diff options
Diffstat (limited to 'fs')
113 files changed, 2431 insertions, 1200 deletions
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index e95d1b64082c..022574202749 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -33,7 +33,7 @@ config ARCH_BINFMT_ELF_RANDOMIZE_PIE config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y - depends on (FRV || BLACKFIN || (SUPERH32 && !MMU)) + depends on (FRV || BLACKFIN || (SUPERH32 && !MMU) || C6X) help ELF FDPIC binaries are based on ELF, but allow the individual load segments of a binary to be located in memory independently of each @@ -93,9 +93,8 @@ static void aio_free_ring(struct kioctx *ctx) put_page(info->ring_pages[i]); if (info->mmap_size) { - down_write(&ctx->mm->mmap_sem); - do_munmap(ctx->mm, info->mmap_base, info->mmap_size); - up_write(&ctx->mm->mmap_sem); + BUG_ON(ctx->mm != current->mm); + vm_munmap(info->mmap_base, info->mmap_size); } if (info->ring_pages && info->ring_pages != info->internal_pages) @@ -389,6 +388,17 @@ void exit_aio(struct mm_struct *mm) "exit_aio:ioctx still alive: %d %d %d\n", atomic_read(&ctx->users), ctx->dead, ctx->reqs_active); + /* + * We don't need to bother with munmap() here - + * exit_mmap(mm) is coming and it'll unmap everything. + * Since aio_free_ring() uses non-zero ->mmap_size + * as indicator that it needs to unmap the area, + * just set it to 0; aio_free_ring() is the only + * place that uses ->mmap_size, so it's safe. + * That way we get all munmap done to current->mm - + * all other callers have ctx->mm == current->mm. + */ + ctx->ring_info.mmap_size = 0; put_ioctx(ctx); } } @@ -1446,6 +1456,10 @@ static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat) if (ret < 0) goto out; + ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret); + if (ret < 0) + goto out; + kiocb->ki_nr_segs = kiocb->ki_nbytes; kiocb->ki_cur_seg = 0; /* ki_nbytes/left now reflect bytes instead of segs */ @@ -1457,11 +1471,17 @@ out: return ret; } -static ssize_t aio_setup_single_vector(struct kiocb *kiocb) +static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb) { + int bytes; + + bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left); + if (bytes < 0) + return bytes; + kiocb->ki_iovec = &kiocb->ki_inline_vec; kiocb->ki_iovec->iov_base = kiocb->ki_buf; - kiocb->ki_iovec->iov_len = kiocb->ki_left; + kiocb->ki_iovec->iov_len = bytes; kiocb->ki_nr_segs = 1; kiocb->ki_cur_seg = 0; return 0; @@ -1486,10 +1506,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf, kiocb->ki_left))) break; - ret = security_file_permission(file, MAY_READ); - if (unlikely(ret)) - break; - ret = aio_setup_single_vector(kiocb); + ret = aio_setup_single_vector(READ, file, kiocb); if (ret) break; ret = -EINVAL; @@ -1504,10 +1521,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf, kiocb->ki_left))) break; - ret = security_file_permission(file, MAY_WRITE); - if (unlikely(ret)) - break; - ret = aio_setup_single_vector(kiocb); + ret = aio_setup_single_vector(WRITE, file, kiocb); if (ret) break; ret = -EINVAL; @@ -1518,9 +1532,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_READ))) break; - ret = security_file_permission(file, MAY_READ); - if (unlikely(ret)) - break; ret = aio_setup_vectored_rw(READ, kiocb, compat); if (ret) break; @@ -1532,9 +1543,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_WRITE))) break; - ret = security_file_permission(file, MAY_WRITE); - if (unlikely(ret)) - break; ret = aio_setup_vectored_rw(WRITE, kiocb, compat); if (ret) break; diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index eb1cc92cd67d..908e18455413 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -110,7 +110,6 @@ struct autofs_sb_info { int sub_version; int min_proto; int max_proto; - int compat_daemon; unsigned long exp_timeout; unsigned int type; int reghost_enabled; @@ -270,6 +269,17 @@ int autofs4_fill_super(struct super_block *, void *, int); struct autofs_info *autofs4_new_ino(struct autofs_sb_info *); void autofs4_clean_ino(struct autofs_info *); +static inline int autofs_prepare_pipe(struct file *pipe) +{ + if (!pipe->f_op || !pipe->f_op->write) + return -EINVAL; + if (!S_ISFIFO(pipe->f_dentry->d_inode->i_mode)) + return -EINVAL; + /* We want a packet pipe */ + pipe->f_flags |= O_DIRECT; + return 0; +} + /* Queue management functions */ int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 9dacb8586701..aa9103f8f01b 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -376,7 +376,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp, err = -EBADF; goto out; } - if (!pipe->f_op || !pipe->f_op->write) { + if (autofs_prepare_pipe(pipe) < 0) { err = -EPIPE; fput(pipe); goto out; @@ -385,7 +385,6 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp, sbi->pipefd = pipefd; sbi->pipe = pipe; sbi->catatonic = 0; - sbi->compat_daemon = is_compat_task(); } out: mutex_unlock(&sbi->wq_mutex); diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index d8dc002e9cc3..6e488ebe7784 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -19,7 +19,6 @@ #include <linux/parser.h> #include <linux/bitops.h> #include <linux/magic.h> -#include <linux/compat.h> #include "autofs_i.h" #include <linux/module.h> @@ -225,7 +224,6 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) set_autofs_type_indirect(&sbi->type); sbi->min_proto = 0; sbi->max_proto = 0; - sbi->compat_daemon = is_compat_task(); mutex_init(&sbi->wq_mutex); mutex_init(&sbi->pipe_mutex); spin_lock_init(&sbi->fs_lock); @@ -292,7 +290,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) printk("autofs: could not open pipe file descriptor\n"); goto fail_dput; } - if (!pipe->f_op || !pipe->f_op->write) + if (autofs_prepare_pipe(pipe) < 0) goto fail_fput; sbi->pipe = pipe; sbi->pipefd = pipefd; diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 9c098db43344..da8876d38a7b 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -91,24 +91,7 @@ static int autofs4_write(struct autofs_sb_info *sbi, return (bytes > 0); } - -/* - * The autofs_v5 packet was misdesigned. - * - * The packets are identical on x86-32 and x86-64, but have different - * alignment. Which means that 'sizeof()' will give different results. - * Fix it up for the case of running 32-bit user mode on a 64-bit kernel. - */ -static noinline size_t autofs_v5_packet_size(struct autofs_sb_info *sbi) -{ - size_t pktsz = sizeof(struct autofs_v5_packet); -#if defined(CONFIG_X86_64) && defined(CONFIG_COMPAT) - if (sbi->compat_daemon > 0) - pktsz -= 4; -#endif - return pktsz; -} - + static void autofs4_notify_daemon(struct autofs_sb_info *sbi, struct autofs_wait_queue *wq, int type) @@ -172,7 +155,8 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, { struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet; - pktsz = autofs_v5_packet_size(sbi); + pktsz = sizeof(*packet); + packet->wait_queue_token = wq->wait_queue_token; packet->len = wq->name.len; memcpy(packet->name, wq->name.name, wq->name.len); diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 2eb12f13593d..d146e181d10d 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -50,9 +50,7 @@ static int set_brk(unsigned long start, unsigned long end) end = PAGE_ALIGN(end); if (end > start) { unsigned long addr; - down_write(¤t->mm->mmap_sem); - addr = do_brk(start, end - start); - up_write(¤t->mm->mmap_sem); + addr = vm_brk(start, end - start); if (BAD_ADDR(addr)) return addr; } @@ -280,9 +278,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) pos = 32; map_size = ex.a_text+ex.a_data; #endif - down_write(¤t->mm->mmap_sem); - error = do_brk(text_addr & PAGE_MASK, map_size); - up_write(¤t->mm->mmap_sem); + error = vm_brk(text_addr & PAGE_MASK, map_size); if (error != (text_addr & PAGE_MASK)) { send_sig(SIGKILL, current, 0); return error; @@ -313,9 +309,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) { loff_t pos = fd_offset; - down_write(¤t->mm->mmap_sem); - do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); - up_write(¤t->mm->mmap_sem); + vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); bprm->file->f_op->read(bprm->file, (char __user *)N_TXTADDR(ex), ex.a_text+ex.a_data, &pos); @@ -325,24 +319,20 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) goto beyond_if; } - down_write(¤t->mm->mmap_sem); - error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, + error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE, fd_offset); - up_write(¤t->mm->mmap_sem); if (error != N_TXTADDR(ex)) { send_sig(SIGKILL, current, 0); return error; } - down_write(¤t->mm->mmap_sem); - error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data, + error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE, fd_offset + ex.a_text); - up_write(¤t->mm->mmap_sem); if (error != N_DATADDR(ex)) { send_sig(SIGKILL, current, 0); return error; @@ -412,9 +402,7 @@ static int load_aout_library(struct file *file) "N_TXTOFF is not page aligned. Please convert library: %s\n", file->f_path.dentry->d_name.name); } - down_write(¤t->mm->mmap_sem); - do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); - up_write(¤t->mm->mmap_sem); + vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); file->f_op->read(file, (char __user *)start_addr, ex.a_text + ex.a_data, &pos); @@ -425,12 +413,10 @@ static int load_aout_library(struct file *file) goto out; } /* Now use mmap to map the library into memory. */ - down_write(¤t->mm->mmap_sem); - error = do_mmap(file, start_addr, ex.a_text + ex.a_data, + error = vm_mmap(file, start_addr, ex.a_text + ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE, N_TXTOFF(ex)); - up_write(¤t->mm->mmap_sem); retval = error; if (error != start_addr) goto out; @@ -438,9 +424,7 @@ static int load_aout_library(struct file *file) len = PAGE_ALIGN(ex.a_text + ex.a_data); bss = ex.a_text + ex.a_data + ex.a_bss; if (bss > len) { - down_write(¤t->mm->mmap_sem); - error = do_brk(start_addr + len, bss - len); - up_write(¤t->mm->mmap_sem); + error = vm_brk(start_addr + len, bss - len); retval = error; if (error != start_addr + len) goto out; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 48ffb3dc610a..16f735417072 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -82,9 +82,7 @@ static int set_brk(unsigned long start, unsigned long end) end = ELF_PAGEALIGN(end); if (end > start) { unsigned long addr; - down_write(¤t->mm->mmap_sem); - addr = do_brk(start, end - start); - up_write(¤t->mm->mmap_sem); + addr = vm_brk(start, end - start); if (BAD_ADDR(addr)) return addr; } @@ -514,9 +512,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1); /* Map the last of the bss segment */ - down_write(¤t->mm->mmap_sem); - error = do_brk(elf_bss, last_bss - elf_bss); - up_write(¤t->mm->mmap_sem); + error = vm_brk(elf_bss, last_bss - elf_bss); if (BAD_ADDR(error)) goto out_close; } @@ -962,10 +958,8 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) and some applications "depend" upon this behavior. Since we do not have the power to recompile these, we emulate the SVr4 behavior. Sigh. */ - down_write(¤t->mm->mmap_sem); - error = do_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC, + error = vm_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE, 0); - up_write(¤t->mm->mmap_sem); } #ifdef ELF_PLAT_INIT @@ -1050,8 +1044,7 @@ static int load_elf_library(struct file *file) eppnt++; /* Now use mmap to map the library into memory. */ - down_write(¤t->mm->mmap_sem); - error = do_mmap(file, + error = vm_mmap(file, ELF_PAGESTART(eppnt->p_vaddr), (eppnt->p_filesz + ELF_PAGEOFFSET(eppnt->p_vaddr)), @@ -1059,7 +1052,6 @@ static int load_elf_library(struct file *file) MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE, (eppnt->p_offset - ELF_PAGEOFFSET(eppnt->p_vaddr))); - up_write(¤t->mm->mmap_sem); if (error != ELF_PAGESTART(eppnt->p_vaddr)) goto out_free_ph; @@ -1072,11 +1064,8 @@ static int load_elf_library(struct file *file) len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr + ELF_MIN_ALIGN - 1); bss = eppnt->p_memsz + eppnt->p_vaddr; - if (bss > len) { - down_write(¤t->mm->mmap_sem); - do_brk(len, bss - len); - up_write(¤t->mm->mmap_sem); - } + if (bss > len) + vm_brk(len, bss - len); error = 0; out_free_ph: diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 9bd5612a8224..d390a0fffc65 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -390,21 +390,17 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, (executable_stack == EXSTACK_DEFAULT && VM_STACK_FLAGS & VM_EXEC)) stack_prot |= PROT_EXEC; - down_write(¤t->mm->mmap_sem); - current->mm->start_brk = do_mmap(NULL, 0, stack_size, stack_prot, + current->mm->start_brk = vm_mmap(NULL, 0, stack_size, stack_prot, MAP_PRIVATE | MAP_ANONYMOUS | MAP_UNINITIALIZED | MAP_GROWSDOWN, 0); if (IS_ERR_VALUE(current->mm->start_brk)) { - up_write(¤t->mm->mmap_sem); retval = current->mm->start_brk; current->mm->start_brk = 0; goto error_kill; } - up_write(¤t->mm->mmap_sem); - current->mm->brk = current->mm->start_brk; current->mm->context.end_brk = current->mm->start_brk; current->mm->context.end_brk += @@ -955,10 +951,8 @@ static int elf_fdpic_map_file_constdisp_on_uclinux( if (params->flags & ELF_FDPIC_FLAG_EXECUTABLE) mflags |= MAP_EXECUTABLE; - down_write(&mm->mmap_sem); - maddr = do_mmap(NULL, load_addr, top - base, + maddr = vm_mmap(NULL, load_addr, top - base, PROT_READ | PROT_WRITE | PROT_EXEC, mflags, 0); - up_write(&mm->mmap_sem); if (IS_ERR_VALUE(maddr)) return (int) maddr; @@ -1096,10 +1090,8 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, /* create the mapping */ disp = phdr->p_vaddr & ~PAGE_MASK; - down_write(&mm->mmap_sem); - maddr = do_mmap(file, maddr, phdr->p_memsz + disp, prot, flags, + maddr = vm_mmap(file, maddr, phdr->p_memsz + disp, prot, flags, phdr->p_offset - disp); - up_write(&mm->mmap_sem); kdebug("mmap[%d] <file> sz=%lx pr=%x fl=%x of=%lx --> %08lx", loop, phdr->p_memsz + disp, prot, flags, @@ -1143,10 +1135,8 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, unsigned long xmaddr; flags |= MAP_FIXED | MAP_ANONYMOUS; - down_write(&mm->mmap_sem); - xmaddr = do_mmap(NULL, xaddr, excess - excess1, + xmaddr = vm_mmap(NULL, xaddr, excess - excess1, prot, flags, 0); - up_write(&mm->mmap_sem); kdebug("mmap[%d] <anon>" " ad=%lx sz=%lx pr=%x fl=%x of=0 --> %08lx", diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 024d20ee3ca3..6b2daf99fab8 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -542,10 +542,8 @@ static int load_flat_file(struct linux_binprm * bprm, */ DBG_FLT("BINFMT_FLAT: ROM mapping of file (we hope)\n"); - down_write(¤t->mm->mmap_sem); - textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, + textpos = vm_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_EXECUTABLE, 0); - up_write(¤t->mm->mmap_sem); if (!textpos || IS_ERR_VALUE(textpos)) { if (!textpos) textpos = (unsigned long) -ENOMEM; @@ -556,10 +554,8 @@ static int load_flat_file(struct linux_binprm * bprm, len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long); len = PAGE_ALIGN(len); - down_write(¤t->mm->mmap_sem); - realdatastart = do_mmap(0, 0, len, + realdatastart = vm_mmap(0, 0, len, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0); - up_write(¤t->mm->mmap_sem); if (realdatastart == 0 || IS_ERR_VALUE(realdatastart)) { if (!realdatastart) @@ -603,10 +599,8 @@ static int load_flat_file(struct linux_binprm * bprm, len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long); len = PAGE_ALIGN(len); - down_write(¤t->mm->mmap_sem); - textpos = do_mmap(0, 0, len, + textpos = vm_mmap(0, 0, len, PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0); - up_write(¤t->mm->mmap_sem); if (!textpos || IS_ERR_VALUE(textpos)) { if (!textpos) diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c index e4fc746629a7..4517aaff61b4 100644 --- a/fs/binfmt_som.c +++ b/fs/binfmt_som.c @@ -147,10 +147,8 @@ static int map_som_binary(struct file *file, code_size = SOM_PAGEALIGN(hpuxhdr->exec_tsize); current->mm->start_code = code_start; current->mm->end_code = code_start + code_size; - down_write(¤t->mm->mmap_sem); - retval = do_mmap(file, code_start, code_size, prot, + retval = vm_mmap(file, code_start, code_size, prot, flags, SOM_PAGESTART(hpuxhdr->exec_tfile)); - up_write(¤t->mm->mmap_sem); if (retval < 0 && retval > -1024) goto out; @@ -158,20 +156,16 @@ static int map_som_binary(struct file *file, data_size = SOM_PAGEALIGN(hpuxhdr->exec_dsize); current->mm->start_data = data_start; current->mm->end_data = bss_start = data_start + data_size; - down_write(¤t->mm->mmap_sem); - retval = do_mmap(file, data_start, data_size, + retval = vm_mmap(file, data_start, data_size, prot | PROT_WRITE, flags, SOM_PAGESTART(hpuxhdr->exec_dfile)); - up_write(¤t->mm->mmap_sem); if (retval < 0 && retval > -1024) goto out; som_brk = bss_start + SOM_PAGEALIGN(hpuxhdr->exec_bsize); current->mm->start_brk = current->mm->brk = som_brk; - down_write(¤t->mm->mmap_sem); - retval = do_mmap(NULL, bss_start, som_brk - bss_start, + retval = vm_mmap(NULL, bss_start, som_brk - bss_start, prot | PROT_WRITE, MAP_FIXED | MAP_PRIVATE, 0); - up_write(¤t->mm->mmap_sem); if (retval > 0 || retval < -1024) retval = 0; out: @@ -505,9 +505,14 @@ EXPORT_SYMBOL(bio_clone); int bio_get_nr_vecs(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - return min_t(unsigned, + int nr_pages; + + nr_pages = min_t(unsigned, queue_max_segments(q), queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1); + + return min_t(unsigned, nr_pages, BIO_MAX_PAGES); + } EXPORT_SYMBOL(bio_get_nr_vecs); diff --git a/fs/block_dev.c b/fs/block_dev.c index e08f6a20a5bb..ba11c30f302d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -70,7 +70,7 @@ static void bdev_inode_switch_bdi(struct inode *inode, spin_unlock(&dst->wb.list_lock); } -static sector_t max_block(struct block_device *bdev) +sector_t blkdev_max_block(struct block_device *bdev) { sector_t retval = ~((sector_t)0); loff_t sz = i_size_read(bdev->bd_inode); @@ -163,7 +163,7 @@ static int blkdev_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { - if (iblock >= max_block(I_BDEV(inode))) { + if (iblock >= blkdev_max_block(I_BDEV(inode))) { if (create) return -EIO; @@ -185,7 +185,7 @@ static int blkdev_get_blocks(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { - sector_t end_block = max_block(I_BDEV(inode)); + sector_t end_block = blkdev_max_block(I_BDEV(inode)); unsigned long max_blocks = bh->b_size >> inode->i_blkbits; if ((iblock + max_blocks) > end_block) { diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index f4e90748940a..bcec06750232 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -22,6 +22,7 @@ #include "ulist.h" #include "transaction.h" #include "delayed-ref.h" +#include "locking.h" /* * this structure records all encountered refs on the way up to the root @@ -893,18 +894,22 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, s64 bytes_left = size - 1; struct extent_buffer *eb = eb_in; struct btrfs_key found_key; + int leave_spinning = path->leave_spinning; if (bytes_left >= 0) dest[bytes_left] = '\0'; + path->leave_spinning = 1; while (1) { len = btrfs_inode_ref_name_len(eb, iref); bytes_left -= len; if (bytes_left >= 0) read_extent_buffer(eb, dest + bytes_left, (unsigned long)(iref + 1), len); - if (eb != eb_in) + if (eb != eb_in) { + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); + } ret = inode_ref_info(parent, 0, fs_root, path, &found_key); if (ret > 0) ret = -ENOENT; @@ -919,8 +924,11 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, slot = path->slots[0]; eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ - if (eb != eb_in) + if (eb != eb_in) { atomic_inc(&eb->refs); + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); @@ -931,6 +939,7 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, } btrfs_release_path(path); + path->leave_spinning = leave_spinning; if (ret) return ERR_PTR(ret); @@ -1247,7 +1256,7 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, struct btrfs_path *path, iterate_irefs_t *iterate, void *ctx) { - int ret; + int ret = 0; int slot; u32 cur; u32 len; @@ -1259,7 +1268,8 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, struct btrfs_inode_ref *iref; struct btrfs_key found_key; - while (1) { + while (!ret) { + path->leave_spinning = 1; ret = inode_ref_info(inum, parent ? parent+1 : 0, fs_root, path, &found_key); if (ret < 0) @@ -1275,6 +1285,8 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ atomic_inc(&eb->refs); + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); btrfs_release_path(path); item = btrfs_item_nr(eb, slot); @@ -1288,13 +1300,12 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, (unsigned long long)found_key.objectid, (unsigned long long)fs_root->objectid); ret = iterate(parent, iref, eb, ctx); - if (ret) { - free_extent_buffer(eb); + if (ret) break; - } len = sizeof(*iref) + name_len; iref = (struct btrfs_inode_ref *)((char *)iref + len); } + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); } @@ -1414,6 +1425,8 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root, void free_ipath(struct inode_fs_paths *ipath) { + if (!ipath) + return; kfree(ipath->fspath); kfree(ipath); } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index e801f226d7e0..4106264fbc65 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -220,10 +220,12 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root) */ static void add_root_to_dirty_list(struct btrfs_root *root) { + spin_lock(&root->fs_info->trans_lock); if (root->track_dirty && list_empty(&root->dirty_list)) { list_add(&root->dirty_list, &root->fs_info->dirty_cowonly_roots); } + spin_unlock(&root->fs_info->trans_lock); } /* @@ -723,7 +725,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, cur = btrfs_find_tree_block(root, blocknr, blocksize); if (cur) - uptodate = btrfs_buffer_uptodate(cur, gen); + uptodate = btrfs_buffer_uptodate(cur, gen, 0); else uptodate = 0; if (!cur || !uptodate) { @@ -1358,7 +1360,12 @@ static noinline int reada_for_balance(struct btrfs_root *root, block1 = btrfs_node_blockptr(parent, slot - 1); gen = btrfs_node_ptr_generation(parent, slot - 1); eb = btrfs_find_tree_block(root, block1, blocksize); - if (eb && btrfs_buffer_uptodate(eb, gen)) + /* + * if we get -eagain from btrfs_buffer_uptodate, we + * don't want to return eagain here. That will loop + * forever + */ + if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0) block1 = 0; free_extent_buffer(eb); } @@ -1366,7 +1373,7 @@ static noinline int reada_for_balance(struct btrfs_root *root, block2 = btrfs_node_blockptr(parent, slot + 1); gen = btrfs_node_ptr_generation(parent, slot + 1); eb = btrfs_find_tree_block(root, block2, blocksize); - if (eb && btrfs_buffer_uptodate(eb, gen)) + if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0) block2 = 0; free_extent_buffer(eb); } @@ -1504,8 +1511,9 @@ read_block_for_search(struct btrfs_trans_handle *trans, tmp = btrfs_find_tree_block(root, blocknr, blocksize); if (tmp) { - if (btrfs_buffer_uptodate(tmp, 0)) { - if (btrfs_buffer_uptodate(tmp, gen)) { + /* first we do an atomic uptodate check */ + if (btrfs_buffer_uptodate(tmp, 0, 1) > 0) { + if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) { /* * we found an up to date block without * sleeping, return @@ -1523,8 +1531,9 @@ read_block_for_search(struct btrfs_trans_handle *trans, free_extent_buffer(tmp); btrfs_set_path_blocking(p); + /* now we're allowed to do a blocking uptodate check */ tmp = read_tree_block(root, blocknr, blocksize, gen); - if (tmp && btrfs_buffer_uptodate(tmp, gen)) { + if (tmp && btrfs_buffer_uptodate(tmp, gen, 0) > 0) { *eb_ret = tmp; return 0; } @@ -1559,7 +1568,7 @@ read_block_for_search(struct btrfs_trans_handle *trans, * and give up so that our caller doesn't loop forever * on our EAGAINs. */ - if (!btrfs_buffer_uptodate(tmp, 0)) + if (!btrfs_buffer_uptodate(tmp, 0, 0)) ret = -EIO; free_extent_buffer(tmp); } @@ -4043,7 +4052,7 @@ again: tmp = btrfs_find_tree_block(root, blockptr, btrfs_level_size(root, level - 1)); - if (tmp && btrfs_buffer_uptodate(tmp, gen)) { + if (tmp && btrfs_buffer_uptodate(tmp, gen, 1) > 0) { free_extent_buffer(tmp); break; } @@ -4166,7 +4175,8 @@ next: struct extent_buffer *cur; cur = btrfs_find_tree_block(root, blockptr, btrfs_level_size(root, level - 1)); - if (!cur || !btrfs_buffer_uptodate(cur, gen)) { + if (!cur || + btrfs_buffer_uptodate(cur, gen, 1) <= 0) { slot++; if (cur) free_extent_buffer(cur); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3f65a812e282..8fd72331d600 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1078,7 +1078,7 @@ struct btrfs_fs_info { * is required instead of the faster short fsync log commits */ u64 last_trans_log_full_commit; - unsigned long mount_opt:21; + unsigned long mount_opt; unsigned long compress_type:4; u64 max_inline; u64 alloc_start; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 20196f411206..a7ffc88a7dbe 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -323,7 +323,8 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, * in the wrong place. */ static int verify_parent_transid(struct extent_io_tree *io_tree, - struct extent_buffer *eb, u64 parent_transid) + struct extent_buffer *eb, u64 parent_transid, + int atomic) { struct extent_state *cached_state = NULL; int ret; @@ -331,6 +332,9 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 0; + if (atomic) + return -EAGAIN; + lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, 0, &cached_state); if (extent_buffer_uptodate(eb) && @@ -372,7 +376,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, ret = read_extent_buffer_pages(io_tree, eb, start, WAIT_COMPLETE, btree_get_extent, mirror_num); - if (!ret && !verify_parent_transid(io_tree, eb, parent_transid)) + if (!ret && !verify_parent_transid(io_tree, eb, + parent_transid, 0)) break; /* @@ -383,17 +388,16 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags)) break; - if (!failed_mirror) { - failed = 1; - printk(KERN_ERR "failed mirror was %d\n", eb->failed_mirror); - failed_mirror = eb->failed_mirror; - } - num_copies = btrfs_num_copies(&root->fs_info->mapping_tree, eb->start, eb->len); if (num_copies == 1) break; + if (!failed_mirror) { + failed = 1; + failed_mirror = eb->read_mirror; + } + mirror_num++; if (mirror_num == failed_mirror) mirror_num++; @@ -564,7 +568,7 @@ struct extent_buffer *find_eb_for_page(struct extent_io_tree *tree, } static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state) + struct extent_state *state, int mirror) { struct extent_io_tree *tree; u64 found_start; @@ -589,6 +593,7 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, if (!reads_done) goto err; + eb->read_mirror = mirror; if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) { ret = -EIO; goto err; @@ -652,7 +657,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror) eb = (struct extent_buffer *)page->private; set_bit(EXTENT_BUFFER_IOERR, &eb->bflags); - eb->failed_mirror = failed_mirror; + eb->read_mirror = failed_mirror; if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) btree_readahead_hook(root, eb, eb->start, -EIO); return -EIO; /* we fixed nothing */ @@ -1202,7 +1207,7 @@ static int __must_check find_and_setup_root(struct btrfs_root *tree_root, root->commit_root = NULL; root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item), blocksize, generation); - if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) { + if (!root->node || !btrfs_buffer_uptodate(root->node, generation, 0)) { free_extent_buffer(root->node); root->node = NULL; return -EIO; @@ -2254,9 +2259,9 @@ int open_ctree(struct super_block *sb, goto fail_sb_buffer; } - if (sectorsize < PAGE_SIZE) { - printk(KERN_WARNING "btrfs: Incompatible sector size " - "found on %s\n", sb->s_id); + if (sectorsize != PAGE_SIZE) { + printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) " + "found on %s\n", (unsigned long)sectorsize, sb->s_id); goto fail_sb_buffer; } @@ -3143,7 +3148,8 @@ int close_ctree(struct btrfs_root *root) return 0; } -int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) +int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, + int atomic) { int ret; struct inode *btree_inode = buf->pages[0]->mapping->host; @@ -3153,7 +3159,9 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) return ret; ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf, - parent_transid); + parent_transid, atomic); + if (ret == -EAGAIN) + return ret; return !ret; } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index a7ace1a2dd12..ab1830aaf0ed 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -66,7 +66,8 @@ void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr); void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr); void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); void btrfs_mark_buffer_dirty(struct extent_buffer *buf); -int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid); +int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, + int atomic); int btrfs_set_buffer_uptodate(struct extent_buffer *buf); int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid); u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2b35f8d14bb9..49fd7b66d57b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2301,6 +2301,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, if (ret) { printk(KERN_DEBUG "btrfs: run_delayed_extent_op returned %d\n", ret); + spin_lock(&delayed_refs->lock); return ret; } @@ -2331,6 +2332,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, if (ret) { printk(KERN_DEBUG "btrfs: run_one_delayed_ref returned %d\n", ret); + spin_lock(&delayed_refs->lock); return ret; } @@ -3769,13 +3771,10 @@ again: */ if (current->journal_info) return -EAGAIN; - ret = wait_event_interruptible(space_info->wait, - !space_info->flush); - /* Must have been interrupted, return */ - if (ret) { - printk(KERN_DEBUG "btrfs: %s returning -EINTR\n", __func__); + ret = wait_event_killable(space_info->wait, !space_info->flush); + /* Must have been killed, return */ + if (ret) return -EINTR; - } spin_lock(&space_info->lock); } @@ -4215,8 +4214,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) num_bytes = calc_global_metadata_size(fs_info); - spin_lock(&block_rsv->lock); spin_lock(&sinfo->lock); + spin_lock(&block_rsv->lock); block_rsv->size = num_bytes; @@ -4242,8 +4241,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) block_rsv->full = 1; } - spin_unlock(&sinfo->lock); spin_unlock(&block_rsv->lock); + spin_unlock(&sinfo->lock); } static void init_global_block_rsv(struct btrfs_fs_info *fs_info) @@ -6569,7 +6568,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, goto skip; } - if (!btrfs_buffer_uptodate(next, generation)) { + if (!btrfs_buffer_uptodate(next, generation, 0)) { btrfs_tree_unlock(next); free_extent_buffer(next); next = NULL; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index cd4b5e400221..c9018a05036e 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -402,20 +402,28 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig, return 0; } +static struct extent_state *next_state(struct extent_state *state) +{ + struct rb_node *next = rb_next(&state->rb_node); + if (next) + return rb_entry(next, struct extent_state, rb_node); + else + return NULL; +} + /* * utility function to clear some bits in an extent state struct. - * it will optionally wake up any one waiting on this state (wake == 1), or - * forcibly remove the state from the tree (delete == 1). + * it will optionally wake up any one waiting on this state (wake == 1) * * If no bits are set on the state struct after clearing things, the * struct is freed and removed from the tree */ -static int clear_state_bit(struct extent_io_tree *tree, - struct extent_state *state, - int *bits, int wake) +static struct extent_state *clear_state_bit(struct extent_io_tree *tree, + struct extent_state *state, + int *bits, int wake) { + struct extent_state *next; int bits_to_clear = *bits & ~EXTENT_CTLBITS; - int ret = state->state & bits_to_clear; if ((bits_to_clear & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) { u64 range = state->end - state->start + 1; @@ -427,6 +435,7 @@ static int clear_state_bit(struct extent_io_tree *tree, if (wake) wake_up(&state->wq); if (state->state == 0) { + next = next_state(state); if (state->tree) { rb_erase(&state->rb_node, &tree->state); state->tree = NULL; @@ -436,8 +445,9 @@ static int clear_state_bit(struct extent_io_tree *tree, } } else { merge_state(tree, state); + next = next_state(state); } - return ret; + return next; } static struct extent_state * @@ -476,7 +486,6 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state *state; struct extent_state *cached; struct extent_state *prealloc = NULL; - struct rb_node *next_node; struct rb_node *node; u64 last_end; int err; @@ -528,14 +537,11 @@ hit_next: WARN_ON(state->end < start); last_end = state->end; - if (state->end < end && !need_resched()) - next_node = rb_next(&state->rb_node); - else - next_node = NULL; - /* the state doesn't have the wanted bits, go ahead */ - if (!(state->state & bits)) + if (!(state->state & bits)) { + state = next_state(state); goto next; + } /* * | ---- desired range ---- | @@ -593,16 +599,13 @@ hit_next: goto out; } - clear_state_bit(tree, state, &bits, wake); + state = clear_state_bit(tree, state, &bits, wake); next: if (last_end == (u64)-1) goto out; start = last_end + 1; - if (start <= end && next_node) { - state = rb_entry(next_node, struct extent_state, - rb_node); + if (start <= end && state && !need_resched()) goto hit_next; - } goto search_again; out: @@ -2301,7 +2304,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) u64 start; u64 end; int whole_page; - int failed_mirror; + int mirror; int ret; if (err) @@ -2340,20 +2343,18 @@ static void end_bio_extent_readpage(struct bio *bio, int err) } spin_unlock(&tree->lock); + mirror = (int)(unsigned long)bio->bi_bdev; if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) { ret = tree->ops->readpage_end_io_hook(page, start, end, - state); + state, mirror); if (ret) uptodate = 0; else clean_io_failure(start, page); } - if (!uptodate) - failed_mirror = (int)(unsigned long)bio->bi_bdev; - if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) { - ret = tree->ops->readpage_io_failed_hook(page, failed_mirror); + ret = tree->ops->readpage_io_failed_hook(page, mirror); if (!ret && !err && test_bit(BIO_UPTODATE, &bio->bi_flags)) uptodate = 1; @@ -2368,8 +2369,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) * can't handle the error it will return -EIO and we * remain responsible for that page. */ - ret = bio_readpage_error(bio, page, start, end, - failed_mirror, NULL); + ret = bio_readpage_error(bio, page, start, end, mirror, NULL); if (ret == 0) { uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); @@ -4120,6 +4120,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, if (atomic_inc_not_zero(&exists->refs)) { spin_unlock(&mapping->private_lock); unlock_page(p); + page_cache_release(p); mark_extent_buffer_accessed(exists); goto free_eb; } @@ -4199,8 +4200,7 @@ free_eb: unlock_page(eb->pages[i]); } - if (!atomic_dec_and_test(&eb->refs)) - return exists; + WARN_ON(!atomic_dec_and_test(&eb->refs)); btrfs_release_extent_buffer(eb); return exists; } @@ -4462,7 +4462,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, } clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags); - eb->failed_mirror = 0; + eb->read_mirror = 0; atomic_set(&eb->io_pages, num_reads); for (i = start_i; i < num_pages; i++) { page = extent_buffer_page(eb, i); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index faf10eb57f75..b516c3b8dec6 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -79,7 +79,7 @@ struct extent_io_ops { u64 start, u64 end, struct extent_state *state); int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end, - struct extent_state *state); + struct extent_state *state, int mirror); int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate); void (*set_bit_hook)(struct inode *inode, struct extent_state *state, @@ -135,7 +135,7 @@ struct extent_buffer { spinlock_t refs_lock; atomic_t refs; atomic_t io_pages; - int failed_mirror; + int read_mirror; struct list_head leak_list; struct rcu_head rcu_head; pid_t lock_owner; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index d83260d7498f..53bf2d764bbc 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -567,6 +567,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode, int extent_type; int recow; int ret; + int modify_tree = -1; if (drop_cache) btrfs_drop_extent_cache(inode, start, end - 1, 0); @@ -575,10 +576,13 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode, if (!path) return -ENOMEM; + if (start >= BTRFS_I(inode)->disk_i_size) + modify_tree = 0; + while (1) { recow = 0; ret = btrfs_lookup_file_extent(trans, root, path, ino, - search_start, -1); + search_start, modify_tree); if (ret < 0) break; if (ret > 0 && path->slots[0] > 0 && search_start == start) { @@ -634,7 +638,8 @@ next_slot: } search_start = max(key.offset, start); - if (recow) { + if (recow || !modify_tree) { + modify_tree = -1; btrfs_release_path(path); continue; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 115bc05e42b0..61b16c641ce0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1947,7 +1947,7 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end, * extent_io.c will try to find good copies for us. */ static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state) + struct extent_state *state, int mirror) { size_t offset = start - ((u64)page->index << PAGE_CACHE_SHIFT); struct inode *inode = page->mapping->host; @@ -4069,7 +4069,7 @@ static struct inode *new_simple_dir(struct super_block *s, BTRFS_I(inode)->dummy_inode = 1; inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID; - inode->i_op = &simple_dir_inode_operations; + inode->i_op = &btrfs_dir_ro_inode_operations; inode->i_fop = &simple_dir_operations; inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; @@ -4140,14 +4140,18 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) static int btrfs_dentry_delete(const struct dentry *dentry) { struct btrfs_root *root; + struct inode *inode = dentry->d_inode; - if (!dentry->d_inode && !IS_ROOT(dentry)) - dentry = dentry->d_parent; + if (!inode && !IS_ROOT(dentry)) + inode = dentry->d_parent->d_inode; - if (dentry->d_inode) { - root = BTRFS_I(dentry->d_inode)->root; + if (inode) { + root = BTRFS_I(inode)->root; if (btrfs_root_refs(&root->root_item) == 0) return 1; + + if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) + return 1; } return 0; } @@ -4188,7 +4192,6 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, struct btrfs_path *path; struct list_head ins_list; struct list_head del_list; - struct qstr q; int ret; struct extent_buffer *leaf; int slot; @@ -4279,7 +4282,6 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, while (di_cur < di_total) { struct btrfs_key location; - struct dentry *tmp; if (verify_dir_item(root, leaf, di)) break; @@ -4300,35 +4302,15 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)]; btrfs_dir_item_key_to_cpu(leaf, di, &location); - q.name = name_ptr; - q.len = name_len; - q.hash = full_name_hash(q.name, q.len); - tmp = d_lookup(filp->f_dentry, &q); - if (!tmp) { - struct btrfs_key *newkey; - - newkey = kzalloc(sizeof(struct btrfs_key), - GFP_NOFS); - if (!newkey) - goto no_dentry; - tmp = d_alloc(filp->f_dentry, &q); - if (!tmp) { - kfree(newkey); - dput(tmp); - goto no_dentry; - } - memcpy(newkey, &location, - sizeof(struct btrfs_key)); - tmp->d_fsdata = newkey; - tmp->d_flags |= DCACHE_NEED_LOOKUP; - d_rehash(tmp); - dput(tmp); - } else { - dput(tmp); - } -no_dentry: + /* is this a reference to our own snapshot? If so - * skip it + * skip it. + * + * In contrast to old kernels, we insert the snapshot's + * dir item and dir index after it has been created, so + * we won't find a reference to our own snapshot. We + * still keep the following code for backward + * compatibility. */ if (location.type == BTRFS_ROOT_ITEM_KEY && location.objectid == root->root_key.objectid) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 18cc23d164a8..14f8e1faa46e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2262,7 +2262,10 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg) di_args->bytes_used = dev->bytes_used; di_args->total_bytes = dev->total_bytes; memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); - strncpy(di_args->path, dev->name, sizeof(di_args->path)); + if (dev->name) + strncpy(di_args->path, dev->name, sizeof(di_args->path)); + else + di_args->path[0] = '\0'; out: if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args))) diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 4f69028a68c4..086e6bdae1c4 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -252,7 +252,7 @@ struct btrfs_data_container { struct btrfs_ioctl_ino_path_args { __u64 inum; /* in */ - __u32 size; /* in */ + __u64 size; /* in */ __u64 reserved[4]; /* struct btrfs_data_container *fspath; out */ __u64 fspath; /* out */ @@ -260,7 +260,7 @@ struct btrfs_ioctl_ino_path_args { struct btrfs_ioctl_logical_ino_args { __u64 logical; /* in */ - __u32 size; /* in */ + __u64 size; /* in */ __u64 reserved[4]; /* struct btrfs_data_container *inodes; out */ __u64 inodes; diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index dc5d33146fdb..ac5d01085884 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -250,14 +250,12 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info, struct btrfs_bio *bbio) { int ret; - int looped = 0; struct reada_zone *zone; struct btrfs_block_group_cache *cache = NULL; u64 start; u64 end; int i; -again: zone = NULL; spin_lock(&fs_info->reada_lock); ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, @@ -274,9 +272,6 @@ again: spin_unlock(&fs_info->reada_lock); } - if (looped) - return NULL; - cache = btrfs_lookup_block_group(fs_info, logical); if (!cache) return NULL; @@ -307,13 +302,15 @@ again: ret = radix_tree_insert(&dev->reada_zones, (unsigned long)(zone->end >> PAGE_CACHE_SHIFT), zone); - spin_unlock(&fs_info->reada_lock); - if (ret) { + if (ret == -EEXIST) { kfree(zone); - looped = 1; - goto again; + ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, + logical >> PAGE_CACHE_SHIFT, 1); + if (ret == 1) + kref_get(&zone->refcnt); } + spin_unlock(&fs_info->reada_lock); return zone; } @@ -323,26 +320,26 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root, struct btrfs_key *top, int level) { int ret; - int looped = 0; struct reada_extent *re = NULL; + struct reada_extent *re_exist = NULL; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree; struct btrfs_bio *bbio = NULL; struct btrfs_device *dev; + struct btrfs_device *prev_dev; u32 blocksize; u64 length; int nzones = 0; int i; unsigned long index = logical >> PAGE_CACHE_SHIFT; -again: spin_lock(&fs_info->reada_lock); re = radix_tree_lookup(&fs_info->reada_tree, index); if (re) kref_get(&re->refcnt); spin_unlock(&fs_info->reada_lock); - if (re || looped) + if (re) return re; re = kzalloc(sizeof(*re), GFP_NOFS); @@ -398,16 +395,31 @@ again: /* insert extent in reada_tree + all per-device trees, all or nothing */ spin_lock(&fs_info->reada_lock); ret = radix_tree_insert(&fs_info->reada_tree, index, re); + if (ret == -EEXIST) { + re_exist = radix_tree_lookup(&fs_info->reada_tree, index); + BUG_ON(!re_exist); + kref_get(&re_exist->refcnt); + spin_unlock(&fs_info->reada_lock); + goto error; + } if (ret) { spin_unlock(&fs_info->reada_lock); - if (ret != -ENOMEM) { - /* someone inserted the extent in the meantime */ - looped = 1; - } goto error; } + prev_dev = NULL; for (i = 0; i < nzones; ++i) { dev = bbio->stripes[i].dev; + if (dev == prev_dev) { + /* + * in case of DUP, just add the first zone. As both + * are on the same device, there's nothing to gain + * from adding both. + * Also, it wouldn't work, as the tree is per device + * and adding would fail with EEXIST + */ + continue; + } + prev_dev = dev; ret = radix_tree_insert(&dev->reada_extents, index, re); if (ret) { while (--i >= 0) { @@ -450,9 +462,7 @@ error: } kfree(bbio); kfree(re); - if (looped) - goto again; - return NULL; + return re_exist; } static void reada_kref_dummy(struct kref *kr) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 017281dbb2a7..646ee21bb035 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1279,7 +1279,9 @@ static int __update_reloc_root(struct btrfs_root *root, int del) if (rb_node) backref_tree_panic(rb_node, -EEXIST, node->bytenr); } else { + spin_lock(&root->fs_info->trans_lock); list_del_init(&root->root_list); + spin_unlock(&root->fs_info->trans_lock); kfree(node); } return 0; @@ -3811,7 +3813,7 @@ restart: ret = btrfs_block_rsv_check(rc->extent_root, rc->block_rsv, 5); if (ret < 0) { - if (ret != -EAGAIN) { + if (ret != -ENOSPC) { err = ret; WARN_ON(1); break; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index bc015f77f3ea..2f3d6f917fb3 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -998,6 +998,7 @@ static int scrub_setup_recheck_block(struct scrub_dev *sdev, page = sblock->pagev + page_index; page->logical = logical; page->physical = bbio->stripes[mirror_index].physical; + /* for missing devices, bdev is NULL */ page->bdev = bbio->stripes[mirror_index].dev->bdev; page->mirror_num = mirror_index + 1; page->page = alloc_page(GFP_NOFS); @@ -1042,6 +1043,12 @@ static int scrub_recheck_block(struct btrfs_fs_info *fs_info, struct scrub_page *page = sblock->pagev + page_num; DECLARE_COMPLETION_ONSTACK(complete); + if (page->bdev == NULL) { + page->io_error = 1; + sblock->no_io_error_seen = 0; + continue; + } + BUG_ON(!page->page); bio = bio_alloc(GFP_NOFS, 1); if (!bio) @@ -1257,12 +1264,6 @@ static int scrub_checksum_data(struct scrub_block *sblock) if (memcmp(csum, on_disk_csum, sdev->csum_size)) fail = 1; - if (fail) { - spin_lock(&sdev->stat_lock); - ++sdev->stat.csum_errors; - spin_unlock(&sdev->stat_lock); - } - return fail; } @@ -1335,15 +1336,6 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) if (memcmp(calculated_csum, on_disk_csum, sdev->csum_size)) ++crc_fail; - if (crc_fail || fail) { - spin_lock(&sdev->stat_lock); - if (crc_fail) - ++sdev->stat.csum_errors; - if (fail) - ++sdev->stat.verify_errors; - spin_unlock(&sdev->stat_lock); - } - return fail || crc_fail; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8d5d380f7bdb..c5f8fca4195f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -815,7 +815,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return 0; } - btrfs_start_delalloc_inodes(root, 0); btrfs_wait_ordered_extents(root, 0, 0); trans = btrfs_start_transaction(root, 0); @@ -1148,13 +1147,15 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; } else { - if (fs_info->fs_devices->rw_devices == 0) + if (fs_info->fs_devices->rw_devices == 0) { ret = -EACCES; goto restore; + } - if (btrfs_super_log_root(fs_info->super_copy) != 0) + if (btrfs_super_log_root(fs_info->super_copy) != 0) { ret = -EINVAL; goto restore; + } ret = btrfs_cleanup_fs_roots(fs_info); if (ret) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 11b77a59db62..36422254ef67 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -73,8 +73,10 @@ loop: cur_trans = root->fs_info->running_transaction; if (cur_trans) { - if (cur_trans->aborted) + if (cur_trans->aborted) { + spin_unlock(&root->fs_info->trans_lock); return cur_trans->aborted; + } atomic_inc(&cur_trans->use_count); atomic_inc(&cur_trans->num_writers); cur_trans->num_joined++; @@ -1400,6 +1402,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, ret = commit_fs_roots(trans, root); if (ret) { mutex_unlock(&root->fs_info->tree_log_mutex); + mutex_unlock(&root->fs_info->reloc_mutex); goto cleanup_transaction; } @@ -1411,6 +1414,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, ret = commit_cowonly_roots(trans, root); if (ret) { mutex_unlock(&root->fs_info->tree_log_mutex); + mutex_unlock(&root->fs_info->reloc_mutex); goto cleanup_transaction; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index d017283ae6f5..eb1ae908582c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -279,7 +279,7 @@ static int process_one_buffer(struct btrfs_root *log, log->fs_info->extent_root, eb->start, eb->len); - if (btrfs_buffer_uptodate(eb, gen)) { + if (btrfs_buffer_uptodate(eb, gen, 0)) { if (wc->write) btrfs_write_tree_block(eb); if (wc->wait) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 759d02486d7c..1411b99555a4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3324,12 +3324,14 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, stripe_size = devices_info[ndevs-1].max_avail; num_stripes = ndevs * dev_stripes; - if (stripe_size * num_stripes > max_chunk_size * ncopies) { + if (stripe_size * ndevs > max_chunk_size * ncopies) { stripe_size = max_chunk_size * ncopies; - do_div(stripe_size, num_stripes); + do_div(stripe_size, ndevs); } do_div(stripe_size, dev_stripes); + + /* align to BTRFS_STRIPE_LEN */ do_div(stripe_size, BTRFS_STRIPE_LEN); stripe_size *= BTRFS_STRIPE_LEN; @@ -3805,10 +3807,11 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, else if (mirror_num) stripe_index += mirror_num - 1; else { + int old_stripe_index = stripe_index; stripe_index = find_live_mirror(map, stripe_index, map->sub_stripes, stripe_index + current->pid % map->sub_stripes); - mirror_num = stripe_index + 1; + mirror_num = stripe_index - old_stripe_index + 1; } } else { /* @@ -4350,8 +4353,10 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid) ret = __btrfs_open_devices(fs_devices, FMODE_READ, root->fs_info->bdev_holder); - if (ret) + if (ret) { + free_fs_devices(fs_devices); goto out; + } if (!fs_devices->seeding) { __btrfs_close_devices(fs_devices); diff --git a/fs/buffer.c b/fs/buffer.c index 36d66653b931..ad5938ca357c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -921,6 +921,7 @@ init_page_buffers(struct page *page, struct block_device *bdev, struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); + sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode)); do { if (!buffer_mapped(bh)) { @@ -929,7 +930,8 @@ init_page_buffers(struct page *page, struct block_device *bdev, bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); - set_buffer_mapped(bh); + if (block < end_block) + set_buffer_mapped(bh); } block++; bh = bh->b_this_page; @@ -985,7 +987,6 @@ grow_dev_page(struct block_device *bdev, sector_t block, return page; failed: - BUG(); unlock_page(page); page_cache_release(page); return NULL; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index d34212822444..541ef81f6ae8 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -370,13 +370,13 @@ cifs_show_options(struct seq_file *s, struct dentry *root) (int)(srcaddr->sa_family)); } - seq_printf(s, ",uid=%d", cifs_sb->mnt_uid); + seq_printf(s, ",uid=%u", cifs_sb->mnt_uid); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) seq_printf(s, ",forceuid"); else seq_printf(s, ",noforceuid"); - seq_printf(s, ",gid=%d", cifs_sb->mnt_gid); + seq_printf(s, ",gid=%u", cifs_sb->mnt_gid); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) seq_printf(s, ",forcegid"); else @@ -434,11 +434,15 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",noperm"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) seq_printf(s, ",strictcache"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID) + seq_printf(s, ",backupuid=%u", cifs_sb->mnt_backupuid); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID) + seq_printf(s, ",backupgid=%u", cifs_sb->mnt_backupgid); - seq_printf(s, ",rsize=%d", cifs_sb->rsize); - seq_printf(s, ",wsize=%d", cifs_sb->wsize); + seq_printf(s, ",rsize=%u", cifs_sb->rsize); + seq_printf(s, ",wsize=%u", cifs_sb->wsize); /* convert actimeo and display it in seconds */ - seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ); + seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ); return 0; } @@ -695,7 +699,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int origin) * origin == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate * the cached file length */ - if (origin != SEEK_SET || origin != SEEK_CUR) { + if (origin != SEEK_SET && origin != SEEK_CUR) { int rc; struct inode *inode = file->f_path.dentry->d_inode; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index d1389bb33ceb..65365358c976 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -125,5 +125,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "1.77" +#define CIFS_VERSION "1.78" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index f52c5ab78f9d..da2f5446fa7a 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -4844,8 +4844,12 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr, max_len = data_end - temp; node->node_name = cifs_strndup_from_utf16(temp, max_len, is_unicode, nls_codepage); - if (!node->node_name) + if (!node->node_name) { rc = -ENOMEM; + goto parse_DFS_referrals_exit; + } + + ref++; } parse_DFS_referrals_exit: diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index f31dc9ac37b7..e0b56d7a19c5 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -164,7 +164,8 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_sign, "sign" }, { Opt_seal, "seal" }, { Opt_direct, "direct" }, - { Opt_direct, "forceddirectio" }, + { Opt_direct, "directio" }, + { Opt_direct, "forcedirectio" }, { Opt_strictcache, "strictcache" }, { Opt_noac, "noac" }, { Opt_fsc, "fsc" }, @@ -215,6 +216,8 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_ignore, "cred" }, { Opt_ignore, "credentials" }, + { Opt_ignore, "cred=%s" }, + { Opt_ignore, "credentials=%s" }, { Opt_ignore, "guest" }, { Opt_ignore, "rw" }, { Opt_ignore, "ro" }, @@ -2183,6 +2186,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) tcp_ses->session_estab = false; tcp_ses->sequence_number = 0; tcp_ses->lstrp = jiffies; + spin_lock_init(&tcp_ses->req_lock); INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); @@ -3228,10 +3232,6 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_uid = pvolume_info->linux_uid; cifs_sb->mnt_gid = pvolume_info->linux_gid; - if (pvolume_info->backupuid_specified) - cifs_sb->mnt_backupuid = pvolume_info->backupuid; - if (pvolume_info->backupgid_specified) - cifs_sb->mnt_backupgid = pvolume_info->backupgid; cifs_sb->mnt_file_mode = pvolume_info->file_mode; cifs_sb->mnt_dir_mode = pvolume_info->dir_mode; cFYI(1, "file mode: 0x%hx dir mode: 0x%hx", @@ -3262,10 +3262,14 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RWPIDFORWARD; if (pvolume_info->cifs_acl) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL; - if (pvolume_info->backupuid_specified) + if (pvolume_info->backupuid_specified) { cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPUID; - if (pvolume_info->backupgid_specified) + cifs_sb->mnt_backupuid = pvolume_info->backupuid; + } + if (pvolume_info->backupgid_specified) { cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPGID; + cifs_sb->mnt_backupgid = pvolume_info->backupgid; + } if (pvolume_info->override_uid) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID; if (pvolume_info->override_gid) @@ -3614,22 +3618,6 @@ cifs_get_volume_info(char *mount_data, const char *devname) return volume_info; } -/* make sure ra_pages is a multiple of rsize */ -static inline unsigned int -cifs_ra_pages(struct cifs_sb_info *cifs_sb) -{ - unsigned int reads; - unsigned int rsize_pages = cifs_sb->rsize / PAGE_CACHE_SIZE; - - if (rsize_pages >= default_backing_dev_info.ra_pages) - return default_backing_dev_info.ra_pages; - else if (rsize_pages == 0) - return rsize_pages; - - reads = default_backing_dev_info.ra_pages / rsize_pages; - return reads * rsize_pages; -} - int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info) { @@ -3717,7 +3705,7 @@ try_mount_again: cifs_sb->rsize = cifs_negotiate_rsize(tcon, volume_info); /* tune readahead according to rsize */ - cifs_sb->bdi.ra_pages = cifs_ra_pages(cifs_sb); + cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_CACHE_SIZE; remote_path_check: #ifdef CONFIG_CIFS_DFS_UPCALL diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index d172c8ed9017..ec4e9a2a12f8 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -668,12 +668,19 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd) return 0; else { /* - * Forcibly invalidate automounting directory inodes - * (remote DFS directories) so to have them - * instantiated again for automount + * If the inode wasn't known to be a dfs entry when + * the dentry was instantiated, such as when created + * via ->readdir(), it needs to be set now since the + * attributes will have been updated by + * cifs_revalidate_dentry(). */ - if (IS_AUTOMOUNT(direntry->d_inode)) - return 0; + if (IS_AUTOMOUNT(direntry->d_inode) && + !