags |= SB_POSIXACL; sb->s_time_gran = 1; - sb->s_export_op = &nfs_export_ops; - } else - sb->s_time_gran = 1000; - - if (server->nfs_client->rpc_ops->version != 4) { sb->s_time_min = 0; sb->s_time_max = U32_MAX; - } else { + sb->s_export_op = &nfs_export_ops; + break; + case 4: + sb->s_flags |= SB_POSIXACL; + sb->s_time_gran = 1; sb->s_time_min = S64_MIN; sb->s_time_max = S64_MAX; + if (server->caps & NFS_CAP_ATOMIC_OPEN_V1) + sb->s_export_op = &nfs_export_ops; + break; } sb->s_magic = NFS_SUPER_MAGIC; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 51a7e202d6e5..f41d24b54fd1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1420,10 +1420,12 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, */ static void nfs_redirty_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host); + /* Bump the transmission count */ req->wb_nio++; nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&nfsi->redirtied_pages); nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1494,31 +1496,6 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); } -/* - * Special version of should_remove_suid() that ignores capabilities. - */ -static int nfs_should_remove_suid(const struct inode *inode) -{ - umode_t mode = inode->i_mode; - int kill = 0; - - /* suid always must be killed */ - if (unlikely(mode & S_ISUID)) - kill = ATTR_KILL_SUID; - - /* - * sgid without any exec bits is just a mandatory locking mark; leave - * it alone. If some exec bits are set, it's a real sgid; kill it. - */ - if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) - kill |= ATTR_KILL_SGID; - - if (unlikely(kill && S_ISREG(mode))) - return kill; - - return 0; -} - static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr, struct nfs_fattr *fattr) { @@ -1904,7 +1881,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) /* We have a mismatch. Write the page again */ dprintk_cont(" mismatch\n"); nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&NFS_I(data->inode)->redirtied_pages); next: nfs_unlock_and_release_request(req); /* Latency breaker */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9f486b788ed0..fc17b0ac8729 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -300,6 +300,10 @@ commit_metadata(struct svc_fh *fhp) static void nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { + /* Ignore mode updates on symlinks */ + if (S_ISLNK(inode->i_mode)) + iap->ia_valid &= ~ATTR_MODE; + /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; @@ -353,7 +357,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, int accmode = NFSD_MAY_SATTR; umode_t ftype = 0; __be32 err; - int host_err; + int host_err = 0; bool get_write_count; bool size_change = (iap->ia_valid & ATTR_SIZE); @@ -391,13 +395,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, dentry = fhp->fh_dentry; inode = d_inode(dentry); - /* Ignore any mode updates on symlinks */ - if (S_ISLNK(inode->i_mode)) - iap->ia_valid &= ~ATTR_MODE; - - if (!iap->ia_valid) - return 0; - nfsd_sanitize_attrs(inode, iap); if (check_guard && guardtime != inode->i_ctime.tv_sec) @@ -448,8 +445,10 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_unlock; } - iap->ia_valid |= ATTR_CTIME; - host_err = notify_change(&init_user_ns, dentry, iap, NULL); + if (iap->ia_valid) { + iap->ia_valid |= ATTR_CTIME; + host_err = notify_change(&init_user_ns, dentry, iap, NULL); + } out_unlock: if (attr->na_seclabel && attr->na_seclabel->len) @@ -846,10 +845,14 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { struct svc_rqst *rqstp = sd->u.data; - - svc_rqst_replace_page(rqstp, buf->page); - if (rqstp->rq_res.page_len == 0) - rqstp->rq_res.page_base = buf->offset; + struct page *page = buf->page; // may be a compound one + unsigned offset = buf->offset; + + page += offset / PAGE_SIZE; + for (int i = sd->len; i > 0; i -= PAGE_SIZE) + svc_rqst_replace_page(rqstp, page++); + if (rqstp->rq_res.page_len == 0) // first call + rqstp->rq_res.page_base = offset % PAGE_SIZE; rqstp->rq_res.page_len += sd->len; return sd->len; } diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 5ae8de09b271..001f4e053c85 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2092,7 +2092,8 @@ get_ctx_vol_failed: // TODO: Initialize security. /* Get the extended system files' directory inode. */ vol->extend_ino = ntfs_iget(sb, FILE_Extend); - if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino)) { + if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino) || + !S_ISDIR(vol->extend_ino->i_mode)) { if (!IS_ERR(vol->extend_ino)) iput(vol->extend_ino); ntfs_error(sb, "Failed to load $Extend."); diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index e8c00dda42ad..71f870d497ae 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -84,8 +84,8 @@ static inline bool attr_must_be_resident(struct ntfs_sb_info *sbi, /* * attr_load_runs - Load all runs stored in @attr. */ -int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, - struct runs_tree *run, const CLST *vcn) +static int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, + struct runs_tree *run, const CLST *vcn) { int err; CLST svcn = le64_to_cpu(attr->nres.svcn); @@ -140,7 +140,10 @@ failed: } if (lcn != SPARSE_LCN) { - mark_as_free_ex(sbi, lcn, clen, trim); + if (sbi) { + /* mark bitmap range [lcn + clen) as free and trim clusters. */ + mark_as_free_ex(sbi, lcn, clen, trim); + } dn += clen; } @@ -173,7 +176,6 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, { int err; CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0; - struct wnd_bitmap *wnd = &sbi->used.bitmap; size_t cnt = run->count; for (;;) { @@ -196,9 +198,7 @@ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, /* Add new fragment into run storage. */ if (!run_add_entry(run, vcn, lcn, flen, opt == ALLOCATE_MFT)) { /* Undo last 'ntfs_look_for_free_space' */ - down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); - wnd_set_free(wnd, lcn, flen); - up_write(&wnd->rw_lock); + mark_as_free_ex(sbi, lcn, len, false); err = -ENOMEM; goto out; } @@ -320,7 +320,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, err = ni_insert_nonresident(ni, attr_s->type, attr_name(attr_s), attr_s->name_len, run, 0, alen, - attr_s->flags, &attr, NULL); + attr_s->flags, &attr, NULL, NULL); if (err) goto out3; @@ -419,40 +419,44 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, struct mft_inode *mi, *mi_b; CLST alen, vcn, lcn, new_alen, old_alen, svcn, evcn; CLST next_svcn, pre_alloc = -1, done = 0; - bool is_ext; + bool is_ext, is_bad = false; u32 align; struct MFT_REC *rec; again: + alen = 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, &mi_b); if (!attr_b) { err = -ENOENT; - goto out; + goto bad_inode; } if (!attr_b->non_res) { err = attr_set_size_res(ni, attr_b, le_b, mi_b, new_size, run, &attr_b); - if (err || !attr_b->non_res) - goto out; + if (err) + return err; + + /* Return if file is still resident. */ + if (!attr_b->non_res) + goto ok1; /* Layout of records may be changed, so do a full search. */ goto again; } is_ext = is_attr_ext(attr_b); - -again_1: align = sbi->cluster_size; - if (is_ext) align <<= attr_b->nres.c_unit; old_valid = le64_to_cpu(attr_b->nres.valid_size); old_size = le64_to_cpu(attr_b->nres.data_size); old_alloc = le64_to_cpu(attr_b->nres.alloc_size); + +again_1: old_alen = old_alloc >> cluster_bits; new_alloc = (new_size + align - 1) & ~(u64)(align - 1); @@ -475,24 +479,27 @@ again_1: mi = mi_b; } else if (!le_b) { err = -EINVAL; - goto out; + goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &vcn, &mi); if (!attr) { err = -EINVAL; - goto out; + goto bad_inode; } next_le_1: svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); } - + /* + * Here we have: + * attr,mi,le - last attribute segment (containing 'vcn'). + * attr_b,mi_b,le_b - base (primary) attribute segment. + */ next_le: rec = mi->mrec; - err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; @@ -507,6 +514,13 @@ next_le: goto ok; } + /* + * Add clusters. In simple case we have to: + * - allocate space (vcn, lcn, len) + * - update packed run in 'mi' + * - update attr->nres.evcn + * - update attr_b->nres.data_size/attr_b->nres.alloc_size + */ to_allocate = new_alen - old_alen; add_alloc_in_same_attr_seg: lcn = 0; @@ -520,9 +534,11 @@ add_alloc_in_same_attr_seg: pre_alloc = 0; if (type == ATTR_DATA && !name_len && sbi->options->prealloc) { - CLST new_alen2 = bytes_to_cluster( - sbi, get_pre_allocated(new_size)); - pre_alloc = new_alen2 - new_alen; + pre_alloc = + bytes_to_cluster( + sbi, + get_pre_allocated(new_size)) - + new_alen; } /* Get the last LCN to allocate from. */ @@ -580,7 +596,7 @@ add_alloc_in_same_attr_seg: pack_runs: err = mi_pack_runs(mi, attr, run, vcn - svcn); if (err) - goto out; + goto undo_1; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; new_alloc_tmp = (u64)next_svcn << cluster_bits; @@ -614,7 +630,7 @@ pack_runs: if (type == ATTR_LIST) { err = ni_expand_list(ni); if (err) - goto out; + goto undo_2; if (next_svcn < vcn) goto pack_runs; @@ -624,8 +640,9 @@ pack_runs: if (!ni->attr_list.size) { err = ni_create_attr_list(ni); + /* In case of error layout of records is not changed. */ if (err) - goto out; + goto undo_2; /* Layout of records is changed. */ } @@ -637,48 +654,57 @@ pack_runs: /* Insert new attribute segment. */ err = ni_insert_nonresident(ni, type, name, name_len, run, next_svcn, vcn - next_svcn, - attr_b->flags, &attr, &mi); - if (err) - goto out; - - if (!is_mft) - run_truncate_head(run, evcn + 1); - - svcn = le64_to_cpu(attr->nres.svcn); - evcn = le64_to_cpu(attr->nres.evcn); + attr_b->flags, &attr, &mi, NULL); - le_b = NULL; /* * Layout of records maybe changed. * Find base attribute to update. */ + le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, &mi_b); if (!attr_b) { - err = -ENOENT; - goto out; + err = -EINVAL; + goto bad_inode; } - attr_b->nres.alloc_size = cpu_to_le64((u64)vcn << cluster_bits); - attr_b->nres.data_size = attr_b->nres.alloc_size; - attr_b->nres.valid_size = attr_b->nres.alloc_size; + if (err) { + /* ni_insert_nonresident failed. */ + attr = NULL; + goto undo_2; + } + + if (!is_mft) + run_truncate_head(run, evcn + 1); + + svcn = le64_to_cpu(attr->nres.svcn); + evcn = le64_to_cpu(attr->nres.evcn); + + /* + * Attribute is in consistency state. + * Save this point to restore to if next steps fail. + */ + old_valid = old_size = old_alloc = (u64)vcn << cluster_bits; + attr_b->nres.valid_size = attr_b->nres.data_size = + attr_b->nres.alloc_size = cpu_to_le64(old_size); mi_b->dirty = true; goto again_1; } if (new_size != old_size || (new_alloc != old_alloc && !keep_prealloc)) { + /* + * Truncate clusters. In simple case we have to: + * - update packed run in 'mi' + * - update attr->nres.evcn + * - update attr_b->nres.data_size/attr_b->nres.alloc_size + * - mark and trim clusters as free (vcn, lcn, len) + */ + CLST dlen = 0; + vcn = max(svcn, new_alen); new_alloc_tmp = (u64)vcn << cluster_bits; - alen = 0; - err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &alen, - true); - if (err) - goto out; - - run_truncate(run, vcn); - if (vcn > svcn) { err = mi_pack_runs(mi, attr, run, vcn - svcn); if (err) @@ -697,7 +723,7 @@ pack_runs: if (!al_remove_le(ni, le)) { err = -EINVAL; - goto out; + goto bad_inode; } le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz); @@ -723,12 +749,20 @@ pack_runs: attr_b->nres.valid_size = attr_b->nres.alloc_size; } + mi_b->dirty = true; - if (is_ext) + err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &dlen, + true); + if (err) + goto out; + + if (is_ext) { + /* dlen - really deallocated clusters. */ le64_sub_cpu(&attr_b->nres.total_size, - ((u64)alen << cluster_bits)); + ((u64)dlen << cluster_bits)); + } - mi_b->dirty = true; + run_truncate(run, vcn); if (new_alloc_tmp <= new_alloc) goto ok; @@ -747,7 +781,7 @@ pack_runs: if (le->type != type || le->name_len != name_len || memcmp(le_name(le), name, name_len * sizeof(short))) { err = -EINVAL; - goto out; + goto bad_inode; } err = ni_load_mi(ni, le, &mi); @@ -757,7 +791,7 @@ pack_runs: attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); if (!attr) { err = -EINVAL; - goto out; + goto bad_inode; } goto next_le_1; } @@ -772,13 +806,13 @@ ok: } } -out: - if (!err && attr_b && ret) +ok1: + if (ret) *ret = attr_b; /* Update inode_set_bytes. */ - if (!err && ((type == ATTR_DATA && !name_len) || - (type == ATTR_ALLOC && name == I30_NAME))) { + if (((type == ATTR_DATA && !name_len) || + (type == ATTR_ALLOC && name == I30_NAME))) { bool dirty = false; if (ni->vfs_inode.i_size != new_size) { @@ -786,7 +820,7 @@ out: dirty = true; } - if (attr_b && attr_b->non_res) { + if (attr_b->non_res) { new_alloc = le64_to_cpu(attr_b->nres.alloc_size); if (inode_get_bytes(&ni->vfs_inode) != new_alloc) { inode_set_bytes(&ni->vfs_inode, new_alloc); @@ -800,6 +834,47 @@ out: } } + return 0; + +undo_2: + vcn -= alen; + attr_b->nres.data_size = cpu_to_le64(old_size); + attr_b->nres.valid_size = cpu_to_le64(old_valid); + attr_b->nres.alloc_size = cpu_to_le64(old_alloc); + + /* Restore 'attr' and 'mi'. */ + if (attr) + goto restore_run; + + if (le64_to_cpu(attr_b->nres.svcn) <= svcn && + svcn <= le64_to_cpu(attr_b->nres.evcn)) { + attr = attr_b; + le = le_b; + mi = mi_b; + } else if (!le_b) { + err = -EINVAL; + goto bad_inode; + } else { + le = le_b; + attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, + &svcn, &mi); + if (!attr) + goto bad_inode; + } + +restore_run: + if (mi_pack_runs(mi, attr, run, evcn - svcn + 1)) + is_bad = true; + +undo_1: + run_deallocate_ex(sbi, run, vcn, alen, NULL, false); + + run_truncate(run, vcn); +out: + if (is_bad) { +bad_inode: + _ntfs_bad_inode(&ni->vfs_inode); + } return err; } @@ -855,7 +930,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, goto out; } - asize = le64_to_cpu(attr_b->nres.alloc_size) >> sbi->cluster_bits; + asize = le64_to_cpu(attr_b->nres.alloc_size) >> cluster_bits; if (vcn >= asize) { err = -EINVAL; goto out; @@ -1047,7 +1122,7 @@ ins_ext: if (evcn1 > next_svcn) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, - attr_b->flags, &attr, &mi); + attr_b->flags, &attr, &mi, NULL); if (err) goto out; } @@ -1173,7 +1248,7 @@ int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type, { struct ntfs_sb_info *sbi = ni->mi.sbi; u8 cluster_bits = sbi->cluster_bits; - CLST vcn = from >> cluster_bits; + CLST vcn; CLST vcn_last = (to - 1) >> cluster_bits; CLST lcn, clen; int err; @@ -1647,7 +1722,7 @@ ins_ext: if (evcn1 > next_svcn) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, - attr_b->flags, &attr, &mi); + attr_b->flags, &attr, &mi, NULL); if (err) goto out; } @@ -1812,18 +1887,12 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) err = ni_insert_nonresident( ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - eat - next_svcn, a_flags, &attr, - &mi); + &mi, &le); if (err) goto out; /* Layout of records maybe changed. */ attr_b = NULL; - le = al_find_ex(ni, NULL, ATTR_DATA, NULL, 0, - &next_svcn); - if (!le) { - err = -EINVAL; - goto out; - } } /* Free all allocated memory. */ @@ -1918,7 +1987,7 @@ next_attr: out: up_write(&ni->file.run_lock); if (err) - make_bad_inode(&ni->vfs_inode); + _ntfs_bad_inode(&ni->vfs_inode); return err; } @@ -1936,9 +2005,11 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; - CLST svcn, evcn1, vcn, len, end, alen, dealloc; + CLST svcn, evcn1, vcn, len, end, alen, hole, next_svcn; u64 total_size, alloc_size; u32 mask; + __le16 a_flags; + struct runs_tree run2; if (!bytes) return 0; @@ -1990,6 +2061,9 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) } down_write(&ni->file.run_lock); + run_init(&run2); + run_truncate(run, 0); + /* * Enumerate all attribute segments and punch hole where necessary. */ @@ -1997,10 +2071,11 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) vcn = vbo >> sbi->cluster_bits; len = bytes >> sbi->cluster_bits; end = vcn + len; - dealloc = 0; + hole = 0; svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + a_flags = attr_b->flags; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; @@ -2008,14 +2083,14 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) mi = mi_b; } else if (!le_b) { err = -EINVAL; - goto out; + goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; - goto out; + goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); @@ -2023,49 +2098,91 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) } while (svcn < end) { - CLST vcn1, zero, dealloc2; + CLST vcn1, zero, hole2 = hole; err = attr_load_runs(attr, ni, run, &svcn); if (err) - goto out; + goto done; vcn1 = max(vcn, svcn); zero = min(end, evcn1) - vcn1; - dealloc2 = dealloc; - err = run_deallocate_ex(sbi, run, vcn1, zero, &dealloc, true); + /* + * Check range [vcn1 + zero). + * Calculate how many clusters there are. + * Don't do any destructive actions. + */ + err = run_deallocate_ex(NULL, run, vcn1, zero, &hole2, false); if (err) - goto out; + goto done; - if (dealloc2 == dealloc) { - /* Looks like the required range is already sparsed. */ - } else { - if (!run_add_entry(run, vcn1, SPARSE_LCN, zero, - false)) { - err = -ENOMEM; - goto out; - } + /* Check if required range is already hole. */ + if (hole2 == hole) + goto next_attr; + + /* Make a clone of run to undo. */ + err = run_clone(run, &run2); + if (err) + goto done; + + /* Make a hole range (sparse) [vcn1 + zero). */ + if (!run_add_entry(run, vcn1, SPARSE_LCN, zero, false)) { + err = -ENOMEM; + goto done; + } - err = mi_pack_runs(mi, attr, run, evcn1 - svcn); + /* Update run in attribute segment. */ + err = mi_pack_runs(mi, attr, run, evcn1 - svcn); + if (err) + goto done; + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + if (next_svcn < evcn1) { + /* Insert new attribute segment. */ + err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, + next_svcn, + evcn1 - next_svcn, a_flags, + &attr, &mi, &le); if (err) - goto out; + goto undo_punch; + + /* Layout of records maybe changed. */ + attr_b = NULL; } + + /* Real deallocate. Should not fail. */ + run_deallocate_ex(sbi, &run2, vcn1, zero, &hole, true); + +next_attr: /* Free all allocated memory. */ run_truncate(run, 0); if (evcn1 >= alen) break; + /* Get next attribute segment. */ attr = ni_enum_attr_ex(ni, attr, &le, &mi); if (!attr) { err = -EINVAL; - goto out; + goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } - total_size -= (u64)dealloc << sbi->cluster_bits; +done: + if (!hole) + goto out; + + if (!attr_b) { + attr_b = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, + &mi_b); + if (!attr_b) { + err = -EINVAL; + goto bad_inode; + } + } + + total_size -= (u64)hole << sbi->cluster_bits; attr_b->nres.total_size = cpu_to_le64(total_size); mi_b->dirty = true; @@ -2075,9 +2192,263 @@ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) mark_inode_dirty(&ni->vfs_inode); out: + run_close(&run2); up_write(&ni->file.run_lock); + return err; + +bad_inode: + _ntfs_bad_inode(&ni->vfs_inode); + goto out; + +undo_punch: + /* + * Restore packed runs. + * 'mi_pack_runs' should not fail, cause we restore original. + */ + if (mi_pack_runs(mi, attr, &run2, evcn1 - svcn)) + goto bad_inode; + + goto done; +} + +/* + * attr_insert_range - Insert range (hole) in file. + * Not for normal files. + */ +int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) +{ + int err = 0; + struct runs_tree *run = &ni->file.run; + struct ntfs_sb_info *sbi = ni->mi.sbi; + struct ATTRIB *attr = NULL, *attr_b; + struct ATTR_LIST_ENTRY *le, *le_b; + struct mft_inode *mi, *mi_b; + CLST vcn, svcn, evcn1, len, next_svcn; + u64 data_size, alloc_size; + u32 mask; + __le16 a_flags; + + if (!bytes) + return 0; + + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); + if (!attr_b) + return -ENOENT; + + if (!is_attr_ext(attr_b)) { + /* It was checked above. See fallocate. */ + return -EOPNOTSUPP; + } + + if (!attr_b->non_res) { + data_size = le32_to_cpu(attr_b->res.data_size); + alloc_size = data_size; + mask = sbi->cluster_mask; /* cluster_size - 1 */ + } else { + data_size = le64_to_cpu(attr_b->nres.data_size); + alloc_size = le64_to_cpu(attr_b->nres.alloc_size); + mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; + } + + if (vbo > data_size) { + /* Insert range after the file size is not allowed. */ + return -EINVAL; + } + + if ((vbo & mask) || (bytes & mask)) { + /* Allow to insert only frame aligned ranges. */ + return -EINVAL; + } + + /* + * valid_size <= data_size <= alloc_size + * Check alloc_size for maximum possible. + */ + if (bytes > sbi->maxbytes_sparse - alloc_size) + return -EFBIG; + + vcn = vbo >> sbi->cluster_bits; + len = bytes >> sbi->cluster_bits; + + down_write(&ni->file.run_lock); + + if (!attr_b->non_res) { + err = attr_set_size(ni, ATTR_DATA, NULL, 0, run, + data_size + bytes, NULL, false, NULL); + + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, + &mi_b); + if (!attr_b) { + err = -EINVAL; + goto