diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-06 03:09:16 +0900 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-06 03:09:16 +0900 |
commit | 11126c611e10abb18b6f1ed0300c0548c3906b54 (patch) | |
tree | 246227ad730c1e68f5a9c03db57cd4592abe7687 /fs | |
parent | 67966e088b0c7dc926f4ce19565ebf208e18d058 (diff) | |
parent | 33e2a4227ddff7c18921ac175fae3ab0e3ff8a76 (diff) |
Merge branch 'akpm' (Andrew's patch-bomb)
Merge misc patches from Andrew Morton:
"The MM tree is rather stuck while I wait to find out what the heck is
happening with sched/numa. Probably I'll need to route around all the
code which was added to -next, sigh.
So this is "everything else", or at least most of it - other small
bits are still awaiting resolutions of various kinds."
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (180 commits)
lib/decompress.c add __init to decompress_method and data
kernel/resource.c: fix stack overflow in __reserve_region_with_split()
omfs: convert to use beXX_add_cpu()
taskstats: cgroupstats_user_cmd() may leak on error
aoe: update aoe-internal version number to 50
aoe: update documentation to better reflect aoe-plus-udev usage
aoe: remove unused code
aoe: make dynamic block minor numbers the default
aoe: update and specify AoE address guards and error messages
aoe: retain static block device numbers for backwards compatibility
aoe: support more AoE addresses with dynamic block device minor numbers
aoe: update documentation with new URL and VM settings reference
aoe: update copyright year in touched files
aoe: update internal version number to 49
aoe: remove unused code and add cosmetic improvements
aoe: increase net_device reference count while using it
aoe: associate frames with the AoE storage target
aoe: disallow unsupported AoE minor addresses
aoe: do revalidation steps in order
aoe: failover remote interface based on aoe_deadsecs parameter
...
Diffstat (limited to 'fs')
-rw-r--r-- | fs/Kconfig.binfmt | 8 | ||||
-rw-r--r-- | fs/Makefile | 3 | ||||
-rw-r--r-- | fs/binfmt_aout.c | 54 | ||||
-rw-r--r-- | fs/binfmt_elf.c | 149 | ||||
-rw-r--r-- | fs/binfmt_elf_fdpic.c | 6 | ||||
-rw-r--r-- | fs/binfmt_flat.c | 2 | ||||
-rw-r--r-- | fs/compat_binfmt_elf.c | 7 | ||||
-rw-r--r-- | fs/coredump.c | 20 | ||||
-rw-r--r-- | fs/coredump.h | 6 | ||||
-rw-r--r-- | fs/eventpoll.c | 38 | ||||
-rw-r--r-- | fs/exec.c | 3 | ||||
-rw-r--r-- | fs/fat/Makefile | 2 | ||||
-rw-r--r-- | fs/fat/cache.c | 10 | ||||
-rw-r--r-- | fs/fat/dir.c | 56 | ||||
-rw-r--r-- | fs/fat/fat.h | 97 | ||||
-rw-r--r-- | fs/fat/fatent.c | 13 | ||||
-rw-r--r-- | fs/fat/inode.c | 187 | ||||
-rw-r--r-- | fs/fat/namei_msdos.c | 7 | ||||
-rw-r--r-- | fs/fat/namei_vfat.c | 5 | ||||
-rw-r--r-- | fs/fat/nfs.c | 101 | ||||
-rw-r--r-- | fs/hpfs/anode.c | 6 | ||||
-rw-r--r-- | fs/hpfs/dnode.c | 28 | ||||
-rw-r--r-- | fs/omfs/file.c | 5 | ||||
-rw-r--r-- | fs/proc/generic.c | 15 | ||||
-rw-r--r-- | fs/proc/inode.c | 1 | ||||
-rw-r--r-- | fs/proc/internal.h | 2 | ||||
-rw-r--r-- | fs/proc/proc_sysctl.c | 3 | ||||
-rw-r--r-- | fs/proc/root.c | 2 | ||||
-rw-r--r-- | fs/super.c | 2 |
29 files changed, 531 insertions, 307 deletions
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 02257420274..0efd1524b97 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -164,3 +164,11 @@ config BINFMT_MISC You may say M here for module support and later load the module when you have use for it; the module is called binfmt_misc. If you don't know what to answer at this point, say Y. + +config COREDUMP + bool "Enable core dump support" if EXPERT + default y + help + This option enables support for performing core dumps. You almost + certainly want to say Y here. Not necessary on systems that never + need debugging or only ever run flawless code. diff --git a/fs/Makefile b/fs/Makefile index 8938f825032..1d7af79288a 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -11,7 +11,7 @@ obj-y := open.o read_write.o file_table.o super.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o drop_caches.o splice.o sync.o utimes.o \ - stack.o fs_struct.o statfs.o coredump.o + stack.o fs_struct.o statfs.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o @@ -48,6 +48,7 @@ obj-$(CONFIG_FS_MBCACHE) += mbcache.o obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o xattr_acl.o obj-$(CONFIG_NFS_COMMON) += nfs_common/ obj-$(CONFIG_GENERIC_ACL) += generic_acl.o +obj-$(CONFIG_COREDUMP) += coredump.o obj-$(CONFIG_FHANDLE) += fhandle.o diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index d146e181d10..0e7a6f81ae3 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -32,31 +32,8 @@ static int load_aout_binary(struct linux_binprm *, struct pt_regs * regs); static int load_aout_library(struct file*); -static int aout_core_dump(struct coredump_params *cprm); - -static struct linux_binfmt aout_format = { - .module = THIS_MODULE, - .load_binary = load_aout_binary, - .load_shlib = load_aout_library, - .core_dump = aout_core_dump, - .min_coredump = PAGE_SIZE -}; - -#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE) - -static int set_brk(unsigned long start, unsigned long end) -{ - start = PAGE_ALIGN(start); - end = PAGE_ALIGN(end); - if (end > start) { - unsigned long addr; - addr = vm_brk(start, end - start); - if (BAD_ADDR(addr)) - return addr; - } - return 0; -} +#ifdef CONFIG_COREDUMP /* * Routine writes a core dump image in the current directory. * Currently only a stub-function. @@ -66,7 +43,6 @@ static int set_brk(unsigned long start, unsigned long end) * field, which also makes sure the core-dumps won't be recursive if the * dumping of the process results in another error.. */ - static int aout_core_dump(struct coredump_params *cprm) { struct file *file = cprm->file; @@ -89,7 +65,7 @@ static int aout_core_dump(struct coredump_params *cprm) current->flags |= PF_DUMPCORE; strncpy(dump.u_comm, current->comm, sizeof(dump.u_comm)); dump.u_ar0 = offsetof(struct user, regs); - dump.signal = cprm->signr; + dump.signal = cprm->siginfo->si_signo; aout_dump_thread(cprm->regs, &dump); /* If the size of the dump file exceeds the rlimit, then see what would happen @@ -135,6 +111,32 @@ end_coredump: set_fs(fs); return has_dumped; } +#else +#define aout_core_dump NULL +#endif + +static struct linux_binfmt aout_format = { + .module = THIS_MODULE, + .load_binary = load_aout_binary, + .load_shlib = load_aout_library, + .core_dump = aout_core_dump, + .min_coredump = PAGE_SIZE +}; + +#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE) + +static int set_brk(unsigned long start, unsigned long end) +{ + start = PAGE_ALIGN(start); + end = PAGE_ALIGN(end); + if (end > start) { + unsigned long addr; + addr = vm_brk(start, end - start); + if (BAD_ADDR(addr)) + return addr; + } + return 0; +} /* * create_aout_tables() parses the env- and arg-strings in new user diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 0225fddf49b..28a64e76952 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -27,6 +27,7 @@ #include <linux/compiler.h> #include <linux/highmem.h> #include <linux/pagemap.h> +#include <linux/vmalloc.h> #include <linux/security.h> #include <linux/random.h> #include <linux/elf.h> @@ -37,6 +38,13 @@ #include <asm/page.h> #include <asm/exec.h> +#ifndef user_long_t +#define user_long_t long +#endif +#ifndef user_siginfo_t +#define user_siginfo_t siginfo_t +#endif + static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs); static int load_elf_library(struct file *); static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *, @@ -881,7 +889,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) } if (elf_interpreter) { - unsigned long uninitialized_var(interp_map_addr); + unsigned long interp_map_addr = 0; elf_entry = load_elf_interp(&loc->interp_elf_ex, interpreter, @@ -1372,6 +1380,103 @@ static void fill_auxv_note(struct memelfnote *note, struct mm_struct *mm) fill_note(note, "CORE", NT_AUXV, i * sizeof(elf_addr_t), auxv); } +static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata, + siginfo_t *siginfo) +{ + mm_segment_t old_fs = get_fs(); + set_fs(KERNEL_DS); + copy_siginfo_to_user((user_siginfo_t __user *) csigdata, siginfo); + set_fs(old_fs); + fill_note(note, "CORE", NT_SIGINFO, sizeof(*csigdata), csigdata); +} + +#define MAX_FILE_NOTE_SIZE (4*1024*1024) +/* + * Format of NT_FILE note: + * + * long count -- how many files are mapped + * long page_size -- units for file_ofs + * array of [COUNT] elements of + * long start + * long end + * long file_ofs + * followed by COUNT filenames in ASCII: "FILE1" NUL "FILE2" NUL... + */ +static void fill_files_note(struct memelfnote *note) +{ + struct vm_area_struct *vma; + unsigned count, size, names_ofs, remaining, n; + user_long_t *data; + user_long_t *start_end_ofs; + char *name_base, *name_curpos; + + /* *Estimated* file count and total data size needed */ + count = current->mm->map_count; + size = count * 64; + + names_ofs = (2 + 3 * count) * sizeof(data[0]); + alloc: + if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */ + goto err; + size = round_up(size, PAGE_SIZE); + data = vmalloc(size); + if (!data) + goto err; + + start_end_ofs = data + 2; + name_base = name_curpos = ((char *)data) + names_ofs; + remaining = size - names_ofs; + count = 0; + for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) { + struct file *file; + const char *filename; + + file = vma->vm_file; + if (!file) + continue; + filename = d_path(&file->f_path, name_curpos, remaining); + if (IS_ERR(filename)) { + if (PTR_ERR(filename) == -ENAMETOOLONG) { + vfree(data); + size = size * 5 / 4; + goto alloc; + } + continue; + } + + /* d_path() fills at the end, move name down */ + /* n = strlen(filename) + 1: */ + n = (name_curpos + remaining) - filename; + remaining = filename - name_curpos; + memmove(name_curpos, filename, n); + name_curpos += n; + + *start_end_ofs++ = vma->vm_start; + *start_end_ofs++ = vma->vm_end; + *start_end_ofs++ = vma->vm_pgoff; + count++; + } + + /* Now we know exact count of files, can store it */ + data[0] = count; + data[1] = PAGE_SIZE; + /* + * Count usually is less than current->mm->map_count, + * we need to move filenames down. + */ + n = current->mm->map_count - count; + if (n != 0) { + unsigned shift_bytes = n * 3 * sizeof(data[0]); + memmove(name_base - shift_bytes, name_base, + name_curpos - name_base); + name_curpos -= shift_bytes; + } + + size = name_curpos - (char *)data; + fill_note(note, "CORE", NT_FILE, size, data); + err: ; +} + #ifdef CORE_DUMP_USE_REGSET #include <linux/regset.h> @@ -1385,7 +1490,10 @@ struct elf_thread_core_info { struct elf_note_info { struct elf_thread_core_info *thread; struct memelfnote psinfo; + struct memelfnote signote; struct memelfnote auxv; + struct memelfnote files; + user_siginfo_t csigdata; size_t size; int thread_notes; }; @@ -1480,7 +1588,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, static int fill_note_info(struct elfhdr *elf, int phdrs, struct elf_note_info *info, - long signr, struct pt_regs *regs) + siginfo_t *siginfo, struct pt_regs *regs) { struct task_struct *dump_task = current; const struct user_regset_view *view = task_user_regset_view(dump_task); @@ -1550,7 +1658,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, * Now fill in each thread's information. */ for (t = info->thread; t != NULL; t = t->next) - if (!fill_thread_core_info(t, view, signr, &info->size)) + if (!fill_thread_core_info(t, view, siginfo->si_signo, &info->size)) return 0; /* @@ -1559,9 +1667,15 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, fill_psinfo(psinfo, dump_task->group_leader, dump_task->mm); info->size += notesize(&info->psinfo); + fill_siginfo_note(&info->signote, &info->csigdata, siginfo); + info->size += notesize(&info->signote); + fill_auxv_note(&info->auxv, current->mm); info->size += notesize(&info->auxv); + fill_files_note(&info->files); + info->size += notesize(&info->files); + return 1; } @@ -1588,8 +1702,12 @@ static int write_note_info(struct elf_note_info *info, if (first && !writenote(&info->psinfo, file, foffset)) return 0; + if (first && !writenote(&info->signote, file, foffset)) + return 0; if (first && !writenote(&info->auxv, file, foffset)) return 0; + if (first && !writenote(&info->files, file, foffset)) + return 0; for (i = 1; i < info->thread_notes; ++i) if (t->notes[i].data && @@ -1616,6 +1734,7 @@ static void free_note_info(struct elf_note_info *info) kfree(t); } kfree(info->psinfo.data); + vfree(info->files.data); } #else @@ -1681,6 +1800,7 @@ struct elf_note_info { #ifdef ELF_CORE_COPY_XFPREGS elf_fpxregset_t *xfpu; #endif + user_siginfo_t csigdata; int thread_status_size; int numnote; }; @@ -1690,8 +1810,8 @@ static int elf_note_info_init(struct elf_note_info *info) memset(info, 0, sizeof(*info)); INIT_LIST_HEAD(&info->thread_list); - /* Allocate space for six ELF notes */ - info->notes = kmalloc(6 * sizeof(struct memelfnote), GFP_KERNEL); + /* Allocate space for ELF notes */ + info->notes = kmalloc(8 * sizeof(struct memelfnote), GFP_KERNEL); if (!info->notes) return 0; info->psinfo = kmalloc(sizeof(*info->psinfo), GFP_KERNEL); @@ -1713,14 +1833,14 @@ static int elf_note_info_init(struct elf_note_info *info) static int fill_note_info(struct elfhdr *elf, int phdrs, struct elf_note_info *info, - long signr, struct pt_regs *regs) + siginfo_t *siginfo, struct pt_regs *regs) { struct list_head *t; if (!elf_note_info_init(info)) return 0; - if (signr) { + if (siginfo->si_signo) { struct core_thread *ct; struct elf_thread_status *ets; @@ -1738,13 +1858,13 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, int sz; ets = list_entry(t, struct elf_thread_status, list); - sz = elf_dump_thread_status(signr, ets); + sz = elf_dump_thread_status(siginfo->si_signo, ets); info->thread_status_size += sz; } } /* now collect the dump for the current */ memset(info->prstatus, 0, sizeof(*info->prstatus)); - fill_prstatus(info->prstatus, current, signr); + fill_prstatus(info->prstatus, current, siginfo->si_signo); elf_core_copy_regs(&info->prstatus->pr_reg, regs); /* Set up header */ @@ -1761,9 +1881,11 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, fill_note(info->notes + 1, "CORE", NT_PRPSINFO, sizeof(*info->psinfo), info->psinfo); - info->numnote = 2; + fill_siginfo_note(info->notes + 2, &info->csigdata, siginfo); + fill_auxv_note(info->notes + 3, current->mm); + fill_files_note(info->notes + 4); - fill_auxv_note(&info->notes[info->numnote++], current->mm); + info->numnote = 5; /* Try to dump the FPU. */ info->prstatus->pr_fpvalid = elf_core_copy_task_fpregs(current, regs, @@ -1825,6 +1947,9 @@ static void free_note_info(struct elf_note_info *info) kfree(list_entry(tmp, struct elf_thread_status, list)); } + /* Free data allocated by fill_files_note(): */ + vfree(info->notes[4].data); + kfree(info->prstatus); kfree(info->psinfo); kfree(info->notes); @@ -1951,7 +2076,7 @@ static int elf_core_dump(struct coredump_params *cprm) * Collect all the non-memory information about the process for the * notes. This also sets up the file header. */ - if (!fill_note_info(elf, e_phnum, &info, cprm->signr, cprm->regs)) + if (!fill_note_info(elf, e_phnum, &info, cprm->siginfo, cprm->regs)) goto cleanup; has_dumped = 1; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 3d77cf81ba3..08d812b3228 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1642,7 +1642,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) goto cleanup; #endif - if (cprm->signr) { + if (cprm->siginfo->si_signo) { struct core_thread *ct; struct elf_thread_status *tmp; @@ -1661,13 +1661,13 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) int sz; tmp = list_entry(t, struct elf_thread_status, list); - sz = elf_dump_thread_status(cprm->signr, tmp); + sz = elf_dump_thread_status(cprm->siginfo->si_signo, tmp); thread_status_size += sz; } } /* now collect the dump for the current */ - fill_prstatus(prstatus, current, cprm->signr); + fill_prstatus(prstatus, current, cprm->siginfo->si_signo); elf_core_copy_regs(&prstatus->pr_reg, cprm->regs); segs = current->mm->map_count; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 178cb70acc2..e280352b28f 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -107,7 +107,7 @@ static struct linux_binfmt flat_format = { static int flat_core_dump(struct coredump_params *cprm) { printk("Process %s:%d received signr %d and should have core dumped\n", - current->comm, current->pid, (int) cprm->signr); + current->comm, current->pid, (int) cprm->siginfo->si_signo); return(1); } diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 112e45a17e9..a81147e2e4e 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -38,6 +38,13 @@ #define elf_addr_t Elf32_Addr /* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_user copy_siginfo_to_user32 + +/* * The machine-dependent core note format types are defined in elfcore-compat.h, * which requires asm/elf.h to define compat_elf_gregset_t et al. */ diff --git a/fs/coredump.c b/fs/coredump.c index f045bbad682..fd37facac8d 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -14,6 +14,7 @@ #include <linux/key.h> #include <linux/personality.h> #include <linux/binfmts.h> +#include <linux/coredump.h> #include <linux/utsname.h> #include <linux/pid_namespace.h> #include <linux/module.h> @@ -39,6 +40,7 @@ #include <trace/events/task.h> #include "internal.h" +#include "coredump.h" #include <trace/events/sched.h> @@ -147,7 +149,7 @@ put_exe_file: * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ -static int format_corename(struct core_name *cn, long signr) +static int format_corename(struct core_name *cn, struct coredump_params *cprm) { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; @@ -192,9 +194,13 @@ static int format_corename(struct core_name *cn, long signr) case 'g': err = cn_printf(cn, "%d", cred->gid); break; + case 'd': + err = cn_printf(cn, "%d", + __get_dumpable(cprm->mm_flags)); + break; /* signal that caused the coredump */ case 's': - err = cn_printf(cn, "%ld", signr); + err = cn_printf(cn, "%ld", cprm->siginfo->si_signo); break; /* UNIX time of coredump */ case 't': { @@ -451,7 +457,7 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) return 0; } -void do_coredump(long signr, int exit_code, struct pt_regs *regs) +void do_coredump(siginfo_t *siginfo, struct pt_regs *regs) { struct core_state core_state; struct core_name cn; @@ -466,7 +472,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) bool need_nonrelative = false; static atomic_t core_dump_count = ATOMIC_INIT(0); struct coredump_params cprm = { - .signr = signr, + .siginfo = siginfo, .regs = regs, .limit = rlimit(RLIMIT_CORE), /* @@ -477,7 +483,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) .mm_flags = mm->flags, }; - audit_core_dumps(signr); + audit_core_dumps(siginfo->si_signo); binfmt = mm->binfmt; if (!binfmt || !binfmt->core_dump) @@ -501,7 +507,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) need_nonrelative = true; } - retval = coredump_wait(exit_code, &core_state); + retval = coredump_wait(siginfo->si_signo, &core_state); if (retval < 0) goto fail_creds; @@ -513,7 +519,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) */ clear_thread_flag(TIF_SIGPENDING); - ispipe = format_corename(&cn, signr); + ispipe = format_corename(&cn, &cprm); if (ispipe) { int dump_count; diff --git a/fs/coredump.h b/fs/coredump.h new file mode 100644 index 00000000000..e39ff072110 --- /dev/null +++ b/fs/coredump.h @@ -0,0 +1,6 @@ +#ifndef _FS_COREDUMP_H +#define _FS_COREDUMP_H + +extern int __get_dumpable(unsigned long mm_flags); + +#endif diff --git a/fs/eventpoll.c b/fs/eventpoll.c index cd96649bfe6..da72250ddc1 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -346,7 +346,7 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p) /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { - return op != EPOLL_CTL_DEL; + return op == EPOLL_CTL_ADD || op == EPOLL_CTL_MOD; } /* Initialize the poll safe wake up structure */ @@ -676,6 +676,34 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) return 0; } +/* + * Disables a "struct epitem" in the eventpoll set. Returns -EBUSY if the item + * had no event flags set, indicating that another thread may be currently + * handling that item's events (in the case that EPOLLONESHOT was being + * used). Otherwise a zero result indicates that the item has been disabled + * from receiving events. A disabled item may be re-enabled via + * EPOLL_CTL_MOD. Must be called with "mtx" held. + */ +static int ep_disable(struct eventpoll *ep, struct epitem *epi) +{ + int result = 0; + unsigned long flags; + + spin_lock_irqsave(&ep->lock, flags); + if (epi->event.events & ~EP_PRIVATE_BITS) { + if (ep_is_linked(&epi->rdllink)) + list_del_init(&epi->rdllink); + /* Ensure ep_poll_callback will not add epi back onto ready + list: */ + epi->event.events &= EP_PRIVATE_BITS; + } + else + result = -EBUSY; + spin_unlock_irqrestore(&ep->lock, flags); + + return result; +} + static void ep_free(struct eventpoll *ep) { struct rb_node *rbp; @@ -1020,8 +1048,6 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) rb_insert_color(&epi->rbn, &ep->rbr); } - - #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate @@ -1787,6 +1813,12 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, } else error = -ENOENT; break; + case EPOLL_CTL_DISABLE: + if (epi) + error = ep_disable(ep, epi); + else + error = -ENOENT; + break; } mutex_unlock(&ep->mtx); diff --git a/fs/exec.c b/fs/exec.c index 48fb26ef8a1..9824473a7ec 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -63,6 +63,7 @@ #include <trace/events/task.h> #include "internal.h" +#include "coredump.h" #include <trace/events/sched.h> @@ -1096,7 +1097,7 @@ void setup_new_exec(struct linux_binprm * bprm) current->sas_ss_sp = current->sas_ss_size = 0; if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid())) - set_dumpable(current->mm, 