diff options
389 files changed, 6253 insertions, 4307 deletions
diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 3a863f692728..88ab81c79109 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -140,7 +140,7 @@ file. struct dentry *parent, struct debugfs_regset32 *regset); - int debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs, + void debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix); The "base" argument may be 0, but you may want to build the reg32 array diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index 2cca5a25ef89..e0950c483c22 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -122,6 +122,10 @@ disable_ext_identify Disable the extension list configured by mkfs, so f2fs inline_xattr Enable the inline xattrs feature. inline_data Enable the inline data feature: New created small(<~3.4k) files can be written into inode block. +inline_dentry Enable the inline dir feature: data in new created + directory entries can be written into inode block. The + space of inode block which is used to store inline + dentries is limited to ~3.4k. flush_merge Merge concurrent cache_flush commands as much as possible to eliminate redundant command issues. If the underlying device handles the cache_flush command relatively slowly, @@ -131,6 +135,9 @@ nobarrier This option can be used if underlying storage guarantees If this option is set, no cache_flush commands are issued but f2fs still guarantees the write ordering of all the data writes. +fastboot This option is used when a system wants to reduce mount + time as much as possible, even though normal performance + can be sacrificed. ================================================================================ DEBUGFS ENTRIES diff --git a/Documentation/filesystems/nfs/Exporting b/Documentation/filesystems/nfs/Exporting index c8f036a9b13f..520a4becb75c 100644 --- a/Documentation/filesystems/nfs/Exporting +++ b/Documentation/filesystems/nfs/Exporting @@ -72,24 +72,11 @@ c/ Helper routines to allocate anonymous dentries, and to help attach DCACHE_DISCONNECTED) dentry is allocated and attached. In the case of a directory, care is taken that only one dentry can ever be attached. - d_splice_alias(inode, dentry) or d_materialise_unique(dentry, inode) - will introduce a new dentry into the tree; either the passed-in - dentry or a preexisting alias for the given inode (such as an - anonymous one created by d_obtain_alias), if appropriate. The two - functions differ in their handling of directories with preexisting - aliases: - d_splice_alias will use any existing IS_ROOT dentry, but it will - return -EIO rather than try to move a dentry with a different - parent. This is appropriate for local filesystems, which - should never see such an alias unless the filesystem is - corrupted somehow (for example, if two on-disk directory - entries refer to the same directory.) - d_materialise_unique will attempt to move any dentry. This is - appropriate for distributed filesystems, where finding a - directory other than where we last cached it may be a normal - consequence of concurrent operations on other hosts. - Both functions return NULL when the passed-in dentry is used, - following the calling convention of ->lookup. + d_splice_alias(inode, dentry) will introduce a new dentry into the tree; + either the passed-in dentry or a preexisting alias for the given inode + (such as an anonymous one created by d_obtain_alias), if appropriate. + It returns NULL when the passed-in dentry is used, following the calling + convention of ->lookup. Filesystem Issues diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 0f3a1390bf00..fa2db081505e 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -463,3 +463,11 @@ in your dentry operations instead. of the in-tree instances did). inode_hash_lock is still held, of course, so they are still serialized wrt removal from inode hash, as well as wrt set() callback of iget5_locked(). +-- +[mandatory] + d_materialise_unique() is gone; d_splice_alias() does everything you + need now. Remember that they have opposite orders of arguments ;-/ +-- +[mandatory] + f_dentry is gone; use f_path.dentry, or, better yet, see if you can avoid + it entirely. diff --git a/Documentation/filesystems/seq_file.txt b/Documentation/filesystems/seq_file.txt index 8ea3e90ace07..b797ed38de46 100644 --- a/Documentation/filesystems/seq_file.txt +++ b/Documentation/filesystems/seq_file.txt @@ -180,23 +180,19 @@ output must be passed to the seq_file code. Some utility functions have been defined which make this task easy. Most code will simply use seq_printf(), which works pretty much like -printk(), but which requires the seq_file pointer as an argument. It is -common to ignore the return value from seq_printf(), but a function -producing complicated output may want to check that value and quit if -something non-zero is returned; an error return means that the seq_file -buffer has been filled and further output will be discarded. +printk(), but which requires the seq_file pointer as an argument. For straight character output, the following functions may be used: - int seq_putc(struct seq_file *m, char c); - int seq_puts(struct seq_file *m, const char *s); - int seq_escape(struct seq_file *m, const char *s, const char *esc); + seq_putc(struct seq_file *m, char c); + seq_puts(struct seq_file *m, const char *s); + seq_escape(struct seq_file *m, const char *s, const char *esc); The first two output a single character and a string, just like one would expect. seq_escape() is like seq_puts(), except that any character in s which is in the string esc will be represented in octal form in the output. -There is also a pair of functions for printing filenames: +There are also a pair of functions for printing filenames: int seq_path(struct seq_file *m, struct path *path, char *esc); int seq_path_root(struct seq_file *m, struct path *path, @@ -209,6 +205,14 @@ root is desired, it can be used with seq_path_root(). Note that, if it turns out that path cannot be reached from root, the value of root will be changed in seq_file_root() to a root which *does* work. +A function producing complicated output may want to check + bool seq_has_overflowed(struct seq_file *m); +and avoid further seq_<output> calls if true is returned. + +A true return from seq_has_overflowed means that the seq_file buffer will +be discarded and the seq_show function will attempt to allocate a larger +buffer and retry printing. + Making it all work diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 20bf204426ca..43ce0507ee25 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -835,7 +835,7 @@ struct file_operations { ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int); int (*setlease)(struct file *, long arg, struct file_lock **, void **); long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len); - int (*show_fdinfo)(struct seq_file *m, struct file *f); + void (*show_fdinfo)(struct seq_file *m, struct file *f); }; Again, all methods are called without any locks being held, unless diff --git a/MAINTAINERS b/MAINTAINERS index 4b79094bb051..079efaf1b5e7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2528,8 +2528,7 @@ M: Steve French <sfrench@samba.org> L: linux-cifs@vger.kernel.org L: samba-technical@lists.samba.org (moderated for non-subscribers) W: http://linux-cifs.samba.org/ -Q: http://patchwork.ozlabs.org/project/linux-cifs-client/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6.git +T: git git://git.samba.org/sfrench/cifs-2.6.git S: Supported F: Documentation/filesystems/cifs/ F: fs/cifs/ diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index f9c732e18284..e51f578636a5 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -104,11 +104,12 @@ struct osf_dirent_callback { }; static int -osf_filldir(void *__buf, const char *name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +osf_filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { struct osf_dirent __user *dirent; - struct osf_dirent_callback *buf = (struct osf_dirent_callback *) __buf; + struct osf_dirent_callback *buf = + container_of(ctx, struct osf_dirent_callback, ctx); unsigned int reclen = ALIGN(NAME_OFFSET + namlen + 1, sizeof(u32)); unsigned int d_ino; diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c index 2bedafea3d94..97a7bf8df348 100644 --- a/arch/parisc/hpux/fs.c +++ b/arch/parisc/hpux/fs.c @@ -56,11 +56,12 @@ struct getdents_callback { #define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de))) -static int filldir(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned d_type) +static int filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned d_type) { struct hpux_dirent __user * dirent; - struct getdents_callback * buf = (struct getdents_callback *) __buf; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); ino_t d_ino; int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 1, sizeof(long)); diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c index 28f1af2db1f5..1c27831df1ac 100644 --- a/arch/powerpc/oprofile/cell/spu_task_sync.c +++ b/arch/powerpc/oprofile/cell/spu_task_sync.c @@ -331,8 +331,7 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp, if (mm->exe_file) { app_cookie = fast_get_dcookie(&mm->exe_file->f_path); - pr_debug("got dcookie for %s\n", - mm->exe_file->f_dentry->d_name.name); + pr_debug("got dcookie for %pD\n", mm->exe_file); } for (vma = mm->mmap; vma; vma = vma->vm_next) { @@ -342,15 +341,14 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp, if (!vma->vm_file) goto fail_no_image_cookie; - pr_debug("Found spu ELF at %X(object-id:%lx) for file %s\n", - my_offset, spu_ref, - vma->vm_file->f_dentry->d_name.name); + pr_debug("Found spu ELF at %X(object-id:%lx) for file %pD\n", + my_offset, spu_ref, vma->vm_file); *offsetp = my_offset; break; } *spu_bin_dcookie = fast_get_dcookie(&vma->vm_file->f_path); - pr_debug("got dcookie for %s\n", vma->vm_file->f_dentry->d_name.name); + pr_debug("got dcookie for %pD\n", vma->vm_file); up_read(&mm->mmap_sem); diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 51effcec30d8..1a3429e1ccb5 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -164,7 +164,7 @@ static void spufs_prune_dir(struct dentry *dir) struct dentry *dentry, *tmp; mutex_lock(&dir->d_inode->i_mutex); - list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) { + list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { spin_lock(&dentry->d_lock); if (!(d_unhashed(dentry)) && dentry->d_inode) { dget_dlock(dentry); diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 2badf2bf9cd7..47fe1055c714 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -83,10 +83,9 @@ static ssize_t dbfs_read(struct file *file, char __user *buf, static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct hypfs_dbfs_file *df; + struct hypfs_dbfs_file *df = file_inode(file)->i_private; long rc; - df = file->f_path.dentry->d_inode->i_private; mutex_lock(&df->lock); if (df->unlocked_ioctl) rc = df->unlocked_ioctl(file, cmd, arg); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 666ac6651c17..bea3a0159496 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -992,6 +992,24 @@ config X86_ESPFIX64 def_bool y depends on X86_16BIT && X86_64 +config X86_VSYSCALL_EMULATION + bool "Enable vsyscall emulation" if EXPERT + default y + depends on X86_64 + ---help--- + This enables emulation of the legacy vsyscall page. Disabling + it is roughly equivalent to booting with vsyscall=none, except + that it will also disable the helpful warning if a program + tries to use a vsyscall. With this option set to N, offending + programs will just segfault, citing addresses of the form + 0xffffffffff600?00. + + This option is required by many programs built before 2013, and + care should be used even with newer programs if set to N. + + Disabling this option saves about 7K of kernel size and + possibly 4K of additional runtime pagetable memory. + config TOSHIBA tristate "Toshiba Laptop support" depends on X86_32 diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 45abc363dd3e..d999398928bc 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -3,6 +3,18 @@ # # create a compressed vmlinux image from the original vmlinux # +# vmlinuz is: +# decompression code (*.o) +# asm globals (piggy.S), including: +# vmlinux.bin.(gz|bz2|lzma|...) +# +# vmlinux.bin is: +# vmlinux stripped of debugging and comments +# vmlinux.bin.all is: +# vmlinux.bin + vmlinux.relocs +# vmlinux.bin.(gz|bz2|lzma|...) is: +# (see scripts/Makefile.lib size_append) +# compressed vmlinux.bin.all + u32 size of vmlinux.bin.all targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 @@ -35,7 +47,8 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/aslr.o $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone -vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o +vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \ + $(objtree)/drivers/firmware/efi/libstub/lib.a $(obj)/vmlinux: $(vmlinux-objs-y) FORCE $(call if_changed,ld) diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 1acf605a646d..92b9a5f2aed6 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -21,8 +21,10 @@ static efi_system_table_t *sys_table; static struct efi_config *efi_early; -#define efi_call_early(f, ...) \ - efi_early->call(efi_early->f, __VA_ARGS__); +__pure const struct efi_config *__efi_early(void) +{ + return efi_early; +} #define BOOT_SERVICES(bits) \ static void setup_boot_services##bits(struct efi_config *c) \ @@ -285,8 +287,6 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) } } -#include "../../../../drivers/firmware/efi/libstub/efi-stub-helper.c" - static void find_bits(unsigned long mask, u8 *pos, u8 *size) { u8 first, len; diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index c88c31ecad12..d487e727f1ec 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -103,20 +103,4 @@ struct efi_uga_draw_protocol { void *blt; }; -struct efi_config { - u64 image_handle; - u64 table; - u64 allocate_pool; - u64 allocate_pages; - u64 get_memory_map; - u64 free_pool; - u64 free_pages; - u64 locate_handle; - u64 handle_protocol; - u64 exit_boot_services; - u64 text_output; - efi_status_t (*call)(unsigned long, ...); - bool is64; -} __packed; - #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 30dd59a9f0b4..dcc1c536cc21 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -260,7 +260,7 @@ static void handle_relocations(void *output, unsigned long output_len) /* * Process relocations: 32 bit relocations first then 64 bit after. - * Two sets of binary relocations are added to the end of the kernel + * Three sets of binary relocations are added to the end of the kernel * before compression. Each relocation table entry is the kernel * address of the location which needs to be updated stored as a * 32-bit value which is sign extended to 64 bits. @@ -270,6 +270,8 @@ static void handle_relocations(void *output, unsigned long output_len) * kernel bits... * 0 - zero terminator for 64 bit relocations * 64 bit relocation repeated + * 0 - zero terminator for inverse 32 bit relocations + * 32 bit inverse relocation repeated * 0 - zero terminator for 32 bit relocations * 32 bit relocation repeated * @@ -286,6 +288,16 @@ static void handle_relocations(void *output, unsigned long output_len) *(uint32_t *)ptr += delta; } #ifdef CONFIG_X86_64 + while (*--reloc) { + long extended = *reloc; + extended += map; + + ptr = (unsigned long)extended; + if (ptr < min_addr || ptr > max_addr) + error("inverse 32-bit relocation outside of kernel!\n"); + + *(int32_t *)ptr -= delta; + } for (reloc--; *reloc; reloc--) { long extended = *reloc; extended += map; diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 32d2e7056c87..419819d6dab3 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -8,6 +8,7 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_FHANDLE=y CONFIG_AUDIT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index a481dd4755d5..4c311ddd973b 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -7,6 +7,7 @@ CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_FHANDLE=y CONFIG_AUDIT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index df91466f973d..ae6aad1d24f7 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -342,8 +342,8 @@ static int load_aout_binary(struct linux_binprm *bprm) time_after(jiffies, error_time + 5*HZ)) { printk(KERN_WARNING "fd_offset is not page aligned. Please convert " - "program: %s\n", - bprm->file->f_path.dentry->d_name.name); + "program: %pD\n", + bprm->file); error_time = jiffies; } #endif @@ -429,8 +429,8 @@ static int load_aout_library(struct file *file) if (time_after(jiffies, error_time + 5*HZ)) { printk(KERN_WARNING "N_TXTOFF is not page aligned. Please convert " - "library: %s\n", - file->f_path.dentry->d_name.name); + "library: %pD\n", + file); error_time = jiffies; } #endif diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 9863ee3747da..47c8e32f621a 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -5,65 +5,6 @@ #include <asm-generic/cacheflush.h> #include <asm/special_insns.h> -#ifdef CONFIG_X86_PAT -/* - * X86 PAT uses page flags WC and Uncached together to keep track of - * memory type of pages that have backing page struct. X86 PAT supports 3 - * different memory types, _PAGE_CACHE_WB, _PAGE_CACHE_WC and - * _PAGE_CACHE_UC_MINUS and fourth state where page's memory type has not - * been changed from its default (value of -1 used to denote this). - * Note we do not support _PAGE_CACHE_UC here. - */ - -#define _PGMT_DEFAULT 0 -#define _PGMT_WC (1UL << PG_arch_1) -#define _PGMT_UC_MINUS (1UL << PG_uncached) -#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1) -#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1) -#define _PGMT_CLEAR_MASK (~_PGMT_MASK) - -static inline unsigned long get_page_memtype(struct page *pg) -{ - unsigned long pg_flags = pg->flags & _PGMT_MASK; - - if (pg_flags == _PGMT_DEFAULT) - return -1; - else if (pg_flags == _PGMT_WC) - return _PAGE_CACHE_WC; - else if (pg_flags == _PGMT_UC_MINUS) - return _PAGE_CACHE_UC_MINUS; - else - return _PAGE_CACHE_WB; -} - -static inline void set_page_memtype(struct page *pg, unsigned long memtype) -{ - unsigned long memtype_flags = _PGMT_DEFAULT; - unsigned long old_flags; - unsigned long new_flags; - - switch (memtype) { - case _PAGE_CACHE_WC: - memtype_flags = _PGMT_WC; - break; - case _PAGE_CACHE_UC_MINUS: - memtype_flags = _PGMT_UC_MINUS; - break; - case _PAGE_CACHE_WB: - memtype_flags = _PGMT_WB; - break; - } - - do { - old_flags = pg->flags; - new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags; - } while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags); -} -#else -static inline unsigned long get_page_memtype(struct page *pg) { return -1; } -static inline void set_page_memtype(struct page *pg, unsigned long memtype) { } -#endif - /* * The set_memory_* API can be used to change various attributes of a virtual * address range. The attributes include: diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 9b11757975d0..25bce45c6fc4 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -158,6 +158,30 @@ static inline efi_status_t efi_thunk_set_virtual_address_map( } #endif /* CONFIG_EFI_MIXED */ + +/* arch specific definitions used by the stub code */ + +struct efi_config { + u64 image_handle; + u64 table; + u64 allocate_pool; + u64 allocate_pages; + u64 get_memory_map; + u64 free_pool; + u64 free_pages; + u64 locate_handle; + u64 handle_protocol; + u64 exit_boot_services; + u64 text_output; + efi_status_t (*call)(unsigned long, ...); + bool is64; +} __packed; + +__pure const struct efi_config *__efi_early(void); + +#define efi_call_early(f, ...) \ + __efi_early()->call(__efi_early()->f, __VA_ARGS__); + extern bool efi_reboot_required(void); #else diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h index 2519d0679d99..c3dd5e71f439 100644 --- a/arch/x86/include/asm/fb.h +++ b/arch/x86/include/asm/fb.h @@ -8,8 +8,12 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma, unsigned long off) { + unsigned long prot; + + prot = pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK; if (boot_cpu_data.x86 > 3) - pgprot_val(vma->vm_page_prot) |= _PAGE_PCD; + pgprot_val(vma->vm_page_prot) = + prot | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS); } extern int fb_is_primary_device(struct fb_info *info); diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index ffb1733ac91f..f80d70009ff8 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -69,7 +69,9 @@ enum fixed_addresses { #ifdef CONFIG_X86_32 FIX_HOLE, #else +#ifdef CONFIG_X86_VSYSCALL_EMULATION VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, +#endif #ifdef CONFIG_PARAVIRT_CLOCK PVCLOCK_FIXMAP_BEGIN, PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, @@ -136,9 +138,7 @@ enum fixed_addresses { extern void reserve_top_address(unsigned long reserve); #define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) #define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) -#define FIXADDR_BOOT_START (FIXADDR_TOP - FIXADDR_BOOT_SIZE) extern int fixmaps_set; diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index 302a323b3f67..04e9d023168f 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -38,17 +38,20 @@ extern unsigned long highstart_pfn, highend_pfn; /* * Ordering is: * - * FIXADDR_TOP - * fixed_addresses - * FIXADDR_START - * temp fixed addresses - * FIXADDR_BOOT_START - * Persistent kmap area - * PKMAP_BASE - * VMALLOC_END - * Vmalloc area - * VMALLOC_START - * high_memory + * high memory on: high_memory off: + * FIXADDR_TOP FIXADDR_TOP + * fixed addresses fixed addresses + * FIXADDR_START FIXADDR_START + * temp fixed addresses/persistent kmap area VMALLOC_END + * PKMAP_BASE temp fixed addresses/vmalloc area + * VMALLOC_END VMALLOC_START + * vmalloc area high_memory + * VMALLOC_START + * high_memory + * + * The temp fixed area is only used during boot for early_ioremap(), and + * it is unused when the ioremap() is functional. vmalloc/pkmap area become + * available after early boot so the temp fixed area is available for re-use. */ #define LAST_PKMAP_MASK (LAST_PKMAP-1) #define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 0cdbe6e81b45..34a5b93704d3 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -318,7 +318,7 @@ extern void *xlate_dev_mem_ptr(phys_addr_t phys); extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, - unsigned long prot_val); + enum page_cache_mode pcm); extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); extern bool is_early_ioremap_ptep(pte_t *ptep); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 958b90f761e5..51b26e895933 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -34,6 +34,10 @@ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ +/* AMD-specific bits */ +#define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */ +#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */ + /* * Note that the full MCACOD field of IA32_MCi_STATUS MSR is * bits 15:0. But bit 12 is the 'F' bit, defined for corrected @@ -78,7 +82,6 @@ /* Software defined banks */ #define MCE_EXTENDED_BANK 128 #define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0) -#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) #define MCE_LOG_LEN 32 #define MCE_LOG_SIGNATURE "MACHINECHECK" diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 64dc362506b7..201b520521ed 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -78,6 +78,7 @@ static inline void __exit exit_amd_microcode(void) {} extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); extern int __init save_microcode_in_initrd(void); +void reload_early_microcode(void); #else static inline void __init load_ucode_bsp(void) {} static inline void load_ucode_ap(void) {} @@ -85,6 +86,7 @@ static inline int __init save_microcode_in_initrd(void) { return 0; } +static inline void reload_early_microcode(void) {} #endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index b7b10b82d3e5..af935397e053 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, extern int __apply_microcode_amd(struct microcode_amd *mc_amd); extern int apply_microcode_amd(int cpu); -extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); +extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size); #define PATCH_MAX_SIZE PAGE_SIZE extern u8 amd_ucode_patch[PATCH_MAX_SIZE]; @@ -68,10 +68,12 @@ extern u8 amd_ucode_patch[PATCH_MAX_SIZE]; extern void __init load_ucode_amd_bsp(void); extern void load_ucode_amd_ap(void); extern int __init save_microcode_in_initrd_amd(void); +void reload_ucode_amd(void); #else static inline void __init load_ucode_amd_bsp(void) {} static inline void load_ucode_amd_ap(void) {} static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; } +void reload_ucode_amd(void) {} #endif #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index bbe296e0bce1..dd4c20043ce7 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -68,11 +68,13 @@ extern void __init load_ucode_intel_bsp(void); extern void load_ucode_intel_ap(void); extern void show_ucode_info_early(void); extern int __init save_microcode_in_initrd_intel(void); +void reload_ucode_intel(void); #else static inline __init void load_ucode_intel_bsp(void) {} static inline void load_ucode_intel_ap(void) {} static inline void show_ucode_info_early(void) {} static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL; } +static inline void reload_ucode_intel(void) {} #endif #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index be91d5736e08..40269a2bf6f9 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -52,7 +52,16 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Stop flush ipis for the previous mm */ cpumask_clear_cpu(cpu, mm_cpumask(prev)); - /* Load the LDT, if the LDT is different: */ + /* + * Load the LDT, if the LDT is different. + * + * It's possible leave_mm(prev) has been called. If so, + * then prev->context.ldt could be out of sync with the + * LDT descriptor or the LDT register. This can only happen + * if prev->context.ldt is non-null, since we never free + * an LDT. But LDTs can't be shared across mms, so + * prev->context.ldt won't be equal to next->context.ldt. + */ if (unlikely(prev->context.ldt != next->context.ldt)) load_LDT_nolock(&next->context); } diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index f408caf73430..b3bebf9e5746 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -39,6 +39,8 @@ void copy_page(void *to, void *from); #endif /* !__ASSEMBLY__ */ -#define __HAVE_ARCH_GATE_AREA 1 +#ifdef CONFIG_X86_VSYSCALL_EMULATION +# define __HAVE_ARCH_GATE_AREA 1 +#endif #endif /* _ASM_X86_PAGE_64_H */ diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index e2c1668dde7a..91bc4ba95f91 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -11,16 +11,17 @@ static const int pat_enabled; #endif extern void pat_init(void); +void pat_init_cache_modes(void); extern int reserve_memtype(u64 start, u64 end, - unsigned long req_type, unsigned long *ret_type); + enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); extern int free_memtype(u64 start, u64 end); extern int kernel_map_sync_memtype(u64 base, unsigned long size, - unsigned long flag); + enum page_cache_mode pcm); int io_reserve_memtype(resource_size_t start, resource_size_t end, - unsigned long *type); + enum page_cache_mode *pcm); void io_free_memtype(resource_size_t start, resource_size_t end); diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index fd472181a1d0..e0ba66ca68c6 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -64,7 +64,7 @@ #define __percpu_prefix "" #endif -#define __percpu_arg(x) __percpu_prefix "%P" #x +#define __percpu_arg(x) __percpu_prefix "%" #x /* * Initialized pointers to per-cpu variables needed for the boot @@ -179,29 +179,58 @@ do { \ } \ } while (0) -#define percpu_from_op(op, var, constraint) \ +#define percpu_from_op(op, var) \ ({ \ typeof(var) pfo_ret__; \ switch (sizeof(var)) { \ case 1: \ asm(op "b "__percpu_arg(1)",%0" \ : "=q" (pfo_ret__) \ - : constraint); \ + : "m" (var)); \ break; \ case 2: \ asm(op "w "__percpu_arg(1)",%0" \ : "=r" (pfo_ret__) \ - : constraint); \ + : "m" (var)); \ break; \ case 4: \ asm(op "l "__percpu_arg(1)",%0" \ : "=r" (pfo_ret__) \ - : constraint); \ + : "m" (var)); \ break; \ case 8: \ asm(op "q "__percpu_arg(1)",%0" \ : "=r" (pfo_ret__) \ - : constraint); \ + : "m" (var)); \ + break; \ + default: __bad_percpu_size(); \ + } \ + pfo_ret__; \ +}) + +#define percpu_stable_op(op, var) \ +({ \ + typeof(var) pfo_ret__; \ + switch (sizeof(var)) { \ + case 1: \ + asm(op "b "__percpu_arg(P1)",%0" \ + : "=q" (pfo_ret__) \ + : "p" (&(var))); \ + break; \ + case 2: \ + asm(op "w "__percpu_arg(P1)",%0" \ + : "=r" (pfo_ret__) \ + : "p" (&(var))); \ + break; \ + case 4: \ + asm(op "l "__percpu_arg(P1)",%0" \ + : "=r" (pfo_ret__) \ + : "p" (&(var))); \ + break; \ + case 8: \ + asm(op "q "__percpu_arg(P1)",%0" \ + : "=r" (pfo_ret__) \ + : "p" (&(var))); \ break; \ default: __bad_percpu_size(); \ } \ @@ -359,11 +388,11 @@ do { \ * per-thread variables implemented as per-cpu variables and thus * stable for the duration of the respective task. */ -#define this_cpu_read_stable(var) percpu_from_op("mov", var, "p" (&(var))) +#define this_cpu_read_stable(var) percpu_stable_op("mov", var) -#define raw_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) -#define raw_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) -#define raw_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define raw_cpu_read_1(pcp) percpu_from_op("mov", pcp) +#define raw_cpu_read_2(pcp) percpu_from_op("mov", pcp) +#define raw_cpu_read_4(pcp) percpu_from_op("mov", pcp) #define raw_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val) #define raw_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val) @@ -381,9 +410,9 @@ do { \ #define raw_cpu_xchg_2(pcp, val) percpu_xchg_op(pcp, val) #define raw_cpu_xchg_4(pcp, val) percpu_xchg_op(pcp, val) -#define this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) -#define this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) -#define this_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define this_cpu_read_1(pcp) percpu_from_op("mov", pcp) +#define this_cpu_read_2(pcp) percpu_from_op("mov", pcp) +#define this_cpu_read_4(pcp) percpu_from_op("mov", pcp) #define this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val) #define this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val) #define this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val) @@ -435,7 +464,7 @@ do { \ * 32 bit must fall back to generic operations. */ #ifdef CONFIG_X86_64 -#define raw_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define raw_cpu_read_8(pcp) percpu_from_op("mov", pcp) #define raw_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) #define raw_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define raw_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) @@ -444,7 +473,7 @@ do { \ #define raw_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval) #define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval) -#define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp)) +#define this_cpu_read_8(pcp) percpu_from_op("mov", pcp) #define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val) #define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val) #define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val) @@ -522,7 +551,7 @@ static inline int x86_this_cpu_variable_test_bit(int nr, #include <asm-generic/percpu.h> /* We can use this directly for local CPU (faster). */ -DECLARE_PER_CPU(unsigned long, this_cpu_off); +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 081d6f45e006..e8a5454acc99 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -9,9 +9,10 @@ /* * Macro to mark a page protection value as UC- */ -#define pgprot_noncached(prot) \ - ((boot_cpu_data.x86 > 3) \ - ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS)) \ +#define pgprot_noncached(prot) \ + ((boot_cpu_data.x86 > 3) \ + ? (__pgprot(pgprot_val(prot) | \ + cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) #ifndef __ASSEMBLY__ @@ -409,8 +410,8 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, - unsigned long flags, - unsigned long new_flags) + enum page_cache_mode pcm, + enum page_cache_mode new_pcm) { /* * PAT type is always WB for untracked ranges, so no need to check. @@ -424,10 +425,10 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back */ - if ((flags == _PAGE_CACHE_UC_MINUS && - new_flags == _PAGE_CACHE_WB) || - (flags == _PAGE_CACHE_WC && - new_flags == _PAGE_CACHE_WB)) { + if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && + new_pcm == _PAGE_CACHE_MODE_WB) || + (pcm == _PAGE_CACHE_MODE_WC && + new_pcm == _PAGE_CACHE_MODE_WB)) { return 0; } diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index ed5903be26fe..9fb2f2bc8245 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -37,7 +37,7 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ #define LAST_PKMAP 1024 #endif -#define PKMAP_BASE ((FIXADDR_BOOT_START - PAGE_SIZE * (LAST_PKMAP + 1)) \ +#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1)) \ & PMD_MASK) #ifdef CONFIG_HIGHMEM diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 7166e25ecb57..602b6028c5b6 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -63,6 +63,8 @@ typedef struct { pteval_t pte; } pte_t; #define MODULES_LEN (MODULES_END - MODULES_VADDR) #define ESPFIX_PGD_ENTRY _AC(-2, UL) #define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) +#define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) +#define EFI_VA_END (-68 * (_AC(1, UL) << 30)) #define EARLY_DYNAMIC_PAGE_TABLES 64 diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 07789647bf33..af447f95e3be 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -128,11 +128,28 @@ _PAGE_SOFT_DIRTY | _PAGE_NUMA) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA) -#define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) -#define _PAGE_CACHE_WB (0) -#define _PAGE_CACHE_WC (_PAGE_PWT) -#define _PAGE_CACHE_UC_MINUS (_PAGE_PCD) -#define _PAGE_CACHE_UC (_PAGE_PCD | _PAGE_PWT) +/* + * The cache modes defined here are used to translate between pure SW usage + * and the HW defined cache mode bits and/or PAT entries. + * + * The resulting bits for PWT, PCD and PAT should be chosen in a way + * to have the WB mode at index 0 (all bits clear). This is the default + * right now and likely would break too much if changed. + */ +#ifndef __ASSEMBLY__ +enum page_cache_mode { + _PAGE_CACHE_MODE_WB = 0, + _PAGE_CACHE_MODE_WC = 1, + _PAGE_CACHE_MODE_UC_MINUS = 2, + _PAGE_CACHE_MODE_UC = 3, + _PAGE_CACHE_MODE_WT = 4, + _PAGE_CACHE_MODE_WP = 5, + _PAGE_CACHE_MODE_NUM = 8 +}; +#endif + +#define _PAGE_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT) +#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) #define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) #define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ @@ -156,41 +173,27 @@ #define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) #define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) -#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT) -#define __PAGE_KERNEL_WC (__PAGE_KERNEL | _PAGE_CACHE_WC) -#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT) -#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL | _PAGE_PCD) +#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) #define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER) #define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) -#define __PAGE_KERNEL_VVAR_NOCACHE (__PAGE_KERNEL_VVAR | _PAGE_PCD | _PAGE_PWT) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) -#define __PAGE_KERNEL_LARGE_NOCACHE (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) #define __PAGE_KERNEL_IO (__PAGE_KERNEL) #define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE) -#define __PAGE_KERNEL_IO_UC_MINUS (__PAGE_KERNEL_UC_MINUS) -#define __PAGE_KERNEL_IO_WC (__PAGE_KERNEL_WC) #define PAGE_KERNEL __pgprot(__PAGE_KERNEL) #define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) #define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) #define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX) -#define PAGE_KERNEL_WC __pgprot(__PAGE_KERNEL_WC) #define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE) -#define PAGE_KERNEL_UC_MINUS __pgprot(__PAGE_KERNEL_UC_MINUS) -#define PAGE_KERNEL_EXEC_NOCACHE __pgprot(__PAGE_KERNEL_EXEC_NOCACHE) #define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE) -#define PAGE_KERNEL_LARGE_NOCACHE __pgprot(__PAGE_KERNEL_LARGE_NOCACHE) #define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC) #define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL) #define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR) -#define PAGE_KERNEL_VVAR_NOCACHE __pgprot(__PAGE_KERNEL_VVAR_NOCACHE) #define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) #define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE) -#define PAGE_KERNEL_IO_UC_MINUS __pgprot(__PAGE_KERNEL_IO_UC_MINUS) -#define PAGE_KERNEL_IO_WC __pgprot(__PAGE_KERNEL_IO_WC) /* xwr */ #define __P000 PAGE_NONE @@ -341,6 +344,59 @@ static inline pmdval_t pmdnuma_flags(pmd_t pmd) #define pgprot_val(x) ((x).pgprot) #define __pgprot(x) ((pgprot_t) { (x) } ) +extern uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM]; +extern uint8_t __pte2cachemode_tbl[8]; + +#define __pte2cm_idx(cb) \ + ((((cb) >> (_PAGE_BIT_PAT - 2)) & 4) | \ + (((cb) >> (_PAGE_BIT_PCD - 1)) & 2) | \ + (((cb) >> _PAGE_BIT_PWT) & 1)) +#define __cm_idx2pte(i) \ + ((((i) & 4) << (_PAGE_BIT_PAT - 2)) | \ + (((i) & 2) << (_PAGE_BIT_PCD - 1)) | \ + (((i) & 1) << _PAGE_BIT_PWT)) + +static inline unsigned long cachemode2protval(enum page_cache_mode pcm) +{ + if (likely(pcm == 0)) + return 0; + return __cachemode2pte_tbl[pcm]; +} +static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm) +{ + return __pgprot(cachemode2protval(pcm)); +} +static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) +{ + unsigned long masked; + + masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK; + if (likely(masked == 0)) + return 0; + return __pte2cachemode_tbl[__pte2cm_idx(masked)]; +} +static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) +{ + pgprot_t new; + unsigned long val; + + val = pgprot_val(pgprot); + pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | + ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); + return new; +} +static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) +{ + pgprot_t new; + unsigned long val; + + val = pgprot_val(pgprot); + pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | + ((val & _PAGE_PAT_LARGE) >> + (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); + return new; +} + typedef struct page *pgtable_t; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 9617a1716813..a092a0cce0b7 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -127,7 +127,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; -} __attribute__((__aligned__(SMP_CACHE_BYTES))); +}; #define X86_VENDOR_INTEL 0 #define X86_VENDOR_CYRIX 1 @@ -151,7 +151,7 @@ extern __u32 cpu_caps_cleared[NCAPINTS]; extern __u32 cpu_caps_set[NCAPINTS]; #ifdef CONFIG_SMP -DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); +DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) #else #define cpu_info boot_cpu_data @@ -894,7 +894,13 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #else /* - * User space process size. 47bits minus one guard page. + * User space process size. 47bits minus one guard page. The guard + * page is necessary on Intel CPUs: if a SYSCALL instruction is at + * the highest possible canonical userspace address, then that + * syscall will enter the kernel with a non-canonical return + * address, and SYSRET will explode dangerously. We avoid this + * particular problem by preventing anything from being mapped + * at the maximum canonical address. */ #define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE) diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index d7f3b3b78ac3..751bf4b7bf11 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -79,12 +79,12 @@ do { \ #else /* CONFIG_X86_32 */ /* frame pointer must be last for get_wchan */ -#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t" +#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t" +#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t" #define __EXTRA_CLOBBER \ , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15" + "r12", "r13", "r14", "r15", "flags" #ifdef CONFIG_CC_STACKPROTECTOR #define __switch_canary \ @@ -100,7 +100,11 @@ do { \ #define __switch_canary_iparam #endif /* CC_STACKPROTECTOR */ -/* Save restore flags to clear handle leaking NT */ +/* + * There is no need to save or restore flags, because flags are always + * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL + * has no effect. + */ #define switch_to(prev, next, last) \ asm volatile(SAVE_CONTEXT \ "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 2d60a7813dfe..fc808b83fccb 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -33,8 +33,8 @@ * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set). */ -#define MAX_CPUS_PER_UVHUB 64 -#define MAX_CPUS_PER_SOCKET 32 +#define MAX_CPUS_PER_UVHUB 128 +#define MAX_CPUS_PER_SOCKET 64 #define ADP_SZ 64 /* hardware-provided max. */ #define UV_CPUS_PER_AS 32 /* hardware-provided max. */ #define ITEMS_PER_DESC 8 diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 3c3366c2e37f..e7e9682a33e9 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -70,4 +70,23 @@ static inline void gtod_write_end(struct vsyscall_gtod_data *s) ++s->seq; } +#ifdef CONFIG_X86_64 + +#define VGETCPU_CPU_MASK 0xfff + +static inline unsigned int __getcpu(void) +{ + unsigned int p; + + /* + * Load per CPU data from GDT. LSL is faster than RDTSCP and + * works on all CPUs. + */ + asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + + return p; +} + +#endif /* CONFIG_X86_64 */ + #endif /* _ASM_X86_VGTOD_H */ diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 2a46ca720afc..6ba66ee79710 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,15 +4,7 @@ #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> -#define VGETCPU_RDTSCP 1 -#define VGETCPU_LSL 2 - -/* kernel space (writeable) */ -extern int vgetcpu_mode; -extern struct timezone sys_tz; - -#include <asm/vvar.h> - +#ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); /* @@ -20,25 +12,12 @@ extern void map_vsyscall(void); * Returns true if handled. */ extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address); - -#ifdef CONFIG_X86_64 - -#define VGETCPU_CPU_MASK 0xfff - -static inline unsigned int __getcpu(void) +#else +static inline void map_vsyscall(void) {} +static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) { - unsigned int p; - - if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) { - /* Load per CPU data from RDTSCP */ - native_read_tscp(&p); - } else { - /* Load per CPU data from GDT */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); - } - - return p; + return false; } -#endif /* CONFIG_X86_64 */ +#endif #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index 5d2b9ad2c6d2..3f32dfc2ab73 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -44,8 +44,6 @@ extern char __vvar_page; /* DECLARE_VVAR(offset, type, name) */ -DECLARE_VVAR(0, volatile unsigned long, jiffies) -DECLARE_VVAR(16, int, vgetcpu_mode) DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data) #undef DECLARE_VVAR diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8f1e77440b2b..5d4502c8b983 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -28,8 +28,7 @@ obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += mcount_64.o obj-y += syscall_$(BITS).o vsyscall_gtod.o -obj-$(CONFIG_X86_64) += vsyscall_64.o -obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 4128b5fcb559..c2fd21fed002 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -40,7 +40,7 @@ static unsigned int get_apic_id(unsigned long x) unsigned int id; rdmsrl(MSR_FAM10H_NODE_ID, value); - id = ((x >> 24) & 0xffU) | ((value << 2) & 0x3f00U); + id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U); return id; } @@ -145,7 +145,7 @@ static void numachip_send_IPI_all(int vector) static void numachip_send_IPI_self(int vector) { - __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); + apic_write(APIC_SELF_IPI, vector); } static int __init numachip_probe(void) @@ -153,20 +153,8 @@ static int __init numachip_probe(void) return apic == &apic_numachip; } -static void __init map_csrs(void) -{ - printk(KERN_INFO "NumaChip: Mapping local CSR space (%016llx - %016llx)\n", - NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_BASE + NUMACHIP_LCSR_SIZE - 1); - init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); - - printk(KERN_INFO "NumaChip: Mapping global CSR space (%016llx - %016llx)\n", - NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_BASE + NUMACHIP_GCSR_SIZE - 1); - init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE); -} - static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) { - if (c->phys_proc_id != node) { c->phys_proc_id = node; per_cpu(cpu_llc_id, smp_processor_id()) = node; @@ -175,19 +163,15 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) static int __init numachip_system_init(void) { - unsigned int val; - if (!numachip_system) return 0; + init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); + init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE); + x86_cpuinit.fixup_cpu_id = fixup_cpu_id; x86_init.pci.arch_init = pci_numachip_init; - map_csrs(); - - val = read_lcsr(CSR_G0_NODE_IDS); - printk(KERN_INFO "NumaChip: Local NodeID = %08x\n", val); - return 0; } early_initcall(numachip_system_init); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index e7c798b354fa..4f9359f36bb7 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -48,7 +48,6 @@ int main(void) #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); - ENTRY(bx); ENTRY(cx); ENTRY(dx); ENTRY(sp); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 813d29d00a17..15c5df92f74e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -566,6 +566,17 @@ static void init_amd_k8(struct cpuinfo_x86 *c) if (!c->x86_model_id[0]) strcpy(c->x86_model_id, "Hammer"); + +#ifdef CONFIG_SMP + /* + * Disable TLB flush filter by setting HWCR.FFDIS on K8 + * bit 6 of msr C001_0015 + * + * Errata 63 for SH-B3 steppings + * Errata 122 for all steppings (F+ have it disabled by default) + */ + msr_set_bit(MSR_K7_HWCR, 6); +#endif } static void init_amd_gh(struct cpuinfo_x86 *c) @@ -636,18 +647,6 @@ static void init_amd(struct cpuinfo_x86 *c) { u32 dummy; -#ifdef CONFIG_SMP - /* - * Disable TLB flush filter by setting HWCR.FFDIS on K8 - * bit 6 of msr C001_0015 - * - * Errata 63 for SH-B3 steppings - * Errata 122 for all steppings (F+ have it disabled by default) - */ - if (c->x86 == 0xf) - msr_set_bit(MSR_K7_HWCR, 6); -#endif - early_init_amd(c); /* diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cfa9b5b2c27a..c6049650c093 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -958,14 +958,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) } #ifdef CONFIG_X86_64 -static void vgetcpu_set_mode(void) -{ - if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) - vgetcpu_mode = VGETCPU_RDTSCP; - else - vgetcpu_mode = VGETCPU_LSL; -} - #ifdef CONFIG_IA32_EMULATION /* May not be __init: called during resume */ static void syscall32_cpu_init(void) @@ -1008,8 +1000,6 @@ void __init identify_boot_cpu(void) #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); -#else - vgetcpu_set_mode(); #endif cpu_detect_tlb(&boot_cpu_data); } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 09edd0b65fef..10b46906767f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -3,6 +3,8 @@ enum severity_level { MCE_NO_SEVERITY, + MCE_DEFERRED_SEVERITY, + MCE_UCNA_SEVERITY = MCE_DEFERRED_SEVERITY, MCE_KEEP_SEVERITY, MCE_SOME_SEVERITY, MCE_AO_SEVERITY, @@ -21,7 +23,7 @@ struct mce_bank { char attrname[ATTR_LEN]; /* attribute name */ }; -int mce_severity(struct mce *a, int tolerant, char **msg); +int mce_severity(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern struct mce_bank *mce_banks; diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index c370e1c4468b..8bb433043a7f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -31,6 +31,7 @@ enum context { IN_KERNEL = 1, IN_USER = 2 }; enum ser { SER_REQUIRED = 1, NO_SER = 2 }; +enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 }; static struct severity { u64 mask; @@ -40,6 +41,7 @@ static struct severity { unsigned char mcgres; unsigned char ser; unsigned char context; + unsigned char excp; unsigned char covered; char *msg; } severities[] = { @@ -48,6 +50,8 @@ static struct severity { #define USER .context = IN_USER #define SER .ser = SER_REQUIRED #define NOSER .ser = NO_SER +#define EXCP .excp = EXCP_CONTEXT +#define NOEXCP .excp = NO_EXCP #define BITCLR(x) .mask = x, .result = 0 #define BITSET(x) .mask = x, .result = x #define MCGMASK(x, y) .mcgmask = x, .mcgres = y @@ -62,7 +66,7 @@ static struct severity { ), MCESEV( NO, "Not enabled", - BITCLR(MCI_STATUS_EN) + EXCP, BITCLR(MCI_STATUS_EN) ), MCESEV( PANIC, "Processor context corrupt", @@ -71,16 +75,20 @@ static struct severity { /* When MCIP is not set something is very confused */ MCESEV( PANIC, "MCIP not set in MCA handler", - MCGMASK(MCG_STATUS_MCIP, 0) + EXCP, MCGMASK(MCG_STATUS_MCIP, 0) ), /* Neither return not error IP -- no chance to recover -> PANIC */ MCESEV( PANIC, "Neither restart nor error IP", - MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0) + EXCP, MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0) ), MCESEV( PANIC, "In kernel and no restart IP", - KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) + EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) + ), + MCESEV( + DEFERRED, "Deferred error", + NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED) ), MCESEV( KEEP, "Corrected error", @@ -89,7 +97,7 @@ static struct severity { /* ignore OVER for UCNA */ MCESEV( - KEEP, "Uncorrected no action required", + UCNA, "Uncorrected no action required", SER, MASK(MCI_UC_SAR, MCI_STATUS_UC) ), MCESEV( @@ -178,8 +186,9 @@ static int error_context(struct mce *m) return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL; } -int mce_severity(struct mce *m, int tolerant, char **msg) +int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp) { + enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); enum context ctx = error_context(m); struct severity *s; @@ -194,6 +203,8 @@ int mce_severity(struct mce *m, int tolerant, char **msg) continue; if (s->context && ctx != s->context) continue; + if (s->excp && excp != s->excp) + continue; if (msg) *msg = s->msg; s->covered = 1; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 61a9668cebfd..d2c611699cd9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -292,10 +292,10 @@ static void print_mce(struct mce *m) #define PANIC_TIMEOUT 5 /* 5 seconds */ -static atomic_t mce_paniced; +static atomic_t mce_panicked; static int fake_panic; -static atomic_t mce_fake_paniced; +static atomic_t mce_fake_panicked; /* Panic in progress. Enable interrupts and wait for final IPI */ static void wait_for_panic(void) @@ -319,7 +319,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) /* * Make sure only one CPU runs in machine check panic */ - if (atomic_inc_return(&mce_paniced) > 1) + if (atomic_inc_return(&mce_panicked) > 1) wait_for_panic(); barrier(); @@ -327,7 +327,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp) console_verbose(); } else { /* Don't log too much for fake panic */ - if (atomic_inc_return(&mce_fake_paniced) > 1) + if (atomic_inc_return(&mce_fake_panicked) > 1) return; } /* First print corrected ones that are still unlogged */ @@ -575,6 +575,37 @@ static void mce_read_aux(struct mce *m, int i) } } +static bool memory_error(struct mce *m) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (c->x86_vendor == X86_VENDOR_AMD) { + /* + * coming soon + */ + return false; + } else if (c->x86_vendor == X86_VENDOR_INTEL) { + /* + * Intel SDM Volume 3B - 15.9.2 Compound Error Codes + * + * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for + * indicating a memory error. Bit 8 is used for indicating a + * cache hierarchy error. The combination of bit 2 and bit 3 + * is used for indicating a `generic' cache hierarchy error + * But we can't just blindly check the above bits, because if + * bit 11 is set, then it is a bus/interconnect error - and + * either way the above bits just gives more detail on what + * bus/interconnect error happened. Note that bit 12 can be + * ignored, as it's the "filter" bit. + */ + return (m->status & 0xef80) == BIT(7) || + (m->status & 0xef00) == BIT(8) || + (m->status & 0xeffc) == 0xc; + } + + return false; +} + DEFINE_PER_CPU(unsigned, mce_poll_count); /* @@ -595,6 +626,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { struct mce m; + int severity; int i; this_cpu_inc(mce_poll_count); @@ -630,6 +662,20 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) if (!(flags & MCP_TIMESTAMP)) m.tsc = 0; + + severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); + + /* + * In the cases where we don't have a valid address after all, + * do not add it into the ring buffer. + */ + if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { + if (m.status & MCI_STATUS_ADDRV) { + mce_ring_add(m.addr >> PAGE_SHIFT); + mce_schedule_work(); + } + } + /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. @@ -668,7 +714,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); } - if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY) + if (mce_severity(m, mca_cfg.tolerant, msg, true) >= + MCE_PANIC_SEVERITY) ret = 1; } return ret; @@ -697,7 +744,7 @@ static int mce_timed_out(u64 *t) * might have been modified by someone else. */ rmb(); - if (atomic_read(&mce_paniced)) + if (atomic_read(&mce_panicked)) wait_for_panic(); if (!mca_cfg.monarch_timeout) goto out; @@ -754,7 +801,7 @@ static void mce_reign(void) for_each_possible_cpu(cpu) { int severity = mce_severity(&per_cpu(mces_seen, cpu), mca_cfg.tolerant, - &nmsg); + &nmsg, true); if (severity > global_worst) { msg = nmsg; global_worst = severity; @@ -1095,13 +1142,14 @@ void do_machine_check(struct pt_regs *regs, long error_code) */ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - severity = mce_severity(&m, cfg->tolerant, NULL); + severity = mce_severity(&m, cfg->tolerant, NULL, true); /* - * When machine check was for corrected handler don't touch, - * unless we're panicing. + * When machine check was for corrected/deferred handler don't + * touch, unless we're panicing. */ - if (severity == MCE_KEEP_SEVERITY && !no_way_out) + if ((severity == MCE_KEEP_SEVERITY || + severity == MCE_UCNA_SEVERITY) && !no_way_out) continue; __set_bit(i, toclear); if (severity == MCE_NO_SEVERITY) { @@ -2520,7 +2568,7 @@ struct dentry *mce_get_debugfs_dir(void) static void mce_reset(void) { cpu_missing = 0; - atomic_set(&mce_fake_paniced, 0); + atomic_set(&mce_fake_panicked, 0); atomic_set(&mce_executing, 0); atomic_set(&mce_callin, 0); atomic_set(&global_nwo, 0); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 5d4999f95aec..f1c3769bbd64 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -212,12 +212,12 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) unsigned int cpu = smp_processor_id(); u32 low = 0, high = 0, address = 0; unsigned int bank, block; - int offset = -1; + int offset = -1, new; for (bank = 0; bank < mca_cfg.banks; ++bank) { for (block = 0; block < NR_BLOCKS; ++block) { if (block == 0) - address = MSR_IA32_MC0_MISC + bank * 4; + address = MSR_IA32_MCx_MISC(bank); else if (block == 1) { address = (low & MASK_BLKPTR_LO) >> 21; if (!address) @@ -247,13 +247,18 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) b.address = address; b.interrupt_capable = lvt_interrupt_supported(bank, high); - if (b.interrupt_capable) { - int new = (high & MASK_LVTOFF_HI) >> 20; - offset = setup_APIC_mce(offset, new); - } + if (!b.interrupt_capable) + goto init; + + new = (high & MASK_LVTOFF_HI) >> 20; + offset = setup_APIC_mce(offset, new); + + if ((offset == new) && + (mce_threshold_vector != amd_threshold_interrupt)) + mce_threshold_vector = amd_threshold_interrupt; +init: mce_threshold_block_init(&b, offset); - mce_threshold_vector = amd_threshold_interrupt; } } } @@ -270,18 +275,17 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; + int cpu = smp_processor_id(); unsigned int bank, block; struct mce m; - mce_setup(&m); - /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { - if (!