bad_inode; + } + + if (err) + goto out; + + if (!attr_b->non_res) { + /* Still resident. */ + char *data = Add2Ptr(attr_b, attr_b->res.data_off); + + memmove(data + bytes, data, bytes); + memset(data, 0, bytes); + goto done; + } + + /* Resident files becomes nonresident. */ + data_size = le64_to_cpu(attr_b->nres.data_size); + alloc_size = le64_to_cpu(attr_b->nres.alloc_size); + } + + /* + * Enumerate all attribute segments and shift start vcn. + */ + a_flags = attr_b->flags; + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + + if (svcn <= vcn && vcn < evcn1) { + attr = attr_b; + le = le_b; + mi = mi_b; + } else if (!le_b) { + err = -EINVAL; + goto bad_inode; + } else { + le = le_b; + attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, + &mi); + if (!attr) { + err = -EINVAL; + goto bad_inode; + } + + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + } + + run_truncate(run, 0); /* clear cached values. */ + err = attr_load_runs(attr, ni, run, NULL); + if (err) + goto out; + + if (!run_insert_range(run, vcn, len)) { + err = -ENOMEM; + goto out; + } + + /* Try to pack in current record as much as possible. */ + err = mi_pack_runs(mi, attr, run, evcn1 + len - svcn); if (err) - make_bad_inode(&ni->vfs_inode); + goto out; + + next_svcn = le64_to_cpu(attr->nres.evcn) + 1; + + while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) && + attr->type == ATTR_DATA && !attr->name_len) { + le64_add_cpu(&attr->nres.svcn, len); + le64_add_cpu(&attr->nres.evcn, len); + if (le) { + le->vcn = attr->nres.svcn; + ni->attr_list.dirty = true; + } + mi->dirty = true; + } + + if (next_svcn < evcn1 + len) { + err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, + next_svcn, evcn1 + len - next_svcn, + a_flags, NULL, NULL, NULL); + + le_b = NULL; + attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, + &mi_b); + if (!attr_b) { + err = -EINVAL; + goto bad_inode; + } + + if (err) { + /* ni_insert_nonresident failed. Try to undo. */ + goto undo_insert_range; + } + } + + /* + * Update primary attribute segment. + */ + if (vbo <= ni->i_valid) + ni->i_valid += bytes; + + attr_b->nres.data_size = le64_to_cpu(data_size + bytes); + attr_b->nres.alloc_size = le64_to_cpu(alloc_size + bytes); + + /* ni->valid may be not equal valid_size (temporary). */ + if (ni->i_valid > data_size + bytes) + attr_b->nres.valid_size = attr_b->nres.data_size; + else + attr_b->nres.valid_size = cpu_to_le64(ni->i_valid); + mi_b->dirty = true; + +done: + ni->vfs_inode.i_size += bytes; + ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + mark_inode_dirty(&ni->vfs_inode); + +out: + run_truncate(run, 0); /* clear cached values. */ + + up_write(&ni->file.run_lock); return err; + +bad_inode: + _ntfs_bad_inode(&ni->vfs_inode); + goto out; + +undo_insert_range: + svcn = le64_to_cpu(attr_b->nres.svcn); + evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; + + if (svcn <= vcn && vcn < evcn1) { + attr = attr_b; + le = le_b; + mi = mi_b; + } else if (!le_b) { + goto bad_inode; + } else { + le = le_b; + attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, + &mi); + if (!attr) { + goto bad_inode; + } + + svcn = le64_to_cpu(attr->nres.svcn); + evcn1 = le64_to_cpu(attr->nres.evcn) + 1; + } + + if (attr_load_runs(attr, ni, run, NULL)) + goto bad_inode; + + if (!run_collapse_range(run, vcn, len)) + goto bad_inode; + + if (mi_pack_runs(mi, attr, run, evcn1 + len - svcn)) + goto bad_inode; + + while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) && + attr->type == ATTR_DATA && !attr->name_len) { + le64_sub_cpu(&attr->nres.svcn, len); + le64_sub_cpu(&attr->nres.evcn, len); + if (le) { + le->vcn = attr->nres.svcn; + ni->attr_list.dirty = true; + } + mi->dirty = true; + } + + goto out; } diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index aa184407520f..5d44ceac855b 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -51,11 +51,6 @@ void ntfs3_exit_bitmap(void) kmem_cache_destroy(ntfs_enode_cachep); } -static inline u32 wnd_bits(const struct wnd_bitmap *wnd, size_t i) -{ - return i + 1 == wnd->nwnd ? wnd->bits_last : wnd->sb->s_blocksize * 8; -} - /* * wnd_scan * @@ -1333,9 +1328,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) if (!new_free) return -ENOMEM; - if (new_free != wnd->free_bits) - memcpy(new_free, wnd->free_bits, - wnd->nwnd * sizeof(short)); + memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short)); memset(new_free + wnd->nwnd, 0, (new_wnd - wnd->nwnd) * sizeof(short)); kfree(wnd->free_bits); @@ -1395,9 +1388,8 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits) void wnd_zone_set(struct wnd_bitmap *wnd, size_t lcn, size_t len) { - size_t zlen; + size_t zlen = wnd->zone_end - wnd->zone_bit; - zlen = wnd->zone_end - wnd->zone_bit; if (zlen) wnd_add_free_ext(wnd, wnd->zone_bit, zlen, false); diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 4a21745711fe..4f2ffc7ef296 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -530,21 +530,35 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size) static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) { struct inode *inode = file->f_mapping->host; + struct address_space *mapping = inode->i_mapping; struct super_block *sb = inode->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(inode); loff_t end = vbo + len; loff_t vbo_down = round_down(vbo, PAGE_SIZE); - loff_t i_size; + bool is_supported_holes = is_sparsed(ni) || is_compressed(ni); + loff_t i_size, new_size; + bool map_locked; int err; /* No support for dir. */ if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; - /* Return error if mode is not supported. */ - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | - FALLOC_FL_COLLAPSE_RANGE)) { + /* + * vfs_fallocate checks all possible combinations of mode. + * Do additional checks here before ntfs_set_state(dirty). + */ + if (mode & FALLOC_FL_PUNCH_HOLE) { + if (!is_supported_holes) + return -EOPNOTSUPP; + } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { + } else if (mode & FALLOC_FL_INSERT_RANGE) { + if (!is_supported_holes) + return -EOPNOTSUPP; + } else if (mode & + ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | + FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)) { ntfs_inode_warn(inode, "fallocate(0x%x) is not supported", mode); return -EOPNOTSUPP; @@ -554,6 +568,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) inode_lock(inode); i_size = inode->i_size; + new_size = max(end, i_size); + map_locked = false; if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) { /* Should never be here, see ntfs_file_open. */ @@ -561,38 +577,27 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) goto out; } + if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | + FALLOC_FL_INSERT_RANGE)) { + inode_dio_wait(inode); + filemap_invalidate_lock(mapping); + map_locked = true; + } + if (mode & FALLOC_FL_PUNCH_HOLE) { u32 frame_size; loff_t mask, vbo_a, end_a, tmp; - if (!(mode & FALLOC_FL_KEEP_SIZE)) { - err = -EINVAL; - goto out; - } - - err = filemap_write_and_wait_range(inode->i_mapping, vbo, - end - 1); + err = filemap_write_and_wait_range(mapping, vbo, end - 1); if (err) goto out; - err = filemap_write_and_wait_range(inode->i_mapping, end, - LLONG_MAX); + err = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (err) goto out; - inode_dio_wait(inode); - truncate_pagecache(inode, vbo_down); - if (!is_sparsed(ni) && !is_compressed(ni)) { - /* - * Normal file, can't make hole. - * TODO: Try to find way to save info about hole. - */ - err = -EOPNOTSUPP; - goto out; - } - ni_lock(ni); err = attr_punch_hole(ni, vbo, len, &frame_size); ni_unlock(ni); @@ -624,17 +629,11 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) ni_unlock(ni); } } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { - if (mode & ~FALLOC_FL_COLLAPSE_RANGE) { - err = -EINVAL; - goto out; - } - /* * Write tail of the last page before removed range since * it will get removed from the page cache below. */ - err = filemap_write_and_wait_range(inode->i_mapping, vbo_down, - vbo); + err = filemap_write_and_wait_range(mapping, vbo_down, vbo); if (err) goto out; @@ -642,34 +641,58 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) * Write data that will be shifted to preserve them * when discarding page cache below. */ - err = filemap_write_and_wait_range(inode->i_mapping, end, - LLONG_MAX); + err = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (err) goto out; - /* Wait for existing dio to complete. */ - inode_dio_wait(inode); - truncate_pagecache(inode, vbo_down); ni_lock(ni); err = attr_collapse_range(ni, vbo, len); ni_unlock(ni); + } else if (mode & FALLOC_FL_INSERT_RANGE) { + /* Check new size. */ + err = inode_newsize_ok(inode, new_size); + if (err) + goto out; + + /* Write out all dirty pages. */ + err = filemap_write_and_wait_range(mapping, vbo_down, + LLONG_MAX); + if (err) + goto out; + truncate_pagecache(inode, vbo_down); + + ni_lock(ni); + err = attr_insert_range(ni, vbo, len); + ni_unlock(ni); } else { - /* - * Normal file: Allocate clusters, do not change 'valid' size. - */ - loff_t new_size = max(end, i_size); + /* Check new size. */ + + /* generic/213: expected -ENOSPC instead of -EFBIG. */ + if (!is_supported_holes) { + loff_t to_alloc = new_size - inode_get_bytes(inode); + + if (to_alloc > 0 && + (to_alloc >> sbi->cluster_bits) > + wnd_zeroes(&sbi->used.bitmap)) { + err = -ENOSPC; + goto out; + } + } err = inode_newsize_ok(inode, new_size); if (err) goto out; + /* + * Allocate clusters, do not change 'valid' size. + */ err = ntfs_set_size(inode, new_size); if (err) goto out; - if (is_sparsed(ni) || is_compressed(ni)) { + if (is_supported_holes) { CLST vcn_v = ni->i_valid >> sbi->cluster_bits; CLST vcn = vbo >> sbi->cluster_bits; CLST cend = bytes_to_cluster(sbi, end); @@ -717,8 +740,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) } out: - if (err == -EFBIG) - err = -ENOSPC; + if (map_locked) + filemap_invalidate_unlock(mapping); if (!err) { inode->i_ctime = inode->i_mtime = current_time(inode); @@ -989,7 +1012,6 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) if (bytes > count) bytes = count; - frame = pos >> frame_bits; frame_vbo = pos & ~(frame_size - 1); index = frame_vbo >> PAGE_SHIFT; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 18842998c8fa..381a38a06ec2 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -7,6 +7,7 @@ #include <linux/fiemap.h> #include <linux/fs.h> +#include <linux/minmax.h> #include <linux/vmalloc.h> #include "debug.h" @@ -468,7 +469,7 @@ ni_ins_new_attr(struct ntfs_inode *ni, struct mft_inode *mi, &ref, &le); if (err) { /* No memory or no space. */ - return NULL; + return ERR_PTR(err); } le_added = true; @@ -649,6 +650,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) struct mft_inode *mi; u32 asize, free; struct MFT_REF ref; + struct MFT_REC *mrec; __le16 id; if (!ni->attr_list.dirty) @@ -692,11 +694,17 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) free -= asize; } + /* Make a copy of primary record to restore if error. */ + mrec = kmemdup(ni->mi.mrec, sbi->record_size, GFP_NOFS); + if (!mrec) + return 0; /* Not critical. */ + /* It seems that attribute list can be removed from primary record. */ mi_remove_attr(NULL, &ni->mi, attr_list); /* - * Repeat the cycle above and move all attributes to primary record. + * Repeat the cycle above and copy all attributes to primary record. + * Do not remove original attributes from subrecords! * It should be success! */ le = NULL; @@ -707,14 +715,14 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) mi = ni_find_mi(ni, ino_get(&le->ref)); if (!mi) { /* Should never happened, 'cause already checked. */ - goto bad; + goto out; } attr = mi_find_attr(mi, NULL, le->type, le_name(le), le->name_len, &le->id); if (!attr) { /* Should never happened, 'cause already checked. */ - goto bad; + goto out; } asize = le32_to_cpu(attr->size); @@ -724,18 +732,33 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) le16_to_cpu(attr->name_off)); if (!attr_ins) { /* - * Internal error. - * Either no space in primary record (already checked). - * Either tried to insert another - * non indexed attribute (logic error). + * No space in primary record (already checked). */ - goto bad; + goto out; } /* Copy all except id. */ id = attr_ins->id; memcpy(attr_ins, attr, asize); attr_ins->id = id; + } + + /* + * Repeat the cycle above and remove all attributes from subrecords. + */ + le = NULL; + while ((le = al_enumerate(ni, le))) { + if (!memcmp(&le->ref, &ref, sizeof(ref))) + continue; + + mi = ni_find_mi(ni, ino_get(&le->ref)); + if (!mi) + continue; + + attr = mi_find_attr(mi, NULL, le->type, le_name(le), + le->name_len, &le->id); + if (!attr) + continue; /* Remove from original record. */ mi_remove_attr(NULL, mi, attr); @@ -748,11 +771,13 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) ni->attr_list.le = NULL; ni->attr_list.dirty = false; + kfree(mrec); + return 0; +out: + /* Restore primary record. */ + swap(mrec, ni->mi.mrec); + kfree(mrec); return 0; -bad: - ntfs_inode_err(&ni->vfs_inode, "Internal error"); - make_bad_inode(&ni->vfs_inode); - return -EINVAL; } /* @@ -986,6 +1011,8 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, name_off, svcn, ins_le); if (!attr) continue; + if (IS_ERR(attr)) + return PTR_ERR(attr); if (ins_attr) *ins_attr = attr; @@ -1007,8 +1034,15 @@ insert_ext: attr = ni_ins_new_attr(ni, mi, le, type, name, name_len, asize, name_off, svcn, ins_le); - if (!attr) + if (!attr) { + err = -EINVAL; goto out2; + } + + if (IS_ERR(attr)) { + err = PTR_ERR(attr); + goto out2; + } if (ins_attr) *ins_attr = attr; @@ -1020,10 +1054,9 @@ insert_ext: out2: ni_remove_mi(ni, mi); mi_put(mi); - err = -EINVAL; out1: - ntfs_mark_rec_free(sbi, rno); + ntfs_mark_rec_free(sbi, rno, is_mft); out: return err; @@ -1076,6 +1109,11 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, if (asize <= free) { attr = ni_ins_new_attr(ni, &ni->mi, NULL, type, name, name_len, asize, name_off, svcn, ins_le); + if (IS_ERR(attr)) { + err = PTR_ERR(attr); + goto out; + } + if (attr) { if (ins_attr) *ins_attr = attr; @@ -1173,6 +1211,11 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, goto out; } + if (IS_ERR(attr)) { + err = PTR_ERR(attr); + goto out; + } + if (ins_attr) *ins_attr = attr; if (ins_mi) @@ -1218,7 +1261,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) mft_min = mft_new; mi_min = mi_new; } else { - ntfs_mark_rec_free(sbi, mft_new); + ntfs_mark_rec_free(sbi, mft_new, true); mft_new = 0; ni_remove_mi(ni, mi_new); } @@ -1262,7 +1305,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) done = asize - run_size - SIZEOF_NONRESIDENT; le32_sub_cpu(&ni->mi.mrec->used, done); - /* Estimate the size of second part: run_buf=NULL. */ + /* Estimate packed size (run_buf=NULL). */ err = run_pack(run, svcn, evcn + 1 - svcn, NULL, sbi->record_size, &plen); if (err < 0) @@ -1288,10 +1331,16 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) goto out; } + if (IS_ERR(attr)) { + err = PTR_ERR(attr); + goto out; + } + attr->non_res = 1; attr->name_off = SIZEOF_NONRESIDENT_LE; attr->flags = 0; + /* This function can't fail - cause already checked above. */ run_pack(run, svcn, evcn + 1 - svcn, Add2Ptr(attr, SIZEOF_NONRESIDENT), run_size, &plen); @@ -1301,7 +1350,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) out: if (mft_new) { - ntfs_mark_rec_free(sbi, mft_new); + ntfs_mark_rec_free(sbi, mft_new, true); ni_remove_mi(ni, mi_new); } @@ -1367,8 +1416,6 @@ int ni_expand_list(struct ntfs_inode *ni) /* Split MFT data as much as possible. */ err = ni_expand_mft_list(ni); - if (err) - goto out; out: return !err && !done ? -EOPNOTSUPP : err; @@ -1381,7 +1428,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, const struct runs_tree *run, CLST svcn, CLST len, __le16 flags, struct ATTRIB **new_attr, - struct mft_inode **mi) + struct mft_inode **mi, struct ATTR_LIST_ENTRY **le) { int err; CLST plen; @@ -1394,6 +1441,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, u32 run_size, asize; struct ntfs_sb_info *sbi = ni->mi.sbi; + /* Estimate packed size (run_buf=NULL). */ err = run_pack(run, svcn, len, NULL, sbi->max_bytes_per_attr - run_off, &plen); if (err < 0) @@ -1414,7 +1462,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, } err = ni_insert_attr(ni, type, name, name_len, asize, name_off, svcn, - &attr, mi, NULL); + &attr, mi, le); if (err) goto out; @@ -1423,12 +1471,12 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, attr->name_off = cpu_to_le16(name_off); attr->flags = flags; + /* This function can't fail - cause already checked above. */ run_pack(run, svcn, len, Add2Ptr(attr, run_off), run_size, &plen); attr->nres.svcn = cpu_to_le64(svcn); attr->nres.evcn = cpu_to_le64((u64)svcn + len - 1); - err = 0; if (new_attr) *new_attr = attr; @@ -1560,7 +1608,7 @@ int ni_delete_all(struct ntfs_inode *ni) mi->dirty = true; mi_write(mi, 0); - ntfs_mark_rec_free(sbi, mi->rno); + ntfs_mark_rec_free(sbi, mi->rno, false); ni_remove_mi(ni, mi); mi_put(mi); node = next; @@ -1571,7 +1619,7 @@ int ni_delete_all(struct ntfs_inode *ni) ni->mi.dirty = true; err = mi_write(&ni->mi, 0); - ntfs_mark_rec_free(sbi, ni->mi.rno); + ntfs_mark_rec_free(sbi, ni->mi.rno, false); return err; } @@ -1589,7 +1637,8 @@ struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, struct ATTRIB *attr = NULL; struct ATTR_FILE_NAME *fname; - *le = NULL; + if (le) + *le = NULL; /* Enumerate all names. */ next: @@ -1605,7 +1654,7 @@ next: goto next; if (!uni) - goto next; + return fname; if (uni->len != fname->name_len) goto next; @@ -2302,10 +2351,8 @@ remove_wof: out: kfree(pages); - if (err) { - make_bad_inode(inode); - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); - } + if (err) + _ntfs_bad_inode(inode); return err; } @@ -2944,7 +2991,7 @@ bool ni_remove_name_undo(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, } /* - * ni_add_name - Add new name in MFT and in directory. + * ni_add_name - Add new name into MFT and into directory. */ int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, struct NTFS_DE *de) @@ -2953,13 +3000,20 @@ int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, struct ATTRIB *attr; struct ATTR_LIST_ENTRY *le; struct mft_inode *mi; + struct ATTR_FILE_NAME *fname; struct ATTR_FILE_NAME *de_name = (struct ATTR_FILE_NAME *)(de + 1); u16 de_key_size = le16_to_cpu(de->key_size); mi_get_ref(&ni->mi, &de->ref); mi_get_ref(&dir_ni->mi, &de_name->home); - /* Insert new name in MFT. */ + /* Fill duplicate from any ATTR_NAME. */ + fname = ni_fname_name(ni, NULL, NULL, NULL, NULL); + if (fname) + memcpy(&de_name->dup, &fname->dup, sizeof(fname->dup)); + de_name->dup.fa = ni->std_fa; + + /* Insert new name into MFT. */ err = ni_insert_resident(ni, de_key_size, ATTR_NAME, NULL, 0, &attr, &mi, &le); if (err) @@ -2967,7 +3021,7 @@ int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), de_name, de_key_size); - /* Insert new name in directory. */ + /* Insert new name into directory. */ err = indx_insert_entry(&dir_ni->dir, dir_ni, de, ni->mi.sbi, NULL, 0); if (err) ni_remove_attr_le(ni, attr, mi, le); @@ -2991,7 +3045,7 @@ int ni_rename(struct ntfs_inode *dir_ni, struct ntfs_inode *new_dir_ni, * 1) Add new name and remove old name. * 2) Remove old name and add new name. * - * In most cases (not all!) adding new name in MFT and in directory can + * In most cases (not all!) adding new name into MFT and into directory can * allocate additional cluster(s). * Second way may result to bad inode if we can't add new name * and then can't restore (add) old name. @@ -3261,7 +3315,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) err = err2; if (is_empty) { - ntfs_mark_rec_free(sbi, mi->rno); + ntfs_mark_rec_free(sbi, mi->rno, false); rb_erase(node, &ni->mi_tree); mi_put(mi); } diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 49b7df616778..e7c494005122 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -3843,6 +3843,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) memset(&rst_info2, 0, sizeof(struct restart_info)); err = log_read_rst(log, l_size, false, &rst_info2); + if (err) + goto out; /* Determine which restart area to use. */ if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn) @@ -5057,7 +5059,7 @@ undo_action_next: goto add_allocated_vcns; vcn = le64_to_cpu(lrh->target_vcn); - vcn &= ~(log->clst_per_page - 1); + vcn &= ~(u64)(log->clst_per_page - 1); add_allocated_vcns: for (i = 0, vcn = le64_to_cpu(lrh->target_vcn), diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 1835e35199c2..4ed15f64b17f 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -703,12 +703,14 @@ out: /* * ntfs_mark_rec_free - Mark record as free. + * is_mft - true if we are changing MFT */ -void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno) +void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft) { struct