1); + set_dumpable(current->mm, SUID_DUMPABLE_ENABLED); else set_dumpable(current->mm, suid_dumpable); diff --git a/fs/fat/Makefile b/fs/fat/Makefile index e06190322c1..964b634f666 100644 --- a/fs/fat/Makefile +++ b/fs/fat/Makefile @@ -6,6 +6,6 @@ obj-$(CONFIG_FAT_FS) += fat.o obj-$(CONFIG_VFAT_FS) += vfat.o obj-$(CONFIG_MSDOS_FS) += msdos.o -fat-y := cache.o dir.o fatent.o file.o inode.o misc.o +fat-y := cache.o dir.o fatent.o file.o inode.o misc.o nfs.o vfat-y := namei_vfat.o msdos-y := namei_msdos.o diff --git a/fs/fat/cache.c b/fs/fat/cache.c index 1cc7038e273..91ad9e1c944 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -190,7 +190,8 @@ static void __fat_cache_inval_inode(struct inode *inode) struct fat_cache *cache; while (!list_empty(&i->cache_lru)) { - cache = list_entry(i->cache_lru.next, struct fat_cache, cache_list); + cache = list_entry(i->cache_lru.next, + struct fat_cache, cache_list); list_del_init(&cache->cache_list); i->nr_caches--; fat_cache_free(cache); @@ -261,9 +262,10 @@ int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) if (nr < 0) goto out; else if (nr == FAT_ENT_FREE) { - fat_fs_error_ratelimit(sb, "%s: invalid cluster chain" - " (i_pos %lld)", __func__, - MSDOS_I(inode)->i_pos); + fat_fs_error_ratelimit(sb, + "%s: invalid cluster chain (i_pos %lld)", + __func__, + MSDOS_I(inode)->i_pos); nr = -EIO; goto out; } else if (nr == FAT_ENT_EOF) { diff --git a/fs/fat/dir.c b/fs/fat/dir.c index dc49ed2cbff..bca6d0a1255 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -18,7 +18,7 @@ #include <linux/time.h> #include <linux/buffer_head.h> #include <linux/compat.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <linux/kernel.h> #include "fat.h" @@ -123,7 +123,8 @@ static inline int fat_get_entry(struct inode *dir, loff_t *pos, { /* Fast stuff first */ if (*bh && *de && - (*de - (struct msdos_dir_entry *)(*bh)->b_data) < MSDOS_SB(dir->i_sb)->dir_per_block - 1) { + (*de - (struct msdos_dir_entry *)(*bh)->b_data) < + MSDOS_SB(dir->i_sb)->dir_per_block - 1) { *pos += sizeof(struct msdos_dir_entry); (*de)++; return 0; @@ -155,7 +156,8 @@ static int uni16_to_x8(struct super_block *sb, unsigned char *ascii, while (*ip && ((len - NLS_MAX_CHARSET_SIZE) > 0)) { ec = *ip++; - if ((charlen = nls->uni2char(ec, op, NLS_MAX_CHARSET_SIZE)) > 0) { + charlen = nls->uni2char(ec, op, NLS_MAX_CHARSET_SIZE); + if (charlen > 0) { op += charlen; len -= charlen; } else { @@ -172,12 +174,12 @@ static int uni16_to_x8(struct super_block *sb, unsigned char *ascii, } if (unlikely(*ip)) { - fat_msg(sb, KERN_WARNING, "filename was truncated while " - "converting."); + fat_msg(sb, KERN_WARNING, + "filename was truncated while converting."); } *op = 0; - return (op - ascii); + return op - ascii; } static inline int fat_uni_to_x8(struct super_block *sb, const wchar_t *uni, @@ -205,7 +207,8 @@ fat_short2uni(struct nls_table *t, unsigned char *c, int clen, wchar_t *uni) } static inline int -fat_short2lower_uni(struct nls_table *t, unsigned char *c, int clen, wchar_t *uni) +fat_short2lower_uni(struct nls_table *t, unsigned char *c, + int clen, wchar_t *uni) { int charlen; wchar_t wc; @@ -220,7 +223,8 @@ fat_short2lower_uni(struct nls_table *t, unsigned char *c, int clen, wchar_t *un if (!nc) nc = *c; - if ( (charlen = t->char2uni(&nc, 1, uni)) < 0) { + charlen = t->char2uni(&nc, 1, uni); + if (charlen < 0) { *uni = 0x003f; /* a question mark */ charlen = 1; } @@ -537,7 +541,6 @@ end_of_dir: return err; } - EXPORT_SYMBOL_GPL(fat_search_long); struct fat_ioctl_filldir_callback { @@ -574,7 +577,8 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent, /* Fake . and .. for the root directory. */ if (inode->i_ino == MSDOS_ROOT_INO) { while (cpos < 2) { - if (filldir(dirent, "..", cpos+1, cpos, MSDOS_ROOT_INO, DT_DIR) < 0) + if (filldir(dirent, "..", cpos+1, cpos, + MSDOS_ROOT_INO, DT_DIR) < 0) goto out; cpos++; filp->f_pos++; @@ -872,25 +876,26 @@ static int fat_get_short_entry(struct inode *dir, loff_t *pos, } /* - * The ".." entry can not provide the "struct fat_slot_info" informations - * for inode. So, this function provide the some informations only. + * The ".." entry can not provide the "struct fat_slot_info" information + * for inode, nor a usable i_pos. So, this function provides some information + * only. + * + * Since this function walks through the on-disk inodes within a directory, + * callers are responsible for taking any locks necessary to prevent the + * directory from changing. */ int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh, - struct msdos_dir_entry **de, loff_t *i_pos) + struct msdos_dir_entry **de) { - loff_t offset; + loff_t offset = 0; - offset = 0; - *bh = NULL; + *de = NULL; while (fat_get_short_entry(dir, &offset, bh, de) >= 0) { - if (!strncmp((*de)->name, MSDOS_DOTDOT, MSDOS_NAME)) { - *i_pos = fat_make_i_pos(dir->i_sb, *bh, *de); + if (!strncmp((*de)->name, MSDOS_DOTDOT, MSDOS_NAME)) return 0; - } } return -ENOENT; } - EXPORT_SYMBOL_GPL(fat_get_dotdot_entry); /* See if directory is empty */ @@ -913,7 +918,6 @@ int fat_dir_empty(struct inode *dir) brelse(bh); return result; } - EXPORT_SYMBOL_GPL(fat_dir_empty); /* @@ -959,7 +963,6 @@ int fat_scan(struct inode *dir, const unsigned char *name, } return -ENOENT; } - EXPORT_SYMBOL_GPL(fat_scan); static int __fat_remove_entries(struct inode *dir, loff_t pos, int nr_slots) @@ -1047,7 +1050,6 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo) return 0; } - EXPORT_SYMBOL_GPL(fat_remove_entries); static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used, @@ -1141,10 +1143,8 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) de[0].ctime_cs = de[1].ctime_cs = 0; de[0].adate = de[0].cdate = de[1].adate = de[1].cdate = 0; } - de[0].start = cpu_to_le16(cluster); - de[0].starthi = cpu_to_le16(cluster >> 16); - de[1].start = cpu_to_le16(MSDOS_I(dir)->i_logstart); - de[1].starthi = cpu_to_le16(MSDOS_I(dir)->i_logstart >> 16); + fat_set_start(&de[0], cluster); + fat_set_start(&de[1], MSDOS_I(dir)->i_logstart); de[0].size = de[1].size = 0; memset(de + 2, 0, sb->s_blocksize - 2 * sizeof(*de)); set_buffer_uptodate(bhs[0]); @@ -1161,7 +1161,6 @@ error_free: error: return err; } - EXPORT_SYMBOL_GPL(fat_alloc_new_dir); static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots, @@ -1377,5 +1376,4 @@ error_remove: __fat_remove_entries(dir, pos, free_slots); return err; } - EXPORT_SYMBOL_GPL(fat_add_entries); diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 7d8e0dcac5d..ca7e8f8bad7 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -5,6 +5,7 @@ #include <linux/string.h> #include <linux/nls.h> #include <linux/fs.h> +#include <linux/hash.h> #include <linux/mutex.h> #include <linux/ratelimit.h> #include <linux/msdos_fs.h> @@ -27,26 +28,27 @@ struct fat_mount_options { kgid_t fs_gid; unsigned short fs_fmask; unsigned short fs_dmask; - unsigned short codepage; /* Codepage for shortname conversions */ - char *iocharset; /* Charset used for filename input/display */ - unsigned short shortname; /* flags for shortname display/create rule */ - unsigned char name_check; /* r = relaxed, n = normal, s = strict */ - unsigned char errors; /* On error: continue, panic, remount-ro */ + unsigned short codepage; /* Codepage for shortname conversions */ + char *iocharset; /* Charset used for filename input/display */ + unsigned short shortname; /* flags for shortname display/create rule */ + unsigned char name_check; /* r = relaxed, n = normal, s = strict */ + unsigned char errors; /* On error: continue, panic, remount-ro */ unsigned short allow_utime;/* permission for setting the [am]time */ - unsigned quiet:1, /* set = fake successful chmods and chowns */ - showexec:1, /* set = only set x bit for com/exe/bat */ - sys_immutable:1, /* set = system files are immutable */ - dotsOK:1, /* set = hidden and system files are named '.filename' */ - isvfat:1, /* 0=no vfat long filename support, 1=vfat support */ - utf8:1, /* Use of UTF-8 character set (Default) */ - unicode_xlate:1, /* create escape sequences for unhandled Unicode */ - numtail:1, /* Does first alias have a numeric '~1' type tail? */ - flush:1, /* write things quickly */ - nocase:1, /* Does this need case conversion? 