(per_cpu(bank_map, m.cpu) & (1 << bank))) + if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; for (block = 0; block < NR_BLOCKS; ++block) { if (block == 0) { - address = MSR_IA32_MC0_MISC + bank * 4; + address = MSR_IA32_MCx_MISC(bank); } else if (block == 1) { address = (low & MASK_BLKPTR_LO) >> 21; if (!address) @@ -309,21 +313,20 @@ static void amd_threshold_interrupt(void) * Log the machine check that caused the threshold * event. */ - machine_check_poll(MCP_TIMESTAMP, - this_cpu_ptr(&mce_poll_banks)); - - if (high & MASK_OVERFLOW_HI) { - rdmsrl(address, m.misc); - rdmsrl(MSR_IA32_MC0_STATUS + bank * 4, - m.status); - m.bank = K8_MCE_THRESHOLD_BASE - + bank * NR_BLOCKS - + block; - mce_log(&m); - return; - } + if (high & MASK_OVERFLOW_HI) + goto log; } } + return; + +log: + mce_setup(&m); + rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status); + m.misc = ((u64)high << 32) | low; + m.bank = bank; + mce_log(&m); + + wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); } /* @@ -617,8 +620,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, - MSR_IA32_MC0_MISC + bank * 4); + err = allocate_threshold_blocks(cpu, bank, 0, MSR_IA32_MCx_MISC(bank)); if (!err) goto out; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 8fffd845e22b..bfbbe6195e2d 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -376,7 +376,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, return UCODE_OK; } -enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) +enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size) { enum ucode_state ret; @@ -390,8 +390,8 @@ enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32) /* save BSP's matching patch for early load */ - if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) { - struct ucode_patch *p = find_patch(smp_processor_id()); + if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { + struct ucode_patch *p = find_patch(cpu); if (p) { memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), @@ -444,7 +444,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - ret = load_microcode_amd(c->x86, fw->data, fw->size); + ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 06674473b0e6..737737edbd1e 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -389,7 +389,7 @@ int __init save_microcode_in_initrd_amd(void) eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); - ret = load_microcode_amd(eax, container, container_size); + ret = load_microcode_amd(smp_processor_id(), eax, container, container_size); if (ret != UCODE_OK) retval = -EINVAL; @@ -402,3 +402,21 @@ int __init save_microcode_in_initrd_amd(void) return retval; } + +void reload_ucode_amd(void) +{ + struct microcode_amd *mc; + u32 rev, eax; + + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); + + mc = (struct microcode_amd *)amd_ucode_patch; + + if (mc && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) { + ucode_new_rev = mc->hdr.patch_id; + pr_info("microcode: reload patch_level=0x%08x\n", + ucode_new_rev); + } + } +} diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 08fe6e8a726e..15c29096136b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -465,16 +465,8 @@ static void mc_bp_resume(void) if (uci->valid && uci->mc) microcode_ops->apply_microcode(cpu); -#ifdef CONFIG_X86_64 else if (!uci->mc) - /* - * We might resume and not have applied late microcode but still - * have a newer patch stashed from the early loader. We don't - * have it in uci->mc so we have to load it the same way we're - * applying patches early on the APs. - */ - load_ucode_ap(); -#endif + reload_early_microcode(); } static struct syscore_ops mc_syscore_ops = { @@ -559,7 +551,7 @@ static int __init microcode_init(void) struct cpuinfo_x86 *c = &cpu_data(0); int error; - if (dis_ucode_ldr) + if (paravirt_enabled() || dis_ucode_ldr) return 0; if (c->x86_vendor == X86_VENDOR_INTEL) diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index 2c017f242a78..d45df4bd16ab 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -176,3 +176,24 @@ int __init save_microcode_in_initrd(void) return 0; } + +void reload_early_microcode(void) +{ + int vendor, x86; + + vendor = x86_vendor(); + x86 = x86_family(); + + switch (vendor) { + case X86_VENDOR_INTEL: + if (x86 >= 6) + reload_ucode_intel(); + break; + case X86_VENDOR_AMD: + if (x86 >= 0x10) + reload_ucode_amd(); + break; + default: + break; + } +} diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index b88343f7a3b3..ec9df6f9cd47 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -650,8 +650,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci) } #endif -static int apply_microcode_early(struct mc_saved_data *mc_saved_data, - struct ucode_cpu_info *uci) +static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) { struct microcode_intel *mc_intel; unsigned int val[2]; @@ -680,7 +679,10 @@ static int apply_microcode_early(struct mc_saved_data *mc_saved_data, #endif uci->cpu_sig.rev = val[1]; - print_ucode(uci); + if (early) + print_ucode(uci); + else + print_ucode_info(uci, mc_intel->hdr.date); return 0; } @@ -715,12 +717,17 @@ _load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, unsigned long initrd_end_early, struct ucode_cpu_info *uci) { + enum ucode_state ret; + collect_cpu_info_early(uci); scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data, mc_saved_in_initrd, uci); - load_microcode(mc_saved_data, mc_saved_in_initrd, - initrd_start_early, uci); - apply_microcode_early(mc_saved_data, uci); + + ret = load_microcode(mc_saved_data, mc_saved_in_initrd, + initrd_start_early, uci); + + if (ret == UCODE_OK) + apply_microcode_early(uci, true); } void __init @@ -749,7 +756,8 @@ load_ucode_intel_bsp(void) initrd_end_early = initrd_start_early + ramdisk_size; _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, - initrd_start_early, initrd_end_early, &uci); + initrd_start_early, initrd_end_early, + &uci); #endif } @@ -783,5 +791,23 @@ void load_ucode_intel_ap(void) collect_cpu_info_early(&uci); load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, initrd_start_addr, &uci); - apply_microcode_early(mc_saved_data_p, &uci); + apply_microcode_early(&uci, true); +} + +void reload_ucode_intel(void) +{ + struct ucode_cpu_info uci; + enum ucode_state ret; + + if (!mc_saved_data.mc_saved_count) + return; + + collect_cpu_info_early(&uci); + + ret = generic_load_microcode_early(mc_saved_data.mc_saved, + mc_saved_data.mc_saved_count, &uci); + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, false); } diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 5433658e598d..e7d8c7608471 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -72,7 +72,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (c->x86_mask || c->cpuid_level >= 0) seq_printf(m, "stepping\t: %d\n", c->x86_mask); else - seq_printf(m, "stepping\t: unknown\n"); + seq_puts(m, "stepping\t: unknown\n"); if (c->microcode) seq_printf(m, "microcode\t: 0x%x\n", c->microcode); @@ -92,12 +92,12 @@ static int show_cpuinfo(struct seq_file *m, void *v) show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); - seq_printf(m, "flags\t\t:"); + seq_puts(m, "flags\t\t:"); for (i = 0; i < 32*NCAPINTS; i++) if (cpu_has(c, i) && x86_cap_flags[i] != NULL) seq_printf(m, " %s", x86_cap_flags[i]); - seq_printf(m, "\nbugs\t\t:"); + seq_puts(m, "\nbugs\t\t:"); for (i = 0; i < 32*NBUGINTS; i++) { unsigned int bug_bit = 32*NCAPINTS + i; @@ -118,7 +118,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n", c->x86_phys_bits, c->x86_virt_bits); - seq_printf(m, "power management:"); + seq_puts(m, "power management:"); for (i = 0; i < 32; i++) { if (c->x86_power & (1 << i)) { if (i < ARRAY_SIZE(x86_power_flags) && @@ -131,7 +131,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) } } - seq_printf(m, "\n\n"); + seq_puts(m, "\n\n"); return 0; } diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 3225ae6c5180..83741a71558f 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -143,7 +143,7 @@ static int cpuid_device_create(int cpu) dev = device_create(cpuid_class, NULL, MKDEV(CPUID_MAJOR, cpu), NULL, "cpu%d", cpu); - return IS_ERR(dev) ? PTR_ERR(dev) : 0; + return PTR_ERR_OR_ZERO(dev); } static void cpuid_device_destroy(int cpu) diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 94d857fb1033..f5d0730e7b08 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -122,9 +122,6 @@ static void init_espfix_random(void) void __init init_espfix_bsp(void) { pgd_t *pgd_p; - pteval_t ptemask; - - ptemask = __supported_pte_mask; /* Install the espfix pud into the kernel page directory */ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 922d28581024..6307a0f0cf17 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -59,78 +59,78 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%*s: ", prec, "NMI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->__nmi_count); - seq_printf(p, " Non-maskable interrupts\n"); + seq_puts(p, " Non-maskable interrupts\n"); #ifdef CONFIG_X86_LOCAL_APIC seq_printf(p, "%*s: ", prec, "LOC"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs); - seq_printf(p, " Local timer interrupts\n"); + seq_puts(p, " Local timer interrupts\n"); seq_printf(p, "%*s: ", prec, "SPU"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count); - seq_printf(p, " Spurious interrupts\n"); + seq_puts(p, " Spurious interrupts\n"); seq_printf(p, "%*s: ", prec, "PMI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs); - seq_printf(p, " Performance monitoring interrupts\n"); + seq_puts(p, " Performance monitoring interrupts\n"); seq_printf(p, "%*s: ", prec, "IWI"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs); - seq_printf(p, " IRQ work interrupts\n"); + seq_puts(p, " IRQ work interrupts\n"); seq_printf(p, "%*s: ", prec, "RTR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count); - seq_printf(p, " APIC ICR read retries\n"); + seq_puts(p, " APIC ICR read retries\n"); #endif if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis); - seq_printf(p, " Platform interrupts\n"); + seq_puts(p, " Platform interrupts\n"); } #ifdef CONFIG_SMP seq_printf(p, "%*s: ", prec, "RES"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count); - seq_printf(p, " Rescheduling interrupts\n"); + seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - irq_stats(j)->irq_tlb_count); - seq_printf(p, " Function call interrupts\n"); + seq_puts(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count); - seq_printf(p, " TLB shootdowns\n"); + seq_puts(p, " TLB shootdowns\n"); #endif #ifdef CONFIG_X86_THERMAL_VECTOR seq_printf(p, "%*s: ", prec, "TRM"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count); - seq_printf(p, " Thermal event interrupts\n"); + seq_puts(p, " Thermal event interrupts\n"); #endif #ifdef CONFIG_X86_MCE_THRESHOLD seq_printf(p, "%*s: ", prec, "THR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count); - seq_printf(p, " Threshold APIC interrupts\n"); + seq_puts(p, " Threshold APIC interrupts\n"); #endif #ifdef CONFIG_X86_MCE seq_printf(p, "%*s: ", prec, "MCE"); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(mce_exception_count, j)); - seq_printf(p, " Machine check exceptions\n"); + seq_puts(p, " Machine check exceptions\n"); seq_printf(p, "%*s: ", prec, "MCP"); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(mce_poll_count, j)); - seq_printf(p, " Machine check polls\n"); + seq_puts(p, " Machine check polls\n"); #endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) seq_printf(p, "%*s: ", prec, "THR"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count); - seq_printf(p, " Hypervisor callback interrupts\n"); + seq_puts(p, " Hypervisor callback interrupts\n"); #endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index c9603ac80de5..113e70784854 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -22,6 +22,8 @@ * an SMP box will direct the access to CPU %d. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> @@ -50,11 +52,11 @@ static loff_t msr_seek(struct file *file, loff_t offset, int orig) mutex_lock(&inode->i_mutex); switch (orig) { - case 0: + case SEEK_SET: file->f_pos = offset; ret = file->f_pos; break; - case 1: + case SEEK_CUR: file->f_pos += offset; ret = file->f_pos; break; @@ -206,7 +208,7 @@ static int msr_device_create(int cpu) dev = device_create(msr_class, NULL, MKDEV(MSR_MAJOR, cpu), NULL, "msr%d", cpu); - return IS_ERR(dev) ? PTR_ERR(dev) : 0; + return PTR_ERR_OR_ZERO(dev); } static void msr_device_destroy(int cpu) @@ -248,8 +250,7 @@ static int __init msr_init(void) i = 0; if (__register_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr", &msr_fops)) { - printk(KERN_ERR "msr: unable to get major %d for msr\n", - MSR_MAJOR); + pr_err("unable to get major %d for msr\n", MSR_MAJOR); err = -EBUSY; goto out; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 214245d6b996..ab4734e5411d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1192,9 +1192,7 @@ void __init setup_arch(char **cmdline_p) tboot_probe(); -#ifdef CONFIG_X86_64 map_vsyscall(); -#endif generic_apic_probe(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 5cdff0357746..e4fcb87ba7a6 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -30,7 +30,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number); #define BOOT_PERCPU_OFFSET 0 #endif -DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET; +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET; EXPORT_PER_CPU_SYMBOL(this_cpu_off); unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 668d8f2a8781..7a8f5845e8eb 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -99,7 +99,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map); DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); /* Per CPU bogomips and other parameters */ -DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); +DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; diff --git a/arch/x86/kernel/sysfb.c b/arch/x86/kernel/sysfb.c index 193ec2ce46c7..160386e9fc17 100644 --- a/arch/x86/kernel/sysfb.c +++ b/arch/x86/kernel/sysfb.c @@ -67,7 +67,7 @@ static __init int sysfb_init(void) pd = platform_device_register_resndata(NULL, name, 0, NULL, 0, si, sizeof(*si)); - return IS_ERR(pd) ? PTR_ERR(pd) : 0; + return PTR_ERR_OR_ZERO(pd); } /* must execute after PCI subsystem for EFI quirks */ diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 86179d409893..764a29f84de7 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -88,8 +88,5 @@ __init int create_simplefb(const struct screen_info *si, pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0, &res, 1, mode, sizeof(*mode)); - if (IS_ERR(pd)) - return PTR_ERR(pd); - - return 0; + return PTR_ERR_OR_ZERO(pd); } diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 0fa29609b2c4..25adc0e16eaa 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -23,7 +23,7 @@ #include <asm/time.h> #ifdef CONFIG_X86_64 -__visible DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES; +__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES; #endif unsigned long profile_pc(struct pt_regs *regs) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 49edf2dd3613..00bf300fd846 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -186,6 +186,8 @@ SECTIONS * start another segment - init. */ PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu) + ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START, + "per-CPU data too large - increase CONFIG_PHYSICAL_START") #endif INIT_TEXT_SECTION(PAGE_SIZE) diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 957779f4eb40..2dcc6ff6fdcc 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -1,59 +1,43 @@ /* + * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net> + * + * Based on the original implementation which is: * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. * - * [ NOTE: this mechanism is now deprecated in favor of the vDSO. ] + * Parts of the original code have been moved to arch/x86/vdso/vma.c + * + * This file implements vsyscall emulation. vsyscalls are a legacy ABI: + * Userspace can request certain kernel services by calling fixed + * addresses. This concept is problematic: * - * Thanks to hpa@transmeta.com for some useful hint. - * Special thanks to Ingo Molnar for his early experience with - * a different vsyscall implementation for Linux/IA32 and for the name. + * - It interferes with ASLR. + * - It's awkward to write code that lives in kernel addresses but is + * callable by userspace at fixed addresses. + * - The whole concept is impossible for 32-bit compat userspace. + * - UML cannot easily virtualize a vsyscall. * - * vsyscall 1 is located at -10Mbyte, vsyscall 2 is located - * at virtual address -10Mbyte+1024bytes etc... There are at max 4 - * vsyscalls. One vsyscall can reserve more than 1 slot to avoid - * jumping out of line if necessary. We cannot add more with this - * mechanism because older kernels won't return -ENOSYS. + * As of mid-2014, I believe that there is no new userspace code that + * will use a vsyscall if the vDSO is present. I hope that there will + * soon be no new userspace code that will ever use a vsyscall. * - * Note: the concept clashes with user mode linux. UML users should - * use the vDSO. + * The code in this file emulates vsyscalls when notified of a page + * fault to a vsyscall address. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/time.h> -#include <linux/init.h> #include <linux/kernel.h> #include <linux/timer.h> -#include <linux/seqlock.h> -#include <linux/jiffies.h> -#include <linux/sysctl.h> -#include <linux/topology.h> -#include <linux/timekeeper_internal.h> -#include <linux/getcpu.h> -#include <linux/cpu.h> -#include <linux/smp.h> -#include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/ratelimit.h> #include <asm/vsyscall.h> -#include <asm/pgtable.h> -#include <asm/compat.h> -#include <asm/page.h> #include <asm/unistd.h> #include <asm/fixmap.h> -#include <asm/errno.h> -#include <asm/io.h> -#include <asm/segment.h> -#include <asm/desc.h> -#include <asm/topology.h> #include <asm/traps.h> #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -DEFINE_VVAR(int, vgetcpu_mode); - static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; static int __init vsyscall_setup(char *str) @@ -222,6 +206,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) "seccomp tried to change syscall nr or ip"); do_exit(SIGSYS); } + regs->orig_ax = -1; if (tmp) goto do_ret; /* skip requested */ @@ -284,46 +269,54 @@ sigsegv: } /* - * Assume __initcall executes before all user space. Hopefully kmod - * doesn't violate that. We'll find out if it does. + * A pseudo VMA to allow ptrace access for the vsyscall page. This only + * covers the 64bit vsyscall page now. 32bit has a real VMA now and does + * not need special handling anymore: */ -static void vsyscall_set_cpu(int cpu) +static const char *gate_vma_name(struct vm_area_struct *vma) { - unsigned long d; - unsigned long node = 0; -#ifdef CONFIG_NUMA - node = cpu_to_node(cpu); -#endif - if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP)) - write_rdtscp_aux((node << 12) | cpu); - - /* - * Store cpu number in limit so that it can be loaded quickly - * in user space in vgetcpu. (12 bits for the CPU and 8 bits for the node) - */ - d = 0x0f40000000000ULL; - d |= cpu; - d |= (node & 0xf) << 12; - d |= (node >> 4) << 48; - - write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); + return "[vsyscall]"; } - -static void cpu_vsyscall_init(void *arg) +static struct vm_operations_struct gate_vma_ops = { + .name = gate_vma_name, +}; +static struct vm_area_struct gate_vma = { + .vm_start = VSYSCALL_ADDR, + .vm_end = VSYSCALL_ADDR + PAGE_SIZE, + .vm_page_prot = PAGE_READONLY_EXEC, + .vm_flags = VM_READ | VM_EXEC, + .vm_ops = &gate_vma_ops, +}; + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { - /* preemption should be already off */ - vsyscall_set_cpu(raw_smp_processor_id()); +#ifdef CONFIG_IA32_EMULATION + if (!mm || mm->context.ia32_compat) + return NULL; +#endif + if (vsyscall_mode == NONE) + return NULL; + return &gate_vma; } -static int -cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg) +int in_gate_area(struct mm_struct *mm, unsigned long addr) { - long cpu = (long)arg; + struct vm_area_struct *vma = get_gate_vma(mm); + + if (!vma) + return 0; - if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) - smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1); + return (addr >= vma->vm_start) && (addr < vma->vm_end); +} - return NOTIFY_DONE; +/* + * Use this when you have no reliable mm, typically from interrupt + * context. It is less reliable than using a task's mm and may give + * false positives. + */ +int in_gate_area_no_mm(unsigned long addr) +{ + return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; } void __init map_vsyscall(void) @@ -331,24 +324,12 @@ void __init map_vsyscall(void) extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + if (vsyscall_mode != NONE) + __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, + vsyscall_mode == NATIVE + ? PAGE_KERNEL_VSYSCALL + : PAGE_KERNEL_VVAR); + BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); } - -static int __init vsyscall_init(void) -{ - cpu_notifier_register_begin(); - - on_each_cpu(cpu_vsyscall_init, NULL, 1); - /* notifier priority > KVM */ - __hotcpu_notifier(cpu_vsyscall_notifier, 30); - - cpu_notifier_register_done(); - - return 0; -} -__initcall(vsyscall_init); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 95a427e57887..f0cedf3395af 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -76,6 +76,9 @@ static struct addr_marker address_markers[] = { # ifdef CONFIG_X86_ESPFIX64 { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, # endif +# ifdef CONFIG_EFI + { EFI_VA_END, "EFI Runtime Services" }, +# endif { __START_KERNEL_map, "High Kernel Mapping" }, { MODULES_VADDR, "Modules" }, { MODULES_END, "End Modules" }, @@ -126,7 +129,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) if (!pgprot_val(prot)) { /* Not present */ - pt_dump_cont_printf(m, dmsg, " "); + pt_dump_cont_printf(m, dmsg, " "); } else { if (pr & _PAGE_USER) pt_dump_cont_printf(m, dmsg, "USR "); @@ -145,18 +148,16 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) else pt_dump_cont_printf(m, dmsg, " "); - /* Bit 9 has a different meaning on level 3 vs 4 */ - if (level <= 3) { - if (pr & _PAGE_PSE) - pt_dump_cont_printf(m, dmsg, "PSE "); - else - pt_dump_cont_printf(m, dmsg, " "); - } else { - if (pr & _PAGE_PAT) - pt_dump_cont_printf(m, dmsg, "pat "); - else - pt_dump_cont_printf(m, dmsg, " "); - } + /* Bit 7 has a different meaning on level 3 vs 4 */ + if (level <= 3 && pr & _PAGE_PSE) + pt_dump_cont_printf(m, dmsg, "PSE "); + else + pt_dump_cont_printf(m, dmsg, " "); + if ((level == 4 && pr & _PAGE_PAT) || + ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE)) + pt_dump_cont_printf(m, dmsg, "pat "); + else + pt_dump_cont_printf(m, dmsg, " "); if (pr & _PAGE_GLOBAL) pt_dump_cont_printf(m, dmsg, "GLB "); else diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 66dba36f2343..82b41d56bb98 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -27,6 +27,35 @@ #include "mm_internal.h" +/* + * Tables translating between page_cache_type_t and pte encoding. + * Minimal supported modes are defined statically, modified if more supported + * cache modes are available. + * Index into __cachemode2pte_tbl is the cachemode. + * Index into __pte2cachemode_tbl are the caching attribute bits of the pte + * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2. + */ +uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { + [_PAGE_CACHE_MODE_WB] = 0, + [_PAGE_CACHE_MODE_WC] = _PAGE_PWT, + [_PAGE_CACHE_MODE_UC_MINUS] = _PAGE_PCD, + [_PAGE_CACHE_MODE_UC] = _PAGE_PCD | _PAGE_PWT, + [_PAGE_CACHE_MODE_WT] = _PAGE_PCD, + [_PAGE_CACHE_MODE_WP] = _PAGE_PCD, +}; +EXPORT_SYMBOL_GPL(__cachemode2pte_tbl); +uint8_t __pte2cachemode_tbl[8] = { + [__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB, + [__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(_PAGE_PCD)] = _PAGE_CACHE_MODE_UC_MINUS, + [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD)] = _PAGE_CACHE_MODE_UC, + [__pte2cm_idx(_PAGE_PAT)] = _PAGE_CACHE_MODE_WB, + [__pte2cm_idx(_PAGE_PWT | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, + [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, +}; +EXPORT_SYMBOL_GPL(__pte2cachemode_tbl); + static unsigned long __initdata pgt_buf_start; static unsigned long __initdata pgt_buf_end; static unsigned long __initdata pgt_buf_top; @@ -687,3 +716,11 @@ void __init zone_sizes_init(void) free_area_init_nodes(max_zone_pfns); } +void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) +{ + /* entry 0 MUST be WB (hardwired to speed up translations) */ + BUG_ON(!entry && cache != _PAGE_CACHE_MODE_WB); + + __cachemode2pte_tbl[cache] = __cm_idx2pte(entry); + __pte2cachemode_tbl[entry] = cache; +} diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 4e5dfec750fc..30eb05ae7061 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -52,7 +52,6 @@ #include <asm/numa.h> #include <asm/cacheflush.h> #include <asm/init.h> -#include <asm/uv/uv.h> #include <asm/setup.h> #include "mm_internal.h" @@ -338,12 +337,15 @@ pte_t * __init populate_extra_pte(unsigned long vaddr) * Create large page table mappings for a range of physical addresses. */ static void __init __init_extra_mapping(unsigned long phys, unsigned long size, - pgprot_t prot) + enum page_cache_mode cache) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; + pgprot_t prot; + pgprot_val(prot) = pgprot_val(PAGE_KERNEL_LARGE) | + pgprot_val(pgprot_4k_2_large(cachemode2pgprot(cache))); BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK)); for (; size; phys += PMD_SIZE, size -= PMD_SIZE) { pgd = pgd_offset_k((unsigned long)__va(phys)); @@ -366,12 +368,12 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size, void __init init_extra_mapping_wb(unsigned long phys, unsigned long size) { - __init_extra_mapping(phys, size, PAGE_KERNEL_LARGE); + __init_extra_mapping(phys, size, _PAGE_CACHE_MODE_WB); } void __init init_extra_mapping_uc(unsigned long phys, unsigned long size) { - __init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE); + __init_extra_mapping(phys, size, _PAGE_CACHE_MODE_UC); } /* @@ -1202,66 +1204,15 @@ int kern_addr_valid(unsigned long addr) return pfn_valid(pte_pfn(*pte)); } -/* - * A pseudo VMA to allow ptrace access for the vsyscall page. This only - * covers the 64bit vsyscall page now. 32bit has a real VMA now and does - * not need special handling anymore: - */ -static const char *gate_vma_name(struct vm_area_struct *vma) -{ - return "[vsyscall]"; -} -static struct vm_operations_struct gate_vma_ops = { - .name = gate_vma_name, -}; -static struct vm_area_struct gate_vma = { - .vm_start = VSYSCALL_ADDR, - .vm_end = VSYSCALL_ADDR + PAGE_SIZE, - .vm_page_prot = PAGE_READONLY_EXEC, - .vm_flags = VM_READ | VM_EXEC, - .vm_ops = &gate_vma_ops, -}; - -struct vm_area_struct *get_gate_vma(struct mm_struct *mm) -{ -#ifdef CONFIG_IA32_EMULATION - if (!mm || mm->context.ia32_compat) - return NULL; -#endif - return &gate_vma; -} - -int in_gate_area(struct mm_struct *mm, unsigned long addr) -{ - struct vm_area_struct *vma = get_gate_vma(mm); - - if (!vma) - return 0; - - return (addr >= vma->vm_start) && (addr < vma->vm_end); -} - -/* - * Use this when you have no reliable mm, typically from interrupt - * context. It is less reliable than using a task's mm and may give - * false positives. - */ -int in_gate_area_no_mm(unsigned long addr) -{ - return (addr & PAGE_MASK) == VSYSCALL_ADDR; -} - static unsigned long probe_memory_block_size(void) { /* start from 2g */ unsigned long bz = 1UL<<31; -#ifdef CONFIG_X86_UV - if (is_uv_system()) { - printk(KERN_INFO "UV: memory block size 2GB\n"); + if (totalram_pages >= (64ULL << (30 - PAGE_SHIFT))) { + pr_info("Using 2GB memory block size for large-memory system\n"); return 2UL * 1024 * 1024 * 1024; } -#endif /* less than 64g installed */ if ((max_pfn << PAGE_SHIFT) < (16UL << 32)) diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 7b179b499fa3..9ca35fc60cfe 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -33,17 +33,17 @@ static int is_io_mapping_possible(resource_size_t base, unsigned long size) int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot) { - unsigned long flag = _PAGE_CACHE_WC; + enum page_cache_mode pcm = _PAGE_CACHE_MODE_WC; int ret; if (!is_io_mapping_possible(base, size)) return -EINVAL; - ret = io_reserve_memtype(base, base + size, &flag); + ret = io_reserve_memtype(base, base + size, &pcm); if (ret) return ret; - *prot = __pgprot(__PAGE_KERNEL | flag); + *prot = __pgprot(__PAGE_KERNEL | cachemode2protval(pcm)); return 0; } EXPORT_SYMBOL_GPL(iomap_create_wc); @@ -82,8 +82,10 @@ iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) * MTRR is UC or WC. UC_MINUS gets the real intention, of the * user, which is "WC if the MTRR is WC, UC if you can't do that." */ - if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC)) - prot = PAGE_KERNEL_UC_MINUS; + if (!pat_enabled && pgprot_val(prot) == + (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC))) + prot = __pgprot(__PAGE_KERNEL | + cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)); return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, prot); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index b12f43c192cf..fdf617c00e2f 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -29,20 +29,20 @@ * conflicts. */ int ioremap_change_attr(unsigned long vaddr, unsigned long size, - unsigned long prot_val) + enum page_cache_mode pcm) { unsigned long nrpages = size >> PAGE_SHIFT; int err; - switch (prot_val) { - case _PAGE_CACHE_UC: + switch (pcm) { + case _PAGE_CACHE_MODE_UC: default: err = _set_memory_uc(vaddr, nrpages); break; - case _PAGE_CACHE_WC: + case _PAGE_CACHE_MODE_WC: err = _set_memory_wc(vaddr, nrpages); break; - case _PAGE_CACHE_WB: + case _PAGE_CACHE_MODE_WB: err = _set_memory_wb(vaddr, nrpages); break; } @@ -75,14 +75,14 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, * caller shouldn't need to know that small detail. */ static void __iomem *__ioremap_caller(resource_size_t phys_addr, - unsigned long size, unsigned long prot_val, void *caller) + unsigned long size, enum page_cache_mode pcm, void *caller) { unsigned long offset, vaddr; resource_size_t pfn, last_pfn, last_addr; const resource_size_t unaligned_phys_addr = phys_addr; const unsigned long unaligned_size = size; struct vm_struct *area; - unsigned long new_prot_val; + enum page_cache_mode new_pcm; pgprot_t prot; int retval; void __iomem *ret_addr; @@ -134,38 +134,40 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, size = PAGE_ALIGN(last_addr+1) - phys_addr; retval = reserve_memtype(phys_addr, (u64)phys_addr + size, - prot_val, &new_prot_val); + pcm, &new_pcm); if (retval) { printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval); return NULL; } - if (prot_val != new_prot_val) { - if (!is_new_memtype_allowed(phys_addr, size, - prot_val, new_prot_val)) { + if (pcm != new_pcm) { + if (!is_new_memtype_allowed(phys_addr, size, pcm, new_pcm)) { printk(KERN_ERR - "ioremap error for 0x%llx-0x%llx, requested 0x%lx, got 0x%lx\n", + "ioremap error for 0x%llx-0x%llx, requested 0x%x, got 0x%x\n", (unsigned long long)phys_addr, (unsigned long long)(phys_addr + size), - prot_val, new_prot_val); + pcm, new_pcm); goto err_free_memtype; } - prot_val = new_prot_val; + pcm = new_pcm; } - switch (prot_val) { - case _PAGE_CACHE_UC: + prot = PAGE_KERNEL_IO; + switch (pcm) { + case _PAGE_CACHE_MODE_UC: default: - prot = PAGE_KERNEL_IO_NOCACHE; + prot = __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_UC)); break; - case _PAGE_CACHE_UC_MINUS: - prot = PAGE_KERNEL_IO_UC_MINUS; + case _PAGE_CACHE_MODE_UC_MINUS: + prot = __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)); break; - case _PAGE_CACHE_WC: - prot = PAGE_KERNEL_IO_WC; + case _PAGE_CACHE_MODE_WC: + prot = __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_WC)); break; - case _PAGE_CACHE_WB: - prot = PAGE_KERNEL_IO; + case _PAGE_CACHE_MODE_WB: break; } @@ -178,7 +180,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; - if (kernel_map_sync_memtype(phys_addr, size, prot_val)) + if (kernel_map_sync_memtype(phys_addr, size, pcm)) goto err_free_area; if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) @@ -227,14 +229,14 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) { /* * Ideally, this should be: - * pat_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS; + * pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS; * * Till we fix all X drivers to use ioremap_wc(), we will use * UC MINUS. */ - unsigned long val = _PAGE_CACHE_UC_MINUS; + enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS; - return __ioremap_caller(phys_addr, size, val, + return __ioremap_caller(phys_addr, size, pcm, __builtin_return_address(0)); } EXPORT_SYMBOL(ioremap_nocache); @@ -252,7 +254,7 @@ EXPORT_SYMBOL(ioremap_nocache); void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size) { if (pat_enabled) - return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC, + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC, __builtin_return_address(0)); else return ioremap_nocache(phys_addr, size); @@ -261,7 +263,7 @@ EXPORT_SYMBOL(ioremap_wc); void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) { - return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WB, + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB, __builtin_return_address(0)); } EXPORT_SYMBOL(ioremap_cache); @@ -269,7 +271,8 @@ EXPORT_SYMBOL(ioremap_cache); void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, unsigned long prot_val) { - return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK), + return __ioremap_caller(phys_addr, size, + pgprot2cachemode(__pgprot(prot_val)), __builtin_return_address(0)); } EXPORT_SYMBOL(ioremap_prot); diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h index 6b563a118891..62474ba66c8e 100644 --- a/arch/x86/mm/mm_internal.h +++ b/arch/x86/mm/mm_internal.h @@ -16,4 +16,6 @@ void zone_sizes_init(void); extern int after_bootmem; +void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache); + #endif /* __X86_MM_INTERNAL_H */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 36de293caf25..a3a5d46605d2 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -485,14 +485,23 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, /* * We are safe now. Check whether the new pgprot is the same: + * Convert protection attributes to 4k-format, as cpa->mask* are set + * up accordingly. */ old_pte = *kpte; - old_prot = req_prot = pte_pgprot(old_pte); + old_prot = req_prot = pgprot_large_2_4k(pte_pgprot(old_pte)); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); /* + * req_prot is in format of 4k pages. It must be converted to large + * page format: the caching mode includes the PAT bit located at + * different bit positions in the two formats. + */ + req_prot = pgprot_4k_2_large(req_prot); + + /* * Set the PSE and GLOBAL flags only if the PRESENT flag is * set otherwise pmd_present/pmd_huge will return true even on * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL @@ -585,13 +594,10 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, paravirt_alloc_pte(&init_mm, page_to_pfn(base)); ref_prot = pte_pgprot(pte_clrhuge(*kpte)); - /* - * If we ever want to utilize the PAT bit, we need to - * update this function to make sure it's converted from - * bit 12 to bit 7 when we cross from the 2MB level to - * the 4K level: - */ - WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE); + + /* promote PAT bit to correct position */ + if (level == PG_LEVEL_2M) + ref_prot = pgprot_large_2_4k(ref_prot); #ifdef CONFIG_X86_64 if (level == PG_LEVEL_1G) { @@ -879,6 +885,7 @@ static int populate_pmd(struct cpa_data *cpa, { unsigned int cur_pages = 0; pmd_t *pmd; + pgprot_t pmd_pgprot; /* * Not on a 2M boundary? @@ -910,6 +917,8 @@ static int populate_pmd(struct cpa_data *cpa, if (num_pages == cur_pages) return cur_pages; + pmd_pgprot = pgprot_4k_2_large(pgprot); + while (end - start >= PMD_SIZE) { /* @@ -921,7 +930,8 @@ static int populate_pmd(struct cpa_data *cpa, pmd = pmd_offset(pud, start); - set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot))); + set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | + massage_pgprot(pmd_pgprot))); start += PMD_SIZE; cpa->pfn += PMD_SIZE; @@ -949,6 +959,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, pud_t *pud; unsigned long end; int cur_pages = 0; + pgprot_t pud_pgprot; end = start + (cpa->numpages << PAGE_SHIFT); @@ -986,12 +997,14 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, return cur_pages; pud = pud_offset(pgd, start); + pud_pgprot = pgprot_4k_2_large(pgprot); /* * Map everything starting from the Gb boundary, possibly with 1G pages */ while (end - start >= PUD_SIZE) { - set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot))); + set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | + massage_pgprot(pud_pgprot))); start += PUD_SIZE; cpa->pfn += PUD_SIZE; @@ -1304,12 +1317,6 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) return 0; } -static inline int cache_attr(pgprot_t attr) -{ - return pgprot_val(attr) & - (_PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PWT | _PAGE_PCD); -} - static int change_page_attr_set_clr(unsigned long *addr, int numpages, pgprot_t mask_set, pgprot_t mask_clr, int force_split, int in_flag, @@ -1390,7 +1397,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, * No need to flush, when we did not set any of the caching * attributes: */ - cache = cache_attr(mask_set); + cache = !!pgprot2cachemode(mask_set); /* * On success we use CLFLUSH, when the CPU supports it to @@ -1445,7 +1452,8 @@ int _set_memory_uc(unsigned long addr, int numpages) * for now UC MINUS. see comments in ioremap_nocache() */ return change_page_attr_set(&addr, numpages, - __pgprot(_PAGE_CACHE_UC_MINUS), 0); + cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), + 0); } int set_memory_uc(unsigned long addr, int numpages) @@ -1456,7 +1464,7 @@ int set_memory_uc(unsigned long addr, int numpages) * for now UC MINUS. see comments in ioremap_nocache() */ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_UC_MINUS, NULL); + _PAGE_CACHE_MODE_UC_MINUS, NULL); if (ret) goto out_err; @@ -1474,7 +1482,7 @@ out_err: EXPORT_SYMBOL(set_memory_uc); static int _set_memory_array(unsigned long *addr, int addrinarray, - unsigned long new_type) + enum page_cache_mode new_type) { int i, j; int ret; @@ -1490,11 +1498,13 @@ static int _set_memory_array(unsigned long *addr, int addrinarray, } ret = change_page_attr_set(addr, addrinarray, - __pgprot(_PAGE_CACHE_UC_MINUS), 1); + cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), + 1); - if (!ret && new_type == _PAGE_CACHE_WC) + if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(addr, addrinarray, - __pgprot(_PAGE_CACHE_WC), + cachemode2pgprot( + _PAGE_CACHE_MODE_WC), __pgprot(_PAGE_CACHE_MASK), 0, CPA_ARRAY, NULL); if (ret) @@ -1511,13 +1521,13 @@ out_free: int set_memory_array_uc(unsigned long *addr, int addrinarray) { - return _set_memory_array(addr, addrinarray, _PAGE_CACHE_UC_MINUS); + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_UC_MINUS); } EXPORT_SYMBOL(set_memory_array_uc); int set_memory_array_wc(unsigned long *addr, int addrinarray) { - return _set_memory_array(addr, addrinarray, _PAGE_CACHE_WC); + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WC); } EXPORT_SYMBOL(set_memory_array_wc); @@ -1527,10 +1537,12 @@ int _set_memory_wc(unsigned long addr, int numpages) unsigned long addr_copy = addr; ret = change_page_attr_set(&addr, numpages, - __pgprot(_PAGE_CACHE_UC_MINUS), 0); + cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), + 0); if (!ret) { ret = change_page_attr_set_clr(&addr_copy, numpages, - __pgprot(_PAGE_CACHE_WC), + cachemode2pgprot( + _PAGE_CACHE_MODE_WC), __pgprot(_PAGE_CACHE_MASK), 0, 0, NULL); } @@ -1545,7 +1557,7 @@ int set_memory_wc(unsigned long addr, int numpages) return set_memory_uc(addr, numpages); ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_WC, NULL); + _PAGE_CACHE_MODE_WC, NULL); if (ret) goto out_err; @@ -1564,6 +1576,7 @@ EXPORT_SYMBOL(set_memory_wc); int _set_memory_wb(unsigned long addr, int numpages) { + /* WB cache mode is hard wired to all cache attribute bits being 0 */ return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_CACHE_MASK), 0); } @@ -1586,6 +1599,7 @@ int set_memory_array_wb(unsigned long *addr, int addrinarray) int i; int ret; + /* WB cache mode is hard wired to all cache attribute bits being 0 */ ret = change_page_attr_clear(addr, addrinarray, __pgprot(_PAGE_CACHE_MASK), 1); if (ret) @@ -1648,7 +1662,7 @@ int set_pages_uc(struct page *page, int numpages) EXPORT_SYMBOL(set_pages_uc); static int _set_pages_array(struct page **pages, int addrinarray, - unsigned long new_type) + enum page_cache_mode new_type) { unsigned long start; unsigned long end; @@ -1666,10 +1680,11 @@ static int _set_pages_array(struct page **pages, int addrinarray, } ret = cpa_set_pages_array(pages, addrinarray, - __pgprot(_PAGE_CACHE_UC_MINUS)); - if (!ret && new_type == _PAGE_CACHE_WC) + cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS)); + if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(NULL, addrinarray, - __pgprot(_PAGE_CACHE_WC), + cachemode2pgprot( + _PAGE_CACHE_MODE_WC), __pgprot(_PAGE_CACHE_MASK), 0, CPA_PAGES_ARRAY, pages); if (ret) @@ -1689,13 +1704,13 @@ err_out: int set_pages_array_uc(struct page **pages, int addrinarray) { - return _set_pages_array(pages, addrinarray, _PAGE_CACHE_UC_MINUS); + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_UC_MINUS); } EXPORT_SYMBOL(set_pages_array_uc); int set_pages_array_wc(struct page **pages, int addrinarray) { - return _set_pages_array(pages, addrinarray, _PAGE_CACHE_WC); + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WC); } EXPORT_SYMBOL(set_pages_array_wc); @@ -1714,6 +1729,7 @@ int set_pages_array_wb(struct page **pages, int addrinarray) unsigned long end; int i; + /* WB cache mode is hard wired to all cache attribute bits being 0 */ retval = cpa_clear_pages_array(pages, addrinarray, __pgprot(_PAGE_CACHE_MASK)); if (retval) diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 657438858e83..edf299c8ff6c 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -31,6 +31,7 @@ #include <asm/io.h> #include "pat_internal.h" +#include "mm_internal.h" #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; @@ -66,6 +67,75 @@ __setup("debugpat", pat_debug_setup); static u64 __read_mostly boot_pat_state; +#ifdef CONFIG_X86_PAT +/* + * X86 PAT uses page flags WC and Uncached together to keep track of + * memory type of pages that have backing page struct. X86 PAT supports 3 + * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and + * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not + * been changed from its default (value of -1 used to denote this). + * Note we do not support _PAGE_CACHE_MODE_UC here. + */ + +#define _PGMT_DEFAULT 0 +#define _PGMT_WC (1UL << PG_arch_1) +#define _PGMT_UC_MINUS (1UL << PG_uncached) +#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_CLEAR_MASK (~_PGMT_MASK) + +static inline enum page_cache_mode get_page_memtype(struct page *pg) +{ + unsigned long pg_flags = pg->flags & _PGMT_MASK; + + if (pg_flags == _PGMT_DEFAULT) + return -1; + else if (pg_flags == _PGMT_WC) + return _PAGE_CACHE_MODE_WC; + else if (pg_flags == _PGMT_UC_MINUS) + return _PAGE_CACHE_MODE_UC_MINUS; + else + return _PAGE_CACHE_MODE_WB; +} + +static inline void set_page_memtype(struct page *pg, + enum page_cache_mode memtype) +{ + unsigned long memtype_flags; + unsigned long old_flags; + unsigned long new_flags; + + switch (memtype) { + case _PAGE_CACHE_MODE_WC: + memtype_flags = _PGMT_WC; + break; + case _PAGE_CACHE_MODE_UC_MINUS: + memtype_flags = _PGMT_UC_MINUS; + break; + case _PAGE_CACHE_MODE_WB: + memtype_flags = _PGMT_WB; + break; + default: + memtype_flags = _PGMT_DEFAULT; + break; + } + + do { + old_flags = pg->flags; + new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags; + } while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags); +} +#else +static inline enum page_cache_mode get_page_memtype(struct page *pg) +{ + return -1; +} +static inline void set_page_memtype(struct page *pg, + enum page_cache_mode memtype) +{ +} +#endif + enum { PAT_UC = 0, /* uncached */ PAT_WC = 1, /* Write combining */ @@ -75,6 +145,52 @@ enum { PAT_UC_MINUS = 7, /* UC, but can be overriden by MTRR */ }; +#define CM(c) (_PAGE_CACHE_MODE_ ## c) + +static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) +{ + enum page_cache_mode cache; + char *cache_mode; + + switch (pat_val) { + case PAT_UC: cache = CM(UC); cache_mode = "UC "; break; + case PAT_WC: cache = CM(WC); cache_mode = "WC "; break; + case PAT_WT: cache = CM(WT); cache_mode = "WT "; break; + case PAT_WP: cache = CM(WP); cache_mode = "WP "; break; + case PAT_WB: cache = CM(WB); cache_mode = "WB "; break; + case PAT_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break; + default: cache = CM(WB); cache_mode = "WB "; break; + } + + memcpy(msg, cache_mode, 4); + + return cache; +} + +#undef CM + +/* + * Update the cache mode to pgprot translation tables according to PAT + * configuration. + * Using lower indices is preferred, so we start with highest index. + */ +void pat_init_cache_modes(void) +{ + int i; + enum page_cache_mode cache; + char pat_msg[33]; + u64 pat; + + rdmsrl(MSR_IA32_CR_PAT, pat); + pat_msg[32] = 0; + for (i = 7; i >= 0; i--) { + cache = pat_get_cache_mode((pat >> (i * 8)) & 7, + pat_msg + 4 * i); + update_cache_mode_entry(i, cache); + } + pr_info("PAT configuration [0-7]: %s\n", pat_msg); +} + #define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) void pat_init(void) @@ -124,8 +240,7 @@ void pat_init(void) wrmsrl(MSR_IA32_CR_PAT, pat); if (boot_cpu) - printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n", - smp_processor_id(), boot_pat_state, pat); + pat_init_cache_modes(); } #undef PAT @@ -139,20 +254,21 @@ static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */ * The intersection is based on "Effective Memory Type" tables in IA-32 * SDM vol 3a */ -static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) +static unsigned long pat_x_mtrr_type(u64 start, u64 end, + enum page_cache_mode req_type) { /* * Look for MTRR hint to get the effective type in case where PAT * request is for WB. */ - if (req_type == _PAGE_CACHE_WB) { + if (req_type == _PAGE_CACHE_MODE_WB) { u8 mtrr_type; mtrr_type = mtrr_type_lookup(start, end); if (mtrr_type != MTRR_TYPE_WRBACK) - return _PAGE_CACHE_UC_MINUS; + return _PAGE_CACHE_MODE_UC_MINUS; - return _PAGE_CACHE_WB; + return _PAGE_CACHE_MODE_WB; } return req_type; @@ -207,25 +323,26 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end) * - Find the memtype of all the pages in the range, look for any conflicts * - In case of no conflicts, set the new memtype for pages in the range */ -static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type, - unsigned long *new_type) +static int reserve_ram_pages_type(u64 start, u64 end, + enum page_cache_mode req_type, + enum page_cache_mode *new_type) { struct page *page; u64 pfn; - if (req_type == _PAGE_CACHE_UC) { + if (req_type == _PAGE_CACHE_MODE_UC) { /* We do not support strong UC */ WARN_ON_ONCE(1); - req_type = _PAGE_CACHE_UC_MINUS; + req_type = _PAGE_CACHE_MODE_UC_MINUS; } for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) { - unsigned long type; + enum page_cache_mode type; page = pfn_to_page(pfn); type = get_page_memtype(page); if (type != -1) { - printk(KERN_INFO "reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%lx, req 0x%lx\n", + pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n", start, end - 1, type, req_type); if (new_type) *new_type = type; @@ -258,21 +375,21 @@ static int free_ram_pages_type(u64 start, u64 end) /* * req_type typically has one of the: - * - _PAGE_CACHE_WB - * - _PAGE_CACHE_WC - * - _PAGE_CACHE_UC_MINUS - * - _PAGE_CACHE_UC + * - _PAGE_CACHE_MODE_WB + * - _PAGE_CACHE_MODE_WC + * - _PAGE_CACHE_MODE_UC_MINUS + * - _PAGE_CACHE_MODE_UC * * If new_type is NULL, function will return an error if it cannot reserve the * region with req_type. If new_type is non-NULL, function will return * available type in new_type in case of no error. In case of any error * it will return a negative return value. */ -int reserve_memtype(u64 start, u64 end, unsigned long req_type, - unsigned long *new_type) +int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, + enum page_cache_mode *new_type) { struct memtype *new; - unsigned long actual_type; + enum page_cache_mode actual_type; int is_range_ram; int err = 0; @@ -281,10 +398,10 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, if (!pat_enabled) { /* This is identical to page table setting without PAT */ if (new_type) { - if (req_type == _PAGE_CACHE_WC) - *new_type = _PAGE_CACHE_UC_MINUS; + if (req_type == _PAGE_CACHE_MODE_WC) + *new_type = _PAGE_CACHE_MODE_UC_MINUS; else - *new_type = req_type & _PAGE_CACHE_MASK; + *new_type = req_type; } return 0; } @@ -292,7 +409,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, /* Low ISA region is always mapped WB in page table. No need to track */ if (x86_platform.is_untracked_pat_range(start, end)) { if (new_type) - *new_type = _PAGE_CACHE_WB; + *new_type = _PAGE_CACHE_MODE_WB; return 0; } @@ -302,7 +419,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, * tools and ACPI tools). Use WB request for WB memory and use * UC_MINUS otherwise. */ - actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK); + actual_type = pat_x_mtrr_type(start, end, req_type); if (new_type) *new_type = actual_type; @@ -394,12 +511,12 @@ int free_memtype(u64 start, u64 end) * * Only to be called when PAT is enabled * - * Returns _PAGE_CACHE_WB, _PAGE_CACHE_WC, _PAGE_CACHE_UC_MINUS or - * _PAGE_CACHE_UC + * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS + * or _PAGE_CACHE_MODE_UC */ -static unsigned long lookup_memtype(u64 paddr) +static enum page_cache_mode lookup_memtype(u64 paddr) { - int rettype = _PAGE_CACHE_WB; + enum page_cache_mode rettype = _PAGE_CACHE_MODE_WB; struct memtype *entry; if (x86_platform.is_untracked_pat_range(paddr, paddr + PAGE_SIZE)) @@ -414,7 +531,7 @@ static unsigned long lookup_memtype(u64 paddr) * default state and not reserved, and hence of type WB */ if (rettype == -1) - rettype = _PAGE_CACHE_WB; + rettype = _PAGE_CACHE_MODE_WB; return rettype; } @@ -425,7 +542,7 @@ static unsigned long lookup_memtype(u64 paddr) if (entry != NULL) rettype = entry->type; else - rettype = _PAGE_CACHE_UC_MINUS; + rettype = _PAGE_CACHE_MODE_UC_MINUS; spin_unlock(&memtype_lock); return rettype; @@ -442,11 +559,11 @@ static unsigned long lookup_memtype(u64 paddr) * On failure, returns non-zero */ int io_reserve_memtype(resource_size_t start, resource_size_t end, - unsigned long *type) + enum page_cache_mode *type) { resource_size_t size = end - start; - unsigned long req_type = *type; - unsigned long new_type; + enum page_cache_mode req_type = *type; + enum page_cache_mode new_type; int ret; WARN_ON_ONCE(iomem_map_sanity_check(start, size)); @@ -520,13 +637,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { - unsigned long flags = _PAGE_CACHE_WB; + enum page_cache_mode pcm = _PAGE_CACHE_MODE_WB; if (!range_is_allowed(pfn, size)) return 0; if (file->f_flags & O_DSYNC) - flags = _PAGE_CACHE_UC_MINUS; + pcm = _PAGE_CACHE_MODE_UC_MINUS; #ifdef CONFIG_X86_32 /* @@ -543,12 +660,12 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, boot_cpu_has(X86_FEATURE_CYRIX_ARR) || boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) && (pfn << PAGE_SHIFT) >= __pa(high_memory)) { - flags = _PAGE_CACHE_UC; + pcm = _PAGE_CACHE_MODE_UC; } #endif *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | - flags); + cachemode2protval(pcm)); return 1; } @@ -556,7 +673,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, * Change the memory type for the physial address range in kernel identity * mapping space if that range is a part of identity map. */ -int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags) +int kernel_map_sync_memtype(u64 base, unsigned long size, + enum page_cache_mode pcm) { unsigned long id_sz; @@ -574,11 +692,11 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags) __pa(high_memory) - base : size; - if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) { + if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) { printk(KERN_INFO "%s:%d ioremap_change_attr failed %s " "for [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, - cattr_name(flags), + cattr_name(pcm), base, (unsigned long long)(base + size-1)); return -EINVAL; } @@ -595,8 +713,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, { int is_ram = 0; int ret; - unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK); - unsigned long flags = want_flags; + enum page_cache_mode want_pcm = pgprot2cachemode(*vma_prot); + enum page_cache_mode pcm = want_pcm; is_ram = pat_pagerange_is_ram(paddr, paddr + size); @@ -609,36 +727,36 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, if (!pat_enabled) return 0; - flags = lookup_memtype(paddr); - if (want_flags != flags) { + pcm = lookup_memtype(paddr); + if (want_pcm != pcm) { printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n", current->comm, current->pid, - cattr_name(want_flags), + cattr_name(want_pcm), (unsigned long long)paddr, (unsigned long long)(paddr + size - 1), - cattr_name(flags)); + cattr_name(pcm)); *vma_prot = __pgprot((pgprot_val(*vma_prot) & - (~_PAGE_CACHE_MASK)) | - flags); + (~_PAGE_CACHE_MASK)) | + cachemode2protval(pcm)); } return 0; } - ret = reserve_memtype(paddr, paddr + size, want_flags, &flags); + ret = reserve_memtype(paddr, paddr + size, want_pcm, &pcm); if (ret) return ret; - if (flags != want_flags) { + if (pcm != want_pcm) { if (strict_prot || - !is_new_memtype_allowed(paddr, size, want_flags, flags)) { + !