wnd_bitmap *wnd = &sbi->mft.bitmap; - down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); + if (!is_mft) + down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); if (rno >= wnd->nbits) goto out; @@ -727,7 +729,8 @@ void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno) sbi->mft.next_free = rno; out: - up_write(&wnd->rw_lock); + if (!is_mft) + up_write(&wnd->rw_lock); } /* @@ -780,7 +783,7 @@ out: */ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) { - CLST zone_limit, zone_max, lcn, vcn, len; + CLST lcn, vcn, len; size_t lcn_s, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; struct ntfs_inode *ni = sbi->mft.ni; @@ -789,16 +792,6 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) if (wnd_zone_len(wnd)) return 0; - /* - * Compute the MFT zone at two steps. - * It would be nice if we are able to allocate 1/8 of - * total clusters for MFT but not more then 512 MB. - */ - zone_limit = (512 * 1024 * 1024) >> sbi->cluster_bits; - zone_max = wnd->nbits >> 3; - if (zone_max > zone_limit) - zone_max = zone_limit; - vcn = bytes_to_cluster(sbi, (u64)sbi->mft.bitmap.nbits << sbi->record_bits); @@ -812,13 +805,7 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) lcn_s = lcn + 1; /* Try to allocate clusters after last MFT run. */ - zlen = wnd_find(wnd, zone_max, lcn_s, 0, &lcn_s); - if (!zlen) { - ntfs_notice(sbi->sb, "MftZone: unavailable"); - return 0; - } - - /* Truncate too large zone. */ + zlen = wnd_find(wnd, sbi->zone_max, lcn_s, 0, &lcn_s); wnd_zone_set(wnd, lcn_s, zlen); return 0; @@ -827,16 +814,21 @@ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) /* * ntfs_update_mftmirr - Update $MFTMirr data. */ -int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) +void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) { int err; struct super_block *sb = sbi->sb; - u32 blocksize = sb->s_blocksize; + u32 blocksize; sector_t block1, block2; u32 bytes; + if (!sb) + return; + + blocksize = sb->s_blocksize; + if (!(sbi->flags & NTFS_FLAGS_MFTMIRR)) - return 0; + return; err = 0; bytes = sbi->mft.recs_mirr << sbi->record_bits; @@ -847,16 +839,13 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) struct buffer_head *bh1, *bh2; bh1 = sb_bread(sb, block1++); - if (!bh1) { - err = -EIO; - goto out; - } + if (!bh1) + return; bh2 = sb_getblk(sb, block2++); if (!bh2) { put_bh(bh1); - err = -EIO; - goto out; + return; } if (buffer_locked(bh2)) @@ -876,13 +865,24 @@ int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) put_bh(bh2); if (err) - goto out; + return; } sbi->flags &= ~NTFS_FLAGS_MFTMIRR; +} -out: - return err; +/* + * ntfs_bad_inode + * + * Marks inode as bad and marks fs as 'dirty' + */ +void ntfs_bad_inode(struct inode *inode, const char *hint) +{ + struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; + + ntfs_inode_err(inode, "%s", hint); + make_bad_inode(inode); + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); } /* @@ -1395,7 +1395,7 @@ int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr, if (buffer_locked(bh)) __wait_on_buffer(bh); - lock_buffer(nb->bh[idx]); + lock_buffer(bh); bh_data = bh->b_data + off; end_data = Add2Ptr(bh_data, op); @@ -2424,7 +2424,7 @@ static inline void ntfs_unmap_and_discard(struct ntfs_sb_info *sbi, CLST lcn, void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) { - CLST end, i; + CLST end, i, zone_len, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); @@ -2459,6 +2459,28 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) ntfs_unmap_and_discard(sbi, lcn, len); wnd_set_free(wnd, lcn, len); + /* append to MFT zone, if possible. */ + zone_len = wnd_zone_len(wnd); + zlen = min(zone_len + len, sbi->zone_max); + + if (zlen == zone_len) { + /* MFT zone already has maximum size. */ + } else if (!zone_len) { + /* Create MFT zone only if 'zlen' is large enough. */ + if (zlen == sbi->zone_max) + wnd_zone_set(wnd, lcn, zlen); + } else { + CLST zone_lcn = wnd_zone_bit(wnd); + + if (lcn + len == zone_lcn) { + /* Append into head MFT zone. */ + wnd_zone_set(wnd, lcn, zlen); + } else if (zone_lcn + zone_len == lcn) { + /* Append into tail MFT zone. */ + wnd_zone_set(wnd, zone_lcn, zlen); + } + } + out: up_write(&wnd->rw_lock); } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 6f81e3a49abf..440328147e7e 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1042,19 +1042,16 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni, { int err; struct NTFS_DE *e; - const struct INDEX_HDR *hdr; struct indx_node *node; if (!root) root = indx_get_root(&ni->dir, ni, NULL, NULL); if (!root) { - err = -EINVAL; - goto out; + /* Should not happen. */ + return -EINVAL; } - hdr = &root->ihdr; - /* Check cache. */ e = fnd->level ? fnd->de[fnd->level - 1] : fnd->root_de; if (e && !de_is_last(e) && @@ -1068,39 +1065,35 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni, fnd_clear(fnd); /* Lookup entry that is <= to the search value. */ - e = hdr_find_e(indx, hdr, key, key_len, ctx, diff); + e = hdr_find_e(indx, &root->ihdr, key, key_len, ctx, diff); if (!e) return -EINVAL; fnd->root_de = e; - err = 0; for (;;) { node = NULL; - if (*diff >= 0 || !de_has_vcn_ex(e)) { - *entry = e; - goto out; - } + if (*diff >= 0 || !de_has_vcn_ex(e)) + break; /* Read next level. */ err = indx_read(indx, ni, de_get_vbn(e), &node); if (err) - goto out; + return err; /* Lookup entry that is <= to the search value. */ e = hdr_find_e(indx, &node->index->ihdr, key, key_len, ctx, diff); if (!e) { - err = -EINVAL; put_indx_node(node); - goto out; + return -EINVAL; } fnd_push(fnd, node, e); } -out: - return err; + *entry = e; + return 0; } int indx_find_sort(struct ntfs_index *indx, struct ntfs_inode *ni, @@ -1354,7 +1347,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, goto out; err = ni_insert_nonresident(ni, ATTR_ALLOC, in->name, in->name_len, - &run, 0, len, 0, &alloc, NULL); + &run, 0, len, 0, &alloc, NULL, NULL); if (err) goto out1; @@ -1685,8 +1678,8 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, { int err; const struct NTFS_DE *sp; - struct NTFS_DE *e, *de_t, *up_e = NULL; - struct indx_node *n2 = NULL; + struct NTFS_DE *e, *de_t, *up_e; + struct indx_node *n2; struct indx_node *n1 = fnd->nodes[level]; struct INDEX_HDR *hdr1 = &n1->index->ihdr; struct INDEX_HDR *hdr2; @@ -1994,7 +1987,7 @@ static int indx_free_children(struct ntfs_index *indx, struct ntfs_inode *ni, const struct NTFS_DE *e, bool trim) { int err; - struct indx_node *n; + struct indx_node *n = NULL; struct INDEX_HDR *hdr; CLST vbn = de_get_vbn(e); size_t i; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 80104afeb2cd..51363d4e8636 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -430,6 +430,7 @@ end_enum: } else if (fname && fname->home.low == cpu_to_le32(MFT_REC_EXTEND) && fname->home.seq == cpu_to_le16(MFT_REC_EXTEND)) { /* Records in $Extend are not a files or general directories. */ + inode->i_op = &ntfs_file_inode_operations; } else { err = -EINVAL; goto out; @@ -500,7 +501,7 @@ struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, inode = ntfs_read_mft(inode, name, ref); else if (ref->seq != ntfs_i(inode)->mi.mrec->seq) { /* Inode overlaps? */ - make_bad_inode(inode); + _ntfs_bad_inode(inode); } return inode; @@ -1632,7 +1633,7 @@ out4: ni->mi.dirty = false; discard_new_inode(inode); out3: - ntfs_mark_rec_free(sbi, ino); + ntfs_mark_rec_free(sbi, ino, false); out2: __putname(new_de); @@ -1655,7 +1656,6 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry) struct ntfs_inode *ni = ntfs_i(inode); struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; struct NTFS_DE *de; - struct ATTR_FILE_NAME *de_name; /* Allocate PATH_MAX bytes. */ de = __getname(); @@ -1670,15 +1670,6 @@ int ntfs_link_inode(struct inode *inode, struct dentry *dentry) if (err) goto out; - de_name = (struct ATTR_FILE_NAME *)(de + 1); - /* Fill duplicate info. */ - de_name->dup.cr_time = de_name->dup.m_time = de_name->dup.c_time = - de_name->dup.a_time = kernel2nt(&inode->i_ctime); - de_name->dup.alloc_size = de_name->dup.data_size = - cpu_to_le64(inode->i_size); - de_name->dup.fa = ni->std_fa; - de_name->dup.ea_size = de_name->dup.reparse = 0; - err = ni_add_name(ntfs_i(d_inode(dentry->d_parent)), ni, de); out: __putname(de); @@ -1731,9 +1722,7 @@ int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry) if (inode->i_nlink) mark_inode_dirty(inode); } else if (!ni_remove_name_undo(dir_ni, ni, de, de2, undo_remove)) { - make_bad_inode(inode); - ntfs_inode_err(inode, "failed to undo unlink"); - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(inode); } else { if (ni_is_dirty(dir)) mark_inode_dirty(dir); diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index bc741213ad84..bc22cc321a74 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -208,7 +208,7 @@ static int ntfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, } /* - * ntfs_rmdir - inode_operations::rm_dir + * ntfs_rmdir - inode_operations::rmdir */ static int ntfs_rmdir(struct inode *dir, struct dentry *dentry) { @@ -308,9 +308,7 @@ static int ntfs_rename(struct user_namespace *mnt_userns, struct inode *dir, err = ni_rename(dir_ni, new_dir_ni, ni, de, new_de, &is_bad); if (is_bad) { /* Restore after failed rename failed too. */ - make_bad_inode(inode); - ntfs_inode_err(inode, "failed to undo rename"); - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(inode); } else if (!err) { inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(dir); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 8dbdca03e1af..2c791222c4e2 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -220,6 +220,7 @@ struct ntfs_sb_info { u32 flags; // See NTFS_FLAGS_XXX. + CLST zone_max; // Maximum MFT zone length in clusters CLST bad_clusters; // The count of marked bad clusters. u16 max_bytes_per_attr; // Maximum attribute size in record. @@ -408,8 +409,6 @@ enum REPARSE_SIGN { }; /* Functions from attrib.c */ -int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, - struct runs_tree *run, const CLST *vcn); int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, @@ -440,6 +439,7 @@ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr, int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, u64 new_valid); int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); +int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size); /* Functions from attrlist.c */ @@ -528,7 +528,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, const