(direntry->d_flags & DCACHE_NEED_AUTOMOUNT)) { + spin_lock(&direntry->d_lock); + direntry->d_flags |= DCACHE_NEED_AUTOMOUNT; + spin_unlock(&direntry->d_lock); + } + return 1; } } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fae765dac934..81725e9286e9 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2178,7 +2178,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, unsigned long nr_pages, i; size_t copied, len, cur_len; ssize_t total_written = 0; - loff_t offset = *poffset; + loff_t offset; struct iov_iter it; struct cifsFileInfo *open_file; struct cifs_tcon *tcon; @@ -2200,6 +2200,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); open_file = file->private_data; tcon = tlink_tcon(open_file->tlink); + offset = *poffset; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) pid = open_file->pid; diff --git a/fs/dcache.c b/fs/dcache.c index b60ddc41d783..8c1ab8fb5012 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -141,18 +141,25 @@ int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ -static inline int dentry_cmp(const unsigned char *cs, size_t scount, - const unsigned char *ct, size_t tcount) -{ #ifdef CONFIG_DCACHE_WORD_ACCESS - unsigned long a,b,mask; - if (unlikely(scount != tcount)) - return 1; +#include <asm/word-at-a-time.h> +/* + * NOTE! 'cs' and 'scount' come from a dentry, so it has a + * aligned allocation for this particular component. We don't + * strictly need the load_unaligned_zeropad() safety, but it + * doesn't hurt either. + * + * In contrast, 'ct' and 'tcount' can be from a pathname, and do + * need the careful unaligned handling. + */ +static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) +{ + unsigned long a,b,mask; for (;;) { a = *(unsigned long *)cs; - b = *(unsigned long *)ct; + b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) @@ -165,10 +172,12 @@ static inline int dentry_cmp(const unsigned char *cs, size_t scount, } mask = ~(~0ul << tcount*8); return unlikely(!!((a ^ b) & mask)); +} + #else - if (scount != tcount) - return 1; +static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) +{ do { if (*cs != *ct) return 1; @@ -177,7 +186,32 @@ static inline int dentry_cmp(const unsigned char *cs, size_t scount, tcount--; } while (tcount); return 0; +} + #endif + +static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) +{ + const unsigned char *cs; + /* + * Be careful about RCU walk racing with rename: + * use ACCESS_ONCE to fetch the name pointer. + * + * NOTE! Even if a rename will mean that the length + * was not loaded atomically, we don't care. The + * RCU walk will check the sequence count eventually, + * and catch it. And we won't overrun the buffer, + * because we're reading the name pointer atomically, + * and a dentry name is guaranteed to be properly + * terminated with a NUL byte. + * + * End result: even if 'len' is wrong, we'll exit + * early because the data cannot match (there can + * be no NUL in the ct/tcount data) + */ + cs = ACCESS_ONCE(dentry->d_name.name); + smp_read_barrier_depends(); + return dentry_string_cmp(cs, ct, tcount); } static void __d_free(struct rcu_head *head) @@ -1240,6 +1274,13 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) if (!dentry) return NULL; + /* + * We guarantee that the inline name is always NUL-terminated. + * This way the memcpy() done by the name switching in rename + * will still always have a NUL at the end, even if we might + * be overwriting an internal NUL character + */ + dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (name->len > DNAME_INLINE_LEN-1) { dname = kmalloc(name->len + 1, GFP_KERNEL); if (!dname) { @@ -1249,13 +1290,16 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) } else { dname = dentry->d_iname; } - dentry->d_name.name = dname; dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; + /* Make sure we always see the terminating NUL character */ + smp_wmb(); + dentry->d_name.name = dname; + dentry->d_count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); @@ -1421,18 +1465,18 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, } list_for_each_entry(alias, &inode->i_dentry, d_alias) { - struct qstr *qstr = &alias->d_name; - /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or * parent changes, because the parent inode i_mutex is held. */ - if (qstr->hash != hash) + if (alias->d_name.hash != hash) continue; if (alias->d_parent != entry->d_parent) continue; - if (dentry_cmp(qstr->name, qstr->len, name, len)) + if (alias->d_name.len != len) + continue; + if (dentry_cmp(alias, name, len)) continue; __dget(alias); return alias; @@ -1471,7 +1515,7 @@ struct dentry *d_make_root(struct inode *root_inode) struct dentry *res = NULL; if (root_inode) { - static const struct qstr name = { .name = "/", .len = 1 }; + static const struct qstr name = QSTR_INIT("/", 1); res = __d_alloc(root_inode->i_sb, &name); if (res) @@ -1709,6 +1753,48 @@ err_out: } EXPORT_SYMBOL(d_add_ci); +/* + * Do the slow-case of the dentry name compare. + * + * Unlike the dentry_cmp() function, we need to atomically + * load the name, length and inode information, so that the + * filesystem can rely on them, and can use the 'name' and + * 'len' information without worrying about walking off the + * end of memory etc. + * + * Thus the read_seqcount_retry() and the "duplicate" info + * in arguments (the low-level filesystem should not look + * at the dentry inode or name contents directly, since + * rename can change them while we're in RCU mode). + */ +enum slow_d_compare { + D_COMP_OK, + D_COMP_NOMATCH, + D_COMP_SEQRETRY, +}; + +static noinline enum slow_d_compare slow_dentry_cmp( + const struct dentry *parent, + struct inode *inode, + struct dentry *dentry, + unsigned int seq, + const struct qstr *name) +{ + int tlen = dentry->d_name.len; + const char *tname = dentry->d_name.name; + struct inode *i = dentry->d_inode; + + if (read_seqcount_retry(&dentry->d_seq, seq)) { + cpu_relax(); + return D_COMP_SEQRETRY; + } + if (parent->d_op->d_compare(parent, inode, + dentry, i, + tlen, tname, name)) + return D_COMP_NOMATCH; + return D_COMP_OK; +} + /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry @@ -1735,15 +1821,17 @@ EXPORT_SYMBOL(d_add_ci); * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. + * + * NOTE! The caller *has* to check the resulting dentry against the sequence + * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, - unsigned *seqp, struct inode **inode) + unsigned *seqp, struct inode *inode) { - unsigned int len = name->len; - unsigned int hash = name->hash; + u64 hashlen = name->hash_len; const unsigned char *str = name->name; - struct hlist_bl_head *b = d_hash(parent, hash); + struct hlist_bl_head *b = d_hash(parent, hashlen_hash(hashlen)); struct hlist_bl_node *node; struct dentry *dentry; @@ -1769,49 +1857,47 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent, */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; - struct inode *i; - const char *tname; - int tlen; - - if (dentry->d_name.hash != hash) - continue; seqretry: - seq = read_seqcount_begin(&dentry->d_seq); + /* + * The dentry sequence count protects us from concurrent + * renames, and thus protects inode, parent and name fields. + * + * The caller must perform a seqcount check in order + * to do anything useful with the returned dentry, + * including using the 'd_inode' pointer. + * + * NOTE! We do a "raw" seqcount_begin here. That means that + * we don't wait for the sequence count to stabilize if it + * is in the middle of a sequence change. If we do the slow + * dentry compare, we will do seqretries until it is stable, + * and if we end up with a successful lookup, we actually + * want to exit RCU lookup anyway. + */ + seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; - tlen = dentry->d_name.len; - tname = dentry->d_name.name; - i = dentry->d_inode; - prefetch(tname); - /* - * This seqcount check is required to ensure name and - * len are loaded atomically, so as not to walk off the - * edge of memory when walking. If we could load this - * atomically some other way, we could drop this check. - */ - if (read_seqcount_retry(&dentry->d_seq, seq)) - goto seqretry; + *seqp = seq; + if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { - if (parent->d_op->d_compare(parent, *inode, - dentry, i, - tlen, tname, name)) + if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; - } else { - if (dentry_cmp(tname, tlen, str, len)) + switch (slow_dentry_cmp(parent, inode, dentry, seq, name)) { + case D_COMP_OK: + return dentry; + case D_COMP_NOMATCH: continue; + default: + goto seqretry; + } } - /* - * No extra seqcount check is required after the name - * compare. The caller must perform a seqcount check in - * order to do anything useful with the returned dentry - * anyway. - */ - *seqp = seq; - *inode = i; - return dentry; + + if (dentry->d_name.hash_len != hashlen) + continue; + if (!dentry_cmp(dentry, str, hashlen_len(hashlen))) + return dentry; } return NULL; } @@ -1890,8 +1976,6 @@ struct dentry *__d_lookup(struct dentry *parent, struct qstr *name) rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { - const char *tname; - int tlen; if (dentry->d_name.hash != hash) continue; @@ -1906,15 +1990,17 @@ struct dentry *__d_lookup(struct dentry *parent, struct qstr *name) * It is safe to compare names since d_move() cannot * change the qstr (protected by d_lock). */ - tlen = dentry->d_name.len; - tname = dentry->d_name.name; if (parent->d_flags & DCACHE_OP_COMPARE) { + int tlen = dentry->d_name.len; + const char *tname = dentry->d_name.name; if (parent->d_op->d_compare(parent, parent->d_inode, dentry, dentry->d_inode, tlen, tname, name)) goto next; } else { - if (dentry_cmp(tname, tlen, str, len)) + if (dentry->d_name.len != len) + goto next; + if (dentry_cmp(dentry, str, len)) goto next; } diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index fa5c07d51dcc..4c58d4a3adc4 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1737,6 +1737,18 @@ static int _can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now) return 1; /* + * Even if the convert is compat with all granted locks, + * QUECVT forces it behind other locks on the convert queue. + */ + + if (now && conv && (lkb->lkb_exflags & DLM_LKF_QUECVT)) { + if (list_empty(&r->res_convertqueue)) + return 1; + else + goto out; + } + + /* * The NOORDER flag is set to avoid the standard vms rules on grant * order. */ diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 739b0985b398..c0b3c70ee87a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1663,8 +1663,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, if (op == EPOLL_CTL_ADD) { if (is_file_epoll(tfile)) { error = -ELOOP; - if (ep_loop_check(ep, tfile) != 0) + if (ep_loop_check(ep, tfile) != 0) { + clear_tfile_check_list(); goto error_tgt_fput; + } } else list_add(&tfile->f_tfile_llink, &tfile_check_list); } diff --git a/fs/exec.c b/fs/exec.c index b1fd2025e59a..d038968b54b4 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1245,6 +1245,13 @@ static int check_unsafe_exec(struct linux_binprm *bprm) bprm->unsafe |= LSM_UNSAFE_PTRACE; } + /* + * This isn't strictly necessary, but it makes it harder for LSMs to + * mess up. + */ + if (current->no_new_privs) + bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS; + n_fs = 1; spin_lock(&p->fs->lock); rcu_read_lock(); @@ -1288,7 +1295,8 @@ int prepare_binprm(struct linux_binprm *bprm) bprm->cred->euid = current_euid(); bprm->cred->egid = current_egid(); - if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) { + if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) && + !current->no_new_privs) { /* Set-uid? */ if (mode & S_ISUID) { bprm->per_clear |= PER_CLEAR_ON_SETID; diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index dffb86536285..f663a67d7bf0 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -79,7 +79,7 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, str struct dentry *ext2_get_parent(struct dentry *child) { - struct qstr dotdot = {.name = "..", .len = 2}; + struct qstr dotdot = QSTR_INIT("..", 2); unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot); if (!ino) return ERR_PTR(-ENOENT); diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index d7940b24cf68..eeb63dfc5d20 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1045,7 +1045,7 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str struct dentry *ext3_get_parent(struct dentry *child) { unsigned long ino; - struct qstr dotdot = {.name = "..", .len = 2}; + struct qstr dotdot = QSTR_INIT("..", 2); struct ext3_dir_entry_2 * de; struct buffer_head *bh; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 349d7b3671c8..e2a3f4b0ff78 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1052,10 +1052,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru struct dentry *ext4_get_parent(struct dentry *child) { __u32 ino; - static const struct qstr dotdot = { - .name = "..", - .len = 2, - }; + static const struct qstr dotdot = QSTR_INIT("..", 2); struct ext4_dir_entry_2 * de; struct buffer_head *bh; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6da193564e43..e1fb1d5de58e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1597,7 +1597,9 @@ static int parse_options(char *options, struct super_block *sb, unsigned int *journal_ioprio, int is_remount) { +#ifdef CONFIG_QUOTA struct ext4_sb_info *sbi = EXT4_SB(sb); +#endif char *p; substring_t args[MAX_OPT_ARGS]; int token; diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 230eb0f005b6..bd4a5892c93c 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -73,12 +73,8 @@ static int gfs2_set_mode(struct inode *inode, umode_t mode) int error = 0; if (mode != inode->i_mode) { - struct iattr iattr; - - iattr.ia_valid = ATTR_MODE; - iattr.ia_mode = mode; - - error = gfs2_setattr_simple(inode, &iattr); + inode->i_mode = mode; + mark_inode_dirty(inode); } return error; @@ -126,9 +122,7 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode) return PTR_ERR(acl); if (!acl) { mode &= ~current_umask(); - if (mode != inode->i_mode) - error = gfs2_set_mode(inode, mode); - return error; + return gfs2_set_mode(inode, mode); } if (S_ISDIR(inode->i_mode)) { diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 9b2ff0e851b1..e80a464850c8 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -36,8 +36,8 @@ #include "glops.h" -void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, - unsigned int from, unsigned int to) +static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, + unsigned int from, unsigned int to) { struct buffer_head *head = page_buffers(page); unsigned int bsize = head->b_size; @@ -517,15 +517,14 @@ out: /** * gfs2_internal_read - read an internal file * @ip: The gfs2 inode - * @ra_state: The readahead state (or NULL for no readahead) * @buf: The buffer to fill * @pos: The file position * @size: The amount to read * */ -int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state, - char *buf, loff_t *pos, unsigned size) +int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, + unsigned size) { struct address_space *mapping = ip->i_inode.i_mapping; unsigned long index = *pos / PAGE_CACHE_SIZE; @@ -943,8 +942,8 @@ static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh) clear_buffer_dirty(bh); bd = bh->b_private; if (bd) { - if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh)) - list_del_init(&bd->bd_le.le_list); + if (!list_empty(&bd->bd_list) && !buffer_pinned(bh)) + list_del_init(&bd->bd_list); else gfs2_remove_from_journal(bh, current->journal_info, 0); } @@ -1084,10 +1083,9 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) bd = bh->b_private; if (bd) { gfs2_assert_warn(sdp, bd->bd_bh == bh); - gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr)); - if (!list_empty(&bd->bd_le.le_list)) { + if (!list_empty(&bd->bd_list)) { if (!buffer_pinned(bh)) - list_del_init(&bd->bd_le.le_list); + list_del_init(&bd->bd_list); else bd = NULL; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 03c04febe26f..dab54099dd98 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -324,7 +324,7 @@ static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp) if (!dblock) return x + 1; - ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, 0, &mp->mp_bh[x+1]); + ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, &mp->mp_bh[x+1]); if (ret) return ret; } @@ -882,7 +882,7 @@ static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh, top = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + mp->mp_list[0]; bottom = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + sdp->sd_diptrs; } else { - error = gfs2_meta_indirect_buffer(ip, height, block, 0, &bh); + error = gfs2_meta_indirect_buffer(ip, height, block, &bh); if (error) return error; @@ -1169,6 +1169,7 @@ static int do_grow(struct inode *inode, u64 size) struct buffer_head *dibh; struct gfs2_qadata *qa = NULL; int error; + int unstuff = 0; if (gfs2_is_stuffed(ip) && (size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) { @@ -1183,13 +1184,14 @@ static int do_grow(struct inode *inode, u64 size) error = gfs2_inplace_reserve(ip, 1); if (error) goto do_grow_qunlock; + unstuff = 1; } error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT, 0); if (error) goto do_grow_release; - if (qa) { + if (unstuff) { error = gfs2_unstuff_dinode(ip, NULL); if (error) goto do_end_trans; @@ -1208,7 +1210,7 @@ static int do_grow(struct inode *inode, u64 size) do_end_trans: gfs2_trans_end(sdp); do_grow_release: - if (qa) { + if (unstuff) { gfs2_inplace_release(ip); do_grow_qunlock: gfs2_quota_unlock(ip); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index a836056343f0..8aaeb07a07b5 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -821,7 +821,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; - struct qstr name = { .name = "", .len = 0, .hash = 0 }; + struct qstr name = { .name = "" }; error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL); if (error) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index a3d2c9ee8d66..31b199f6efc1 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -558,14 +558,14 @@ fail: } /** - * gfs2_close - called to close a struct file + * gfs2_release - called to close a struct file * @inode: the inode the struct file belongs to * @file: the struct file being closed * * Returns: errno */ -static int gfs2_close(struct inode *inode, struct file *file) +static int gfs2_release(struct inode *inode, struct file *file) { struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; struct gfs2_file *fp; @@ -1005,7 +1005,7 @@ const struct file_operations gfs2_file_fops = { .unlocked_ioctl = gfs2_ioctl, .mmap = gfs2_mmap, .open = gfs2_open, - .release = gfs2_close, + .release = gfs2_release, .fsync = gfs2_fsync, .lock = gfs2_lock, .flock = gfs2_flock, @@ -1019,7 +1019,7 @@ const struct file_operations gfs2_dir_fops = { .readdir = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, - .release = gfs2_close, + .release = gfs2_release, .fsync = gfs2_fsync, .lock = gfs2_lock, .flock = gfs2_flock, @@ -1037,7 +1037,7 @@ const struct file_operations gfs2_file_fops_nolock = { .unlocked_ioctl = gfs2_ioctl, .mmap = gfs2_mmap, .open = gfs2_open, - .release = gfs2_close, + .release = gfs2_release, .fsync = gfs2_fsync, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, @@ -1049,7 +1049,7 @@ const struct file_operations gfs2_dir_fops_nolock = { .readdir = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, - .release = gfs2_close, + .release = gfs2_release, .fsync = gfs2_fsync, .llseek = default_llseek, }; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 1656df7aacd2..4bdcf3784187 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -94,7 +94,6 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) /* A shortened, inline version of gfs2_trans_begin() */ tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64)); tr.tr_ip = (unsigned long)__builtin_return_address(0); - INIT_LIST_HEAD(&tr.tr_list_buf); gfs2_log_reserve(sdp, tr.tr_reserved); BUG_ON(current->journal_info); current->journal_info = &tr; @@ -379,11 +378,6 @@ int gfs2_inode_refresh(struct gfs2_inode *ip) if (error) return error; - if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), dibh, GFS2_METATYPE_DI)) { - brelse(dibh); - return -EIO; - } - error = gfs2_dinode_in(ip, dibh->b_data); brelse(dibh); clear_bit(GIF_INVALID, &ip->i_flags); diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 47d0bda5ac2b..aa9949e5de26 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -26,7 +26,7 @@ #define DIO_METADATA 0x00000020 struct gfs2_log_operations; -struct gfs2_log_element; +struct gfs2_bufdata; struct gfs2_holder; struct gfs2_glock; struct gfs2_quota_data; @@ -52,7 +52,7 @@ struct gfs2_log_header_host { */ struct gfs2_log_operations { - void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_log_element *le); + void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_bufdata *bd); void (*lo_before_commit) (struct gfs2_sbd *sdp); void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai); void (*lo_before_scan) (struct gfs2_jdesc *jd, @@ -64,11 +64,6 @@ struct gfs2_log_operations { const char *lo_name; }; -struct gfs2_log_element { - struct list_head le_list; - const struct gfs2_log_operations *le_ops; -}; - #define GBF_FULL 1 struct gfs2_bitmap { @@ -118,15 +113,10 @@ TAS_BUFFER_FNS(Zeronew, zeronew) struct gfs2_bufdata { struct buffer_head *bd_bh; struct gfs2_glock *bd_gl; + u64 bd_blkno; - union { - struct list_head list_tr; - u64 blkno; - } u; -#define bd_list_tr u.list_tr -#define bd_blkno u.blkno - - struct gfs2_log_element bd_le; + struct list_head bd_list; + const struct gfs2_log_operations *bd_ops; struct gfs2_ail *bd_ail; struct list_head bd_ail_st_list; @@ -411,13 +401,10 @@ struct gfs2_trans { int tr_touched; - unsigned int tr_num_buf; unsigned int tr_num_buf_new; unsigned int tr_num_databuf_new; unsigned int tr_num_buf_rm; unsigned int tr_num_databuf_rm; - struct list_head tr_list_buf; - unsigned int tr_num_revoke; unsigned int tr_num_revoke_rm; }; @@ -699,7 +686,6 @@ struct gfs2_sbd { struct list_head sd_log_le_buf; struct list_head sd_log_le_revoke; - struct list_head sd_log_le_rg; struct list_head sd_log_le_databuf; struct list_head sd_log_le_ordered; @@ -716,7 +702,9 @@ struct gfs2_sbd { struct rw_semaphore sd_log_flush_lock; atomic_t sd_log_in_flight; + struct bio *sd_log_bio; wait_queue_head_t sd_log_flush_wait; + int sd_log_error; unsigned int sd_log_flush_head; u64 sd_log_flush_wrapped; diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 276e7b52b658..c53c7477f6da 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -17,10 +17,7 @@ extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); extern int gfs2_internal_read(struct gfs2_inode *ip, - struct file_ra_state *ra_state, char *buf, loff_t *pos, unsigned size); -extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, - unsigned int from, unsigned int to); extern void gfs2_set_aops(struct inode *inode); static inline int gfs2_is_stuffed(const struct gfs2_inode *ip) diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index f8411bd1b805..5f5e70e047dc 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -200,10 +200,11 @@ static int make_mode(const unsigned int lmstate) return -1; } -static u32 make_flags(const u32 lkid, const unsigned int gfs_flags, +static u32 make_flags(struct gfs2_glock *gl, const unsigned int gfs_flags, const int req) { u32 lkf = DLM_LKF_VALBLK; + u32 lkid = gl->gl_lksb.sb_lkid; if (gfs_flags & LM_FLAG_TRY) lkf |= DLM_LKF_NOQUEUE; @@ -227,8 +228,11 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags, BUG(); } - if (lkid != 0) + if (lkid != 0) { lkf |= DLM_LKF_CONVERT; + if (test_bit(GLF_BLOCKING, &gl->gl_flags)) + lkf |= DLM_LKF_QUECVT; + } return lkf; } @@ -250,7 +254,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state, char strname[GDLM_STRNAME_BYTES] = ""; req = make_mode(req_state); - lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req); + lkf = make_flags(gl, flags, req); gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT); gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT); if (gl->gl_lksb.sb_lkid) { diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 4752eadc7f6e..f4beeb9c81c1 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -32,8 +32,6 @@ #include "dir.h" #include "trace_gfs2.h" -#define PULL 1 - /** * gfs2_struct2blk - compute stuff * @sdp: the filesystem @@ -359,18 +357,6 @@ retry: return 0; } -u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn) -{ - struct gfs2_journal_extent *je; - - list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) { - if (lbn >= je->lblock && lbn < je->lblock + je->blocks) - return je->dblock + lbn - je->lblock; - } - - return -1; -} - /** * log_distance - Compute distance between two journal blocks * @sdp: The GFS2 superblock @@ -466,17 +452,6 @@ static unsigned int current_tail(struct gfs2_sbd *sdp) return tail; } -void gfs2_log_incr_head(struct gfs2_sbd *sdp) -{ - BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) && - (sdp->sd_log_flush_head != sdp->sd_log_head)); - - if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) { - sdp->sd_log_flush_head = 0; - sdp->sd_log_flush_wrapped = 1; - } -} - static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail) { unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail); @@ -511,8 +486,8 @@ static int bd_cmp(void *priv, struct list_head *a, struct list_head *b) { struct gfs2_bufdata *bda, *bdb; - bda = list_entry(a, struct gfs2_bufdata, bd_le.le_list); - bdb = list_entry(b, struct gfs2_bufdata, bd_le.le_list); + bda = list_entry(a, struct gfs2_bufdata, bd_list); + bdb = list_entry(b, struct gfs2_bufdata, bd_list); if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr) return -1; @@ -530,8 +505,8 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) gfs2_log_lock(sdp); list_sort(NULL, &sdp->sd_log_le_ordered, &bd_cmp); while (!list_empty(&sdp->sd_log_le_ordered)) { - bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list); - list_move(&bd->bd_le.le_list, &written); + bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_list); + list_move(&bd->bd_list, &written); bh = bd->bd_bh; if (!buffer_dirty(bh)) continue; @@ -558,7 +533,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) gfs2_log_lock(sdp); while (!list_empty(&sdp->sd_log_le_ordered)) { - bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_le.le_list); + bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_list); bh = bd->bd_bh; if (buffer_locked(bh)) { get_bh(bh); @@ -568,7 +543,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) gfs2_log_lock(sdp); continue; } - list_del_init(&bd->bd_le.le_list); + list_del_init(&bd->bd_list); } gfs2_log_unlock(sdp); } @@ -580,25 +555,19 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) * Returns: the initialized log buffer descriptor */ -static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) +static void log_write_header(struct gfs2_sbd *sdp, u32 flags) { - u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head); - struct buffer_head *bh; struct gfs2_log_header *lh; unsigned int tail; u32 hash; - - bh = sb_getblk(sdp->sd_vfs, blkno); - lock_buffer(bh); - memset(bh->b_data, 0, bh->b_size); - set_buffer_uptodate(bh); - clear_buffer_dirty(bh); + int rw = WRITE_FLUSH_FUA | REQ_META; + struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + lh = page_address(page); + clear_page(lh); gfs2_ail1_empty(sdp); tail = current_tail(sdp); - lh = (struct gfs2_log_header *)bh->b_data; - memset(lh, 0, sizeof(struct gfs2_log_header)); lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC); lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH); lh->lh_header.__pad0 = cpu_to_be64(0); @@ -608,31 +577,22 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) lh->lh_flags = cpu_to_be32(flags); lh->lh_tail = cpu_to_be32(tail); lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head); - hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header)); + hash = gfs2_disk_hash(page_address(page), sizeof(struct gfs2_log_header)); lh->lh_hash = cpu_to_be32(hash); - bh->b_end_io = end_buffer_write_sync; - get_bh(bh); if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) { gfs2_ordered_wait(sdp); log_flush_wait(sdp); - submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh); - } else { - submit_bh(WRITE_FLUSH_FUA | REQ_META, bh); + rw = WRITE_SYNC | REQ_META | REQ_PRIO; } - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) - gfs2_io_error_bh(sdp, bh); - brelse(bh); + sdp->sd_log_idle = (tail == sdp->sd_log_flush_head); + gfs2_log_write_page(sdp, page); + gfs2_log_flush_bio(sdp, rw); + log_flush_wait(sdp); if (sdp->sd_log_tail != tail) log_pull_tail(sdp, tail); - else - gfs2_assert_withdraw(sdp, !pull); - - sdp->sd_log_idle = (tail == sdp->sd_log_flush_head); - gfs2_log_incr_head(sdp); } /** @@ -678,15 +638,14 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) gfs2_ordered_write(sdp); lops_before_commit(sdp); + gfs2_log_flush_bio(sdp, WRITE); if (sdp->sd_log_head != sdp->sd_log_flush_head) { - log_write_header(sdp, 0, 0); + log_write_header(sdp, 0); } else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){ - gfs2_log_lock(sdp); atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */ trace_gfs2_log_blocks(sdp, -1); - gfs2_log_unlock(sdp); - log_write_header(sdp, 0, PULL); + log_write_header(sdp, 0); } lops_after_commit(sdp, ai); @@ -735,21 +694,6 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) gfs2_log_unlock(sdp); } -static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) -{ - struct list_head *head = &tr->tr_list_buf; - struct gfs2_bufdata *bd; - - gfs2_log_lock(sdp); - while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr); - list_del_init(&bd->bd_list_tr); - tr->tr_num_buf--; - } - gfs2_log_unlock(sdp); - gfs2_assert_warn(sdp, !tr->tr_num_buf); -} - /** * gfs2_log_commit - Commit a transaction to the log * @sdp: the filesystem @@ -768,8 +712,6 @@ static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { log_refund(sdp, tr); - buf_lo_incore_commit(sdp, tr); - up_read(&sdp->sd_log_flush_lock); if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) || @@ -798,8 +740,7 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) sdp->sd_log_flush_head = sdp->sd_log_head; sdp->sd_log_flush_wrapped = 0; - log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT, - (sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL); + log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT); gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks); gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail); @@ -854,11 +795,9 @@ int gfs2_logd(void *data) struct gfs2_sbd *sdp = data; unsigned long t = 1; DEFINE_WAIT(wait); - unsigned preflush; while (!kthread_should_stop()) { - preflush = atomic_read(&sdp->sd_log_pinned); if (gfs2_jrnl_flush_reqd(sdp) || t == 0) { gfs2_ail1_empty(sdp); gfs2_log_flush(sdp, NULL); diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index ff07454b582c..3fd5215ea25f 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -52,8 +52,6 @@ extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct, unsigned int ssize); extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks); -extern void gfs2_log_incr_head(struct gfs2_sbd *sdp); -extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn); extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl); extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans); extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 6b1efb594d90..852c1be1dd3b 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -127,146 +127,277 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, atomic_dec(&sdp->sd_log_pinned); } - -static inline struct gfs2_log_descriptor *bh_log_desc(struct buffer_head *bh) +static void gfs2_log_incr_head(struct gfs2_sbd *sdp) { - return (struct gfs2_log_descriptor *)bh->b_data; + BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) && + (sdp->sd_log_flush_head != sdp->sd_log_head)); + + if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) { + sdp->sd_log_flush_head = 0; + sdp->sd_log_flush_wrapped = 1; + } } -static inline __be64 *bh_log_ptr(struct buffer_head *bh) +static u64 gfs2_log_bmap(struct gfs2_sbd *sdp) { - struct gfs2_log_descriptor *ld = bh_log_desc(bh); - return (__force __be64 *)(ld + 1); + unsigned int lbn = sdp->sd_log_flush_head; + struct gfs2_journal_extent *je; + u64 block; + + list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) { + if (lbn >= je->lblock && lbn < je->lblock + je->blocks) { + block = je->dblock + lbn - je->lblock; + gfs2_log_incr_head(sdp); + return block; + } + } + + return -1; } -static inline __be64 *bh_ptr_end(struct buffer_head *bh) +/** + * gfs2_end_log_write_bh - end log write of pagecache data with buffers + * @sdp: The superblock + * @bvec: The bio_vec + * @error: The i/o status + * + * This finds the relavent buffers and unlocks then and sets the + * error flag according to the status of the i/o request. This is + * used when the log is writing data which has an in-place version + * that is pinned in the pagecache. + */ + +static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, + int error) { - return (__force __be64 *)(bh->b_data + bh->b_size); + struct buffer_head *bh, *next; + struct page *page = bvec->bv_page; + unsigned size; + + bh = page_buffers(page); + size = bvec->bv_len; + while (bh_offset(bh) < bvec->bv_offset) + bh = bh->b_this_page; + do { + if (error) + set_buffer_write_io_error(bh); + unlock_buffer(bh); + next = bh->b_this_page; + size -= bh->b_size; + brelse(bh); + bh = next; + } while(bh && size); } /** - * gfs2_log_write_endio - End of I/O for a log buffer - * @bh: The buffer head - * @uptodate: I/O Status + * gfs2_end_log_write - end of i/o to the log + * @bio: The bio + * @error: Status of i/o request + * + * Each bio_vec contains either data from the pagecache or data + * relating to the log itself. Here we iterate over the bio_vec + * array, processing both kinds of data. * */ -static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate) +static void gfs2_end_log_write(struct bio *bio, int error) { - struct gfs2_sbd *sdp = bh->b_private; - bh->b_private = NULL; + struct gfs2_sbd *sdp = bio->bi_private; + struct bio_vec *bvec; + struct page *page; + int i; - end_buffer_write_sync(bh, uptodate); + if (error) { + sdp->sd_log_error = error; + fs_err(sdp, "Error %d writing to log\n", error); + } + + bio_for_each_segment(bvec, bio, i) { + page = bvec->bv_page; + if (page_has_buffers(page)) + gfs2_end_log_write_bh(sdp, bvec, error); + else + mempool_free(page, gfs2_page_pool); + } + + bio_put(bio); if (atomic_dec_and_test(&sdp->sd_log_in_flight)) wake_up(&sdp->sd_log_flush_wait); } /** - * gfs2_log_get_buf - Get and initialize a buffer to use for log control data - * @sdp: The GFS2 superblock + * gfs2_log_flush_bio - Submit any pending log bio + * @sdp: The superblock + * @rw: The rw flags * - * tReturns: the buffer_head + * Submit any pending part-built or full bio to the block device. If + * there is no pending bio, then this is a no-op. */ -static struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp) +void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw) { - u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head); - struct buffer_head *bh; + if (sdp->sd_log_bio) { + atomic_inc(&sdp->sd_log_in_flight); + submit_bio(rw, sdp->sd_log_bio); + sdp->sd_log_bio = NULL; + } +} - bh = sb_getblk(sdp->sd_vfs, blkno); - lock_buffer(bh); - memset(bh->b_data, 0, bh->b_size); - set_buffer_uptodate(bh); - clear_buffer_dirty(bh); - gfs2_log_incr_head(sdp); - atomic_inc(&sdp->sd_log_in_flight); - bh->b_private = sdp; - bh->b_end_io = gfs2_log_write_endio; +/** + * gfs2_log_alloc_bio - Allocate a new bio for log writing + * @sdp: The superblock + * @blkno: The next device block number we want to write to + * + * This should never be called when there is a cached bio in the + * super block. When it returns, there will be a cached bio in the + * super block which will have as many bio_vecs as the device is + * happy to handle. + * + * Returns: Newly allocated bio + */ - return bh; +static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno) +{ + struct super_block *sb = sdp->sd_vfs; + unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev); + struct bio *bio; + + BUG_ON(sdp->sd_log_bio); + + while (1) { + bio = bio_alloc(GFP_NOIO, nrvecs); + if (likely(bio)) + break; + nrvecs = max(nrvecs/2, 1U); + } + + bio->bi_sector = blkno * (sb->s_blocksize >> 9); + bio->bi_bdev = sb->s_bdev; + bio->bi_end_io = gfs2_end_log_write; + bio->bi_private = sdp; + + sdp->sd_log_bio = bio; + + return bio; } /** - * gfs2_fake_write_endio - - * @bh: The buffer head - * @uptodate: The I/O Status + * gfs2_log_get_bio - Get cached log bio, or allocate a new one + * @sdp: The superblock + * @blkno: The device block number we want to write to + * + * If there is a cached bio, then if the next block number is sequential + * with the previous one, return it, otherwise flush the bio to the + * device. If there is not a cached bio, or we just flushed it, then + * allocate a new one. * + * Returns: The bio to use for log writes */ -static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate) +static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno) { - struct buffer_head *real_bh = bh->b_private; - struct gfs2_bufdata *bd = real_bh->b_private; - struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd; + struct bio *bio = sdp->sd_log_bio; + u64 nblk; + + if (bio) { + nblk = bio->bi_sector + bio_sectors(bio); + nblk >>= sdp->sd_fsb2bb_shift; + if (blkno == nblk) + return bio; + gfs2_log_flush_bio(sdp, WRITE); + } - end_buffer_write_sync(bh, uptodate); - mempool_free(bh, gfs2_bh_pool); - unlock_buffer(real_bh); - brelse(real_bh); - if (atomic_dec_and_test(&sdp->sd_log_in_flight)) - wake_up(&sdp->sd_log_flush_wait); + return gfs2_log_alloc_bio(sdp, blkno); } + /** - * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log + * gfs2_log_write - write to log * @sdp: the filesystem - * @data: the data the buffer_head should point to + * @page: the page to write + * @size: the size of the data to write + * @offset: the offset within the page * - * Returns: the log buffer descriptor + * Try and add the page segment to the current bio. If that fails, + * submit the current bio to the device and create a new one, and + * then add the page segment to that. */ -static struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp, - struct buffer_head *real) +static void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, + unsigned size, unsigned offset) { - u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head); - struct buffer_head *bh; + u64 blkno = gfs2_log_bmap(sdp); + struct bio *bio; + int ret; + + bio = gfs2_log_get_bio(sdp, blkno); + ret = bio_add_page(bio, page, size, offset); + if (ret == 0) { + gfs2_log_flush_bio(sdp, WRITE); + bio = gfs2_log_alloc_bio(sdp, blkno); + ret = bio_add_page(bio, page, size, offset); + WARN_ON(ret == 0); + } +} + +/** + * gfs2_log_write_bh - write a buffer's content to the log + * @sdp: The super block + * @bh: The buffer pointing to the in-place location + * + * This writes the content of the buffer to the next available location + * in the log. The buffer will be unlocked once the i/o to the log has + * completed. + */ - bh = mempool_alloc(gfs2_bh_pool, GFP_NOFS); - atomic_set(&bh->b_count, 1); - bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock); - set_bh_page(bh, real->b_page, bh_offset(real)); - bh->b_blocknr = blkno; - bh->b_size = sdp->sd_sb.sb_bsize; - bh->b_bdev = sdp->sd_vfs->s_bdev; - bh->b_private = real; - bh->b_end_io = gfs2_fake_write_endio; +static void gfs2_log_write_bh(struct gfs2_sbd *sdp, struct buffer_head *bh) +{ + gfs2_log_write(sdp, bh->b_page, bh->b_size, bh_offset(bh)); +} - gfs2_log_incr_head(sdp); - atomic_inc(&sdp->sd_log_in_flight); +/** + * gfs2_log_write_page - write one block stored in a page, into the log + * @sdp: The superblock + * @page: The struct page + * + * This writes the first block-sized part of the page into the log. Note + * that the page must have been allocated from the gfs2_page_pool mempool + * and that after this has been called, ownership has been transferred and + * the page may be freed at any time. + */ - return bh; +void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) +{ + struct super_block *sb = sdp->sd_vfs; + gfs2_log_write(sdp, page, sb->s_blocksize, 0); } -static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type) +static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, + u32 ld_length, u32 ld_data1) { - struct buffer_head *bh = gfs2_log_get_buf(sdp); - struct gfs2_log_descriptor *ld = bh_log_desc(bh); + struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + struct gfs2_log_descriptor *ld = page_address(page); + clear_page(ld); ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC); ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD); ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD); ld->ld_type = cpu_to_be32(ld_type); - ld->ld_length = 0; - ld->ld_data1 = 0; + ld->ld_length = cpu_to_be32(ld_length); + ld->ld_data1 = cpu_to_be32(ld_data1); ld->ld_data2 = 0; - memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved)); - return bh; + return page; } -static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); struct gfs2_meta_header *mh; struct gfs2_trans *tr; lock_buffer(bd->bd_bh); gfs2_log_lock(sdp); - if (!list_empty(&bd->bd_list_tr)) - goto out; tr = current->journal_info; tr->tr_touched = 1; - tr->tr_num_buf++; - list_add(&bd->bd_list_tr, &tr->tr_list_buf); - if (!list_empty(&le->le_list)) + if (!list_empty(&bd->bd_list)) goto out; set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); @@ -276,62 +407,86 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) mh->__pad0 = cpu_to_be64(0); mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); sdp->sd_log_num_buf++; - list_add(&le->le_list, &sdp->sd_log_le_buf); + list_add(&bd->bd_list, &sdp->sd_log_le_buf); tr->tr_num_buf_new++; out: gfs2_log_unlock(sdp); unlock_buffer(bd->bd_bh); } -static void buf_lo_before_commit(struct gfs2_sbd *sdp) +static void gfs2_check_magic(struct buffer_head *bh) +{ + void *kaddr; + __be32 *ptr; + + clear_buffer_escaped(bh); + kaddr = kmap_atomic(bh->b_page); + ptr = kaddr + bh_offset(bh); + if (*ptr == cpu_to_be32(GFS2_MAGIC)) + set_buffer_escaped(bh); + kunmap_atomic(kaddr); +} + +static void gfs2_before_commit(struct gfs2_sbd *sdp, unsigned int limit, + unsigned int total, struct list_head *blist, + bool is_databuf) { - struct buffer_head *bh; struct gfs2_log_descriptor *ld; struct gfs2_bufdata *bd1 = NULL, *bd2; - unsigned int total; - unsigned int limit; + struct page *page; unsigned int num; unsigned n; __be64 *ptr; - limit = buf_limit(sdp); - /* for 4k blocks, limit = 503 */ - gfs2_log_lock(sdp); - total = sdp->sd_log_num_buf; - bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list); + bd1 = bd2 = list_prepare_entry(bd1, blist, bd_list); while(total) { num = total; if (total > limit) num = limit; gfs2_log_unlock(sdp); - bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA); + page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA, num + 1, num); + ld = page_address(page); gfs2_log_lock(sdp); - ld = bh_log_desc(bh); - ptr = bh_log_ptr(bh); - ld->ld_length = cpu_to_be32(num + 1); - ld->ld_data1 = cpu_to_be32(num); + ptr = (__be64 *)(ld + 1); n = 0; - list_for_each_entry_continue(bd1, &sdp->sd_log_le_buf, - bd_le.le_list) { + list_for_each_entry_continue(bd1, blist, bd_list) { *ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr); + if (is_databuf) { + gfs2_check_magic(bd1->bd_bh); + *ptr++ = cpu_to_be64(buffer_escaped(bd1->bd_bh) ? 1 : 0); + } if (++n >= num) break; } gfs2_log_unlock(sdp); - submit_bh(WRITE_SYNC, bh); + gfs2_log_write_page(sdp, page); gfs2_log_lock(sdp); n = 0; - list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf, - bd_le.le_list) { + list_for_each_entry_continue(bd2, blist, bd_list) { get_bh(bd2->bd_bh); gfs2_log_unlock(sdp); lock_buffer(bd2->bd_bh); - bh = gfs2_log_fake_buf(sdp, bd2->bd_bh); - submit_bh(WRITE_SYNC, bh); + + if (buffer_escaped(bd2->bd_bh)) { + void *kaddr; + page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + ptr = page_address(page); + kaddr = kmap_atomic(bd2->bd_bh->b_page); + memcpy(ptr, kaddr + bh_offset(bd2->bd_bh), + bd2->bd_bh->b_size); + kunmap_atomic(kaddr); + *(__be32 *)ptr = 0; + clear_buffer_escaped(bd2->bd_bh); + unlock_buffer(bd2->bd_bh); + brelse(bd2->bd_bh); + gfs2_log_write_page(sdp, page); + } else { + gfs2_log_write_bh(sdp, bd2->bd_bh); + } gfs2_log_lock(sdp); if (++n >= num) break; @@ -343,14 +498,22 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) gfs2_log_unlock(sdp); } +static void buf_lo_before_commit(struct gfs2_sbd *sdp) +{ + unsigned int limit = buf_limit(sdp); /* 503 for 4k blocks */ + + gfs2_before_commit(sdp, limit, sdp->sd_log_num_buf, + &sdp->sd_log_le_buf, 0); +} + static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) { struct list_head *head = &sdp->sd_log_le_buf; struct gfs2_bufdata *bd; while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list); - list_del_init(&bd->bd_le.le_list); + bd = list_entry(head->next, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); sdp->sd_log_num_buf--; gfs2_unpin(sdp, bd->bd_bh, ai); @@ -437,9 +600,8 @@ static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass) jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks); } -static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); struct gfs2_glock *gl = bd->bd_gl; struct gfs2_trans *tr; @@ -449,48 +611,48 @@ static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) sdp->sd_log_num_revoke++; atomic_inc(&gl->gl_revokes); set_bit(GLF_LFLUSH, &gl->gl_flags); - list_add(&le->le_list, &sdp->sd_log_le_revoke); + list_add(&bd->bd_list, &sdp->sd_log_le_revoke); } static void revoke_lo_before_commit(struct gfs2_sbd *sdp) { struct gfs2_log_descriptor *ld; struct gfs2_meta_header *mh; - struct buffer_head *bh; unsigned int offset; struct list_head *head = &sdp->sd_log_le_revoke; struct gfs2_bufdata *bd; + struct page *page; + unsigned int length; if (!sdp->sd_log_num_revoke) return; - bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE); - ld = bh_log_desc(bh); - ld->ld_length = cpu_to_be32(gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, - sizeof(u64))); - ld->ld_data1 = cpu_to_be32(sdp->sd_log_num_revoke); + length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64)); + page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke); + ld = page_address(page); offset = sizeof(struct gfs2_log_descriptor); - list_for_each_entry(bd, head, bd_le.le_list) { + list_for_each_entry(bd, head, bd_list) { sdp->sd_log_num_revoke--; if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) { - submit_bh(WRITE_SYNC, bh); - bh = gfs2_log_get_buf(sdp); - mh = (struct gfs2_meta_header *)bh->b_data; + gfs2_log_write_page(sdp, page); + page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + mh = page_address(page); + clear_page(mh); mh->mh_magic = cpu_to_be32(GFS2_MAGIC); mh->mh_type = cpu_to_be32(GFS2_METATYPE_LB); mh->mh_format = cpu_to_be32(GFS2_FORMAT_LB); offset = sizeof(struct gfs2_meta_header); } - *(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno); + *(__be64 *)(page_address(page) + offset) = cpu_to_be64(bd->bd_blkno); offset += sizeof(u64); } gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); - submit_bh(WRITE_SYNC, bh); + gfs2_log_write_page(sdp, page); } static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) @@ -500,8 +662,8 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) struct gfs2_glock *gl; while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list); - list_del_init(&bd->bd_le.le_list); + bd = list_entry(head->next, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); gl = bd->bd_gl; atomic_dec(&gl->gl_revokes); clear_bit(GLF_LFLUSH, &gl->gl_flags); @@ -604,108 +766,33 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass) * blocks, which isn't an enormous overhead but twice as much as * for normal metadata blocks. */ -static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); struct gfs2_trans *tr = current->journal_info; struct address_space *mapping = bd->bd_bh->b_page->mapping; struct gfs2_inode *ip = GFS2_I(mapping->host); lock_buffer(bd->bd_bh); gfs2_log_lock(sdp); - if (tr) { - if (!list_empty(&bd->bd_list_tr)) - goto out; + if (tr) tr->tr_touched = 1; - if (gfs2_is_jdata(ip)) { - tr->tr_num_buf++; - list_add(&bd->bd_list_tr, &tr->tr_list_buf); - } - } - if (!list_empty(&le->le_list)) + if (!list_empty(&bd->bd_list)) goto out; - set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); if (gfs2_is_jdata(ip)) { gfs2_pin(sdp, bd->bd_bh); tr->tr_num_databuf_new++; sdp->sd_log_num_databuf++; - list_add_tail(&le->le_list, &sdp->sd_log_le_databuf); + list_add_tail(&bd->bd_list, &sdp->sd_log_le_databuf); } else { - list_add_tail(&le->le_list, &sdp->sd_log_le_ordered); + list_add_tail(&bd->bd_list, &sdp->sd_log_le_ordered); } out: gfs2_log_unlock(sdp); unlock_buffer(bd->bd_bh); } -static void gfs2_check_magic(struct buffer_head *bh) -{ - void *kaddr; - __be32 *ptr; - - clear_buffer_escaped(bh); - kaddr = kmap_atomic(bh->b_page); - ptr = kaddr + bh_offset(bh); - if (*ptr == cpu_to_be32(GFS2_MAGIC)) - set_buffer_escaped(bh); - kunmap_atomic(kaddr); -} - -static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, - struct list_head *list, struct list_head *done, - unsigned int n) -{ - struct buffer_head *bh1; - struct gfs2_log_descriptor *ld; - struct gfs2_bufdata *bd; - __be64 *ptr; - - if (!bh) - return; - - ld = bh_log_desc(bh); - ld->ld_length = cpu_to_be32(n + 1); - ld->ld_data1 = cpu_to_be32(n); - - ptr = bh_log_ptr(bh); - - get_bh(bh); - submit_bh(WRITE_SYNC, bh); - gfs2_log_lock(sdp); - while(!list_empty(list)) { - bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list); - list_move_tail(&bd->bd_le.le_list, done); - get_bh(bd->bd_bh); - while (be64_to_cpu(*ptr) != bd->bd_bh->b_blocknr) { - gfs2_log_incr_head(sdp); - ptr += 2; - } - gfs2_log_unlock(sdp); - lock_buffer(bd->bd_bh); - if (buffer_escaped(bd->bd_bh)) { - void *kaddr; - bh1 = gfs2_log_get_buf(sdp); - kaddr = kmap_atomic(bd->bd_bh->b_page); - memcpy(bh1->b_data, kaddr + bh_offset(bd->bd_bh), - bh1->b_size); - kunmap_atomic(kaddr); - *(__be32 *)bh1->b_data = 0; - clear_buffer_escaped(bd->bd_bh); - unlock_buffer(bd->bd_bh); - brelse(bd->bd_bh); - } else { - bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh); - } - submit_bh(WRITE_SYNC, bh1); - gfs2_log_lock(sdp); - ptr += 2; - } - gfs2_log_unlock(sdp); - brelse(bh); -} - /** * databuf_lo_before_commit - Scan the data buffers, writing as we go * @@ -713,37 +800,10 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, static void databuf_lo_before_commit(struct gfs2_sbd *sdp) { - struct gfs2_bufdata *bd = NULL; - struct buffer_head *bh = NULL; - unsigned int n = 0; - __be64 *ptr = NULL, *end = NULL; - LIST_HEAD(processed); - LIST_HEAD(in_progress); + unsigned int limit = buf_limit(sdp) / 2; - gfs2_log_lock(sdp); - while (!list_empty(&sdp->sd_log_le_databuf)) { - if (ptr == end) { - gfs2_log_unlock(sdp); - gfs2_write_blocks(sdp, bh, &in_progress, &processed, n); - n = 0; - bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_JDATA); - ptr = bh_log_ptr(bh); - end = bh_ptr_end(bh) - 1; - gfs2_log_lock(sdp); - continue; - } - bd = list_entry(sdp->sd_log_le_databuf.next, struct gfs2_bufdata, bd_le.le_list); - list_move_tail(&bd->bd_le.le_list, &in_progress); - gfs2_check_magic(bd->bd_bh); - *ptr++ = cpu_to_be64(bd->bd_bh->b_blocknr); - *ptr++ = cpu_to_be64(buffer_escaped(bh) ? 