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) { free_memtype(paddr, paddr + size); printk(KERN_ERR "%s:%d map pfn expected mapping type %s" " for [mem %#010Lx-%#010Lx], got %s\n", current->comm, current->pid, - cattr_name(want_flags), + cattr_name(want_pcm), (unsigned long long)paddr, (unsigned long long)(paddr + size - 1), - cattr_name(flags)); + cattr_name(pcm)); return -EINVAL; } /* @@ -647,10 +765,10 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, */ *vma_prot = __pgprot((pgprot_val(*vma_prot) & (~_PAGE_CACHE_MASK)) | - flags); + cachemode2protval(pcm)); } - if (kernel_map_sync_memtype(paddr, size, flags) < 0) { + if (kernel_map_sync_memtype(paddr, size, pcm) < 0) { free_memtype(paddr, paddr + size); return -EINVAL; } @@ -709,7 +827,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size) { resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT; - unsigned long flags; + enum page_cache_mode pcm; /* reserve the whole chunk starting from paddr */ if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) { @@ -728,18 +846,18 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, * For anything smaller than the vma size we set prot based on the * lookup. */ - flags = lookup_memtype(paddr); + pcm = lookup_memtype(paddr); /* Check memtype for the remaining pages */ while (size > PAGE_SIZE) { size -= PAGE_SIZE; paddr += PAGE_SIZE; - if (flags != lookup_memtype(paddr)) + if (pcm != lookup_memtype(paddr)) return -EINVAL; } *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | - flags); + cachemode2protval(pcm)); return 0; } @@ -747,15 +865,15 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn) { - unsigned long flags; + enum page_cache_mode pcm; if (!pat_enabled) return 0; /* Set prot based on lookup */ - flags = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT); + pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT); *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | - flags); + cachemode2protval(pcm)); return 0; } @@ -791,7 +909,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, pgprot_t pgprot_writecombine(pgprot_t prot) { if (pat_enabled) - return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC); + return __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_WC)); else return pgprot_noncached(prot); } @@ -824,7 +943,7 @@ static void *memtype_seq_start(struct seq_file *seq, loff_t *pos) { if (*pos == 0) { ++*pos; - seq_printf(seq, "PAT memtype list:\n"); + seq_puts(seq, "PAT memtype list:\n"); } return memtype_get_idx(*pos); diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h index 77e5ba153fac..f6411620305d 100644 --- a/arch/x86/mm/pat_internal.h +++ b/arch/x86/mm/pat_internal.h @@ -10,30 +10,32 @@ struct memtype { u64 start; u64 end; u64 subtree_max_end; - unsigned long type; + enum page_cache_mode type; struct rb_node rb; }; -static inline char *cattr_name(unsigned long flags) +static inline char *cattr_name(enum page_cache_mode pcm) { - switch (flags & _PAGE_CACHE_MASK) { - case _PAGE_CACHE_UC: return "uncached"; - case _PAGE_CACHE_UC_MINUS: return "uncached-minus"; - case _PAGE_CACHE_WB: return "write-back"; - case _PAGE_CACHE_WC: return "write-combining"; - default: return "broken"; + switch (pcm) { + case _PAGE_CACHE_MODE_UC: return "uncached"; + case _PAGE_CACHE_MODE_UC_MINUS: return "uncached-minus"; + case _PAGE_CACHE_MODE_WB: return "write-back"; + case _PAGE_CACHE_MODE_WC: return "write-combining"; + case _PAGE_CACHE_MODE_WT: return "write-through"; + case _PAGE_CACHE_MODE_WP: return "write-protected"; + default: return "broken"; } } #ifdef CONFIG_X86_PAT extern int rbt_memtype_check_insert(struct memtype *new, - unsigned long *new_type); + enum page_cache_mode *new_type); extern struct memtype *rbt_memtype_erase(u64 start, u64 end); extern struct memtype *rbt_memtype_lookup(u64 addr); extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos); #else static inline int rbt_memtype_check_insert(struct memtype *new, - unsigned long *new_type) + enum page_cache_mode *new_type) { return 0; } static inline struct memtype *rbt_memtype_erase(u64 start, u64 end) { return NULL; } diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 415f6c4ced36..6582adcc8bd9 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -122,11 +122,12 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, static int memtype_rb_check_conflict(struct rb_root *root, u64 start, u64 end, - unsigned long reqtype, unsigned long *newtype) + enum page_cache_mode reqtype, + enum page_cache_mode *newtype) { struct rb_node *node; struct memtype *match; - int found_type = reqtype; + enum page_cache_mode found_type = reqtype; match = memtype_rb_lowest_match(&memtype_rbroot, start, end); if (match == NULL) @@ -187,7 +188,8 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata) rb_insert_augmented(&newdata->rb, root, &memtype_rb_augment_cb); } -int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type) +int rbt_memtype_check_insert(struct memtype *new, + enum page_cache_mode *ret_type) { int err = 0; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 37c1435889ce..9b18ef315a55 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -433,14 +433,14 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, return -EINVAL; if (pat_enabled && write_combine) - prot |= _PAGE_CACHE_WC; + prot |= cachemode2protval(_PAGE_CACHE_MODE_WC); else if (pat_enabled || boot_cpu_data.x86 > 3) /* * ioremap() and ioremap_nocache() defaults to UC MINUS for now. * To avoid attribute conflicts, request UC MINUS here * as well. */ - prot |= _PAGE_CACHE_UC_MINUS; + prot |= cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS); vma->vm_page_prot = __pgprot(prot); diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c index 7307d9d12d15..2e565e65c893 100644 --- a/arch/x86/pci/numachip.c +++ b/arch/x86/pci/numachip.c @@ -103,7 +103,7 @@ static int pci_mmcfg_write_numachip(unsigned int seg, unsigned int bus, return 0; } -const struct pci_raw_ops pci_mmcfg_numachip = { +static const struct pci_raw_ops pci_mmcfg_numachip = { .read = pci_mmcfg_read_numachip, .write = pci_mmcfg_write_numachip, }; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 35aecb6042fb..17e80d829df0 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -48,8 +48,7 @@ static unsigned long efi_flags __initdata; * We allocate runtime services regions bottom-up, starting from -4G, i.e. * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G. */ -static u64 efi_va = -4 * (1UL << 30); -#define EFI_VA_END (-68 * (1UL << 30)) +static u64 efi_va = EFI_VA_START; /* * Scratch space used for switching the pagetable in the EFI stub diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 3968d67d366b..994798548b1a 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1367,23 +1367,25 @@ static int ptc_seq_show(struct seq_file *file, void *data) cpu = *(loff_t *)data; if (!cpu) { - seq_printf(file, - "# cpu bauoff sent stime self locals remotes ncpus localhub "); - seq_printf(file, - "remotehub numuvhubs numuvhubs16 numuvhubs8 "); - seq_printf(file, - "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries "); - seq_printf(file, - "rok resetp resett giveup sto bz throt disable "); - seq_printf(file, - "enable wars warshw warwaits enters ipidis plugged "); - seq_printf(file, - "ipiover glim cong swack recv rtime all one mult "); - seq_printf(file, - "none retry canc nocan reset rcan\n"); + seq_puts(file, + "# cpu bauoff sent stime self locals remotes ncpus localhub "); + seq_puts(file, "remotehub numuvhubs numuvhubs16 numuvhubs8 "); + seq_puts(file, + "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries "); + seq_puts(file, + "rok resetp resett giveup sto bz throt disable "); + seq_puts(file, + "enable wars warshw warwaits enters ipidis plugged "); + seq_puts(file, + "ipiover glim cong swack recv rtime all one mult "); + seq_puts(file, "none retry canc nocan reset rcan\n"); } if (cpu < num_possible_cpus() && cpu_online(cpu)) { bcp = &per_cpu(bau_control, cpu); + if (bcp->nobau) { + seq_printf(file, "cpu %d bau disabled\n", cpu); + return 0; + } stat = bcp->statp; /* source side statistics */ seq_printf(file, diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index f52e033557c9..2c835e356349 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -24,6 +24,7 @@ quiet_cmd_bin2c = BIN2C $@ $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE $(call if_changed,bin2c) + @: obj-$(CONFIG_KEXEC_FILE) += kexec-purgatory.o diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index a5efb21d5228..0c2fae8d929d 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -20,7 +20,10 @@ struct relocs { static struct relocs relocs16; static struct relocs relocs32; +#if ELF_BITS == 64 +static struct relocs relocs32neg; static struct relocs relocs64; +#endif struct section { Elf_Shdr shdr; @@ -762,11 +765,16 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, switch (r_type) { case R_X86_64_NONE: + /* NONE can be ignored. */ + break; + case R_X86_64_PC32: /* - * NONE can be ignored and PC relative relocations don't - * need to be adjusted. + * PC relative relocations don't need to be adjusted unless + * referencing a percpu symbol. */ + if (is_percpu_sym(sym, symname)) + add_reloc(&relocs32neg, offset); break; case R_X86_64_32: @@ -986,7 +994,10 @@ static void emit_relocs(int as_text, int use_real_mode) /* Order the relocations for more efficient processing */ sort_relocs(&relocs16); sort_relocs(&relocs32); +#if ELF_BITS == 64 + sort_relocs(&relocs32neg); sort_relocs(&relocs64); +#endif /* Print the relocations */ if (as_text) { @@ -1007,14 +1018,21 @@ static void emit_relocs(int as_text, int use_real_mode) for (i = 0; i < relocs32.count; i++) write_reloc(relocs32.offset[i], stdout); } else { - if (ELF_BITS == 64) { - /* Print a stop */ - write_reloc(0, stdout); +#if ELF_BITS == 64 + /* Print a stop */ + write_reloc(0, stdout); - /* Now print each relocation */ - for (i = 0; i < relocs64.count; i++) - write_reloc(relocs64.offset[i], stdout); - } + /* Now print each relocation */ + for (i = 0; i < relocs64.count; i++) + write_reloc(relocs64.offset[i], stdout); + + /* Print a stop */ + write_reloc(0, stdout); + + /* Now print each inverse 32-bit relocation */ + for (i = 0; i < relocs32neg.count; i++) + write_reloc(relocs32neg.offset[i], stdout); +#endif /* Print a stop */ write_reloc(0, stdout); diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c index 2f94b039e55b..8ec3d1f4ce9a 100644 --- a/arch/x86/vdso/vgetcpu.c +++ b/arch/x86/vdso/vgetcpu.c @@ -7,9 +7,7 @@ #include <linux/kernel.h> #include <linux/getcpu.h> -#include <linux/jiffies.h> #include <linux/time.h> -#include <asm/vsyscall.h> #include <asm/vgtod.h> notrace long diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 970463b566cf..009495b9ab4b 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -1,7 +1,8 @@ /* - * Set up the VMAs to tell the VM about the vDSO. * Copyright 2007 Andi Kleen, SUSE Labs. * Subject to the GPL, v.2 + * + * This contains most of the x86 vDSO kernel-side code. */ #include <linux/mm.h> #include <linux/err.h> @@ -10,17 +11,17 @@ #include <linux/init.h> #include <linux/random.h> #include <linux/elf.h> -#include <asm/vsyscall.h> +#include <linux/cpu.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> +#include <asm/vvar.h> #include <asm/page.h> #include <asm/hpet.h> +#include <asm/desc.h> #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; - -extern unsigned short vdso_sync_cpuid; #endif void __init init_vdso_image(const struct vdso_image *image) @@ -38,20 +39,6 @@ void __init init_vdso_image(const struct vdso_image *image) image->alt_len)); } -#if defined(CONFIG_X86_64) -static int __init init_vdso(void) -{ - init_vdso_image(&vdso_image_64); - -#ifdef CONFIG_X86_X32_ABI - init_vdso_image(&vdso_image_x32); -#endif - - return 0; -} -subsys_initcall(init_vdso); -#endif - struct linux_binprm; /* Put the vdso above the (randomized) stack with another randomized offset. @@ -238,3 +225,63 @@ static __init int vdso_setup(char *s) } __setup("vdso=", vdso_setup); #endif + +#ifdef CONFIG_X86_64 +static void vgetcpu_cpu_init(void *arg) +{ + int cpu = smp_processor_id(); + struct desc_struct d = { }; + unsigned long node = 0; +#ifdef CONFIG_NUMA + node = cpu_to_node(cpu); +#endif + if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP)) + write_rdtscp_aux((node << 12) | cpu); + + /* + * Store cpu number in limit so that it can be loaded + * quickly in user space in vgetcpu. (12 bits for the CPU + * and 8 bits for the node) + */ + d.limit0 = cpu | ((node & 0xf) << 12); + d.limit = node >> 4; + d.type = 5; /* RO data, expand down, accessed */ + d.dpl = 3; /* Visible to user code */ + d.s = 1; /* Not a system segment */ + d.p = 1; /* Present */ + d.d = 1; /* 32-bit */ + + write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); +} + +static int +vgetcpu_cpu_notifier(struct notifier_block *n, unsigned long action, void *arg) +{ + long cpu = (long)arg; + + if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) + smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1); + + return NOTIFY_DONE; +} + +static int __init init_vdso(void) +{ + init_vdso_image(&vdso_image_64); + +#ifdef CONFIG_X86_X32_ABI + init_vdso_image(&vdso_image_x32); +#endif + + cpu_notifier_register_begin(); + + on_each_cpu(vgetcpu_cpu_init, NULL, 1); + /* notifier priority > KVM */ + __hotcpu_notifier(vgetcpu_cpu_notifier, 30); + + cpu_notifier_register_done(); + + return 0; +} +subsys_initcall(init_vdso); +#endif /* CONFIG_X86_64 */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index fac5e4f9607c..6bf3a13e3e0f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1100,12 +1100,6 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) /* Fast syscall setup is all done in hypercalls, so these are all ignored. Stub them out here to stop Xen console noise. */ - break; - - case MSR_IA32_CR_PAT: - if (smp_processor_id() == 0) - xen_set_pat(((u64)high << 32) | low); - break; default: ret = native_write_msr_safe(msr, low, high); @@ -1561,10 +1555,6 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Prevent unwanted bits from being set in PTEs. */ __supported_pte_mask &= ~_PAGE_GLOBAL; -#if 0 - if (!xen_initial_domain()) -#endif - __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); /* * Prevent page tables from being allocated in highmem, even @@ -1618,14 +1608,6 @@ asmlinkage __visible void __init xen_start_kernel(void) */ acpi_numa = -1; #endif -#ifdef CONFIG_X86_PAT - /* - * For right now disable the PAT. We should remove this once - * git commit 8eaffa67b43e99ae581622c5133e20b0f48bcef1 - * (xen/pat: Disable PAT support for now) is reverted. - */ - pat_enabled = 0; -#endif /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; @@ -1636,6 +1618,13 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_raw_console_write("mapping kernel into physical memory\n"); xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages); + /* + * Modify the cache mode translation tables to match Xen's PAT + * configuration. + */ + + pat_init_cache_modes(); + /* keep using Xen gdt for now; no urgent need to change it */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index a8a1a3d08d4d..8c8298d78185 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -410,13 +410,7 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) __visible pteval_t xen_pte_val(pte_t pte) { pteval_t pteval = pte.pte; -#if 0 - /* If this is a WC pte, convert back from Xen WC to Linux WC */ - if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) { - WARN_ON(!pat_enabled); - pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT; - } -#endif + return pte_mfn_to_pfn(pteval); } PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val); @@ -427,47 +421,8 @@ __visible pgdval_t xen_pgd_val(pgd_t pgd) } PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val); -/* - * Xen's PAT setup is part of its ABI, though I assume entries 6 & 7 - * are reserved for now, to correspond to the Intel-reserved PAT - * types. - * - * We expect Linux's PAT set as follows: - * - * Idx PTE flags Linux Xen Default - * 0 WB WB WB - * 1 PWT WC WT WT - * 2 PCD UC- UC- UC- - * 3 PCD PWT UC UC UC - * 4 PAT WB WC WB - * 5 PAT PWT WC WP WT - * 6 PAT PCD UC- rsv UC- - * 7 PAT PCD PWT UC rsv UC - */ - -void xen_set_pat(u64 pat) -{ - /* We expect Linux to use a PAT setting of - * UC UC- WC WB (ignoring the PAT flag) */ - WARN_ON(pat != 0x0007010600070106ull); -} - __visible pte_t xen_make_pte(pteval_t pte) { -#if 0 - /* If Linux is trying to set a WC pte, then map to the Xen WC. - * If _PAGE_PAT is set, then it probably means it is really - * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope - * things work out OK... - * - * (We should never see kernel mappings with _PAGE_PSE set, - * but we could see hugetlbfs mappings, I think.). - */ - if (pat_enabled && !WARN_ON(pte & _PAGE_PAT)) { - if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT) - pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT; - } -#endif pte = pte_pfn_to_mfn(pte); return native_make_pte(pte); @@ -1457,8 +1412,10 @@ static int xen_pgd_alloc(struct mm_struct *mm) page->private = (unsigned long)user_pgd; if (user_pgd != NULL) { +#ifdef CONFIG_X86_VSYSCALL_EMULATION user_pgd[pgd_index(VSYSCALL_ADDR)] = __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); +#endif ret = 0; } @@ -2021,7 +1978,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) # ifdef CONFIG_HIGHMEM case FIX_KMAP_BEGIN ... FIX_KMAP_END: # endif -#else +#elif defined(CONFIG_X86_VSYSCALL_EMULATION) case VSYSCALL_PAGE: #endif case FIX_TEXT_POKE0: @@ -2060,7 +2017,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) __native_set_fixmap(idx, pte); -#ifdef CONFIG_X86_64 +#ifdef CONFIG_X86_VSYSCALL_EMULATION /* Replicate changes to map the vsyscall page into the user pagetable vsyscall mapping. */ if (idx == VSYSCALL_PAGE) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 28c7e0be56e4..4ab9298c5e17 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -33,7 +33,6 @@ extern unsigned long xen_max_p2m_pfn; void xen_mm_pin_all(void); void xen_mm_unpin_all(void); -void xen_set_pat(u64); char * __init xen_memory_setup(void); char * xen_auto_xlated_memory_setup(void); diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index fc5f780bb61d..1b6aa514848f 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -128,7 +128,7 @@ static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); static struct gen_pool *ghes_estatus_pool; static unsigned long ghes_estatus_pool_size_request; -struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE]; +static struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE]; static atomic_t ghes_estatus_cache_alloced; static int ghes_ioremap_init(void) @@ -738,20 +738,6 @@ static LIST_HEAD(ghes_nmi); static int ghes_panic_timeout __read_mostly = 30; -static struct llist_node *llist_nodes_reverse(struct llist_node *llnode) -{ - struct llist_node *next, *tail = NULL; - - while (llnode) { - next = llnode->next; - llnode->next = tail; - tail = llnode; - llnode = next; - } - - return tail; -} - static void ghes_proc_in_irq(struct irq_work *irq_work) { struct llist_node *llnode, *next; @@ -765,7 +751,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work) * Because the time order of estatus in list is reversed, * revert it back to proper order. */ - llnode = llist_nodes_reverse(llnode); + llnode = llist_reverse_order(llnode); while (llnode) { next = llnode->next; estatus_node = llist_entry(llnode, struct ghes_estatus_node, @@ -798,7 +784,7 @@ static void ghes_print_queued_estatus(void) * Because the time order of estatus in list is reversed, * revert it back to proper order. */ - llnode = llist_nodes_reverse(llnode); + llnode = llist_reverse_order(llnode); while (llnode) { estatus_node = llist_entry(llnode, struct ghes_estatus_node, llnode); diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c index 900d4d3272d1..9a950022ff88 100644 --- a/drivers/block/drbd/drbd_debugfs.c +++ b/drivers/block/drbd/drbd_debugfs.c @@ -419,7 +419,7 @@ static int in_flight_summary_show(struct seq_file *m, void *pos) return 0; } -/* simple_positive(file->f_dentry) respectively debugfs_positive(), +/* simple_positive(file->f_path.dentry) respectively debugfs_positive(), * but neither is "reachable" from here. * So we have our own inline version of it above. :-( */ static inline int debugfs_positive(struct dentry *dentry) @@ -437,14 +437,14 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo /* Are we still linked, * or has debugfs_remove() already been called? */ - parent = file->f_dentry->d_parent; + parent = file->f_path.dentry->d_parent; /* not sure if this can happen: */ if (!parent || !parent->d_inode) goto out; /* serialize with d_delete() */ mutex_lock(&parent->d_inode->i_mutex); /* Make sure the object is still alive */ - if (debugfs_positive(file->f_dentry) + if (debugfs_positive(file->f_path.dentry) && kref_get_unless_zero(kref)) ret = 0; mutex_unlock(&parent->d_inode->i_mutex); diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h index 51b7e3a36e37..c2359a1ea6b3 100644 --- a/drivers/edac/mce_amd.h +++ b/drivers/edac/mce_amd.h @@ -32,9 +32,6 @@ #define R4(x) (((x) >> 4) & 0xf) #define R4_MSG(x) ((R4(x) < 9) ? rrrr_msgs[R4(x)] : "Wrong R4!") -#define MCI_STATUS_DEFERRED BIT_64(44) -#define MCI_STATUS_POISON BIT_64(43) - extern const char * const pp_msgs[]; enum tt_ids { diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index aef6a95adef5..d8be608a9f3b 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_EFI_VARS_PSTORE) += efi-pstore.o obj-$(CONFIG_UEFI_CPER) += cper.o obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o obj-$(CONFIG_EFI_RUNTIME_WRAPPERS) += runtime-wrappers.o -obj-$(CONFIG_EFI_ARM_STUB) += libstub/ +obj-$(CONFIG_EFI_STUB) += libstub/ diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index 7496f55611a5..ef5feeecec84 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -226,7 +226,7 @@ struct armada_gem_object *armada_gem_alloc_object(struct drm_device *dev, obj->dev_addr = DMA_ERROR_CODE; - mapping = obj->obj.filp->f_path.dentry->d_inode->i_mapping; + mapping = file_inode(obj->obj.filp)->i_mapping; mapping_set_gfp_mask(mapping, GFP_HIGHUSER | __GFP_RECLAIMABLE); DRM_DEBUG_DRIVER("alloc obj %p size %zu\n", obj, size); diff --git a/drivers/media/pci/zoran/zoran_procfs.c b/drivers/media/pci/zoran/zoran_procfs.c index f7ceee0cdefd..437652761093 100644 --- a/drivers/media/pci/zoran/zoran_procfs.c +++ b/drivers/media/pci/zoran/zoran_procfs.c @@ -157,8 +157,8 @@ static ssize_t zoran_write(struct file *file, const char __user *buffer, return -EFAULT; } string[count] = 0; - dprintk(4, KERN_INFO "%s: write_proc: name=%s count=%zu zr=%p\n", - ZR_DEVNAME(zr), file->f_path.dentry->d_name.name, count, zr); + dprintk(4, KERN_INFO "%s: write_proc: name=%pD count=%zu zr=%p\n", + ZR_DEVNAME(zr), file, count, zr); ldelim = " \t\n"; tdelim = "="; line = strpbrk(sp, ldelim); diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c index 5918586f2f76..c49d244265ec 100644 --- a/drivers/misc/genwqe/card_dev.c +++ b/drivers/misc/genwqe/card_dev.c @@ -395,7 +395,7 @@ static void genwqe_vma_open(struct vm_area_struct *vma) static void genwqe_vma_close(struct vm_area_struct *vma) { unsigned long vsize = vma->vm_end - vma->vm_start; - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); struct dma_mapping *dma_map; struct genwqe_dev *cd = container_of(inode->i_cdev, struct genwqe_dev, cdev_genwqe); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 9dd3746994a4..4d332dc93b70 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2222,7 +2222,7 @@ static int tun_chr_close(struct inode *inode, struct file *file) } #ifdef CONFIG_PROC_FS -static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f) +static void tun_chr_show_fdinfo(struct seq_file *m, struct file *f) { struct tun_struct *tun; struct ifreq ifr; @@ -2238,7 +2238,7 @@ static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f) if (tun) tun_put(tun); - return seq_printf(m, "iff:\t%s\n", ifr.ifr_name); + seq_printf(m, "iff:\t%s\n", ifr.ifr_name); } #endif diff --git a/drivers/s390/char/hmcdrv_dev.c b/drivers/s390/char/hmcdrv_dev.c index 0c5176179c17..43cee7fcd01c 100644 --- a/drivers/s390/char/hmcdrv_dev.c +++ b/drivers/s390/char/hmcdrv_dev.c @@ -136,8 +136,7 @@ static int hmcdrv_dev_open(struct inode *inode, struct file *fp) if (rc) module_put(THIS_MODULE); - pr_debug("open file '/dev/%s' with return code %d\n", - fp->f_dentry->d_name.name, rc); + pr_debug("open file '/dev/%pD' with return code %d\n", fp, rc); return rc; } @@ -146,7 +145,7 @@ static int hmcdrv_dev_open(struct inode *inode, struct file *fp) */ static int hmcdrv_dev_release(struct inode *inode, struct file *fp) { - pr_debug("closing file '/dev/%s'\n", fp->f_dentry->d_name.name); + pr_debug("closing file '/dev/%pD'\n", fp); kfree(fp->private_data); fp->private_data = NULL; hmcdrv_ftp_shutdown(); @@ -231,8 +230,8 @@ static ssize_t hmcdrv_dev_read(struct file *fp, char __user *ubuf, retlen = hmcdrv_dev_transfer((char *) fp->private_data, *pos, ubuf, len); - pr_debug("read from file '/dev/%s' at %lld returns %zd/%zu\n", - fp->f_dentry->d_name.name, (long long) *pos, retlen, len); + pr_debug("read from file '/dev/%pD' at %lld returns %zd/%zu\n", + fp, (long long) *pos, retlen, len); if (retlen > 0) *pos += retlen; @@ -248,8 +247,8 @@ static ssize_t hmcdrv_dev_write(struct file *fp, const char __user *ubuf, { ssize_t retlen; - pr_debug("writing file '/dev/%s' at pos. %lld with length %zd\n", - fp->f_dentry->d_name.name, (long long) *pos, len); + pr_debug("writing file '/dev/%pD' at pos. %lld with length %zd\n", + fp, (long long) *pos, len); if (!fp->private_data) { /* first expect a cmd write */ fp->private_data = kmalloc(len + 1, GFP_KERNEL); @@ -272,8 +271,7 @@ static ssize_t hmcdrv_dev_write(struct file *fp, const char __user *ubuf, if (retlen > 0) *pos += retlen; - pr_debug("write to file '/dev/%s' returned %zd\n", - fp->f_dentry->d_name.name, retlen); + pr_debug("write to file '/dev/%pD' returned %zd\n", fp, retlen); return retlen; } diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 786a2aff7b59..5633e7dadc08 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -968,8 +968,8 @@ lpfc_debugfs_dumpDif_open(struct inode *inode, struct file *file) goto out; /* Round to page boundary */ - printk(KERN_ERR "9060 BLKGRD: %s: _dump_buf_dif=0x%p file=%s\n", - __func__, _dump_buf_dif, file->f_dentry->d_name.name); + printk(KERN_ERR "9060 BLKGRD: %s: _dump_buf_dif=0x%p file=%pD\n", + __func__, _dump_buf_dif, file); debug->buffer = _dump_buf_dif; if (!debug->buffer) { kfree(debug); @@ -1011,7 +1011,7 @@ static ssize_t lpfc_debugfs_dif_err_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { - struct dentry *dent = file->f_dentry; + struct dentry *dent = file->f_path.dentry; struct lpfc_hba *phba = file->private_data; char cbuf[32]; uint64_t tmp = 0; @@ -1052,7 +1052,7 @@ static ssize_t lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos) { - struct dentry *dent = file->f_dentry; + struct dentry *dent = file->f_path.dentry; struct lpfc_hba *phba = file->private_data; char dstbuf[32]; uint64_t tmp = 0; diff --git a/drivers/staging/lustre/lustre/libcfs/tracefile.c b/drivers/staging/lustre/lustre/libcfs/tracefile.c index 7e3f6a45da00..7561030c96e6 100644 --- a/drivers/staging/lustre/lustre/libcfs/tracefile.c +++ b/drivers/staging/lustre/lustre/libcfs/tracefile.c @@ -1025,8 +1025,8 @@ static int tracefiled(void *arg) if (f_pos >= (off_t)cfs_tracefile_size) f_pos = 0; - else if (f_pos > i_size_read(filp->f_dentry->d_inode)) - f_pos = i_size_read(filp->f_dentry->d_inode); + else if (f_pos > i_size_read(file_inode(filp))) + f_pos = i_size_read(file_inode(filp)); buf = kmap(tage->page); rc = vfs_write(filp, (__force const char __user *)buf, diff --git a/drivers/staging/lustre/lustre/llite/dcache.c b/drivers/staging/lustre/lustre/llite/dcache.c index 439e4875b05c..f692261e9b5c 100644 --- a/drivers/staging/lustre/lustre/llite/dcache.c +++ b/drivers/staging/lustre/lustre/llite/dcache.c @@ -151,10 +151,10 @@ static int ll_ddelete(const struct dentry *de) { LASSERT(de); - CDEBUG(D_DENTRY, "%s dentry %.*s (%p, parent %p, inode %p) %s%s\n", + CDEBUG(D_DENTRY, "%s dentry %pd (%p, parent %p, inode %p) %s%s\n", d_lustre_invalid((struct dentry *)de) ? "deleting" : "keeping", - de->d_name.len, de->d_name.name, de, de->d_parent, de->d_inode, - d_unhashed((struct dentry *)de) ? "" : "hashed,", + de, de, de->d_parent, de->d_inode, + d_unhashed(de) ? "" : "hashed,", list_empty(&de->d_subdirs) ? "" : "subdirs"); /* kernel >= 2.6.38 last refcount is decreased after this function. */ @@ -180,8 +180,8 @@ int ll_d_init(struct dentry *de) { LASSERT(de != NULL); - CDEBUG(D_DENTRY, "ldd on dentry %.*s (%p) parent %p inode %p refc %d\n", - de->d_name.len, de->d_name.name, de, de->d_parent, de->d_inode, + CDEBUG(D_DENTRY, "ldd on dentry %pd (%p) parent %p inode %p refc %d\n", + de, de, de->d_parent, de->d_inode, d_count(de)); if (de->d_fsdata == NULL) { @@ -258,10 +258,9 @@ void ll_invalidate_aliases(struct inode *inode) inode->i_ino, inode->i_generation, inode); ll_lock_dcache(inode); - ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { - CDEBUG(D_DENTRY, "dentry in drop %.*s (%p) parent %p " - "inode %p flags %d\n", dentry->d_name.len, - dentry->d_name.name, dentry, dentry->d_parent, + ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_u.d_alias) { + CDEBUG(D_DENTRY, "dentry in drop %pd (%p) parent %p " + "inode %p flags %d\n", dentry, dentry, dentry->d_parent, dentry->d_inode, dentry->d_flags); if (unlikely(dentry == dentry->d_sb->s_root)) { @@ -352,8 +351,8 @@ static int ll_revalidate_nd(struct dentry *dentry, unsigned int flags) { int rc; - CDEBUG(D_VFSTRACE, "VFS Op:name=%s, flags=%u\n", - dentry->d_name.name, flags); + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, flags=%u\n", + dentry, flags); rc = ll_revalidate_dentry(dentry, flags); return rc; diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c index b0bb7095dde5..a79fd65ec4c6 100644 --- a/drivers/staging/lustre/lustre/llite/dir.c +++ b/drivers/staging/lustre/lustre/llite/dir.c @@ -593,7 +593,7 @@ int ll_dir_read(struct inode *inode, struct dir_context *ctx) static int ll_readdir(struct file *filp, struct dir_context *ctx) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = file_inode(filp); struct ll_file_data *lfd = LUSTRE_FPRIVATE(filp); struct ll_sb_info *sbi = ll_i2sbi(inode); int hash64 = sbi->ll_flags & LL_SBI_64BIT_HASH; @@ -1242,7 +1242,7 @@ ll_getname(const char __user *filename) static long ll_dir_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct ll_sb_info *sbi = ll_i2sbi(inode); struct obd_ioctl_data *data; int rc = 0; @@ -1389,7 +1389,7 @@ lmv_out_free: return -EFAULT; } - if (inode->i_sb->s_root == file->f_dentry) + if (is_root_inode(inode)) set_default = 1; /* in v1 and v3 cases lumv1 points to data */ @@ -1780,8 +1780,7 @@ out_quotactl: return ll_flush_ctx(inode); #ifdef CONFIG_FS_POSIX_ACL case LL_IOC_RMTACL: { - if (sbi->ll_flags & LL_SBI_RMT_CLIENT && - inode == inode->i_sb->s_root->d_inode) { + if (sbi->ll_flags & LL_SBI_RMT_CLIENT && is_root_inode(inode)) { struct ll_file_data *fd = LUSTRE_FPRIVATE(file); LASSERT(fd != NULL); diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c index c99b74117152..a2ae9a68a9a0 100644 --- a/drivers/staging/lustre/lustre/llite/file.c +++ b/drivers/staging/lustre/lustre/llite/file.c @@ -266,6 +266,10 @@ static int ll_md_close(struct obd_export *md_exp, struct inode *inode, { struct ll_file_data *fd = LUSTRE_FPRIVATE(file); struct ll_inode_info *lli = ll_i2info(inode); + int lockmode; + __u64 flags = LDLM_FL_BLOCK_GRANTED | LDLM_FL_TEST_LOCK; + struct lustre_handle lockh; + ldlm_policy_data_t policy = {.l_inodebits={MDS_INODELOCK_OPEN}}; int rc = 0; /* clear group lock, if present */ @@ -292,39 +296,26 @@ static int ll_md_close(struct obd_export *md_exp, struct inode *inode, /* Let's see if we have good enough OPEN lock on the file and if we can skip talking to MDS */ - if (file->f_dentry->d_inode) { /* Can this ever be false? */ - int lockmode; - __u64 flags = LDLM_FL_BLOCK_GRANTED | LDLM_FL_TEST_LOCK; - struct lustre_handle lockh; - struct inode *inode = file->f_dentry->d_inode; - ldlm_policy_data_t policy = {.l_inodebits={MDS_INODELOCK_OPEN}}; - - mutex_lock(&lli->lli_och_mutex); - if (fd->fd_omode & FMODE_WRITE) { - lockmode = LCK_CW; - LASSERT(lli->lli_open_fd_write_count); - lli->lli_open_fd_write_count--; - } else if (fd->fd_omode & FMODE_EXEC) { - lockmode = LCK_PR; - LASSERT(lli->lli_open_fd_exec_count); - lli->lli_open_fd_exec_count--; - } else { - lockmode = LCK_CR; - LASSERT(lli->lli_open_fd_read_count); - lli->lli_open_fd_read_count--; - } - mutex_unlock(&lli->lli_och_mutex); - if (!md_lock_match(md_exp, flags, ll_inode2fid(inode), - LDLM_IBITS, &policy, lockmode, - &lockh)) { - rc = ll_md_real_close(file->f_dentry->d_inode, - fd->fd_omode); - } + mutex_lock(&lli->lli_och_mutex); + if (fd->fd_omode & FMODE_WRITE) { + lockmode = LCK_CW; + LASSERT(lli->lli_open_fd_write_count); + lli->lli_open_fd_write_count--; + } else if (fd->fd_omode & FMODE_EXEC) { + lockmode = LCK_PR; + LASSERT(lli->lli_open_fd_exec_count); + lli->lli_open_fd_exec_count--; } else { - CERROR("Releasing a file %p with negative dentry %p. Name %s", - file, file->f_dentry, file->f_dentry->d_name.name); + lockmode = LCK_CR; + LASSERT(lli->lli_open_fd_read_count); + lli->lli_open_fd_read_count--; } + mutex_unlock(&lli->lli_och_mutex); + + if (!md_lock_match(md_exp, flags, ll_inode2fid(inode), + LDLM_IBITS, &policy, lockmode, &lockh)) + rc = ll_md_real_close(inode, fd->fd_omode); out: LUSTRE_FPRIVATE(file) = NULL; @@ -350,8 +341,7 @@ int ll_file_release(struct inode *inode, struct file *file) inode->i_generation, inode); #ifdef CONFIG_FS_POSIX_ACL - if (sbi->ll_flags & LL_SBI_RMT_CLIENT && - inode == inode->i_sb->s_root->d_inode) { + if (sbi->ll_flags & LL_SBI_RMT_CLIENT && is_root_inode(inode)) { struct ll_file_data *fd = LUSTRE_FPRIVATE(file); LASSERT(fd != NULL); @@ -363,7 +353,7 @@ int ll_file_release(struct inode *inode, struct file *file) } #endif - if (inode->i_sb->s_root != file->f_dentry) + if (!is_root_inode(inode)) ll_stats_ops_tally(sbi, LPROC_LL_RELEASE, 1); fd = LUSTRE_FPRIVATE(file); LASSERT(fd != NULL); @@ -375,7 +365,7 @@ int ll_file_release(struct inode *inode, struct file *file) lli->lli_opendir_pid != 0) ll_stop_statahead(inode, lli->lli_opendir_key); - if (inode->i_sb->s_root == file->f_dentry) { + if (is_root_inode(inode)) { LUSTRE_FPRIVATE(file) = NULL; ll_file_data_put(fd); return 0; @@ -394,21 +384,19 @@ int ll_file_release(struct inode *inode, struct file *file) return rc; } -static int ll_intent_file_open(struct file *file, void *lmm, +static int ll_intent_file_open(struct dentry *dentry, void *lmm, int lmmsize, struct lookup_intent *itp) { - struct ll_sb_info *sbi = ll_i2sbi(file->f_dentry->d_inode); - struct dentry *parent = file->f_dentry->d_parent; - const char *name = file->f_dentry->d_name.name; - const int len = file->f_dentry->d_name.len; + struct inode *inode = dentry->d_inode; + struct ll_sb_info *sbi = ll_i2sbi(inode); + struct dentry *parent = dentry->d_parent; + const char *name = dentry->d_name.name; + const int len = dentry->d_name.len; struct md_op_data *op_data; struct ptlrpc_request *req; __u32 opc = LUSTRE_OPC_ANY; int rc; - if (!parent) - return -ENOENT; - /* Usually we come here only for NFSD, and we want open lock. But we can also get here with pre 2.6.15 patchless kernels, and in that case that lock is also ok */ @@ -425,7 +413,7 @@ static int ll_intent_file_open(struct file *file, void *lmm, } op_data = ll_prep_md_op_data(NULL, parent->d_inode, - file->f_dentry->d_inode, name, len, + inode, name, len, O_RDWR, opc, NULL); if (IS_ERR(op_data)) return PTR_ERR(op_data); @@ -441,7 +429,7 @@ static int ll_intent_file_open(struct file *file, void *lmm, if (!it_disposition(itp, DISP_OPEN_OPEN) || it_open_error(DISP_OPEN_OPEN, itp)) goto out; - ll_release_openhandle(file->f_dentry, itp); + ll_release_openhandle(inode, itp); goto out; } @@ -456,10 +444,9 @@ static int ll_intent_file_open(struct file *file, void *lmm, goto out; } - rc = ll_prep_inode(&file->f_dentry->d_inode, req, NULL, itp); + rc = ll_prep_inode(&inode, req, NULL, itp); if (!rc && itp->d.lustre.it_lock_mode) - ll_set_lock_data(sbi->ll_md_exp, file->f_dentry->d_inode, - itp, NULL); + ll_set_lock_data(sbi->ll_md_exp, inode, itp, NULL); out: ptlrpc_req_finished(req); @@ -501,7 +488,7 @@ static int ll_och_fill(struct obd_export *md_exp, struct lookup_intent *it, static int ll_local_open(struct file *file, struct lookup_intent *it, struct ll_file_data *fd, struct obd_client_handle *och) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct ll_inode_info *lli = ll_i2info(inode); LASSERT(!LUSTRE_FPRIVATE(file)); @@ -574,7 +561,7 @@ int ll_file_open(struct inode *inode, struct file *file) spin_unlock(&lli->lli_sa_lock); } - if (inode->i_sb->s_root == file->f_dentry) { + if (is_root_inode(inode)) { LUSTRE_FPRIVATE(file) = fd; return 0; } @@ -632,7 +619,7 @@ restart: goto out_openerr; } - ll_release_openhandle(file->f_dentry, it); + ll_release_openhandle(inode, it); } (*och_usecount)++; @@ -652,7 +639,7 @@ restart: result in a deadlock */ mutex_unlock(&lli->lli_och_mutex); it->it_create_mode |= M_CHECK_STALE; - rc = ll_intent_file_open(file, NULL, 0, it); + rc = ll_intent_file_open(file->f_path.dentry, NULL, 0, it); it->it_create_mode &= ~M_CHECK_STALE; if (rc) goto out_openerr; @@ -1065,7 +1052,7 @@ int ll_glimpse_ioctl(struct ll_sb_info *sbi, struct lov_stripe_md *lsm, static bool file_is_noatime(const struct file *file) { const struct vfsmount *mnt = file->f_path.mnt; - const struct inode *inode = file->f_path.dentry->d_inode; + const struct inode *inode = file_inode(file); /* Adapted from file_accessed() and touch_atime().*/ if (file->f_flags & O_NOATIME) @@ -1091,7 +1078,7 @@ static bool file_is_noatime(const struct file *file) void ll_io_init(struct cl_io *io, const struct file *file, int write) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); io->u.ci_rw.crw_nonblock = file->f_flags & O_NONBLOCK; if (write) { @@ -1117,7 +1104,7 @@ ll_file_io_generic(const struct lu_env *env, struct vvp_io_args *args, struct file *file, enum cl_io_type iot, loff_t *ppos, size_t count) { - struct ll_inode_info *lli = ll_i2info(file->f_dentry->d_inode); + struct ll_inode_info *lli = ll_i2info(file_inode(file)); struct ll_file_data *fd = LUSTRE_FPRIVATE(file); struct cl_io *io; ssize_t result; @@ -1178,20 +1165,20 @@ out: /* If any bit been read/written (result != 0), we just return * short read/write instead of restart io. */ if ((result == 0 || result == -ENODATA) && io->ci_need_restart) { - CDEBUG(D_VFSTRACE, "Restart %s on %s from %lld, count:%zd\n", + CDEBUG(D_VFSTRACE, "Restart %s on %pD from %lld, count:%zd\n", iot == CIT_READ ? "read" : "write", - file->f_dentry->d_name.name, *ppos, count); + file, *ppos, count); LASSERTF(io->ci_nob == 0, "%zd", io->ci_nob); goto restart; } if (iot == CIT_READ) { if (result >= 0) - ll_stats_ops_tally(ll_i2sbi(file->f_dentry->d_inode), + ll_stats_ops_tally(ll_i2sbi(file_inode(file)), LPROC_LL_READ_BYTES, result); } else if (iot == CIT_WRITE) { if (result >= 0) { - ll_stats_ops_tally(ll_i2sbi(file->f_dentry->d_inode), + ll_stats_ops_tally(ll_i2sbi(file_inode(file)), LPROC_LL_WRITE_BYTES, result); fd->fd_write_failed = false; } else if (result != -ERESTARTSYS) { @@ -1354,7 +1341,7 @@ static int ll_lov_recreate_fid(struct inode *inode, unsigned long arg) return ll_lov_recreate(inode, &oi, ost_idx); } -int ll_lov_setstripe_ea_info(struct inode *inode, struct file *file, +int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry, int flags, struct lov_user_md *lum, int lum_size) { struct lov_stripe_md *lsm = NULL; @@ -1371,21 +1358,20 @@ int ll_lov_setstripe_ea_info(struct inode *inode, struct file *file, } ll_inode_size_lock(inode); - rc = ll_intent_file_open(file, lum, lum_size, &oit); + rc = ll_intent_file_open(dentry, lum, lum_size, &oit); if (rc) goto out_unlock; rc = oit.d.lustre.it_status; if (rc < 0) goto out_req_free; - ll_release_openhandle(file->f_dentry, &oit); + ll_release_openhandle(inode, &oit); out_unlock: ll_inode_size_unlock(inode); ll_intent_release(&oit); ccc_inode_lsm_put(inode, lsm); out: - cl_lov_delay_create_clear(&file->f_flags); return rc; out_req_free: ptlrpc_req_finished((struct ptlrpc_request *) oit.d.lustre.it_data); @@ -1499,7 +1485,9 @@ static int ll_lov_setea(struct inode *inode, struct file *file, return -EFAULT; } - rc = ll_lov_setstripe_ea_info(inode, file, flags, lump, lum_size); + rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, lump, + lum_size); + cl_lov_delay_create_clear(&file->f_flags); OBD_FREE_LARGE(lump, lum_size); return rc; @@ -1526,7 +1514,9 @@ static int ll_lov_setstripe(struct inode *inode, struct file *file, return -EFAULT; } - rc = ll_lov_setstripe_ea_info(inode, file, flags, lumv1, lum_size); + rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, lumv1, + lum_size); + cl_lov_delay_create_clear(&file->f_flags); if (rc == 0) { struct lov_stripe_md *lsm; __u32 gen; @@ -1631,22 +1621,21 @@ int ll_put_grouplock(struct inode *inode, struct file *file, unsigned long arg) /** * Close inode open handle * - * \param dentry [in] dentry which contains the inode + * \param inode [in] inode in question * \param it [in,out] intent which contains open info and result * * \retval 0 success * \retval <0 failure */ -int ll_release_openhandle(struct dentry *dentry, struct lookup_intent *it) +int ll_release_openhandle(struct inode *inode, struct lookup_intent *it) { - struct inode *inode = dentry->d_inode; struct obd_client_handle *och; int rc; LASSERT(inode); /* Root ? Do nothing. */ - if (dentry->d_inode->i_sb->s_root == dentry) + if (is_root_inode(inode)) return 0; /* No open handle to close? Move away */ @@ -1959,8 +1948,8 @@ static int ll_swap_layouts(struct file *file1, struct file *file2, if (!llss) return -ENOMEM; - llss->inode1 = file1->f_dentry->d_inode; - llss->inode2 = file2->f_dentry->d_inode; + llss->inode1 = file_inode(file1); + llss->inode2 = file_inode(file2); if (!S_ISREG(llss->inode2->i_mode)) { rc = -EINVAL; @@ -2092,7 +2081,7 @@ putgl: rc = 0; if (llss->ia2.ia_valid != 0) { mutex_lock(&llss->inode1->i_mutex); - rc = ll_setattr(file1->f_dentry, &llss->ia2); + rc = ll_setattr(file1->f_path.dentry, &llss->ia2); mutex_unlock(&llss->inode1->i_mutex); } @@ -2100,7 +2089,7 @@ putgl: int rc1; mutex_lock(&llss->inode2->i_mutex); - rc1 = ll_setattr(file2->f_dentry, &llss->ia1); + rc1 = ll_setattr(file2->f_path.dentry, &llss->ia1); mutex_unlock(&llss->inode2->i_mutex); if (rc == 0) rc = rc1; @@ -2185,7 +2174,7 @@ static int ll_hsm_import(struct inode *inode, struct file *file, mutex_lock(&inode->i_mutex); - rc = ll_setattr_raw(file->f_dentry, attr, true); + rc = ll_setattr_raw(file->f_path.dentry, attr, true); if (rc == -ENODATA) rc = 0; @@ -2204,7 +2193,7 @@ out: static long ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct ll_file_data *fd = LUSTRE_FPRIVATE(file); int flags, rc; @@ -2523,7 +2512,7 @@ ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static loff_t ll_file_seek(struct file *file, loff_t offset, int origin) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); loff_t retval, eof = 0; retval = offset + ((origin == SEEK_END) ? i_size_read(inode) : @@ -2547,7 +2536,7 @@ static loff_t ll_file_seek(struct file *file, loff_t offset, int origin) static int ll_flush(struct file *file, fl_owner_t id) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct ll_inode_info *lli = ll_i2info(inode); struct ll_file_data *fd = LUSTRE_FPRIVATE(file); int rc, err; @@ -2622,16 +2611,9 @@ int cl_sync_file_range(struct inode *inode, loff_t start, loff_t end, return result; } -/* - * When dentry is provided (the 'else' case), *file->f_dentry may be - * null and dentry must be used directly rather than pulled from - * *file->f_dentry as is done otherwise. - */ - int ll_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct dentry *dentry = file->f_dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(file); struct ll_inode_info *lli = ll_i2info(inode); struct ptlrpc_request *req; struct obd_capa *oc; @@ -2684,7 +2666,7 @@ int ll_fsync(struct file *file, loff_t start, loff_t end, int datasync) static int ll_file_flock(struct file *file, int cmd, struct file_lock *file_lock) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct ll_sb_info *sbi = ll_i2sbi(inode); struct ldlm_enqueue_info einfo = { .ei_type = LDLM_FLOCK, @@ -2908,8 +2890,8 @@ static int __ll_inode_revalidate(struct dentry *dentry, __u64 ibits) LASSERT(inode != NULL); - CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu/%u(%p),name=%s\n", - inode->i_ino, inode->i_generation, inode, dentry->d_name.name); + CDEBUG(D_VFSTRACE, "VFS Op:inode=%lu/%u(%p),name=%pd\n", + inode->i_ino, inode->i_generation, inode, dentry); exp = ll_i2mdexp(inode); @@ -3119,7 +3101,7 @@ int ll_inode_permission(struct inode *inode, int mask) /* as root inode are NOT getting validated in lookup operation, * need to do it before permission check. */ - if (inode == inode->i_sb->s_root->d_inode) { + if (is_root_inode(inode)) { rc = __ll_inode_revalidate(inode->i_sb->s_root, MDS_INODELOCK_LOOKUP); if (rc) diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h index 36aa0fd147f2..77d1c12704b4 100644 --- a/drivers/staging/lustre/lustre/llite/llite_internal.h +++ b/drivers/staging/lustre/lustre/llite/llite_internal.h @@ -748,7 +748,7 @@ int ll_file_release(struct inode *inode, struct file *file); int ll_glimpse_ioctl(struct ll_sb_info *sbi, struct lov_stripe_md *lsm, lstat_t *st); void ll_ioepoch_open(struct ll_inode_info *lli, __u64 ioepoch); -int ll_release_openhandle(struct dentry *, struct lookup_intent *); +int ll_release_openhandle(struct inode *, struct lookup_intent *); int ll_md_real_close(struct inode *inode, fmode_t fmode); void ll_ioepoch_close(struct inode *inode, struct md_op_data *op_data, struct obd_client_handle **och, unsigned long flags); @@ -763,7 +763,7 @@ struct posix_acl *ll_get_acl(struct inode *inode, int type); int ll_inode_permission(struct inode *inode, int mask); -int ll_lov_setstripe_ea_info(struct inode *inode, struct file *file, +int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry, int flags, struct lov_user_md *lum, int lum_size); int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename, @@ -1413,7 +1413,7 @@ extern ssize_t ll_direct_rw_pages(const struct lu_env *env, struct cl_io *io, static inline int ll_file_nolock(const struct file *file) { struct ll_file_data *fd = LUSTRE_FPRIVATE(file); - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); LASSERT(fd != NULL); return ((fd->fd_flags & LL_FILE_IGNORE_LOCK) || @@ -1489,8 +1489,8 @@ static inline void __d_lustre_invalidate(struct dentry *dentry) */ static inline void d_lustre_invalidate(struct dentry *dentry, int nested) { - CDEBUG(D_DENTRY, "invalidate dentry %.*s (%p) parent %p inode %p " - "refc %d\n", dentry->d_name.len, dentry->d_name.name, dentry, + CDEBUG(D_DENTRY, "invalidate dentry %pd (%p) parent %p inode %p " + "refc %d\n", dentry, dentry, dentry->d_parent, dentry->d_inode, d_count(dentry)); spin_lock_nested(&dentry->d_lock, diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c index a8bcc51057f1..7b6b9e2e0102 100644 --- a/drivers/staging/lustre/lustre/llite/llite_lib.c +++ b/drivers/staging/lustre/lustre/llite/llite_lib.c @@ -698,10 +698,8 @@ void lustre_dump_dentry(struct dentry *dentry, int recur) list_for_each(tmp, &dentry->d_subdirs) subdirs++; - CERROR("dentry %p dump: name=%.*s parent=%.*s (%p), inode=%p, count=%u," - " flags=0x%x, fsdata=%p, %d subdirs\n", dentry, - dentry->d_name.len, dentry->d_name.name, - dentry->d_parent->d_name.len, dentry->d_parent->d_name.name, + CERROR("dentry %p dump: name=%pd parent=%p, inode=%p, count=%u," + " flags=0x%x, fsdata=%p, %d subdirs\n", dentry, dentry, dentry->d_parent, dentry->d_inode, d_count(dentry), dentry->d_flags, dentry->d_fsdata, subdirs); if (dentry->d_inode != NULL) @@ -711,7 +709,7 @@ void lustre_dump_dentry(struct dentry *dentry, int recur) return; list_for_each(tmp, &dentry->d_subdirs) { - struct dentry *d = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *d = list_entry(tmp, struct dentry, d_child); lustre_dump_dentry(d, recur - 1); } } diff --git a/drivers/staging/lustre/lustre/llite/llite_mmap.c b/drivers/staging/lustre/lustre/llite/llite_mmap.c index ae605a6d9dc2..ba1c047ae927 100644 --- a/drivers/staging/lustre/lustre/llite/llite_mmap.c +++ b/drivers/staging/lustre/lustre/llite/llite_mmap.c @@ -100,7 +100,7 @@ ll_fault_io_init(struct vm_area_struct *vma, struct lu_env **env_ret, unsigned long *ra_flags) { struct file *file = vma->vm_file; - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); struct cl_io *io; struct cl_fault_io *fio; struct lu_env *env; @@ -213,7 +213,7 @@ static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage, cfs_restore_sigs(set); if (result == 0) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); struct ll_inode_info *lli = ll_i2info(inode); lock_page(vmpage); @@ -396,7 +396,7 @@ static int ll_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) CWARN("app(%s): the page %lu of file %lu is under heavy" " contention.\n", current->comm, vmf->pgoff, - vma->vm_file->f_dentry->d_inode->i_ino); + file_inode(vma->vm_file)->i_ino); printed = true; } } while (retry); @@ -430,7 +430,7 @@ static int ll_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) */ static void ll_vm_open(struct vm_area_struct *vma) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); struct ccc_object *vob = cl_inode2ccc(inode); LASSERT(vma->vm_file); @@ -443,7 +443,7 @@ static void ll_vm_open(struct vm_area_struct *vma) */ static void ll_vm_close(struct vm_area_struct *vma) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); struct ccc_object *vob = cl_inode2ccc(inode); LASSERT(vma->vm_file); @@ -476,7 +476,7 @@ static const struct vm_operations_struct ll_file_vm_ops = { int ll_file_mmap(struct file *file, struct vm_area_struct *vma) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode(file); int rc; if (ll_file_nolock(file)) diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c index ae3a12ab7fa1..243a7840457f 100644 --- a/drivers/staging/lustre/lustre/llite/llite_nfs.c +++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c @@ -207,13 +207,15 @@ static int ll_encode_fh(struct inode *inode, __u32 *fh, int *plen, return LUSTRE_NFS_FID; } -static int ll_nfs_get_name_filldir(void *cookie, const char *name, int namelen, - loff_t hash, u64 ino, unsigned type) +static int ll_nfs_get_name_filldir(struct dir_context *ctx, const char *name, + int namelen, loff_t hash, u64 ino, + unsigned type) { /* It is hack to access lde_fid for comparison with lgd_fid. * So the input 'name' must be part of the 'lu_dirent'. */ struct lu_dirent *lde = container_of0(name, struct lu_dirent, lde_name); - struct ll_getname_data *lgd = cookie; + struct ll_getname_data *lgd = + container_of(ctx, struct ll_getname_data, ctx); struct lu_fid fid; fid_le_to_cpu(&fid, &lde->lde_fid); diff --git a/drivers/staging/lustre/lustre/llite/lloop.c b/drivers/staging/lustre/lustre/llite/lloop.c index 264e5ec3fed6..9e31b789b790 100644 --- a/drivers/staging/lustre/lustre/llite/lloop.c +++ b/drivers/staging/lustre/lustre/llite/lloop.c @@ -187,7 +187,7 @@ static int do_bio_lustrebacked(struct lloop_device *lo, struct bio *head) { const struct lu_env *env = lo->lo_env; struct cl_io *io = &lo->lo_io; - struct inode *inode = lo->lo_backing_file->f_dentry->d_inode; + struct inode *inode = file_inode(lo->lo_backing_file); struct cl_object *obj = ll_i2info(inode)->lli_clob; pgoff_t offset; int ret; @@ -626,7 +626,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, break; } if (inode == NULL) - inode = lo->lo_backing_file->f_dentry->d_inode; + inode = file_inode(lo->lo_backing_file); if (lo->lo_state == LLOOP_BOUND) fid = ll_i2info(inode)->lli_fid; else @@ -692,8 +692,7 @@ static enum llioc_iter lloop_ioctl(struct inode *unused, struct file *file, lo_free = lo; continue; } - if (lo->lo_backing_file->f_dentry->d_inode == - file->f_dentry->d_inode) + if (file_inode(lo->lo_backing_file) == file_inode(file)) break; } if (lo || !lo_free) { diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c index 7a68c1e027e0..8e926b385a60 100644 --- a/drivers/staging/lustre/lustre/llite/namei.c +++ b/drivers/staging/lustre/lustre/llite/namei.c @@ -54,27 +54,6 @@ static int ll_create_it(struct inode *, struct dentry *, int, struct lookup_intent *); -/* - * Check if we have something mounted at the named dchild. - * In such a case there would always be dentry present. - */ -static int ll_d_mountpoint(struct dentry *dparent, struct dentry *dchild, - struct qstr *name) -{ - int mounted = 0; - - if (unlikely(dchild)) { - mounted = d_mountpoint(dchild); - } else if (dparent) { - dchild = d_lookup(dparent, name); - if (dchild) { - mounted = d_mountpoint(dchild); - dput(dchild); - } - } - return mounted; -} - /* called from iget5_locked->find_inode() under inode_hash_lock spinlock */ static int ll_test_inode(struct inode *inode, void *opaque) { @@ -167,14 +146,14 @@ static void ll_invalidate_negative_children(struct inode *dir) struct ll_d_hlist_node *p; ll_lock_dcache(dir); - ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_alias) { + ll_d_hlist_for_each_entry(dentry, p, &dir->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!list_empty(&dentry->d_subdirs)) { struct dentry *child; list_for_each_entry_safe(child, tmp_subdir, &dentry->d_subdirs, - d_u.d_child) { + d_child) { if (child->d_inode == NULL) d_lustre_invalidate(child, 1); } @@ -285,7 +264,7 @@ int ll_md_blocking_ast(struct ldlm_lock *lock, struct ldlm_lock_desc *desc, if ((bits & (MDS_INODELOCK_LOOKUP | MDS_INODELOCK_PERM)) && inode->i_sb->s_root != NULL && - inode != inode->i_sb->s_root->d_inode) + is_root_inode(inode)) ll_invalidate_aliases(inode); iput(inode); @@ -362,7 +341,7 @@ static struct dentry *ll_find_alias(struct inode *inode, struct dentry *dentry) discon_alias = invalid_alias = NULL; ll_lock_dcache(inode); - ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { + ll_d_hlist_for_each_entry(alias, p, &inode->i_dentry, d_u.d_alias) { LASSERT(alias != dentry); spin_lock(&alias->d_lock); @@ -509,8 +488,8 @@ static struct dentry *ll_lookup_it(struct inode *parent, struct dentry *dentry, if (dentry->d_name.len > ll_i2sbi(parent)->ll_namelen) return ERR_PTR(-ENAMETOOLONG); - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p),intent=%s\n", - dentry->d_name.len, dentry->d_name.name, parent->i_ino, + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p),intent=%s\n", + dentry, parent->i_ino, parent->i_generation, parent, LL_IT2STR(it)); if (d_mountpoint(dentry)) @@ -563,7 +542,7 @@ static struct dentry *ll_lookup_it(struct inode *parent, struct dentry *dentry, if ((it->it_op & IT_OPEN) && dentry->d_inode && !S_ISREG(dentry->d_inode->i_mode) && !S_ISDIR(dentry->d_inode->i_mode)) { - ll_release_openhandle(dentry, it); + ll_release_openhandle(dentry->d_inode, it); } ll_lookup_finish_locks(it, dentry); @@ -586,8 +565,8 @@ static struct dentry *ll_lookup_nd(struct inode *parent, struct dentry *dentry, struct lookup_intent *itp, it = { .it_op = IT_GETATTR }; struct dentry *de; - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p),flags=%u\n", - dentry->d_name.len, dentry->d_name.name, parent->i_ino, + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p),flags=%u\n", + dentry, parent->i_ino, parent->i_generation, parent, flags); /* Optimize away (CREATE && !OPEN). Let .create handle the race. */ @@ -619,9 +598,9 @@ static int ll_atomic_open(struct inode *dir, struct dentry *dentry, long long lookup_flags = LOOKUP_OPEN; int rc = 0; - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p),file %p," + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p),file %p," "open_flags %x,mode %x opened %d\n", - dentry->d_name.len, dentry->d_name.name, dir->i_ino, + dentry, dir->i_ino, dir->i_generation, dir, file, open_flags, mode, *opened); it = kzalloc(sizeof(*it), GFP_NOFS); @@ -741,8 +720,8 @@ static int ll_create_it(struct inode *dir, struct dentry *dentry, int mode, struct inode *inode; int rc = 0; - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p),intent=%s\n", - dentry->d_name.len, dentry->d_name.name, dir->i_ino, + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p),intent=%s\n", + dentry, dir->i_ino, dir->i_generation, dir, LL_IT2STR(it)); rc = it_open_error(DISP_OPEN_CREATE, it); @@ -775,9 +754,9 @@ static void ll_update_times(struct ptlrpc_request *request, LTIME_S(inode->i_ctime) = body->ctime; } -static int ll_new_node(struct inode *dir, struct qstr *name, +static int ll_new_node(struct inode *dir, struct dentry *dentry, const char *tgt, int mode, int rdev, - struct dentry *dchild, __u32 opc) + __u32 opc) { struct ptlrpc_request *request = NULL; struct md_op_data *op_data; @@ -789,8 +768,10 @@ static int ll_new_node(struct inode *dir, struct qstr *name, if (unlikely(tgt != NULL)) tgt_len = strlen(tgt) + 1; - op_data = ll_prep_md_op_data(NULL, dir, NULL, name->name, - name->len, 0, opc, NULL); + op_data = ll_prep_md_op_data(NULL, dir, NULL, + dentry->d_name.name, + dentry->d_name.len, + 0, opc, NULL); if (IS_ERR(op_data)) { err = PTR_ERR(op_data); goto err_exit; @@ -806,27 +787,25 @@ static int ll_new_node(struct inode *dir, struct qstr *name, ll_update_times(request, dir); - if (dchild) { - err = ll_prep_inode(&inode, request, dchild->d_sb, NULL); - if (err) - goto err_exit; + err = ll_prep_inode(&inode, request, dir->i_sb, NULL); + if (err) + goto err_exit; - d_instantiate(dchild, inode); - } + d_instantiate(dentry, inode); err_exit: ptlrpc_req_finished(request); return err; } -static int ll_mknod_generic(struct inode *dir, struct qstr *name, int mode, - unsigned rdev, struct dentry *dchild) +static int ll_mknod(struct inode *dir, struct dentry *dchild, + umode_t mode, dev_t rdev) { int err; - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p) mode %o dev %x\n", - name->len, name->name, dir->i_ino, dir->i_generation, dir, - mode, rdev); + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p) mode %o dev %x\n", + dchild, dir->i_ino, dir->i_generation, dir, + mode, old_encode_dev(rdev)); if (!IS_POSIXACL(dir) || !exp_connect_umask(ll_i2mdexp(dir))) mode &= ~current_umask(); @@ -839,7 +818,8 @@ static int ll_mknod_generic(struct inode *dir, struct qstr *name, int mode, case S_IFBLK: case S_IFIFO: case S_IFSOCK: - err = ll_new_node(dir, name, NULL, mode, rdev, dchild, + err = ll_new_node(dir, dchild, NULL, mode, + old_encode_dev(rdev), LUSTRE_OPC_MKNOD); break; case S_IFDIR: @@ -863,134 +843,25 @@ static int ll_create_nd(struct inode *dir, struct dentry *dentry, { int rc; - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p)," + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p)," "flags=%u, excl=%d\n", - dentry->d_name.len, dentry->d_name.name, dir->i_ino, + dentry, dir->i_ino, dir->i_generation, dir, mode, want_excl); - rc = ll_mknod_generic(dir, &dentry->d_name, mode, 0, dentry); + rc = ll_mknod(dir, dentry, mode, 0); ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_CREATE, 1); - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s, unhashed %d\n", - dentry->d_name.len, dentry->d_name.name, d_unhashed(dentry)); + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, unhashed %d\n", + dentry, d_unhashed(dentry)); return rc; } -static int ll_symlink_generic(struct inode *dir, struct qstr *name, - const char *tgt, struct dentry *dchild) +static inline void ll_get_child_fid(struct dentry *child, struct lu_fid *fid) { - int err; - - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p),target=%.