struct runs_tree *run, CLST svcn, CLST len, __le16 flags, struct ATTRIB **new_attr, - struct mft_inode **mi); + struct mft_inode **mi, struct ATTR_LIST_ENTRY **le); int ni_insert_resident(struct ntfs_inode *ni, u32 data_size, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct ATTRIB **new_attr, struct mft_inode **mi, @@ -589,10 +589,12 @@ int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len, enum ALLOCATE_OPT opt); int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, struct ntfs_inode *ni, struct mft_inode **mi); -void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno); +void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft); int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to); int ntfs_refresh_zone(struct ntfs_sb_info *sbi); -int ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait); +void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait); +void ntfs_bad_inode(struct inode *inode, const char *hint); +#define _ntfs_bad_inode(i) ntfs_bad_inode(i, __func__) enum NTFS_DIRTY_FLAGS { NTFS_DIRTY_CLEAR = 0, NTFS_DIRTY_DIRTY = 1, @@ -738,7 +740,6 @@ static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec, int mi_write(struct mft_inode *mi, int wait); int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, __le16 flags, bool is_mft); -void mi_mark_free(struct mft_inode *mi); struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, const __le16 *name, u8 name_len, u32 asize, u16 name_off); @@ -780,10 +781,10 @@ bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn, void run_truncate(struct runs_tree *run, CLST vcn); void run_truncate_head(struct runs_tree *run, CLST vcn); void run_truncate_around(struct runs_tree *run, CLST vcn); -bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *Index); bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len, bool is_mft); bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len); +bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len); bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn, CLST *lcn, CLST *len); bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn); @@ -802,6 +803,7 @@ int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, #define run_unpack_ex run_unpack #endif int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn); +int run_clone(const struct runs_tree *run, struct runs_tree *new_run); /* Globals from super.c */ void *ntfs_set_shared(void *ptr, u32 bytes); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 861e35791506..7d2fac5ee215 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -395,28 +395,6 @@ int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, } /* - * mi_mark_free - Mark record as unused and marks it as free in bitmap. - */ -void mi_mark_free(struct mft_inode *mi) -{ - CLST rno = mi->rno; - struct ntfs_sb_info *sbi = mi->sbi; - - if (rno >= MFT_REC_RESERVED && rno < MFT_REC_FREE) { - ntfs_clear_mft_tail(sbi, rno, rno + 1); - mi->dirty = false; - return; - } - - if (mi->mrec) { - clear_rec_inuse(mi->mrec); - mi->dirty = true; - mi_write(mi, 0); - } - ntfs_mark_rec_free(sbi, rno); -} - -/* * mi_insert_attr - Reserve space for new attribute. * * Return: Not full constructed attribute or NULL if not possible to create. @@ -445,12 +423,11 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, attr = NULL; while ((attr = mi_enum_attr(mi, attr))) { diff = compare_attr(attr, type, name, name_len, upcase); - if (diff > 0) - break; + if (diff < 0) continue; - if (!is_attr_indexed(attr)) + if (!diff && !is_attr_indexed(attr)) return NULL; break; } diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c index a8fec651f973..aaaa0d3d35a2 100644 --- a/fs/ntfs3/run.c +++ b/fs/ntfs3/run.c @@ -31,7 +31,7 @@ struct ntfs_run { * Case of entry missing from list 'index' will be set to * point to insertion position for the entry question. */ -bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index) +static bool run_lookup(const struct runs_tree *run, CLST vcn, size_t *index) { size_t min_idx, max_idx, mid_idx; struct ntfs_run *r; @@ -547,6 +547,48 @@ bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len) return true; } +/* run_insert_range + * + * Helper for attr_insert_range(), + * which is helper for fallocate(insert_range). + */ +bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len) +{ + size_t index; + struct ntfs_run *r, *e; + + if (WARN_ON(!run_lookup(run, vcn, &index))) + return false; /* Should never be here. */ + + e = run->runs + run->count; + r = run->runs + index; + + if (vcn > r->vcn) + r += 1; + + for (; r < e; r++) + r->vcn += len; + + r = run->runs + index; + + if (vcn > r->vcn) { + /* split fragment. */ + CLST len1 = vcn - r->vcn; + CLST len2 = r->len - len1; + CLST lcn2 = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len1); + + r->len = len1; + + if (!run_add_entry(run, vcn + len, lcn2, len2, false)) + return false; + } + + if (!run_add_entry(run, vcn, SPARSE_LCN, len, false)) + return false; + + return true; +} + /* * run_get_entry - Return index-th mapped region. */ @@ -778,26 +820,36 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, CLST next_vcn, vcn, lcn; CLST prev_lcn = 0; CLST evcn1 = svcn + len; + const struct ntfs_run *r, *r_end; int packed_size = 0; size_t i; - bool ok; s64 dlcn; int offset_size, size_size, tmp; - next_vcn = vcn = svcn; - *packed_vcns = 0; if (!len) goto out; - ok = run_lookup_entry(run, vcn, &lcn, &len, &i); + /* Check all required entries [svcn, encv1) available. */ + if (!run_lookup(run, svcn, &i)) + return -ENOENT; + + r_end = run->runs + run->count; + r = run->runs + i; - if (!ok) - goto error; + for (next_vcn = r->vcn + r->len; next_vcn < evcn1; + next_vcn = r->vcn + r->len) { + if (++r >= r_end || r->vcn != next_vcn) + return -ENOENT; + } - if (next_vcn != vcn) - goto error; + /* Repeat cycle above and pack runs. Assume no errors. */ + r = run->runs + i; + len = svcn - r->vcn; + vcn = svcn; + lcn = r->lcn == SPARSE_LCN ? SPARSE_LCN : (r->lcn + len); + len = r->len - len; for (;;) { next_vcn = vcn + len; @@ -846,12 +898,10 @@ int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, if (packed_size + 1 >= run_buf_size || next_vcn >= evcn1) goto out; - ok = run_get_entry(run, ++i, &vcn, &lcn, &len); - if (!ok) - goto error; - - if (next_vcn != vcn) - goto error; + r += 1; + vcn = r->vcn; + lcn = r->lcn; + len = r->len; } out: @@ -860,9 +910,6 @@ out: run_buf[0] = 0; return packed_size + 1; - -error: - return -EOPNOTSUPP; } /* @@ -1109,3 +1156,28 @@ int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn) *highest_vcn = vcn64 - 1; return 0; } + +/* + * run_clone + * + * Make a copy of run + */ +int run_clone(const struct runs_tree *run, struct runs_tree *new_run) +{ + size_t bytes = run->count * sizeof(struct ntfs_run); + + if (bytes > new_run->allocated) { + struct ntfs_run *new_ptr = kvmalloc(bytes, GFP_KERNEL); + + if (!new_ptr) + return -ENOMEM; + + kvfree(new_run->runs); + new_run->runs = new_ptr; + new_run->allocated = bytes; + } + + memcpy(new_run->runs, run->runs, bytes); + new_run->count = run->count; + return 0; +} diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 0c6de6287737..47012c9bf505 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -30,6 +30,7 @@ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/log2.h> +#include <linux/minmax.h> #include <linux/module.h> #include <linux/nls.h> #include <linux/seq_file.h> @@ -390,7 +391,7 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) return -EINVAL; } - memcpy(sbi->options, new_opts, sizeof(*new_opts)); + swap(sbi->options, fc->fs_private); return 0; } @@ -870,6 +871,13 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sb->s_maxbytes = 0xFFFFFFFFull << sbi->cluster_bits; #endif + /* + * Compute the MFT zone at two steps. + * It would be nice if we are able to allocate 1/8 of + * total clusters for MFT but not more then 512 MB. + */ + sbi->zone_max = min_t(CLST, 0x20000000 >> sbi->cluster_bits, clusters >> 3); + err = 0; out: @@ -900,6 +908,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.high = 0; sbi->sb = sb; + sbi->options = fc->fs_private; + fc->fs_private = NULL; sb->s_flags |= SB_NODIRATIME; sb->s_magic = 0x7366746e; // "ntfs" sb->s_op = &ntfs_sops; @@ -1262,8 +1272,6 @@ load_root: goto put_inode_out; } - fc->fs_private = NULL; - return 0; put_inode_out: @@ -1378,7 +1386,7 @@ static const struct fs_context_operations ntfs_context_ops = { /* * ntfs_init_fs_context - Initialize spi and opts * - * This will called when mount/remount. We will first initiliaze + * This will called when mount/remount. We will first initialize * options so that if remount we can use just that. */ static int ntfs_init_fs_context(struct fs_context *fc) @@ -1416,7 +1424,6 @@ static int ntfs_init_fs_context(struct fs_context *fc) mutex_init(&sbi->compress.mtx_lzx); #endif - sbi->options = opts; fc->s_fs_info = sbi; ok: fc->fs_private = opts; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 5e0e0280e70d..6ae1f56b7358 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -118,7 +118,7 @@ static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea, run_init(&run); - err = attr_load_runs(attr_ea, ni, &run, NULL); + err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &run, 0, size); if (!err) err = ntfs_read_run_nb(sbi, &run, 0, ea_p, size, NULL); run_close(&run); @@ -444,6 +444,11 @@ update_ea: /* Delete xattr, ATTR_EA */ ni_remove_attr_le(ni, attr, mi, le); } else if (attr->non_res) { + err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &ea_run, 0, + size); + if (err) + goto out; + err = ntfs_sb_write_run(sbi, &ea_run, 0, ea_all, size, 0); if (err) goto out; @@ -478,8 +483,7 @@ out: } #ifdef CONFIG_NTFS3_FS_POSIX_ACL -static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns, - struct inode *inode, int type, +static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type, int locked) { struct ntfs_inode *ni = ntfs_i(inode); @@ -514,7 +518,7 @@ static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns, /* Translate extended attribute to acl. */ if (err >= 0) { - acl = posix_acl_from_xattr(mnt_userns, buf, err); + acl = posix_acl_from_xattr(&init_user_ns, buf, err); } else if (err == -ENODATA) { acl = NULL; } else { @@ -537,8 +541,7 @@ struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu) if (rcu) return ERR_PTR(-ECHILD); - /* TODO: init_user_ns? */ - return ntfs_get_acl_ex(&init_user_ns, inode, type, 