1 : 0); - n++; - } - gfs2_log_unlock(sdp); - gfs2_write_blocks(sdp, bh, &in_progress, &processed, n); - gfs2_log_lock(sdp); - list_splice(&processed, &sdp->sd_log_le_databuf); - gfs2_log_unlock(sdp); + gfs2_before_commit(sdp, limit, sdp->sd_log_num_databuf, + &sdp->sd_log_le_databuf, 1); } static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start, @@ -822,8 +882,8 @@ static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) struct gfs2_bufdata *bd; while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list); - list_del_init(&bd->bd_le.le_list); + bd = list_entry(head->next, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); sdp->sd_log_num_databuf--; gfs2_unpin(sdp, bd->bd_bh, ai); } diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 3c0b2737658a..954a330585f4 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -27,6 +27,8 @@ extern const struct gfs2_log_operations gfs2_rg_lops; extern const struct gfs2_log_operations gfs2_databuf_lops; extern const struct gfs2_log_operations *gfs2_log_ops[]; +extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); +extern void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { @@ -44,17 +46,17 @@ static inline unsigned int databuf_limit(struct gfs2_sbd *sdp) return limit; } -static inline void lops_init_le(struct gfs2_log_element *le, +static inline void lops_init_le(struct gfs2_bufdata *bd, const struct gfs2_log_operations *lops) { - INIT_LIST_HEAD(&le->le_list); - le->le_ops = lops; + INIT_LIST_HEAD(&bd->bd_list); + bd->bd_ops = lops; } -static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - if (le->le_ops->lo_add) - le->le_ops->lo_add(sdp, le); + if (bd->bd_ops->lo_add) + bd->bd_ops->lo_add(sdp, bd); } static inline void lops_before_commit(struct gfs2_sbd *sdp) diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 754426b1e52c..6cdb0f2a1b09 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -70,16 +70,6 @@ static void gfs2_init_gl_aspace_once(void *foo) address_space_init_once(mapping); } -static void *gfs2_bh_alloc(gfp_t mask, void *data) -{ - return alloc_buffer_head(mask); -} - -static void gfs2_bh_free(void *ptr, void *data) -{ - return free_buffer_head(ptr); -} - /** * init_gfs2_fs - Register GFS2 as a filesystem * @@ -143,6 +133,12 @@ static int __init init_gfs2_fs(void) if (!gfs2_quotad_cachep) goto fail; + gfs2_rsrv_cachep = kmem_cache_create("gfs2_mblk", + sizeof(struct gfs2_blkreserv), + 0, 0, NULL); + if (!gfs2_rsrv_cachep) + goto fail; + register_shrinker(&qd_shrinker); error = register_filesystem(&gfs2_fs_type); @@ -164,8 +160,8 @@ static int __init init_gfs2_fs(void) if (!gfs2_control_wq) goto fail_recovery; - gfs2_bh_pool = mempool_create(1024, gfs2_bh_alloc, gfs2_bh_free, NULL); - if (!gfs2_bh_pool) + gfs2_page_pool = mempool_create_page_pool(64, 0); + if (!gfs2_page_pool) goto fail_control; gfs2_register_debugfs(); @@ -186,6 +182,9 @@ fail: unregister_shrinker(&qd_shrinker); gfs2_glock_exit(); + if (gfs2_rsrv_cachep) + kmem_cache_destroy(gfs2_rsrv_cachep); + if (gfs2_quotad_cachep) kmem_cache_destroy(gfs2_quotad_cachep); @@ -225,7 +224,8 @@ static void __exit exit_gfs2_fs(void) rcu_barrier(); - mempool_destroy(gfs2_bh_pool); + mempool_destroy(gfs2_page_pool); + kmem_cache_destroy(gfs2_rsrv_cachep); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); kmem_cache_destroy(gfs2_bufdata_cachep); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 181586e673f9..6c1e5d1c404a 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -293,11 +293,10 @@ void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh, bd->bd_bh = bh; bd->bd_gl = gl; - INIT_LIST_HEAD(&bd->bd_list_tr); if (meta) - lops_init_le(&bd->bd_le, &gfs2_buf_lops); + lops_init_le(bd, &gfs2_buf_lops); else - lops_init_le(&bd->bd_le, &gfs2_databuf_lops); + lops_init_le(bd, &gfs2_databuf_lops); bh->b_private = bd; if (meta) @@ -313,7 +312,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int if (test_clear_buffer_pinned(bh)) { trace_gfs2_pin(bd, 0); atomic_dec(&sdp->sd_log_pinned); - list_del_init(&bd->bd_le.le_list); + list_del_init(&bd->bd_list); if (meta) { gfs2_assert_warn(sdp, sdp->sd_log_num_buf); sdp->sd_log_num_buf--; @@ -375,33 +374,24 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen) * @ip: The GFS2 inode * @height: The level of this buf in the metadata (indir addr) tree (if any) * @num: The block number (device relative) of the buffer - * @new: Non-zero if we may create a new buffer * @bhp: the buffer is returned here * * Returns: errno */ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, - int new, struct buffer_head **bhp) + struct buffer_head **bhp) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_glock *gl = ip->i_gl; struct buffer_head *bh; int ret = 0; + u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI; - if (new) { - BUG_ON(height == 0); - bh = gfs2_meta_new(gl, num); - gfs2_trans_add_bh(ip->i_gl, bh, 1); - gfs2_metatype_set(bh, GFS2_METATYPE_IN, GFS2_FORMAT_IN); - gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header)); - } else { - u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI; - ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh); - if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { - brelse(bh); - ret = -EIO; - } + ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh); + if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { + brelse(bh); + ret = -EIO; } *bhp = bh; return ret; diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 22c526593131..c30973b07a7c 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -65,12 +65,12 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen); int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, - int new, struct buffer_head **bhp); + struct buffer_head **bhp); static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip, struct buffer_head **bhp) { - return gfs2_meta_indirect_buffer(ip, 0, ip->i_no_addr, 0, bhp); + return gfs2_meta_indirect_buffer(ip, 0, ip->i_no_addr, bhp); } struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 6f3a18f9e176..c5871ae40561 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -99,7 +99,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) atomic_set(&sdp->sd_log_pinned, 0); INIT_LIST_HEAD(&sdp->sd_log_le_buf); INIT_LIST_HEAD(&sdp->sd_log_le_revoke); - INIT_LIST_HEAD(&sdp->sd_log_le_rg); INIT_LIST_HEAD(&sdp->sd_log_le_databuf); INIT_LIST_HEAD(&sdp->sd_log_le_ordered); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 6019da3dcaed..b97178e7d397 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -652,7 +652,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, } memset(&q, 0, sizeof(struct gfs2_quota)); - err = gfs2_internal_read(ip, NULL, (char *)&q, &loc, sizeof(q)); + err = gfs2_internal_read(ip, (char *)&q, &loc, sizeof(q)); if (err < 0) return err; @@ -744,7 +744,7 @@ get_a_page: i_size_write(inode, size); inode->i_mtime = inode->i_atime = CURRENT_TIME; mark_inode_dirty(inode); - return err; + return 0; unlock_out: unlock_page(page); @@ -852,7 +852,7 @@ static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd) memset(&q, 0, sizeof(struct gfs2_quota)); pos = qd2offset(qd); - error = gfs2_internal_read(ip, NULL, (char *)&q, &pos, sizeof(q)); + error = gfs2_internal_read(ip, (char *)&q, &pos, sizeof(q)); if (error < 0) return error; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 3df65c9ab73b..f74fb9bd1973 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -70,15 +70,15 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, /** * gfs2_setbit - Set a bit in the bitmaps - * @buffer: the buffer that holds the bitmaps - * @buflen: the length (in bytes) of the buffer + * @rgd: the resource group descriptor + * @buf2: the clone buffer that holds the bitmaps + * @bi: the bitmap structure * @block: the block to set * @new_state: the new state of the block * */ -static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1, - unsigned char *buf2, unsigned int offset, +static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf2, struct gfs2_bitmap *bi, u32 block, unsigned char new_state) { @@ -86,8 +86,8 @@ static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1, unsigned int buflen = bi->bi_len; const unsigned int bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE; - byte1 = buf1 + offset + (block / GFS2_NBBY); - end = buf1 + offset + buflen; + byte1 = bi->bi_bh->b_data + bi->bi_offset + (block / GFS2_NBBY); + end = bi->bi_bh->b_data + bi->bi_offset + buflen; BUG_ON(byte1 >= end); @@ -110,7 +110,7 @@ static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1, *byte1 ^= (cur_state ^ new_state) << bit; if (buf2) { - byte2 = buf2 + offset + (block / GFS2_NBBY); + byte2 = buf2 + bi->bi_offset + (block / GFS2_NBBY); cur_state = (*byte2 >> bit) & GFS2_BIT_MASK; *byte2 ^= (cur_state ^ new_state) << bit; } @@ -118,6 +118,7 @@ static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1, /** * gfs2_testbit - test a bit in the bitmaps + * @rgd: the resource group descriptor * @buffer: the buffer that holds the bitmaps * @buflen: the length (in bytes) of the buffer * @block: the block to read @@ -179,7 +180,7 @@ static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state) /** * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing * a block in a given allocation state. - * @buffer: the buffer that holds the bitmaps + * @buf: the buffer that holds the bitmaps * @len: the length (in bytes) of the buffer * @goal: start search at this block's bit-pair (within @buffer) * @state: GFS2_BLKST_XXX the state of the block we're looking for. @@ -231,6 +232,7 @@ static u32 gfs2_bitfit(const u8 *buf, const unsigned int len, /** * gfs2_bitcount - count the number of bits in a certain state + * @rgd: the resource group descriptor * @buffer: the buffer that holds the bitmaps * @buflen: the length (in bytes) of the buffer * @state: the state of the block we're looking for @@ -264,7 +266,6 @@ static u32 gfs2_bitcount(struct gfs2_rgrpd *rgd, const u8 *buffer, /** * gfs2_rgrp_verify - Verify that a resource group is consistent - * @sdp: the filesystem * @rgd: the rgrp * */ @@ -322,7 +323,8 @@ static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block) /** * gfs2_blk2rgrpd - Find resource group for a given data/meta block number * @sdp: The GFS2 superblock - * @n: The data block number + * @blk: The data block number + * @exact: True if this needs to be an exact match * * Returns: The resource group, or NULL if not found */ @@ -380,7 +382,7 @@ struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp) /** * gfs2_rgrpd_get_next - get the next RG - * @rgd: A RG + * @rgd: the resource group descriptor * * Returns: The next rgrp */ @@ -529,6 +531,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) /** * gfs2_ri_total - Total up the file system space, according to the rindex. + * @sdp: the filesystem * */ u64 gfs2_ri_total(struct gfs2_sbd *sdp) @@ -537,16 +540,14 @@ u64 gfs2_ri_total(struct gfs2_sbd *sdp) struct inode *inode = sdp->sd_rindex; struct gfs2_inode *ip = GFS2_I(inode); char buf[sizeof(struct gfs2_rindex)]; - struct file_ra_state ra_state; int error, rgrps; - file_ra_state_init(&ra_state, inode->i_mapping); for (rgrps = 0;; rgrps++) { loff_t pos = rgrps * sizeof(struct gfs2_rindex); if (pos + sizeof(struct gfs2_rindex) > i_size_read(inode)) break; - error = gfs2_internal_read(ip, &ra_state, buf, &pos, + error = gfs2_internal_read(ip, buf, &pos, sizeof(struct gfs2_rindex)); if (error != sizeof(struct gfs2_rindex)) break; @@ -582,13 +583,12 @@ static int rgd_insert(struct gfs2_rgrpd *rgd) /** * read_rindex_entry - Pull in a new resource index entry from the disk - * @gl: The glock covering the rindex inode + * @ip: Pointer to the rindex inode * * Returns: 0 on success, > 0 on EOF, error code otherwise */ -static int read_rindex_entry(struct gfs2_inode *ip, - struct file_ra_state *ra_state) +static int read_rindex_entry(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex); @@ -599,7 +599,7 @@ static int read_rindex_entry(struct gfs2_inode *ip, if (pos >= i_size_read(&ip->i_inode)) return 1; - error = gfs2_internal_read(ip, ra_state, (char *)&buf, &pos, + error = gfs2_internal_read(ip, (char *)&buf, &pos, sizeof(struct gfs2_rindex)); if (error != sizeof(struct gfs2_rindex)) @@ -655,13 +655,10 @@ fail: static int gfs2_ri_update(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct inode *inode = &ip->i_inode; - struct file_ra_state ra_state; int error; - file_ra_state_init(&ra_state, inode->i_mapping); do { - error = read_rindex_entry(ip, &ra_state); + error = read_rindex_entry(ip); } while (error == 0); if (error < 0) @@ -741,7 +738,7 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf) /** * gfs2_rgrp_go_lock - Read in a RG's header and bitmaps - * @rgd: the struct gfs2_rgrpd describing the RG to read in + * @gh: The glock holder for the resource group * * Read in all of a Resource Group's header and bitmap blocks. * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps. @@ -801,7 +798,7 @@ fail: /** * gfs2_rgrp_go_unlock - Release RG bitmaps read in with gfs2_rgrp_bh_get() - * @rgd: the struct gfs2_rgrpd describing the RG to read in + * @gh: The glock holder for the resource group * */ @@ -1002,11 +999,13 @@ struct gfs2_qadata *gfs2_qadata_get(struct gfs2_inode *ip) * Returns: the struct gfs2_qadata */ -static struct gfs2_blkreserv *gfs2_blkrsv_get(struct gfs2_inode *ip) +static int gfs2_blkrsv_get(struct gfs2_inode *ip) { BUG_ON(ip->i_res != NULL); - ip->i_res = kzalloc(sizeof(struct gfs2_blkreserv), GFP_NOFS); - return ip->i_res; + ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS); + if (!ip->i_res) + return -ENOMEM; + return 0; } /** @@ -1038,6 +1037,8 @@ static inline u32 gfs2_bi2rgd_blk(struct gfs2_bitmap *bi, u32 blk) /** * try_rgrp_unlink - Look for any unlinked, allocated, but unused inodes * @rgd: The rgrp + * @last_unlinked: block address of the last dinode we unlinked + * @skip: block address we should explicitly not unlink * * Returns: 0 if no error * The inode, if one has been found, in inode. @@ -1102,7 +1103,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip /** * get_local_rgrp - Choose and lock a rgrp for allocation * @ip: the inode to reserve space for - * @rgp: the chosen and locked rgrp + * @last_unlinked: the last unlinked block * * Try to acquire rgrp in way which avoids contending with others. * @@ -1164,13 +1165,14 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked) static void gfs2_blkrsv_put(struct gfs2_inode *ip) { BUG_ON(ip->i_res == NULL); - kfree(ip->i_res); + kmem_cache_free(gfs2_rsrv_cachep, ip->i_res); ip->i_res = NULL; } /** * gfs2_inplace_reserve - Reserve space in the filesystem * @ip: the inode to reserve space for + * @requested: the number of blocks to be reserved * * Returns: errno */ @@ -1179,14 +1181,15 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, u32 requested) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_blkreserv *rs; - int error = 0; + int error; u64 last_unlinked = NO_BLOCK; int tries = 0; - rs = gfs2_blkrsv_get(ip); - if (!rs) - return -ENOMEM; + error = gfs2_blkrsv_get(ip); + if (error) + return error; + rs = ip->i_res; rs->rs_requested = requested; if (gfs2_assert_warn(sdp, requested)) { error = -EINVAL; @@ -1268,7 +1271,6 @@ static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block) * @rgd: the resource group descriptor * @goal: the goal block within the RG (start here to search for avail block) * @state: GFS2_BLKST_XXX the before-allocation state to find - * @dinode: TRUE if the first block we allocate is for a dinode * @rbi: address of the pointer to the bitmap containing the block found * * Walk rgrp's bitmap to find bits that represent a block in @state. @@ -1282,13 +1284,12 @@ static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block) * Returns: the block number found relative to the bitmap rbi */ -static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, - unsigned char state, +static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, unsigned char state, struct gfs2_bitmap **rbi) { struct gfs2_bitmap *bi = NULL; const u32 length = rgd->rd_length; - u32 blk = BFITNOENT; + u32 biblk = BFITNOENT; unsigned int buf, x; const u8 *buffer = NULL; @@ -1325,8 +1326,8 @@ do_search: if (state != GFS2_BLKST_UNLINKED && bi->bi_clone) buffer = bi->bi_clone + bi->bi_offset; - blk = gfs2_bitfit(buffer, bi->bi_len, goal, state); - if (blk != BFITNOENT) + biblk = gfs2_bitfit(buffer, bi->bi_len, goal, state); + if (biblk != BFITNOENT) break; if ((goal == 0) && (state == GFS2_BLKST_FREE)) @@ -1339,10 +1340,10 @@ skip: goal = 0; } - if (blk != BFITNOENT) + if (biblk != BFITNOENT) *rbi = bi; - return blk; + return biblk; } /** @@ -1367,8 +1368,8 @@ static u64 gfs2_alloc_extent(struct gfs2_rgrpd *rgd, struct gfs2_bitmap *bi, *n = 0; buffer = bi->bi_bh->b_data + bi->bi_offset; gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); - gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset, - bi, blk, dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); + gfs2_setbit(rgd, bi->bi_clone, bi, blk, + dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); (*n)++; goal = blk; while (*n < elen) { @@ -1378,8 +1379,7 @@ static u64 gfs2_alloc_extent(struct gfs2_rgrpd *rgd, struct gfs2_bitmap *bi, if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) != GFS2_BLKST_FREE) break; - gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset, - bi, goal, GFS2_BLKST_USED); + gfs2_setbit(rgd, bi->bi_clone, bi, goal, GFS2_BLKST_USED); (*n)++; } blk = gfs2_bi2rgd_blk(bi, blk); @@ -1436,8 +1436,7 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, bi->bi_len); } gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); - gfs2_setbit(rgd, bi->bi_bh->b_data, NULL, bi->bi_offset, - bi, buf_blk, new_state); + gfs2_setbit(rgd, NULL, bi, buf_blk, new_state); } return rgd; @@ -1557,7 +1556,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, ip->i_inode.i_gid); rgd->rd_free_clone -= *nblocks; - trace_gfs2_block_alloc(ip, block, *nblocks, + trace_gfs2_block_alloc(ip, rgd, block, *nblocks, dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); *bn = block; return 0; @@ -1584,7 +1583,7 @@ void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta) rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE); if (!rgd) return; - trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE); + trace_gfs2_block_alloc(ip, rgd, bstart, blen, GFS2_BLKST_FREE); rgd->rd_free += blen; rgd->rd_flags &= ~GFS2_RGF_TRIMMED; gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); @@ -1622,7 +1621,7 @@ void gfs2_unlink_di(struct inode *inode) rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED); if (!rgd) return; - trace_gfs2_block_alloc(ip, blkno, 1, GFS2_BLKST_UNLINKED); + trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED); gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data); } @@ -1652,7 +1651,7 @@ static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno) void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) { gfs2_free_uninit_di(rgd, ip->i_no_addr); - trace_gfs2_block_alloc(ip, ip->i_no_addr, 1, GFS2_BLKST_FREE); + trace_gfs2_block_alloc(ip, rgd, ip->i_no_addr, 1, GFS2_BLKST_FREE); gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid); gfs2_meta_wipe(ip, ip->i_no_addr, 1); } @@ -1752,7 +1751,6 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist, * and initialize an array of glock holders for them * @rlist: the list of resource groups * @state: the lock state to acquire the RG lock in - * @flags: the modifier flags for the holder structures * * FIXME: Don't use NOFAIL * diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h index dfa89cd75534..1b8b81588199 100644 --- a/fs/gfs2/trace_gfs2.h +++ b/fs/gfs2/trace_gfs2.h @@ -457,10 +457,10 @@ TRACE_EVENT(gfs2_bmap, /* Keep track of blocks as they are allocated/freed */ TRACE_EVENT(gfs2_block_alloc, - TP_PROTO(const struct gfs2_inode *ip, u64 block, unsigned len, - u8 block_state), + TP_PROTO(const struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, + u64 block, unsigned len, u8 block_state), - TP_ARGS(ip, block, len, block_state), + TP_ARGS(ip, rgd, block, len, block_state), TP_STRUCT__entry( __field( dev_t, dev ) @@ -468,6 +468,8 @@ TRACE_EVENT(gfs2_block_alloc, __field( u64, inum ) __field( u32, len ) __field( u8, block_state ) + __field( u64, rd_addr ) + __field( u32, rd_free_clone ) ), TP_fast_assign( @@ -476,14 +478,18 @@ TRACE_EVENT(gfs2_block_alloc, __entry->inum = ip->i_no_addr; __entry->len = len; __entry->block_state = block_state; + __entry->rd_addr = rgd->rd_addr; + __entry->rd_free_clone = rgd->rd_free_clone; ), - TP_printk("%u,%u bmap %llu alloc %llu/%lu %s", + TP_printk("%u,%u bmap %llu alloc %llu/%lu %s rg:%llu rf:%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->inum, (unsigned long long)__entry->start, (unsigned long)__entry->len, - block_state_name(__entry->block_state)) + block_state_name(__entry->block_state), + (unsigned long long)__entry->rd_addr, + __entry->rd_free_clone) ); #endif /* _TRACE_GFS2_H */ diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 86ac75d99d31..ad3e2fb763d7 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -50,8 +50,6 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, if (revokes) tr->tr_reserved += gfs2_struct2blk(sdp, revokes, sizeof(u64)); - INIT_LIST_HEAD(&tr->tr_list_buf); - gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh); error = gfs2_glock_nq(&tr->tr_t_gh); @@ -93,10 +91,21 @@ static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks) up_read(&sdp->sd_log_flush_lock); } +static void gfs2_print_trans(const struct gfs2_trans *tr) +{ + print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip); + printk(KERN_WARNING "GFS2: blocks=%u revokes=%u reserved=%u touched=%d\n", + tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched); + printk(KERN_WARNING "GFS2: Buf %u/%u Databuf %u/%u Revoke %u/%u\n", + tr->tr_num_buf_new, tr->tr_num_buf_rm, + tr->tr_num_databuf_new, tr->tr_num_databuf_rm, + tr->tr_num_revoke, tr->tr_num_revoke_rm); +} + void gfs2_trans_end(struct gfs2_sbd *sdp) { struct gfs2_trans *tr = current->journal_info; - + s64 nbuf; BUG_ON(!tr); current->journal_info = NULL; @@ -110,16 +119,13 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) return; } - if (gfs2_assert_withdraw(sdp, tr->tr_num_buf <= tr->tr_blocks)) { - fs_err(sdp, "tr_num_buf = %u, tr_blocks = %u ", - tr->tr_num_buf, tr->tr_blocks); - print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip); - } - if (gfs2_assert_withdraw(sdp, tr->tr_num_revoke <= tr->tr_revokes)) { - fs_err(sdp, "tr_num_revoke = %u, tr_revokes = %u ", - tr->tr_num_revoke, tr->tr_revokes); - print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip); - } + nbuf = tr->tr_num_buf_new + tr->tr_num_databuf_new; + nbuf -= tr->tr_num_buf_rm; + nbuf -= tr->tr_num_databuf_rm; + + if (gfs2_assert_withdraw(sdp, (nbuf <= tr->tr_blocks) && + (tr->tr_num_revoke <= tr->tr_revokes))) + gfs2_print_trans(tr); gfs2_log_commit(sdp, tr); if (tr->tr_t_gh.gh_gl) { @@ -152,16 +158,16 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta) gfs2_attach_bufdata(gl, bh, meta); bd = bh->b_private; } - lops_add(sdp, &bd->bd_le); + lops_add(sdp, bd); } void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - BUG_ON(!list_empty(&bd->bd_le.le_list)); + BUG_ON(!list_empty(&bd->bd_list)); BUG_ON(!list_empty(&bd->bd_ail_st_list)); BUG_ON(!list_empty(&bd->bd_ail_gl_list)); - lops_init_le(&bd->bd_le, &gfs2_revoke_lops); - lops_add(sdp, &bd->bd_le); + lops_init_le(bd, &gfs2_revoke_lops); + lops_add(sdp, bd); } void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) @@ -171,9 +177,9 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) unsigned int n = len; gfs2_log_lock(sdp); - list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_le.le_list) { + list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_list) { if ((bd->bd_blkno >= blkno) && (bd->bd_blkno < (blkno + len))) { - list_del_init(&bd->bd_le.le_list); + list_del_init(&bd->bd_list); gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke); sdp->sd_log_num_revoke--; kmem_cache_free(gfs2_bufdata_cachep, bd); diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 9e7765e8e7b0..f00d7c5744f6 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -25,7 +25,8 @@ struct kmem_cache *gfs2_inode_cachep __read_mostly; struct kmem_cache *gfs2_bufdata_cachep __read_mostly; struct kmem_cache *gfs2_rgrpd_cachep __read_mostly; struct kmem_cache *gfs2_quotad_cachep __read_mostly; -mempool_t *gfs2_bh_pool __read_mostly; +struct kmem_cache *gfs2_rsrv_cachep __read_mostly; +mempool_t *gfs2_page_pool __read_mostly; void gfs2_assert_i(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index a4ce76c67dbb..3586b0dd6aa7 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -152,7 +152,8 @@ extern struct kmem_cache *gfs2_inode_cachep; extern struct kmem_cache *gfs2_bufdata_cachep; extern struct kmem_cache *gfs2_rgrpd_cachep; extern struct kmem_cache *gfs2_quotad_cachep; -extern mempool_t *gfs2_bh_pool; +extern struct kmem_cache *gfs2_rsrv_cachep; +extern mempool_t *gfs2_page_pool; static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt, unsigned int *p) diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 4dfbfec357e8..ec2a9c23f0c9 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -366,6 +366,10 @@ int hfsplus_rename_cat(u32 cnid, err = hfs_brec_find(&src_fd); if (err) goto out; + if (src_fd.entrylength > sizeof(entry) || src_fd.entrylength < 0) { + err = -EIO; + goto out; + } hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset, src_fd.entrylength); diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 88e155f895c6..26b53fb09f68 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -150,6 +150,11 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) filp->f_pos++; /* fall through */ case 1: + if (fd.entrylength > sizeof(entry) || fd.entrylength < 0) { + err = -EIO; + goto out; + } + hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); if (be16_to_cpu(entry.type) != HFSPLUS_FOLDER_THREAD) { @@ -181,6 +186,12 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) err = -EIO; goto out; } + + if (fd.entrylength > sizeof(entry) || fd.entrylength < 0) { + err = -EIO; + goto out; + } + hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); type = be16_to_cpu(entry.type); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 28cf06e4ec84..001ef01d2fe2 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -485,6 +485,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); + lockdep_annotate_inode_mutex_key(inode); } return inode; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 806525a7269c..840f70f50792 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -723,7 +723,7 @@ start_journal_io: if (commit_transaction->t_need_data_flush && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL); /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, @@ -859,7 +859,7 @@ wait_for_iobuf: if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) && journal->j_flags & JBD2_BARRIER) { - blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL); + blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL); } if (err) diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index ad271c70aa25..5a2dec2b064c 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -234,8 +234,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c) return 0; jffs2_dbg(1, "No progress from erasing block; doing GC anyway\n"); - spin_lock(&c->erase_completion_lock); mutex_lock(&c->alloc_sem); + spin_lock(&c->erase_completion_lock); } /* First, work out which block we're garbage-collecting */ diff --git a/fs/libfs.c b/fs/libfs.c index 18d08f5db53a..f86ec27a4230 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -68,7 +68,7 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct na int dcache_dir_open(struct inode *inode, struct file *file) { - static struct qstr cursor_name = {.len = 1, .name = "."