0=need case conversion*/ - usefree:1, /* Use free_clusters for FAT32 */ - tz_utc:1, /* Filesystem timestamps are in UTC */ - rodir:1, /* allow ATTR_RO for directory */ - discard:1; /* Issue discard requests on deletions */ + unsigned quiet:1, /* set = fake successful chmods and chowns */ + showexec:1, /* set = only set x bit for com/exe/bat */ + sys_immutable:1, /* set = system files are immutable */ + dotsOK:1, /* set = hidden and system files are named '.filename' */ + isvfat:1, /* 0=no vfat long filename support, 1=vfat support */ + utf8:1, /* Use of UTF-8 character set (Default) */ + unicode_xlate:1, /* create escape sequences for unhandled Unicode */ + numtail:1, /* Does first alias have a numeric '~1' type tail? */ + flush:1, /* write things quickly */ + nocase:1, /* Does this need case conversion? 0=need case conversion*/ + usefree:1, /* Use free_clusters for FAT32 */ + tz_utc:1, /* Filesystem timestamps are in UTC */ + rodir:1, /* allow ATTR_RO for directory */ + discard:1, /* Issue discard requests on deletions */ + nfs:1; /* Do extra work needed for NFS export */ }; #define FAT_HASH_BITS 8 @@ -56,28 +58,28 @@ struct fat_mount_options { * MS-DOS file system in-core superblock data */ struct msdos_sb_info { - unsigned short sec_per_clus; /* sectors/cluster */ - unsigned short cluster_bits; /* log2(cluster_size) */ - unsigned int cluster_size; /* cluster size */ - unsigned char fats,fat_bits; /* number of FATs, FAT bits (12 or 16) */ + unsigned short sec_per_clus; /* sectors/cluster */ + unsigned short cluster_bits; /* log2(cluster_size) */ + unsigned int cluster_size; /* cluster size */ + unsigned char fats, fat_bits; /* number of FATs, FAT bits (12 or 16) */ unsigned short fat_start; - unsigned long fat_length; /* FAT start & length (sec.) */ + unsigned long fat_length; /* FAT start & length (sec.) */ unsigned long dir_start; - unsigned short dir_entries; /* root dir start & entries */ - unsigned long data_start; /* first data sector */ - unsigned long max_cluster; /* maximum cluster number */ - unsigned long root_cluster; /* first cluster of the root directory */ - unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */ + unsigned short dir_entries; /* root dir start & entries */ + unsigned long data_start; /* first data sector */ + unsigned long max_cluster; /* maximum cluster number */ + unsigned long root_cluster; /* first cluster of the root directory */ + unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */ struct mutex fat_lock; - unsigned int prev_free; /* previously allocated cluster number */ - unsigned int free_clusters; /* -1 if undefined */ + unsigned int prev_free; /* previously allocated cluster number */ + unsigned int free_clusters; /* -1 if undefined */ unsigned int free_clus_valid; /* is free_clusters valid? */ struct fat_mount_options options; - struct nls_table *nls_disk; /* Codepage used on disk */ - struct nls_table *nls_io; /* Charset used for input and display */ - const void *dir_ops; /* Opaque; default directory operations */ - int dir_per_block; /* dir entries per block */ - int dir_per_block_bits; /* log2(dir_per_block) */ + struct nls_table *nls_disk; /* Codepage used on disk */ + struct nls_table *nls_io; /* Charset used for input and display */ + const void *dir_ops; /* Opaque; default directory operations */ + int dir_per_block; /* dir entries per block */ + int dir_per_block_bits; /* log2(dir_per_block) */ int fatent_shift; struct fatent_operations *fatent_ops; @@ -88,6 +90,9 @@ struct msdos_sb_info { spinlock_t inode_hash_lock; struct hlist_head inode_hashtable[FAT_HASH_SIZE]; + + spinlock_t dir_hash_lock; + struct hlist_head dir_hashtable[FAT_HASH_SIZE]; }; #define FAT_CACHE_VALID 0 /* special case for valid cache */ @@ -110,6 +115,7 @@ struct msdos_inode_info { int i_attrs; /* unused attribute bits */ loff_t i_pos; /* on-disk position of directory entry or 0 */ struct hlist_node i_fat_hash; /* hash by i_location */ + struct hlist_node i_dir_hash; /* hash by i_logstart */ struct rw_semaphore truncate_lock; /* protect bmap against truncate */ struct inode vfs_inode; }; @@ -262,7 +268,7 @@ extern int fat_subdirs(struct inode *dir); extern int fat_scan(struct inode *dir, const unsigned char *name, struct fat_slot_info *sinfo); extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh, - struct msdos_dir_entry **de, loff_t *i_pos); + struct msdos_dir_entry **de); extern int fat_alloc_new_dir(struct inode *dir, struct timespec *ts); extern int fat_add_entries(struct inode *dir, void *slots, int nr_slots, struct fat_slot_info *sinfo); @@ -322,7 +328,7 @@ extern long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); extern const struct file_operations fat_file_operations; extern const struct inode_operations fat_file_inode_operations; -extern int fat_setattr(struct dentry * dentry, struct iattr * attr); +extern int fat_setattr(struct dentry *dentry, struct iattr *attr); extern void fat_truncate_blocks(struct inode *inode, loff_t offset); extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); @@ -340,7 +346,12 @@ extern int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, void (*setup)(struct super_block *)); extern int fat_flush_inodes(struct super_block *sb, struct inode *i1, - struct inode *i2); + struct inode *i2); +static inline unsigned long fat_dir_hash(int logstart) +{ + return hash_32(logstart, FAT_HASH_BITS); +} + /* fat/misc.c */ extern __printf(3, 4) __cold void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...); @@ -366,6 +377,14 @@ extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs); int fat_cache_init(void); void fat_cache_destroy(void); +/* fat/nfs.c */ +struct fid; +extern struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); +extern struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type); +extern struct dentry *fat_get_parent(struct dentry *child_dir); + /* helper for printk */ typedef unsigned long long llu; diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 31f08ab62c5..260705c5806 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -186,9 +186,6 @@ static void fat16_ent_put(struct fat_entry *fatent, int new) static void fat32_ent_put(struct fat_entry *fatent, int new) { - if (new == FAT_ENT_EOF) - new = EOF_FAT32; - WARN_ON(new & 0xf0000000); new |= le32_to_cpu(*fatent->u.ent32_p) & ~0x0fffffff; *fatent->u.ent32_p = cpu_to_le32(new); @@ -203,15 +200,18 @@ static int fat12_ent_next(struct fat_entry *fatent) fatent->entry++; if (fatent->nr_bhs == 1) { - WARN_ON(ent12_p[0] > (u8 *)(bhs[0]->b_data + (bhs[0]->b_size - 2))); - WARN_ON(ent12_p[1] > (u8 *)(bhs[0]->b_data + (bhs[0]->b_size - 1))); + WARN_ON(ent12_p[0] > (u8 *)(bhs[0]->b_data + + (bhs[0]->b_size - 2))); + WARN_ON(ent12_p[1] > (u8 *)(bhs[0]->b_data + + (bhs[0]->b_size - 1))); if (nextp < (u8 *)(bhs[0]->b_data + (bhs[0]->b_size - 1))) { ent12_p[0] = nextp - 1; ent12_p[1] = nextp; return 1; } } else { - WARN_ON(ent12_p[0] != (u8 *)(bhs[0]->b_data + (bhs[0]->b_size - 1))); + WARN_ON(ent12_p[0] != (u8 *)(bhs[0]->b_data + + (bhs[0]->b_size - 1))); WARN_ON(ent12_p[1] != (u8 *)bhs[1]->b_data); ent12_p[0] = nextp - 1; ent12_p[1] = nextp; @@ -631,7 +631,6 @@ error: return err; } - EXPORT_SYMBOL_GPL(fat_free_clusters); /* 128kb is the whole sectors for FAT12 and FAT16 */ diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 4e5a6ac54eb..76f60c642c0 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -281,15 +281,42 @@ static inline unsigned long fat_hash(loff_t i_pos) return hash_32(i_pos, FAT_HASH_BITS); } +static void dir_hash_init(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int i; + + spin_lock_init(&sbi->dir_hash_lock); + for (i = 0; i < FAT_HASH_SIZE; i++) + INIT_HLIST_HEAD(&sbi->dir_hashtable[i]); +} + void fat_attach(struct inode *inode, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); - struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); - spin_lock(&sbi->inode_hash_lock); - MSDOS_I(inode)->i_pos = i_pos; - hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head); - spin_unlock(&sbi->inode_hash_lock); + if (inode->i_ino != MSDOS_ROOT_INO) { + struct hlist_head *head = sbi->inode_hashtable + + fat_hash(i_pos); + + spin_lock(&sbi->inode_hash_lock); + MSDOS_I(inode)->i_pos = i_pos; + hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head); + spin_unlock(&sbi->inode_hash_lock); + } + + /* If NFS support is enabled, cache the mapping of start cluster + * to directory inode. This is used during reconnection of + * dentries to the filesystem root. + */ + if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { + struct hlist_head *d_head = sbi->dir_hashtable; + d_head += fat_dir_hash(MSDOS_I(inode)->i_logstart); + + spin_lock(&sbi->dir_hash_lock); + hlist_add_head(&MSDOS_I(inode)->i_dir_hash, d_head); + spin_unlock(&sbi->dir_hash_lock); + } } EXPORT_SYMBOL_GPL(fat_attach); @@ -300,6 +327,12 @@ void fat_detach(struct inode *inode) MSDOS_I(inode)->i_pos = 0; hlist_del_init(&MSDOS_I(inode)->i_fat_hash); spin_unlock(&sbi->inode_hash_lock); + + if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { + spin_lock(&sbi->dir_hash_lock); + hlist_del_init(&MSDOS_I(inode)->i_dir_hash); + spin_unlock(&sbi->dir_hash_lock); + } } EXPORT_SYMBOL_GPL(fat_detach); @@ -504,6 +537,7 @@ static void init_once(void *foo) ei->cache_valid_id = FAT_CACHE_VALID + 1; INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_fat_hash); + INIT_HLIST_NODE(&ei->i_dir_hash); inode_init_once(&ei->vfs_inode); } @@ -668,125 +702,9 @@ static const struct super_operations fat_sops = { .show_options = fat_show_options, }; -/* - * a FAT file handle with fhtype 3 is - * 0/ i_ino - for fast, reliable lookup if still in the cache - * 1/ i_generation - to see if i_ino is still valid - * bit 0 == 0 iff directory - * 2/ i_pos(8-39) - if ino has changed, but still in cache - * 3/ i_pos(4-7)|i_logstart - to semi-verify inode found at i_pos - * 4/ i_pos(0-3)|parent->i_logstart - maybe used to hunt for the file on disc - * - * Hack for NFSv2: Maximum FAT entry number is 28bits and maximum - * i_pos is 40bits (blocknr(32) + dir offset(8)), so two 4bits - * of i_logstart is used to store the directory entry offset. - */ - -static struct dentry *fat_fh_to_dentry(struct super_block *sb, - struct fid *fid, int fh_len, int fh_type) -{ - struct inode *inode = NULL; - u32 *fh = fid->raw; - - if (fh_len < 5 || fh_type != 3) - return NULL; - - inode = ilookup(sb, fh[0]); - if (!inode || inode->i_generation != fh[1]) { - if (inode) - iput(inode); - inode = NULL; - } - if (!inode) { - loff_t i_pos; - int i_logstart = fh[3] & 0x0fffffff; - - i_pos = (loff_t)fh[2] << 8; - i_pos |= ((fh[3] >> 24) & 0xf0) | (fh[4] >> 28); - - /* try 2 - see if i_pos is in F-d-c - * require i_logstart to be the same - * Will fail if you truncate and then re-write - */ - - inode = fat_iget(sb, i_pos); - if (inode && MSDOS_I(inode)->i_logstart != i_logstart) { - iput(inode); - inode = NULL; - } - } - - /* - * For now, do nothing if the inode is not found. - * - * What we could do is: - * - * - follow the file starting at fh[4], and record the ".." entry, - * and the name of the fh[2] entry. - * - then follow the ".." file finding the next step up. - * - * This way we build a path to the root of the tree. If this works, we - * lookup the path and so get this inode into the cache. Finally try - * the fat_iget lookup again. If that fails, then we are totally out - * of luck. But all that is for another day - */ - return d_obtain_alias(inode); -} - -static int -fat_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent) -{ - int len = *lenp; - struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); - loff_t i_pos; - - if (len < 5) { - *lenp = 5; - return 255; /* no room */ - } - - i_pos = fat_i_pos_read(sbi, inode); - *lenp = 5; - fh[0] = inode->i_ino; - fh[1] = inode->i_generation; - fh[2] = i_pos >> 8; - fh[3] = ((i_pos & 0xf0) << 24) | MSDOS_I(inode)->i_logstart; - fh[4] = (i_pos & 0x0f) << 28; - if (parent) - fh[4] |= MSDOS_I(parent)->i_logstart; - return 3; -} - -static struct dentry *fat_get_parent(struct dentry *child) -{ - struct super_block *sb = child->d_sb; - struct buffer_head *bh; - struct msdos_dir_entry *de; - loff_t i_pos; - struct dentry *parent; - struct inode *inode; - int err; - - lock_super(sb); - - err = fat_get_dotdot_entry(child->d_inode, &bh, &de, &i_pos); - if (err) { - parent = ERR_PTR(err); - goto out; - } - inode = fat_build_inode(sb, de, i_pos); - brelse(bh); - - parent = d_obtain_alias(inode); -out: - unlock_super(sb); - - return parent; -} - static const struct export_operations fat_export_ops = { - .encode_fh = fat_encode_fh, .fh_to_dentry = fat_fh_to_dentry, + .fh_to_parent = fat_fh_to_parent, .get_parent = fat_get_parent, }; @@ -836,6 +754,8 @@ static int fat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",usefree"); if (opts->quiet) seq_puts(m, ",quiet"); + if (opts->nfs) + seq_puts(m, ",nfs"); if (opts->showexec) seq_puts(m, ",showexec"); if (opts->sys_immutable) @@ -880,7 +800,7 @@ enum { Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes, Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes, Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont, - Opt_err_panic, Opt_err_ro, Opt_discard, Opt_err, + Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_err, }; static const match_table_t fat_tokens = { @@ -909,6 +829,7 @@ static const match_table_t fat_tokens = { {Opt_err_panic, "errors=panic"}, {Opt_err_ro, "errors=remount-ro"}, {Opt_discard, "discard"}, + {Opt_nfs, "nfs"}, {Opt_obsolete, "conv=binary"}, {Opt_obsolete, "conv=text"}, {Opt_obsolete, "conv=auto"}, @@ -989,6 +910,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, opts->numtail = 1; opts->usefree = opts->nocase = 0; opts->tz_utc = 0; + opts->nfs = 0; opts->errors = FAT_ERRORS_RO; *debug = 0; @@ -1153,6 +1075,9 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, case Opt_discard: opts->discard = 1; break; + case Opt_nfs: + opts->nfs = 1; + break; /* obsolete mount options */ case Opt_obsolete: @@ -1443,6 +1368,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, /* set up enough so that it can read an inode */ fat_hash_init(sb); + dir_hash_init(sb); fat_ent_access_init(sb); /* @@ -1497,6 +1423,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, } error = -ENOMEM; insert_inode_hash(root_inode); + fat_attach(root_inode, 0); sb->s_root = d_make_root(root_inode); if (!sb->s_root) { fat_msg(sb, KERN_ERR, "get root inode failed"); @@ -1536,18 +1463,14 @@ static int writeback_inode(struct inode *inode) { int ret; - struct address_space *mapping = inode->i_mapping; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - .nr_to_write = 0, - }; - /* if we used WB_SYNC_ALL, sync_inode waits for the io for the - * inode to finish. So WB_SYNC_NONE is sent down to sync_inode + + /* if we used wait=1, sync_inode_metadata waits for the io for the + * inode to finish. So wait=0 is sent down to sync_inode_metadata * and filemap_fdatawrite is used for the data blocks */ - ret = sync_inode(inode, &wbc); + ret = sync_inode_metadata(inode, 0); if (!ret) - ret = filemap_fdatawrite(mapping); + ret = filemap_fdatawrite(inode->i_mapping); return ret; } diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index b0e12bf9f4a..c1055e778ff 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -407,7 +407,7 @@ out: static int msdos_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = dentry->d_inode; - struct super_block *sb= inode->i_sb; + struct super_block *sb = inode->i_sb; struct fat_slot_info sinfo; int err; @@ -440,7 +440,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, struct inode *old_inode, *new_inode; struct fat_slot_info old_sinfo, sinfo; struct timespec ts; - loff_t dotdot_i_pos, new_i_pos; + loff_t new_i_pos; int err, old_attrs, is_dir, update_dotdot, corrupt = 0; old_sinfo.bh = sinfo.bh = dotdot_bh = NULL; @@ -456,8 +456,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, is_dir = S_ISDIR(old_inode->i_mode); update_dotdot = (is_dir && old_dir != new_dir); if (update_dotdot) { - if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de, - &dotdot_i_pos) < 0) { + if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de)) { err = -EIO; goto out; } diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 6a6d8c0715a..e535dd75b98 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -914,7 +914,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *old_inode, *new_inode; struct fat_slot_info old_sinfo, sinfo; struct timespec ts; - loff_t dotdot_i_pos, new_i_pos; + loff_t new_i_pos; int err, is_dir, update_dotdot, corrupt = 0; struct super_block *sb = old_dir->i_sb; @@ -929,8 +929,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, is_dir = S_ISDIR(old_inode->i_mode); update_dotdot = (is_dir && old_dir != new_dir); if (update_dotdot) { - if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de, - &dotdot_i_pos) < 0) { + if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de)) { err = -EIO; goto out; } diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c new file mode 100644 index 00000000000..ef4b5faba87 --- /dev/null +++ b/fs/fat/nfs.c @@ -0,0 +1,101 @@ +/* fs/fat/nfs.c + * + * 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/exportfs.h> +#include "fat.h" + +/** + * Look up a directory inode given its starting cluster. + */ +static struct inode *fat_dget(struct super_block *sb, int i_logstart) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct hlist_head *head; + struct hlist_node *_p; + struct msdos_inode_info *i; + struct inode *inode = NULL; + + head = sbi->dir_hashtable + fat_dir_hash(i_logstart); + spin_lock(&sbi->dir_hash_lock); + hlist_for_each_entry(i, _p, head, i_dir_hash) { + BUG_ON(i->vfs_inode.i_sb != sb); + if (i->i_logstart != i_logstart) + continue; + inode = igrab(&i->vfs_inode); + if (inode) + break; + } + spin_unlock(&sbi->dir_hash_lock); + return inode; +} + +static struct inode *fat_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation) +{ + struct inode *inode; + + if ((ino < MSDOS_ROOT_INO) || (ino == MSDOS_FSINFO_INO)) + return NULL; + + inode = ilookup(sb, ino); + if (inode && generation && (inode->i_generation != generation)) { + iput(inode); + inode = NULL; + } + + return inode; +} + +/** + * Map a NFS file handle to a corresponding dentry. + * The dentry may or may not be connected to the filesystem root. + */ +struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + fat_nfs_get_inode); +} + +/* + * Find the parent for a file specified by NFS handle. + * This requires that the handle contain the i_ino of the parent. + */ +struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + fat_nfs_get_inode); +} + +/* + * Find the parent for a directory that is not currently connected to + * the filesystem root. + * + * On entry, the caller holds child_dir->d_inode->i_mutex. + */ +struct dentry *fat_get_parent(struct dentry *child_dir) +{ + struct super_block *sb = child_dir->d_sb; + struct buffer_head *bh = NULL; + struct msdos_dir_entry *de; + struct inode *parent_inode = NULL; + + if (!fat_get_dotdot_entry(child_dir->d_inode, &bh, &de)) { + int parent_logstart = fat_get_start(MSDOS_SB(sb), de); + parent_inode = fat_dget(sb, parent_logstart); + } + brelse(bh); + + return d_obtain_alias(parent_inode); +} diff --git a/fs/hpfs/anode.c b/fs/hpfs/anode.c index 4bae4a4a60b..2d5b254ad9e 100644 --- a/fs/hpfs/anode.c +++ b/fs/hpfs/anode.c @@ -102,7 +102,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi return -1; } if (hpfs_alloc_if_possible(s, se = le32_to_cpu(btree->u.external[n].disk_secno) + le32_to_cpu(btree->u.external[n].length))) { - btree->u.external[n].length = cpu_to_le32(le32_to_cpu(btree->u.external[n].length) + 1); + le32_add_cpu(&btree->u.external[n].length, 1); mark_buffer_dirty(bh); brelse(bh); return se; @@ -153,7 +153,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi btree = &anode->btree; } btree->n_free_nodes--; n = btree->n_used_nodes++; - btree->first_free = cpu_to_le16(le16_to_cpu(btree->first_free) + 12); + le16_add_cpu(&btree->first_free, 12); btree->u.external[n].disk_secno = cpu_to_le32(se); btree->u.external[n].file_secno = cpu_to_le32(fs); btree->u.external[n].length = cpu_to_le32(1); @@ -174,7 +174,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi } if (btree->n_free_nodes) { btree->n_free_nodes--; n = btree->n_used_nodes++; - btree->first_free = cpu_to_le16(le16_to_cpu(btree->first_free) + 8); + le16_add_cpu(&btree->first_free, 8); btree->u.internal[n].file_secno = cpu_to_le32(-1); btree->u.internal[n].down = cpu_to_le32(na); btree->u.internal[n-1].file_secno = cpu_to_le32(fs); diff --git a/fs/hpfs/dnode.c b/fs/hpfs/dnode.c index 3228c524ebe..4364b2a02c5 100644 --- a/fs/hpfs/dnode.c +++ b/fs/hpfs/dnode.c @@ -145,10 +145,10 @@ static void set_last_pointer(struct super_block *s, struct dnode *d, dnode_secno } } if (ptr) { - d->first_free = cpu_to_le32(le32_to_cpu(d->first_free) + 