0); + return ntfs_get_acl_ex(inode, type, 0); } static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, @@ -547,28 +550,23 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, { const char *name; size_t size, name_len; - void *value = NULL; - int err = 0; + void *value; + int err; int flags; + umode_t mode; if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; + mode = inode->i_mode; switch (type) { case ACL_TYPE_ACCESS: /* Do not change i_mode if we are in init_acl */ if (acl && !init_acl) { - umode_t mode; - err = posix_acl_update_mode(mnt_userns, inode, &mode, &acl); if (err) - goto out; - - if (inode->i_mode != mode) { - inode->i_mode = mode; - mark_inode_dirty(inode); - } + return err; } name = XATTR_NAME_POSIX_ACL_ACCESS; name_len = sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1; @@ -595,7 +593,7 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, value = kmalloc(size, GFP_NOFS); if (!value) return -ENOMEM; - err = posix_acl_to_xattr(mnt_userns, acl, value, size); + err = posix_acl_to_xattr(&init_user_ns, acl, value, size); if (err < 0) goto out; flags = 0; @@ -604,8 +602,13 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns, err = ntfs_set_ea(inode, name, name_len, value, size, flags, 0); if (err == -ENODATA && !size) err = 0; /* Removing non existed xattr. */ - if (!err) + if (!err) { set_cached_acl(inode, type, acl); + if (inode->i_mode != mode) { + inode->i_mode = mode; + mark_inode_dirty(inode); + } + } out: kfree(value); @@ -641,7 +644,7 @@ static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns, if (!acl) return -ENODATA; - err = posix_acl_to_xattr(mnt_userns, acl, buffer, size); + err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return err; @@ -665,12 +668,12 @@ static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns, if (!value) { acl = NULL; } else { - acl = posix_acl_from_xattr(mnt_userns, value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { - err = posix_acl_valid(mnt_userns, acl); + err = posix_acl_valid(&init_user_ns, acl); if (err) goto release_and_out; } @@ -706,13 +709,13 @@ int ntfs_init_acl(struct user_namespace *mnt_userns, struct inode *inode, inode->i_default_acl = NULL; } - if (!acl) - inode->i_acl = NULL; - else { + if (acl) { if (!err) err = ntfs_set_acl_ex(mnt_userns, inode, acl, ACL_TYPE_ACCESS, true); posix_acl_release(acl); + } else { + inode->i_acl = NULL; } return err; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 801e60bab955..c28bc983a7b1 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3403,10 +3403,12 @@ void ocfs2_dlm_shutdown(struct ocfs2_super *osb, ocfs2_lock_res_free(&osb->osb_nfs_sync_lockres); ocfs2_lock_res_free(&osb->osb_orphan_scan.os_lockres); - ocfs2_cluster_disconnect(osb->cconn, hangup_pending); - osb->cconn = NULL; + if (osb->cconn) { + ocfs2_cluster_disconnect(osb->cconn, hangup_pending); + osb->cconn = NULL; - ocfs2_dlm_shutdown_debug(osb); + ocfs2_dlm_shutdown_debug(osb); + } } static int ocfs2_drop_lock(struct ocfs2_super *osb, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 013a727bd7c8..e2cc9eec287c 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1914,8 +1914,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) !ocfs2_is_hard_readonly(osb)) hangup_needed = 1; - if (osb->cconn) - ocfs2_dlm_shutdown(osb, hangup_needed); + ocfs2_dlm_shutdown(osb, hangup_needed); ocfs2_blockcheck_stats_debugfs_remove(&osb->osb_ecc_stats); debugfs_remove_recursive(osb->osb_debug_root); diff --git a/fs/open.c b/fs/open.c index 8a813fa5ca56..cf7e5c350a54 100644 --- a/fs/open.c +++ b/fs/open.c @@ -716,6 +716,8 @@ int chown_common(const struct path *path, uid_t user, gid_t group) fs_userns = i_user_ns(inode); retry_deleg: + newattrs.ia_vfsuid = INVALID_VFSUID; + newattrs.ia_vfsgid = INVALID_VFSGID; newattrs.ia_valid = ATTR_CTIME; if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid)) return -EINVAL; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b45fea69fff3..0fbcb590af84 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -460,9 +460,12 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) * of the POSIX ACLs retrieved from the lower layer to this function to not * alter the POSIX ACLs for the underlying filesystem. */ -static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns, +static void ovl_idmap_posix_acl(struct inode *realinode, + struct user_namespace *mnt_userns, struct posix_acl *acl) { + struct user_namespace *fs_userns = i_user_ns(realinode); + for (unsigned int i = 0; i < acl->a_count; i++) { vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -470,11 +473,11 @@ static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns, struct posix_acl_entry *e = &acl->a_entries[i]; switch (e->e_tag) { case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, e->e_uid); + vfsuid = make_vfsuid(mnt_userns, fs_userns, e->e_uid); e->e_uid = vfsuid_into_kuid(vfsuid); break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, e->e_gid); + vfsgid = make_vfsgid(mnt_userns, fs_userns, e->e_gid); e->e_gid = vfsgid_into_kgid(vfsgid); break; } @@ -536,7 +539,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) if (!clone) clone = ERR_PTR(-ENOMEM); else - ovl_idmap_posix_acl(mnt_user_ns(realpath.mnt), clone); + ovl_idmap_posix_acl(realinode, mnt_user_ns(realpath.mnt), clone); /* * Since we're not in RCU path walk we always need to release the * original ACLs. diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 1d17d7b13dcd..5af33800743e 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -361,6 +361,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; + struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -376,7 +377,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, goto check_perm; break; case ACL_USER: - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, + vfsuid = make_vfsuid(mnt_userns, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; @@ -390,7 +391,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, } break; case ACL_GROUP: - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, + vfsgid = make_vfsgid(mnt_userns, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; @@ -736,6 +737,7 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; + struct user_namespace *fs_userns = i_user_ns(inode); int count; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -753,13 +755,13 @@ void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns, switch (le16_to_cpu(entry->e_tag)) { case ACL_USER: uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); - vfsuid = make_vfsuid(mnt_userns, &init_user_ns, uid); + vfsuid = make_vfsuid(mnt_userns, fs_userns, uid); entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); - vfsgid = make_vfsgid(mnt_userns, &init_user_ns, gid); + vfsgid = make_vfsgid(mnt_userns, fs_userns, gid); entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, vfsgid_into_kgid(vfsgid))); break; @@ -775,6 +777,7 @@ void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns, { struct posix_acl_xattr_header *header = value; struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end; + struct user_namespace *fs_userns = i_user_ns(inode); int count; vfsuid_t vfsuid; vfsgid_t vfsgid; @@ -793,13 +796,13 @@ void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns, case ACL_USER: uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); vfsuid = VFSUIDT_INIT(uid); - uid = from_vfsuid(mnt_userns, &init_user_ns, vfsuid); + uid = from_vfsuid(mnt_userns, fs_userns, vfsuid); entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, uid)); break; case ACL_GROUP: gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); vfsgid = VFSGIDT_INIT(gid); - gid = from_vfsgid(mnt_userns, &init_user_ns, vfsgid); + gid = from_vfsgid(mnt_userns, fs_userns, vfsgid); entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, gid)); break; default: diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index a3398d0f1927..4e0023643f8b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -527,10 +527,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; - bool migration = false; + bool migration = false, young = false, dirty = false; if (pte_present(*pte)) { page = vm_normal_page(vma, addr, *pte); + young = pte_young(*pte); + dirty = pte_dirty(*pte); } else if (is_swap_pte(*pte)) { swp_entry_t swpent = pte_to_swp_entry(*pte); @@ -560,8 +562,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), - locked, migration); + smaps_account(mss, page, false, young, dirty, locked, migration); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index b2fd3c20e7c2..0c034ea39954 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -28,14 +28,11 @@ #include <linux/crypto.h> #include <linux/string.h> #include <linux/timer.h> -#include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/jiffies.h> #include <linux/workqueue.h> -#include <crypto/acompress.h> - #include "internal.h" /* @@ -93,8 +90,7 @@ module_param(compress, charp, 0444); MODULE_PARM_DESC(compress, "compression to use"); /* Compression parameters */ -static struct crypto_acomp *tfm; -static struct acomp_req *creq; +static struct crypto_comp *tfm; struct pstore_zbackend { int (*zbufsize)(size_t size); @@ -272,21 +268,12 @@ static const struct pstore_zbackend zbackends[] = { static int pstore_compress(const void *in, void *out, unsigned int inlen, unsigned int outlen) { - struct scatterlist src, dst; int ret; if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS)) return -EINVAL; - sg_init_table(&src, 1); - sg_set_buf(&src, in, inlen); - - sg_init_table(&dst, 1); - sg_set_buf(&dst, out, outlen); - - acomp_request_set_params(creq, &src, &dst, inlen, outlen); - - ret = crypto_acomp_compress(creq); + ret = crypto_comp_compress(tfm, in, inlen, out, &outlen); if (ret) { pr_err("crypto_comp_compress failed, ret = %d!