}; + static struct qstr cursor_name = QSTR_INIT(".", 1); file->private_data = d_alloc(file->f_path.dentry, &cursor_name); @@ -225,7 +225,7 @@ struct dentry *mount_pseudo(struct file_system_type *fs_type, char *name, struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); struct dentry *dentry; struct inode *root; - struct qstr d_name = {.name = name, .len = strlen(name)}; + struct qstr d_name = QSTR_INIT(name, strlen(name)); if (IS_ERR(s)) return ERR_CAST(s); diff --git a/fs/namei.c b/fs/namei.c index 0062dd17eb55..f9e883c1b856 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -116,47 +116,37 @@ * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ -static int do_getname(const char __user *filename, char *page) -{ - int retval; - unsigned long len = PATH_MAX; - - if (!segment_eq(get_fs(), KERNEL_DS)) { - if ((unsigned long) filename >= TASK_SIZE) - return -EFAULT; - if (TASK_SIZE - (unsigned long) filename < PATH_MAX) - len = TASK_SIZE - (unsigned long) filename; - } - - retval = strncpy_from_user(page, filename, len); - if (retval > 0) { - if (retval < len) - return 0; - return -ENAMETOOLONG; - } else if (!retval) - retval = -ENOENT; - return retval; -} - static char *getname_flags(const char __user *filename, int flags, int *empty) { - char *result = __getname(); - int retval; + char *result = __getname(), *err; + int len; - if (!result) + if (unlikely(!result)) return ERR_PTR(-ENOMEM); - retval = do_getname(filename, result); - if (retval < 0) { - if (retval == -ENOENT && empty) + len = strncpy_from_user(result, filename, PATH_MAX); + err = ERR_PTR(len); + if (unlikely(len < 0)) + goto error; + + /* The empty path is special. */ + if (unlikely(!len)) { + if (empty) *empty = 1; - if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) { - __putname(result); - return ERR_PTR(retval); - } + err = ERR_PTR(-ENOENT); + if (!(flags & LOOKUP_EMPTY)) + goto error; + } + + err = ERR_PTR(-ENAMETOOLONG); + if (likely(len < PATH_MAX)) { + audit_getname(result); + return result; } - audit_getname(result); - return result; + +error: + __putname(result); + return err; } char *getname(const char __user * filename) @@ -1154,12 +1144,25 @@ static int do_lookup(struct nameidata *nd, struct qstr *name, */ if (nd->flags & LOOKUP_RCU) { unsigned seq; - *inode = nd->inode; - dentry = __d_lookup_rcu(parent, name, &seq, inode); + dentry = __d_lookup_rcu(parent, name, &seq, nd->inode); if (!dentry) goto unlazy; - /* Memory barrier in read_seqcount_begin of child is enough */ + /* + * This sequence count validates that the inode matches + * the dentry name information from lookup. + */ + *inode = dentry->d_inode; + if (read_seqcount_retry(&dentry->d_seq, seq)) + return -ECHILD; + + /* + * This sequence count validates that the parent had no + * changes while we did the lookup of the dentry above. + * + * The memory barrier in read_seqcount_begin of child is + * enough, we can use __read_seqcount_retry here. + */ if (__read_seqcount_retry(&parent->d_seq, nd->seq)) return -ECHILD; nd->seq = seq; @@ -1429,7 +1432,7 @@ unsigned int full_name_hash(const unsigned char *name, unsigned int len) unsigned long hash = 0; for (;;) { - a = *(unsigned long *)name; + a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; hash += a; @@ -1459,7 +1462,7 @@ static inline unsigned long hash_name(const char *name, unsigned int *hashp) do { hash = (hash + a) * 9; len += sizeof(unsigned long); - a = *(unsigned long *)(name+len); + a = load_unaligned_zeropad(name+len); /* Do we have any NUL or '/' bytes in this word? */ mask = has_zero(a) | has_zero(a ^ REPEAT_BYTE('/')); } while (!mask); diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 9c94297bb70e..7f6a23f0244e 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -38,6 +38,8 @@ #include <linux/buffer_head.h> /* various write calls */ #include <linux/prefetch.h> +#include "../pnfs.h" +#include "../internal.h" #include "blocklayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD @@ -868,7 +870,7 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, * GETDEVICEINFO's maxcount */ max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = max_resp_sz >> PAGE_SHIFT; + max_pages = nfs_page_array_len(0, max_resp_sz); dprintk("%s max_resp_sz %u max_pages %d\n", __func__, max_resp_sz, max_pages); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index da7b5e4ff9ec..60f7e4ec842c 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1729,7 +1729,8 @@ error: */ struct nfs_server *nfs_clone_server(struct nfs_server *source, struct nfs_fh *fh, - struct nfs_fattr *fattr) + struct nfs_fattr *fattr, + rpc_authflavor_t flavor) { struct nfs_server *server; struct nfs_fattr *fattr_fsinfo; @@ -1758,7 +1759,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source, error = nfs_init_server_rpcclient(server, source->client->cl_timeout, - source->client->cl_auth->au_flavor); + flavor); if (error < 0) goto out_free_server; if (!IS_ERR(source->client_acl)) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 4aaf0316d76a..eedd24d0ad2e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -477,10 +477,7 @@ different: static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) { - struct qstr filename = { - .len = entry->len, - .name = entry->name, - }; + struct qstr filename = QSTR_INIT(entry->name, entry->len); struct dentry *dentry; struct dentry *alias; struct inode *dir = parent->d_inode; @@ -1429,7 +1426,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry } open_flags = nd->intent.open.flags; - attr.ia_valid = 0; + attr.ia_valid = ATTR_OPEN; ctx = create_nfs_open_context(dentry, open_flags); res = ERR_CAST(ctx); @@ -1536,7 +1533,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd) if (IS_ERR(ctx)) goto out; - attr.ia_valid = 0; + attr.ia_valid = ATTR_OPEN; if (openflags & O_TRUNC) { attr.ia_valid |= ATTR_SIZE; attr.ia_size = 0; diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b7f348bb618b..ba3019f5934c 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -554,12 +554,16 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, struct nfs_client *clp; int error = 0; + if (!try_module_get(THIS_MODULE)) + return 0; + while ((clp = nfs_get_client_for_event(sb->s_fs_info, event))) { error = __rpc_pipefs_event(clp, event, sb); nfs_put_client(clp); if (error) break; } + module_put(THIS_MODULE); return error; } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2476dc69365f..b777bdaba4c5 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -165,7 +165,8 @@ extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, - struct nfs_fattr *); + struct nfs_fattr *, + rpc_authflavor_t); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern int nfs4_check_client_ready(struct nfs_client *clp); extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, @@ -186,10 +187,10 @@ static inline void nfs_fs_proc_exit(void) /* nfs4namespace.c */ #ifdef CONFIG_NFS_V4 -extern struct vfsmount *nfs_do_refmount(struct dentry *dentry); +extern struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry); #else static inline -struct vfsmount *nfs_do_refmount(struct dentry *dentry) +struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) { return ERR_PTR(-ENOENT); } @@ -234,7 +235,6 @@ extern const u32 nfs41_maxwrite_overhead; /* nfs4proc.c */ #ifdef CONFIG_NFS_V4 extern struct rpc_procinfo nfs4_procedures[]; -void nfs_fixup_secinfo_attributes(struct nfs_fattr *, struct nfs_fh *); #endif extern int nfs4_init_ds_session(struct nfs_client *clp); diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 1807866bb3ab..d51868e5683c 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -148,66 +148,31 @@ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) return pseudoflavor; } -static int nfs_negotiate_security(const struct dentry *parent, - const struct dentry *dentry, - rpc_authflavor_t *flavor) +static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, + struct qstr *name, + struct nfs_fh *fh, + struct nfs_fattr *fattr) { - struct page *page; - struct nfs4_secinfo_flavors *flavors; - int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); - int ret = -EPERM; - - secinfo = NFS_PROTO(parent->d_inode)->secinfo; - if (secinfo != NULL) { - page = alloc_page(GFP_KERNEL); - if (!page) { - ret = -ENOMEM; - goto out; - } - flavors = page_address(page); - ret = secinfo(parent->d_inode, &dentry->d_name, flavors); - *flavor = nfs_find_best_sec(flavors); - put_page(page); - } - -out: - return ret; -} - -static int nfs_lookup_with_sec(struct nfs_server *server, struct dentry *parent, - struct dentry *dentry, struct path *path, - struct nfs_fh *fh, struct nfs_fattr *fattr, - rpc_authflavor_t *flavor) -{ - struct rpc_clnt *clone; - struct rpc_auth *auth; int err; - err = nfs_negotiate_security(parent, path->dentry, flavor); - if (err < 0) - goto out; - clone = rpc_clone_client(server->client); - auth = rpcauth_create(*flavor, clone); - if (!auth) { - err = -EIO; - goto out_shutdown; - } - err = server->nfs_client->rpc_ops->lookup(clone, parent->d_inode, - &path->dentry->d_name, - fh, fattr); -out_shutdown: - rpc_shutdown_client(clone); -out: - return err; + if (NFS_PROTO(dir)->version == 4) + return nfs4_proc_lookup_mountpoint(dir, name, fh, fattr); + + err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr); + if (err) + return ERR_PTR(err); + return rpc_clone_client(NFS_SERVER(dir)->client); } #else /* CONFIG_NFS_V4 */ -static inline int nfs_lookup_with_sec(struct nfs_server *server, - struct dentry *parent, struct dentry *dentry, - struct path *path, struct nfs_fh *fh, - struct nfs_fattr *fattr, - rpc_authflavor_t *flavor) +static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir, + struct qstr *name, + struct nfs_fh *fh, + struct nfs_fattr *fattr) { - return -EPERM; + int err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr); + if (err) + return ERR_PTR(err); + return rpc_clone_client(NFS_SERVER(dir)->client); } #endif /* CONFIG_NFS_V4 */ @@ -226,12 +191,10 @@ static inline int nfs_lookup_with_sec(struct nfs_server *server, struct vfsmount *nfs_d_automount(struct path *path) { struct vfsmount *mnt; - struct nfs_server *server = NFS_SERVER(path->dentry->d_inode); struct dentry *parent; struct nfs_fh *fh = NULL; struct nfs_fattr *fattr = NULL; - int err; - rpc_authflavor_t flavor = RPC_AUTH_UNIX; + struct rpc_clnt *client; dprintk("--> nfs_d_automount()\n"); @@ -249,21 +212,19 @@ struct vfsmount *nfs_d_automount(struct path *path) /* Look it up again to get its attributes */ parent = dget_parent(path->dentry); - err = server->nfs_client->rpc_ops->lookup(server->client, parent->d_inode, - &path->dentry->d_name, - fh, fattr); - if (err == -EPERM && NFS_PROTO(parent->d_inode)->secinfo != NULL) - err = nfs_lookup_with_sec(server, parent, path->dentry, path, fh, fattr, &flavor); + client = nfs_lookup_mountpoint(parent->d_inode, &path->dentry->d_name, fh, fattr); dput(parent); - if (err != 0) { - mnt = ERR_PTR(err); + if (IS_ERR(client)) { + mnt = ERR_CAST(client); goto out; } if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) - mnt = nfs_do_refmount(path->dentry); + mnt = nfs_do_refmount(client, path->dentry); else - mnt = nfs_do_submount(path->dentry, fh, fattr, flavor); + mnt = nfs_do_submount(path->dentry, fh, fattr, client->cl_auth->au_flavor); + rpc_shutdown_client(client); + if (IS_ERR(mnt)) goto out; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 5242eae6711a..75c68299358e 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -398,8 +398,7 @@ nfs3_proc_remove(struct inode *dir, struct qstr *name) { struct nfs_removeargs arg = { .fh = NFS_FH(dir), - .name.len = name->len, - .name.name = name->name, + .name = *name, }; struct nfs_removeres res; struct rpc_message msg = { diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 97ecc863dd76..8d75021020b3 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -59,6 +59,7 @@ struct nfs_unique_id { #define NFS_SEQID_CONFIRMED 1 struct nfs_seqid_counter { + ktime_t create_time; int owner_id; int flags; u32 counter; @@ -204,6 +205,9 @@ struct nfs4_state_maintenance_ops { extern const struct dentry_operations nfs4_dentry_operations; extern const struct inode_operations nfs4_dir_inode_operations; +/* nfs4namespace.c */ +struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); + /* nfs4proc.c */ extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *); @@ -212,8 +216,11 @@ extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); -extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, - struct nfs4_fs_locations *fs_locations, struct page *page); +extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, + struct nfs4_fs_locations *, struct page *); +extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *, + struct nfs_fh *, struct nfs_fattr *); +extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); extern int nfs4_release_lockowner(struct nfs4_lock_state *); extern const struct xattr_handler *nfs4_xattr_handlers[]; diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index a866bbd2890a..c9cff9adb2d3 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -699,7 +699,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_fla * GETDEVICEINFO's maxcount */ max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = max_resp_sz >> PAGE_SHIFT; + max_pages = nfs_page_array_len(0, max_resp_sz); dprintk("%s inode %p max_resp_sz %u max_pages %d\n", __func__, inode, max_resp_sz, max_pages); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 9c8eca315f43..a7f3dedc4ec7 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -52,6 +52,30 @@ Elong: } /* + * return the path component of "<server>:<path>" + * nfspath - the "<server>:<path>" string + * end - one past the last char that could contain "<server>:" + * returns NULL on failure + */ +static char *nfs_path_component(const char *nfspath, const char *end) +{ + char *p; + + if (*nfspath == '[') { + /* parse [] escaped IPv6 addrs */ + p = strchr(nfspath, ']'); + if (p != NULL && ++p < end && *p == ':') + return p + 1; + } else { + /* otherwise split on first colon */ + p = strchr(nfspath, ':'); + if (p != NULL && p < end) + return p + 1; + } + return NULL; +} + +/* * Determine the mount path as a string */ static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen) @@ -59,9 +83,9 @@ static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen) char *limit; char *path = nfs_path(&limit, dentry, buffer, buflen); if (!IS_ERR(path)) { - char *colon = strchr(path, ':'); - if (colon && colon < limit) - path = colon + 1; + char *path_component = nfs_path_component(path, limit); + if (path_component) + return path_component; } return path; } @@ -108,6 +132,58 @@ static size_t nfs_parse_server_name(char *string, size_t len, return ret; } +static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name) +{ + struct page *page; + struct nfs4_secinfo_flavors *flavors; + rpc_authflavor_t flavor; + int err; + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + flavors = page_address(page); + + err = nfs4_proc_secinfo(inode, name, flavors); + if (err < 0) { + flavor = err; + goto out; + } + + flavor = nfs_find_best_sec(flavors); + +out: + put_page(page); + return flavor; +} + +/* + * Please call rpc_shutdown_client() when you are done with this client. + */ +struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *inode, + struct qstr *name) +{ + struct rpc_clnt *clone; + struct rpc_auth *auth; + rpc_authflavor_t flavor; + + flavor = nfs4_negotiate_security(inode, name); + if (flavor < 0) + return ERR_PTR(flavor); + + clone = rpc_clone_client(clnt); + if (IS_ERR(clone)) + return clone; + + auth = rpcauth_create(flavor, clone); + if (!auth) { + rpc_shutdown_client(clone); + clone = ERR_PTR(-EIO); + } + + return clone; +} + static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, char *page, char *page2, const struct nfs4_fs_location *location) @@ -224,7 +300,7 @@ out: * @dentry - dentry of referral * */ -struct vfsmount *nfs_do_refmount(struct dentry *dentry) +struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) { struct vfsmount *mnt = ERR_PTR(-ENOMEM); struct dentry *parent; @@ -250,7 +326,7 @@ struct vfsmount *nfs_do_refmount(struct dentry *dentry) dprintk("%s: getting locations for %s/%s\n", __func__, parent->d_name.name, dentry->d_name.name); - err = nfs4_proc_fs_locations(parent->d_inode, &dentry->d_name, fs_locations, page); + err = nfs4_proc_fs_locations(client, parent->d_inode, &dentry->d_name, fs_locations, page); dput(parent); if (err != 0 || fs_locations->nlocations <= 0 || diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f82bde005a82..ab985f6f0da8 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -838,7 +838,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.open_flags = flags; p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE); p->o_arg.clientid = server->nfs_client->cl_clientid; - p->o_arg.id = sp->so_seqid.owner_id; + p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time); + p->o_arg.id.uniquifier = sp->so_seqid.owner_id; p->o_arg.name = &dentry->d_name; p->o_arg.server = server; p->o_arg.bitmask = server->attr_bitmask; @@ -1466,8 +1467,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) goto unlock_no_action; rcu_read_unlock(); } - /* Update sequence id. */ - data->o_arg.id = sp->so_seqid.owner_id; + /* Update client id. */ data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid; if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) { task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR]; @@ -1954,10 +1954,19 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, }; int err; do { - err = nfs4_handle_exception(server, - _nfs4_do_setattr(inode, cred, fattr, sattr, state), - &exception); + err = _nfs4_do_setattr(inode, cred, fattr, sattr, state); + switch (err) { + case -NFS4ERR_OPENMODE: + if (state && !(state->state & FMODE_WRITE)) { + err = -EBADF; + if (sattr->ia_valid & ATTR_OPEN) + err = -EACCES; + goto out; + } + } + err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); +out: return err; } @@ -2368,8 +2377,9 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, * Note that we'll actually follow the referral later when * we detect fsid mismatch in inode revalidation */ -static int nfs4_get_referral(struct inode *dir, const struct qstr *name, - struct nfs_fattr *fattr, struct nfs_fh *fhandle) +static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, struct nfs_fattr *fattr, + struct nfs_fh *fhandle) { int status = -ENOMEM; struct page *page = NULL; @@ -2382,7 +2392,7 @@ static int nfs4_get_referral(struct inode *dir, const struct qstr *name, if (locations == NULL) goto out; - status = nfs4_proc_fs_locations(dir, name, locations, page); + status = nfs4_proc_fs_locations(client, dir, name, locations, page); if (status != 0) goto out; /* Make sure server returned a different fsid for the referral */ @@ -2519,39 +2529,84 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, return status; } -void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr, struct nfs_fh *fh) +static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr) { - memset(fh, 0, sizeof(struct nfs_fh)); - fattr->fsid.major = 1; fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE | - NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_FSID | NFS_ATTR_FATTR_MOUNTPOINT; + NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_MOUNTPOINT; fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO; fattr->nlink = 2; } -static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, - struct nfs_fh *fhandle, struct nfs_fattr *fattr) +static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, + struct qstr *name, struct nfs_fh *fhandle, + struct nfs_fattr *fattr) { struct nfs4_exception exception = { }; + struct rpc_clnt *client = *clnt; int err; do { - int status; - - status = _nfs4_proc_lookup(clnt, dir, name, fhandle, fattr); - switch (status) { + err = _nfs4_proc_lookup(client, dir, name, fhandle, fattr); + switch (err) { case -NFS4ERR_BADNAME: - return -ENOENT; + err = -ENOENT; + goto out; case -NFS4ERR_MOVED: - return nfs4_get_referral(dir, name, fattr, fhandle); + err = nfs4_get_referral(client, dir, name, fattr, fhandle); + goto out; case -NFS4ERR_WRONGSEC: - nfs_fixup_secinfo_attributes(fattr, fhandle); + err = -EPERM; + if (client != *clnt) + goto out; + + client = nfs4_create_sec_client(client, dir, name); + if (IS_ERR(client)) + return PTR_ERR(client); + + exception.retry = 1; + break; + default: + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } - err = nfs4_handle_exception(NFS_SERVER(dir), - status, &exception); } while (exception.retry); + +out: + if (err == 0) + *clnt = client; + else if (client != *clnt) + rpc_shutdown_client(client); + return err; } +static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) +{ + int status; + struct rpc_clnt *client = NFS_CLIENT(dir); + + status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr); + if (client != NFS_CLIENT(dir)) { + rpc_shutdown_client(client); + nfs_fixup_secinfo_attributes(fattr); + } + return status; +} + +struct rpc_clnt * +nfs4_proc_lookup_mountpoint(struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) +{ + int status; + struct rpc_clnt *client = rpc_clone_client(NFS_CLIENT(dir)); + + status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr); + if (status < 0) { + rpc_shutdown_client(client); + return ERR_PTR(status); + } + return client; +} + static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) { struct nfs_server *server = NFS_SERVER(inode); @@ -2727,8 +2782,7 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) struct nfs_server *server = NFS_SERVER(dir); struct nfs_removeargs args = { .fh = NFS_FH(dir), - .name.len = name->len, - .name.name = name->name, + .name = *name, .bitmask = server->attr_bitmask, }; struct nfs_removeres res = { @@ -3619,16 +3673,16 @@ out: return ret; } -static void nfs4_write_cached_acl(struct inode *inode, const char *buf, size_t acl_len) +static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len) { struct nfs4_cached_acl *acl; - if (buf && acl_len <= PAGE_SIZE) { + if (pages && acl_len <= PAGE_SIZE) { acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL); if (acl == NULL) goto out; acl->cached = 1; - memcpy(acl->data, buf, acl_len); + _copy_from_pages(acl->data, pages, pgbase, acl_len); } else { acl = kmalloc(sizeof(*acl), GFP_KERNEL); if (acl == NULL) @@ -3661,7 +3715,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu struct nfs_getaclres res = { .acl_len = buflen, }; - void *resp_buf; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETACL], .rpc_argp = &args, @@ -3675,24 +3728,27 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu if (npages == 0) npages = 1; + /* Add an extra page to handle the bitmap returned */ + npages++; + for (i = 0; i < npages; i++) { pages[i] = alloc_page(GFP_KERNEL); if (!pages[i]) goto out_free; } - if (npages > 1) { - /* for decoding across pages */ - res.acl_scratch = alloc_page(GFP_KERNEL); - if (!res.acl_scratch) - goto out_free; - } + + /* for decoding across pages */ + res.acl_scratch = alloc_page(GFP_KERNEL); + if (!res.acl_scratch) + goto out_free; + args.acl_len = npages * PAGE_SIZE; args.acl_pgbase = 0; + /* Let decode_getfacl know not to fail if the ACL data is larger than * the page we send as a guess */ if (buf == NULL) res.acl_flags |= NFS4_ACL_LEN_REQUEST; - resp_buf = page_address(pages[0]); dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n", __func__, buf, buflen, npages, args.acl_len); @@ -3703,9 +3759,9 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu acl_len = res.acl_len - res.acl_data_offset; if (acl_len > args.acl_len) - nfs4_write_cached_acl(inode, NULL, acl_len); + nfs4_write_cached_acl(inode, NULL, 0, acl_len); else - nfs4_write_cached_acl(inode, resp_buf + res.acl_data_offset, + nfs4_write_cached_acl(inode, pages, res.acl_data_offset, acl_len); if (buf) { ret = -ERANGE; @@ -4558,7 +4614,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request) { struct nfs_server *server = NFS_SERVER(state->inode); - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .inode = state->inode, + }; int err; do { @@ -4576,7 +4634,9 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request) { struct nfs_server *server = NFS_SERVER(state->inode); - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .inode = state->inode, + }; int err; err = nfs4_set_lock_state(state, request); @@ -4676,6 +4736,7 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock * { struct nfs4_exception exception = { .state = state, + .inode = state->inode, }; int err; @@ -4721,6 +4782,20 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request) if (state == NULL) return -ENOLCK; + /* + * Don't rely on the VFS having checked the file open mode, + * since it won't do this for flock() locks. + */ + switch (request->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) { + case F_RDLCK: + if (!