*s\n", - name->len, name->name, dir->i_ino, dir->i_generation, - dir, 3000, tgt); - - err = ll_new_node(dir, name, (char *)tgt, S_IFLNK | S_IRWXUGO, - 0, dchild, LUSTRE_OPC_SYMLINK); - - if (!err) - ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_SYMLINK, 1); - - return err; -} - -static int ll_link_generic(struct inode *src, struct inode *dir, - struct qstr *name, struct dentry *dchild) -{ - struct ll_sb_info *sbi = ll_i2sbi(dir); - struct ptlrpc_request *request = NULL; - struct md_op_data *op_data; - int err; - - CDEBUG(D_VFSTRACE, - "VFS Op: inode=%lu/%u(%p), dir=%lu/%u(%p), target=%.*s\n", - src->i_ino, src->i_generation, src, dir->i_ino, - dir->i_generation, dir, name->len, name->name); - - op_data = ll_prep_md_op_data(NULL, src, dir, name->name, name->len, - 0, LUSTRE_OPC_ANY, NULL); - if (IS_ERR(op_data)) - return PTR_ERR(op_data); - - err = md_link(sbi->ll_md_exp, op_data, &request); - ll_finish_md_op_data(op_data); - if (err) - goto out; - - ll_update_times(request, dir); - ll_stats_ops_tally(sbi, LPROC_LL_LINK, 1); -out: - ptlrpc_req_finished(request); - return err; -} - -static int ll_mkdir_generic(struct inode *dir, struct qstr *name, - int mode, struct dentry *dchild) - -{ - int err; - - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p)\n", - name->len, name->name, dir->i_ino, dir->i_generation, dir); - - if (!IS_POSIXACL(dir) || !exp_connect_umask(ll_i2mdexp(dir))) - mode &= ~current_umask(); - mode = (mode & (S_IRWXUGO|S_ISVTX)) | S_IFDIR; - err = ll_new_node(dir, name, NULL, mode, 0, dchild, LUSTRE_OPC_MKDIR); - - if (!err) - ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_MKDIR, 1); - - return err; -} - -/* Try to find the child dentry by its name. - If found, put the result fid into @fid. */ -static void ll_get_child_fid(struct inode * dir, struct qstr *name, - struct lu_fid *fid) -{ - struct dentry *parent, *child; - - parent = ll_d_hlist_entry(dir->i_dentry, struct dentry, d_alias); - child = d_lookup(parent, name); - if (child) { - if (child->d_inode) - *fid = *ll_inode2fid(child->d_inode); - dput(child); - } -} - -static int ll_rmdir_generic(struct inode *dir, struct dentry *dparent, - struct dentry *dchild, struct qstr *name) -{ - struct ptlrpc_request *request = NULL; - struct md_op_data *op_data; - int rc; - - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p)\n", - name->len, name->name, dir->i_ino, dir->i_generation, dir); - - if (unlikely(ll_d_mountpoint(dparent, dchild, name))) - return -EBUSY; - - op_data = ll_prep_md_op_data(NULL, dir, NULL, name->name, name->len, - S_IFDIR, LUSTRE_OPC_ANY, NULL); - if (IS_ERR(op_data)) - return PTR_ERR(op_data); - - ll_get_child_fid(dir, name, &op_data->op_fid3); - op_data->op_fid2 = op_data->op_fid3; - rc = md_unlink(ll_i2sbi(dir)->ll_md_exp, op_data, &request); - ll_finish_md_op_data(op_data); - if (rc == 0) { - ll_update_times(request, dir); - ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_RMDIR, 1); - } - - ptlrpc_req_finished(request); - return rc; + if (child->d_inode) + *fid = *ll_inode2fid(child->d_inode); } /** @@ -1099,32 +970,26 @@ out: return rc; } -/* ll_unlink_generic() doesn't update the inode with the new link count. +/* ll_unlink() doesn't update the inode with the new link count. * Instead, ll_ddelete() and ll_d_iput() will update it based upon if there * is any lock existing. They will recycle dentries and inodes based upon locks * too. b=20433 */ -static int ll_unlink_generic(struct inode *dir, struct dentry *dparent, - struct dentry *dchild, struct qstr *name) +static int ll_unlink(struct inode * dir, struct dentry *dentry) { struct ptlrpc_request *request = NULL; struct md_op_data *op_data; int rc; - CDEBUG(D_VFSTRACE, "VFS Op:name=%.*s,dir=%lu/%u(%p)\n", - name->len, name->name, dir->i_ino, dir->i_generation, dir); - - /* - * XXX: unlink bind mountpoint maybe call to here, - * just check it as vfs_unlink does. - */ - if (unlikely(ll_d_mountpoint(dparent, dchild, name))) - return -EBUSY; + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p)\n", + dentry, dir->i_ino, dir->i_generation, dir); - op_data = ll_prep_md_op_data(NULL, dir, NULL, name->name, - name->len, 0, LUSTRE_OPC_ANY, NULL); + op_data = ll_prep_md_op_data(NULL, dir, NULL, + dentry->d_name.name, + dentry->d_name.len, + 0, LUSTRE_OPC_ANY, NULL); if (IS_ERR(op_data)) return PTR_ERR(op_data); - ll_get_child_fid(dir, name, &op_data->op_fid3); + ll_get_child_fid(dentry, &op_data->op_fid3); op_data->op_fid2 = op_data->op_fid3; rc = md_unlink(ll_i2sbi(dir)->ll_md_exp, op_data, &request); ll_finish_md_op_data(op_data); @@ -1140,95 +1005,140 @@ static int ll_unlink_generic(struct inode *dir, struct dentry *dparent, return rc; } -static int ll_rename_generic(struct inode *src, struct dentry *src_dparent, - struct dentry *src_dchild, struct qstr *src_name, - struct inode *tgt, struct dentry *tgt_dparent, - struct dentry *tgt_dchild, struct qstr *tgt_name) +static int ll_mkdir(struct inode *dir, struct dentry *dentry, ll_umode_t mode) { - struct ptlrpc_request *request = NULL; - struct ll_sb_info *sbi = ll_i2sbi(src); - struct md_op_data *op_data; int err; - CDEBUG(D_VFSTRACE, - "VFS Op:oldname=%.*s,src_dir=%lu/%u(%p),newname=%.*s," - "tgt_dir=%lu/%u(%p)\n", src_name->len, src_name->name, - src->i_ino, src->i_generation, src, tgt_name->len, - tgt_name->name, tgt->i_ino, tgt->i_generation, tgt); + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p)\n", + dentry, dir->i_ino, dir->i_generation, dir); - if (unlikely(ll_d_mountpoint(src_dparent, src_dchild, src_name) || - ll_d_mountpoint(tgt_dparent, tgt_dchild, tgt_name))) - return -EBUSY; + if (!IS_POSIXACL(dir) || !exp_connect_umask(ll_i2mdexp(dir))) + mode &= ~current_umask(); + mode = (mode & (S_IRWXUGO|S_ISVTX)) | S_IFDIR; + err = ll_new_node(dir, dentry, NULL, mode, 0, LUSTRE_OPC_MKDIR); - op_data = ll_prep_md_op_data(NULL, src, tgt, NULL, 0, 0, - LUSTRE_OPC_ANY, NULL); + if (!err) + ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_MKDIR, 1); + + return err; +} + +static int ll_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct ptlrpc_request *request = NULL; + struct md_op_data *op_data; + int rc; + + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p)\n", + dentry, dir->i_ino, dir->i_generation, dir); + + op_data = ll_prep_md_op_data(NULL, dir, NULL, + dentry->d_name.name, + dentry->d_name.len, + S_IFDIR, LUSTRE_OPC_ANY, NULL); if (IS_ERR(op_data)) return PTR_ERR(op_data); - ll_get_child_fid(src, src_name, &op_data->op_fid3); - ll_get_child_fid(tgt, tgt_name, &op_data->op_fid4); - err = md_rename(sbi->ll_md_exp, op_data, - src_name->name, src_name->len, - tgt_name->name, tgt_name->len, &request); + ll_get_child_fid(dentry, &op_data->op_fid3); + op_data->op_fid2 = op_data->op_fid3; + rc = md_unlink(ll_i2sbi(dir)->ll_md_exp, op_data, &request); ll_finish_md_op_data(op_data); - if (!err) { - ll_update_times(request, src); - ll_update_times(request, tgt); - ll_stats_ops_tally(sbi, LPROC_LL_RENAME, 1); - err = ll_objects_destroy(request, src); + if (rc == 0) { + ll_update_times(request, dir); + ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_RMDIR, 1); } ptlrpc_req_finished(request); - - return err; + return rc; } -static int ll_mknod(struct inode *dir, struct dentry *dchild, ll_umode_t mode, - dev_t rdev) +static int ll_symlink(struct inode *dir, struct dentry *dentry, + const char *oldname) { - return ll_mknod_generic(dir, &dchild->d_name, mode, - old_encode_dev(rdev), dchild); -} + int err; -static int ll_unlink(struct inode * dir, struct dentry *dentry) -{ - return ll_unlink_generic(dir, NULL, dentry, &dentry->d_name); -} + CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p),target=%.*s\n", + dentry, dir->i_ino, dir->i_generation, + dir, 3000, oldname); -static int ll_mkdir(struct inode *dir, struct dentry *dentry, ll_umode_t mode) -{ - return ll_mkdir_generic(dir, &dentry->d_name, mode, dentry); -} + err = ll_new_node(dir, dentry, oldname, S_IFLNK | S_IRWXUGO, + 0, LUSTRE_OPC_SYMLINK); -static int ll_rmdir(struct inode *dir, struct dentry *dentry) -{ - return ll_rmdir_generic(dir, NULL, dentry, &dentry->d_name); -} + if (!err) + ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_SYMLINK, 1); -static int ll_symlink(struct inode *dir, struct dentry *dentry, - const char *oldname) -{ - return ll_symlink_generic(dir, &dentry->d_name, oldname, dentry); + return err; } static int ll_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { - return ll_link_generic(old_dentry->d_inode, dir, &new_dentry->d_name, - new_dentry); + struct inode *src = old_dentry->d_inode; + struct ll_sb_info *sbi = ll_i2sbi(dir); + struct ptlrpc_request *request = NULL; + struct md_op_data *op_data; + int err; + + CDEBUG(D_VFSTRACE, + "VFS Op: inode=%lu/%u(%p), dir=%lu/%u(%p), target=%pd\n", + src->i_ino, src->i_generation, src, dir->i_ino, + dir->i_generation, dir, new_dentry); + + op_data = ll_prep_md_op_data(NULL, src, dir, new_dentry->d_name.name, + new_dentry->d_name.len, + 0, LUSTRE_OPC_ANY, NULL); + if (IS_ERR(op_data)) + return PTR_ERR(op_data); + + err = md_link(sbi->ll_md_exp, op_data, &request); + ll_finish_md_op_data(op_data); + if (err) + goto out; + + ll_update_times(request, dir); + ll_stats_ops_tally(sbi, LPROC_LL_LINK, 1); +out: + ptlrpc_req_finished(request); + return err; } static int ll_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { + struct ptlrpc_request *request = NULL; + struct ll_sb_info *sbi = ll_i2sbi(old_dir); + struct md_op_data *op_data; int err; - err = ll_rename_generic(old_dir, NULL, - old_dentry, &old_dentry->d_name, - new_dir, NULL, new_dentry, - &new_dentry->d_name); + + CDEBUG(D_VFSTRACE, + "VFS Op:oldname=%pd,src_dir=%lu/%u(%p),newname=%pd," + "tgt_dir=%lu/%u(%p)\n", old_dentry, + old_dir->i_ino, old_dir->i_generation, old_dir, new_dentry, + new_dir->i_ino, new_dir->i_generation, new_dir); + + op_data = ll_prep_md_op_data(NULL, old_dir, new_dir, NULL, 0, 0, + LUSTRE_OPC_ANY, NULL); + if (IS_ERR(op_data)) + return PTR_ERR(op_data); + + ll_get_child_fid(old_dentry, &op_data->op_fid3); + ll_get_child_fid(new_dentry, &op_data->op_fid4); + err = md_rename(sbi->ll_md_exp, op_data, + old_dentry->d_name.name, + old_dentry->d_name.len, + new_dentry->d_name.name, + new_dentry->d_name.len, &request); + ll_finish_md_op_data(op_data); if (!err) { - d_move(old_dentry, new_dentry); + ll_update_times(request, old_dir); + ll_update_times(request, new_dir); + ll_stats_ops_tally(sbi, LPROC_LL_RENAME, 1); + err = ll_objects_destroy(request, old_dir); } + + ptlrpc_req_finished(request); + if (!err) + d_move(old_dentry, new_dentry); return err; } diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c index 06b71bcf97a7..09d965e76842 100644 --- a/drivers/staging/lustre/lustre/llite/statahead.c +++ b/drivers/staging/lustre/lustre/llite/statahead.c @@ -969,8 +969,8 @@ static int ll_agl_thread(void *arg) struct l_wait_info lwi = { 0 }; thread->t_pid = current_pid(); - CDEBUG(D_READA, "agl thread started: sai %p, parent %.*s\n", - sai, parent->d_name.len, parent->d_name.name); + CDEBUG(D_READA, "agl thread started: sai %p, parent %pd\n", + sai, parent); atomic_inc(&sbi->ll_agl_total); spin_lock(&plli->lli_agl_lock); @@ -1019,8 +1019,8 @@ static int ll_agl_thread(void *arg) spin_unlock(&plli->lli_agl_lock); wake_up(&thread->t_ctl_waitq); ll_sai_put(sai); - CDEBUG(D_READA, "agl thread stopped: sai %p, parent %.*s\n", - sai, parent->d_name.len, parent->d_name.name); + CDEBUG(D_READA, "agl thread stopped: sai %p, parent %pd\n", + sai, parent); return 0; } @@ -1031,8 +1031,8 @@ static void ll_start_agl(struct dentry *parent, struct ll_statahead_info *sai) struct ll_inode_info *plli; struct task_struct *task; - CDEBUG(D_READA, "start agl thread: sai %p, parent %.*s\n", - sai, parent->d_name.len, parent->d_name.name); + CDEBUG(D_READA, "start agl thread: sai %p, parent %pd\n", + sai, parent); plli = ll_i2info(parent->d_inode); task = kthread_run(ll_agl_thread, parent, @@ -1066,8 +1066,8 @@ static int ll_statahead_thread(void *arg) struct l_wait_info lwi = { 0 }; thread->t_pid = current_pid(); - CDEBUG(D_READA, "statahead thread starting: sai %p, parent %.*s\n", - sai, parent->d_name.len, parent->d_name.name); + CDEBUG(D_READA, "statahead thread starting: sai %p, parent %pd\n", + sai, parent); if (sbi->ll_flags & LL_SBI_AGL_ENABLED) ll_start_agl(parent, sai); @@ -1288,8 +1288,8 @@ out: wake_up(&thread->t_ctl_waitq); ll_sai_put(sai); dput(parent); - CDEBUG(D_READA, "statahead thread stopped: sai %p, parent %.*s\n", - sai, parent->d_name.len, parent->d_name.name); + CDEBUG(D_READA, "statahead thread stopped: sai %p, parent %pd\n", + sai, parent); return rc; } @@ -1612,10 +1612,9 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp, } else if ((*dentryp)->d_inode != inode) { /* revalidate, but inode is recreated */ CDEBUG(D_READA, - "stale dentry %.*s inode %lu/%u, " + "stale dentry %pd inode %lu/%u, " "statahead inode %lu/%u\n", - (*dentryp)->d_name.len, - (*dentryp)->d_name.name, + *dentryp, (*dentryp)->d_inode->i_ino, (*dentryp)->d_inode->i_generation, inode->i_ino, @@ -1666,9 +1665,9 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp, if (unlikely(sai->sai_inode != parent->d_inode)) { struct ll_inode_info *nlli = ll_i2info(parent->d_inode); - CWARN("Race condition, someone changed %.*s just now: " + CWARN("Race condition, someone changed %pd just now: " "old parent "DFID", new parent "DFID"\n", - (*dentryp)->d_name.len, (*dentryp)->d_name.name, + *dentryp, PFID(&lli->lli_fid), PFID(&nlli->lli_fid)); dput(parent); iput(sai->sai_inode); @@ -1676,8 +1675,8 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp, goto out; } - CDEBUG(D_READA, "start statahead thread: sai %p, parent %.*s\n", - sai, parent->d_name.len, parent->d_name.name); + CDEBUG(D_READA, "start statahead thread: sai %p, parent %pd\n", + sai, parent); /* The sai buffer already has one reference taken at allocation time, * but as soon as we expose the sai by attaching it to the lli that diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c index d3f967a78138..e540a6d286f8 100644 --- a/drivers/staging/lustre/lustre/llite/vvp_io.c +++ b/drivers/staging/lustre/lustre/llite/vvp_io.c @@ -108,7 +108,7 @@ static int vvp_io_fault_iter_init(const struct lu_env *env, struct inode *inode = ccc_object_inode(ios->cis_obj); LASSERT(inode == - cl2ccc_io(env, ios)->cui_fd->fd_file->f_dentry->d_inode); + file_inode(cl2ccc_io(env, ios)->cui_fd->fd_file)); vio->u.fault.ft_mtime = LTIME_S(inode->i_mtime); return 0; } @@ -239,7 +239,7 @@ static int vvp_mmap_locks(const struct lu_env *env, down_read(&mm->mmap_sem); while ((vma = our_vma(mm, addr, count)) != NULL) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = file_inode(vma->vm_file); int flags = CEF_MUST; if (ll_file_nolock(vma->vm_file)) { diff --git a/drivers/staging/lustre/lustre/llite/xattr.c b/drivers/staging/lustre/lustre/llite/xattr.c index 252a6194ed9b..3151baf5585c 100644 --- a/drivers/staging/lustre/lustre/llite/xattr.c +++ b/drivers/staging/lustre/lustre/llite/xattr.c @@ -241,14 +241,11 @@ int ll_setxattr(struct dentry *dentry, const char *name, lump->lmm_stripe_offset = -1; if (lump != NULL && S_ISREG(inode->i_mode)) { - struct file f; int flags = FMODE_WRITE; int lum_size = (lump->lmm_magic == LOV_USER_MAGIC_V1) ? sizeof(*lump) : sizeof(struct lov_user_md_v3); - memset(&f, 0, sizeof(f)); /* f.f_flags is used below */ - f.f_dentry = dentry; - rc = ll_lov_setstripe_ea_info(inode, &f, flags, lump, + rc = ll_lov_setstripe_ea_info(inode, dentry, flags, lump, lum_size); /* b10667: rc always be 0 here for now */ rc = 0; @@ -519,8 +516,8 @@ ssize_t ll_getxattr(struct dentry *dentry, const char *name, } if (size < lmmsize) { - CERROR("server bug: replied size %d > %d for %s (%s)\n", - lmmsize, (int)size, dentry->d_name.name, name); + CERROR("server bug: replied size %d > %d for %pd (%s)\n", + lmmsize, (int)size, dentry, name); rc = -ERANGE; goto out; } diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c index 4aa56ba78f32..6d9ef39810c8 100644 --- a/drivers/video/fbdev/gbefb.c +++ b/drivers/video/fbdev/gbefb.c @@ -54,7 +54,8 @@ struct gbefb_par { #endif #endif #ifdef CONFIG_X86 -#define pgprot_fb(_prot) ((_prot) | _PAGE_PCD) +#define pgprot_fb(_prot) (((_prot) & ~_PAGE_CACHE_MASK) | \ + cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)) #endif /* diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c index 5f930aeccf1f..6b70d7f62b2f 100644 --- a/drivers/video/fbdev/vermilion/vermilion.c +++ b/drivers/video/fbdev/vermilion/vermilion.c @@ -1003,13 +1003,15 @@ static int vmlfb_mmap(struct fb_info *info, struct vm_area_struct *vma) struct vml_info *vinfo = container_of(info, struct vml_info, info); unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; int ret; + unsigned long prot; ret = vmlfb_vram_offset(vinfo, offset); if (ret) return -EINVAL; - pgprot_val(vma->vm_page_prot) |= _PAGE_PCD; - pgprot_val(vma->vm_page_prot) &= ~_PAGE_PWT; + prot = pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK; + pgprot_val(vma->vm_page_prot) = + prot | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS); return vm_iomap_memory(vma, vinfo->vram_start, vinfo->vram_contig_size); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 296482fc77a9..9ee5343d4884 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -832,7 +832,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, * moved b under k and client parallely did a lookup for * k/b. */ - res = d_materialise_unique(dentry, inode); + res = d_splice_alias(inode, dentry); if (!res) v9fs_fid_add(dentry, fid); else if (!IS_ERR(res)) diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 02b64f4e576a..6054c16b8fae 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -826,8 +826,8 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, struct dentry *dir_dentry; struct posix_acl *dacl = NULL, *pacl = NULL; - p9_debug(P9_DEBUG_VFS, " %lu,%s mode: %hx MAJOR: %u MINOR: %u\n", - dir->i_ino, dentry->d_name.name, omode, + p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n", + dir->i_ino, dentry, omode, MAJOR(rdev), MINOR(rdev)); if (!new_valid_dev(rdev)) diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index abc853968fed..937ce8754b24 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -125,7 +125,7 @@ affs_fix_dcache(struct inode *inode, u32 entry_ino) { struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { if (entry_ino == (u32)(long)dentry->d_fsdata) { dentry->d_fsdata = (void *)inode->i_ino; break; diff --git a/fs/affs/inode.c b/fs/affs/inode.c index e217c511459b..d0609a282e1d 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -348,9 +348,9 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3 u32 block = 0; int retval; - pr_debug("%s(dir=%u, inode=%u, \"%*s\", type=%d)\n", + pr_debug("%s(dir=%u, inode=%u, \"%pd\", type=%d)\n", __func__, (u32)dir->i_ino, - (u32)inode->i_ino, (int)dentry->d_name.len, dentry->d_name.name, type); + (u32)inode->i_ino, dentry, type); retval = -EIO; bh = affs_bread(sb, inode->i_ino); diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 035bd31556fc..bbc38530e924 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -190,8 +190,7 @@ affs_find_entry(struct inode *dir, struct dentry *dentry) toupper_t toupper = affs_get_toupper(sb); u32 key; - pr_debug("%s(\"%.*s\")\n", - __func__, (int)dentry->d_name.len, dentry->d_name.name); + pr_debug("%s(\"%pd\")\n", __func__, dentry); bh = affs_bread(sb, dir->i_ino); if (!bh) @@ -219,8 +218,7 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) struct buffer_head *bh; struct inode *inode = NULL; - pr_debug("%s(\"%.*s\")\n", - __func__, (int)dentry->d_name.len, dentry->d_name.name); + pr_debug("%s(\"%pd\")\n", __func__, dentry); affs_lock_dir(dir); bh = affs_find_entry(dir, dentry); @@ -250,9 +248,9 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) int affs_unlink(struct inode *dir, struct dentry *dentry) { - pr_debug("%s(dir=%d, %lu \"%.*s\")\n", + pr_debug("%s(dir=%d, %lu \"%pd\")\n", __func__, (u32)dir->i_ino, dentry->d_inode->i_ino, - (int)dentry->d_name.len, dentry->d_name.name); + dentry); return affs_remove_header(dentry); } @@ -264,9 +262,8 @@ affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) struct inode *inode; int error; - pr_debug("%s(%lu,\"%.*s\",0%ho)\n", - __func__, dir->i_ino, (int)dentry->d_name.len, - dentry->d_name.name,mode); + pr_debug("%s(%lu,\"%pd\",0%ho)\n", + __func__, dir->i_ino, dentry, mode); inode = affs_new_inode(dir); if (!inode) @@ -294,9 +291,8 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct inode *inode; int error; - pr_debug("%s(%lu,\"%.*s\",0%ho)\n", - __func__, dir->i_ino, (int)dentry->d_name.len, - dentry->d_name.name, mode); + pr_debug("%s(%lu,\"%pd\",0%ho)\n", + __func__, dir->i_ino, dentry, mode); inode = affs_new_inode(dir); if (!inode) @@ -321,9 +317,9 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) int affs_rmdir(struct inode *dir, struct dentry *dentry) { - pr_debug("%s(dir=%u, %lu \"%.*s\")\n", + pr_debug("%s(dir=%u, %lu \"%pd\")\n", __func__, (u32)dir->i_ino, dentry->d_inode->i_ino, - (int)dentry->d_name.len, dentry->d_name.name); + dentry); return affs_remove_header(dentry); } @@ -338,9 +334,8 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) int i, maxlen, error; char c, lc; - pr_debug("%s(%lu,\"%.*s\" -> \"%s\")\n", - __func__, dir->i_ino, (int)dentry->d_name.len, - dentry->d_name.name, symname); + pr_debug("%s(%lu,\"%pd\" -> \"%s\")\n", + __func__, dir->i_ino, dentry, symname); maxlen = AFFS_SB(sb)->s_hashsize * sizeof(u32) - 1; inode = affs_new_inode(dir); @@ -409,9 +404,9 @@ affs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = old_dentry->d_inode; - pr_debug("%s(%u, %u, \"%.*s\")\n", + pr_debug("%s(%u, %u, \"%pd\")\n", __func__, (u32)inode->i_ino, (u32)dir->i_ino, - (int)dentry->d_name.len,dentry->d_name.name); + dentry); return affs_add_entry(dir, inode, dentry, ST_LINKFILE); } @@ -424,10 +419,9 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry, struct buffer_head *bh = NULL; int retval; - pr_debug("%s(old=%u,\"%*s\" to new=%u,\"%*s\")\n", - __func__, (u32)old_dir->i_ino, (int)old_dentry->d_name.len, - old_dentry->d_name.name, (u32)new_dir->i_ino, - (int)new_dentry->d_name.len, new_dentry->d_name.name); + pr_debug("%s(old=%u,\"%pd\" to new=%u,\"%pd\")\n", + __func__, (u32)old_dir->i_ino, old_dentry, + (u32)new_dir->i_ino, new_dentry); retval = affs_check_name(new_dentry->d_name.name, new_dentry->d_name.len, diff --git a/fs/afs/dir.c b/fs/afs/dir.c index a1645b88fe8a..4ec35e9130e1 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -26,7 +26,7 @@ static int afs_readdir(struct file *file, struct dir_context *ctx); static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); static int afs_d_delete(const struct dentry *dentry); static void afs_d_release(struct dentry *dentry); -static int afs_lookup_filldir(void *_cookie, const char *name, int nlen, +static int afs_lookup_filldir(struct dir_context *ctx, const char *name, int nlen, loff_t fpos, u64 ino, unsigned dtype); static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl); @@ -391,10 +391,11 @@ static int afs_readdir(struct file *file, struct dir_context *ctx) * - if afs_dir_iterate_block() spots this function, it'll pass the FID * uniquifier through dtype */ -static int afs_lookup_filldir(void *_cookie, const char *name, int nlen, - loff_t fpos, u64 ino, unsigned dtype) +static int afs_lookup_filldir(struct dir_context *ctx, const char *name, + int nlen, loff_t fpos, u64 ino, unsigned dtype) { - struct afs_lookup_cookie *cookie = _cookie; + struct afs_lookup_cookie *cookie = + container_of(ctx, struct afs_lookup_cookie, ctx); _enter("{%s,%u},%s,%u,,%llu,%u", cookie->name.name, cookie->name.len, name, nlen, @@ -433,7 +434,7 @@ static int afs_do_lookup(struct inode *dir, struct dentry *dentry, }; int ret; - _enter("{%lu},%p{%s},", dir->i_ino, dentry, dentry->d_name.name); + _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); /* search the directory */ ret = afs_dir_iterate(dir, &cookie.ctx, key); @@ -465,8 +466,8 @@ static struct inode *afs_try_auto_mntpt( struct afs_vnode *vnode = AFS_FS_I(dir); struct inode *inode; - _enter("%d, %p{%s}, {%x:%u}, %p", - ret, dentry, devname, vnode->fid.vid, vnode->fid.vnode, key); + _enter("%d, %p{%pd}, {%x:%u}, %p", + ret, dentry, dentry, vnode->fid.vid, vnode->fid.vnode, key); if (ret != -ENOENT || !test_bit(AFS_VNODE_AUTOCELL, &vnode->flags)) @@ -501,8 +502,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, vnode = AFS_FS_I(dir); - _enter("{%x:%u},%p{%s},", - vnode->fid.vid, vnode->fid.vnode, dentry, dentry->d_name.name); + _enter("{%x:%u},%p{%pd},", + vnode->fid.vid, vnode->fid.vnode, dentry, dentry); ASSERTCMP(dentry->d_inode, ==, NULL); @@ -588,11 +589,11 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) vnode = AFS_FS_I(dentry->d_inode); if (dentry->d_inode) - _enter("{v={%x:%u} n=%s fl=%lx},", - vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name, + _enter("{v={%x:%u} n=%pd fl=%lx},", + vnode->fid.vid, vnode->fid.vnode, dentry, vnode->flags); else - _enter("{neg n=%s}", dentry->d_name.name); + _enter("{neg n=%pd}", dentry); key = afs_request_key(AFS_FS_S(dentry->d_sb)->volume->cell); if (IS_ERR(key)) @@ -607,7 +608,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) afs_validate(dir, key); if (test_bit(AFS_VNODE_DELETED, &dir->flags)) { - _debug("%s: parent dir deleted", dentry->d_name.name); + _debug("%pd: parent dir deleted", dentry); goto out_bad; } @@ -625,16 +626,16 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) if (!dentry->d_inode) goto out_bad; if (is_bad_inode(dentry->d_inode)) { - printk("kAFS: afs_d_revalidate: %s/%s has bad inode\n", - parent->d_name.name, dentry->d_name.name); + printk("kAFS: afs_d_revalidate: %pd2 has bad inode\n", + dentry); goto out_bad; } /* if the vnode ID has changed, then the dirent points to a * different file */ if (fid.vnode != vnode->fid.vnode) { - _debug("%s: dirent changed [%u != %u]", - dentry->d_name.name, fid.vnode, + _debug("%pd: dirent changed [%u != %u]", + dentry, fid.vnode, vnode->fid.vnode); goto not_found; } @@ -643,8 +644,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) * been deleted and replaced, and the original vnode ID has * been reused */ if (fid.unique != vnode->fid.unique) { - _debug("%s: file deleted (uq %u -> %u I:%u)", - dentry->d_name.name, fid.unique, + _debug("%pd: file deleted (uq %u -> %u I:%u)", + dentry, fid.unique, vnode->fid.unique, dentry->d_inode->i_generation); spin_lock(&vnode->lock); @@ -656,14 +657,14 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) case -ENOENT: /* the filename is unknown */ - _debug("%s: dirent not found", dentry->d_name.name); + _debug("%pd: dirent not found", dentry); if (dentry->d_inode) goto not_found; goto out_valid; default: - _debug("failed to iterate dir %s: %d", - parent->d_name.name, ret); + _debug("failed to iterate dir %pd: %d", + parent, ret); goto out_bad; } @@ -681,8 +682,7 @@ not_found: spin_unlock(&dentry->d_lock); out_bad: - _debug("dropping dentry %s/%s", - parent->d_name.name, dentry->d_name.name); + _debug("dropping dentry %pd2", dentry); dput(parent); key_put(key); @@ -698,7 +698,7 @@ out_bad: */ static int afs_d_delete(const struct dentry *dentry) { - _enter("%s", dentry->d_name.name); + _enter("%pd", dentry); if (dentry->d_flags & DCACHE_NFSFS_RENAMED) goto zap; @@ -721,7 +721,7 @@ zap: */ static void afs_d_release(struct dentry *dentry) { - _enter("%s", dentry->d_name.name); + _enter("%pd", dentry); } /* @@ -740,8 +740,8 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) dvnode = AFS_FS_I(dir); - _enter("{%x:%u},{%s},%ho", - dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode); + _enter("{%x:%u},{%pd},%ho", + dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { @@ -801,8 +801,8 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) dvnode = AFS_FS_I(dir); - _enter("{%x:%u},{%s}", - dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name); + _enter("{%x:%u},{%pd}", + dvnode->fid.vid, dvnode->fid.vnode, dentry); key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { @@ -843,8 +843,8 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) dvnode = AFS_FS_I(dir); - _enter("{%x:%u},{%s}", - dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name); + _enter("{%x:%u},{%pd}", + dvnode->fid.vid, dvnode->fid.vnode, dentry); ret = -ENAMETOOLONG; if (dentry->d_name.len >= AFSNAMEMAX) @@ -917,8 +917,8 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, dvnode = AFS_FS_I(dir); - _enter("{%x:%u},{%s},%ho,", - dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode); + _enter("{%x:%u},{%pd},%ho,", + dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { @@ -980,10 +980,10 @@ static int afs_link(struct dentry *from, struct inode *dir, vnode = AFS_FS_I(from->d_inode); dvnode = AFS_FS_I(dir); - _enter("{%x:%u},{%x:%u},{%s}", + _enter("{%x:%u},{%x:%u},{%pd}", vnode->fid.vid, vnode->fid.vnode, dvnode->fid.vid, dvnode->fid.vnode, - dentry->d_name.name); + dentry); key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { @@ -1025,8 +1025,8 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, dvnode = AFS_FS_I(dir); - _enter("{%x:%u},{%s},%s", - dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, + _enter("{%x:%u},{%pd},%s", + dvnode->fid.vid, dvnode->fid.vnode, dentry, content); ret = -EINVAL; @@ -1093,11 +1093,11 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, orig_dvnode = AFS_FS_I(old_dir); new_dvnode = AFS_FS_I(new_dir); - _enter("{%x:%u},{%x:%u},{%x:%u},{%s}", + _enter("{%x:%u},{%x:%u},{%x:%u},{%pd}", orig_dvnode->fid.vid, orig_dvnode->fid.vnode, vnode->fid.vid, vnode->fid.vnode, new_dvnode->fid.vid, new_dvnode->fid.vnode, - new_dentry->d_name.name); + new_dentry); key = afs_request_key(orig_dvnode->volume->cell); if (IS_ERR(key)) { diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 294671288449..8a1d38ef0fc2 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -462,8 +462,8 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) struct key *key; int ret; - _enter("{%x:%u},{n=%s},%x", - vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name, + _enter("{%x:%u},{n=%pd},%x", + vnode->fid.vid, vnode->fid.vnode, dentry, attr->ia_valid); if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID | diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 9682c33d5daf..938c5ab06d5a 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -106,14 +106,7 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - _enter("%p,%p{%p{%s},%s}", - dir, - dentry, - dentry->d_parent, - dentry->d_parent ? - dentry->d_parent->d_name.name : (const unsigned char *) "", - dentry->d_name.name); - + _enter("%p,%p{%pd2}", dir, dentry, dentry); return ERR_PTR(-EREMOTE); } @@ -122,14 +115,7 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir, */ static int afs_mntpt_open(struct inode *inode, struct file *file) { - _enter("%p,%p{%p{%s},%s}", - inode, file, - file->f_path.dentry->d_parent, - file->f_path.dentry->d_parent ? - file->f_path.dentry->d_parent->d_name.name : - (const unsigned char *) "", - file->f_path.dentry->d_name.name); - + _enter("%p,%p{%pD2}", inode, file, file); return -EREMOTE; } @@ -146,7 +132,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) bool rwpath = false; int ret; - _enter("{%s}", mntpt->d_name.name); + _enter("{%pd}", mntpt); BUG_ON(!mntpt->d_inode); @@ -242,7 +228,7 @@ struct vfsmount *afs_d_automount(struct path *path) { struct vfsmount *newmnt; - _enter("{%s}", path->dentry->d_name.name); + _enter("{%pd}", path->dentry); newmnt = afs_mntpt_do_automount(path->dentry); if (IS_ERR(newmnt)) diff --git a/fs/afs/write.c b/fs/afs/write.c index ab6adfd52516..c13cb08964ed 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -682,14 +682,13 @@ int afs_writeback_all(struct afs_vnode *vnode) */ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = file->f_mapping->host; + struct inode *inode = file_inode(file); struct afs_writeback *wb, *xwb; - struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode); + struct afs_vnode *vnode = AFS_FS_I(inode); int ret; - _enter("{%x:%u},{n=%s},%d", - vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name, + _enter("{%x:%u},{n=%pD},%d", + vnode->fid.vid, vnode->fid.vnode, file, datasync); ret = filemap_write_and_wait_range(inode->i_mapping, start, end); diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 683a5b9ce22a..bfdbaba9c2ba 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -41,8 +41,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry) struct path path = {.mnt = mnt, .dentry = dentry}; int status = 1; - DPRINTK("dentry %p %.*s", - dentry, (int)dentry->d_name.len, dentry->d_name.name); + DPRINTK("dentry %p %pd", dentry, dentry); path_get(&path); @@ -85,7 +84,7 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev, spin_lock(&root->d_lock); if (prev) - next = prev->d_u.d_child.next; + next = prev->d_child.next; else { prev = dget_dlock(root); next = prev->d_subdirs.next; @@ -99,13 +98,13 @@ cont: return NULL; } - q = list_entry(next, struct dentry, d_u.d_child); + q = list_entry(next, struct dentry, d_child); spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED); /* Already gone or negative dentry (under construction) - try next */ if (!d_count(q) || !simple_positive(q)) { spin_unlock(&q->d_lock); - next = q->d_u.d_child.next; + next = q->d_child.next; goto cont; } dget_dlock(q); @@ -155,13 +154,13 @@ again: goto relock; } spin_unlock(&p->d_lock); - next = p->d_u.d_child.next; + next = p->d_child.next; p = parent; if (next != &parent->d_subdirs) break; } } - ret = list_entry(next, struct dentry, d_u.d_child); + ret = list_entry(next, struct dentry, d_child); spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED); /* Negative dentry - try next */ @@ -192,8 +191,7 @@ static int autofs4_direct_busy(struct vfsmount *mnt, unsigned long timeout, int do_now) { - DPRINTK("top %p %.*s", - top, (int) top->d_name.len, top->d_name.name); + DPRINTK("top %p %pd", top, top); /* If it's busy update the expiry counters */ if (!may_umount_tree(mnt)) { @@ -221,8 +219,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt, struct autofs_info *top_ino = autofs4_dentry_ino(top); struct dentry *p; - DPRINTK("top %p %.*s", - top, (int)top->d_name.len, top->d_name.name); + DPRINTK("top %p %pd", top, top); /* Negative dentry - give up */ if (!simple_positive(top)) @@ -230,8 +227,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt, p = NULL; while ((p = get_next_positive_dentry(p, top))) { - DPRINTK("dentry %p %.*s", - p, (int) p->d_name.len, p->d_name.name); + DPRINTK("dentry %p %pd", p, p); /* * Is someone visiting anywhere in the subtree ? @@ -277,13 +273,11 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt, { struct dentry *p; - DPRINTK("parent %p %.*s", - parent, (int)parent->d_name.len, parent->d_name.name); + DPRINTK("parent %p %pd", parent, parent); p = NULL; while ((p = get_next_positive_dentry(p, parent))) { - DPRINTK("dentry %p %.*s", - p, (int) p->d_name.len, p->d_name.name); + DPRINTK("dentry %p %pd", p, p); if (d_mountpoint(p)) { /* Can we umount this guy */ @@ -368,8 +362,7 @@ static struct dentry *should_expire(struct dentry *dentry, * offset (autofs-5.0+). */ if (d_mountpoint(dentry)) { - DPRINTK("checking mountpoint %p %.*s", - dentry, (int)dentry->d_name.len, dentry->d_name.name); + DPRINTK("checking mountpoint %p %pd", dentry, dentry); /* Can we umount this guy */ if (autofs4_mount_busy(mnt, dentry)) @@ -382,8 +375,7 @@ static struct dentry *should_expire(struct dentry *dentry, } if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)) { - DPRINTK("checking symlink %p %.*s", - dentry, (int)dentry->d_name.len, dentry->d_name.name); + DPRINTK("checking symlink %p %pd", dentry, dentry); /* * A symlink can't be "busy" in the usual sense so * just check last used for expire timeout. @@ -479,8 +471,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, return NULL; found: - DPRINTK("returning %p %.*s", - expired, (int)expired->d_name.len, expired->d_name.name); + DPRINTK("returning %p %pd", expired, expired); ino->flags |= AUTOFS_INF_EXPIRING; smp_mb(); ino->flags &= ~AUTOFS_INF_NO_RCU; @@ -489,7 +480,7 @@ found: spin_lock(&sbi->lookup_lock); spin_lock(&expired->d_parent->d_lock); spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); + list_move(&expired->d_parent->d_subdirs, &expired->d_child); spin_unlock(&expired->d_lock); spin_unlock(&expired->d_parent->d_lock); spin_unlock(&sbi->lookup_lock); @@ -512,8 +503,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk) if (ino->flags & AUTOFS_INF_EXPIRING) { spin_unlock(&sbi->fs_lock); - DPRINTK("waiting for expire %p name=%.*s", - dentry, dentry->d_name.len, dentry->d_name.name); + DPRINTK("waiting for expire %p name=%pd", dentry, dentry); status = autofs4_wait(sbi, dentry, NFY_NONE); wait_for_completion(&ino->expire_complete); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index d76d083f2f06..dbb5b7212ce1 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -108,8 +108,7 @@ static int autofs4_dir_open(struct inode *inode, struct file *file) struct dentry *dentry = file->f_path.dentry; struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - DPRINTK("file=%p dentry=%p %.*s", - file, dentry, dentry->d_name.len, dentry->d_name.name); + DPRINTK("file=%p dentry=%p %pD", file, dentry, dentry); if (autofs4_oz_mode(sbi)) goto out; @@ -279,8 +278,7 @@ static int autofs4_mount_wait(struct dentry *dentry, bool rcu_walk) if (ino->flags & AUTOFS_INF_PENDING) { if (rcu_walk) return -ECHILD; - DPRINTK("waiting for mount name=%.*s", - dentry->d_name.len, dentry->d_name.name); + DPRINTK("waiting for mount name=%pd", dentry); status = autofs4_wait(sbi, dentry, NFY_MOUNT); DPRINTK("mount wait done status=%d", status); } @@ -340,8 +338,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path) struct autofs_info *ino = autofs4_dentry_ino(dentry); int status; - DPRINTK("dentry=%p %.*s", - dentry, dentry->d_name.len, dentry->d_name.name); + DPRINTK("dentry=%p %pd", dentry, dentry); /* The daemon never triggers a mount. */ if (autofs4_oz_mode(sbi)) @@ -428,8 +425,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk) struct autofs_info *ino = autofs4_dentry_ino(dentry); int status; - DPRINTK("dentry=%p %.*s", - dentry, dentry->d_name.len, dentry->d_name.name); + DPRINTK("dentry=%p %pd", dentry, dentry); /* The daemon never waits. */ if (autofs4_oz_mode(sbi)) { @@ -504,7 +500,7 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u struct autofs_info *ino; struct dentry *active; - DPRINTK("name = %.*s", dentry->d_name.len, dentry->d_name.name); + DPRINTK("name = %pd", dentry); /* File name too long to exist */ if (dentry->d_name.len > NAME_MAX) @@ -558,8 +554,7 @@ static int autofs4_dir_symlink(struct inode *dir, size_t size = strlen(symname); char *cp; - DPRINTK("%s <- %.*s", symname, - dentry->d_name.len, dentry->d_name.name); + DPRINTK("%s <- %pd", symname, dentry); if (!autofs4_oz_mode(sbi)) return -EACCES; @@ -687,7 +682,7 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry) /* only consider parents below dentrys in the root */ if (IS_ROOT(parent->d_parent)) return; - d_child = &dentry->d_u.d_child; + d_child = &dentry->d_child; /* Set parent managed if it's becoming empty */ if (d_child->next == &parent->d_subdirs && d_child->prev == &parent->d_subdirs) @@ -701,8 +696,7 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) struct autofs_info *ino = autofs4_dentry_ino(dentry); struct autofs_info *p_ino; - DPRINTK("dentry %p, removing %.*s", - dentry, dentry->d_name.len, dentry->d_name.name); + DPRINTK("dentry %p, removing %pd", dentry, dentry); if (!autofs4_oz_mode(sbi)) return -EACCES; @@ -744,8 +738,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m if (!autofs4_oz_mode(sbi)) return -EACCES; - DPRINTK("dentry %p, creating %.*s", - dentry, dentry->d_name.len, dentry->d_name.name); + DPRINTK("dentry %p, creating %pd", dentry, dentry); BUG_ON(!ino); diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 4cf61ec6b7a8..b94d1cc9cd30 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -172,8 +172,8 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) char *utfname; const char *name = dentry->d_name.name; - befs_debug(sb, "---> %s name %s inode %ld", __func__, - dentry->d_name.name, dir->i_ino); + befs_debug(sb, "---> %s name %pd inode %ld", __func__, + dentry, dir->i_ino); /* Convert to UTF-8 */ if (BEFS_SB(sb)->nls) { @@ -191,8 +191,7 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) } if (ret == BEFS_BT_NOT_FOUND) { - befs_debug(sb, "<--- %s %s not found", __func__, - dentry->d_name.name); + befs_debug(sb, "<--- %s %pd not found", __func__, dentry); return ERR_PTR(-ENOENT); } else if (ret != BEFS_OK || offset == 0) { @@ -222,10 +221,9 @@ befs_readdir(struct file *file, struct dir_context *ctx) size_t keysize; unsigned char d_type; char keybuf[BEFS_NAME_LEN + 1]; - const char *dirname = file->f_path.dentry->d_name.name; - befs_debug(sb, "---> %s name %s, inode %ld, ctx->pos %lld", - __func__, dirname, inode->i_ino, ctx->pos); + befs_debug(sb, "---> %s name %pD, inode %ld, ctx->pos %lld", + __func__, file, inode->i_ino, ctx->pos); more: result = befs_btree_read(sb, ds, ctx->pos, BEFS_NAME_LEN + 1, @@ -233,8 +231,8 @@ more: if (result == BEFS_ERR) { befs_debug(sb, "<--- %s ERROR", __func__); - befs_error(sb, "IO error reading %s (inode %lu)", - dirname, inode->i_ino); + befs_error(sb, "IO error reading %pD (inode %lu)", + file, inode->i_ino); return -EIO; } else if (result == BEFS_BT_END) { diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 929dec08c348..4c556680fa74 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -292,8 +292,8 @@ static int load_aout_binary(struct linux_binprm * bprm) if ((fd_offset & ~PAGE_MASK) != 0 && printk_ratelimit()) { printk(KERN_WARNING - "fd_offset is not page aligned. Please convert program: %s\n", - bprm->file->f_path.dentry->d_name.name); + "fd_offset is not page aligned. Please convert program: %pD\n", + bprm->file); } if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) { @@ -375,8 +375,8 @@ static int load_aout_library(struct file *file) if (printk_ratelimit()) { printk(KERN_WARNING - "N_TXTOFF is not page aligned. Please convert library: %s\n", - file->f_path.dentry->d_name.name); + "N_TXTOFF is not page aligned. Please convert library: %pD\n", + file); } vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); diff --git a/fs/block_dev.c b/fs/block_dev.c index 1d9c9f3754f8..b48c41bf0f86 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -235,7 +235,10 @@ struct super_block *freeze_bdev(struct block_device *bdev) sb = get_active_super(bdev); if (!sb) goto out; - error = freeze_super(sb); + if (sb->s_op->freeze_super) + error = sb->s_op->freeze_super(sb); + else + error = freeze_super(sb); if (error) { deactivate_super(sb); bdev->bd_fsfreeze_count--; @@ -272,7 +275,10 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb) if (!sb) goto out; - error = thaw_super(sb); + if (sb->s_op->thaw_super) + error = sb->s_op->thaw_super(sb); + else + error = thaw_super(sb); if (error) { bdev->bd_fsfreeze_count++; mutex_unlock(&bdev->bd_fsfreeze_mutex); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d23362f4464e..ff0dcc016b71 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5303,7 +5303,7 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, return ERR_CAST(inode); } - return d_materialise_unique(dentry, inode); + return d_splice_alias(inode, dentry); } unsigned char btrfs_filetype_table[] = { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4399f0c3a4ce..080fe66c0349 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5296,7 +5296,7 @@ long btrfs_ioctl(struct file *file, unsigned int ret = btrfs_start_delalloc_roots(root->fs_info, 0, -1); if (ret) return ret; - ret = btrfs_sync_fs(file->f_dentry->d_sb, 1); + ret = btrfs_sync_fs(file_inode(file)->i_sb, 1); /* * The transaction thread may want to do more work, * namely it pokes the cleaner ktread that will start diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index e12f189d539b..7f8e83f9d74e 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -102,8 +102,7 @@ static void cachefiles_mark_object_buried(struct cachefiles_cache *cache, struct cachefiles_object *object; struct rb_node *p; - _enter(",'%*.*s'", - dentry->d_name.len, dentry->d_name.len, dentry->d_name.name); + _enter(",'%pd'", dentry); write_lock(&cache->active_lock); @@ -273,9 +272,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache, char nbuffer[8 + 8 + 1]; int ret; - _enter(",'%*.*s','%*.*s'", - dir->d_name.len, dir->d_name.len, dir->d_name.name, - rep->d_name.len, rep->d_name.len, rep->d_name.name); + _enter(",'%pd','%pd'", dir, rep); _debug("remove %p from %p", rep, dir); @@ -597,8 +594,7 @@ lookup_again: /* if we've found that the terminal object exists, then we need to * check its attributes and delete it if it's out of date */ if (!object->new) { - _debug("validate '%*.*s'", - next->d_name.len, next->d_name.len, next->d_name.name); + _debug("validate '%pd'", next); ret = cachefiles_check_object_xattr(object, auxdata); if (ret == -ESTALE) { @@ -827,8 +823,8 @@ static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache, unsigned long start; int ret; - //_enter(",%*.*s/,%s", - // dir->d_name.len, dir->d_name.len, dir->d_name.name, filename); + //_enter(",%pd/,%s", + // dir, filename); /* look up the victim */ mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); @@ -910,8 +906,7 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, struct dentry *victim; int ret; - _enter(",%*.*s/,%s", - dir->d_name.len, dir->d_name.len, dir->d_name.name, filename); + _enter(",%pd/,%s", dir, filename); victim = cachefiles_check_active(cache, dir, filename); if (IS_ERR(victim)) @@ -969,8 +964,8 @@ int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir, { struct dentry *victim; - //_enter(",%*.*s/,%s", - // dir->d_name.len, dir->d_name.len, dir->d_name.name, filename); + //_enter(",%pd/,%s", + // dir, filename); victim = cachefiles_check_active(cache, dir, filename); if (IS_ERR(victim)) diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index acbc1f094fb1..a8a68745e11d 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -51,9 +51,8 @@ int cachefiles_check_object_type(struct cachefiles_object *object) } if (ret != -EEXIST) { - pr_err("Can't set xattr on %*.*s [%lu] (err %d)\n", - dentry->d_name.len, dentry->d_name.len, - dentry->d_name.name, dentry->d_inode->i_ino, + pr_err("Can't set xattr on %pd [%lu] (err %d)\n", + dentry, dentry->d_inode->i_ino, -ret); goto error; } @@ -64,9 +63,8 @@ int cachefiles_check_object_type(struct cachefiles_object *object) if (ret == -ERANGE) goto bad_type_length; - pr_err("Can't read xattr on %*.*s [%lu] (err %d)\n", - dentry->d_name.len, dentry->d_name.len, - dentry->d_name.name, dentry->d_inode->i_ino, + pr_err("Can't read xattr on %pd [%lu] (err %d)\n", + dentry, dentry->d_inode->i_ino, -ret); goto error; } @@ -92,9 +90,8 @@ bad_type_length: bad_type: xtype[2] = 0; - pr_err("Cache object %*.*s [%lu] type %s not %s\n", - dentry->d_name.len, dentry->d_name.len, - dentry->d_name.name, dentry->d_inode->i_ino, + pr_err("Cache object %pd [%lu] type %s not %s\n", + dentry, dentry->d_inode->i_ino, xtype, type); ret = -EIO; goto error; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 5d5a4c8c8496..1b2355109b9f 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -83,10 +83,9 @@ static int mdsc_show(struct seq_file *s, void *p) if (IS_ERR(path)) path = NULL; spin_lock(&req->r_dentry->d_lock); - seq_printf(s, " #%llx/%.*s (%s)", + seq_printf(s, " #%llx/%pd (%s)", ceph_ino(req->r_dentry->d_parent->d_inode), - req->r_dentry->d_name.len, - req->r_dentry->d_name.name, + req->r_dentry, path ? path : ""); spin_unlock(&req->r_dentry->d_lock); kfree(path); @@ -103,11 +102,10 @@ static int mdsc_show(struct seq_file *s, void *p) if (IS_ERR(path)) path = NULL; spin_lock(&req->r_old_dentry->d_lock); - seq_printf(s, " #%llx/%.*s (%s)", + seq_printf(s, " #%llx/%pd (%s)", req->r_old_dentry_dir ? ceph_ino(req->r_old_dentry_dir) : 0, - req->r_old_dentry->d_name.len, - req->r_old_dentry->d_name.name, + req->r_old_dentry, path ? path : ""); spin_unlock(&req->r_old_dentry->d_lock); kfree(path); @@ -150,8 +148,8 @@ static int dentry_lru_show(struct seq_file *s, void *ptr) spin_lock(&mdsc->dentry_lru_lock); list_for_each_entry(di, &mdsc->dentry_lru, lru) { struct dentry *dentry = di->dentry; - seq_printf(s, "%p %p\t%.*s\n", - di, dentry, dentry->d_name.len, dentry->d_name.name); + seq_printf(s, "%p %p\t%pd\n", + di, dentry, dentry); } spin_unlock(&mdsc->dentry_lru_lock); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index e6d63f8f98c0..681a8537b64f 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -111,7 +111,7 @@ static int fpos_cmp(loff_t l, loff_t r) /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on - * d_u.d_child when we initially get results back from the MDS, and + * d_child when we initially get results back from the MDS, and * falling back to a "normal" sync readdir if any dentries in the dir * are dropped. * @@ -123,7 +123,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, u32 shared_gen) { struct ceph_file_info *fi = file->private_data; - struct dentry *parent = file->f_dentry; + struct dentry *parent = file->f_path.dentry; struct inode *dir = parent->d_inode; struct list_head *p; struct dentry *dentry, *last; @@ -147,11 +147,11 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, p = parent->d_subdirs.prev; dout(" initial p %p/%p\n", p->prev, p->next); } else { - p = last->d_u.d_child.prev; + p = last->d_child.prev; } more: - dentry = list_entry(p, struct dentry, d_u.d_child); + dentry = list_entry(p, struct dentry, d_child); di = ceph_dentry(dentry); while (1) { dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next, @@ -168,13 +168,13 @@ more: ceph_ino(dentry->d_inode) != CEPH_INO_CEPH && fpos_cmp(ctx->pos, di->offset) <= 0) break; - dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry, - dentry->d_name.len, dentry->d_name.name, di->offset, + dout(" skipping %p %pd at %llu (%llu)%s%s\n", dentry, + dentry, di->offset, ctx->pos, d_unhashed(dentry) ? " unhashed" : "", !dentry->d_inode ? " null" : ""); spin_unlock(&dentry->d_lock); p = p->prev; - dentry = list_entry(p, struct dentry, d_u.d_child); + dentry = list_entry(p, struct dentry, d_child); di = ceph_dentry(dentry); } @@ -190,8 +190,8 @@ more: goto out; } - dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, ctx->pos, - dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode); + dout(" %llu (%llu) dentry %p %pd %p\n", di->offset, ctx->pos, + dentry, dentry, dentry->d_inode); if (!dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, ceph_translate_ino(dentry->d_sb, dentry->d_inode->i_ino), @@ -274,7 +274,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx) off = 1; } if (ctx->pos == 1) { - ino_t ino = parent_ino(file->f_dentry); + ino_t ino = parent_ino(file->f_path.dentry); dout("readdir off 1 -> '..'\n"); if (!dir_emit(ctx, "..", 2, ceph_translate_ino(inode->i_sb, ino), @@ -337,7 +337,7 @@ more: } req->r_inode = inode; ihold(inode); - req->r_dentry = dget(file->f_dentry); + req->r_dentry = dget(file->f_path.dentry); /* hints to request -> mds selection code */ req->r_direct_mode = USE_AUTH_MDS; req->r_direct_hash = ceph_frag_value(frag); @@ -538,8 +538,8 @@ int ceph_handle_snapdir(struct ceph_mds_request *req, strcmp(dentry->d_name.name, fsc->mount_options->snapdir_name) == 0) { struct inode *inode = ceph_get_snapdir(parent); - dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n", - dentry, dentry->d_name.len, dentry->d_name.name, inode); + dout("ENOENT on snapdir %p '%pd', linking to snapdir %p\n", + dentry, dentry, inode); BUG_ON(!d_unhashed(dentry)); d_add(dentry, inode); err = 0; @@ -603,8 +603,8 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, int op; int err; - dout("lookup %p dentry %p '%.*s'\n", - dir, dentry, dentry->d_name.len, dentry->d_name.name); + dout("lookup %p dentry %p '%pd'\n", + dir, dentry, dentry); if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); @@ -774,8 +774,8 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (ceph_snap(dir) == CEPH_SNAPDIR) { /* mkdir .snap/foo is a MKSNAP */ op = CEPH_MDS_OP_MKSNAP; - dout("mksnap dir %p snap '%.*s' dn %p\n", dir, - dentry->d_name.len, dentry->d_name.name, dentry); + dout("mksnap dir %p snap '%pd' dn %p\n", dir, + dentry, dentry); } else if (ceph_snap(dir) == CEPH_NOSNAP) { dout("mkdir dir %p dn %p mode 0%ho\n", dir, dentry, mode); op = CEPH_MDS_OP_MKDIR; @@ -888,8 +888,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) if (ceph_snap(dir) == CEPH_SNAPDIR) { /* rmdir .snap/foo is RMSNAP */ - dout("rmsnap dir %p '%.*s' dn %p\n", dir, dentry->d_name.len, - dentry->d_name.name, dentry); + dout("rmsnap dir %p '%pd' dn %p\n", dir, dentry, dentry); op = CEPH_MDS_OP_RMSNAP; } else if (ceph_snap(dir) == CEPH_NOSNAP) { dout("unlink/rmdir dir %p dn %p inode %p\n", @@ -1063,16 +1062,15 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) if (flags & LOOKUP_RCU) return -ECHILD; - dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry, - dentry->d_name.len, dentry->d_name.name, dentry->d_inode, - ceph_dentry(dentry)->offset); + dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry, + dentry, dentry->d_inode, ceph_dentry(dentry)->offset); dir = ceph_get_dentry_parent_inode(dentry); /* always trust cached snapped dentries, snapdir dentry */ if (ceph_snap(dir) != CEPH_NOSNAP) { - dout("d_revalidate %p '%.*s' inode %p is SNAPPED\n", dentry, - dentry->d_name.len, dentry->d_name.name, dentry->d_inode); + dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry, + dentry, dentry->d_inode); valid = 1; } else if (dentry->d_inode && ceph_snap(dentry->d_inode) == CEPH_SNAPDIR) { @@ -1265,8 +1263,7 @@ void ceph_dentry_lru_add(struct dentry *dn) struct ceph_dentry_info *di = ceph_dentry(dn); struct ceph_mds_client *mdsc; - dout("dentry_lru_add %p %p '%.