\n", ret); return ret; @@ -297,7 +284,7 @@ static int pstore_compress(const void *in, void *out, static void allocate_buf_for_compression(void) { - struct crypto_acomp *acomp; + struct crypto_comp *ctx; int size; char *buf; @@ -309,7 +296,7 @@ static void allocate_buf_for_compression(void) if (!psinfo || tfm) return; - if (!crypto_has_acomp(zbackend->name, 0, CRYPTO_ALG_ASYNC)) { + if (!crypto_has_comp(zbackend->name, 0, 0)) { pr_err("Unknown compression: %s\n", zbackend->name); return; } @@ -328,24 +315,16 @@ static void allocate_buf_for_compression(void) return; } - acomp = crypto_alloc_acomp(zbackend->name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(acomp)) { + ctx = crypto_alloc_comp(zbackend->name, 0, 0); + if (IS_ERR_OR_NULL(ctx)) { kfree(buf); pr_err("crypto_alloc_comp('%s') failed: %ld\n", zbackend->name, - PTR_ERR(acomp)); - return; - } - - creq = acomp_request_alloc(acomp); - if (!creq) { - crypto_free_acomp(acomp); - kfree(buf); - pr_err("acomp_request_alloc('%s') failed\n", zbackend->name); + PTR_ERR(ctx)); return; } /* A non-NULL big_oops_buf indicates compression is available. */ - tfm = acomp; + tfm = ctx; big_oops_buf_sz = size; big_oops_buf = buf; @@ -355,8 +334,7 @@ static void allocate_buf_for_compression(void) static void free_buf_for_compression(void) { if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && tfm) { - acomp_request_free(creq); - crypto_free_acomp(tfm); + crypto_free_comp(tfm); tfm = NULL; } kfree(big_oops_buf); @@ -693,8 +671,6 @@ static void decompress_record(struct pstore_record *record) int ret; int unzipped_len; char *unzipped, *workspace; - struct acomp_req *dreq; - struct scatterlist src, dst; if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !record->compressed) return; @@ -718,30 +694,16 @@ static void decompress_record(struct pstore_record *record) if (!workspace) return; - dreq = acomp_request_alloc(tfm); - if (!dreq) { - kfree(workspace); - return; - } - - sg_init_table(&src, 1); - sg_set_buf(&src, record->buf, record->size); - - sg_init_table(&dst, 1); - sg_set_buf(&dst, workspace, unzipped_len); - - acomp_request_set_params(dreq, &src, &dst, record->size, unzipped_len); - /* After decompression "unzipped_len" is almost certainly smaller. */ - ret = crypto_acomp_decompress(dreq); + ret = crypto_comp_decompress(tfm, record->buf, record->size, + workspace, &unzipped_len); if (ret) { - pr_err("crypto_acomp_decompress failed, ret = %d!\n", ret); + pr_err("crypto_comp_decompress failed, ret = %d!\n", ret); kfree(workspace); return; } /* Append ECC notice to decompressed buffer. */ - unzipped_len = dreq->dlen; memcpy(workspace + unzipped_len, record->buf + record->size, record->ecc_notice_size); @@ -749,7 +711,6 @@ static void decompress_record(struct pstore_record *record) unzipped = kmemdup(workspace, unzipped_len + record->ecc_notice_size, GFP_KERNEL); kfree(workspace); - acomp_request_free(dreq); if (!unzipped) return; diff --git a/fs/read_write.c b/fs/read_write.c index 1a261dcf1778..328ce8cf9a85 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -496,14 +496,9 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t } /* caller is responsible for file_start_write/file_end_write */ -ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) +ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { - struct kvec iov = { - .iov_base = (void *)buf, - .iov_len = min_t(size_t, count, MAX_RW_COUNT), - }; struct kiocb kiocb; - struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) @@ -519,8 +514,7 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; - iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len); - ret = file->f_op->write_iter(&kiocb, &iter); + ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; @@ -530,6 +524,18 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t inc_syscw(current); return ret; } + +/* caller is responsible for file_start_write/file_end_write */ +ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) +{ + struct kvec iov = { + .iov_base = (void *)buf, + .iov_len = min_t(size_t, count, MAX_RW_COUNT), + }; + struct iov_iter iter; + iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len); + return __kernel_write_iter(file, &iter, pos); +} /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 98e64fec75b7..e56510964b22 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -593,7 +593,7 @@ static void squashfs_readahead(struct readahead_control *ractl) res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); - kfree(actor); + squashfs_page_actor_free(actor); if (res == expected) { int bytes; diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index be4b12d31e0c..f1ccad519e28 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -74,7 +74,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, /* Decompress directly into the page cache buffers */ res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); - kfree(actor); + squashfs_page_actor_free(actor); if (res < 0) goto mark_errored; diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c index b23b780d8f42..54b93bf4a25c 100644 --- a/fs/squashfs/page_actor.c +++ b/fs/squashfs/page_actor.c @@ -52,6 +52,7 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, actor->buffer = buffer; actor->pages = pages; actor->next_page = 0; + actor->tmp_buffer = NULL; actor->squashfs_first_page = cache_first_page; actor->squashfs_next_page = cache_next_page; actor->squashfs_finish_page = cache_finish_page; @@ -68,20 +69,9 @@ static void *handle_next_page(struct squashfs_page_actor *actor) if ((actor->next_page == actor->pages) || (actor->next_index != actor->page[actor->next_page]->index)) { - if (actor->alloc_buffer) { - void *tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); - - if (tmp_buffer) { - actor->tmp_buffer = tmp_buffer; - actor->next_index++; - actor->returned_pages++; - return tmp_buffer; - } - } - actor->next_index++; actor->returned_pages++; - return ERR_PTR(-ENOMEM); + return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM); } actor->next_index++; @@ -96,11 +86,10 @@ static void *direct_first_page(struct squashfs_page_actor *actor) static void *direct_next_page(struct squashfs_page_actor *actor) { - if (actor->pageaddr) + if (actor->pageaddr) { kunmap_local(actor->pageaddr); - - kfree(actor->tmp_buffer); - actor->pageaddr = actor->tmp_buffer = NULL; + actor->pageaddr = NULL; + } return handle_next_page(actor); } @@ -109,8 +98,6 @@ static void direct_finish_page(struct squashfs_page_actor *actor) { if (actor->pageaddr) kunmap_local(actor->pageaddr); - - kfree(actor->tmp_buffer); } struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk, @@ -121,6 +108,16 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_ if (actor == NULL) return NULL; + if (msblk->decompressor->alloc_buffer) { + actor->tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); + + if (actor->tmp_buffer == NULL) { + kfree(actor); + return NULL; + } + } else + actor->tmp_buffer = NULL; + actor->length = length ? : pages * PAGE_SIZE; actor->page = page; actor->pages = pages; @@ -128,7 +125,6 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_ actor->returned_pages = 0; actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1); actor->pageaddr = NULL; - actor->tmp_buffer = NULL; actor->alloc_buffer = msblk->decompressor->alloc_buffer; actor->squashfs_first_page = direct_first_page; actor->squashfs_next_page = direct_next_page; diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h index 24841d28bc0f..95ffbb543d91 100644 --- a/fs/squashfs/page_actor.h +++ b/fs/squashfs/page_actor.h @@ -29,6 +29,11 @@ extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, extern struct squashfs_page_actor *squashfs_page_actor_init_special( struct squashfs_sb_info *msblk, struct page **page, int pages, int length); +static inline void squashfs_page_actor_free(struct squashfs_page_actor *actor) +{ + kfree(actor->tmp_buffer); + kfree(actor); +} static inline void *squashfs_first_page(struct squashfs_page_actor *actor) { return actor->squashfs_first_page(actor); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 81d26abf486f..da85b3979195 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -141,6 +141,8 @@ struct tracefs_mount_opts { kuid_t uid; kgid_t gid; umode_t mode; + /* Opt_* bitfield. */ + unsigned int opts; }; enum { @@ -241,6 +243,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) kgid_t gid; char *p; + opts->opts = 0; opts->mode = TRACEFS_DEFAULT_MODE; while ((p = strsep(&data, ",")) != NULL) { @@ -275,24 +278,36 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) * but traditionally tracefs has ignored all mount options */ } + + opts->opts |= BIT(token); } return 0; } -static int tracefs_apply_options(struct super_block *sb) +static int tracefs_apply_options(struct super_block *sb, bool remount) { struct tracefs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); struct tracefs_mount_opts *opts = &fsi->mount_opts; - inode->i_mode &= ~S_IALLUGO; - inode->i_mode |= opts->mode; + /* + * On remount, only reset mode/uid/gid if they were provided as mount + * options. + */ + + if (!remount || opts->opts & BIT(Opt_mode)) { + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= opts->mode; + } - inode->i_uid = opts->uid; + if (!remount || opts->opts & BIT(Opt_uid)) + inode->i_uid = opts->uid; - /* Set all the group ids to the mount option */ - set_gid(sb->s_root, opts->gid); + if (!remount || opts->opts & BIT(Opt_gid)) { + /* Set all the group ids to the mount option */ + set_gid(sb->s_root, opts->gid); + } return 0; } @@ -307,7 +322,7 @@ static int tracefs_remount(struct super_block *sb, int *flags, char *data) if (err) goto fail; - tracefs_apply_options(sb); + tracefs_apply_options(sb, true); fail: return err; @@ -359,7 +374,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &tracefs_super_operations; - tracefs_apply_options(sb); + tracefs_apply_options(sb, false); return 0; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index e6ffe7bc59e3..0c1d33c4f74c 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1601,6 +1601,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } + /* Reset ptes for the whole vma range if wr-protected */ + if (userfaultfd_wp(vma)) + uffd_wp_range(mm, vma, start, vma_end - start, false); + new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 69d9c83ea4b2..5b1f9a24ed59 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -175,13 +175,13 @@ xfs_dax_notify_failure( u64 ddev_start; u64 ddev_end; - if (!(mp->m_sb.sb_flags & SB_BORN)) { + if (!(mp->m_super->s_flags & SB_BORN)) { xfs_warn(mp, "filesystem is not ready for notify_failure()!"); return -EIO; } if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { - xfs_warn(mp, + xfs_debug(mp, "notify_failure() not supported on realtime device!"); return -EOPNOTSUPP; } @@ -194,7 +194,7 @@ xfs_dax_notify_failure( } if (!xfs_has_rmapbt(mp)) { - xfs_warn(mp, "notify_failure() needs rmapbt enabled!"); + xfs_debug(mp, "notify_failure() needs rmapbt enabled!"); return -EOPNOTSUPP; } |