(filp->f_mode & FMODE_READ)) + return -EBADF; + break; + case F_WRLCK: + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + } + do { status = nfs4_proc_setlk(state, cmd, request); if ((status != -EAGAIN) || IS_SETLK(cmd)) @@ -4891,8 +4966,10 @@ static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr) fattr->nlink = 2; } -int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, - struct nfs4_fs_locations *fs_locations, struct page *page) +static int _nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, + struct nfs4_fs_locations *fs_locations, + struct page *page) { struct nfs_server *server = NFS_SERVER(dir); u32 bitmask[2] = { @@ -4926,11 +5003,26 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, nfs_fattr_init(&fs_locations->fattr); fs_locations->server = server; fs_locations->nlocations = 0; - status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); + status = nfs4_call_sync(client, server, &msg, &args.seq_args, &res.seq_res, 0); dprintk("%s: returned status = %d\n", __func__, status); return status; } +int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, + struct nfs4_fs_locations *fs_locations, + struct page *page) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = nfs4_handle_exception(NFS_SERVER(dir), + _nfs4_proc_fs_locations(client, dir, name, fs_locations, page), + &exception); + } while (exception.retry); + return err; +} + static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors) { int status; @@ -4953,8 +5045,8 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct return status; } -static int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, - struct nfs4_secinfo_flavors *flavors) +int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, + struct nfs4_secinfo_flavors *flavors) { struct nfs4_exception exception = { }; int err; @@ -5029,10 +5121,9 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) nfs4_construct_boot_verifier(clp, &verifier); args.id_len = scnprintf(args.id, sizeof(args.id), - "%s/%s.%s/%u", + "%s/%s/%u", clp->cl_ipaddr, - init_utsname()->nodename, - init_utsname()->domainname, + clp->cl_rpcclient->cl_nodename, clp->cl_rpcclient->cl_auth->au_flavor); res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 0f43414eb25a..7f0fcfc1fe9d 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -393,6 +393,7 @@ nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp) static void nfs4_init_seqid_counter(struct nfs_seqid_counter *sc) { + sc->create_time = ktime_get(); sc->flags = 0; sc->counter = 0; spin_lock_init(&sc->lock); @@ -434,13 +435,17 @@ nfs4_alloc_state_owner(struct nfs_server *server, static void nfs4_drop_state_owner(struct nfs4_state_owner *sp) { - if (!RB_EMPTY_NODE(&sp->so_server_node)) { + struct rb_node *rb_node = &sp->so_server_node; + + if (!RB_EMPTY_NODE(rb_node)) { struct nfs_server *server = sp->so_server; struct nfs_client *clp = server->nfs_client; spin_lock(&clp->cl_lock); - rb_erase(&sp->so_server_node, &server->state_owners); - RB_CLEAR_NODE(&sp->so_server_node); + if (!RB_EMPTY_NODE(rb_node)) { + rb_erase(rb_node, &server->state_owners); + RB_CLEAR_NODE(rb_node); + } spin_unlock(&clp->cl_lock); } } @@ -516,6 +521,14 @@ out: /** * nfs4_put_state_owner - Release a nfs4_state_owner * @sp: state owner data to release + * + * Note that we keep released state owners on an LRU + * list. + * This caches valid state owners so that they can be + * reused, to avoid the OPEN_CONFIRM on minor version 0. + * It also pins the uniquifier of dropped state owners for + * a while, to ensure that those state owner names are + * never reused. */ void nfs4_put_state_owner(struct nfs4_state_owner *sp) { @@ -525,15 +538,9 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp) if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock)) return; - if (!RB_EMPTY_NODE(&sp->so_server_node)) { - sp->so_expires = jiffies; - list_add_tail(&sp->so_lru, &server->state_owners_lru); - spin_unlock(&clp->cl_lock); - } else { - nfs4_remove_state_owner_locked(sp); - spin_unlock(&clp->cl_lock); - nfs4_free_state_owner(sp); - } + sp->so_expires = jiffies; + list_add_tail(&sp->so_lru, &server->state_owners_lru); + spin_unlock(&clp->cl_lock); } /** diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index c74fdb114b48..c54aae364bee 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -74,7 +74,7 @@ static int nfs4_stat_to_errno(int); /* lock,open owner id: * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT >> 2) */ -#define open_owner_id_maxsz (1 + 1 + 4) +#define open_owner_id_maxsz (1 + 2 + 1 + 1 + 2) #define lock_owner_id_maxsz (1 + 1 + 4) #define decode_lockowner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) #define compound_encode_hdr_maxsz (3 + (NFS4_MAXTAGLEN >> 2)) @@ -1340,12 +1340,13 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena */ encode_nfs4_seqid(xdr, arg->seqid); encode_share_access(xdr, arg->fmode); - p = reserve_space(xdr, 32); + p = reserve_space(xdr, 36); p = xdr_encode_hyper(p, arg->clientid); - *p++ = cpu_to_be32(20); + *p++ = cpu_to_be32(24); p = xdr_encode_opaque_fixed(p, "open id:", 8); *p++ = cpu_to_be32(arg->server->s_dev); - xdr_encode_hyper(p, arg->id); + *p++ = cpu_to_be32(arg->id.uniquifier); + xdr_encode_hyper(p, arg->id.create_time); } static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg) @@ -4257,8 +4258,6 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, status = decode_attr_error(xdr, bitmap, &err); if (status < 0) goto xdr_error; - if (err == -NFS4ERR_WRONGSEC) - nfs_fixup_secinfo_attributes(fattr, fh); status = decode_attr_filehandle(xdr, bitmap, fh); if (status < 0) @@ -4901,11 +4900,19 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, bitmap[3] = {0}; struct kvec *iov = req->rq_rcv_buf.head; int status; + size_t page_len = xdr->buf->page_len; res->acl_len = 0; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) goto out; + bm_p = xdr->p; + res->acl_data_offset = be32_to_cpup(bm_p) + 2; + res->acl_data_offset <<= 2; + /* Check if the acl data starts beyond the allocated buffer */ + if (res->acl_data_offset > page_len) + return -ERANGE; + if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) goto out; if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) @@ -4915,28 +4922,24 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_ACL)) { size_t hdrlen; - u32 recvd; /* The bitmap (xdr len + bitmaps) and the attr xdr len words * are stored with the acl data to handle the problem of * variable length bitmaps.*/ xdr->p = bm_p; - res->acl_data_offset = be32_to_cpup(bm_p) + 2; - res->acl_data_offset <<= 2; /* We ignore &savep and don't do consistency checks on * the attr length. Let userspace figure it out.... */ hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base; attrlen += res->acl_data_offset; - recvd = req->rq_rcv_buf.len - hdrlen; - if (attrlen > recvd) { + if (attrlen > page_len) { if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { /* getxattr interface called with a NULL buf */ res->acl_len = attrlen; goto out; } - dprintk("NFS: acl reply: attrlen %u > recvd %u\n", - attrlen, recvd); + dprintk("NFS: acl reply: attrlen %u > page_len %zu\n", + attrlen, page_len); return -EINVAL; } xdr_read_pages(xdr, attrlen); @@ -5089,16 +5092,13 @@ out_err: return -EINVAL; } -static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +static int decode_secinfo_common(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) { struct nfs4_secinfo_flavor *sec_flavor; int status; __be32 *p; int i, num_flavors; - status = decode_op_hdr(xdr, OP_SECINFO); - if (status) - goto out; p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; @@ -5124,6 +5124,7 @@ static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) res->flavors->num_flavors++; } + status = 0; out: return status; out_overflow: @@ -5131,7 +5132,23 @@ out_overflow: return -EIO; } +static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +{ + int status = decode_op_hdr(xdr, OP_SECINFO); + if (status) + return status; + return decode_secinfo_common(xdr, res); +} + #if defined(CONFIG_NFS_V4_1) +static int decode_secinfo_no_name(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +{ + int status = decode_op_hdr(xdr, OP_SECINFO_NO_NAME); + if (status) + return status; + return decode_secinfo_common(xdr, res); +} + static int decode_exchange_id(struct xdr_stream *xdr, struct nfs41_exchange_id_res *res) { @@ -6816,7 +6833,7 @@ static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp, status = decode_putrootfh(xdr); if (status) goto out; - status = decode_secinfo(xdr, res); + status = decode_secinfo_no_name(xdr, res); out: return status; } diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index 8d45f1c318ce..595c5fc21a19 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -604,7 +604,6 @@ int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay, { struct objlayout_deviceinfo *odi; struct pnfs_device pd; - struct super_block *sb; struct page *page, **pages; u32 *p; int err; @@ -623,7 +622,6 @@ int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay, pd.pglen = PAGE_SIZE; pd.mincount = 0; - sb = pnfslay->plh_inode->i_sb; err = nfs4_proc_getdeviceinfo(NFS_SERVER(pnfslay->plh_inode), &pd); dprintk("%s nfs_getdeviceinfo returned %d\n", __func__, err); if (err) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b5d451586943..38512bcd2e98 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -587,7 +587,7 @@ send_layoutget(struct pnfs_layout_hdr *lo, /* allocate pages for xdr post processing */ max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = max_resp_sz >> PAGE_SHIFT; + max_pages = nfs_page_array_len(0, max_resp_sz); pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags); if (!pages) diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index b63b6f4d14fb..d6408b6437de 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -335,8 +335,7 @@ nfs_proc_remove(struct inode *dir, struct qstr *name) { struct nfs_removeargs arg = { .fh = NFS_FH(dir), - .name.len = name->len, - .name.name = name->name, + .name = *name, }; struct rpc_message msg = { .rpc_proc = &nfs_procedures[NFSPROC_REMOVE], diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 9a0e8ef4a409..0a4be28c2ea3 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -322,7 +322,7 @@ out_bad: while (!list_empty(res)) { data = list_entry(res->next, struct nfs_read_data, list); list_del(&data->list); - nfs_readdata_free(data); + nfs_readdata_release(data); } nfs_readpage_release(req); return -ENOMEM; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 37412f706b32..4ac7fca7e4bf 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2428,7 +2428,7 @@ nfs_xdev_mount(struct file_system_type *fs_type, int flags, dprintk("--> nfs_xdev_mount()\n"); /* create a new volume representation */ - server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr); + server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor); if (IS_ERR(server)) { error = PTR_ERR(server); goto out_err_noserver; @@ -2767,11 +2767,15 @@ static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type, char *root_devname; size_t len; - len = strlen(hostname) + 3; + len = strlen(hostname) + 5; root_devname = kmalloc(len, GFP_KERNEL); if (root_devname == NULL) return ERR_PTR(-ENOMEM); - snprintf(root_devname, len, "%s:/", hostname); + /* Does hostname needs to be enclosed in brackets? */ + if (strchr(hostname, ':')) + snprintf(root_devname, len, "[%s]:/", hostname); + else + snprintf(root_devname, len, "%s:/", hostname); root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data); kfree(root_devname); return root_mnt; @@ -2951,7 +2955,7 @@ nfs4_xdev_mount(struct file_system_type *fs_type, int flags, dprintk("--> nfs4_xdev_mount()\n"); /* create a new volume representation */ - server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr); + server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor); if (IS_ERR(server)) { error = PTR_ERR(server); goto out_err_noserver; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2c68818f68ac..c07462320f6b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -682,7 +682,8 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, req->wb_bytes = rqend - req->wb_offset; out_unlock: spin_unlock(&inode->i_lock); - nfs_clear_request_commit(req); + if (req) + nfs_clear_request_commit(req); return req; out_flushme: spin_unlock(&inode->i_lock); @@ -1018,7 +1019,7 @@ out_bad: while (!list_empty(res)) { data = list_entry(res->next, struct nfs_write_data, list); list_del(&data->list); - nfs_writedata_free(data); + nfs_writedata_release(data); } nfs_redirty_request(req); return -ENOMEM; diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 4767429264a2..ed3f9206a0ee 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -577,7 +577,7 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) struct cld_net *cn = nn->cld_net; if (mlen != sizeof(*cmsg)) { - dprintk("%s: got %lu bytes, expected %lu\n", __func__, mlen, + dprintk("%s: got %zu bytes, expected %zu\n", __func__, mlen, sizeof(*cmsg)); return -EINVAL; } diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index fce2bbee66d4..0bb2c2010b95 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -441,7 +441,7 @@ static struct dentry *nilfs_get_parent(struct dentry *child) { unsigned long ino; struct inode *inode; - struct qstr dotdot = {.name = "..", .len = 2}; + struct qstr dotdot = QSTR_INIT("..", 2); struct nilfs_root *root; ino = nilfs_inode_by_name(child->d_inode, &dotdot); diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 044e7b58d31c..1bfe8802cc1e 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -2005,7 +2005,7 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port) o2net_listen_sock = sock; INIT_WORK(&o2net_listen_work, o2net_accept_many); - sock->sk->sk_reuse = 1; + sock->sk->sk_reuse = SK_CAN_REUSE; ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin)); if (ret < 0) { printk(KERN_ERR "o2net: Error %d while binding socket at " diff --git a/fs/open.c b/fs/open.c index 5720854156db..5eccdcea2d1b 100644 --- a/fs/open.c +++ b/fs/open.c @@ -681,7 +681,7 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, f->f_op = fops_get(inode->i_fop); - error = security_dentry_open(f, cred); + error = security_file_open(f, cred); if (error) goto cleanup_all; diff --git a/fs/pipe.c b/fs/pipe.c index 25feaa3faac0..fec5e4ad071a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -346,6 +346,16 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = { .get = generic_pipe_buf_get, }; +static const struct pipe_buf_operations packet_pipe_buf_ops = { + .can_merge = 0, + .map = generic_pipe_buf_map, + .unmap = generic_pipe_buf_unmap, + .confirm = generic_pipe_buf_confirm, + .release = anon_pipe_buf_release, + .steal = generic_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + static ssize_t pipe_read(struct kiocb *iocb, const struct iovec *_iov, unsigned long nr_segs, loff_t pos) @@ -407,6 +417,13 @@ redo: ret += chars; buf->offset += chars; buf->len -= chars; + + /* Was it a packet buffer? Clean up and exit */ + if (buf->flags & PIPE_BUF_FLAG_PACKET) { + total_len = chars; + buf->len = 0; + } + if (!buf->len) { buf->ops = NULL; ops->release(pipe, buf); @@ -459,6 +476,11 @@ redo: return ret; } +static inline int is_packetized(struct file *file) +{ + return (file->f_flags & O_DIRECT) != 0; +} + static ssize_t pipe_write(struct kiocb *iocb, const struct iovec *_iov, unsigned long nr_segs, loff_t ppos) @@ -593,6 +615,11 @@ redo2: buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = chars; + buf->flags = 0; + if (is_packetized(filp)) { + buf->ops = &packet_pipe_buf_ops; + buf->flags = PIPE_BUF_FLAG_PACKET; + } pipe->nrbufs = ++bufs; pipe->tmp_page = NULL; @@ -1013,7 +1040,7 @@ struct file *create_write_pipe(int flags) goto err_dentry; f->f_mapping = inode->i_mapping; - f->f_flags = O_WRONLY | (flags & O_NONBLOCK); + f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)); f->f_version = 0; return f; @@ -1057,7 +1084,7 @@ int do_pipe_flags(int *fd, int flags) int error; int fdw, fdr; - if (flags & ~(O_CLOEXEC | O_NONBLOCK)) + if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT)) return -EINVAL; fw = create_write_pipe(flags); diff --git a/fs/proc/base.c b/fs/proc/base.c index 1c8b280146d7..57b8159f26f3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1799,10 +1799,15 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) if (task) { files = get_files_struct(task); if (files) { + struct file *file; rcu_read_lock(); - if (fcheck_files(files, fd)) { + file = fcheck_files(files, fd); + if (file) { + unsigned i_mode, f_mode = file->f_mode; + rcu_read_unlock(); put_files_struct(files); + if (task_dumpable(task)) { rcu_read_lock(); cred = __task_cred(task); @@ -1813,7 +1818,14 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) inode->i_uid = 0; inode->i_gid = 0; } - inode->i_mode &= ~(S_ISUID | S_ISGID); + + i_mode = S_IFLNK; + if (f_mode & FMODE_READ) + i_mode |= S_IRUSR | S_IXUSR; + if (f_mode & FMODE_WRITE) + i_mode |= S_IWUSR | S_IXUSR; + inode->i_mode = i_mode; + security_task_to_inode(task, inode); put_task_struct(task); return 1; @@ -1837,8 +1849,6 @@ static struct dentry *proc_fd_instantiate(struct inode *dir, struct dentry *dentry, struct task_struct *task, const void *ptr) { unsigned fd = *(const unsigned *)ptr; - struct file *file; - struct files_struct *files; struct inode *inode; struct proc_inode *ei; struct dentry *error = ERR_PTR(-ENOENT); @@ -1848,25 +1858,6 @@ static struct dentry *proc_fd_instantiate(struct inode *dir, goto out; ei = PROC_I(inode); ei->fd = fd; - files = get_files_struct(task); - if (!files) - goto out_iput; - inode->i_mode = S_IFLNK; - - /* - * We are not taking a ref to the file structure, so we must - * hold ->file_lock. - */ - spin_lock(&files->file_lock); - file = fcheck_files(files, fd); - if (!file) - goto out_unlock; - if (file->f_mode & FMODE_READ) - inode->i_mode |= S_IRUSR | S_IXUSR; - if (file->f_mode & FMODE_WRITE) - inode->i_mode |= S_IWUSR | S_IXUSR; - spin_unlock(&files->file_lock); - put_files_struct(files); inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; @@ -1879,12 +1870,6 @@ static struct dentry *proc_fd_instantiate(struct inode *dir, out: return error; -out_unlock: - spin_unlock(&files->file_lock); - put_files_struct(files); -out_iput: - iput(inode); - goto out; } static struct dentry *proc_lookupfd_common(struct inode *dir, @@ -2177,16 +2162,16 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, goto out; result = ERR_PTR(-EACCES); - if (lock_trace(task)) + if (!ptrace_may_access(task, PTRACE_MODE_READ)) goto out_put_task; result = ERR_PTR(-ENOENT); if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) - goto out_unlock; + goto out_put_task; mm = get_task_mm(task); if (!mm) - goto out_unlock; + goto out_put_task; down_read(&mm->mmap_sem); vma = find_exact_vma(mm, vm_start, vm_end); @@ -2198,8 +2183,6 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, out_no_vma: up_read(&mm->mmap_sem); mmput(mm); -out_unlock: - unlock_trace(task); out_put_task: put_task_struct(task); out: @@ -2233,7 +2216,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) goto out; ret = -EACCES; - if (lock_trace(task)) + if (!ptrace_may_access(task, PTRACE_MODE_READ)) goto out_put_task; ret = 0; @@ -2241,12 +2224,12 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) case 0: ino = inode->i_ino; if (filldir(dirent, ".", 1, 0, ino, DT_DIR) < 0) - goto out_unlock; + goto out_put_task; filp->f_pos++; case 1: ino = parent_ino(dentry); if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) - goto out_unlock; + goto out_put_task; filp->f_pos++; default: { @@ -2257,7 +2240,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) mm = get_task_mm(task); if (!mm) - goto out_unlock; + goto out_put_task; down_read(&mm->mmap_sem); nr_files = 0; @@ -2287,7 +2270,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) flex_array_free(fa); up_read(&mm->mmap_sem); mmput(mm); - goto out_unlock; + goto out_put_task; } for (i = 0, vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) { @@ -2332,8 +2315,6 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) } } -out_unlock: - unlock_trace(task); out_put_task: put_task_struct(task); out: diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 2b9a7607cbd5..1030a716d155 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -597,9 +597,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, if (!page) continue; - if (PageReserved(page)) - continue; - /* Clear accessed and referenced bits. */ ptep_test_and_clear_young(vma, addr, pte); ClearPageReferenced(page); @@ -750,6 +747,8 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, pte_t pte) else if (pte_present(pte)) *pme = make_pme(PM_PFRAME(pte_pfn(pte)) | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); + else + *pme = make_pme(PM_NOT_PRESENT); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -764,6 +763,8 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, if (pmd_present(pmd)) *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset) | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); + else + *pme = make_pme(PM_NOT_PRESENT); } #else static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, @@ -804,8 +805,10 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, /* check to see if we've left 'vma' behind * and need a new, higher one */ - if (vma && (addr >= vma->vm_end)) + if (vma && (addr >= vma->vm_end)) { vma = find_vma(walk->mm, addr); + pme = make_pme(PM_NOT_PRESENT); + } /* check that 'vma' actually covers this address, * and that it isn't a huge page vma */ @@ -833,6 +836,8 @@ static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, if (pte_present(pte)) *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); + else + *pme = make_pme(PM_NOT_PRESENT); } /* This function walks within one hugetlb entry in the single call */ @@ -842,7 +847,7 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, { struct pagemapread *pm = walk->private; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT); + pagemap_entry_t pme; for (; addr != end; addr += PAGE_SIZE) { int offset = (addr & ~hmask) >> PAGE_SHIFT; diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 8007ae7c0d8c..23ade2680a4a 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -11,3 +11,20 @@ config PSTORE (e.g. ACPI_APEI on X86) which will select this for you. If you don't have a platform persistent store driver, say N. + +config PSTORE_RAM + tristate "Log panic/oops to a RAM buffer" + depends on PSTORE + depends on HAS_IOMEM + depends on HAVE_MEMBLOCK + select REED_SOLOMON + select REED_SOLOMON_ENC8 + select REED_SOLOMON_DEC8 + help + This enables panic and oops messages to be logged to a circular + buffer in RAM where it can be read back at some later point. + + Note that for historical reasons, the module will be named + "ramoops.ko". + + For more information, see Documentation/ramoops.txt. diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile index 760f4bce7d1d..278a44e0d4e1 100644 --- a/fs/pstore/Makefile +++ b/fs/pstore/Makefile @@ -5,3 +5,6 @@ obj-y += pstore.o pstore-objs += inode.o platform.o + +ramoops-objs += ram.o ram_core.o +obj-$(CONFIG_PSTORE_RAM) += ramoops.o diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c new file mode 100644 index 000000000000..9123cce28c1e --- /dev/null +++ b/fs/pstore/ram.c @@ -0,0 +1,383 @@ +/* + * RAM Oops/Panic logger + * + * Copyright (C) 2010 Marco Stornelli <marco.stornelli@gmail.com> + * Copyright (C) 2011 Kees Cook <keescook@chromium.org> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/pstore.h> +#include <linux/time.h> +#include <linux/io.h> +#include <linux/ioport.