*s'\n", di, dn, - dn->d_name.len, dn->d_name.name); + dout("dentry_lru_add %p %p '%pd'\n", di, dn, dn); mdsc = ceph_sb_to_client(dn->d_sb)->mdsc; spin_lock(&mdsc->dentry_lru_lock); list_add_tail(&di->lru, &mdsc->dentry_lru); @@ -1279,8 +1276,8 @@ void ceph_dentry_lru_touch(struct dentry *dn) struct ceph_dentry_info *di = ceph_dentry(dn); struct ceph_mds_client *mdsc; - dout("dentry_lru_touch %p %p '%.*s' (offset %lld)\n", di, dn, - dn->d_name.len, dn->d_name.name, di->offset); + dout("dentry_lru_touch %p %p '%pd' (offset %lld)\n", di, dn, dn, + di->offset); mdsc = ceph_sb_to_client(dn->d_sb)->mdsc; spin_lock(&mdsc->dentry_lru_lock); list_move_tail(&di->lru, &mdsc->dentry_lru); @@ -1292,8 +1289,7 @@ void ceph_dentry_lru_del(struct dentry *dn) struct ceph_dentry_info *di = ceph_dentry(dn); struct ceph_mds_client *mdsc; - dout("dentry_lru_del %p %p '%.*s'\n", di, dn, - dn->d_name.len, dn->d_name.name); + dout("dentry_lru_del %p %p '%pd'\n", di, dn, dn); mdsc = ceph_sb_to_client(dn->d_sb)->mdsc; spin_lock(&mdsc->dentry_lru_lock); list_del_init(&di->lru); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d7e0da8366e6..9f8e3572040e 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -211,7 +211,7 @@ int ceph_open(struct inode *inode, struct file *file) req->r_num_caps = 1; if (flags & O_CREAT) - parent_inode = ceph_get_dentry_parent_inode(file->f_dentry); + parent_inode = ceph_get_dentry_parent_inode(file->f_path.dentry); err = ceph_mdsc_do_request(mdsc, parent_inode, req); iput(parent_inode); if (!err) @@ -238,8 +238,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, struct ceph_acls_info acls = {}; int err; - dout("atomic_open %p dentry %p '%.*s' %s flags %d mode 0%o\n", - dir, dentry, dentry->d_name.len, dentry->d_name.name, + dout("atomic_open %p dentry %p '%pd' %s flags %d mode 0%o\n", + dir, dentry, dentry, d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode); if (dentry->d_name.len > NAME_MAX) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 7b6139004401..a5593d51d035 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -967,7 +967,7 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, /* dn must be unhashed */ if (!d_unhashed(dn)) d_drop(dn); - realdn = d_materialise_unique(dn, in); + realdn = d_splice_alias(in, dn); if (IS_ERR(realdn)) { pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n", PTR_ERR(realdn), dn, in, ceph_vinop(in)); @@ -1186,20 +1186,18 @@ retry_lookup: struct inode *olddir = req->r_old_dentry_dir; BUG_ON(!olddir); - dout(" src %p '%.*s' dst %p '%.*s'\n", + dout(" src %p '%pd' dst %p '%pd'\n", req->r_old_dentry, - req->r_old_dentry->d_name.len, - req->r_old_dentry->d_name.name, - dn, dn->d_name.len, dn->d_name.name); + req->r_old_dentry, + dn, dn); dout("fill_trace doing d_move %p -> %p\n", req->r_old_dentry, dn); d_move(req->r_old_dentry, dn); - dout(" src %p '%.*s' dst %p '%.*s'\n", + dout(" src %p '%pd' dst %p '%pd'\n", + req->r_old_dentry, req->r_old_dentry, - req->r_old_dentry->d_name.len, - req->r_old_dentry->d_name.name, - dn, dn->d_name.len, dn->d_name.name); + dn, dn); /* ensure target dentry is invalidated, despite rehashing bug in vfs_rename_dir */ @@ -1399,7 +1397,7 @@ retry_lookup: /* reorder parent's d_subdirs */ spin_lock(&parent->d_lock); spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&dn->d_u.d_child, &parent->d_subdirs); + list_move(&dn->d_child, &parent->d_subdirs); spin_unlock(&dn->d_lock); spin_unlock(&parent->d_lock); } diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 44ec72684df5..9c56ef776407 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -34,27 +34,9 @@ void cifs_dump_mem(char *label, void *data, int length) { - int i, j; - int *intptr = data; - char *charptr = data; - char buf[10], line[80]; - - printk(KERN_DEBUG "%s: dump of %d bytes of data at 0x%p\n", - label, length, data); - for (i = 0; i < length; i += 16) { - line[0] = 0; - for (j = 0; (j < 4) && (i + j * 4 < length); j++) { - sprintf(buf, " %08x", intptr[i / 4 + j]); - strcat(line, buf); - } - buf[0] = ' '; - buf[2] = 0; - for (j = 0; (j < 16) && (i + j < length); j++) { - buf[1] = isprint(charptr[i + j]) ? charptr[i + j] : '.'; - strcat(line, buf); - } - printk(KERN_DEBUG "%s\n", line); - } + pr_debug("%s: dump of %d bytes of data at 0x%p\n", label, length, data); + print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 16, 4, + data, length, true); } #ifdef CONFIG_CIFS_DEBUG @@ -68,7 +50,7 @@ void cifs_vfs_err(const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - printk(KERN_ERR "CIFS VFS: %pV", &vaf); + pr_err("CIFS VFS: %pV", &vaf); va_end(args); } @@ -274,6 +256,7 @@ static ssize_t cifs_stats_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { char c; + bool bv; int rc; struct list_head *tmp1, *tmp2, *tmp3; struct TCP_Server_Info *server; @@ -284,7 +267,7 @@ static ssize_t cifs_stats_proc_write(struct file *file, if (rc) return rc; - if (c == '1' || c == 'y' || c == 'Y' || c == '0') { + if (strtobool(&c, &bv) == 0) { #ifdef CONFIG_CIFS_STATS2 atomic_set(&totBufAllocCount, 0); atomic_set(&totSmBufAllocCount, 0); @@ -451,15 +434,14 @@ static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { char c; + bool bv; int rc; rc = get_user(c, buffer); if (rc) return rc; - if (c == '0' || c == 'n' || c == 'N') - cifsFYI = 0; - else if (c == '1' || c == 'y' || c == 'Y') - cifsFYI = 1; + if (strtobool(&c, &bv) == 0) + cifsFYI = bv; else if ((c > '1') && (c <= '9')) cifsFYI = (int) (c - '0'); /* see cifs_debug.h for meanings */ @@ -490,15 +472,18 @@ static ssize_t cifs_linux_ext_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { char c; + bool bv; int rc; rc = get_user(c, buffer); if (rc) return rc; - if (c == '0' || c == 'n' || c == 'N') - linuxExtEnabled = 0; - else if (c == '1' || c == 'y' || c == 'Y') - linuxExtEnabled = 1; + + rc = strtobool(&c, &bv); + if (rc) + return rc; + + linuxExtEnabled = bv; return count; } @@ -527,15 +512,18 @@ static ssize_t cifs_lookup_cache_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { char c; + bool bv; int rc; rc = get_user(c, buffer); if (rc) return rc; - if (c == '0' || c == 'n' || c == 'N') - lookupCacheEnabled = 0; - else if (c == '1' || c == 'y' || c == 'Y') - lookupCacheEnabled = 1; + + rc = strtobool(&c, &bv); + if (rc) + return rc; + + lookupCacheEnabled = bv; return count; } @@ -564,15 +552,18 @@ static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { char c; + bool bv; int rc; rc = get_user(c, buffer); if (rc) return rc; - if (c == '0' || c == 'n' || c == 'N') - traceSMB = 0; - else if (c == '1' || c == 'y' || c == 'Y') - traceSMB = 1; + + rc = strtobool(&c, &bv); + if (rc) + return rc; + + traceSMB = bv; return count; } @@ -630,6 +621,7 @@ static ssize_t cifs_security_flags_proc_write(struct file *file, unsigned int flags; char flags_string[12]; char c; + bool bv; if ((count < 1) || (count > 11)) return -EINVAL; @@ -642,11 +634,8 @@ static ssize_t cifs_security_flags_proc_write(struct file *file, if (count < 3) { /* single char or single char followed by null */ c = flags_string[0]; - if (c == '0' || c == 'n' || c == 'N') { - global_secflags = CIFSSEC_DEF; /* default */ - return count; - } else if (c == '1' || c == 'y' || c == 'Y') { - global_secflags = CIFSSEC_MAX; + if (strtobool(&c, &bv) == 0) { + global_secflags = bv ? CIFSSEC_MAX : CIFSSEC_DEF; return count; } else if (!isdigit(c)) { cifs_dbg(VFS, "Invalid SecurityFlags: %s\n", diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index c99b40fb609b..f40fbaca1b2a 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -53,13 +53,12 @@ __printf(1, 2) void cifs_vfs_err(const char *fmt, ...); do { \ if (type == FYI) { \ if (cifsFYI & CIFS_INFO) { \ - printk(KERN_DEBUG "%s: " fmt, \ - __FILE__, ##__VA_ARGS__); \ + pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__); \ } \ } else if (type == VFS) { \ cifs_vfs_err(fmt, ##__VA_ARGS__); \ } else if (type == NOISY && type != 0) { \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ + pr_debug(fmt, ##__VA_ARGS__); \ } \ } while (0) @@ -71,7 +70,7 @@ do { \ #define cifs_dbg(type, fmt, ...) \ do { \ if (0) \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ + pr_debug(fmt, ##__VA_ARGS__); \ } while (0) #endif diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 9d7996e8e793..d72fe37f5420 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -209,8 +209,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len) { - struct super_block *sb = file->f_path.dentry->d_sb; - struct cifs_sb_info *cifs_sb = CIFS_SB(sb); + struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct TCP_Server_Info *server = tcon->ses->server; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 002e0c173939..252f5c15806b 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -136,5 +136,5 @@ 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 "2.05" +#define CIFS_VERSION "2.06" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 02a33e529904..6e139111fdb2 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1168,6 +1168,12 @@ CIFS_SB(struct super_block *sb) return sb->s_fs_info; } +static inline struct cifs_sb_info * +CIFS_FILE_SB(struct file *file) +{ + return CIFS_SB(file_inode(file)->i_sb); +} + static inline char CIFS_DIR_SEP(const struct cifs_sb_info *cifs_sb) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 24fa08d261fb..2a772da16b83 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1466,9 +1466,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->seal = 1; break; case Opt_noac: - printk(KERN_WARNING "CIFS: Mount option noac not " - "supported. Instead set " - "/proc/fs/cifs/LookupCacheEnabled to 0\n"); + pr_warn("CIFS: Mount option noac not supported. Instead set /proc/fs/cifs/LookupCacheEnabled to 0\n"); break; case Opt_fsc: #ifndef CONFIG_CIFS_FSCACHE @@ -1598,7 +1596,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (strnlen(string, CIFS_MAX_USERNAME_LEN) > CIFS_MAX_USERNAME_LEN) { - printk(KERN_WARNING "CIFS: username too long\n"); + pr_warn("CIFS: username too long\n"); goto cifs_parse_mount_err; } vol->username = kstrdup(string, GFP_KERNEL); @@ -1662,8 +1660,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, temp_len = strlen(value); vol->password = kzalloc(temp_len+1, GFP_KERNEL); if (vol->password == NULL) { - printk(KERN_WARNING "CIFS: no memory " - "for password\n"); + pr_warn("CIFS: no memory for password\n"); goto cifs_parse_mount_err; } @@ -1687,8 +1684,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (!cifs_convert_address(dstaddr, string, strlen(string))) { - printk(KERN_ERR "CIFS: bad ip= option (%s).\n", - string); + pr_err("CIFS: bad ip= option (%s).\n", string); goto cifs_parse_mount_err; } got_ip = true; @@ -1700,15 +1696,13 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (strnlen(string, CIFS_MAX_DOMAINNAME_LEN) == CIFS_MAX_DOMAINNAME_LEN) { - printk(KERN_WARNING "CIFS: domain name too" - " long\n"); + pr_warn("CIFS: domain name too long\n"); goto cifs_parse_mount_err; } vol->domainname = kstrdup(string, GFP_KERNEL); if (!vol->domainname) { - printk(KERN_WARNING "CIFS: no memory " - "for domainname\n"); + pr_warn("CIFS: no memory for domainname\n"); goto cifs_parse_mount_err; } cifs_dbg(FYI, "Domain name set\n"); @@ -1721,8 +1715,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (!cifs_convert_address( (struct sockaddr *)&vol->srcaddr, string, strlen(string))) { - printk(KERN_WARNING "CIFS: Could not parse" - " srcaddr: %s\n", string); + pr_warn("CIFS: Could not parse srcaddr: %s\n", + string); goto cifs_parse_mount_err; } break; @@ -1732,8 +1726,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, goto out_nomem; if (strnlen(string, 1024) >= 65) { - printk(KERN_WARNING "CIFS: iocharset name " - "too long.\n"); + pr_warn("CIFS: iocharset name too long.\n"); goto cifs_parse_mount_err; } @@ -1741,8 +1734,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->iocharset = kstrdup(string, GFP_KERNEL); if (!vol->iocharset) { - printk(KERN_WARNING "CIFS: no memory" - "for charset\n"); + pr_warn("CIFS: no memory for charset\n"); goto cifs_parse_mount_err; } } @@ -1773,9 +1765,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, * set at top of the function */ if (i == RFC1001_NAME_LEN && string[i] != 0) - printk(KERN_WARNING "CIFS: netbiosname" - " longer than 15 truncated.\n"); - + pr_warn("CIFS: netbiosname longer than 15 truncated.\n"); break; case Opt_servern: /* servernetbiosname specified override *SMBSERVER */ @@ -1801,8 +1791,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, /* The string has 16th byte zero still from set at top of the function */ if (i == RFC1001_NAME_LEN && string[i] != 0) - printk(KERN_WARNING "CIFS: server net" - "biosname longer than 15 truncated.\n"); + pr_warn("CIFS: server netbiosname longer than 15 truncated.\n"); break; case Opt_ver: string = match_strdup(args); @@ -1814,8 +1803,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, break; } /* For all other value, error */ - printk(KERN_WARNING "CIFS: Invalid version" - " specified\n"); + pr_warn("CIFS: Invalid version specified\n"); goto cifs_parse_mount_err; case Opt_vers: string = match_strdup(args); @@ -1856,7 +1844,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, } if (!sloppy && invalid) { - printk(KERN_ERR "CIFS: Unknown mount option \"%s\"\n", invalid); + pr_err("CIFS: Unknown mount option \"%s\"\n", invalid); goto cifs_parse_mount_err; } @@ -1882,8 +1870,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, /* No ip= option specified? Try to get it from UNC */ if (!cifs_convert_address(dstaddr, &vol->UNC[2], strlen(&vol->UNC[2]))) { - printk(KERN_ERR "Unable to determine destination " - "address.\n"); + pr_err("Unable to determine destination address.\n"); goto cifs_parse_mount_err; } } @@ -1894,20 +1881,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (uid_specified) vol->override_uid = override_uid; else if (override_uid == 1) - printk(KERN_NOTICE "CIFS: ignoring forceuid mount option " - "specified with no uid= option.\n"); + pr_notice("CIFS: ignoring forceuid mount option specified with no uid= option.\n"); if (gid_specified) vol->override_gid = override_gid; else if (override_gid == 1) - printk(KERN_NOTICE "CIFS: ignoring forcegid mount option " - "specified with no gid= option.\n"); + pr_notice("CIFS: ignoring forcegid mount option specified with no gid= option.\n"); kfree(mountdata_copy); return 0; out_nomem: - printk(KERN_WARNING "Could not allocate temporary buffer\n"); + pr_warn("Could not allocate temporary buffer\n"); cifs_parse_mount_err: kfree(string); kfree(mountdata_copy); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index b123a64d7be4..96b7e9b7706d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1586,7 +1586,7 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag, tcon->ses->server); - cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + cifs_sb = CIFS_FILE_SB(file); netfid = cfile->fid.netfid; cinode = CIFS_I(file_inode(file)); @@ -2305,7 +2305,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct cifs_tcon *tcon; struct TCP_Server_Info *server; struct cifsFileInfo *smbfile = file->private_data; - struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct inode *inode = file->f_mapping->host; rc = filemap_write_and_wait_range(inode->i_mapping, start, end); @@ -2585,7 +2585,7 @@ cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset) iov_iter_truncate(from, len); INIT_LIST_HEAD(&wdata_list); - cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + cifs_sb = CIFS_FILE_SB(file); open_file = file->private_data; tcon = tlink_tcon(open_file->tlink); @@ -3010,7 +3010,7 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) return 0; INIT_LIST_HEAD(&rdata_list); - cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + cifs_sb = CIFS_FILE_SB(file); open_file = file->private_data; tcon = tlink_tcon(open_file->tlink); @@ -3155,7 +3155,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset) __u32 pid; xid = get_xid(); - cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + cifs_sb = CIFS_FILE_SB(file); /* FIXME: set up handlers for larger reads and/or convert to async */ rsize = min_t(unsigned int, cifs_sb->rsize, CIFSMaxBufSize); @@ -3462,7 +3462,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, int rc; struct list_head tmplist; struct cifsFileInfo *open_file = file->private_data; - struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct TCP_Server_Info *server; pid_t pid; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 197cb503d528..0c3ce464cae4 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -895,7 +895,7 @@ inode_has_hashed_dentries(struct inode *inode) struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { if (!d_unhashed(dentry) || IS_ROOT(dentry)) { spin_unlock(&inode->i_lock); return true; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index b7415d596dbd..337946355b29 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -513,39 +513,11 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) void dump_smb(void *buf, int smb_buf_length) { - int i, j; - char debug_line[17]; - unsigned char *buffer = buf; - if (traceSMB == 0) return; - for (i = 0, j = 0; i < smb_buf_length; i++, j++) { - if (i % 8 == 0) { - /* have reached the beginning of line */ - printk(KERN_DEBUG "| "); - j = 0; - } - printk("%0#4x ", buffer[i]); - debug_line[2 * j] = ' '; - if (isprint(buffer[i])) - debug_line[1 + (2 * j)] = buffer[i]; - else - debug_line[1 + (2 * j)] = '_'; - - if (i % 8 == 7) { - /* reached end of line, time to print ascii */ - debug_line[16] = 0; - printk(" | %s\n", debug_line); - } - } - for (; j < 8; j++) { - printk(" "); - debug_line[2 * j] = ' '; - debug_line[1 + (2 * j)] = ' '; - } - printk(" | %s\n", debug_line); - return; + print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 8, 2, buf, + smb_buf_length, true); } void diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 8fd2a95860ba..8eaf20a80649 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -123,7 +123,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, if (!inode) goto out; - alias = d_materialise_unique(dentry, inode); + alias = d_splice_alias(inode, dentry); if (alias && !IS_ERR(alias)) dput(alias); out: @@ -261,7 +261,7 @@ initiate_cifs_search(const unsigned int xid, struct file *file) int rc = 0; char *full_path = NULL; struct cifsFileInfo *cifsFile; - struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct tcon_link *tlink = NULL; struct cifs_tcon *tcon; struct TCP_Server_Info *server; @@ -561,7 +561,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, loff_t first_entry_in_buffer; loff_t index_to_find = pos; struct cifsFileInfo *cfile = file->private_data; - struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct TCP_Server_Info *server = tcon->ses->server; /* check if index in the buffer */ @@ -679,7 +679,7 @@ static int cifs_filldir(char *find_entry, struct file *file, char *scratch_buf, unsigned int max_len) { struct cifsFileInfo *file_info = file->private_data; - struct super_block *sb = file->f_path.dentry->d_sb; + struct super_block *sb = file_inode(file)->i_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_dirent de = { NULL, }; struct cifs_fattr fattr; @@ -753,7 +753,7 @@ static int cifs_filldir(char *find_entry, struct file *file, */ fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; - cifs_prime_dcache(file->f_dentry, &name, &fattr); + cifs_prime_dcache(file->f_path.dentry, &name, &fattr); ino = cifs_uniqueid_to_ino_t(fattr.cf_uniqueid); return !dir_emit(ctx, name.name, name.len, ino, fattr.cf_dtype); @@ -794,10 +794,6 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) if it before then restart search if after then keep searching till find it */ - if (file->private_data == NULL) { - rc = -EINVAL; - goto rddir2_exit; - } cifsFile = file->private_data; if (cifsFile->srch_inf.endOfSearch) { if (cifsFile->srch_inf.emptyDir) { diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index ab0fda6e8e58..bce6fdcd5d48 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -1303,6 +1303,11 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) if (le16_to_cpu(pSMB->resp.Action) & GUEST_LOGIN) cifs_dbg(FYI, "Guest login\n"); /* BB mark SesInfo struct? */ + if (ses->Suid != smb_buf->Uid) { + ses->Suid = smb_buf->Uid; + cifs_dbg(FYI, "UID changed! new UID = %llu\n", ses->Suid); + } + bytes_remaining = get_bcc(smb_buf); bcc_ptr = pByteArea(smb_buf); blob_len = le16_to_cpu(pSMB->resp.SecurityBlobLength); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 7ecac610b44b..93fd0586f9ec 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1102,6 +1102,64 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, return rc; } +static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, + loff_t off, loff_t len, bool keep_size) +{ + struct inode *inode; + struct cifsInodeInfo *cifsi; + struct cifsFileInfo *cfile = file->private_data; + long rc = -EOPNOTSUPP; + unsigned int xid; + + xid = get_xid(); + + inode = cfile->dentry->d_inode; + cifsi = CIFS_I(inode); + + /* if file not oplocked can't be sure whether asking to extend size */ + if (!CIFS_CACHE_READ(cifsi)) + if (keep_size == false) + return -EOPNOTSUPP; + + /* + * Files are non-sparse by default so falloc may be a no-op + * Must check if file sparse. If not sparse, and not extending + * then no need to do anything since file already allocated + */ + if ((cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) == 0) { + if (keep_size == true) + return 0; + /* check if extending file */ + else if (i_size_read(inode) >= off + len) + /* not extending file and already not sparse */ + return 0; + /* BB: in future add else clause to extend file */ + else + return -EOPNOTSUPP; + } + + if ((keep_size == true) || (i_size_read(inode) >= off + len)) { + /* + * Check if falloc starts within first few pages of file + * and ends within a few pages of the end of file to + * ensure that most of file is being forced to be + * fallocated now. If so then setting whole file sparse + * ie potentially making a few extra pages at the beginning + * or end of the file non-sparse via set_sparse is harmless. + */ + if ((off > 8192) || (off + len + 8192 < i_size_read(inode))) + return -EOPNOTSUPP; + + rc = smb2_set_sparse(xid, tcon, cfile, inode, false); + } + /* BB: else ... in future add code to extend file and set sparse */ + + + free_xid(xid); + return rc; +} + + static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode, loff_t off, loff_t len) { @@ -1112,7 +1170,10 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode, if (mode & FALLOC_FL_KEEP_SIZE) return smb3_zero_range(file, tcon, off, len, true); return smb3_zero_range(file, tcon, off, len, false); - } + } else if (mode == FALLOC_FL_KEEP_SIZE) + return smb3_simple_falloc(file, tcon, off, len, true); + else if (mode == 0) + return smb3_simple_falloc(file, tcon, off, len, false); return -EOPNOTSUPP; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 08f73e168b0b..3417340bf89e 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -431,8 +431,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) if (rc) goto neg_exit; if (blob_length) - rc = decode_neg_token_init(security_blob, blob_length, - &server->sec_type); + rc = decode_negTokenInit(security_blob, blob_length, server); if (rc == 1) rc = 0; else if (rc == 0) { diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index fbd4df1e1683..ce858477002a 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -836,6 +836,25 @@ struct smb2_query_directory_rsp { #define SMB2_O_INFO_SECURITY 0x03 #define SMB2_O_INFO_QUOTA 0x04 +/* Security info type additionalinfo flags. See MS-SMB2 (2.2.37) or MS-DTYP */ +#define OWNER_SECINFO 0x00000001 +#define GROUP_SECINFO 0x00000002 +#define DACL_SECINFO 0x00000004 +#define SACL_SECINFO 0x00000008 +#define LABEL_SECINFO 0x00000010 +#define ATTRIBUTE_SECINFO 0x00000020 +#define SCOPE_SECINFO 0x00000040 +#define BACKUP_SECINFO 0x00010000 +#define UNPROTECTED_SACL_SECINFO 0x10000000 +#define UNPROTECTED_DACL_SECINFO 0x20000000 +#define PROTECTED_SACL_SECINFO 0x40000000 +#define PROTECTED_DACL_SECINFO 0x80000000 + +/* Flags used for FileFullEAinfo */ +#define SL_RESTART_SCAN 0x00000001 +#define SL_RETURN_SINGLE_ENTRY 0x00000002 +#define SL_INDEX_SPECIFIED 0x00000004 + struct smb2_query_info_req { struct smb2_hdr hdr; __le16 StructureSize; /* Must be 41 */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 9d087f4e7d4e..126f46b887cc 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -99,9 +99,9 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) something is wrong, unless it is quite a slow link or server */ if ((now - midEntry->when_alloc) > HZ) { if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) { - printk(KERN_DEBUG " CIFS slow rsp: cmd %d mid %llu", + pr_debug(" CIFS slow rsp: cmd %d mid %llu", midEntry->command, midEntry->mid); - printk(" A: 0x%lx S: 0x%lx R: 0x%lx\n", + pr_info(" A: 0x%lx S: 0x%lx R: 0x%lx\n", now - midEntry->when_alloc, now - midEntry->when_sent, now - midEntry->when_received); diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 278f8fdeb9ef..46ee6f238985 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -92,7 +92,7 @@ static void coda_flag_children(struct dentry *parent, int flag) struct dentry *de; spin_lock(&parent->d_lock); - list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(de, &parent->d_subdirs, d_child) { /* don't know what to do with negative dentries */ if (de->d_inode ) coda_flag_inode(de->d_inode, flag); diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c index 1326d38960db..f1714cfb589c 100644 --- a/fs/coda/coda_linux.c +++ b/fs/coda/coda_linux.c @@ -40,12 +40,6 @@ int coda_iscontrol(const char *name, size_t length) (strncmp(name, CODA_CONTROL, CODA_CONTROLLEN) == 0)); } -/* recognize /coda inode */ -int coda_isroot(struct inode *i) -{ - return ( i->i_sb->s_root->d_inode == i ); -} - unsigned short coda_flags_to_cflags(unsigned short flags) { unsigned short coda_flags = 0; diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h index d42b725b1d21..d6f7a76a1f5b 100644 --- a/fs/coda/coda_linux.h +++ b/fs/coda/coda_linux.h @@ -52,7 +52,6 @@ int coda_setattr(struct dentry *, struct iattr *); /* this file: heloers */ char *coda_f2s(struct CodaFid *f); -int coda_isroot(struct inode *i); int coda_iscontrol(const char *name, size_t length); void coda_vattr_to_iattr(struct inode *, struct coda_vattr *); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 9c3dedc000d1..7ff025966e4f 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -107,7 +107,7 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsig } /* control object, create inode on the fly */ - if (coda_isroot(dir) && coda_iscontrol(name, length)) { + if (is_root_inode(dir) && coda_iscontrol(name, length)) { inode = coda_cnode_makectl(sb); type = CODA_NOCACHE; } else { @@ -195,7 +195,7 @@ static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool struct CodaFid newfid; struct coda_vattr attrs; - if (coda_isroot(dir) && coda_iscontrol(name, length)) + if (is_root_inode(dir) && coda_iscontrol(name, length)) return -EPERM; error = venus_create(dir->i_sb, coda_i2f(dir), name, length, @@ -227,7 +227,7 @@ static int coda_mkdir(struct inode *dir, struct dentry *de, umode_t mode) int error; struct CodaFid newfid; - if (coda_isroot(dir) && coda_iscontrol(name, len)) + if (is_root_inode(dir) && coda_iscontrol(name, len)) return -EPERM; attrs.va_mode = mode; @@ -261,7 +261,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode, int len = de->d_name.len; int error; - if (coda_isroot(dir_inode) && coda_iscontrol(name, len)) + if (is_root_inode(dir_inode) && coda_iscontrol(name, len)) return -EPERM; error = venus_link(dir_inode->i_sb, coda_i2f(inode), @@ -287,7 +287,7 @@ static int coda_symlink(struct inode *dir_inode, struct dentry *de, int symlen; int error; - if (coda_isroot(dir_inode) && coda_iscontrol(name, len)) + if (is_root_inode(dir_inode) && coda_iscontrol(name, len)) return -EPERM; symlen = strlen(symname); @@ -507,7 +507,7 @@ static int coda_dentry_revalidate(struct dentry *de, unsigned int flags) return -ECHILD; inode = de->d_inode; - if (!inode || coda_isroot(inode)) + if (!inode || is_root_inode(inode)) goto out; if (is_bad_inode(inode)) goto bad; diff --git a/fs/compat.c b/fs/compat.c index b13df99f3534..6fd272d455e4 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -847,10 +847,12 @@ struct compat_readdir_callback { int result; }; -static int compat_fillonedir(void *__buf, const char *name, int namlen, - loff_t offset, u64 ino, unsigned int d_type) +static int compat_fillonedir(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { - struct compat_readdir_callback *buf = __buf; + struct compat_readdir_callback *buf = + container_of(ctx, struct compat_readdir_callback, ctx); struct compat_old_linux_dirent __user *dirent; compat_ulong_t d_ino; @@ -915,11 +917,12 @@ struct compat_getdents_callback { int error; }; -static int compat_filldir(void *__buf, const char *name, int namlen, +static int compat_filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct compat_linux_dirent __user * dirent; - struct compat_getdents_callback *buf = __buf; + struct compat_getdents_callback *buf = + container_of(ctx, struct compat_getdents_callback, ctx); compat_ulong_t d_ino; int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + namlen + 2, sizeof(compat_long_t)); @@ -1001,11 +1004,13 @@ struct compat_getdents_callback64 { int error; }; -static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int compat_filldir64(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { struct linux_dirent64 __user *dirent; - struct compat_getdents_callback64 *buf = __buf; + struct compat_getdents_callback64 *buf = + container_of(ctx, struct compat_getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); u64 off; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 668dcabc5695..c9c298bd3058 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -386,7 +386,7 @@ static void remove_dir(struct dentry * d) if (d->d_inode) simple_rmdir(parent->d_inode,d); - pr_debug(" o %s removing done (%d)\n",d->d_name.name, d_count(d)); + pr_debug(" o %pd removing done (%d)\n", d, d_count(d)); dput(parent); } diff --git a/fs/dcache.c b/fs/dcache.c index 5bc72b07fde2..e368d4f412f9 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -44,7 +44,7 @@ /* * Usage: * dcache->d_inode->i_lock protects: - * - i_dentry, d_alias, d_inode of aliases + * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_anon bl list spinlock protects: @@ -59,7 +59,7 @@ * - d_unhashed() * - d_parent and d_subdirs * - childrens' d_child and d_parent - * - d_alias, d_inode + * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock @@ -252,14 +252,12 @@ static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - WARN_ON(!hlist_unhashed(&dentry->d_alias)); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - WARN_ON(!hlist_unhashed(&dentry->d_alias)); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } @@ -271,6 +269,7 @@ static inline int dname_external(const struct dentry *dentry) static void dentry_free(struct dentry *dentry) { + WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->u.count))) { @@ -311,7 +310,7 @@ static void dentry_iput(struct dentry * dentry) struct inode *inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -336,7 +335,7 @@ static void dentry_unlink_inode(struct dentry * dentry) struct inode *inode = dentry->d_inode; __d_clear_type(dentry); dentry->d_inode = NULL; - hlist_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_u.d_alias); dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); @@ -496,7 +495,7 @@ static void __dentry_kill(struct dentry *dentry) } /* if it was on the hash then remove it */ __d_drop(dentry); - list_del(&dentry->d_u.d_child); + __list_del_entry(&dentry->d_child); /* * Inform d_walk() that we are no longer attached to the * dentry tree @@ -722,7 +721,7 @@ static struct dentry *__d_find_alias(struct inode *inode) again: discon_alias = NULL; - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) { if (IS_ROOT(alias) && @@ -772,7 +771,7 @@ void d_prune_aliases(struct inode *inode) struct dentry *dentry; restart: spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) { struct dentry *parent = lock_parent(dentry); @@ -1051,7 +1050,7 @@ repeat: resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); @@ -1083,33 +1082,31 @@ resume: /* * All done at this level ... ascend and resume the search. */ + rcu_read_lock(); +ascend: if (this_parent != parent) { struct dentry *child = this_parent; this_parent = child->d_parent; - rcu_read_lock(); spin_unlock(&child->d_lock); spin_lock(&this_parent->d_lock); - /* - * might go back up the wrong parent if we have had a rename - * or deletion - */ - if (this_parent != child->d_parent || - (child->d_flags & DCACHE_DENTRY_KILLED) || - need_seqretry(&rename_lock, seq)) { - spin_unlock(&this_parent->d_lock); - rcu_read_unlock(); + /* might go back up the wrong parent if we have had a rename. */ + if (need_seqretry(&rename_lock, seq)) goto rename_retry; + next = child->d_child.next; + while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) { + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + next = next->next; } rcu_read_unlock(); - next = child->d_u.d_child.next; goto resume; } - if (need_seqretry(&rename_lock, seq)) { - spin_unlock(&this_parent->d_lock); + if (need_seqretry(&rename_lock, seq)) goto rename_retry; - } + rcu_read_unlock(); if (finish) finish(data); @@ -1119,6 +1116,9 @@ out_unlock: return; rename_retry: + spin_unlock(&this_parent->d_lock); + rcu_read_unlock(); + BUG_ON(seq & 1); if (!retry) return; seq = 1; @@ -1455,8 +1455,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); - INIT_HLIST_NODE(&dentry->d_alias); - INIT_LIST_HEAD(&dentry->d_u.d_child); + INIT_HLIST_NODE(&dentry->d_u.d_alias); + INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); this_cpu_inc(nr_dentry); @@ -1486,7 +1486,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) */ __dget_dlock(parent); dentry->d_parent = parent; - list_add(&dentry->d_u.d_child, &parent->d_subdirs); + list_add(&dentry->d_child, &parent->d_subdirs); spin_unlock(&parent->d_lock); return dentry; @@ -1579,7 +1579,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); __d_set_type(dentry, add_flags); if (inode) - hlist_add_head(&dentry->d_alias, &inode->i_dentry); + hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); dentry->d_inode = inode; dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); @@ -1603,7 +1603,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) void d_instantiate(struct dentry *entry, struct inode * inode) { - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) spin_lock(&inode->i_lock); __d_instantiate(entry, inode); @@ -1642,7 +1642,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, return NULL; } - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or @@ -1668,7 +1668,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode) { struct dentry *result; - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) spin_lock(&inode->i_lock); @@ -1699,7 +1699,7 @@ EXPORT_SYMBOL(d_instantiate_unique); */ int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode) { - BUG_ON(!hlist_unhashed(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) { @@ -1738,7 +1738,7 @@ static struct dentry * __d_find_any_alias(struct inode *inode) if (hlist_empty(&inode->i_dentry)) return NULL; - alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); __dget(alias); return alias; } @@ -1800,7 +1800,7 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected) spin_lock(&tmp->d_lock); tmp->d_inode = inode; tmp->d_flags |= add_flags; - hlist_add_head(&tmp->d_alias, &inode->i_dentry); + hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry); hlist_bl_lock(&tmp->d_sb->s_anon); hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon); hlist_bl_unlock(&tmp->d_sb->s_anon); @@ -1889,51 +1889,19 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); - if (unlikely(IS_ERR(found))) - goto err_out; if (!found) { new = d_alloc(dentry->d_parent, name); if (!new) { found = ERR_PTR(-ENOMEM); - goto err_out; - } - - found = d_splice_alias(inode, new); - if (found) { - dput(new); - return found; - } - return new; - } - - /* - * If a matching dentry exists, and it's not negative use it. - * - * Decrement the reference count to balance the iget() done - * earlier on. - */ - if (found->d_inode) { - if (unlikely(found->d_inode != inode)) { - /* This can't happen because bad inodes are unhashed. */ - BUG_ON(!is_bad_inode(inode)); - BUG_ON(!is_bad_inode(found->d_inode)); + } else { + found = d_splice_alias(inode, new); + if (found) { + dput(new); + return found; + } + return new; } - iput(inode); - return found; } - - /* - * Negative dentry: instantiate it unless the inode is a directory and - * already has a dentry. - */ - new = d_splice_alias(inode, found); - if (new) { - dput(found); - found = new; - } - return found; - -err_out: iput(inode); return found; } @@ -2235,7 +2203,7 @@ int d_validate(struct dentry *dentry, struct dentry *dparent) struct dentry *child; spin_lock(&dparent->d_lock); - list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dparent->d_subdirs, d_child) { if (dentry == child) { spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); __dget_dlock(dentry); @@ -2393,6 +2361,8 @@ static void swap_names(struct dentry *dentry, struct dentry *target) */ unsigned int i; BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); + kmemcheck_mark_initialized(dentry->d_iname, DNAME_INLINE_LEN); + kmemcheck_mark_initialized(target->d_iname, DNAME_INLINE_LEN); for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { swap(((long *) &dentry->d_iname)[i], ((long *) &target->d_iname)[i]); @@ -2526,13 +2496,13 @@ static void __d_move(struct dentry *dentry, struct dentry *target, /* splicing a tree */ dentry->d_parent = target->d_parent; target->d_parent = target; - list_del_init(&target->d_u.d_child); - list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs); + list_del_init(&target->d_child); + list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); } else { /* swapping two dentries */ swap(dentry->d_parent, target->d_parent); - list_move(&target->d_u.d_child, &target->d_parent->d_subdirs); - list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs); + list_move(&target->d_child, &target->d_parent->d_subdirs); + list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); if (exchange) fsnotify_d_move(target); fsnotify_d_move(dentry); @@ -2608,11 +2578,11 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ -static struct dentry *__d_unalias(struct inode *inode, +static int __d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL, *m2 = NULL; - struct dentry *ret = ERR_PTR(-EBUSY); + int ret = -EBUSY; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) @@ -2627,7 +2597,7 @@ static struct dentry *__d_unalias(struct inode *inode, m2 = &alias->d_parent->d_inode->i_mutex; out_unalias: __d_move(alias, dentry, false); - ret = alias; + ret = 0; out_err: spin_unlock(&inode->i_lock); if (m2) @@ -2662,130 +2632,57 @@ out_err: */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { - struct dentry *new = NULL; - if (IS_ERR(inode)) return ERR_CAST(inode); - if (inode && S_ISDIR(inode->i_mode)) { - spin_lock(&inode->i_lock); - new = __d_find_any_alias(inode); - if (new) { - if (!IS_ROOT(new)) { - spin_unlock(&inode->i_lock); - dput(new); - iput(inode); - return ERR_PTR(-EIO); - } - if (d_ancestor(new, dentry)) { - spin_unlock(&inode->i_lock); - dput(new); - iput(inode); - return ERR_PTR(-EIO); - } - write_seqlock(&rename_lock); - __d_move(new, dentry, false); - write_sequnlock(&rename_lock); - spin_unlock(&inode->i_lock); - security_d_instantiate(new, inode); - iput(inode); - } else { - /* already taking inode->i_lock, so d_add() by hand */ - __d_instantiate(dentry, inode); - spin_unlock(&inode->i_lock); - security_d_instantiate(dentry, inode); - d_rehash(dentry); - } - } else { - d_instantiate(dentry, inode); - if (d_unhashed(dentry)) - d_rehash(dentry); - } - return new; -} -EXPORT_SYMBOL(d_splice_alias); - -/** - * d_materialise_unique - introduce an inode into the tree - * @dentry: candidate dentry - * @inode: inode to bind to the dentry, to which aliases may be attached - * - * Introduces an dentry into the tree, substituting an extant disconnected - * root directory alias in its place if there is one. Caller must hold the - * i_mutex of the parent directory. - */ -struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode) -{ - struct dentry *actual; - BUG_ON(!d_unhashed(dentry)); if (!inode) { - actual = dentry; __d_instantiate(dentry, NULL); - d_rehash(actual); - goto out_nolock; + goto out; } - spin_lock(&inode->i_lock); - if (S_ISDIR(inode->i_mode)) { - struct dentry *alias; - - /* Does an aliased dentry already exist? */ - alias = __d_find_alias(inode); - if (alias) { - actual = alias; + struct dentry *new = __d_find_any_alias(inode); + if (unlikely(new)) { write_seqlock(&rename_lock); - - if (d_ancestor(alias, dentry)) { - /* Check for loops */ - actual = ERR_PTR(-ELOOP); + if (unlikely(d_ancestor(new, dentry))) { + write_sequnlock(&rename_lock); spin_unlock(&inode->i_lock); - } else if (IS_ROOT(alias)) { - /* Is this an anonymous mountpoint that we - * could splice into our tree? */ - __d_move(alias, dentry, false); + dput(new); + new = ERR_PTR(-ELOOP); + pr_warn_ratelimited( + "VFS: Lookup of '%s' in %s %s" + " would have caused loop\n", + dentry->d_name.name, + inode->i_sb->s_type->name, + inode->i_sb->s_id); + } else if (!IS_ROOT(new)) { + int err = __d_unalias(inode, dentry, new); write_sequnlock(&rename_lock); - goto found; + if (err) { + dput(new); + new = ERR_PTR(err); + } } else { - /* Nope, but we must(!) avoid directory - * aliasing. This drops inode->i_lock */ - actual = __d_unalias(inode, dentry, alias); - } - write_sequnlock(&rename_lock); - if (IS_ERR(actual)) { - if (PTR_ERR(actual) == -ELOOP) - pr_warn_ratelimited( - "VFS: Lookup of '%s' in %s %s" - " would have caused loop\n", - dentry->d_name.name, - inode->i_sb->s_type->name, - inode->i_sb->s_id); - dput(alias); + __d_move(new, dentry, false); + write_sequnlock(&rename_lock); + spin_unlock(&inode->i_lock); + security_d_instantiate(new, inode); } - goto out_nolock; + iput(inode); + return new; } } - - /* Add a unique reference */ - actual = __d_instantiate_unique(dentry, inode); - if (!actual) - actual = dentry; - - d_rehash(actual); -found: + /* already taking inode->i_lock, so d_add() by hand */ + __d_instantiate(dentry, inode); spin_unlock(&inode->i_lock); -out_nolock: - if (actual == dentry) { - security_d_instantiate(dentry, inode); - return NULL; - } - - iput(inode); - return actual; +out: + security_d_instantiate(dentry, inode); + d_rehash(dentry); + return NULL; } -EXPORT_SYMBOL_GPL(d_materialise_unique); +EXPORT_SYMBOL(d_splice_alias); static int prepend(char **buffer, int *buflen, const char *str, int namelen) { @@ -3321,7 +3218,7 @@ void d_tmpfile(struct dentry *dentry, struct inode *inode) { inode_dec_link_count(inode); BUG_ON(dentry->d_name.name != dentry->d_iname || - !hlist_unhashed(&dentry->d_alias) || + !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 76c08c2beb2f..8e0f2f410189 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -692,18 +692,19 @@ EXPORT_SYMBOL_GPL(debugfs_create_u32_array); * because some peripherals have several blocks of identical registers, * for example configuration of dma channels */ -int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, - int nregs, void __iomem *base, char *prefix) +void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, + int nregs, void __iomem *base, char *prefix) { - int i, ret = 0; + int i; for (i = 0; i < nregs; i++, regs++) { if (prefix) - ret += seq_printf(s, "%s", prefix); - ret += seq_printf(s, "%s = 0x%08x\n", regs->name, - readl(base + regs->offset)); + seq_printf(s, "%s", prefix); + seq_printf(s, "%s = 0x%08x\n", regs->name, + readl(base + regs->offset)); + if (seq_has_overflowed(s)) + break; } - return ret; } EXPORT_SYMBOL_GPL(debugfs_print_regs32); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 1e3b99d3db0d..05f2960ed7c3 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -553,7 +553,7 @@ void debugfs_remove_recursive(struct dentry *dentry) * use the d_u.d_child as the rcu head and corrupt this list. */ spin_lock(&parent->d_lock); - list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &parent->d_subdirs, d_child) { if (!debugfs_positive(child)) continue; diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index 1323c568e362..eea64912c9c0 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -48,8 +48,8 @@ static char *print_lockmode(int mode) } } -static int print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb, - struct dlm_rsb *res) +static void print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb, + struct dlm_rsb *res) { seq_printf(s, "%08x %s", lkb->lkb_id, print_lockmode(lkb->lkb_grmode)); @@ -68,21 +68,17 @@ static int print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb, if (lkb->lkb_wait_type) seq_printf(s, " wait_type: %d", lkb->lkb_wait_type); - return seq_puts(s, "\n"); + seq_puts(s, "\n"); } -static int print_format1(struct dlm_rsb *res, struct seq_file *s) +static void print_format1(struct dlm_rsb *res, struct seq_file *s) { struct dlm_lkb *lkb; int i, lvblen = res->res_ls->ls_lvblen, recover_list, root_list; - int rv; lock_rsb(res); - rv = seq_printf(s, "\nResource %p Name (len=%d) \"", - res, res->res_length); - if (rv) - goto out; + seq_printf(s, "\nResource %p Name (len=%d) \"", res, res->res_length); for (i = 0; i < res->res_length; i++) { if (isprint(res->res_name[i])) @@ -92,17 +88,16 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s) } if (res->res_nodeid > 0) - rv = seq_printf(s, "\"\nLocal Copy, Master is node %d\n", - res->res_nodeid); + seq_printf(s, "\"\nLocal Copy, Master is node %d\n", + res->res_nodeid); else if (res->res_nodeid == 0) - rv = seq_puts(s, "\"\nMaster Copy\n"); + seq_puts(s, "\"\nMaster Copy\n"); else if (res->res_nodeid == -1) - rv = seq_printf(s, "\"\nLooking up master (lkid %x)\n", - res->res_first_lkid); + seq_printf(s, "\"\nLooking up master (lkid %x)\n", + res->res_first_lkid); else - rv = seq_printf(s, "\"\nInvalid master %d\n", - res->res_nodeid); - if (rv) + seq_printf(s, "\"\nInvalid master %d\n", res->res_nodeid); + if (seq_has_overflowed(s)) goto out; /* Print the LVB: */ @@ -116,8 +111,8 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s) } if (rsb_flag(res, RSB_VALNOTVALID)) seq_puts(s, " (INVALID)"); - rv = seq_puts(s, "\n"); - if (rv) + seq_puts(s, "\n"); + if (seq_has_overflowed(s)) goto out; } @@ -125,32 +120,30 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s) recover_list = !list_empty(&res->res_recover_list); if (root_list || recover_list) { - rv = seq_printf(s, "Recovery: root %d recover %d flags %lx " - "count %d\n", root_list, recover_list, - res->res_flags, res->res_recover_locks_count); - if (rv) - goto out; + seq_printf(s, "Recovery: root %d recover %d flags %lx count %d\n", + root_list, recover_list, + res->res_flags, res->res_recover_locks_count); } /* Print the locks attached to this resource */ seq_puts(s, "Granted Queue\n"); list_for_each_entry(lkb, &res->res_grantqueue, lkb_statequeue) { - rv = print_format1_lock(s, lkb, res); - if (rv) + print_format1_lock(s, lkb, res); + if (seq_has_overflowed(s)) goto out; } seq_puts(s, "Conversion Queue\n"); list_for_each_entry(lkb, &res->res_convertqueue, lkb_statequeue) { - rv = print_format1_lock(s, lkb, res); - if (rv) + print_format1_lock(s, lkb, res); + if (seq_has_overflowed(s)) goto out; } seq_puts(s, "Waiting Queue\n"); list_for_each_entry(lkb, &res->res_waitqueue, lkb_statequeue) { - rv = print_format1_lock(s, lkb, res); - if (rv) + print_format1_lock(s, lkb, res); + if (seq_has_overflowed(s)) goto out; } @@ -159,23 +152,23 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s) seq_puts(s, "Lookup Queue\n"); list_for_each_entry(lkb, &res->res_lookup, lkb_rsb_lookup) { - rv = seq_printf(s, "%08x %s", lkb->lkb_id, - print_lockmode(lkb->lkb_rqmode)); + seq_printf(s, "%08x %s", + lkb->lkb_id, print_lockmode(lkb->lkb_rqmode)); if (lkb->lkb_wait_type) seq_printf(s, " wait_type: %d", lkb->lkb_wait_type); - rv = seq_puts(s, "\n"); + seq_puts(s, "\n"); + if (seq_has_overflowed(s)) + goto out; } out: unlock_rsb(res); - return rv; } -static int print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb, - struct dlm_rsb *r) +static void print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb, + struct dlm_rsb *r) { u64 xid = 0; u64 us; - int rv; if (lkb->lkb_flags & DLM_IFL_USER) { if (lkb->lkb_ua) @@ -188,103 +181,97 @@ static int print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb, /* id nodeid remid pid xid exflags flags sts grmode rqmode time_us r_nodeid r_len r_name */ - rv = seq_printf(s, "%x %d %x %u %llu %x %x %d %d %d %llu %u %d \"%s\"\n", - lkb->lkb_id, - lkb->lkb_nodeid, - lkb->lkb_remid, - lkb->lkb_ownpid, - (unsigned long long)xid, - lkb->lkb_exflags, - lkb->lkb_flags, - lkb->lkb_status, - lkb->lkb_grmode, - lkb->lkb_rqmode, - (unsigned long long)us, - r->res_nodeid, - r->res_length, - r->res_name); - return rv; + seq_printf(s, "%x %d %x %u %llu %x %x %d %d %d %llu %u %d \"%s\"\n", + lkb->lkb_id, + lkb->lkb_nodeid, + lkb->lkb_remid, + lkb->lkb_ownpid, + (unsigned long long)xid, + lkb->lkb_exflags, + lkb->lkb_flags, + lkb->lkb_status, + lkb->lkb_grmode, + lkb->lkb_rqmode, + (unsigned long long)us, + r->res_nodeid, + r->res_length, + r->res_name); } -static int print_format2(struct dlm_rsb *r, struct seq_file *s) +static void print_format2(struct dlm_rsb *r, struct seq_file *s) { struct dlm_lkb *lkb; - int rv = 0; lock_rsb(r); list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { - rv = print_format2_lock(s, lkb, r); - if (rv) + print_format2_lock(s, lkb, r); + if (seq_has_overflowed(s)) goto out; } list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { - rv = print_format2_lock(s, lkb, r); - if (rv) + print_format2_lock(s, lkb, r); + if (seq_has_overflowed(s)) goto out; } list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) { - rv = print_format2_lock(s, lkb, r); - if (rv) + print_format2_lock(s, lkb, r); + if (seq_has_overflowed(s)) goto out; } out: unlock_rsb(r); - return rv; } -static int print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb, +static void print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb, int rsb_lookup) { u64 xid = 0; - int rv; if (lkb->lkb_flags & DLM_IFL_USER) { if (lkb->lkb_ua) xid = lkb->lkb_ua->xid; } - rv = seq_printf(s, "lkb %x %d %x %u %llu %x %x %d %d %d %d %d %d %u %llu %llu\n", - lkb->lkb_id, - lkb->lkb_nodeid, - lkb->lkb_remid, - lkb->lkb_ownpid, - (unsigned long long)xid, - lkb->lkb_exflags, - lkb->lkb_flags, - lkb->lkb_status, - lkb->lkb_grmode, - lkb->lkb_rqmode, - lkb->lkb_last_bast.mode, - rsb_lookup, - lkb->lkb_wait_type, - lkb->lkb_lvbseq, - (unsigned long long)ktime_to_ns(lkb->lkb_timestamp), - (unsigned long long)ktime_to_ns(lkb->lkb_last_bast_time)); - return rv; + seq_printf(s, "lkb %x %d %x %u %llu %x %x %d %d %d %d %d %d %u %llu %llu\n", + lkb->lkb_id, + lkb->lkb_nodeid, + lkb->lkb_remid, + lkb->lkb_ownpid, + (unsigned long long)xid, + lkb->lkb_exflags, + lkb->lkb_flags, + lkb->lkb_status, + lkb->lkb_grmode, + lkb->lkb_rqmode, + lkb->lkb_last_bast.mode, + rsb_lookup, + lkb->lkb_wait_type, + lkb->lkb_lvbseq, + (unsigned long long)ktime_to_ns(lkb->lkb_timestamp), + (unsigned long long)ktime_to_ns(lkb->lkb_last_bast_time)); } -static int print_format3(struct dlm_rsb *r, struct seq_file *s) +static void print_format3(struct dlm_rsb *r, struct seq_file *s) { struct dlm_lkb *lkb; int i, lvblen = r->res_ls->ls_lvblen; int print_name = 1; - int rv; lock_rsb(r); - rv = seq_printf(s, "rsb %p %d %x %lx %d %d %u %d ", - r, - r->res_nodeid, - r->res_first_lkid, - r->res_flags, - !list_empty(&r->res_root_list), - !list_empty(&r->res_recover_list), - r->res_recover_locks_count, - r->res_length); - if (rv) + seq_printf(s, "rsb %p %d %x %lx %d %d %u %d ", + r, + r->res_nodeid, + r->res_first_lkid, + r->res_flags, + !list_empty(&r->res_root_list), + !list_empty(&r->res_recover_list), + r->res_recover_locks_count, + r->res_length); + if (seq_has_overflowed(s)) goto out; for (i = 0; i < r->res_length; i++) { @@ -292,7 +279,7 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s) print_name = 0; } - seq_printf(s, "%s", print_name ? "str " : "hex"); + seq_puts(s, print_name ? "str " : "hex"); for (i = 0; i < r->res_length; i++) { if (print_name) @@ -300,8 +287,8 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s) else seq_printf(s, " %02x", (unsigned char)r->res_name[i]); } - rv = seq_puts(s, "\n"); - if (rv) + seq_puts(s, "\n"); + if (seq_has_overflowed(s)) goto out; if (!r->res_lvbptr) @@ -311,65 +298,62 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s) for (i = 0; i < lvblen; i++) seq_printf(s, " %02x", (unsigned char)r->res_lvbptr[i]); - rv = seq_puts(s, "\n"); - if (rv) + seq_puts(s, "\n"); + if (seq_has_overflowed(s)) goto out; do_locks: list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { - rv = print_format3_lock(s, lkb, 0); - if (rv) + print_format3_lock(s, lkb, 0); + if (seq_has_overflowed(s)) goto out; } list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { - rv = print_format3_lock(s, lkb, 0); - if (rv) + print_format3_lock(s, lkb, 0); + if (seq_has_overflowed(s)) goto out; } list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) { - rv = print_format3_lock(s, lkb, 0); - if (rv) + print_format3_lock(s, lkb, 0); + if (seq_has_overflowed(s)) goto out; } list_for_each_entry(lkb, &r->res_lookup, lkb_rsb_lookup) { - rv = print_format3_lock(s, lkb, 1); - if (rv) + print_format3_lock(s, lkb, 1); + if (seq_has_overflowed(s)) goto out; } out: unlock_rsb(r); - return rv; } -static int print_format4(struct dlm_rsb *r, struct seq_file *s) +static void print_format4(struct dlm_rsb *r, struct seq_file *s) { int our_nodeid = dlm_our_nodeid(); int print_name = 1; - int i, rv; + int i; lock_rsb(r); - rv = seq_printf(s, "rsb %p %d %d %d %d %lu %lx %d ", - r, - r->res_nodeid, - r->res_master_nodeid, - r->res_dir_nodeid, - our_nodeid, - r->res_toss_time, - r->res_flags, - r->res_length); - if (rv) - goto out; + seq_printf(s, "rsb %p %d %d %d %d %lu %lx %d ", + r, + r->res_nodeid, + r->res_master_nodeid, + r->res_dir_nodeid, + our_nodeid, + r->res_toss_time, + r->res_flags, + r->res_length); for (i = 0; i < r->res_length; i++) { if (!isascii(r->res_name[i]) || !isprint(r->res_name[i])) print_name = 0; } - seq_printf(s, "%s", print_name ? "str " : "hex"); + seq_puts(s, print_name ? "str " : "hex"); for (i = 0; i < r->res_length; i++) { if (print_name) @@ -377,10 +361,9 @@ static int print_format4(struct dlm_rsb *r, struct seq_file *s) else seq_printf(s, " %02x", (unsigned char)r->res_name[i]); } - rv = seq_puts(s, "\n"); - out: + seq_puts(s, "\n"); + unlock_rsb(r); - return rv; } struct rsbtbl_iter { @@ -390,47 +373,45 @@ struct rsbtbl_iter { int header; }; -/* seq_printf returns -1 if the buffer is full, and 0 otherwise. - If the buffer is full, seq_printf can be called again, but it - does nothing and just returns -1. So, the these printing routines - periodically check the return value to avoid wasting too much time - trying to print to a full buffer. */ +/* + * If the buffer is full, seq_printf can be called again, but it + * does nothing. So, the these printing routines periodically check + * seq_has_overflowed to avoid wasting too much time trying to print to + * a full buffer. + */ static int table_seq_show(struct seq_file *seq, void *iter_ptr) { struct rsbtbl_iter *ri = iter_ptr; - int rv = 0; switch (ri->format) { case 1: - rv = print_format1(ri->rsb, seq); + print_format1(ri->rsb, seq); break; case 