4); + le32_add_cpu(&d->first_free, 4); if (le32_to_cpu(d->first_free) > 2048) { hpfs_error(s, "set_last_pointer: too long dnode %08x", le32_to_cpu(d->self)); - d->first_free = cpu_to_le32(le32_to_cpu(d->first_free) - 4); + le32_add_cpu(&d->first_free, -4); return; } de->length = cpu_to_le16(36); @@ -184,7 +184,7 @@ struct hpfs_dirent *hpfs_add_de(struct super_block *s, struct dnode *d, de->not_8x3 = hpfs_is_name_long(name, namelen); de->namelen = namelen; memcpy(de->name, name, namelen); - d->first_free = cpu_to_le32(le32_to_cpu(d->first_free) + d_size); + le32_add_cpu(&d->first_free, d_size); return de; } @@ -314,7 +314,7 @@ static int hpfs_add_to_dnode(struct inode *i, dnode_secno dno, set_last_pointer(i->i_sb, ad, de->down ? de_down_pointer(de) : 0); de = de_next_de(de); memmove((char *)nd + 20, de, le32_to_cpu(nd->first_free) + (char *)nd - (char *)de); - nd->first_free = cpu_to_le32(le32_to_cpu(nd->first_free) - ((char *)de - (char *)nd - 20)); + le32_add_cpu(&nd->first_free, -((char *)de - (char *)nd - 20)); memcpy(d, nd, le32_to_cpu(nd->first_free)); for_all_poss(i, hpfs_pos_del, (loff_t)dno << 4, pos); fix_up_ptrs(i->i_sb, ad); @@ -474,8 +474,8 @@ static secno move_to_top(struct inode *i, dnode_secno from, dnode_secno to) hpfs_brelse4(&qbh); return 0; } - dnode->first_free = cpu_to_le32(le32_to_cpu(dnode->first_free) - 4); - de->length = cpu_to_le16(le16_to_cpu(de->length) - 4); + le32_add_cpu(&dnode->first_free, -4); + le16_add_cpu(&de->length, -4); de->down = 0; hpfs_mark_4buffers_dirty(&qbh); dno = up; @@ -570,8 +570,8 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno) for_all_poss(i, hpfs_pos_subst, ((loff_t)dno << 4) | 1, ((loff_t)up << 4) | p); if (!down) { de->down = 0; - de->length = cpu_to_le16(le16_to_cpu(de->length) - 4); - dnode->first_free = cpu_to_le32(le32_to_cpu(dnode->first_free) - 4); + le16_add_cpu(&de->length, -4); + le32_add_cpu(&dnode->first_free, -4); memmove(de_next_de(de), (char *)de_next_de(de) + 4, (char *)dnode + le32_to_cpu(dnode->first_free) - (char *)de_next_de(de)); } else { @@ -647,14 +647,14 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno) printk("HPFS: warning: unbalanced dnode tree, see hpfs.txt 4 more info\n"); printk("HPFS: warning: goin'on\n"); } - del->length = cpu_to_le16(le16_to_cpu(del->length) + 4); + le16_add_cpu(&del->length, 4); del->down = 1; - d1->first_free = cpu_to_le32(le32_to_cpu(d1->first_free) + 4); + le32_add_cpu(&d1->first_free, 4); } if (dlp && !down) { - del->length = cpu_to_le16(le16_to_cpu(del->length) - 4); + le16_add_cpu(&del->length, -4); del->down = 0; - d1->first_free = cpu_to_le32(le32_to_cpu(d1->first_free) - 4); + le32_add_cpu(&d1->first_free, -4); } else if (down) *(__le32 *) ((void *) del + le16_to_cpu(del->length) - 4) = cpu_to_le32(down); } else goto endm; @@ -668,9 +668,9 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno) memcpy(de_cp, de_prev, le16_to_cpu(de_prev->length)); hpfs_delete_de(i->i_sb, dnode, de_prev); if (!de_prev->down) { - de_prev->length = cpu_to_le16(le16_to_cpu(de_prev->length) + 4); + le16_add_cpu(&de_prev->length, 4); de_prev->down = 1; - dnode->first_free = cpu_to_le32(le32_to_cpu(dnode->first_free) + 4); + le32_add_cpu(&dnode->first_free, 4); } *(__le32 *) ((void *) de_prev + le16_to_cpu(de_prev->length) - 4) = cpu_to_le32(ndown); hpfs_mark_4buffers_dirty(&qbh); diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 2c6d95257a4..77e3cb2962b 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -146,8 +146,7 @@ static int omfs_grow_extent(struct inode *inode, struct omfs_extent *oe, be64_to_cpu(entry->e_blocks); if (omfs_allocate_block(inode->i_sb, new_block)) { - entry->e_blocks = - cpu_to_be64(be64_to_cpu(entry->e_blocks) + 1); + be64_add_cpu(&entry->e_blocks, 1); terminator->e_blocks = ~(cpu_to_be64( be64_to_cpu(~terminator->e_blocks) + 1)); goto out; @@ -177,7 +176,7 @@ static int omfs_grow_extent(struct inode *inode, struct omfs_extent *oe, be64_to_cpu(~terminator->e_blocks) + (u64) new_count)); /* write in new entry */ - oe->e_extent_count = cpu_to_be32(1 + be32_to_cpu(oe->e_extent_count)); + be32_add_cpu(&oe->e_extent_count, 1); out: *ret_block = new_block; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index b3647fe6a60..0d80cef4cfb 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -427,7 +427,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, if (!memcmp(dentry->d_name.name, de->name, de->namelen)) { pde_get(de); spin_unlock(&proc_subdir_lock); - error = -EINVAL; + error = -ENOMEM; inode = proc_get_inode(dir->i_sb, de); goto out_unlock; } @@ -605,7 +605,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, unsigned int len; /* make sure name is valid */ - if (!name || !strlen(name)) goto out; + if (!name || !strlen(name)) + goto out; if (xlate_proc_name(name, parent, &fn) != 0) goto out; @@ -616,20 +617,18 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, len = strlen(fn); - ent = kmalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL); - if (!ent) goto out; + ent = kzalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL); + if (!ent) + goto out; - memset(ent, 0, sizeof(struct proc_dir_entry)); memcpy(ent->name, fn, len + 1); ent->namelen = len; ent->mode = mode; ent->nlink = nlink; atomic_set(&ent->count, 1); - ent->pde_users = 0; spin_lock_init(&ent->pde_unload_lock); - ent->pde_unload_completion = NULL; INIT_LIST_HEAD(&ent->pde_openers); - out: +out: return ent; } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 7ac817b64a7..3b22bbdee9e 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -450,7 +450,6 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) return NULL; if (inode->i_state & I_NEW) { inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - PROC_I(inode)->fd = 0; PROC_I(inode)->pde = de; if (de->mode) { diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 67925a7bd8c..cceaab07ad5 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -103,7 +103,7 @@ static inline int task_dumpable(struct task_struct *task) if (mm) dumpable = get_dumpable(mm); task_unlock(task); - if(dumpable == 1) + if (dumpable == SUID_DUMPABLE_ENABLED) return 1; return 0; } diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index eb7cc91b725..dcd56f84db7 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -266,8 +266,7 @@ void sysctl_head_put(struct ctl_table_header *head) static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) { - if (!head) - BUG(); + BUG_ON(!head); spin_lock(&sysctl_lock); if (!use_table(head)) head = ERR_PTR(-ENOENT); diff --git a/fs/proc/root.c b/fs/proc/root.c index 9a2d9fd7cad..9889a92d2e0 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -61,7 +61,7 @@ static int proc_parse_options(char *options, struct pid_namespace *pid) if (!*p) continue; - args[0].to = args[0].from = 0; + args[0].to = args[0].from = NULL; token = match_token(p, tokens, args); switch (token) { case Opt_gid: diff --git a/fs/super.c b/fs/super.c index 5fdf7ff32c4..a3bc935069d 100644 --- a/fs/super.c +++ b/fs/super.c @@ -865,7 +865,7 @@ int get_anon_bdev(dev_t *p) else if (error) return -EAGAIN; - if ((dev & MAX_ID_MASK) == (1 << MINORBITS)) { + if ((dev & MAX_IDR_MASK) == (1 << MINORBITS)) { spin_lock(&unnamed_dev_lock); ida_remove(&unnamed_dev_ida, dev); if (unnamed_dev_start > dev) |