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/pstore_ram.h> + +#define RAMOOPS_KERNMSG_HDR "====" +#define MIN_MEM_SIZE 4096UL + +static ulong record_size = MIN_MEM_SIZE; +module_param(record_size, ulong, 0400); +MODULE_PARM_DESC(record_size, + "size of each dump done on oops/panic"); + +static ulong mem_address; +module_param(mem_address, ulong, 0400); +MODULE_PARM_DESC(mem_address, + "start of reserved RAM used to store oops/panic logs"); + +static ulong mem_size; +module_param(mem_size, ulong, 0400); +MODULE_PARM_DESC(mem_size, + "size of reserved RAM used to store oops/panic logs"); + +static int dump_oops = 1; +module_param(dump_oops, int, 0600); +MODULE_PARM_DESC(dump_oops, + "set to 1 to dump oopses, 0 to only dump panics (default 1)"); + +static int ramoops_ecc; +module_param_named(ecc, ramoops_ecc, int, 0600); +MODULE_PARM_DESC(ramoops_ecc, + "set to 1 to enable ECC support"); + +struct ramoops_context { + struct persistent_ram_zone **przs; + phys_addr_t phys_addr; + unsigned long size; + size_t record_size; + int dump_oops; + bool ecc; + unsigned int count; + unsigned int max_count; + unsigned int read_count; + struct pstore_info pstore; +}; + +static struct platform_device *dummy; +static struct ramoops_platform_data *dummy_data; + +static int ramoops_pstore_open(struct pstore_info *psi) +{ + struct ramoops_context *cxt = psi->data; + + cxt->read_count = 0; + return 0; +} + +static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, + struct timespec *time, + char **buf, + struct pstore_info *psi) +{ + ssize_t size; + struct ramoops_context *cxt = psi->data; + struct persistent_ram_zone *prz; + + if (cxt->read_count >= cxt->max_count) + return -EINVAL; + + *id = cxt->read_count++; + prz = cxt->przs[*id]; + + /* Only supports dmesg output so far. */ + *type = PSTORE_TYPE_DMESG; + /* TODO(kees): Bogus time for the moment. */ + time->tv_sec = 0; + time->tv_nsec = 0; + + size = persistent_ram_old_size(prz); + *buf = kmalloc(size, GFP_KERNEL); + if (*buf == NULL) + return -ENOMEM; + memcpy(*buf, persistent_ram_old(prz), size); + + return size; +} + +static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz) +{ + char *hdr; + struct timeval timestamp; + size_t len; + + do_gettimeofday(×tamp); + hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu\n", + (long)timestamp.tv_sec, (long)timestamp.tv_usec); + WARN_ON_ONCE(!hdr); + len = hdr ? strlen(hdr) : 0; + persistent_ram_write(prz, hdr, len); + kfree(hdr); + + return len; +} + +static int ramoops_pstore_write(enum pstore_type_id type, + enum kmsg_dump_reason reason, + u64 *id, + unsigned int part, + size_t size, struct pstore_info *psi) +{ + struct ramoops_context *cxt = psi->data; + struct persistent_ram_zone *prz = cxt->przs[cxt->count]; + size_t hlen; + + /* Currently ramoops is designed to only store dmesg dumps. */ + if (type != PSTORE_TYPE_DMESG) + return -EINVAL; + + /* Out of the various dmesg dump types, ramoops is currently designed + * to only store crash logs, rather than storing general kernel logs. + */ + if (reason != KMSG_DUMP_OOPS && + reason != KMSG_DUMP_PANIC) + return -EINVAL; + + /* Skip Oopes when configured to do so. */ + if (reason == KMSG_DUMP_OOPS && !cxt->dump_oops) + return -EINVAL; + + /* Explicitly only take the first part of any new crash. + * If our buffer is larger than kmsg_bytes, this can never happen, + * and if our buffer is smaller than kmsg_bytes, we don't want the + * report split across multiple records. + */ + if (part != 1) + return -ENOSPC; + + hlen = ramoops_write_kmsg_hdr(prz); + if (size + hlen > prz->buffer_size) + size = prz->buffer_size - hlen; + persistent_ram_write(prz, cxt->pstore.buf, size); + + cxt->count = (cxt->count + 1) % cxt->max_count; + + return 0; +} + +static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, + struct pstore_info *psi) +{ + struct ramoops_context *cxt = psi->data; + + if (id >= cxt->max_count) + return -EINVAL; + + persistent_ram_free_old(cxt->przs[id]); + + return 0; +} + +static struct ramoops_context oops_cxt = { + .pstore = { + .owner = THIS_MODULE, + .name = "ramoops", + .open = ramoops_pstore_open, + .read = ramoops_pstore_read, + .write = ramoops_pstore_write, + .erase = ramoops_pstore_erase, + }, +}; + +static int __init ramoops_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct ramoops_platform_data *pdata = pdev->dev.platform_data; + struct ramoops_context *cxt = &oops_cxt; + int err = -EINVAL; + int i; + + /* Only a single ramoops area allowed at a time, so fail extra + * probes. + */ + if (cxt->max_count) + goto fail_out; + + if (!pdata->mem_size || !pdata->record_size) { + pr_err("The memory size and the record size must be " + "non-zero\n"); + goto fail_out; + } + + pdata->mem_size = rounddown_pow_of_two(pdata->mem_size); + pdata->record_size = rounddown_pow_of_two(pdata->record_size); + + /* Check for the minimum memory size */ + if (pdata->mem_size < MIN_MEM_SIZE && + pdata->record_size < MIN_MEM_SIZE) { + pr_err("memory size too small, minimum is %lu\n", + MIN_MEM_SIZE); + goto fail_out; + } + + if (pdata->mem_size < pdata->record_size) { + pr_err("The memory size must be larger than the " + "records size\n"); + goto fail_out; + } + + cxt->max_count = pdata->mem_size / pdata->record_size; + cxt->count = 0; + cxt->size = pdata->mem_size; + cxt->phys_addr = pdata->mem_address; + cxt->record_size = pdata->record_size; + cxt->dump_oops = pdata->dump_oops; + cxt->ecc = pdata->ecc; + + cxt->przs = kzalloc(sizeof(*cxt->przs) * cxt->max_count, GFP_KERNEL); + if (!cxt->przs) { + err = -ENOMEM; + dev_err(dev, "failed to initialize a prz array\n"); + goto fail_out; + } + + for (i = 0; i < cxt->max_count; i++) { + size_t sz = cxt->record_size; + phys_addr_t start = cxt->phys_addr + sz * i; + + cxt->przs[i] = persistent_ram_new(start, sz, cxt->ecc); + if (IS_ERR(cxt->przs[i])) { + err = PTR_ERR(cxt->przs[i]); + dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n", + sz, (unsigned long long)start, err); + goto fail_przs; + } + } + + cxt->pstore.data = cxt; + cxt->pstore.bufsize = cxt->przs[0]->buffer_size; + cxt->pstore.buf = kmalloc(cxt->pstore.bufsize, GFP_KERNEL); + spin_lock_init(&cxt->pstore.buf_lock); + if (!cxt->pstore.buf) { + pr_err("cannot allocate pstore buffer\n"); + goto fail_clear; + } + + err = pstore_register(&cxt->pstore); + if (err) { + pr_err("registering with pstore failed\n"); + goto fail_buf; + } + + /* + * Update the module parameter variables as well so they are visible + * through /sys/module/ramoops/parameters/ + */ + mem_size = pdata->mem_size; + mem_address = pdata->mem_address; + record_size = pdata->record_size; + dump_oops = pdata->dump_oops; + + pr_info("attached 0x%lx@0x%llx (%ux0x%zx), ecc: %s\n", + cxt->size, (unsigned long long)cxt->phys_addr, + cxt->max_count, cxt->record_size, + ramoops_ecc ? "on" : "off"); + + return 0; + +fail_buf: + kfree(cxt->pstore.buf); +fail_clear: + cxt->pstore.bufsize = 0; + cxt->max_count = 0; +fail_przs: + for (i = 0; cxt->przs[i]; i++) + persistent_ram_free(cxt->przs[i]); + kfree(cxt->przs); +fail_out: + return err; +} + +static int __exit ramoops_remove(struct platform_device *pdev) +{ +#if 0 + /* TODO(kees): We cannot unload ramoops since pstore doesn't support + * unregistering yet. + */ + struct ramoops_context *cxt = &oops_cxt; + + iounmap(cxt->virt_addr); + release_mem_region(cxt->phys_addr, cxt->size); + cxt->max_count = 0; + + /* TODO(kees): When pstore supports unregistering, call it here. */ + kfree(cxt->pstore.buf); + cxt->pstore.bufsize = 0; + + return 0; +#endif + return -EBUSY; +} + +static struct platform_driver ramoops_driver = { + .remove = __exit_p(ramoops_remove), + .driver = { + .name = "ramoops", + .owner = THIS_MODULE, + }, +}; + +static int __init ramoops_init(void) +{ + int ret; + ret = platform_driver_probe(&ramoops_driver, ramoops_probe); + if (ret == -ENODEV) { + /* + * If we didn't find a platform device, we use module parameters + * building platform data on the fly. + */ + pr_info("platform device not found, using module parameters\n"); + dummy_data = kzalloc(sizeof(struct ramoops_platform_data), + GFP_KERNEL); + if (!dummy_data) + return -ENOMEM; + dummy_data->mem_size = mem_size; + dummy_data->mem_address = mem_address; + dummy_data->record_size = record_size; + dummy_data->dump_oops = dump_oops; + dummy_data->ecc = ramoops_ecc; + dummy = platform_create_bundle(&ramoops_driver, ramoops_probe, + NULL, 0, dummy_data, + sizeof(struct ramoops_platform_data)); + + if (IS_ERR(dummy)) + ret = PTR_ERR(dummy); + else + ret = 0; + } + + return ret; +} + +static void __exit ramoops_exit(void) +{ + platform_driver_unregister(&ramoops_driver); + kfree(dummy_data); +} + +module_init(ramoops_init); +module_exit(ramoops_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Marco Stornelli <marco.stornelli@gmail.com>"); +MODULE_DESCRIPTION("RAM Oops/Panic logger/driver"); diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c new file mode 100644 index 000000000000..31f8d184f3a0 --- /dev/null +++ b/fs/pstore/ram_core.c @@ -0,0 +1,532 @@ +/* + * Copyright (C) 2012 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/device.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/list.h> +#include <linux/memblock.h> +#include <linux/rslib.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/pstore_ram.h> +#include <asm/page.h> + +struct persistent_ram_buffer { + uint32_t sig; + atomic_t start; + atomic_t size; + uint8_t data[0]; +}; + +#define PERSISTENT_RAM_SIG (0x43474244) /* DBGC */ + +static __initdata LIST_HEAD(persistent_ram_list); + +static inline size_t buffer_size(struct persistent_ram_zone *prz) +{ + return atomic_read(&prz->buffer->size); +} + +static inline size_t buffer_start(struct persistent_ram_zone *prz) +{ + return atomic_read(&prz->buffer->start); +} + +/* increase and wrap the start pointer, returning the old value */ +static inline size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a) +{ + int old; + int new; + + do { + old = atomic_read(&prz->buffer->start); + new = old + a; + while (unlikely(new > prz->buffer_size)) + new -= prz->buffer_size; + } while (atomic_cmpxchg(&prz->buffer->start, old, new) != old); + + return old; +} + +/* increase the size counter until it hits the max size */ +static inline void buffer_size_add(struct persistent_ram_zone *prz, size_t a) +{ + size_t old; + size_t new; + + if (atomic_read(&prz->buffer->size) == prz->buffer_size) + return; + + do { + old = atomic_read(&prz->buffer->size); + new = old + a; + if (new > prz->buffer_size) + new = prz->buffer_size; + } while (atomic_cmpxchg(&prz->buffer->size, old, new) != old); +} + +static void notrace persistent_ram_encode_rs8(struct persistent_ram_zone *prz, + uint8_t *data, size_t len, uint8_t *ecc) +{ + int i; + uint16_t par[prz->ecc_size]; + + /* Initialize the parity buffer */ + memset(par, 0, sizeof(par)); + encode_rs8(prz->rs_decoder, data, len, par, 0); + for (i = 0; i < prz->ecc_size; i++) + ecc[i] = par[i]; +} + +static int persistent_ram_decode_rs8(struct persistent_ram_zone *prz, + void *data, size_t len, uint8_t *ecc) +{ + int i; + uint16_t par[prz->ecc_size]; + + for (i = 0; i < prz->ecc_size; i++) + par[i] = ecc[i]; + return decode_rs8(prz->rs_decoder, data, par, len, + NULL, 0, NULL, 0, NULL); +} + +static void notrace persistent_ram_update_ecc(struct persistent_ram_zone *prz, + unsigned int start, unsigned int count) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + uint8_t *buffer_end = buffer->data + prz->buffer_size; + uint8_t *block; + uint8_t *par; + int ecc_block_size = prz->ecc_block_size; + int ecc_size = prz->ecc_size; + int size = prz->ecc_block_size; + + if (!prz->ecc) + return; + + block = buffer->data + (start & ~(ecc_block_size - 1)); + par = prz->par_buffer + (start / ecc_block_size) * prz->ecc_size; + + do { + if (block + ecc_block_size > buffer_end) + size = buffer_end - block; + persistent_ram_encode_rs8(prz, block, size, par); + block += ecc_block_size; + par += ecc_size; + } while (block < buffer->data + start + count); +} + +static void persistent_ram_update_header_ecc(struct persistent_ram_zone *prz) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + + if (!prz->ecc) + return; + + persistent_ram_encode_rs8(prz, (uint8_t *)buffer, sizeof(*buffer), + prz->par_header); +} + +static void persistent_ram_ecc_old(struct persistent_ram_zone *prz) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + uint8_t *block; + uint8_t *par; + + if (!prz->ecc) + return; + + block = buffer->data; + par = prz->par_buffer; + while (block < buffer->data + buffer_size(prz)) { + int numerr; + int size = prz->ecc_block_size; + if (block + size > buffer->data + prz->buffer_size) + size = buffer->data + prz->buffer_size - block; + numerr = persistent_ram_decode_rs8(prz, block, size, par); + if (numerr > 0) { + pr_devel("persistent_ram: error in block %p, %d\n", + block, numerr); + prz->corrected_bytes += numerr; + } else if (numerr < 0) { + pr_devel("persistent_ram: uncorrectable error in block %p\n", + block); + prz->bad_blocks++; + } + block += prz->ecc_block_size; + par += prz->ecc_size; + } +} + +static int persistent_ram_init_ecc(struct persistent_ram_zone *prz, + size_t buffer_size) +{ + int numerr; + struct persistent_ram_buffer *buffer = prz->buffer; + int ecc_blocks; + + if (!prz->ecc) + return 0; + + prz->ecc_block_size = 128; + prz->ecc_size = 16; + prz->ecc_symsize = 8; + prz->ecc_poly = 0x11d; + + ecc_blocks = DIV_ROUND_UP(prz->buffer_size, prz->ecc_block_size); + prz->buffer_size -= (ecc_blocks + 1) * prz->ecc_size; + + if (prz->buffer_size > buffer_size) { + pr_err("persistent_ram: invalid size %zu, non-ecc datasize %zu\n", + buffer_size, prz->buffer_size); + return -EINVAL; + } + + prz->par_buffer = buffer->data + prz->buffer_size; + prz->par_header = prz->par_buffer + ecc_blocks * prz->ecc_size; + + /* + * first consecutive root is 0 + * primitive element to generate roots = 1 + */ + prz->rs_decoder = init_rs(prz->ecc_symsize, prz->ecc_poly, 0, 1, + prz->ecc_size); + if (prz->rs_decoder == NULL) { + pr_info("persistent_ram: init_rs failed\n"); + return -EINVAL; + } + + prz->corrected_bytes = 0; + prz->bad_blocks = 0; + + numerr = persistent_ram_decode_rs8(prz, buffer, sizeof(*buffer), + prz->par_header); + if (numerr > 0) { + pr_info("persistent_ram: error in header, %d\n", numerr); + prz->corrected_bytes += numerr; + } else if (numerr < 0) { + pr_info("persistent_ram: uncorrectable error in header\n"); + prz->bad_blocks++; + } + + return 0; +} + +ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz, + char *str, size_t len) +{ + ssize_t ret; + + if (prz->corrected_bytes || prz->bad_blocks) + ret = snprintf(str, len, "" + "\n%d Corrected bytes, %d unrecoverable blocks\n", + prz->corrected_bytes, prz->bad_blocks); + else + ret = snprintf(str, len, "\nNo errors detected\n"); + + return ret; +} + +static void notrace persistent_ram_update(struct persistent_ram_zone *prz, + const void *s, unsigned int start, unsigned int count) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + memcpy(buffer->data + start, s, count); + persistent_ram_update_ecc(prz, start, count); +} + +static void __init +persistent_ram_save_old(struct persistent_ram_zone *prz) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + size_t size = buffer_size(prz); + size_t start = buffer_start(prz); + char *dest; + + persistent_ram_ecc_old(prz); + + dest = kmalloc(size, GFP_KERNEL); + if (dest == NULL) { + pr_err("persistent_ram: failed to allocate buffer\n"); + return; + } + + prz->old_log = dest; + prz->old_log_size = size; + memcpy(prz->old_log, &buffer->data[start], size - start); + memcpy(prz->old_log + size - start, &buffer->data[0], start); +} + +int notrace persistent_ram_write(struct persistent_ram_zone *prz, + const void *s, unsigned int count) +{ + int rem; + int c = count; + size_t start; + + if (unlikely(c > prz->buffer_size)) { + s += c - prz->buffer_size; + c = prz->buffer_size; + } + + buffer_size_add(prz, c); + + start = buffer_start_add(prz, c); + + rem = prz->buffer_size - start; + if (unlikely(rem < c)) { + persistent_ram_update(prz, s, start, rem); + s += rem; + c -= rem; + start = 0; + } + persistent_ram_update(prz, s, start, c); + + persistent_ram_update_header_ecc(prz); + + return count; +} + +size_t persistent_ram_old_size(struct persistent_ram_zone *prz) +{ + return prz->old_log_size; +} + +void *persistent_ram_old(struct persistent_ram_zone *prz) +{ + return prz->old_log; +} + +void persistent_ram_free_old(struct persistent_ram_zone *prz) +{ + kfree(prz->old_log); + prz->old_log = NULL; + prz->old_log_size = 0; +} + +static void *persistent_ram_vmap(phys_addr_t start, size_t size) +{ + struct page **pages; + phys_addr_t page_start; + unsigned int page_count; + pgprot_t prot; + unsigned int i; + void *vaddr; + + page_start = start - offset_in_page(start); + page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE); + + prot = pgprot_noncached(PAGE_KERNEL); + + pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL); + if (!pages) { + pr_err("%s: Failed to allocate array for %u pages\n", __func__, + page_count); + return NULL; + } + + for (i = 0; i < page_count; i++) { + phys_addr_t addr = page_start + i * PAGE_SIZE; + pages[i] = pfn_to_page(addr >> PAGE_SHIFT); + } + vaddr = vmap(pages, page_count, VM_MAP, prot); + kfree(pages); + + return vaddr; +} + +static void *persistent_ram_iomap(phys_addr_t start, size_t size) +{ + if (!request_mem_region(start, size, "persistent_ram")) { + pr_err("request mem region (0x%llx@0x%llx) failed\n", + (unsigned long long)size, (unsigned long long)start); + return NULL; + } + + return ioremap(start, size); +} + +static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, + struct persistent_ram_zone *prz) +{ + prz->paddr = start; + prz->size = size; + + if (pfn_valid(start >> PAGE_SHIFT)) + prz->vaddr = persistent_ram_vmap(start, size); + else + prz->vaddr = persistent_ram_iomap(start, size); + + if (!prz->vaddr) { + pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__, + (unsigned long long)size, (unsigned long long)start); + return -ENOMEM; + } + + prz->buffer = prz->vaddr + offset_in_page(start); + prz->buffer_size = size - sizeof(struct persistent_ram_buffer); + + return 0; +} + +static int __init persistent_ram_post_init(struct persistent_ram_zone *prz, bool ecc) +{ + int ret; + + prz->ecc = ecc; + + ret = persistent_ram_init_ecc(prz, prz->buffer_size); + if (ret) + return ret; + + if (prz->buffer->sig == PERSISTENT_RAM_SIG) { + if (buffer_size(prz) > prz->buffer_size || + buffer_start(prz) > buffer_size(prz)) + pr_info("persistent_ram: found existing invalid buffer," + " size %zu, start %zu\n", + buffer_size(prz), buffer_start(prz)); + else { + pr_info("persistent_ram: found existing buffer," + " size %zu, start %zu\n", + buffer_size(prz), buffer_start(prz)); + persistent_ram_save_old(prz); + } + } else { + pr_info("persistent_ram: no valid data in buffer" + " (sig = 0x%08x)\n", prz->buffer->sig); + } + + prz->buffer->sig = PERSISTENT_RAM_SIG; + atomic_set(&prz->buffer->start, 0); + atomic_set(&prz->buffer->size, 0); + + return 0; +} + +void persistent_ram_free(struct persistent_ram_zone *prz) +{ + if (pfn_valid(prz->paddr >> PAGE_SHIFT)) { + vunmap(prz->vaddr); + } else { + iounmap(prz->vaddr); + release_mem_region(prz->paddr, prz->size); + } + persistent_ram_free_old(prz); + kfree(prz); +} + +struct persistent_ram_zone * __init persistent_ram_new(phys_addr_t start, + size_t size, + bool ecc) +{ + struct persistent_ram_zone *prz; + int ret = -ENOMEM; + + prz = kzalloc(sizeof(struct persistent_ram_zone), GFP_KERNEL); + if (!prz) { + pr_err("persistent_ram: failed to allocate persistent ram zone\n"); + goto err; + } + + ret = persistent_ram_buffer_map(start, size, prz); + if (ret) + goto err; + + persistent_ram_post_init(prz, ecc); + persistent_ram_update_header_ecc(prz); + + return prz; +err: + kfree(prz); + return ERR_PTR(ret); +} + +#ifndef MODULE +static int __init persistent_ram_buffer_init(const char *name, + struct persistent_ram_zone *prz) +{ + int i; + struct persistent_ram *ram; + struct persistent_ram_descriptor *desc; + phys_addr_t start; + + list_for_each_entry(ram, &persistent_ram_list, node) { + start = ram->start; + for (i = 0; i < ram->num_descs; i++) { + desc = &ram->descs[i]; + if (!strcmp(desc->name, name)) + return persistent_ram_buffer_map(start, + desc->size, prz); + start += desc->size; + } + } + + return -EINVAL; +} + +static __init +struct persistent_ram_zone *__persistent_ram_init(struct device *dev, bool ecc) +{ + struct persistent_ram_zone *prz; + int ret = -ENOMEM; + + prz = kzalloc(sizeof(struct persistent_ram_zone), GFP_KERNEL); + if (!prz) { + pr_err("persistent_ram: failed to allocate persistent ram zone\n"); + goto err; + } + + ret = persistent_ram_buffer_init(dev_name(dev), prz); + if (ret) { + pr_err("persistent_ram: failed to initialize buffer\n"); + goto err; + } + + persistent_ram_post_init(prz, ecc); + + return prz; +err: + kfree(prz); + return ERR_PTR(ret); +} + +struct persistent_ram_zone * __init +persistent_ram_init_ringbuffer(struct device *dev, bool ecc) +{ + return __persistent_ram_init(dev, ecc); +} + +int __init persistent_ram_early_init(struct persistent_ram *ram) +{ + int ret; + + ret = memblock_reserve(ram->start, ram->size); + if (ret) { + pr_err("Failed to reserve persistent memory from %08lx-%08lx\n", + (long)ram->start, (long)(ram->start + ram->size - 1)); + return ret; + } + + list_add_tail(&ram->node, &persistent_ram_list); + + pr_info("Initialized persistent memory from %08lx-%08lx\n", + (long)ram->start, (long)(ram->start + ram->size - 1)); + + return 0; +} +#endif diff --git a/fs/stat.c b/fs/stat.c index c733dc5753ae..0cef3366a919 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -57,12 +57,13 @@ EXPORT_SYMBOL(vfs_getattr); int vfs_fstat(unsigned int fd, struct kstat *stat) { - struct file *f = fget(fd); + int fput_needed; + struct file *f = fget_light(fd, &fput_needed); int error = -EBADF; if (f) { error = vfs_getattr(f->f_path.mnt, f->f_path.dentry, stat); - fput(f); + fput_light(f, fput_needed); } return error; } @@ -190,24 +191,32 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat #endif /* __ARCH_WANT_OLD_STAT */ +#if BITS_PER_LONG == 32 +# define choose_32_64(a,b) a +#else +# define choose_32_64(a,b) b +#endif + +#define valid_dev(x) choose_32_64(old_valid_dev,new_valid_dev)(x) +#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) + +#ifndef INIT_STRUCT_STAT_PADDING +# define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) +#endif + static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; -#if BITS_PER_LONG == 32 - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + if (!valid_dev(stat->dev) || !valid_dev(stat->rdev)) return -EOVERFLOW; -#else - if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev)) +#if BITS_PER_LONG == 32 + if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif - memset(&tmp, 0, sizeof(tmp)); -#if BITS_PER_LONG == 32 - tmp.st_dev = old_encode_dev(stat->dev); -#else - tmp.st_dev = new_encode_dev(stat->dev); -#endif + INIT_STRUCT_STAT_PADDING(tmp); + tmp.st_dev = encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -217,15 +226,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) return -EOVERFLOW; SET_UID(tmp.st_uid, stat->uid); SET_GID(tmp.st_gid, stat->gid); -#if BITS_PER_LONG == 32 - tmp.st_rdev = old_encode_dev(stat->rdev); -#else - tmp.st_rdev = new_encode_dev(stat->rdev); -#endif -#if BITS_PER_LONG == 32 - if (stat->size > MAX_NON_LFS) - return -EOVERFLOW; -#endif + tmp.st_rdev = encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; @@ -327,11 +328,15 @@ SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf, /* ---------- LFS-64 ----------- */ #ifdef __ARCH_WANT_STAT64 +#ifndef INIT_STRUCT_STAT64_PADDING +# define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st)) +#endif + static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) { struct stat64 tmp; - memset(&tmp, 0, sizeof(struct stat64)); + INIT_STRUCT_STAT64_PADDING(tmp); #ifdef CONFIG_MIPS /* mips has weird padding, so we don't get 64 bits there */ if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev)) diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 35a36d39fa2c..e6bb9b2a4cbe 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -132,6 +132,24 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd) rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children); } +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +/* Test for attributes that want to ignore lockdep for read-locking */ +static bool ignore_lockdep(struct sysfs_dirent *sd) +{ + return sysfs_type(sd) == SYSFS_KOBJ_ATTR && + sd->s_attr.attr->ignore_lockdep; +} + +#else + +static inline bool ignore_lockdep(struct sysfs_dirent *sd) +{ + return true; +} + +#endif + /** * sysfs_get_active - get an active reference to sysfs_dirent * @sd: sysfs_dirent to get an active reference to @@ -155,15 +173,17 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd) return NULL; t = atomic_cmpxchg(&sd->s_active, v, v + 1); - if (likely(t == v)) { - rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); - return sd; - } + if (likely(t == v)) + break; if (t < 0) return NULL; cpu_relax(); } + + if (likely(!ignore_lockdep(sd))) + rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); + return sd; } /** @@ -180,7 +200,8 @@ void sysfs_put_active(struct sysfs_dirent *sd) if (unlikely(!sd)) return; - rwsem_release(&sd->dep_map, 1, _RET_IP_); + if (likely(!ignore_lockdep(sd))) + rwsem_release(&sd->dep_map, 1, _RET_IP_); v = atomic_dec_return(&sd->s_active); if (likely(v != SD_DEACTIVATED_BIAS)) return; @@ -858,7 +879,6 @@ int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd, const void *new_ns, const char *new_name) { - const char *dup_name = NULL; int error; mutex_lock(&sysfs_mutex); @@ -875,11 +895,11 @@ int sysfs_rename(struct sysfs_dirent *sd, /* rename sysfs_dirent */ if (strcmp(sd->s_name, new_name) != 0) { error = -ENOMEM; - new_name = dup_name = kstrdup(new_name, GFP_KERNEL); + new_name = kstrdup(new_name, GFP_KERNEL); if (!new_name) goto out; - dup_name = sd->s_name; + kfree(sd->s_name); sd->s_name = new_name; } @@ -895,7 +915,6 @@ int sysfs_rename(struct sysfs_dirent *sd, error = 0; out: mutex_unlock(&sysfs_mutex); - kfree(dup_name); return error; } diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 16ad84d8402f..abd51331345e 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -2361,7 +2361,7 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, * by passing 'ubifs_tnc_remove_nm()' the same key but * an unmatchable name. */ - struct qstr noname = { .len = 0, .name = "" }; + struct qstr noname = { .name = "" }; err = dbg_check_tnc(c, 0); mutex_unlock(&c->tnc_mutex); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 85b272268754..7a8bafa19c9f 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -298,7 +298,7 @@ int ubifs_setxattr(struct dentry *dentry, const char *name, { struct inode *inode, *host = dentry->d_inode; struct ubifs_info *c = host->i_sb->s_fs_info; - struct qstr nm = { .name = name, .len = strlen(name) }; + struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_dent_node *xent; union ubifs_key key; int err, type; @@ -361,7 +361,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, { struct inode *inode, *host = dentry->d_inode; struct ubifs_info *c = host->i_sb->s_fs_info; - struct qstr nm = { .name = name, .len = strlen(name) }; + struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_inode *ui; struct ubifs_dent_node *xent; union ubifs_key key; @@ -524,7 +524,7 @@ int ubifs_removexattr(struct dentry *dentry, const char *name) { struct inode *inode, *host = dentry->d_inode; struct ubifs_info *c = host->i_sb->s_fs_info; - struct qstr nm = { .name = name, .len = strlen(name) }; + struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_dent_node *xent; union ubifs_key key; int err; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 38de8f234b94..a165c66e3eef 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -1193,7 +1193,7 @@ static struct dentry *udf_get_parent(struct dentry *child) { struct kernel_lb_addr tloc; struct inode *inode = NULL; - struct qstr dotdot = {.name = "..", .len = 2}; + struct qstr dotdot = QSTR_INIT("..", 2); struct fileIdentDesc cfi; struct udf_fileident_bh fibh; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index ac8e279eccc6..302f340d0071 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -146,10 +146,7 @@ static struct dentry *ufs_fh_to_parent(struct super_block *sb, struct fid *fid, static struct dentry *ufs_get_parent(struct dentry *child) { - struct qstr dot_dot = { - .name = "..", - .len = 2, - }; + struct qstr dot_dot = QSTR_INIT("..", 2); ino_t ino; ino = ufs_inode_by_name(child->d_inode, &dot_dot); |