2: if (ri->header) { - seq_printf(seq, "id nodeid remid pid xid exflags " - "flags sts grmode rqmode time_ms " - "r_nodeid r_len r_name\n"); + seq_puts(seq, "id nodeid remid pid xid exflags flags sts grmode rqmode time_ms r_nodeid r_len r_name\n"); ri->header = 0; } - rv = print_format2(ri->rsb, seq); + print_format2(ri->rsb, seq); break; case 3: if (ri->header) { - seq_printf(seq, "version rsb 1.1 lvb 1.1 lkb 1.1\n"); + seq_puts(seq, "version rsb 1.1 lvb 1.1 lkb 1.1\n"); ri->header = 0; } - rv = print_format3(ri->rsb, seq); + print_format3(ri->rsb, seq); break; case 4: if (ri->header) { - seq_printf(seq, "version 4 rsb 2\n"); + seq_puts(seq, "version 4 rsb 2\n"); ri->header = 0; } - rv = print_format4(ri->rsb, seq); + print_format4(ri->rsb, seq); break; } - return rv; + return 0; } static const struct seq_operations format1_seq_ops; diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 83f3d5520307..35502d4046f5 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -5886,6 +5886,78 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, return error; } +/* + * The caller asks for an orphan lock on a given resource with a given mode. + * If a matching lock exists, it's moved to the owner's list of locks and + * the lkid is returned. + */ + +int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, + int mode, uint32_t flags, void *name, unsigned int namelen, + unsigned long timeout_cs, uint32_t *lkid) +{ + struct dlm_lkb *lkb; + struct dlm_user_args *ua; + int found_other_mode = 0; + int found = 0; + int rv = 0; + + mutex_lock(&ls->ls_orphans_mutex); + list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) { + if (lkb->lkb_resource->res_length != namelen) + continue; + if (memcmp(lkb->lkb_resource->res_name, name, namelen)) + continue; + if (lkb->lkb_grmode != mode) { + found_other_mode = 1; + continue; + } + + found = 1; + list_del_init(&lkb->lkb_ownqueue); + lkb->lkb_flags &= ~DLM_IFL_ORPHAN; + *lkid = lkb->lkb_id; + break; + } + mutex_unlock(&ls->ls_orphans_mutex); + + if (!found && found_other_mode) { + rv = -EAGAIN; + goto out; + } + + if (!found) { + rv = -ENOENT; + goto out; + } + + lkb->lkb_exflags = flags; + lkb->lkb_ownpid = (int) current->pid; + + ua = lkb->lkb_ua; + + ua->proc = ua_tmp->proc; + ua->xid = ua_tmp->xid; + ua->castparam = ua_tmp->castparam; + ua->castaddr = ua_tmp->castaddr; + ua->bastparam = ua_tmp->bastparam; + ua->bastaddr = ua_tmp->bastaddr; + ua->user_lksb = ua_tmp->user_lksb; + + /* + * The lkb reference from the ls_orphans list was not + * removed above, and is now considered the reference + * for the proc locks list. + */ + + spin_lock(&ua->proc->locks_spin); + list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks); + spin_unlock(&ua->proc->locks_spin); + out: + kfree(ua_tmp); + return rv; +} + int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, uint32_t flags, uint32_t lkid, char *lvb_in) { @@ -6029,7 +6101,7 @@ static int orphan_proc_lock(struct dlm_ls *ls, struct dlm_lkb *lkb) struct dlm_args args; int error; - hold_lkb(lkb); + hold_lkb(lkb); /* reference for the ls_orphans list */ mutex_lock(&ls->ls_orphans_mutex); list_add_tail(&lkb->lkb_ownqueue, &ls->ls_orphans); mutex_unlock(&ls->ls_orphans_mutex); @@ -6217,7 +6289,7 @@ int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc, { int error = 0; - if (nodeid != dlm_our_nodeid()) { + if (nodeid && (nodeid != dlm_our_nodeid())) { error = send_purge(ls, nodeid, pid); } else { dlm_lock_recovery(ls); diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h index 5e0c72e36a9b..ed8ebd3a8593 100644 --- a/fs/dlm/lock.h +++ b/fs/dlm/lock.h @@ -49,6 +49,9 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode, int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, int mode, uint32_t flags, uint32_t lkid, char *lvb_in, unsigned long timeout_cs); +int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, + int mode, uint32_t flags, void *name, unsigned int namelen, + unsigned long timeout_cs, uint32_t *lkid); int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, uint32_t flags, uint32_t lkid, char *lvb_in); int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 142e21655eed..fb85f32e9eca 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -238,6 +238,7 @@ static int device_user_lock(struct dlm_user_proc *proc, { struct dlm_ls *ls; struct dlm_user_args *ua; + uint32_t lkid; int error = -ENOMEM; ls = dlm_find_lockspace_local(proc->lockspace); @@ -260,12 +261,20 @@ static int device_user_lock(struct dlm_user_proc *proc, ua->bastaddr = params->bastaddr; ua->xid = params->xid; - if (params->flags & DLM_LKF_CONVERT) + if (params->flags & DLM_LKF_CONVERT) { error = dlm_user_convert(ls, ua, params->mode, params->flags, params->lkid, params->lvb, (unsigned long) params->timeout); - else { + } else if (params->flags & DLM_LKF_ORPHAN) { + error = dlm_user_adopt_orphan(ls, ua, + params->mode, params->flags, + params->name, params->namelen, + (unsigned long) params->timeout, + &lkid); + if (!error) + error = lkid; + } else { error = dlm_user_request(ls, ua, params->mode, params->flags, params->name, params->namelen, diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 2f6735dbf1a9..c2d6604667b0 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1373,7 +1373,7 @@ out: int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode) { struct dentry *lower_dentry = - ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_dentry; + ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_path.dentry; ssize_t size; int rc = 0; diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index f5bce9096555..80154ec4f8c2 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -75,11 +75,11 @@ struct ecryptfs_getdents_callback { /* Inspired by generic filldir in fs/readdir.c */ static int -ecryptfs_filldir(void *dirent, const char *lower_name, int lower_namelen, - loff_t offset, u64 ino, unsigned int d_type) +ecryptfs_filldir(struct dir_context *ctx, const char *lower_name, + int lower_namelen, loff_t offset, u64 ino, unsigned int d_type) { struct ecryptfs_getdents_callback *buf = - (struct ecryptfs_getdents_callback *)dirent; + container_of(ctx, struct ecryptfs_getdents_callback, ctx); size_t name_size; char *name; int rc; diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 564a1fa34b99..4626976794e7 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -419,7 +419,7 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode) ssize_t size; void *xattr_virt; struct dentry *lower_dentry = - ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_dentry; + ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_path.dentry; struct inode *lower_inode = lower_dentry->d_inode; int rc; diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index cdb2971192a5..90001da9abfd 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -47,8 +47,8 @@ static ssize_t efivarfs_file_write(struct file *file, if (bytes == -ENOENT) { drop_nlink(inode); - d_delete(file->f_dentry); - dput(file->f_dentry); + d_delete(file->f_path.dentry); + dput(file->f_path.dentry); } else { mutex_lock(&inode->i_mutex); i_size_write(inode, datasize + sizeof(attributes)); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 0a48886e069c..6dad1176ec52 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -236,6 +236,7 @@ static void efivarfs_kill_sb(struct super_block *sb) } static struct file_system_type efivarfs_type = { + .owner = THIS_MODULE, .name = "efivarfs", .mount = efivarfs_mount, .kill_sb = efivarfs_kill_sb, @@ -244,17 +245,23 @@ static struct file_system_type efivarfs_type = { static __init int efivarfs_init(void) { if (!efi_enabled(EFI_RUNTIME_SERVICES)) - return 0; + return -ENODEV; if (!efivars_kobject()) - return 0; + return -ENODEV; return register_filesystem(&efivarfs_type); } +static __exit void efivarfs_exit(void) +{ + unregister_filesystem(&efivarfs_type); +} + MODULE_AUTHOR("Matthew Garrett, Jeremy Kerr"); MODULE_DESCRIPTION("EFI Variable Filesystem"); MODULE_LICENSE("GPL"); MODULE_ALIAS_FS("efivarfs"); module_init(efivarfs_init); +module_exit(efivarfs_exit); diff --git a/fs/eventfd.c b/fs/eventfd.c index d6a88e7812f3..4b0a226024fa 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -287,17 +287,14 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c } #ifdef CONFIG_PROC_FS -static int eventfd_show_fdinfo(struct seq_file *m, struct file *f) +static void eventfd_show_fdinfo(struct seq_file *m, struct file *f) { struct eventfd_ctx *ctx = f->private_data; - int ret; spin_lock_irq(&ctx->wqh.lock); - ret = seq_printf(m, "eventfd-count: %16llx\n", - (unsigned long long)ctx->count); + seq_printf(m, "eventfd-count: %16llx\n", + (unsigned long long)ctx->count); spin_unlock_irq(&ctx->wqh.lock); - - return ret; } #endif diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 7bcfff900f05..d77f94491352 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -870,25 +870,22 @@ static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait) } #ifdef CONFIG_PROC_FS -static int ep_show_fdinfo(struct seq_file *m, struct file *f) +static void ep_show_fdinfo(struct seq_file *m, struct file *f) { struct eventpoll *ep = f->private_data; struct rb_node *rbp; - int ret = 0; mutex_lock(&ep->mtx); for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); - ret = seq_printf(m, "tfd: %8d events: %8x data: %16llx\n", - epi->ffd.fd, epi->event.events, - (long long)epi->event.data); - if (ret) + seq_printf(m, "tfd: %8d events: %8x data: %16llx\n", + epi->ffd.fd, epi->event.events, + (long long)epi->event.data); + if (seq_has_overflowed(m)) break; } mutex_unlock(&ep->mtx); - - return ret; } #endif diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index b01fbfb51f43..fdfd206c737a 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -50,7 +50,7 @@ find_acceptable_alias(struct dentry *result, inode = result->d_inode; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) @@ -241,10 +241,11 @@ struct getdents_callback { * A rather strange filldir function to capture * the name matching the specified inode number. */ -static int filldir_one(void * __buf, const char * name, int len, +static int filldir_one(struct dir_context *ctx, const char *name, int len, loff_t pos, u64 ino, unsigned int d_type) { - struct getdents_callback *buf = __buf; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); int result = 0; buf->sequence++; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index d9a17d0b124d..e4279ead4a05 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -689,6 +689,9 @@ struct ext2_inode_info { struct mutex truncate_mutex; struct inode vfs_inode; struct list_head i_orphan; /* unlinked but open inodes */ +#ifdef CONFIG_QUOTA + struct dquot *i_dquot[MAXQUOTAS]; +#endif }; /* diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 170dc41e8bf4..ae55fddc26a9 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -166,6 +166,10 @@ static struct inode *ext2_alloc_inode(struct super_block *sb) return NULL; ei->i_block_alloc_info = NULL; ei->vfs_inode.i_version = 1; +#ifdef CONFIG_QUOTA + memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); +#endif + return &ei->vfs_inode; } @@ -303,6 +307,10 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root) #ifdef CONFIG_QUOTA static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); +static struct dquot **ext2_get_dquots(struct inode *inode) +{ + return EXT2_I(inode)->i_dquot; +} #endif static const struct super_operations ext2_sops = { @@ -320,6 +328,7 @@ static const struct super_operations ext2_sops = { #ifdef CONFIG_QUOTA .quota_read = ext2_quota_read, .quota_write = ext2_quota_write, + .get_dquots = ext2_get_dquots, #endif }; @@ -1090,6 +1099,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->dq_op = &dquot_operations; sb->s_qcop = &dquot_quotactl_ops; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; #endif root = ext2_iget(sb, EXT2_ROOT_INO); diff --git a/fs/ext3/ext3.h b/fs/ext3/ext3.h index fc3cdcf24aed..f483a80b3fe7 100644 --- a/fs/ext3/ext3.h +++ b/fs/ext3/ext3.h @@ -615,6 +615,10 @@ struct ext3_inode_info { atomic_t i_sync_tid; atomic_t i_datasync_tid; +#ifdef CONFIG_QUOTA + struct dquot *i_dquot[MAXQUOTAS]; +#endif + struct inode vfs_inode; }; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index eb742d0e67ff..9b4e7d750d4f 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -485,6 +485,10 @@ static struct inode *ext3_alloc_inode(struct super_block *sb) ei->vfs_inode.i_version = 1; atomic_set(&ei->i_datasync_tid, 0); atomic_set(&ei->i_sync_tid, 0); +#ifdef CONFIG_QUOTA + memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); +#endif + return &ei->vfs_inode; } @@ -764,6 +768,10 @@ static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext3_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); +static struct dquot **ext3_get_dquots(struct inode *inode) +{ + return EXT3_I(inode)->i_dquot; +} static const struct dquot_operations ext3_quota_operations = { .write_dquot = ext3_write_dquot, @@ -803,6 +811,7 @@ static const struct super_operations ext3_sops = { #ifdef CONFIG_QUOTA .quota_read = ext3_quota_read, .quota_write = ext3_quota_write, + .get_dquots = ext3_get_dquots, #endif .bdev_try_to_free_page = bdev_try_to_free_page, }; @@ -2001,6 +2010,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->s_qcop = &ext3_qctl_operations; sb->dq_op = &ext3_quota_operations; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; #endif memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c55a1faaed58..db3f772e57ae 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -941,6 +941,10 @@ struct ext4_inode_info { tid_t i_sync_tid; tid_t i_datasync_tid; +#ifdef CONFIG_QUOTA + struct dquot *i_dquot[MAXQUOTAS]; +#endif + /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ __u32 i_csum_seed; }; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2c9e6864abd9..63e802b8ec68 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -892,6 +892,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) spin_lock_init(&(ei->i_block_reservation_lock)); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; + memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_rsv_conversion_list); @@ -1068,6 +1069,11 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); static int ext4_enable_quotas(struct super_block *sb); +static struct dquot **ext4_get_dquots(struct inode *inode) +{ + return EXT4_I(inode)->i_dquot; +} + static const struct dquot_operations ext4_quota_operations = { .get_reserved_space = ext4_get_reserved_space, .write_dquot = ext4_write_dquot, @@ -1117,6 +1123,7 @@ static const struct super_operations ext4_sops = { #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, + .get_dquots = ext4_get_dquots, #endif .bdev_try_to_free_page = bdev_try_to_free_page, }; @@ -3932,6 +3939,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_qcop = &ext4_qctl_sysfile_operations; else sb->s_qcop = &ext4_qctl_operations; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; #endif memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 83b9b5a8d112..1ccb26bc2a0b 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -162,7 +162,8 @@ fail: return ERR_PTR(-EINVAL); } -struct posix_acl *f2fs_get_acl(struct inode *inode, int type) +static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type, + struct page *dpage) { int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT; void *value = NULL; @@ -172,12 +173,13 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type) if (type == ACL_TYPE_ACCESS) name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; - retval = f2fs_getxattr(inode, name_index, "", NULL, 0); + retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage); if (retval > 0) { value = kmalloc(retval, GFP_F2FS_ZERO); if (!value) return ERR_PTR(-ENOMEM); - retval = f2fs_getxattr(inode, name_index, "", value, retval); + retval = f2fs_getxattr(inode, name_index, "", value, + retval, dpage); } if (retval > 0) @@ -194,6 +196,11 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type) return acl; } +struct posix_acl *f2fs_get_acl(struct inode *inode, int type) +{ + return __f2fs_get_acl(inode, type, NULL); +} + static int __f2fs_set_acl(struct inode *inode, int type, struct posix_acl *acl, struct page *ipage) { @@ -229,7 +236,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, if (acl) { value = f2fs_acl_to_disk(acl, &size); if (IS_ERR(value)) { - cond_clear_inode_flag(fi, FI_ACL_MODE); + clear_inode_flag(fi, FI_ACL_MODE); return (int)PTR_ERR(value); } } @@ -240,7 +247,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, if (!error) set_cached_acl(inode, type, acl); - cond_clear_inode_flag(fi, FI_ACL_MODE); + clear_inode_flag(fi, FI_ACL_MODE); return error; } @@ -249,12 +256,137 @@ int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return __f2fs_set_acl(inode, type, acl, NULL); } -int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage) +/* + * Most part of f2fs_acl_clone, f2fs_acl_create_masq, f2fs_acl_create + * are copied from posix_acl.c + */ +static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl, + gfp_t flags) +{ + struct posix_acl *clone = NULL; + + if (acl) { + int size = sizeof(struct posix_acl) + acl->a_count * + sizeof(struct posix_acl_entry); + clone = kmemdup(acl, size, flags); + if (clone) + atomic_set(&clone->a_refcount, 1); + } + return clone; +} + +static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) +{ + struct posix_acl_entry *pa, *pe; + struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; + umode_t mode = *mode_p; + int not_equiv = 0; + + /* assert(atomic_read(acl->a_refcount) == 1); */ + + FOREACH_ACL_ENTRY(pa, acl, pe) { + switch(pa->e_tag) { + case ACL_USER_OBJ: + pa->e_perm &= (mode >> 6) | ~S_IRWXO; + mode &= (pa->e_perm << 6) | ~S_IRWXU; + break; + + case ACL_USER: + case ACL_GROUP: + not_equiv = 1; + break; + + case ACL_GROUP_OBJ: + group_obj = pa; + break; + + case ACL_OTHER: + pa->e_perm &= mode | ~S_IRWXO; + mode &= pa->e_perm | ~S_IRWXO; + break; + + case ACL_MASK: + mask_obj = pa; + not_equiv = 1; + break; + + default: + return -EIO; + } + } + + if (mask_obj) { + mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; + mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; + } else { + if (!group_obj) + return -EIO; + group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; + mode &= (group_obj->e_perm << 3) | ~S_IRWXG; + } + + *mode_p = (*mode_p & ~S_IRWXUGO) | mode; + return not_equiv; +} + +static int f2fs_acl_create(struct inode *dir, umode_t *mode, + struct posix_acl **default_acl, struct posix_acl **acl, + struct page *dpage) +{ + struct posix_acl *p; + int ret; + + if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) + goto no_acl; + + p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage); + if (IS_ERR(p)) { + if (p == ERR_PTR(-EOPNOTSUPP)) + goto apply_umask; + return PTR_ERR(p); + } + + if (!p) + goto apply_umask; + + *acl = f2fs_acl_clone(p, GFP_NOFS); + if (!*acl) + return -ENOMEM; + + ret = f2fs_acl_create_masq(*acl, mode); + if (ret < 0) { + posix_acl_release(*acl); + return -ENOMEM; + } + + if (ret == 0) { + posix_acl_release(*acl); + *acl = NULL; + } + + if (!S_ISDIR(*mode)) { + posix_acl_release(p); + *default_acl = NULL; + } else { + *default_acl = p; + } + return 0; + +apply_umask: + *mode &= ~current_umask(); +no_acl: + *default_acl = NULL; + *acl = NULL; + return 0; +} + +int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, + struct page *dpage) { - struct posix_acl *default_acl, *acl; + struct posix_acl *default_acl = NULL, *acl = NULL; int error = 0; - error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); + error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dpage); if (error) return error; diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index e0864651cdc1..997ca8edb6cb 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -38,14 +38,15 @@ struct f2fs_acl_header { extern struct posix_acl *f2fs_get_acl(struct inode *, int); extern int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type); -extern int f2fs_init_acl(struct inode *, struct inode *, struct page *); +extern int f2fs_init_acl(struct inode *, struct inode *, struct page *, + struct page *); #else #define f2fs_check_acl NULL #define f2fs_get_acl NULL #define f2fs_set_acl NULL static inline int f2fs_init_acl(struct inode *inode, struct inode *dir, - struct page *page) + struct page *ipage, struct page *dpage) { return 0; } diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index dd10a031c052..e6c271fefaca 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -72,36 +72,36 @@ out: return page; } -struct page *get_meta_page_ra(struct f2fs_sb_info *sbi, pgoff_t index) -{ - bool readahead = false; - struct page *page; - - page = find_get_page(META_MAPPING(sbi), index); - if (!page || (page && !PageUptodate(page))) - readahead = true; - f2fs_put_page(page, 0); - - if (readahead) - ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR); - return get_meta_page(sbi, index); -} - -static inline block_t get_max_meta_blks(struct f2fs_sb_info *sbi, int type) +static inline bool is_valid_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type) { switch (type) { case META_NAT: - return NM_I(sbi)->max_nid / NAT_ENTRY_PER_BLOCK; + break; case META_SIT: - return SIT_BLK_CNT(sbi); + if (unlikely(blkaddr >= SIT_BLK_CNT(sbi))) + return false; + break; case META_SSA: + if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) || + blkaddr < SM_I(sbi)->ssa_blkaddr)) + return false; + break; case META_CP: - return 0; + if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr || + blkaddr < __start_cp_addr(sbi))) + return false; + break; case META_POR: - return MAX_BLKADDR(sbi); + if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || + blkaddr < MAIN_BLKADDR(sbi))) + return false; + break; default: BUG(); } + + return true; } /* @@ -112,7 +112,6 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type block_t prev_blk_addr = 0; struct page *page; block_t blkno = start; - block_t max_blks = get_max_meta_blks(sbi, type); struct f2fs_io_info fio = { .type = META, @@ -122,18 +121,20 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type for (; nrpages-- > 0; blkno++) { block_t blk_addr; + if (!is_valid_blkaddr(sbi, blkno, type)) + goto out; + switch (type) { case META_NAT: - /* get nat block addr */ - if (unlikely(blkno >= max_blks)) + if (unlikely(blkno >= + NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid))) blkno = 0; + /* get nat block addr */ blk_addr = current_nat_addr(sbi, blkno * NAT_ENTRY_PER_BLOCK); break; case META_SIT: /* get sit block addr */ - if (unlikely(blkno >= max_blks)) - goto out; blk_addr = current_sit_addr(sbi, blkno * SIT_ENTRY_PER_BLOCK); if (blkno != start && prev_blk_addr + 1 != blk_addr) @@ -143,10 +144,6 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type case META_SSA: case META_CP: case META_POR: - if (unlikely(blkno >= max_blks)) - goto out; - if (unlikely(blkno < SEG0_BLKADDR(sbi))) - goto out; blk_addr = blkno; break; default: @@ -169,6 +166,20 @@ out: return blkno - start; } +void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) +{ + struct page *page; + bool readahead = false; + + page = find_get_page(META_MAPPING(sbi), index); + if (!page || (page && !PageUptodate(page))) + readahead = true; + f2fs_put_page(page, 0); + + if (readahead) + ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR); +} + static int f2fs_write_meta_page(struct page *page, struct writeback_control *wbc) { @@ -178,7 +189,7 @@ static int f2fs_write_meta_page(struct page *page, if (unlikely(sbi->por_doing)) goto redirty_out; - if (wbc->for_reclaim) + if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0)) goto redirty_out; if (unlikely(f2fs_cp_error(sbi))) goto redirty_out; @@ -187,6 +198,9 @@ static int f2fs_write_meta_page(struct page *page, write_meta_page(sbi, page); dec_page_count(sbi, F2FS_DIRTY_META); unlock_page(page); + + if (wbc->for_reclaim) + f2fs_submit_merged_bio(sbi, META, WRITE); return 0; redirty_out: @@ -298,46 +312,57 @@ const struct address_space_operations f2fs_meta_aops = { static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { + struct inode_management *im = &sbi->im[type]; struct ino_entry *e; retry: - spin_lock(&sbi->ino_lock[type]); + if (radix_tree_preload(GFP_NOFS)) { + cond_resched(); + goto retry; + } + + spin_lock(&im->ino_lock); - e = radix_tree_lookup(&sbi->ino_root[type], ino); + e = radix_tree_lookup(&im->ino_root, ino); if (!e) { e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC); if (!e) { - spin_unlock(&sbi->ino_lock[type]); + spin_unlock(&im->ino_lock); + radix_tree_preload_end(); goto retry; } - if (radix_tree_insert(&sbi->ino_root[type], ino, e)) { - spin_unlock(&sbi->ino_lock[type]); + if (radix_tree_insert(&im->ino_root, ino, e)) { + spin_unlock(&im->ino_lock); kmem_cache_free(ino_entry_slab, e); + radix_tree_preload_end(); goto retry; } memset(e, 0, sizeof(struct ino_entry)); e->ino = ino; - list_add_tail(&e->list, &sbi->ino_list[type]); + list_add_tail(&e->list, &im->ino_list); + if (type != ORPHAN_INO) + im->ino_num++; } - spin_unlock(&sbi->ino_lock[type]); + spin_unlock(&im->ino_lock); + radix_tree_preload_end(); } static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { + struct inode_management *im = &sbi->im[type]; struct ino_entry *e; - spin_lock(&sbi->ino_lock[type]); - e = radix_tree_lookup(&sbi->ino_root[type], ino); + spin_lock(&im->ino_lock); + e = radix_tree_lookup(&im->ino_root, ino); if (e) { list_del(&e->list); - radix_tree_delete(&sbi->ino_root[type], ino); - if (type == ORPHAN_INO) - sbi->n_orphans--; - spin_unlock(&sbi->ino_lock[type]); + radix_tree_delete(&im->ino_root, ino); + im->ino_num--; + spin_unlock(&im->ino_lock); kmem_cache_free(ino_entry_slab, e); return; } - spin_unlock(&sbi->ino_lock[type]); + spin_unlock(&im->ino_lock); } void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) @@ -355,10 +380,12 @@ void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) /* mode should be APPEND_INO or UPDATE_INO */ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) { + struct inode_management *im = &sbi->im[mode]; struct ino_entry *e; - spin_lock(&sbi->ino_lock[mode]); - e = radix_tree_lookup(&sbi->ino_root[mode], ino); - spin_unlock(&sbi->ino_lock[mode]); + + spin_lock(&im->ino_lock); + e = radix_tree_lookup(&im->ino_root, ino); + spin_unlock(&im->ino_lock); return e ? true : false; } @@ -368,36 +395,42 @@ void release_dirty_inode(struct f2fs_sb_info *sbi) int i; for (i = APPEND_INO; i <= UPDATE_INO; i++) { - spin_lock(&sbi->ino_lock[i]); - list_for_each_entry_safe(e, tmp, &sbi->ino_list[i], list) { + struct inode_management *im = &sbi->im[i]; + + spin_lock(&im->ino_lock); + list_for_each_entry_safe(e, tmp, &im->ino_list, list) { list_del(&e->list); - radix_tree_delete(&sbi->ino_root[i], e->ino); + radix_tree_delete(&im->ino_root, e->ino); kmem_cache_free(ino_entry_slab, e); + im->ino_num--; } - spin_unlock(&sbi->ino_lock[i]); + spin_unlock(&im->ino_lock); } } int acquire_orphan_inode(struct f2fs_sb_info *sbi) { + struct inode_management *im = &sbi->im[ORPHAN_INO]; int err = 0; - spin_lock(&sbi->ino_lock[ORPHAN_INO]); - if (unlikely(sbi->n_orphans >= sbi->max_orphans)) + spin_lock(&im->ino_lock); + if (unlikely(im->ino_num >= sbi->max_orphans)) err = -ENOSPC; else - sbi->n_orphans++; - spin_unlock(&sbi->ino_lock[ORPHAN_INO]); + im->ino_num++; + spin_unlock(&im->ino_lock); return err; } void release_orphan_inode(struct f2fs_sb_info *sbi) { - spin_lock(&sbi->ino_lock[ORPHAN_INO]); - f2fs_bug_on(sbi, sbi->n_orphans == 0); - sbi->n_orphans--; - spin_unlock(&sbi->ino_lock[ORPHAN_INO]); + struct inode_management *im = &sbi->im[ORPHAN_INO]; + + spin_lock(&im->ino_lock); + f2fs_bug_on(sbi, im->ino_num == 0); + im->ino_num--; + spin_unlock(&im->ino_lock); } void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) @@ -460,17 +493,19 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) struct f2fs_orphan_block *orphan_blk = NULL; unsigned int nentries = 0; unsigned short index; - unsigned short orphan_blocks = - (unsigned short)GET_ORPHAN_BLOCKS(sbi->n_orphans); + unsigned short orphan_blocks; struct page *page = NULL; struct ino_entry *orphan = NULL; + struct inode_management *im = &sbi->im[ORPHAN_INO]; + + orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num); for (index = 0; index < orphan_blocks; index++) grab_meta_page(sbi, start_blk + index); index = 1; - spin_lock(&sbi->ino_lock[ORPHAN_INO]); - head = &sbi->ino_list[ORPHAN_INO]; + spin_lock(&im->ino_lock); + head = &im->ino_list; /* loop for each orphan inode entry and write them in Jornal block */ list_for_each_entry(orphan, head, list) { @@ -510,7 +545,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) f2fs_put_page(page, 1); } - spin_unlock(&sbi->ino_lock[ORPHAN_INO]); + spin_unlock(&im->ino_lock); } static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, @@ -731,6 +766,9 @@ void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi) struct dir_inode_entry *entry; struct inode *inode; retry: + if (unlikely(f2fs_cp_error(sbi))) + return; + spin_lock(&sbi->dir_inode_lock); head = &sbi->dir_inode_list; @@ -830,6 +868,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; nid_t last_nid = nm_i->next_scan_nid; block_t start_blk; struct page *cp_page; @@ -889,7 +928,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) else clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); - orphan_blocks = GET_ORPHAN_BLOCKS(sbi->n_orphans); + orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num); ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks + orphan_blocks); @@ -905,7 +944,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) orphan_blocks); } - if (sbi->n_orphans) + if (orphan_num) set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); else clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); @@ -940,7 +979,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) f2fs_put_page(cp_page, 1); } - if (sbi->n_orphans) { + if (orphan_num) { write_orphan_inodes(sbi, start_blk); start_blk += orphan_blocks; } @@ -975,6 +1014,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* Here, we only have one bio having CP pack */ sync_meta_pages(sbi, META_FLUSH, LONG_MAX); + /* wait for previous submitted meta pages writeback */ + wait_on_all_pages_writeback(sbi); + release_dirty_inode(sbi); if (unlikely(f2fs_cp_error(sbi))) @@ -1036,9 +1078,12 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi) int i; for (i = 0; i < MAX_INO_ENTRY; i++) { - INIT_RADIX_TREE(&sbi->ino_root[i], GFP_ATOMIC); - spin_lock_init(&sbi->ino_lock[i]); - INIT_LIST_HEAD(&sbi->ino_list[i]); + struct inode_management *im = &sbi->im[i]; + + INIT_RADIX_TREE(&im->ino_root, GFP_ATOMIC); + spin_lock_init(&im->ino_lock); + INIT_LIST_HEAD(&im->ino_list); + im->ino_num = 0; } /* @@ -1047,7 +1092,6 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi) * orphan entries with the limitation one reserved segment * for cp pack we can have max 1020*504 orphan entries */ - sbi->n_orphans = 0; sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS - NR_CURSEG_TYPE) * F2FS_ORPHANS_PER_BLOCK; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8e58c4cc2cb9..7ec697b37f19 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -61,11 +61,6 @@ static void f2fs_write_end_io(struct bio *bio, int err) dec_page_count(sbi, F2FS_WRITEBACK); } - if (sbi->wait_io) { - complete(sbi->wait_io); - sbi->wait_io = NULL; - } - if (!get_pages(sbi, F2FS_WRITEBACK) && !list_empty(&sbi->cp_wait.task_list)) wake_up(&sbi->cp_wait); @@ -95,34 +90,18 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, static void __submit_merged_bio(struct f2fs_bio_info *io) { struct f2fs_io_info *fio = &io->fio; - int rw; if (!io->bio) return; - rw = fio->rw; - - if (is_read_io(rw)) { - trace_f2fs_submit_read_bio(io->sbi->sb, rw, - fio->type, io->bio); - submit_bio(rw, io->bio); - } else { - trace_f2fs_submit_write_bio(io->sbi->sb, rw, - fio->type, io->bio); - /* - * META_FLUSH is only from the checkpoint procedure, and we - * should wait this metadata bio for FS consistency. - */ - if (fio->type == META_FLUSH) { - DECLARE_COMPLETION_ONSTACK(wait); - io->sbi->wait_io = &wait; - submit_bio(rw, io->bio); - wait_for_completion(&wait); - } else { - submit_bio(rw, io->bio); - } - } + if (is_read_io(fio->rw)) + trace_f2fs_submit_read_bio(io->sbi->sb, fio->rw, + fio->type, io->bio); + else + trace_f2fs_submit_write_bio(io->sbi->sb, fio->rw, + fio->type, io->bio); + submit_bio(fio->rw, io->bio); io->bio = NULL; } @@ -257,9 +236,6 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) bool need_put = dn->inode_page ? false : true; int err; - /* if inode_page exists, index should be zero */ - f2fs_bug_on(F2FS_I_SB(dn->inode), !need_put && index); - err = get_dnode_of_data(dn, index, ALLOC_NODE); if (err) return err; @@ -740,14 +716,14 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, static int f2fs_read_data_page(struct file *file, struct page *page) { struct inode *inode = page->mapping->host; - int ret; + int ret = -EAGAIN; trace_f2fs_readpage(page, DATA); /* If the file has inline data, try to read it directly */ if (f2fs_has_inline_data(inode)) ret = f2fs_read_inline_data(inode, page); - else + if (ret == -EAGAIN) ret = mpage_readpage(page, get_data_block); return ret; @@ -859,10 +835,11 @@ write: else if (has_not_enough_free_secs(sbi, 0)) goto redirty_out; + err = -EAGAIN; f2fs_lock_op(sbi); - if (f2fs_has_inline_data(inode) || f2fs_may_inline(inode)) - err = f2fs_write_inline_data(inode, page, offset); - else + if (f2fs_has_inline_data(inode)) + err = f2fs_write_inline_data(inode, page); + if (err == -EAGAIN) err = do_write_data_page(page, &fio); f2fs_unlock_op(sbi); done: @@ -951,7 +928,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct page *page; + struct page *page, *ipage; pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; struct dnode_of_data dn; int err = 0; @@ -959,45 +936,60 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, trace_f2fs_write_begin(inode, pos, len, flags); f2fs_balance_fs(sbi); -repeat: - err = f2fs_convert_inline_data(inode, pos + len, NULL); - if (err) - goto fail; + /* + * We should check this at this moment to avoid deadlock on inode page + * and #0 page. The locking rule for inline_data conversion should be: + * lock_page(page #0) -> lock_page(inode_page) + */ + if (index != 0) { + err = f2fs_convert_inline_inode(inode); + if (err) + goto fail; + } +repeat: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) { err = -ENOMEM; goto fail; } - /* to avoid latency during memory pressure */ - unlock_page(page); - *pagep = page; - if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA) - goto inline_data; - f2fs_lock_op(sbi); - set_new_dnode(&dn, inode, NULL, NULL, 0); - err = f2fs_reserve_block(&dn, index); - f2fs_unlock_op(sbi); - if (err) { - f2fs_put_page(page, 0); - goto fail; - } -inline_data: - lock_page(page); - if (unlikely(page->mapping != mapping)) { - f2fs_put_page(page, 1); - goto repeat; + + /* check inline_data */ + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto unlock_fail; } - f2fs_wait_on_page_writeback(page, DATA); + set_new_dnode(&dn, inode, ipage, ipage, 0); + + if (f2fs_has_inline_data(inode)) { + if (pos + len <= MAX_INLINE_DATA) { + read_inline_data(page, ipage); + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + sync_inode_page(&dn); + goto put_next; + } + err = f2fs_convert_inline_page(&dn, page); + if (err) + goto put_fail; + } + err = f2fs_reserve_block(&dn, index); + if (err) + goto put_fail; +put_next: + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); if ((len == PAGE_CACHE_SIZE) || PageUptodate(page)) return 0; + f2fs_wait_on_page_writeback(page, DATA); + if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { unsigned start = pos & (PAGE_CACHE_SIZE - 1); unsigned end = start + len; @@ -1010,18 +1002,10 @@ inline_data: if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); } else { - if (f2fs_has_inline_data(inode)) { - err = f2fs_read_inline_data(inode, page); - if (err) { - page_cache_release(page); - goto fail; - } - } else { - err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, - READ_SYNC); - if (err) - goto fail; - } + err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, + READ_SYNC); + if (err) + goto fail; lock_page(page); if (unlikely(!PageUptodate(page))) { @@ -1038,6 +1022,12 @@ out: SetPageUptodate(page); clear_cold_data(page); return 0; + +put_fail: + f2fs_put_dnode(&dn); +unlock_fail: + f2fs_unlock_op(sbi); + f2fs_put_page(page, 1); fail: f2fs_write_failed(mapping, pos + len); return err; @@ -1052,10 +1042,7 @@ static int f2fs_write_end(struct file *file, trace_f2fs_write_end(inode, pos, len, copied); - if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode)) - register_inmem_page(inode, page); - else - set_page_dirty(page); + set_page_dirty(page); if (pos + copied > i_size_read(inode)) { i_size_write(inode, pos + copied); @@ -1093,9 +1080,12 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); int err; - /* Let buffer I/O handle the inline data case. */ - if (f2fs_has_inline_data(inode)) - return 0; + /* we don't need to use inline_data strictly */ + if (f2fs_has_inline_data(inode)) { + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } if (check_direct_IO(inode, rw, iter, offset)) return 0; @@ -1119,6 +1109,9 @@ static void f2fs_invalidate_data_page(struct page *page, unsigned int offset, if (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE) return; + if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode)) + invalidate_inmem_page(inode, page); + if (PageDirty(page)) inode_dec_dirty_pages(inode); ClearPagePrivate(page); @@ -1138,6 +1131,12 @@ static int f2fs_set_data_page_dirty(struct page *page) trace_f2fs_set_page_dirty(page, DATA); SetPageUptodate(page); + + if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode)) { + register_inmem_page(inode, page); + return 1; + } + mark_inode_dirty(inode); if (!PageDirty(page)) { @@ -1152,9 +1151,12 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; - if (f2fs_has_inline_data(inode)) - return 0; - + /* we don't need to use inline_data strictly */ + if (f2fs_has_inline_data(inode)) { + int err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } return generic_block_bmap(mapping, block, get_data_block); } diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 0a91ab813a9e..91e8f699ab30 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -39,13 +39,15 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS); si->ndirty_dirs = sbi->n_dirty_dirs; si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META); + si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES); si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg; si->rsvd_segs = reserved_segments(sbi); si->overp_segs = overprovision_segments(sbi); si->valid_count = valid_user_blocks(sbi); si->valid_node_count = valid_node_count(sbi); si->valid_inode_count = valid_inode_count(sbi); - si->inline_inode = sbi->inline_inode; + si->inline_inode = atomic_read(&sbi->inline_inode); + si->inline_dir = atomic_read(&sbi->inline_dir); si->utilization = utilization(sbi); si->free_segs = free_segments(sbi); @@ -118,6 +120,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); unsigned npages; + int i; if (si->base_mem) goto get_cache; @@ -167,8 +170,9 @@ get_cache: si->cache_mem += npages << PAGE_CACHE_SHIFT; npages = META_MAPPING(sbi)->nrpages; si->cache_mem += npages << PAGE_CACHE_SHIFT; - si->cache_mem += sbi->n_orphans * sizeof(struct ino_entry); si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry); + for (i = 0; i <= UPDATE_INO; i++) + si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry); } static int stat_show(struct seq_file *s, void *v) @@ -200,6 +204,8 @@ static int stat_show(struct seq_file *s, void *v) si->valid_count - si->valid_node_count); seq_printf(s, " - Inline_data Inode: %u\n", si->inline_inode); + seq_printf(s, " - Inline_dentry Inode: %u\n", + si->inline_dir); seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n", si->main_area_segs, si->main_area_sections, si->main_area_zones); @@ -244,6 +250,8 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, "\nExtent Hit Ratio: %d / %d\n", si->hit_ext, si->total_ext); seq_puts(s, "\nBalancing F2FS Async:\n"); + seq_printf(s, " - inmem: %4d\n", + si->inmem_pages); seq_printf(s, " - nodes: %4d in %4d\n", si->ndirty_node, si->node_pages); seq_printf(s, " - dents: %4d in dirs:%4d\n", @@ -321,6 +329,9 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) si->sbi = sbi; sbi->stat_info = si; + atomic_set(&sbi->inline_inode, 0); + atomic_set(&sbi->inline_dir, 0); + mutex_lock(&f2fs_stat_mutex); list_add_tail(&si->stat_list, &f2fs_stat_list); mutex_unlock(&f2fs_stat_mutex); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index b54f87149c09..b1a7d5737cd0 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -37,7 +37,7 @@ static unsigned int bucket_blocks(unsigned int level) return 4; } -static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = { +unsigned char f2fs_filetype_table[F2FS_FT_MAX] = { [F2FS_FT_UNKNOWN] = DT_UNKNOWN, [F2FS_FT_REG_FILE] = DT_REG, [F2FS_FT_DIR] = DT_DIR, @@ -59,7 +59,7 @@ static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = { [S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK, }; -static void set_de_type(struct f2fs_dir_entry *de, struct inode *inode) +void set_de_type(struct f2fs_dir_entry *de, struct inode *inode) { umode_t mode = inode->i_mode; de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT]; @@ -90,51 +90,70 @@ static bool early_match_name(size_t namelen, f2fs_hash_t namehash, } static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, - struct qstr *name, int *max_slots, - f2fs_hash_t namehash, struct page **res_page) + struct qstr *name, int *max_slots, + struct page **res_page) +{ + struct f2fs_dentry_block *dentry_blk; + struct f2fs_dir_entry *de; + struct f2fs_dentry_ptr d; + + dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page); + + make_dentry_ptr(&d, (void *)dentry_blk, 1); + de = find_target_dentry(name, max_slots, &d); + + if (de) + *res_page = dentry_page; + else + kunmap(dentry_page); + + /* + * For the most part, it should be a bug when name_len is zero. + * We stop here for figuring out where the bugs has occurred. + */ + f2fs_bug_on(F2FS_P_SB(dentry_page), d.max < 0); + return de; +} + +struct f2fs_dir_entry *find_target_dentry(struct qstr *name, int *max_slots, + struct f2fs_dentry_ptr *d) { struct f2fs_dir_entry *de; unsigned long bit_pos = 0; - struct f2fs_dentry_block *dentry_blk = kmap(dentry_page); - const void *dentry_bits = &dentry_blk->dentry_bitmap; + f2fs_hash_t namehash = f2fs_dentry_hash(name); int max_len = 0; - while (bit_pos < NR_DENTRY_IN_BLOCK) { - if (!test_bit_le(bit_pos, dentry_bits)) { + if (max_slots) + *max_slots = 0; + while (bit_pos < d->max) { + if (!test_bit_le(bit_pos, d->bitmap)) { if (bit_pos == 0) max_len = 1; - else if (!test_bit_le(bit_pos - 1, dentry_bits)) + else if (!test_bit_le(bit_pos - 1, d->bitmap)) max_len++; bit_pos++; continue; } - de = &dentry_blk->dentry[bit_pos]; - if (early_match_name(name->len, namehash, de)) { - if (!memcmp(dentry_blk->filename[bit_pos], - name->name, - name->len)) { - *res_page = dentry_page; - goto found; - } - } - if (max_len > *max_slots) { + de = &d->dentry[bit_pos]; + if (early_match_name(name->len, namehash, de) && + !memcmp(d->filename[bit_pos], name->name, name->len)) + goto found; + + if (max_slots && *max_slots >= 0 && max_len > *max_slots) { *max_slots = max_len; max_len = 0; } - /* - * For the most part, it should be a bug when name_len is zero. - * We stop here for figuring out where the bugs has occurred. - */ - f2fs_bug_on(F2FS_P_SB(dentry_page), !de->name_len); + /* remain bug on condition */ + if (unlikely(!de->name_len)) + d->max = -1; bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); } de = NULL; - kunmap(dentry_page); found: - if (max_len > *max_slots) + if (max_slots && max_len > *max_slots) *max_slots = max_len; return de; } @@ -149,7 +168,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, struct page *dentry_page; struct f2fs_dir_entry *de = NULL; bool room = false; - int max_slots = 0; + int max_slots; f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH); @@ -168,8 +187,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, continue; } - de = find_in_block(dentry_page, name, &max_slots, - namehash, res_page); + de = find_in_block(dentry_page, name, &max_slots, res_page); if (de) break; @@ -201,6 +219,9 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, unsigned int max_depth; unsigned int level; + if (f2fs_has_inline_dentry(dir)) + return find_in_inline_dir(dir, child, res_page); + if (npages == 0) return NULL; @@ -227,6 +248,9 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p) struct f2fs_dir_entry *de; struct f2fs_dentry_block *dentry_blk; + if (f2fs_has_inline_dentry(dir)) + return f2fs_parent_inline_dir(dir, p); + page = get_lock_data_page(dir, 0); if (IS_ERR(page)) return NULL; @@ -247,7 +271,7 @@ ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr) de = f2fs_find_entry(dir, qstr, &page); if (de) { res = le32_to_cpu(de->ino); - kunmap(page); + f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); } @@ -257,11 +281,13 @@ ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr) void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, struct page *page, struct inode *inode) { + enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA; lock_page(page); - f2fs_wait_on_page_writeback(page, DATA); + f2fs_wait_on_page_writeback(page, type); de->ino = cpu_to_le32(inode->i_ino); set_de_type(de, inode); - kunmap(page); + if (!f2fs_has_inline_dentry(dir)) + kunmap(page); set_page_dirty(page); dir->i_mtime = dir->i_ctime = CURRENT_TIME; mark_inode_dirty(dir); @@ -296,36 +322,48 @@ int update_dent_inode(struct inode *inode, const struct qstr *name) return 0; } -static int make_empty_dir(struct inode *inode, - struct inode *parent, struct page *page) +void do_make_empty_dir(struct inode *inode, struct inode *parent, + struct f2fs_dentry_ptr *d) { - struct page *dentry_page; - struct f2fs_dentry_block *dentry_blk; struct f2fs_dir_entry *de; - dentry_page = get_new_data_page(inode, page, 0, true); - if (IS_ERR(dentry_page)) - return PTR_ERR(dentry_page); - - - dentry_blk = kmap_atomic(dentry_page); - - de = &dentry_blk->dentry[0]; + de = &d->dentry[0]; de->name_len = cpu_to_le16(1); de->hash_code = 0; de->ino = cpu_to_le32(inode->i_ino); - memcpy(dentry_blk->filename[0], ".", 1); + memcpy(d->filename[0], ".", 1); set_de_type(de, inode); - de = &dentry_blk->dentry[1]; + de = &d->dentry[1]; de->hash_code = 0; de->name_len = cpu_to_le16(2); de->ino = cpu_to_le32(parent->i_ino); - memcpy(dentry_blk->filename[1], "..", 2); + memcpy(d->filename[1], "..", 2); set_de_type(de, inode); - test_and_set_bit_le(0, &dentry_blk->dentry_bitmap); - test_and_set_bit_le(1, &dentry_blk->dentry_bitmap); + test_and_set_bit_le(0, (void *)d->bitmap); + test_and_set_bit_le(1, (void *)d->bitmap); +} + +static int make_empty_dir(struct inode *inode, + struct inode *parent, struct page *page) +{ + struct page *dentry_page; + struct f2fs_dentry_block *dentry_blk; + struct f2fs_dentry_ptr d; + + if (f2fs_has_inline_dentry(inode)) + return make_empty_inline_dir(inode, parent, page); + + dentry_page = get_new_data_page(inode, page, 0, true); + if (IS_ERR(dentry_page)) + return PTR_ERR(dentry_page); + + dentry_blk = kmap_atomic(dentry_page); + + make_dentry_ptr(&d, (void *)dentry_blk, 1); + do_make_empty_dir(inode, parent, &d); + kunmap_atomic(dentry_blk); set_page_dirty(dentry_page); @@ -333,8 +371,8 @@ static int make_empty_dir(struct inode *inode, return 0; } -static struct page *init_inode_metadata(struct inode *inode, - struct inode *dir, const struct qstr *name) +struct page *init_inode_metadata(struct inode *inode, struct inode *dir, + const struct qstr *name, struct page *dpage) { struct page *page; int err; @@ -350,7 +388,7 @@ static struct page *init_inode_metadata(struct inode *inode, goto error; } - err = f2fs_init_acl(inode, dir, page); + err = f2fs_init_acl(inode, dir, page, dpage); if (err) goto put_error; @@ -395,7 +433,7 @@ error: return ERR_PTR(err); } -static void update_parent_metadata(struct inode *dir, struct inode *inode, +void update_parent_metadata(struct inode *dir, struct inode *inode, unsigned int current_depth) { if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { @@ -417,27 +455,23 @@ static void update_parent_metadata(struct inode *dir, struct inode *inode, clear_inode_flag(F2FS_I(inode), FI_INC_LINK); } -static int room_for_filename(struct f2fs_dentry_block *dentry_blk, int slots) +int room_for_filename(const void *bitmap, int slots, int max_slots) { int bit_start = 0; int zero_start, zero_end; next: - zero_start = find_next_zero_bit_le(&dentry_blk->dentry_bitmap, - NR_DENTRY_IN_BLOCK, - bit_start); - if (zero_start >= NR_DENTRY_IN_BLOCK) - return NR_DENTRY_IN_BLOCK; + zero_start = find_next_zero_bit_le(bitmap, max_slots, bit_start); + if (zero_start >= max_slots) + return max_slots; - zero_end = find_next_bit_le(&dentry_blk->dentry_bitmap, - NR_DENTRY_IN_BLOCK, - zero_start); + zero_end = find_next_bit_le(bitmap, max_slots, zero_start); if (zero_end - zero_start >= slots) return zero_start; bit_start = zero_end + 1; - if (zero_end + 1 >= NR_DENTRY_IN_BLOCK) - return NR_DENTRY_IN_BLOCK; + if (zero_end + 1 >= max_slots) + return max_slots; goto next; } @@ -463,6 +497,14 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, int err = 0; int i; + if (f2fs_has_inline_dentry(dir)) { + err = f2fs_add_inline_entry(dir, name, inode); + if (!err || err != -EAGAIN) + return err; + else + err = 0; + } + dentry_hash = f2fs_dentry_hash(name); level = 0; current_depth = F2FS_I(dir)->i_current_depth; @@ -491,7 +533,8 @@ start: return PTR_ERR(dentry_page); dentry_blk = kmap(dentry_page); - bit_pos = room_for_filename(dentry_blk, slots); + bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, + slots, NR_DENTRY_IN_BLOCK); if (bit_pos < NR_DENTRY_IN_BLOCK) goto add_dentry; @@ -506,7 +549,7 @@ add_dentry: f2fs_wait_on_page_writeback(dentry_page, DATA); down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, name); + page = init_inode_metadata(inode, dir, name, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; @@ -545,7 +588,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) int err = 0; down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, NULL); + page = init_inode_metadata(inode, dir, NULL, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; @@ -560,26 +603,57 @@ fail: return err; } +void f2fs_drop_nlink(struct inode *dir, struct inode *inode, struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + + down_write(&F2FS_I(inode)->i_sem); + + if (S_ISDIR(inode->i_mode)) { + drop_nlink(dir); + if (page) + update_inode(dir, page); + else + update_inode_page(dir); + } + inode->i_ctime = CURRENT_TIME; + + drop_nlink(inode); + if (S_ISDIR(inode->i_mode)) { + drop_nlink(inode); + i_size_write(inode, 0); + } + up_write(&F2FS_I(inode)->i_sem); + update_inode_page(inode); + + if (inode->i_nlink == 0) + add_orphan_inode(sbi, inode->i_ino); + else + release_orphan_inode(sbi); +} + /* * It only removes the dentry from the dentry page, corresponding name * entry in name page does not need to be touched during deletion. */ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, - struct inode *inode) + struct inode *dir, struct inode *inode) { struct f2fs_dentry_block *dentry_blk; unsigned int bit_pos; - struct inode *dir = page->mapping->host; int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); int i; + if (f2fs_has_inline_dentry(dir)) + return f2fs_delete_inline_entry(dentry, page, dir, inode); + lock_page(page); f2fs_wait_on_page_writeback(page, DATA); dentry_blk = page_address(page); bit_pos = dentry - dentry_blk->dentry; for (i = 0; i < slots; i++) - test_and_clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); + clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); /* Let's check and deallocate this dentry page */ bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, @@ -590,29 +664,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, dir->i_ctime = dir->i_mtime = CURRENT_TIME; - if (inode) { - struct f2fs_sb_info *sbi = F2FS_I_SB(dir); - - down_write(&F2FS_I(inode)->i_sem); - - if (S_ISDIR(inode->i_mode)) { - drop_nlink(dir); - update_inode_page(dir); - } - inode->i_ctime = CURRENT_TIME; - drop_nlink(inode); - if (S_ISDIR(inode->i_mode)) { - drop_nlink(inode); - i_size_write(inode, 0); - } - up_write(&F2FS_I(inode)->i_sem); - update_inode_page(inode); - - if (inode->i_nlink == 0) - add_orphan_inode(sbi, inode->i_ino); - else - release_orphan_inode(sbi); - } + if (inode) + f2fs_drop_nlink(dir, inode, NULL); if (bit_pos == NR_DENTRY_IN_BLOCK) { truncate_hole(dir, page->index, page->index + 1); @@ -628,9 +681,12 @@ bool f2fs_empty_dir(struct inode *dir) unsigned long bidx; struct page *dentry_page; unsigned int bit_pos; - struct f2fs_dentry_block *dentry_blk; + struct f2fs_dentry_block *dentry_blk; unsigned long nblock = dir_blocks(dir); + if (f2fs_has_inline_dentry(dir)) + return f2fs_empty_inline_dir(dir); + for (bidx = 0; bidx < nblock; bidx++) { dentry_page = get_lock_data_page(dir, bidx); if (IS_ERR(dentry_page)) { @@ -640,7 +696,6 @@ bool f2fs_empty_dir(struct inode *dir) return false; } - dentry_blk = kmap_atomic(dentry_page); if (bidx == 0) bit_pos = 2; @@ -659,19 +714,48 @@ bool f2fs_empty_dir(struct inode *dir) return true; } +bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, + unsigned int start_pos) +{ + unsigned char d_type = DT_UNKNOWN; + unsigned int bit_pos; + struct f2fs_dir_entry *de = NULL; + + bit_pos = ((unsigned long)ctx->pos % d->max); + + while (bit_pos < d->max) { + bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos); + if (bit_pos >= d->max) + break; + + de = &d->dentry[bit_pos]; + if (de->file_type < F2FS_FT_MAX) + d_type = f2fs_filetype_table[de->file_type]; + else + d_type = DT_UNKNOWN; + if (!dir_emit(ctx, d->filename[bit_pos], + le16_to_cpu(de->name_len), + le32_to_cpu(de->ino), d_type)) + return true; + + bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); + ctx->pos = start_pos + bit_pos; + } + return false; +} + static int f2fs_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); unsigned long npages = dir_blocks(inode); - unsigned int bit_pos = 0; struct f2fs_dentry_block *dentry_blk = NULL; - struct f2fs_dir_entry *de = NULL; struct page *dentry_page = NULL; struct file_ra_state *ra = &file->f_ra; unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK); - unsigned char d_type = DT_UNKNOWN; + struct f2fs_dentry_ptr d; - bit_pos = ((unsigned long)ctx->pos % NR_DENTRY_IN_BLOCK); + if (f2fs_has_inline_dentry(inode)) + return f2fs_read_inline_dir(file, ctx); /* readahead for multi pages of dir */ if (npages - n > 1 && !ra_has_index(ra, n)) @@ -684,28 +768,12 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) continue; dentry_blk = kmap(dentry_page); - while (bit_pos < NR_DENTRY_IN_BLOCK) { - bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, - NR_DENTRY_IN_BLOCK, - bit_pos); - if (bit_pos >= NR_DENTRY_IN_BLOCK) - break; - - de = &dentry_blk->dentry[bit_pos]; - if (de->file_type < F2FS_FT_MAX) - d_type = f2fs_filetype_table[de->file_type]; - else - d_type = DT_UNKNOWN; - if (!dir_emit(ctx, - dentry_blk->filename[bit_pos], - le16_to_cpu(de->name_len), - le32_to_cpu(de->ino), d_type)) - goto stop; - bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); - ctx->pos = n * NR_DENTRY_IN_BLOCK + bit_pos; - } - bit_pos = 0; + make_dentry_ptr(&d, (void *)dentry_blk, 1); + + if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK)) + goto stop; + ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK; kunmap(dentry_page); f2fs_put_page(dentry_page, 1); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8171e80b2ee9..ec58bb2373fc 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -46,8 +46,10 @@ #define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040 #define F2FS_MOUNT_INLINE_XATTR 0x00000080 #define F2FS_MOUNT_INLINE_DATA 0x00000100 -#define F2FS_MOUNT_FLUSH_MERGE 0x00000200 -#define F2FS_MOUNT_NOBARRIER 0x00000400 +#define F2FS_MOUNT_INLINE_DENTRY 0x00000200 +#define F2FS_MOUNT_FLUSH_MERGE 0x00000400 +#define F2FS_MOUNT_NOBARRIER 0x00000800 +#define F2FS_MOUNT_FASTBOOT 0x00001000 #define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) @@ -211,6 +213,32 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, /* * For INODE and NODE manager */ +/* for directory operations */ +struct f2fs_dentry_ptr { + const void *bitmap; + struct f2fs_dir_entry *dentry; + __u8 (*filename)[F2FS_SLOT_LEN]; + int max; +}; + +static inline void make_dentry_ptr(struct f2fs_dentry_ptr *d, + void *src, int type) +{ + if (type == 1) { + struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src; + d->max = NR_DENTRY_IN_BLOCK; + d->bitmap = &t->dentry_bitmap; + d->dentry = t->dentry; + d->filename = t->filename; + } else { + struct f2fs_inline_dentry *t = (struct f2fs_inline_dentry *)src; + d->max = NR_INLINE_DENTRY; + d->bitmap = &t->dentry_bitmap; + d->dentry = t->dentry; + d->filename = t->filename; + } +} + /* * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1 * as its node offset to distinguish from index node blocks. @@ -269,6 +297,7 @@ struct f2fs_inode_info { struct extent_info ext; /* in-memory extent cache entry */ struct dir_inode_entry *dirty_dir; /* the pointer of dirty dir */ + struct radix_tree_root inmem_root; /* radix tree for inmem pages */ struct list_head inmem_pages; /* inmemory pages managed by f2fs */ struct mutex inmem_lock; /* lock for inmemory pages */ }; @@ -303,7 +332,7 @@ struct f2fs_nm_info { /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ struct radix_tree_root nat_set_root;/* root of the nat set cache */ - rwlock_t nat_tree_lock; /* protect nat_tree_lock */ + struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ struct list_head nat_entries; /* cached nat entry list (clean) */ unsigned int nat_cnt; /* the # of cached nat entries */ unsigned int dirty_nat_cnt; /* total num of nat entries in set */ @@ -433,6 +462,7 @@ enum count_type { F2FS_DIRTY_DENTS, F2FS_DIRTY_NODES, F2FS_DIRTY_META, + F2FS_INMEM_PAGES, NR_COUNT_TYPE, }; @@ -470,6 +500,14 @@ struct f2fs_bio_info { struct rw_semaphore io_rwsem; /* blocking op for bio */ }; +/* for inner inode cache management */ +struct inode_management { + struct radix_tree_root ino_root; /* ino entry array */ + spinlock_t ino_lock; /* for ino entry lock */ + struct list_head ino_list; /* inode list head */ + unsigned long ino_num; /* number of entries */ +}; + struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ struct proc_dir_entry *s_proc; /* proc entry */ @@ -488,7 +526,6 @@ struct f2fs_sb_info { /* for bio operations */ struct f2fs_bio_info read_io; /* for read bios */ struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */ - struct completion *wait_io; /* for completion bios */ /* for checkpoint */ struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ @@ -500,13 +537,9 @@ struct f2fs_sb_info { bool por_doing; /* recovery is doing or not */ wait_queue_head_t cp_wait; - /* for inode management */ - struct radix_tree_root ino_root[MAX_INO_ENTRY]; /* ino entry array */ - spinlock_t ino_lock[MAX_INO_ENTRY]; /* for ino entry lock */ - struct list_head ino_list[MAX_INO_ENTRY]; /* inode list head */ + struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ /* for orphan inode, use 0'th array */ - unsigned int n_orphans; /* # of orphan inodes */ unsigned int max_orphans; /* max orphan inodes */ /* for directory inode management */ @@ -557,7 +590,8 @@ struct f2fs_sb_info { unsigned int segment_count[2]; /* # of allocated segments */ unsigned int block_count[2]; /* # of allocated blocks */ int total_hit_ext, read_hit_ext; /* extent cache hit ratio */ - int inline_inode; /* # of inline_data inodes */ + atomic_t inline_inode; /* # of inline_data inodes */ + atomic_t inline_dir; /* # of inline_dentry inodes */ int bg_gc; /* background gc calls */ unsigned int n_dirty_dirs; /* # of dir inodes */ #endif @@ -988,6 +1022,13 @@ retry: return entry; } +static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, + unsigned long index, void *item) +{ + while (radix_tree_insert(root, index, item)) + cond_resched(); +} + #define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino) static inline bool IS_INODE(struct page *page) @@ -1020,7 +1061,7 @@ static inline int f2fs_test_bit(unsigned int nr, char *addr) return mask & *addr; } -static inline int f2fs_set_bit(unsigned int nr, char *addr) +static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) { int mask; int ret; @@ -1032,7 +1073,7 @@ static inline int f2fs_set_bit(unsigned int nr, char *addr) return ret; } -static inline int f2fs_clear_bit(unsigned int nr, char *addr) +static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr) { int mask; int ret; @@ -1044,6 +1085,15 @@ static inline int f2fs_clear_bit(unsigned int nr, char *addr) return ret; } +static inline void f2fs_change_bit(unsigned int nr, char *addr) +{ + int mask; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + *addr ^= mask; +} + /* used for f2fs_inode_info->flags */ enum { FI_NEW_INODE, /* indicate newly allocated inode */ @@ -1057,11 +1107,13 @@ enum { FI_NO_EXTENT, /* not to use the extent cache */ FI_INLINE_XATTR, /* used for inline xattr */ FI_INLINE_DATA, /* used for inline data*/ + FI_INLINE_DENTRY, /* used for inline dentry */ FI_APPEND_WRITE, /* inode has appended data */ FI_UPDATE_WRITE, /* inode has in-place-update data */ FI_NEED_IPU, /* used for ipu per file */ FI_ATOMIC_FILE, /* indicate atomic file */ FI_VOLATILE_FILE, /* indicate volatile file */ + FI_DATA_EXIST, /* indicate data exists */ }; static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag) @@ -1087,15 +1139,6 @@ static inline void set_acl_inode(struct f2fs_inode_info *fi, umode_t mode) set_inode_flag(fi, FI_ACL_MODE); } -static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag) -{ - if (is_inode_flag_set(fi, FI_ACL_MODE)) { - clear_inode_flag(fi, FI_ACL_MODE); - return 1; - } - return 0; -} - static inline void get_inline_info(struct f2fs_inode_info *fi, struct f2fs_inode *ri) { @@ -1103,6 +1146,10 @@ static inline void get_inline_info(struct f2fs_inode_info *fi, set_inode_flag(fi, FI_INLINE_XATTR); if (ri->i_inline & F2FS_INLINE_DATA) set_inode_flag(fi, FI_INLINE_DATA); + if (ri->i_inline & F2FS_INLINE_DENTRY) + set_inode_flag(fi, FI_INLINE_DENTRY); + if (ri->i_inline & F2FS_DATA_EXIST) + set_inode_flag(fi, FI_DATA_EXIST); } static inline void set_raw_inline(struct f2fs_inode_info *fi, @@ -1114,6 +1161,10 @@ static inline void set_raw_inline(struct f2fs_inode_info *fi, ri->i_inline |= F2FS_INLINE_XATTR; if (is_inode_flag_set(fi, FI_INLINE_DATA)) ri->i_inline |= F2FS_INLINE_DATA; + if (is_inode_flag_set(fi, FI_INLINE_DENTRY)) + ri->i_inline |= F2FS_INLINE_DENTRY; + if (is_inode_flag_set(fi, FI_DATA_EXIST)) + ri->i_inline |= F2FS_DATA_EXIST; } static inline int f2fs_has_inline_xattr(struct inode *inode) @@ -1148,6 +1199,17 @@ static inline int f2fs_has_inline_data(struct inode *inode) return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA); } +static inline void f2fs_clear_inline_inode(struct inode *inode) +{ + clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + clear_inode_flag(F2FS_I(inode), FI_DATA_EXIST); +} + +static inline int f2fs_exist_data(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_DATA_EXIST); +} + static inline bool f2fs_is_atomic_file(struct inode *inode) { return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE); @@ -1164,6 +1226,23 @@ static inline void *inline_data_addr(struct page *page) return (void *)&(ri->i_addr[1]); } +static inline int f2fs_has_inline_dentry(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DENTRY); +} + +static inline void *inline_dentry_addr(struct page *page) +{ + struct f2fs_inode *ri = F2FS_INODE(page); + return (void *)&(ri->i_addr[1]); +} + +static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page) +{ + if (!f2fs_has_inline_dentry(dir)) + kunmap(page); +} + static inline int f2fs_readonly(struct super_block *sb) { return sb->s_flags & MS_RDONLY; @@ -1224,6 +1303,19 @@ struct dentry *f2fs_get_parent(struct dentry *child); /* * dir.c */ +extern unsigned char f2fs_filetype_table[F2FS_FT_MAX]; +void set_de_type(struct f2fs_dir_entry *, struct inode *); +struct f2fs_dir_entry *find_target_dentry(struct qstr *, int *, + struct f2fs_dentry_ptr *); +bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *, + unsigned int); +void do_make_empty_dir(struct inode *, struct inode *, + struct f2fs_dentry_ptr *); +struct page *init_inode_metadata(struct inode *, struct inode *, + const struct qstr *, struct page *); +void update_parent_metadata(struct inode *, struct inode *, unsigned int); +int room_for_filename(const void *, int, int); +void f2fs_drop_nlink(struct inode *, struct inode *, struct page *); struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *, struct page **); struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **); @@ -1232,7 +1324,8 @@ void f2fs_set_link(struct inode *, struct f2fs_dir_entry *, struct page *, struct inode *); int update_dent_inode(struct inode *, const struct qstr *); int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *); -void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *); +void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *, + struct inode *); int f2fs_do_tmpfile(struct inode *, struct inode *); int f2fs_make_empty(struct inode *, struct inode *); bool f2fs_empty_dir(struct inode *); @@ -1296,6 +1389,7 @@ void destroy_node_manager_caches(void); * segment.c */ void register_inmem_page(struct inode *, struct page *); +void invalidate_inmem_page(struct inode *, struct page *); void commit_inmem_pages(struct inode *, bool); void f2fs_balance_fs(struct f2fs_sb_info *); void f2fs_balance_fs_bg(struct f2fs_sb_info *); @@ -1337,8 +1431,8 @@ void destroy_segment_manager_caches(void); */ struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t); struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t); -struct page *get_meta_page_ra(struct f2fs_sb_info *, pgoff_t); int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int); +void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t); long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type); void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type); @@ -1405,7 +1499,7 @@ struct f2fs_stat_info { int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta; int nats, sits, fnids; int total_count, utilization; - int bg_gc, inline_inode; + int bg_gc, inline_inode, inline_dir, inmem_pages; unsigned int valid_count, valid_node_count, valid_inode_count; unsigned int bimodal, avg_vblocks; int util_free, util_valid, util_invalid; @@ -1438,14 +1532,23 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) #define stat_inc_inline_inode(inode) \ do { \ if (f2fs_has_inline_data(inode)) \ - ((F2FS_I_SB(inode))->inline_inode++); \ + (atomic_inc(&F2FS_I_SB(inode)->inline_inode)); \ } while (0) #define stat_dec_inline_inode(inode) \ do { \ if (f2fs_has_inline_data(inode)) \ - ((F2FS_I_SB(inode))->inline_inode--); \ + (atomic_dec(&F2FS_I_SB(inode)->inline_inode)); \ + } while (0) +#define stat_inc_inline_dir(inode) \ + do { \ + if (f2fs_has_inline_dentry(inode)) \ + (atomic_inc(&F2FS_I_SB(inode)->inline_dir)); \ + } while (0) +#define stat_dec_inline_dir(inode) \ + do { \ + if (f2fs_has_inline_dentry(inode)) \ + (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \ } while (0) - #define stat_inc_seg_type(sbi, curseg) \ ((sbi)->segment_count[(curseg)->alloc_type]++) #define stat_inc_block_count(sbi, curseg) \ @@ -1492,6 +1595,8 @@ void f2fs_destroy_root_stats(void); #define stat_inc_read_hit(sb) #define stat_inc_inline_inode(inode) #define stat_dec_inline_inode(inode) +#define stat_inc_inline_dir(inode) +#define stat_dec_inline_dir(inode) #define stat_inc_seg_type(sbi, curseg) #define stat_inc_block_count(sbi, curseg) #define stat_inc_seg_count(si, type) @@ -1519,9 +1624,20 @@ extern const struct inode_operations f2fs_special_inode_operations; * inline.c */ bool f2fs_may_inline(struct inode *); +void read_inline_data(struct page *, struct page *); int f2fs_read_inline_data(struct inode *, struct page *); -int f2fs_convert_inline_data(struct inode *, pgoff_t, struct page *); -int f2fs_write_inline_data(struct inode *, struct page *, unsigned int); -void truncate_inline_data(struct inode *, u64); +int f2fs_convert_inline_page(struct dnode_of_data *, struct page *); +int f2fs_convert_inline_inode(struct inode *); +int f2fs_write_inline_data(struct inode *, struct page *); +void truncate_inline_data(struct page *, u64); bool recover_inline_data(struct inode *, struct page *); +struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *, + struct page **); +struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **); +int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *); +int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *); +void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *, + struct inode *, struct inode *); +bool f2fs_empty_inline_dir(struct inode *); +int f2fs_read_inline_dir(struct file *, struct dir_context *); #endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 8e68bb64f835..3c27e0ecb3bc 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -41,18 +41,18 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, sb_start_pagefault(inode->i_sb); - /* force to convert with normal data indices */ - err = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, page); - if (err) - goto out; + f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); /* block allocation */ f2fs_lock_op(sbi); set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_reserve_block(&dn, page->index); - f2fs_unlock_op(sbi); - if (err) + if (err) { + f2fs_unlock_op(sbi); goto out; + } + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); file_update_time(vma->vm_file); lock_page(page); @@ -130,10 +130,45 @@ static inline bool need_do_checkpoint(struct inode *inode) need_cp = true; else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi))) need_cp = true; + else if (test_opt(sbi, FASTBOOT)) + need_cp = true; + else if (sbi->active_logs == 2) + need_cp = true; return need_cp; } +static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct page *i = find_get_page(NODE_MAPPING(sbi), ino); + bool ret = false; + /* But we need to avoid that there are some inode updates */ + if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) + ret = true; + f2fs_put_page(i, 0); + return ret; +} + +static void try_to_fix_pino(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + nid_t pino; + + down_write(&fi->i_sem); + fi->xattr_ver = 0; + if (file_wrong_pino(inode) && inode->i_nlink == 1 && + get_parent_ino(inode, &pino)) { + fi->i_pino = pino; + file_got_pino(inode); + up_write(&fi->i_sem); + + mark_inode_dirty_sync(inode); + f2fs_write_inode(inode, NULL); + } else { + up_write(&fi->i_sem); + } +} + int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; @@ -164,19 +199,21 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) return ret; } + /* if the inode is dirty, let's recover all the time */ + if (!datasync && is_inode_flag_set(fi, FI_DIRTY_INODE)) { + update_inode_page(inode); + goto go_write; + } + /* * if there is no written data, don't waste time to write recovery info. */ if (!is_inode_flag_set(fi, FI_APPEND_WRITE) && !exist_written_data(sbi, ino, APPEND_INO)) { - struct page *i = find_get_page(NODE_MAPPING(sbi), ino); - /* But we need to avoid that there are some inode updates */ - if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) { - f2fs_put_page(i, 0); + /* it may call write_inode just prior to fsync */ + if (need_inode_page_update(sbi, ino)) goto go_write; - } - f2fs_put_page(i, 0); if (is_inode_flag_set(fi, FI_UPDATE_WRITE) || exist_written_data(sbi, ino, UPDATE_INO)) @@ -196,49 +233,36 @@ go_write: up_read(&fi->i_sem); if (need_cp) { - nid_t pino; - /* all the dirty node pages should be flushed for POR */ ret = f2fs_sync_fs(inode->i_sb, 1); - down_write(&fi->i_sem); - F2FS_I(inode)->xattr_ver = 0; - if (file_wrong_pino(inode) && inode->i_nlink == 1 && - get_parent_ino(inode, &pino)) { - F2FS_I(inode)->i_pino = pino; - file_got_pino(inode); - up_write(&fi->i_sem); - mark_inode_dirty_sync(inode); - ret = f2fs_write_inode(inode, NULL); - if (ret) - goto out; - } else { - up_write(&fi->i_sem); - } - } else { + /* + * We've secured consistency through sync_fs. Following pino + * will be used only for fsynced inodes after checkpoint. + */ + try_to_fix_pino(inode); + goto out; + } sync_nodes: - sync_node_pages(sbi, ino, &wbc); - - if (need_inode_block_update(sbi, ino)) { - mark_inode_dirty_sync(inode); - ret = f2fs_write_inode(inode, NULL); - if (ret) - goto out; - goto sync_nodes; - } + sync_node_pages(sbi, ino, &wbc); - ret = wait_on_node_pages_writeback(sbi, ino); - if (ret) - goto out; + if (need_inode_block_update(sbi, ino)) { + mark_inode_dirty_sync(inode); + f2fs_write_inode(inode, NULL); + goto sync_nodes; + } + + ret = wait_on_node_pages_writeback(sbi, ino); + if (ret) + goto out; - /* once recovery info is written, don't need to tack this */ - remove_dirty_inode(sbi, ino, APPEND_INO); - clear_inode_flag(fi, FI_APPEND_WRITE); + /* once recovery info is written, don't need to tack this */ + remove_dirty_inode(sbi, ino, APPEND_INO); + clear_inode_flag(fi, FI_APPEND_WRITE); flush_out: - remove_dirty_inode(sbi, ino, UPDATE_INO); - clear_inode_flag(fi, FI_UPDATE_WRITE); - ret = f2fs_issue_flush(F2FS_I_SB(inode)); - } + remove_dirty_inode(sbi, ino, UPDATE_INO); + clear_inode_flag(fi, FI_UPDATE_WRITE); + ret = f2fs_issue_flush(sbi); out: trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); return ret; @@ -296,7 +320,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) goto fail; /* handle inline data case */ - if (f2fs_has_inline_data(inode)) { + if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) { if (whence == SEEK_HOLE) data_ofs = isize; goto found; @@ -374,6 +398,15 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) { + struct inode *inode = file_inode(file); + + /* we don't need to use inline_data strictly */ + if (f2fs_has_inline_data(inode)) { + int err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } + file_accessed(file); vma->vm_ops = &f2fs_file_vm_ops; return 0; @@ -415,20 +448,17 @@ void truncate_data_blocks(struct dnode_of_data *dn) truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); } -static void truncate_partial_data_page(struct inode *inode, u64 from) +static int truncate_partial_data_page(struct inode *inode, u64 from) { unsigned offset = from & (PAGE_CACHE_SIZE - 1); struct page *page; - if (f2fs_has_inline_data(inode)) - return truncate_inline_data(inode, from); - if (!offset) - return; + return 0; page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false); if (IS_ERR(page)) - return; + return 0; lock_page(page); if (unlikely(!PageUptodate(page) || @@ -438,9 +468,9 @@ static void truncate_partial_data_page(struct inode *inode, u64 from) f2fs_wait_on_page_writeback(page, DATA); zero_user(page, offset, PAGE_CACHE_SIZE - offset); set_page_dirty(page); - out: f2fs_put_page(page, 1); + return 0; } int truncate_blocks(struct inode *inode, u64 from, bool lock) @@ -450,27 +480,33 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) struct dnode_of_data dn; pgoff_t free_from; int count = 0, err = 0; + struct page *ipage; trace_f2fs_truncate_blocks_enter(inode, from); - if (f2fs_has_inline_data(inode)) - goto done; - free_from = (pgoff_t) - ((from + blocksize - 1) >> (sbi->log_blocksize)); + ((from + blocksize - 1) >> (sbi->log_blocksize)); if (lock) f2fs_lock_op(sbi); - set_new_dnode(&dn, inode, NULL, NULL, 0); + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto out; + } + + if (f2fs_has_inline_data(inode)) { + f2fs_put_page(ipage, 1); + goto out; + } + + set_new_dnode(&dn, inode, ipage, NULL, 0); err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE); if (err) { if (err == -ENOENT) goto free_next; - if (lock) - f2fs_unlock_op(sbi); - trace_f2fs_truncate_blocks_exit(inode, err); - return err; + goto out; } count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); @@ -486,11 +522,13 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) f2fs_put_dnode(&dn); free_next: err = truncate_inode_blocks(inode, free_from); +out: if (lock) f2fs_unlock_op(sbi); -done: + /* lastly zero out the first data page */ - truncate_partial_data_page(inode, from); + if (!err) + err = truncate_partial_data_page(inode, from); trace_f2fs_truncate_blocks_exit(inode, err); return err; @@ -504,6 +542,12 @@ void f2fs_truncate(struct inode *inode) trace_f2fs_truncate(inode); + /* we should check inline_data size */ + if (f2fs_has_inline_data(inode) && !f2fs_may_inline(inode)) { + if (f2fs_convert_inline_inode(inode)) + return; + } + if (!truncate_blocks(inode, i_size_read(inode), true)) { inode->i_mtime = inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); @@ -561,10 +605,6 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) return err; if (attr->ia_valid & ATTR_SIZE) { - err = f2fs_convert_inline_data(inode, attr->ia_size, NULL); - if (err) - return err; - if (attr->ia_size != i_size_read(inode)) { truncate_setsize(inode, attr->ia_size); f2fs_truncate(inode); @@ -665,9 +705,11 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) if (offset >= inode->i_size) return ret; - ret = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL); - if (ret) - return ret; + if (f2fs_has_inline_data(inode)) { + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + } pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; @@ -721,9 +763,11 @@ static int expand_inode_data(struct inode *inode, loff_t offset, if (ret) return ret; - ret = f2fs_convert_inline_data(inode, offset + len, NULL); - if (ret) - return ret; + if (f2fs_has_inline_data(inode)) { + ret = f2fs_convert_inline_inode(inode); + if (ret) + return ret; + } pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; @@ -874,7 +918,15 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); - return f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL); + return f2fs_convert_inline_inode(inode); +} + +static int f2fs_release_file(struct inode *inode, struct file *filp) +{ + /* some remained atomic pages should discarded */ + if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode)) + commit_inmem_pages(inode, true); + return 0; } static int f2fs_ioc_commit_atomic_write(struct file *filp) @@ -908,7 +960,8 @@ static int f2fs_ioc_start_volatile_write(struct file *filp) return -EACCES; set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); - return 0; + + return f2fs_convert_inline_inode(inode); } static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) @@ -985,6 +1038,7 @@ const struct file_operations f2fs_file_operations = { .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .open = generic_file_open, + .release = f2fs_release_file, .mmap = f2fs_file_mmap, .fsync = f2fs_sync_file, .fallocate = f2fs_fallocate, diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 2a8f4acdb86b..eec0933a4819 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -96,8 +96,6 @@ int start_gc_thread(struct f2fs_sb_info *sbi) dev_t dev = sbi->sb->s_bdev->bd_dev; int err = 0; - if (!test_opt(sbi, BG_GC)) - goto out; gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL); if (!gc_th) { err = -ENOMEM; @@ -340,34 +338,39 @@ static const struct victim_selection default_v_ops = { .get_victim = get_victim_by_default, }; -static struct inode *find_gc_inode(nid_t ino, struct list_head *ilist) +static struct inode *find_gc_inode(struct gc_inode_list *gc_list, nid_t ino) { struct inode_entry *ie; - list_for_each_entry(ie, ilist, list) - if (ie->inode->i_ino == ino) - return ie->inode; + ie = radix_tree_lookup(&gc_list->iroot, ino); + if (ie) + return ie->inode; return NULL; } -static void add_gc_inode(struct inode *inode, struct list_head *ilist) +static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode) { struct inode_entry *new_ie; - if (inode == find_gc_inode(inode->i_ino, ilist)) { + if (inode == find_gc_inode(gc_list, inode->i_ino)) { iput(inode); return; } - new_ie = f2fs_kmem_cache_alloc(winode_slab, GFP_NOFS); new_ie->inode = inode; - list_add_tail(&new_ie->list, ilist); +retry: + if (radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie)) { + cond_resched(); + goto retry; + } + list_add_tail(&new_ie->list, &gc_list->ilist); } -static void put_gc_inode(struct list_head *ilist) +static void put_gc_inode(struct gc_inode_list *gc_list) { struct inode_entry *ie, *next_ie; - list_for_each_entry_safe(ie, next_ie, ilist, list) { + list_for_each_entry_safe(ie, next_ie, &gc_list->ilist, list) { + radix_tree_delete(&gc_list->iroot, ie->inode->i_ino); iput(ie->inode); list_del(&ie->list); kmem_cache_free(winode_slab, ie); @@ -553,7 +556,7 @@ out: * the victim data block is ignored. */ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, - struct list_head *ilist, unsigned int segno, int gc_type) + struct gc_inode_list *gc_list, unsigned int segno, int gc_type) { struct super_block *sb = sbi->sb; struct f2fs_summary *entry; @@ -605,27 +608,27 @@ next_step: data_page = find_data_page(inode, start_bidx + ofs_in_node, false); - if (IS_ERR(data_page)) - goto next_iput; + if (IS_ERR(data_page)) { + iput(inode); + continue; + } f2fs_put_page(data_page, 0); - add_gc_inode(inode, ilist); - } else { - inode = find_gc_inode(dni.ino, ilist); - if (inode) { - start_bidx = start_bidx_of_node(nofs, - F2FS_I(inode)); - data_page = get_lock_data_page(inode, + add_gc_inode(gc_list, inode); + continue; + } + + /* phase 3 */ + inode = find_gc_inode(gc_list, dni.ino); + if (inode) { + start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + data_page = get_lock_data_page(inode, start_bidx + ofs_in_node); - if (IS_ERR(data_page)) - continue; - move_data_page(inode, data_page, gc_type); - stat_inc_data_blk_count(sbi, 1); - } + if (IS_ERR(data_page)) + continue; + move_data_page(inode, data_page, gc_type); + stat_inc_data_blk_count(sbi, 1); } - continue; -next_iput: - iput(inode); } if (++phase < 4) @@ -646,18 +649,20 @@ next_iput: } static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, - int gc_type, int type) + int gc_type) { struct sit_info *sit_i = SIT_I(sbi); int ret; + mutex_lock(&sit_i->sentry_lock); - ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type, type, LFS); + ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type, + NO_CHECK_TYPE, LFS); mutex_unlock(&sit_i->sentry_lock); return ret; } static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, - struct list_head *ilist, int gc_type) + struct gc_inode_list *gc_list, int gc_type) { struct page *sum_page; struct f2fs_summary_block *sum; @@ -675,7 +680,7 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, gc_node_segment(sbi, sum->entries, segno, gc_type); break; case SUM_TYPE_DATA: - gc_data_segment(sbi, sum->entries, ilist, segno, gc_type); + gc_data_segment(sbi, sum->entries, gc_list, segno, gc_type); break; } blk_finish_plug(&plug); @@ -688,16 +693,18 @@ static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, int f2fs_gc(struct f2fs_sb_info *sbi) { - struct list_head ilist; unsigned int segno, i; int gc_type = BG_GC; int nfree = 0; int ret = -1; - struct cp_control cpc = { - .reason = CP_SYNC, + struct cp_control cpc; + struct gc_inode_list gc_list = { + .ilist = LIST_HEAD_INIT(gc_list.ilist), + .iroot = RADIX_TREE_INIT(GFP_NOFS), }; - INIT_LIST_HEAD(&ilist); + cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC; + gc_more: if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) goto stop; @@ -709,7 +716,7 @@ gc_more: write_checkpoint(sbi, &cpc); } - if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE)) + if (!__get_victim(sbi, &segno, gc_type)) goto stop; ret = 0; @@ -719,7 +726,7 @@ gc_more: META_SSA); for (i = 0; i < sbi->segs_per_sec; i++) - do_garbage_collect(sbi, segno + i, &ilist, gc_type); + do_garbage_collect(sbi, segno + i, &gc_list, gc_type); if (gc_type == FG_GC) { sbi->cur_victim_sec = NULL_SEGNO; @@ -735,7 +742,7 @@ gc_more: stop: mutex_unlock(&sbi->gc_mutex); - put_gc_inode(&ilist); + put_gc_inode(&gc_list); return ret; } diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index 16f0b2b22999..6ff7ad38463e 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -40,6 +40,11 @@ struct inode_entry { struct inode *inode; }; +struct gc_inode_list { + struct list_head ilist; + struct radix_tree_root iroot; +}; + /* * inline functions */ diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 88036fd75797..f2d3c581e776 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -15,35 +15,44 @@ bool f2fs_may_inline(struct inode *inode) { - block_t nr_blocks; - loff_t i_size; - if (!test_opt(F2FS_I_SB(inode), INLINE_DATA)) return false; if (f2fs_is_atomic_file(inode)) return false; - nr_blocks = F2FS_I(inode)->i_xattr_nid ? 3 : 2; - if (inode->i_blocks > nr_blocks) + if (!S_ISREG(inode->i_mode)) return false; - i_size = i_size_read(inode); - if (i_size > MAX_INLINE_DATA) + if (i_size_read(inode) > MAX_INLINE_DATA) return false; return true; } -int f2fs_read_inline_data(struct inode *inode, struct page *page) +void read_inline_data(struct page *page, struct page *ipage) { - struct page *ipage; void *src_addr, *dst_addr; - if (page->index) { - zero_user_segment(page, 0, PAGE_CACHE_SIZE); - goto out; - } + if (PageUptodate(page)) + return; + + f2fs_bug_on(F2FS_P_SB(page), page->index); + + zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); + + /* Copy the whole inline data block */ + src_addr = inline_data_addr(ipage); + dst_addr = kmap_atomic(page); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + flush_dcache_page(page); + kunmap_atomic(dst_addr); + SetPageUptodate(page); +} + +int f2fs_read_inline_data(struct inode *inode, struct page *page) +{ + struct page *ipage; ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) { @@ -51,112 +60,116 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) return PTR_ERR(ipage); } - zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); + if (!f2fs_has_inline_data(inode)) { + f2fs_put_page(ipage, 1); + return -EAGAIN; + } - /* Copy the whole inline data block */ - src_addr = inline_data_addr(ipage); - dst_addr = kmap(page); - memcpy(dst_addr, src_addr, MAX_INLINE_DATA); - kunmap(page); - f2fs_put_page(ipage, 1); + if (page->index) + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + else + read_inline_data(page, ipage); -out: SetPageUptodate(page); + f2fs_put_page(ipage, 1); unlock_page(page); - return 0; } -static int __f2fs_convert_inline_data(struct inode *inode, struct page *page) +int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) { - int err = 0; - struct page *ipage; - struct dnode_of_data dn; void *src_addr, *dst_addr; block_t new_blk_addr; - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_io_info fio = { .type = DATA, .rw = WRITE_SYNC | REQ_PRIO, }; + int dirty, err; - f2fs_lock_op(sbi); - ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); - goto out; - } + f2fs_bug_on(F2FS_I_SB(dn->inode), page->index); - /* someone else converted inline_data already */ - if (!f2fs_has_inline_data(inode)) - goto out; + if (!f2fs_exist_data(dn->inode)) + goto clear_out; - /* - * i_addr[0] is not used for inline data, - * so reserving new block will not destroy inline data - */ - set_new_dnode(&dn, inode, ipage, NULL, 0); - err = f2fs_reserve_block(&dn, 0); + err = f2fs_reserve_block(dn, 0); if (err) - goto out; + return err; f2fs_wait_on_page_writeback(page, DATA); + + if (PageUptodate(page)) + goto no_update; + zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); /* Copy the whole inline data block */ - src_addr = inline_data_addr(ipage); - dst_addr = kmap(page); + src_addr = inline_data_addr(dn->inode_page); + dst_addr = kmap_atomic(page); memcpy(dst_addr, src_addr, MAX_INLINE_DATA); - kunmap(page); + flush_dcache_page(page); + kunmap_atomic(dst_addr); SetPageUptodate(page); +no_update: + /* clear dirty state */ + dirty = clear_page_dirty_for_io(page); /* write data page to try to make data consistent */ set_page_writeback(page); - write_data_page(page, &dn, &new_blk_addr, &fio); - update_extent_cache(new_blk_addr, &dn); + + write_data_page(page, dn, &new_blk_addr, &fio); + update_extent_cache(new_blk_addr, dn); f2fs_wait_on_page_writeback(page, DATA); + if (dirty) + inode_dec_dirty_pages(dn->inode); - /* clear inline data and flag after data writeback */ - zero_user_segment(ipage, INLINE_DATA_OFFSET, - INLINE_DATA_OFFSET + MAX_INLINE_DATA); - clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); - stat_dec_inline_inode(inode); + /* this converted inline_data should be recovered. */ + set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE); - sync_inode_page(&dn); - f2fs_put_dnode(&dn); -out: - f2fs_unlock_op(sbi); - return err; + /* clear inline data and flag after data writeback */ + truncate_inline_data(dn->inode_page, 0); +clear_out: + stat_dec_inline_inode(dn->inode); + f2fs_clear_inline_inode(dn->inode); + sync_inode_page(dn); + f2fs_put_dnode(dn); + return 0; } -int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size, - struct page *page) +int f2fs_convert_inline_inode(struct inode *inode) { - struct page *new_page = page; - int err; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct dnode_of_data dn; + struct page *ipage, *page; + int err = 0; - if (!f2fs_has_inline_data(inode)) - return 0; - else if (to_size <= MAX_INLINE_DATA) - return 0; + page = grab_cache_page(inode->i_mapping, 0); + if (!page) + return -ENOMEM; + + f2fs_lock_op(sbi); - if (!page || page->index != 0) { - new_page = grab_cache_page(inode->i_mapping, 0); - if (!new_page) - return -ENOMEM; + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto out; } - err = __f2fs_convert_inline_data(inode, new_page); - if (!page || page->index != 0) - f2fs_put_page(new_page, 1); + set_new_dnode(&dn, inode, ipage, ipage, 0); + + if (f2fs_has_inline_data(inode)) + err = f2fs_convert_inline_page(&dn, page); + + f2fs_put_dnode(&dn); +out: + f2fs_unlock_op(sbi); + + f2fs_put_page(page, 1); return err; } -int f2fs_write_inline_data(struct inode *inode, - struct page *page, unsigned size) +int f2fs_write_inline_data(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; - struct page *ipage; struct dnode_of_data dn; int err; @@ -164,47 +177,39 @@ int f2fs_write_inline_data(struct inode *inode, err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); if (err) return err; - ipage = dn.inode_page; - f2fs_wait_on_page_writeback(ipage, NODE); - zero_user_segment(ipage, INLINE_DATA_OFFSET, - INLINE_DATA_OFFSET + MAX_INLINE_DATA); - src_addr = kmap(page); - dst_addr = inline_data_addr(ipage); - memcpy(dst_addr, src_addr, size); - kunmap(page); - - /* Release the first data block if it is allocated */ if (!f2fs_has_inline_data(inode)) { - truncate_data_blocks_range(&dn, 1); - set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); - stat_inc_inline_inode(inode); + f2fs_put_dnode(&dn); + return -EAGAIN; } + f2fs_bug_on(F2FS_I_SB(inode), page->index); + + f2fs_wait_on_page_writeback(dn.inode_page, NODE); + src_addr = kmap_atomic(page); + dst_addr = inline_data_addr(dn.inode_page); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + kunmap_atomic(src_addr); + set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + sync_inode_page(&dn); f2fs_put_dnode(&dn); - return 0; } -void truncate_inline_data(struct inode *inode, u64 from) +void truncate_inline_data(struct page *ipage, u64 from) { - struct page *ipage; + void *addr; if (from >= MAX_INLINE_DATA) return; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); - if (IS_ERR(ipage)) - return; - f2fs_wait_on_page_writeback(ipage, NODE); - zero_user_segment(ipage, INLINE_DATA_OFFSET + from, - INLINE_DATA_OFFSET + MAX_INLINE_DATA); - set_page_dirty(ipage); - f2fs_put_page(ipage, 1); + addr = inline_data_addr(ipage); + memset(addr + from, 0, MAX_INLINE_DATA - from); } bool recover_inline_data(struct inode *inode, struct page *npage) @@ -236,6 +241,10 @@ process_inline: src_addr = inline_data_addr(npage); dst_addr = inline_data_addr(ipage); memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + + set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + update_inode(inode, ipage); f2fs_put_page(ipage, 1); return true; @@ -244,16 +253,279 @@ process_inline: if (f2fs_has_inline_data(inode)) { ipage = get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); - f2fs_wait_on_page_writeback(ipage, NODE); - zero_user_segment(ipage, INLINE_DATA_OFFSET, - INLINE_DATA_OFFSET + MAX_INLINE_DATA); - clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + truncate_inline_data(ipage, 0); + f2fs_clear_inline_inode(inode); update_inode(inode, ipage); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { truncate_blocks(inode, 0, false); - set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); goto process_inline; } return false; } + +struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, + struct qstr *name, struct page **res_page) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); + struct f2fs_inline_dentry *inline_dentry; + struct f2fs_dir_entry *de; + struct f2fs_dentry_ptr d; + struct page *ipage; + + ipage = get_node_page(sbi, dir->i_ino); + if (IS_ERR(ipage)) + return NULL; + + inline_dentry = inline_data_addr(ipage); + + make_dentry_ptr(&d, (void *)inline_dentry, 2); + de = find_target_dentry(name, NULL, &d); + + unlock_page(ipage); + if (de) + *res_page = ipage; + else + f2fs_put_page(ipage, 0); + + /* + * For the most part, it should be a bug when name_len is zero. + * We stop here for figuring out where the bugs has occurred. + */ + f2fs_bug_on(sbi, d.max < 0); + return de; +} + +struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *dir, + struct page **p) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct page *ipage; + struct f2fs_dir_entry *de; + struct f2fs_inline_dentry *dentry_blk; + + ipage = get_node_page(sbi, dir->i_ino); + if (IS_ERR(ipage)) + return NULL; + + dentry_blk = inline_data_addr(ipage); + de = &dentry_blk->dentry[1]; + *p = ipage; + unlock_page(ipage); + return de; +} + +int make_empty_inline_dir(struct inode *inode, struct inode *parent, + struct page *ipage) +{ + struct f2fs_inline_dentry *dentry_blk; + struct f2fs_dentry_ptr d; + + dentry_blk = inline_data_addr(ipage); + + make_dentry_ptr(&d, (void *)dentry_blk, 2); + do_make_empty_dir(inode, parent, &d); + + set_page_dirty(ipage); + + /* update i_size to MAX_INLINE_DATA */ + if (i_size_read(inode) < MAX_INLINE_DATA) { + i_size_write(inode, MAX_INLINE_DATA); + set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); + } + return 0; +} + +static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, + struct f2fs_inline_dentry *inline_dentry) +{ + struct page *page; + struct dnode_of_data dn; + struct f2fs_dentry_block *dentry_blk; + int err; + + page = grab_cache_page(dir->i_mapping, 0); + if (!page) + return -ENOMEM; + + set_new_dnode(&dn, dir, ipage, NULL, 0); + err = f2fs_reserve_block(&dn, 0); + if (err) + goto out; + + f2fs_wait_on_page_writeback(page, DATA); + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + + dentry_blk = kmap_atomic(page); + + /* copy data from inline dentry block to new dentry block */ + memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap, + INLINE_DENTRY_BITMAP_SIZE); + memcpy(dentry_blk->dentry, inline_dentry->dentry, + sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY); + memcpy(dentry_blk->filename, inline_dentry->filename, + NR_INLINE_DENTRY * F2FS_SLOT_LEN); + + kunmap_atomic(dentry_blk); + SetPageUptodate(page); + set_page_dirty(page); + + /* clear inline dir and flag after data writeback */ + truncate_inline_data(ipage, 0); + + stat_dec_inline_dir(dir); + clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY); + + if (i_size_read(dir) < PAGE_CACHE_SIZE) { + i_size_write(dir, PAGE_CACHE_SIZE); + set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); + } + + sync_inode_page(&dn); +out: + f2fs_put_page(page, 1); + return err; +} + +int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, + struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct page *ipage; + unsigned int bit_pos; + f2fs_hash_t name_hash; + struct f2fs_dir_entry *de; + size_t namelen = name->len; + struct f2fs_inline_dentry *dentry_blk = NULL; + int slots = GET_DENTRY_SLOTS(namelen); + struct page *page; + int err = 0; + int i; + + name_hash = f2fs_dentry_hash(name); + + ipage = get_node_page(sbi, dir->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + dentry_blk = inline_data_addr(ipage); + bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, + slots, NR_INLINE_DENTRY); + if (bit_pos >= NR_INLINE_DENTRY) { + err = f2fs_convert_inline_dir(dir, ipage, dentry_blk); + if (!err) + err = -EAGAIN; + goto out; + } + + down_write(&F2FS_I(inode)->i_sem); + page = init_inode_metadata(inode, dir, name, ipage); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto fail; + } + + f2fs_wait_on_page_writeback(ipage, NODE); + de = &dentry_blk->dentry[bit_pos]; + de->hash_code = name_hash; + de->name_len = cpu_to_le16(namelen); + memcpy(dentry_blk->filename[bit_pos], name->name, name->len); + de->ino = cpu_to_le32(inode->i_ino); + set_de_type(de, inode); + for (i = 0; i < slots; i++) + test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); + set_page_dirty(ipage); + + /* we don't need to mark_inode_dirty now */ + F2FS_I(inode)->i_pino = dir->i_ino; + update_inode(inode, page); + f2fs_put_page(page, 1); + + update_parent_metadata(dir, inode, 0); +fail: + up_write(&F2FS_I(inode)->i_sem); + + if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) { + update_inode(dir, ipage); + clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); + } +out: + f2fs_put_page(ipage, 1); + return err; +} + +void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, + struct inode *dir, struct inode *inode) +{ + struct f2fs_inline_dentry *inline_dentry; + int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); + unsigned int bit_pos; + int i; + + lock_page(page); + f2fs_wait_on_page_writeback(page, NODE); + + inline_dentry = inline_data_addr(page); + bit_pos = dentry - inline_dentry->dentry; + for (i = 0; i < slots; i++) + test_and_clear_bit_le(bit_pos + i, + &inline_dentry->dentry_bitmap); + + set_page_dirty(page); + + dir->i_ctime = dir->i_mtime = CURRENT_TIME; + + if (inode) + f2fs_drop_nlink(dir, inode, page); + + f2fs_put_page(page, 1); +} + +bool f2fs_empty_inline_dir(struct inode *dir) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct page *ipage; + unsigned int bit_pos = 2; + struct f2fs_inline_dentry *dentry_blk; + + ipage = get_node_page(sbi, dir->i_ino); + if (IS_ERR(ipage)) + return false; + + dentry_blk = inline_data_addr(ipage); + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_INLINE_DENTRY, + bit_pos); + + f2fs_put_page(ipage, 1); + + if (bit_pos < NR_INLINE_DENTRY) + return false; + + return true; +} + +int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx) +{ + struct inode *inode = file_inode(file); + struct f2fs_inline_dentry *inline_dentry = NULL; + struct page *ipage = NULL; + struct f2fs_dentry_ptr d; + + if (ctx->pos == NR_INLINE_DENTRY) + return 0; + + ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + inline_dentry = inline_data_addr(ipage); + + make_dentry_ptr(&d, (void *)inline_dentry, 2); + + if (!f2fs_fill_dentries(ctx, &d, 0)) + ctx->pos = NR_INLINE_DENTRY; + + f2fs_put_page(ipage, 1); + return 0; +} diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 0deead4505e7..196cc7843aaf 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -67,12 +67,38 @@ static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri) } } +static int __recover_inline_status(struct inode *inode, struct page *ipage) +{ + void *inline_data = inline_data_addr(ipage); + struct f2fs_inode *ri; + void *zbuf; + + zbuf = kzalloc(MAX_INLINE_DATA, GFP_NOFS); + if (!zbuf) + return -ENOMEM; + + if (!memcmp(zbuf, inline_data, MAX_INLINE_DATA)) { + kfree(zbuf); + return 0; + } + kfree(zbuf); + + f2fs_wait_on_page_writeback(ipage, NODE); + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + + ri = F2FS_INODE(ipage); + set_raw_inline(F2FS_I(inode), ri); + set_page_dirty(ipage); + return 0; +} + static int do_read_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct page *node_page; struct f2fs_inode *ri; + int err = 0; /* Check if ino is within scope */ if (check_nid_range(sbi, inode->i_ino)) { @@ -114,11 +140,19 @@ static int do_read_inode(struct inode *inode) get_extent_info(&fi->ext, ri->i_ext); get_inline_info(fi, ri); + /* check data exist */ + if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) + err = __recover_inline_status(inode, node_page); + /* get rdev by using inline_info */ __get_inode_rdev(inode, ri); f2fs_put_page(node_page, 1); - return 0; + + stat_inc_inline_inode(inode); + stat_inc_inline_dir(inode); + + return err; } struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) @@ -156,7 +190,7 @@ make_now: inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO); + mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &f2fs_symlink_inode_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; @@ -295,11 +329,12 @@ void f2fs_evict_inode(struct inode *inode) f2fs_lock_op(sbi); remove_inode_page(inode); - stat_dec_inline_inode(inode); f2fs_unlock_op(sbi); sb_end_intwrite(inode->i_sb); no_delete: + stat_dec_inline_dir(inode); + stat_dec_inline_inode(inode); invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino); if (xnid) invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); @@ -325,8 +360,9 @@ void handle_failed_inode(struct inode *inode) f2fs_truncate(inode); remove_inode_page(inode); - stat_dec_inline_inode(inode); + clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + clear_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); alloc_nid_failed(sbi, inode->i_ino); f2fs_unlock_op(sbi); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 0d2526e5aa11..547a2deeb1ac 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -54,6 +54,12 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) nid_free = true; goto out; } + + if (f2fs_may_inline(inode)) + set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + if (test_opt(sbi, INLINE_DENTRY) && S_ISDIR(inode->i_mode)) + set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); + trace_f2fs_new_inode(inode, 0); mark_inode_dirty(inode); return inode; @@ -129,8 +135,12 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, alloc_nid_done(sbi, ino); + stat_inc_inline_inode(inode); d_instantiate(dentry, inode); unlock_new_inode(inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); return 0; out: handle_failed_inode(inode); @@ -157,6 +167,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, f2fs_unlock_op(sbi); d_instantiate(dentry, inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); return 0; out: clear_inode_flag(F2FS_I(inode), FI_INC_LINK); @@ -187,14 +200,12 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, de = f2fs_find_entry(dir, &dentry->d_name, &page); if (de) { nid_t ino = le32_to_cpu(de->ino); - kunmap(page); + f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); inode = f2fs_iget(dir->i_sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); - - stat_inc_inline_inode(inode); } return d_splice_alias(inode, dentry); @@ -219,15 +230,18 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) err = acquire_orphan_inode(sbi); if (err) { f2fs_unlock_op(sbi); - kunmap(page); + f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); goto fail; } - f2fs_delete_entry(de, page, inode); + f2fs_delete_entry(de, page, dir, inode); f2fs_unlock_op(sbi); /* In order to evict this inode, we set it dirty */ mark_inode_dirty(inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); fail: trace_f2fs_unlink_exit(inode, err); return err; @@ -261,6 +275,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, d_instantiate(dentry, inode); unlock_new_inode(inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); return err; out: handle_failed_inode(inode); @@ -291,11 +308,14 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out_fail; f2fs_unlock_op(sbi); + stat_inc_inline_dir(inode); alloc_nid_done(sbi, inode->i_ino); d_instantiate(dentry, inode); unlock_new_inode(inode); + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); return 0; out_fail: @@ -338,8 +358,12 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, f2fs_unlock_op(sbi); alloc_nid_done(sbi, inode->i_ino); + d_instantiate(dentry, inode); unlock_new_inode(inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); return 0; out: handle_failed_inode(inode); @@ -435,7 +459,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, old_inode->i_ctime = CURRENT_TIME; mark_inode_dirty(old_inode); - f2fs_delete_entry(old_entry, old_page, NULL); + f2fs_delete_entry(old_entry, old_page, old_dir, NULL); if (old_dir_entry) { if (old_dir != new_dir) { @@ -443,7 +467,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, old_dir_page, new_dir); update_inode_page(old_inode); } else { - kunmap(old_dir_page); + f2fs_dentry_kunmap(old_inode, old_dir_page); f2fs_put_page(old_dir_page, 0); } drop_nlink(old_dir); @@ -452,19 +476,22 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, } f2fs_unlock_op(sbi); + + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) + f2fs_sync_fs(sbi->sb, 1); return 0; put_out_dir: f2fs_unlock_op(sbi); - kunmap(new_page); + f2fs_dentry_kunmap(new_dir, new_page); f2fs_put_page(new_page, 0); out_dir: if (old_dir_entry) { - kunmap(old_dir_page); + f2fs_dentry_kunmap(old_inode, old_dir_page); f2fs_put_page(old_dir_page, 0); } out_old: - kunmap(old_page); + f2fs_dentry_kunmap(old_dir, old_page); f2fs_put_page(old_page, 0); out: return err; @@ -588,6 +615,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, update_inode_page(new_dir); f2fs_unlock_op(sbi); + + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) + f2fs_sync_fs(sbi->sb, 1); return 0; out_undo: /* Still we may fail to recover name info of f2fs_inode here */ @@ -596,19 +626,19 @@ out_unlock: f2fs_unlock_op(sbi); out_new_dir: if (new_dir_entry) { - kunmap(new_dir_page); + f2fs_dentry_kunmap(new_inode, new_dir_page); f2fs_put_page(new_dir_page, 0); } out_old_dir: if (old_dir_entry) { - kunmap(old_dir_page); + f2fs_dentry_kunmap(old_inode, old_dir_page); f2fs_put_page(old_dir_page, 0); } out_new: - kunmap(new_page); + f2fs_dentry_kunmap(new_dir, new_page); f2fs_put_page(new_page, 0); out_old: - kunmap(old_page); + f2fs_dentry_kunmap(old_dir, old_page); f2fs_put_page(old_page, 0); out: return err; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 44b8afef43d9..f83326ca32ef 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -31,22 +31,38 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct sysinfo val; + unsigned long avail_ram; unsigned long mem_size = 0; bool res = false; si_meminfo(&val); - /* give 25%, 25%, 50% memory for each components respectively */ + + /* only uses low memory */ + avail_ram = val.totalram - val.totalhigh; + + /* give 25%, 25%, 50%, 50% memory for each components respectively */ if (type == FREE_NIDS) { - mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> 12; - res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2); + mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> + PAGE_CACHE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == NAT_ENTRIES) { - mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12; - res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2); + mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> + PAGE_CACHE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == DIRTY_DENTS) { if (sbi->sb->s_bdi->dirty_exceeded) return false; mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); - res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1); + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); + } else if (type == INO_ENTRIES) { + int i; + + if (sbi->sb->s_bdi->dirty_exceeded) + return false; + for (i = 0; i <= UPDATE_INO; i++) + mem_size += (sbi->im[i].ino_num * + sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } return res; } @@ -131,7 +147,7 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, if (get_nat_flag(ne, IS_DIRTY)) return; -retry: + head = radix_tree_lookup(&nm_i->nat_set_root, set); if (!head) { head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC); @@ -140,11 +156,7 @@ retry: INIT_LIST_HEAD(&head->set_list); head->set = set; head->entry_cnt = 0; - - if (radix_tree_insert(&nm_i->nat_set_root, set, head)) { - cond_resched(); - goto retry; - } + f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head); } list_move_tail(&ne->list, &head->entry_list); nm_i->dirty_nat_cnt++; @@ -155,7 +167,7 @@ retry: static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, struct nat_entry *ne) { - nid_t set = ne->ni.nid / NAT_ENTRY_PER_BLOCK; + nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid); struct nat_entry_set *head; head = radix_tree_lookup(&nm_i->nat_set_root, set); @@ -180,11 +192,11 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool is_cp = true; - read_lock(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e && !get_nat_flag(e, IS_CHECKPOINTED)) is_cp = false; - read_unlock(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return is_cp; } @@ -194,11 +206,11 @@ bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino) struct nat_entry *e; bool fsynced = false; - read_lock(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ino); if (e && get_nat_flag(e, HAS_FSYNCED_INODE)) fsynced = true; - read_unlock(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return fsynced; } @@ -208,13 +220,13 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) struct nat_entry *e; bool need_update = true; - read_lock(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ino); if (e && get_nat_flag(e, HAS_LAST_FSYNC) && (get_nat_flag(e, IS_CHECKPOINTED) || get_nat_flag(e, HAS_FSYNCED_INODE))) need_update = false; - read_unlock(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need_update; } @@ -222,13 +234,8 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) { struct nat_entry *new; - new = kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC); - if (!new) - return NULL; - if (radix_tree_insert(&nm_i->nat_root, nid, new)) { - kmem_cache_free(nat_entry_slab, new); - return NULL; - } + new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC); + f2fs_radix_tree_insert(&nm_i->nat_root, nid, new); memset(new, 0, sizeof(struct nat_entry)); nat_set_nid(new, nid); nat_reset_flag(new); @@ -241,18 +248,14 @@ static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, struct f2fs_nat_entry *ne) { struct nat_entry *e; -retry: - write_lock(&nm_i->nat_tree_lock); + + down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (!e) { e = grab_nat_entry(nm_i, nid); - if (!e) { - write_unlock(&nm_i->nat_tree_lock); - goto retry; - } node_info_from_raw_nat(&e->ni, ne); } - write_unlock(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, @@ -260,15 +263,11 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; -retry: - write_lock(&nm_i->nat_tree_lock); + + down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ni->nid); if (!e) { e = grab_nat_entry(nm_i, ni->nid); - if (!e) { - write_unlock(&nm_i->nat_tree_lock); - goto retry; - } e->ni = *ni; f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR); } else if (new_blkaddr == NEW_ADDR) { @@ -310,7 +309,7 @@ retry: set_nat_flag(e, HAS_FSYNCED_INODE, true); set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); } - write_unlock(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) @@ -320,7 +319,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) if (available_free_memory(sbi, NAT_ENTRIES)) return 0; - write_lock(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); while (nr_shrink && !list_empty(&nm_i->nat_entries)) { struct nat_entry *ne; ne = list_first_entry(&nm_i->nat_entries, @@ -328,7 +327,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) __del_from_nat_cache(nm_i, ne); nr_shrink--; } - write_unlock(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); return nr_shrink; } @@ -351,14 +350,14 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) ni->nid = nid; /* Check nat cache */ - read_lock(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); } - read_unlock(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); if (e) return; @@ -1298,16 +1297,22 @@ static int f2fs_write_node_page(struct page *page, return 0; } - if (wbc->for_reclaim) - goto redirty_out; - - down_read(&sbi->node_write); + if (wbc->for_reclaim) { + if (!down_read_trylock(&sbi->node_write)) + goto redirty_out; + } else { + down_read(&sbi->node_write); + } set_page_writeback(page); write_node_page(sbi, page, &fio, nid, ni.blk_addr, &new_addr); set_node_addr(sbi, &ni, new_addr, is_fsync_dnode(page)); dec_page_count(sbi, F2FS_DIRTY_NODES); up_read(&sbi->node_write); unlock_page(page); + + if (wbc->for_reclaim) + f2fs_submit_merged_bio(sbi, NODE, WRITE); + return 0; redirty_out: @@ -1410,13 +1415,13 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) if (build) { /* do not add allocated nids */ - read_lock(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); ne = __lookup_nat_cache(nm_i, nid); if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || nat_get_blkaddr(ne) != NULL_ADDR)) allocated = true; - read_unlock(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); if (allocated) return 0; } @@ -1425,15 +1430,22 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) i->nid = nid; i->state = NID_NEW; + if (radix_tree_preload(GFP_NOFS)) { + kmem_cache_free(free_nid_slab, i); + return 0; + } + spin_lock(&nm_i->free_nid_list_lock); if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) { spin_unlock(&nm_i->free_nid_list_lock); + radix_tree_preload_end(); kmem_cache_free(free_nid_slab, i); return 0; } list_add_tail(&i->list, &nm_i->free_nid_list); nm_i->fcnt++; spin_unlock(&nm_i->free_nid_list_lock); + radix_tree_preload_end(); return 1; } @@ -1804,21 +1816,15 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi) nid_t nid = le32_to_cpu(nid_in_journal(sum, i)); raw_ne = nat_in_journal(sum, i); -retry: - write_lock(&nm_i->nat_tree_lock); - ne = __lookup_nat_cache(nm_i, nid); - if (ne) - goto found; - ne = grab_nat_entry(nm_i, nid); + down_write(&nm_i->nat_tree_lock); + ne = __lookup_nat_cache(nm_i, nid); if (!ne) { - write_unlock(&nm_i->nat_tree_lock); - goto retry; + ne = grab_nat_entry(nm_i, nid); + node_info_from_raw_nat(&ne->ni, &raw_ne); } - node_info_from_raw_nat(&ne->ni, &raw_ne); -found: __set_nat_cache_dirty(nm_i, ne); - write_unlock(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } update_nats_in_cursum(sum, -i); mutex_unlock(&curseg->curseg_mutex); @@ -1889,10 +1895,10 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, } raw_nat_from_node_info(raw_ne, &ne->ni); - write_lock(&NM_I(sbi)->nat_tree_lock); + down_write(&NM_I(sbi)->nat_tree_lock); nat_reset_flag(ne); __clear_nat_cache_dirty(NM_I(sbi), ne); - write_unlock(&NM_I(sbi)->nat_tree_lock); + up_write(&NM_I(sbi)->nat_tree_lock); if (nat_get_blkaddr(ne) == NULL_ADDR) add_free_nid(sbi, nid, false); @@ -1903,10 +1909,10 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, else f2fs_put_page(page, 1); - if (!set->entry_cnt) { - radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); - kmem_cache_free(nat_entry_set_slab, set); - } + f2fs_bug_on(sbi, set->entry_cnt); + + radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); + kmem_cache_free(nat_entry_set_slab, set); } /* @@ -1923,6 +1929,8 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) nid_t set_idx = 0; LIST_HEAD(sets); + if (!nm_i->dirty_nat_cnt) + return; /* * if there are no enough space in journal to store dirty nat * entries, remove all entries from journal and merge them @@ -1931,9 +1939,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL)) remove_nats_in_journal(sbi); - if (!nm_i->dirty_nat_cnt) - return; - while ((found = __gang_lookup_nat_set(nm_i, set_idx, NATVEC_SIZE, setvec))) { unsigned idx; @@ -1973,13 +1978,13 @@ static int init_node_manager(struct f2fs_sb_info *sbi) INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC); INIT_LIST_HEAD(&nm_i->free_nid_list); - INIT_RADIX_TREE(&nm_i->nat_root, GFP_ATOMIC); - INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_ATOMIC); + INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO); + INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO); INIT_LIST_HEAD(&nm_i->nat_entries); mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->free_nid_list_lock); - rwlock_init(&nm_i->nat_tree_lock); + init_rwsem(&nm_i->nat_tree_lock); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); @@ -2035,7 +2040,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) spin_unlock(&nm_i->free_nid_list_lock); /* destroy nat cache */ - write_lock(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_cache(nm_i, nid, NATVEC_SIZE, natvec))) { unsigned idx; @@ -2044,7 +2049,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) __del_from_nat_cache(nm_i, natvec[idx]); } f2fs_bug_on(sbi, nm_i->nat_cnt); - write_unlock(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); kfree(nm_i->nat_bitmap); sbi->nm_info = NULL; @@ -2061,17 +2066,17 @@ int __init create_node_manager_caches(void) free_nid_slab = f2fs_kmem_cache_create("free_nid", sizeof(struct free_nid)); if (!free_nid_slab) - goto destory_nat_entry; + goto destroy_nat_entry; nat_entry_set_slab = f2fs_kmem_cache_create("nat_entry_set", sizeof(struct nat_entry_set)); if (!nat_entry_set_slab) - goto destory_free_nid; + goto destroy_free_nid; return 0; -destory_free_nid: +destroy_free_nid: kmem_cache_destroy(free_nid_slab); -destory_nat_entry: +destroy_nat_entry: kmem_cache_destroy(nat_entry_slab); fail: return -ENOMEM; diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 8d5e6e0dd840..d10b6448a671 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -106,7 +106,8 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne, enum mem_type { FREE_NIDS, /* indicates the free nid list */ NAT_ENTRIES, /* indicates the cached nat entry */ - DIRTY_DENTS /* indicates dirty dentry pages */ + DIRTY_DENTS, /* indicates dirty dentry pages */ + INO_ENTRIES, /* indicates inode entries */ }; struct nat_entry_set { @@ -192,10 +193,7 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid) { unsigned int block_off = NAT_BLOCK_OFFSET(start_nid); - if (f2fs_test_bit(block_off, nm_i->nat_bitmap)) - f2fs_clear_bit(block_off, nm_i->nat_bitmap); - else - f2fs_set_bit(block_off, nm_i->nat_bitmap); + f2fs_change_bit(block_off, nm_i->nat_bitmap); } static inline void fill_node_footer(struct page *page, nid_t nid, diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index ebd013225788..9160a37e1c7a 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -111,7 +111,7 @@ retry: iput(einode); goto out_unmap_put; } - f2fs_delete_entry(de, page, einode); + f2fs_delete_entry(de, page, dir, einode); iput(einode); goto retry; } @@ -129,7 +129,7 @@ retry: goto out; out_unmap_put: - kunmap(page); + f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); out_err: iput(dir); @@ -170,13 +170,15 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + ra_meta_pages(sbi, blkaddr, 1, META_POR); + while (1) { struct fsync_inode_entry *entry; if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi)) return 0; - page = get_meta_page_ra(sbi, blkaddr); + page = get_meta_page(sbi, blkaddr); if (cp_ver != cpver_of_node(page)) break; @@ -227,6 +229,8 @@ next: /* check next segment */ blkaddr = next_blkaddr_of_node(page); f2fs_put_page(page, 1); + + ra_meta_pages_cond(sbi, blkaddr); } f2fs_put_page(page, 1); return err; @@ -436,7 +440,9 @@ static int recover_data(struct f2fs_sb_info *sbi, if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi)) break; - page = get_meta_page_ra(sbi, blkaddr); + ra_meta_pages_cond(sbi, blkaddr); + + page = get_meta_page(sbi, blkaddr); if (cp_ver != cpver_of_node(page)) { f2fs_put_page(page, 1); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 923cb76fdc46..42607a679923 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -178,17 +178,47 @@ void register_inmem_page(struct inode *inode, struct page *page) { struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *new; + int err; + + SetPagePrivate(page); new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); /* add atomic page indices to the list */ new->page = page; INIT_LIST_HEAD(&new->list); - +retry: /* increase reference count with clean state */ mutex_lock(&fi->inmem_lock); + err = radix_tree_insert(&fi->inmem_root, page->index, new); + if (err == -EEXIST) { + mutex_unlock(&fi->inmem_lock); + kmem_cache_free(inmem_entry_slab, new); + return; + } else if (err) { + mutex_unlock(&fi->inmem_lock); + goto retry; + } get_page(page); list_add_tail(&new->list, &fi->inmem_pages); + inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); + mutex_unlock(&fi->inmem_lock); +} + +void invalidate_inmem_page(struct inode *inode, struct page *page) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct inmem_pages *cur; + + mutex_lock(&fi->inmem_lock); + cur = radix_tree_lookup(&fi->inmem_root, page->index); + if (cur) { + radix_tree_delete(&fi->inmem_root, cur->page->index); + f2fs_put_page(cur->page, 0); + list_del(&cur->list); + kmem_cache_free(inmem_entry_slab, cur); + dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); + } mutex_unlock(&fi->inmem_lock); } @@ -203,7 +233,16 @@ void commit_inmem_pages(struct inode *inode, bool abort) .rw = WRITE_SYNC, }; - f2fs_balance_fs(sbi); + /* + * The abort is true only when f2fs_evict_inode is called. + * Basically, the f2fs_evict_inode doesn't produce any data writes, so + * that we don't need to call f2fs_balance_fs. + * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this + * inode becomes free by iget_locked in f2fs_iget. + */ + if (!abort) + f2fs_balance_fs(sbi); + f2fs_lock_op(sbi); mutex_lock(&fi->inmem_lock); @@ -216,9 +255,11 @@ void commit_inmem_pages(struct inode *inode, bool abort) do_write_data_page(cur->page, &fio); submit_bio = true; } + radix_tree_delete(&fi->inmem_root, cur->page->index); f2fs_put_page(cur->page, 1); list_del(&cur->list); kmem_cache_free(inmem_entry_slab, cur); + dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); } if (submit_bio) f2fs_submit_merged_bio(sbi, DATA, WRITE); @@ -248,7 +289,8 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) { /* check the # of cached NAT entries and prefree segments */ if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) || - excess_prefree_segs(sbi)) + excess_prefree_segs(sbi) || + available_free_memory(sbi, INO_ENTRIES)) f2fs_sync_fs(sbi->sb, true); } @@ -441,10 +483,33 @@ void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr) } } -static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) +static void __add_discard_entry(struct f2fs_sb_info *sbi, + struct cp_control *cpc, unsigned int start, unsigned int end) { struct list_head *head = &SM_I(sbi)->discard_list; - struct discard_entry *new; + struct discard_entry *new, *last; + + if (!list_empty(head)) { + last = list_last_entry(head, struct discard_entry, list); + if (START_BLOCK(sbi, cpc->trim_start) + start == + last->blkaddr + last->len) { + last->len += end - start; + goto done; + } + } + + new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS); + INIT_LIST_HEAD(&new->list); + new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start; + new->len = end - start; + list_add_tail(&new->list, head); +done: + SM_I(sbi)->nr_discards += end - start; + cpc->trimmed += end - start; +} + +static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) +{ int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long); int max_blocks = sbi->blocks_per_seg; struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start); @@ -473,13 +538,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) } mutex_unlock(&dirty_i->seglist_lock); - new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS); - INIT_LIST_HEAD(&new->list); - new->blkaddr = START_BLOCK(sbi, cpc->trim_start); - new->len = sbi->blocks_per_seg; - list_add_tail(&new->list, head); - SM_I(sbi)->nr_discards += sbi->blocks_per_seg; - cpc->trimmed += sbi->blocks_per_seg; + __add_discard_entry(sbi, cpc, 0, sbi->blocks_per_seg); return; } @@ -489,7 +548,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */ for (i = 0; i < entries; i++) - dmap[i] = (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i]; + dmap[i] = ~(cur_map[i] | ckpt_map[i]); while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) { start = __find_rev_next_bit(dmap, max_blocks, end + 1); @@ -501,14 +560,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (end - start < cpc->trim_minlen) continue; - new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS); - INIT_LIST_HEAD(&new->list); - new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start; - new->len = end - start; - cpc->trimmed += end - start; - - list_add_tail(&new->list, head); - SM_I(sbi)->nr_discards += end - start; + __add_discard_entry(sbi, cpc, start, end); } } @@ -620,10 +672,10 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) /* Update valid block bitmap */ if (del > 0) { - if (f2fs_set_bit(offset, se->cur_valid_map)) + if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) f2fs_bug_on(sbi, 1); } else { - if (!f2fs_clear_bit(offset, se->cur_valid_map)) + if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) f2fs_bug_on(sbi, 1); } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) @@ -1004,6 +1056,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) range->len < sbi->blocksize) return -EINVAL; + cpc.trimmed = 0; if (end <= MAIN_BLKADDR(sbi)) goto out; @@ -1015,10 +1068,11 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) cpc.trim_start = start_segno; cpc.trim_end = end_segno; cpc.trim_minlen = range->minlen >> sbi->log_blocksize; - cpc.trimmed = 0; /* do checkpoint to issue discard commands safely */ + mutex_lock(&sbi->gc_mutex); write_checkpoint(sbi, &cpc); + mutex_unlock(&sbi->gc_mutex); out: range->len = cpc.trimmed << sbi->log_blocksize; return 0; @@ -1050,8 +1104,8 @@ static int __get_segment_type_4(struct page *page, enum page_type p_type) else return CURSEG_COLD_DATA; } else { - if (IS_DNODE(page) && !is_cold_node(page)) - return CURSEG_HOT_NODE; + if (IS_DNODE(page) && is_cold_node(page)) + return CURSEG_WARM_NODE; else return CURSEG_COLD_NODE; } @@ -1524,17 +1578,7 @@ int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type, static struct page *get_current_sit_page(struct f2fs_sb_info *sbi, unsigned int segno) { - struct sit_info *sit_i = SIT_I(sbi); - unsigned int offset = SIT_BLOCK_OFFSET(segno); - block_t blk_addr = sit_i->sit_base_addr + offset; - - check_seg_range(sbi, segno); - - /* calculate sit block address */ - if (f2fs_test_bit(offset, sit_i->sit_bitmap)) - blk_addr += sit_i->sit_blocks; - - return get_meta_page(sbi, blk_addr); + return get_meta_page(sbi, current_sit_addr(sbi, segno)); } static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, @@ -1687,7 +1731,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) * #2, flush sit entries to sit page. */ list_for_each_entry_safe(ses, tmp, head, set_list) { - struct page *page; + struct page *page = NULL; struct f2fs_sit_block *raw_sit = NULL; unsigned int start_segno = ses->start_segno; unsigned int end = min(start_segno + SIT_ENTRY_PER_BLOCK, @@ -2200,7 +2244,7 @@ int __init create_segment_manager_caches(void) goto fail; sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set", - sizeof(struct nat_entry_set)); + sizeof(struct sit_entry_set)); if (!sit_entry_set_slab) goto destory_discard_entry; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 2495bec1c621..7f327c0ba4e3 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -657,10 +657,7 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start) { unsigned int block_off = SIT_BLOCK_OFFSET(start); - if (f2fs_test_bit(block_off, sit_i->sit_bitmap)) - f2fs_clear_bit(block_off, sit_i->sit_bitmap); - else - f2fs_set_bit(block_off, sit_i->sit_bitmap); + f2fs_change_bit(block_off, sit_i->sit_bitmap); } static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi) @@ -714,6 +711,9 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi) */ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type) { + if (sbi->sb->s_bdi->dirty_exceeded) + return 0; + if (type == DATA) return sbi->blocks_per_seg; else if (type == NODE) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 41d6f700f4ee..f71421d70475 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -51,8 +51,10 @@ enum { Opt_disable_ext_identify, Opt_inline_xattr, Opt_inline_data, + Opt_inline_dentry, Opt_flush_merge, Opt_nobarrier, + Opt_fastboot, Opt_err, }; @@ -69,8 +71,10 @@ static match_table_t f2fs_tokens = { {Opt_disable_ext_identify, "disable_ext_identify"}, {Opt_inline_xattr, "inline_xattr"}, {Opt_inline_data, "inline_data"}, + {Opt_inline_dentry, "inline_dentry"}, {Opt_flush_merge, "flush_merge"}, {Opt_nobarrier, "nobarrier"}, + {Opt_fastboot, "fastboot"}, {Opt_err, NULL}, }; @@ -340,12 +344,18 @@ static int parse_options(struct super_block *sb, char *options) case Opt_inline_data: set_opt(sbi, INLINE_DATA); break; + case Opt_inline_dentry: + set_opt(sbi, INLINE_DENTRY); + break; case Opt_flush_merge: set_opt(sbi, FLUSH_MERGE); break; case Opt_nobarrier: set_opt(sbi, NOBARRIER); break; + case Opt_fastboot: + set_opt(sbi, FASTBOOT); + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -373,6 +383,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) fi->i_advise = 0; rwlock_init(&fi->ext.ext_lock); init_rwsem(&fi->i_sem); + INIT_RADIX_TREE(&fi->inmem_root, GFP_NOFS); INIT_LIST_HEAD(&fi->inmem_pages); mutex_init(&fi->inmem_lock); @@ -473,9 +484,9 @@ int f2fs_sync_fs(struct super_block *sb, int sync) trace_f2fs_sync_fs(sb, sync); if (sync) { - struct cp_control cpc = { - .reason = CP_SYNC, - }; + struct cp_control cpc; + + cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC; mutex_lock(&sbi->gc_mutex); write_checkpoint(sbi, &cpc); mutex_unlock(&sbi->gc_mutex); @@ -562,10 +573,14 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",disable_ext_identify"); if (test_opt(sbi, INLINE_DATA)) seq_puts(seq, ",inline_data"); + if (test_opt(sbi, INLINE_DENTRY)) + seq_puts(seq, ",inline_dentry"); if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE)) seq_puts(seq, ",flush_merge"); if (test_opt(sbi, NOBARRIER)) seq_puts(seq, ",nobarrier"); + if (test_opt(sbi, FASTBOOT)) + seq_puts(seq, ",fastboot"); seq_printf(seq, ",active_logs=%u", sbi->active_logs); return 0; @@ -654,7 +669,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) f2fs_sync_fs(sb, 1); need_restart_gc = true; } - } else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) { + } else if (!sbi->gc_thread) { err = start_gc_thread(sbi); if (err) goto restore_opts; @@ -667,7 +682,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) */ if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) { destroy_flush_cmd_control(sbi); - } else if (test_opt(sbi, FLUSH_MERGE) && !SM_I(sbi)->cmd_control_info) { + } else if (!SM_I(sbi)->cmd_control_info) { err = create_flush_cmd_control(sbi); if (err) goto restore_gc; @@ -922,7 +937,7 @@ retry: static int f2fs_fill_super(struct super_block *sb, void *data, int silent) { struct f2fs_sb_info *sbi; - struct f2fs_super_block *raw_super; + struct f2fs_super_block *raw_super = NULL; struct buffer_head *raw_super_buf; struct inode *root; long err = -EINVAL; @@ -1123,7 +1138,7 @@ try_onemore: * If filesystem is not mounted as read-only then * do start the gc_thread. */ - if (!f2fs_readonly(sb)) { + if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) { /* After POR, we can run background GC thread.*/ err = start_gc_thread(sbi); if (err) diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index deca8728117b..5072bf9ae0ef 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -83,7 +83,7 @@ static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name, } if (strcmp(name, "") == 0) return -EINVAL; - return f2fs_getxattr(dentry->d_inode, type, name, buffer, size); + return f2fs_getxattr(dentry->d_inode, type, name, buffer, size, NULL); } static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name, @@ -398,7 +398,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, } int f2fs_getxattr(struct inode *inode, int index, const char *name, - void *buffer, size_t buffer_size) + void *buffer, size_t buffer_size, struct page *ipage) { struct f2fs_xattr_entry *entry; void *base_addr; @@ -412,7 +412,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, if (len > F2FS_NAME_LEN) return -ERANGE; - base_addr = read_all_xattrs(inode, NULL); + base_addr = read_all_xattrs(inode, ipage); if (!base_addr) return -ENOMEM; diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 34ab7dbcf5e3..969d792ca362 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -115,7 +115,8 @@ extern const struct xattr_handler *f2fs_xattr_handlers[]; extern int f2fs_setxattr(struct inode *, int, const char *, const void *, size_t, struct page *, int); -extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t); +extern int f2fs_getxattr(struct inode *, int, const char *, void *, + size_t, struct page *); extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t); #else @@ -126,7 +127,8 @@ static inline int f2fs_setxattr(struct inode *inode, int index, return -EOPNOTSUPP; } static inline int f2fs_getxattr(struct inode *inode, int index, - const char *name, void *buffer, size_t buffer_size) + const char *name, void *buffer, + size_t buffer_size, struct page *dpage) { return -EOPNOTSUPP; } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 3963ede84eb0..c5d6bb939d19 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -702,10 +702,11 @@ static int fat_readdir(struct file *file, struct dir_context *ctx) } #define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type) \ -static int func(void *__buf, const char *name, int name_len, \ +static int func(struct dir_context *ctx, const char *name, int name_len, \ loff_t offset, u64 ino, unsigned int d_type) \ { \ - struct fat_ioctl_filldir_callback *buf = __buf; \ + struct fat_ioctl_filldir_callback *buf = \ + container_of(ctx, struct fat_ioctl_filldir_callback, ctx); \ struct dirent_type __user *d1 = buf->dirent; \ struct dirent_type __user *d2 = d1 + 1; \ \ diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index dbab798f5caf..df562cc87763 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -372,7 +372,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, if (inode && get_node_id(inode) == FUSE_ROOT_ID) goto out_iput; - newent = d_materialise_unique(entry, inode); + newent = d_splice_alias(inode, entry); err = PTR_ERR(newent); if (IS_ERR(newent)) goto out_err; @@ -1320,7 +1320,7 @@ static int fuse_direntplus_link(struct file *file, if (!inode) goto out; - alias = d_materialise_unique(dentry, inode); + alias = d_splice_alias(inode, dentry); err = PTR_ERR(alias); if (IS_ERR(alias)) goto out; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index caa8d95b24e8..bf50259012ab 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1988,7 +1988,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { pgoff_t index = pos >> PAGE_CACHE_SHIFT; - struct fuse_conn *fc = get_fuse_conn(file->f_dentry->d_inode); + struct fuse_conn *fc = get_fuse_conn(file_inode(file)); struct page *page; loff_t fsize; int err = -ENOMEM; diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 5d4261ff5d23..c5a34f09e228 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -365,23 +365,17 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip) ret = gfs2_dir_read_data(ip, hc, hsize); if (ret < 0) { - if (is_vmalloc_addr(hc)) - vfree(hc); - else - kfree(hc); + kvfree(hc); return ERR_PTR(ret); } spin_lock(&inode->i_lock); - if (ip->i_hash_cache) { - if (is_vmalloc_addr(hc)) - vfree(hc); - else - kfree(hc); - } else { + if (likely(!ip->i_hash_cache)) { ip->i_hash_cache = hc; + hc = NULL; } spin_unlock(&inode->i_lock); + kvfree(hc); return ip->i_hash_cache; } @@ -396,10 +390,7 @@ void gfs2_dir_hash_inval(struct gfs2_inode *ip) { __be64 *hc = ip->i_hash_cache; ip->i_hash_cache = NULL; - if (is_vmalloc_addr(hc)) - vfree(hc); - else - kfree(hc); + kvfree(hc); } static inline int gfs2_dirent_sentinel(const struct gfs2_dirent *dent) @@ -1168,10 +1159,7 @@ fail: gfs2_dinode_out(dip, dibh->b_data); brelse(dibh); out_kfree: - if (is_vmalloc_addr(hc2)) - vfree(hc2); - else - kfree(hc2); + kvfree(hc2); return error; } @@ -1302,14 +1290,6 @@ static void *gfs2_alloc_sort_buffer(unsigned size) return ptr; } -static void gfs2_free_sort_buffer(void *ptr) -{ - if (is_vmalloc_addr(ptr)) - vfree(ptr); - else - kfree(ptr); -} - static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, int *copied, unsigned *depth, u64 leaf_no) @@ -1393,7 +1373,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, out_free: for(i = 0; i < leaf; i++) brelse(larr[i]); - gfs2_free_sort_buffer(larr); + kvfree(larr); out: return error; } @@ -2004,10 +1984,7 @@ out_rlist: gfs2_rlist_free(&rlist); gfs2_quota_unhold(dip); out: - if (is_vmalloc_addr(ht)) - vfree(ht); - else - kfree(ht); + kvfree(ht); return error; } diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c index 8b9b3775e2e7..c41d255b6a7b 100644 --- a/fs/gfs2/export.c +++ b/fs/gfs2/export.c @@ -69,10 +69,12 @@ struct get_name_filldir { char *name; }; -static int get_name_filldir(void *opaque, const char *name, int length, - loff_t offset, u64 inum, unsigned int type) +static int get_name_filldir(struct dir_context *ctx, const char *name, + int length, loff_t offset, u64 inum, + unsigned int type) { - struct get_name_filldir *gnfd = opaque; + struct get_name_filldir *gnfd = + container_of(ctx, struct get_name_filldir, ctx); if (inum != gnfd->inum.no_addr) return 0; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 80dd44dca028..6e600abf694a 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -337,7 +337,8 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size) size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift; int hint = min_t(size_t, INT_MAX, blks); - atomic_set(&ip->i_res->rs_sizehint, hint); + if (hint > atomic_read(&ip->i_res->rs_sizehint)) + atomic_set(&ip->i_res->rs_sizehint, hint); } /** @@ -728,7 +729,6 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len, struct gfs2_inode *ip = GFS2_I(inode); struct buffer_head *dibh; int error; - loff_t size = len; unsigned int nr_blks; sector_t lblock = offset >> inode->i_blkbits; @@ -762,11 +762,6 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len, goto out; } } - if (offset + size > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE)) - i_size_write(inode, offset + size); - - mark_inode_dirty(inode); - out: brelse(dibh); return error; @@ -796,8 +791,7 @@ static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len, } } -static long gfs2_fallocate(struct file *file, int mode, loff_t offset, - loff_t len) +static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -811,14 +805,9 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t bsize_mask = ~((loff_t)sdp->sd_sb.sb_bsize - 1); loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift; loff_t max_chunk_size = UINT_MAX & bsize_mask; - struct gfs2_holder gh; next = (next + 1) << sdp->sd_sb.sb_bsize_shift; - /* We only support the FALLOC_FL_KEEP_SIZE mode */ - if (mode & ~FALLOC_FL_KEEP_SIZE) - return -EOPNOTSUPP; - offset &= bsize_mask; len = next - offset; @@ -829,17 +818,6 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, if (bytes == 0) bytes = sdp->sd_sb.sb_bsize; - error = gfs2_rs_alloc(ip); - if (error) - return error; - - mutex_lock(&inode->i_mutex); - - gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - error = gfs2_glock_nq(&gh); - if (unlikely(error)) - goto out_uninit; - gfs2_size_hint(file, offset, len); while (len > 0) { @@ -852,8 +830,7 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, } error = gfs2_quota_lock_check(ip); if (error) - goto out_unlock; - + return error; retry: gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks); @@ -895,20 +872,64 @@ retry: gfs2_quota_unlock(ip); } - if (error == 0) - error = generic_write_sync(file, pos, count); - goto out_unlock; + if (!(mode & FALLOC_FL_KEEP_SIZE) && (pos + count) > inode->i_size) { + i_size_write(inode, pos + count); + /* Marks the inode as dirty */ + file_update_time(file); + } + + return generic_write_sync(file, pos, count); out_trans_fail: gfs2_inplace_release(ip); out_qunlock: gfs2_quota_unlock(ip); + return error; +} + +static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(file); + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; + int ret; + + if (mode & ~FALLOC_FL_KEEP_SIZE) + return -EOPNOTSUPP; + + mutex_lock(&inode->i_mutex); + + gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + ret = gfs2_glock_nq(&gh); + if (ret) + goto out_uninit; + + if (!(mode & FALLOC_FL_KEEP_SIZE) && + (offset + len) > inode->i_size) { + ret = inode_newsize_ok(inode, offset + len); + if (ret) + goto out_unlock; + } + + ret = get_write_access(inode); + if (ret) + goto out_unlock; + + ret = gfs2_rs_alloc(ip); + if (ret) + goto out_putw; + + ret = __gfs2_fallocate(file, mode, offset, len); + if (ret) + gfs2_rs_deltree(ip->i_res); +out_putw: + put_write_access(inode); out_unlock: gfs2_glock_dq(&gh); out_uninit: gfs2_holder_uninit(&gh); mutex_unlock(&inode->i_mutex); - return error; + return ret; } #ifdef CONFIG_GFS2_FS_LOCKING_DLM diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 8f0c19d1d943..a23524aa3eac 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -836,8 +836,7 @@ void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder * gh->gh_flags = flags; gh->gh_iflags = 0; gh->gh_ip = _RET_IP_; - if (gh->gh_owner_pid) - put_pid(gh->gh_owner_pid); + put_pid(gh->gh_owner_pid); gh->gh_owner_pid = get_pid(task_pid(current)); } diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 1cc0bba6313f..fe91951c3361 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -28,6 +28,8 @@ #include "trans.h" #include "dir.h" +struct workqueue_struct *gfs2_freeze_wq; + static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh) { fs_err(gl->gl_sbd, "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page state 0x%lx\n", @@ -94,11 +96,8 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) * on the stack */ tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64)); tr.tr_ip = _RET_IP_; - sb_start_intwrite(sdp->sd_vfs); - if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0) { - sb_end_intwrite(sdp->sd_vfs); + if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0) return; - } WARN_ON_ONCE(current->journal_info); current->journal_info = &tr; @@ -469,20 +468,19 @@ static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl) static void freeze_go_sync(struct gfs2_glock *gl) { + int error = 0; struct gfs2_sbd *sdp = gl->gl_sbd; - DEFINE_WAIT(wait); if (gl->gl_state == LM_ST_SHARED && test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { - atomic_set(&sdp->sd_log_freeze, 1); - wake_up(&sdp->sd_logd_waitq); - do { - prepare_to_wait(&sdp->sd_log_frozen_wait, &wait, - TASK_UNINTERRUPTIBLE); - if (atomic_read(&sdp->sd_log_freeze)) - io_schedule(); - } while(atomic_read(&sdp->sd_log_freeze)); - finish_wait(&sdp->sd_log_frozen_wait, &wait); + atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); + error = freeze_super(sdp->sd_vfs); + if (error) { + printk(KERN_INFO "GFS2: couldn't freeze filesystem: %d\n", error); + gfs2_assert_withdraw(sdp, 0); + } + queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work); + gfs2_log_flush(sdp, NULL, FREEZE_FLUSH); } } diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h index 7455d2629bcb..8ed1857c1a8d 100644 --- a/fs/gfs2/glops.h +++ b/fs/gfs2/glops.h @@ -12,6 +12,8 @@ #include "incore.h" +extern struct workqueue_struct *gfs2_freeze_wq; + extern const struct gfs2_glock_operations gfs2_meta_glops; extern const struct gfs2_glock_operations gfs2_inode_glops; extern const struct gfs2_glock_operations gfs2_rgrp_glops; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 39e7e9959b74..7a2dbbc0d634 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -97,6 +97,7 @@ struct gfs2_rgrpd { #define GFS2_RDF_CHECK 0x10000000 /* check for unlinked inodes */ #define GFS2_RDF_UPTODATE 0x20000000 /* rg is up to date */ #define GFS2_RDF_ERROR 0x40000000 /* error in rg */ +#define GFS2_RDF_PREFERRED 0x80000000 /* This rgrp is preferred */ #define GFS2_RDF_MASK 0xf0000000 /* mask for internal flags */ spinlock_t rd_rsspin; /* protects reservation related vars */ struct rb_root rd_rstree; /* multi-block reservation tree */ @@ -587,6 +588,12 @@ enum { SDF_SKIP_DLM_UNLOCK = 8, }; +enum gfs2_freeze_state { + SFS_UNFROZEN = 0, + SFS_STARTING_FREEZE = 1, + SFS_FROZEN = 2, +}; + #define GFS2_FSNAME_LEN 256 struct gfs2_inum_host { @@ -684,6 +691,7 @@ struct gfs2_sbd { struct gfs2_holder sd_live_gh; struct gfs2_glock *sd_rename_gl; struct gfs2_glock *sd_freeze_gl; + struct work_struct sd_freeze_work; wait_queue_head_t sd_glock_wait; atomic_t sd_glock_disposal; struct completion sd_locking_init; @@ -788,6 +796,9 @@ struct gfs2_sbd { wait_queue_head_t sd_log_flush_wait; int sd_log_error; + atomic_t sd_reserving_log; + wait_queue_head_t sd_reserving_log_wait; + unsigned int sd_log_flush_head; u64 sd_log_flush_wrapped; @@ -797,12 +808,8 @@ struct gfs2_sbd { /* For quiescing the filesystem */ struct gfs2_holder sd_freeze_gh; - struct gfs2_holder sd_freeze_root_gh; - struct gfs2_holder sd_thaw_gh; - atomic_t sd_log_freeze; - atomic_t sd_frozen_root; - wait_queue_head_t sd_frozen_root_wait; - wait_queue_head_t sd_log_frozen_wait; + atomic_t sd_freeze_state; + struct mutex sd_freeze_mutex; char sd_fsname[GFS2_FSNAME_LEN]; char sd_table_name[GFS2_FSNAME_LEN]; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index c4ed823d150e..9054002ebe70 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -596,7 +596,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, struct gfs2_inode *dip = GFS2_I(dir), *ip; struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct gfs2_glock *io_gl; - struct dentry *d; int error, free_vfs_inode = 0; u32 aflags = 0; unsigned blocks = 1; @@ -624,22 +623,18 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, inode = gfs2_dir_search(dir, &dentry->d_name, !S_ISREG(mode) || excl); error = PTR_ERR(inode); if (!IS_ERR(inode)) { - d = d_splice_alias(inode, dentry); - error = PTR_ERR(d); - if (IS_ERR(d)) { - inode = ERR_CAST(d); + if (S_ISDIR(inode->i_mode)) { + iput(inode); + inode = ERR_PTR(-EISDIR); goto fail_gunlock; } + d_instantiate(dentry, inode); error = 0; if (file) { - if (S_ISREG(inode->i_mode)) { - WARN_ON(d != NULL); + if (S_ISREG(inode->i_mode)) error = finish_open(file, dentry, gfs2_open_common, opened); - } else { - error = finish_no_open(file, d); - } - } else { - dput(d); + else + error = finish_no_open(file, NULL); } gfs2_glock_dq_uninit(ghs); return error; @@ -1045,11 +1040,7 @@ static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, if (error) return error; - error = gfs2_dir_check(&dip->i_inode, name, ip); - if (error) - return error; - - return 0; + return gfs2_dir_check(&dip->i_inode, name, ip); } /** @@ -1254,11 +1245,8 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, if (d != NULL) dentry = d; if (dentry->d_inode) { - if (!(*opened & FILE_OPENED)) { - if (d == NULL) - dget(dentry); - return finish_no_open(file, dentry); - } + if (!(*opened & FILE_OPENED)) + return finish_no_open(file, d); dput(d); return 0; } @@ -1622,26 +1610,18 @@ int gfs2_permission(struct inode *inode, int mask) { struct gfs2_inode *ip; struct gfs2_holder i_gh; - struct gfs2_sbd *sdp = GFS2_SB(inode); int error; int unlock = 0; - int frozen_root = 0; ip = GFS2_I(inode); if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) { - if (unlikely(gfs2_glock_is_held_excl(sdp->sd_freeze_gl) && - inode == sdp->sd_root_dir->d_inode && - atomic_inc_not_zero(&sdp->sd_frozen_root))) - frozen_root = 1; - else { - if (mask & MAY_NOT_BLOCK) - return -ECHILD; - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); - if (error) - return error; - unlock = 1; - } + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); + if (error) + return error; + unlock = 1; } if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode)) @@ -1650,8 +1630,6 @@ int gfs2_permission(struct inode *inode, int mask) error = generic_permission(inode, mask); if (unlock) gfs2_glock_dq_uninit(&i_gh); - else if (frozen_root && atomic_dec_and_test(&sdp->sd_frozen_root)) - wake_up(&sdp->sd_frozen_root_wait); return error; } @@ -1824,29 +1802,19 @@ static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry, struct inode *inode = dentry->d_inode; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; - struct gfs2_sbd *sdp = GFS2_SB(inode); int error; int unlock = 0; - int frozen_root = 0; if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) { - if (unlikely(gfs2_glock_is_held_excl(sdp->sd_freeze_gl) && - inode == sdp->sd_root_dir->d_inode && - atomic_inc_not_zero(&sdp->sd_frozen_root))) - frozen_root = 1; - else { - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh); - if (error) - return error; - unlock = 1; - } + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh); + if (error) + return error; + unlock = 1; } generic_fillattr(inode, stat); if (unlock) gfs2_glock_dq_uninit(&gh); - else if (frozen_root && atomic_dec_and_test(&sdp->sd_frozen_root)) - wake_up(&sdp->sd_frozen_root_wait); return 0; } diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 3966fadbcebd..536e7a6252cd 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -339,6 +339,7 @@ void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks) int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks) { + int ret = 0; unsigned reserved_blks = 7 * (4096 / sdp->sd_vfs->s_blocksize); unsigned wanted = blks + reserved_blks; DEFINE_WAIT(wait); @@ -362,9 +363,13 @@ retry: } while(free_blocks <= wanted); finish_wait(&sdp->sd_log_waitq, &wait); } + atomic_inc(&sdp->sd_reserving_log); if (atomic_cmpxchg(&sdp->sd_log_blks_free, free_blocks, - free_blocks - blks) != free_blocks) + free_blocks - blks) != free_blocks) { + if (atomic_dec_and_test(&sdp->sd_reserving_log)) + wake_up(&sdp->sd_reserving_log_wait); goto retry; + } trace_gfs2_log_blocks(sdp, -blks); /* @@ -377,9 +382,11 @@ retry: down_read(&sdp->sd_log_flush_lock); if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) { gfs2_log_release(sdp, blks); - return -EROFS; + ret = -EROFS; } - return 0; + if (atomic_dec_and_test(&sdp->sd_reserving_log)) + wake_up(&sdp->sd_reserving_log_wait); + return ret; } /** @@ -652,9 +659,12 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags) u32 hash; int rw = WRITE_FLUSH_FUA | REQ_META; struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); lh = page_address(page); clear_page(lh); + gfs2_assert_withdraw(sdp, (state != SFS_FROZEN)); + tail = current_tail(sdp); lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC); @@ -695,6 +705,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, enum gfs2_flush_type type) { struct gfs2_trans *tr; + enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); down_write(&sdp->sd_log_flush_lock); @@ -713,8 +724,12 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, INIT_LIST_HEAD(&tr->tr_ail1_list); INIT_LIST_HEAD(&tr->tr_ail2_list); tr->tr_first = sdp->sd_log_flush_head; + if (unlikely (state == SFS_FROZEN)) + gfs2_assert_withdraw(sdp, !tr->tr_num_buf_new && !tr->tr_num_databuf_new); } + if (unlikely(state == SFS_FROZEN)) + gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke); @@ -745,8 +760,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, spin_unlock(&sdp->sd_ail_lock); gfs2_log_unlock(sdp); - if (atomic_read(&sdp->sd_log_freeze)) - type = FREEZE_FLUSH; if (type != NORMAL_FLUSH) { if (!sdp->sd_log_idle) { for (;;) { @@ -763,21 +776,8 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, } if (type == SHUTDOWN_FLUSH || type == FREEZE_FLUSH) gfs2_log_shutdown(sdp); - if (type == FREEZE_FLUSH) { - int error; - - atomic_set(&sdp->sd_log_freeze, 0); - wake_up(&sdp->sd_log_frozen_wait); - error = gfs2_glock_nq_init(sdp->sd_freeze_gl, - LM_ST_SHARED, 0, - &sdp->sd_thaw_gh); - if (error) { - printk(KERN_INFO "GFS2: couln't get freeze lock : %d\n", error); - gfs2_assert_withdraw(sdp, 0); - } - else - gfs2_glock_dq_uninit(&sdp->sd_thaw_gh); - } + if (type == FREEZE_FLUSH) + atomic_set(&sdp->sd_freeze_state, SFS_FROZEN); } trace_gfs2_log_flush(sdp, 0); @@ -888,7 +888,7 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp) { - return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1) || atomic_read(&sdp->sd_log_freeze)); + return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1)); } static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp) diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 82b6ac829656..241a399bf83d 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -30,6 +30,7 @@ #include "quota.h" #include "recovery.h" #include "dir.h" +#include "glops.h" struct workqueue_struct *gfs2_control_wq; @@ -161,9 +162,14 @@ static int __init init_gfs2_fs(void) if (!gfs2_control_wq) goto fail_recovery; + gfs2_freeze_wq = alloc_workqueue("freeze_workqueue", 0, 0); + + if (!gfs2_freeze_wq) + goto fail_control; + gfs2_page_pool = mempool_create_page_pool(64, 0); if (!gfs2_page_pool) - goto fail_control; + goto fail_freeze; gfs2_register_debugfs(); @@ -171,6 +177,8 @@ static int __init init_gfs2_fs(void) return 0; +fail_freeze: + destroy_workqueue(gfs2_freeze_wq); fail_control: destroy_workqueue(gfs2_control_wq); fail_recovery: @@ -224,6 +232,7 @@ static void __exit exit_gfs2_fs(void) unregister_filesystem(&gfs2meta_fs_type); destroy_workqueue(gfs_recovery_wq); destroy_workqueue(gfs2_control_wq); + destroy_workqueue(gfs2_freeze_wq); list_lru_destroy(&gfs2_qd_lru); rcu_barrier(); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index d3eae244076e..8633ad328ee2 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -129,11 +129,11 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) init_rwsem(&sdp->sd_log_flush_lock); atomic_set(&sdp->sd_log_in_flight, 0); + atomic_set(&sdp->sd_reserving_log, 0); + init_waitqueue_head(&sdp->sd_reserving_log_wait); init_waitqueue_head(&sdp->sd_log_flush_wait); - init_waitqueue_head(&sdp->sd_log_frozen_wait); - atomic_set(&sdp->sd_log_freeze, 0); - atomic_set(&sdp->sd_frozen_root, 0); - init_waitqueue_head(&sdp->sd_frozen_root_wait); + atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); + mutex_init(&sdp->sd_freeze_mutex); return sdp; } @@ -760,15 +760,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) set_bit(SDF_JOURNAL_CHECKED, &sdp->sd_flags); gfs2_glock_dq_uninit(&ji_gh); jindex = 0; - if (!sdp->sd_args.ar_spectator) { - error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0, - &sdp->sd_thaw_gh); - if (error) { - fs_err(sdp, "can't acquire freeze glock: %d\n", error); - goto fail_jinode_gh; - } - } - gfs2_glock_dq_uninit(&sdp->sd_thaw_gh); + INIT_WORK(&sdp->sd_freeze_work, gfs2_freeze_func); return 0; fail_jinode_gh: @@ -1082,6 +1074,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent sb->s_export_op = &gfs2_export_ops; sb->s_xattr = gfs2_xattr_handlers; sb->s_qcop = &gfs2_quotactl_ops; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; sb->s_time_gran = 1; sb->s_maxbytes = MAX_LFS_FILESIZE; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 64b29f7f6b4c..c8b148bbdc8b 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1360,13 +1360,8 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp) gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count)); - if (sdp->sd_quota_bitmap) { - if (is_vmalloc_addr(sdp->sd_quota_bitmap)) - vfree(sdp->sd_quota_bitmap); - else - kfree(sdp->sd_quota_bitmap); - sdp->sd_quota_bitmap = NULL; - } + kvfree(sdp->sd_quota_bitmap); + sdp->sd_quota_bitmap = NULL; } static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error) diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 7474c413ffd1..9150207f365c 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -936,7 +936,7 @@ static int read_rindex_entry(struct gfs2_inode *ip) rgd->rd_gl->gl_vm.start = rgd->rd_addr * bsize; rgd->rd_gl->gl_vm.end = rgd->rd_gl->gl_vm.start + (rgd->rd_length * bsize) - 1; rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr; - rgd->rd_flags &= ~GFS2_RDF_UPTODATE; + rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED); if (rgd->rd_data > sdp->sd_max_rg_data) sdp->sd_max_rg_data = rgd->rd_data; spin_lock(&sdp->sd_rindex_spin); @@ -955,6 +955,36 @@ fail: } /** + * set_rgrp_preferences - Run all the rgrps, selecting some we prefer to use + * @sdp: the GFS2 superblock + * + * The purpose of this function is to select a subset of the resource groups + * and mark them as PREFERRED. We do it in such a way that each node prefers + * to use a unique set of rgrps to minimize glock contention. + */ +static void set_rgrp_preferences(struct gfs2_sbd *sdp) +{ + struct gfs2_rgrpd *rgd, *first; + int i; + + /* Skip an initial number of rgrps, based on this node's journal ID. + That should start each node out on its own set. */ + rgd = gfs2_rgrpd_get_first(sdp); + for (i = 0; i < sdp->sd_lockstruct.ls_jid; i++) + rgd = gfs2_rgrpd_get_next(rgd); + first = rgd; + + do { + rgd->rd_flags |= GFS2_RDF_PREFERRED; + for (i = 0; i < sdp->sd_journals; i++) { + rgd = gfs2_rgrpd_get_next(rgd); + if (rgd == first) + break; + } + } while (rgd != first); +} + +/** * gfs2_ri_update - Pull in a new resource index from the disk * @ip: pointer to the rindex inode * @@ -973,6 +1003,8 @@ static int gfs2_ri_update(struct gfs2_inode *ip) if (error < 0) return error; + set_rgrp_preferences(sdp); + sdp->sd_rindex_uptodate = 1; return 0; } @@ -1891,6 +1923,25 @@ static bool gfs2_select_rgrp(struct gfs2_rgrpd **pos, const struct gfs2_rgrpd *b } /** + * fast_to_acquire - determine if a resource group will be fast to acquire + * + * If this is one of our preferred rgrps, it should be quicker to acquire, + * because we tried to set ourselves up as dlm lock master. + */ +static inline int fast_to_acquire(struct gfs2_rgrpd *rgd) +{ + struct gfs2_glock *gl = rgd->rd_gl; + + if (gl->gl_state != LM_ST_UNLOCKED && list_empty(&gl->gl_holders) && + !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags) && + !test_bit(GLF_DEMOTE, &gl->gl_flags)) + return 1; + if (rgd->rd_flags & GFS2_RDF_PREFERRED) + return 1; + return 0; +} + +/** * gfs2_inplace_reserve - Reserve space in the filesystem * @ip: the inode to reserve space for * @ap: the allocation parameters @@ -1932,10 +1983,15 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a rg_locked = 0; if (skip && skip--) goto next_rgrp; - if (!gfs2_rs_active(rs) && (loops < 2) && - gfs2_rgrp_used_recently(rs, 1000) && - gfs2_rgrp_congested(rs->rs_rbm.rgd, loops)) - goto next_rgrp; + if (!gfs2_rs_active(rs)) { + if (loops == 0 && + !fast_to_acquire(rs->rs_rbm.rgd)) + goto next_rgrp; + if ((loops < 2) && + gfs2_rgrp_used_recently(rs, 1000) && + gfs2_rgrp_congested(rs->rs_rbm.rgd, loops)) + goto next_rgrp; + } error = gfs2_glock_nq_init(rs->rs_rbm.rgd->rd_gl, LM_ST_EXCLUSIVE, flags, &rs->rs_rgd_gh); @@ -2195,6 +2251,9 @@ static void gfs2_adjust_reservation(struct gfs2_inode *ip, trace_gfs2_rs(rs, TRACE_RS_CLAIM); if (rs->rs_free && !ret) goto out; + /* We used up our block reservation, so we should + reserve more blocks next time. */ + atomic_add(RGRP_RSRV_ADDBLKS, &rs->rs_sizehint); } __rs_deltree(rs); } diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 5d8f085f7ade..b104f4af3afd 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -20,6 +20,7 @@ */ #define RGRP_RSRV_MINBYTES 8 #define RGRP_RSRV_MINBLKS ((u32)(RGRP_RSRV_MINBYTES * GFS2_NBBY)) +#define RGRP_RSRV_ADDBLKS 64 struct gfs2_rgrpd; struct gfs2_sbd; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index a346f56c4c6d..5b327f837de7 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -26,6 +26,7 @@ #include <linux/wait.h> #include <linux/writeback.h> #include <linux/backing-dev.h> +#include <linux/kernel.h> #include "gfs2.h" #include "incore.h" @@ -399,7 +400,7 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) { struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode); struct gfs2_glock *j_gl = ip->i_gl; - struct gfs2_holder thaw_gh; + struct gfs2_holder freeze_gh; struct gfs2_log_header_host head; int error; @@ -408,7 +409,7 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) return error; error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0, - &thaw_gh); + &freeze_gh); if (error) goto fail_threads; @@ -434,13 +435,13 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); - gfs2_glock_dq_uninit(&thaw_gh); + gfs2_glock_dq_uninit(&freeze_gh); return 0; fail: - thaw_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq_uninit(&thaw_gh); + freeze_gh.gh_flags |= GL_NOCACHE; + gfs2_glock_dq_uninit(&freeze_gh); fail_threads: kthread_stop(sdp->sd_quotad_process); kthread_stop(sdp->sd_logd_process); @@ -580,14 +581,15 @@ int gfs2_statfs_sync(struct super_block *sb, int type) struct buffer_head *m_bh, *l_bh; int error; + sb_start_write(sb); error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE, GL_NOCACHE, &gh); if (error) - return error; + goto out; error = gfs2_meta_inode_buffer(m_ip, &m_bh); if (error) - goto out; + goto out_unlock; spin_lock(&sdp->sd_statfs_spin); gfs2_statfs_change_in(m_sc, m_bh->b_data + @@ -615,8 +617,10 @@ out_bh2: brelse(l_bh); out_bh: brelse(m_bh); -out: +out_unlock: gfs2_glock_dq_uninit(&gh); +out: + sb_end_write(sb); return error; } @@ -643,14 +647,8 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp, struct lfcc *lfcc; LIST_HEAD(list); struct gfs2_log_header_host lh; - struct gfs2_inode *dip = GFS2_I(sdp->sd_root_dir->d_inode); int error; - error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, - &sdp->sd_freeze_root_gh); - if (error) - return error; - atomic_set(&sdp->sd_frozen_root, 1); list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { lfcc = kmalloc(sizeof(struct lfcc), GFP_KERNEL); if (!lfcc) { @@ -692,11 +690,6 @@ out: gfs2_glock_dq_uninit(&lfcc->gh); kfree(lfcc); } - if (error) { - atomic_dec(&sdp->sd_frozen_root); - wait_event(sdp->sd_frozen_root_wait, atomic_read(&sdp->sd_frozen_root) == 0); - gfs2_glock_dq_uninit(&sdp->sd_freeze_root_gh); - } return error; } @@ -834,18 +827,14 @@ out: static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) { - struct gfs2_holder thaw_gh; + struct gfs2_holder freeze_gh; int error; error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE, - &thaw_gh); + &freeze_gh); if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) return error; - down_write(&sdp->sd_log_flush_lock); - clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); - up_write(&sdp->sd_log_flush_lock); - kthread_stop(sdp->sd_quotad_process); kthread_stop(sdp->sd_logd_process); @@ -853,11 +842,16 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); + down_write(&sdp->sd_log_flush_lock); + clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); + up_write(&sdp->sd_log_flush_lock); + gfs2_log_flush(sdp, NULL, SHUTDOWN_FLUSH); + wait_event(sdp->sd_reserving_log_wait, atomic_read(&sdp->sd_reserving_log) == 0); gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks); - if (thaw_gh.gh_gl) - gfs2_glock_dq_uninit(&thaw_gh); + if (freeze_gh.gh_gl) + gfs2_glock_dq_uninit(&freeze_gh); gfs2_quota_cleanup(sdp); @@ -943,11 +937,41 @@ static int gfs2_sync_fs(struct super_block *sb, int wait) struct gfs2_sbd *sdp = sb->s_fs_info; gfs2_quota_sync(sb, -1); - if (wait && sdp && !atomic_read(&sdp->sd_log_freeze)) + if (wait && sdp) gfs2_log_flush(sdp, NULL, NORMAL_FLUSH); return 0; } +void gfs2_freeze_func(struct work_struct *work) +{ + int error; + struct gfs2_holder freeze_gh; + struct gfs2_sbd *sdp = container_of(work, struct gfs2_sbd, sd_freeze_work); + struct super_block *sb = sdp->sd_vfs; + + atomic_inc(&sb->s_active); + error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0, + &freeze_gh); + if (error) { + printk(KERN_INFO "GFS2: couln't get freeze lock : %d\n", error); + gfs2_assert_withdraw(sdp, 0); + } + else { + atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); + error = thaw_super(sb); + if (error) { + printk(KERN_INFO "GFS2: couldn't thaw filesystem: %d\n", + error); + gfs2_assert_withdraw(sdp, 0); + } + if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) + freeze_gh.gh_flags |= GL_NOCACHE; + gfs2_glock_dq_uninit(&freeze_gh); + } + deactivate_super(sb); + return; +} + /** * gfs2_freeze - prevent further writes to the filesystem * @sb: the VFS structure for the filesystem @@ -957,10 +981,16 @@ static int gfs2_sync_fs(struct super_block *sb, int wait) static int gfs2_freeze(struct super_block *sb) { struct gfs2_sbd *sdp = sb->s_fs_info; - int error; + int error = 0; - if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) - return -EINVAL; + mutex_lock(&sdp->sd_freeze_mutex); + if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) + goto out; + + if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) { + error = -EINVAL; + goto out; + } for (;;) { error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh); @@ -980,7 +1010,10 @@ static int gfs2_freeze(struct super_block *sb) fs_err(sdp, "retrying...\n"); msleep(1000); } - return 0; + error = 0; +out: + mutex_unlock(&sdp->sd_freeze_mutex); + return error; } /** @@ -993,10 +1026,15 @@ static int gfs2_unfreeze(struct super_block *sb) { struct gfs2_sbd *sdp = sb->s_fs_info; + mutex_lock(&sdp->sd_freeze_mutex); + if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN || + sdp->sd_freeze_gh.gh_gl == NULL) { + mutex_unlock(&sdp->sd_freeze_mutex); + return 0; + } + gfs2_glock_dq_uninit(&sdp->sd_freeze_gh); - atomic_dec(&sdp->sd_frozen_root); - wait_event(sdp->sd_frozen_root_wait, atomic_read(&sdp->sd_frozen_root) == 0); - gfs2_glock_dq_uninit(&sdp->sd_freeze_root_gh); + mutex_unlock(&sdp->sd_freeze_mutex); return 0; } @@ -1618,8 +1656,8 @@ const struct super_operations gfs2_super_ops = { .evict_inode = gfs2_evict_inode, .put_super = gfs2_put_super, .sync_fs = gfs2_sync_fs, - .freeze_fs = gfs2_freeze, - .unfreeze_fs = gfs2_unfreeze, + .freeze_super = gfs2_freeze, + .thaw_super = gfs2_unfreeze, .statfs = gfs2_statfs, .remount_fs = gfs2_remount_fs, .drop_inode = gfs2_drop_inode, diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index 90e3322ffa10..73c97dccae21 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -45,6 +45,7 @@ extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, struct buffer_head *l_bh); extern int gfs2_statfs_sync(struct super_block *sb, int type); +extern void gfs2_freeze_func(struct work_struct *work); extern struct file_system_type gfs2_fs_type; extern struct file_system_type gfs2meta_fs_type; diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 42bfd3361979..88bff2430669 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -89,14 +89,17 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) { struct gfs2_trans *tr = current->journal_info; s64 nbuf; + int alloced = tr->tr_alloced; + BUG_ON(!tr); current->journal_info = NULL; if (!tr->tr_touched) { gfs2_log_release(sdp, tr->tr_reserved); - if (tr->tr_alloced) + if (alloced) { kfree(tr); - sb_end_intwrite(sdp->sd_vfs); + sb_end_intwrite(sdp->sd_vfs); + } return; } @@ -109,13 +112,14 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) gfs2_print_trans(tr); gfs2_log_commit(sdp, tr); - if (tr->tr_alloced && !tr->tr_attached) + if (alloced && !tr->tr_attached) kfree(tr); up_read(&sdp->sd_log_flush_lock); if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS) gfs2_log_flush(sdp, NULL, NORMAL_FLUSH); - sb_end_intwrite(sdp->sd_vfs); + if (alloced) + sb_end_intwrite(sdp->sd_vfs); } static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl, @@ -192,6 +196,7 @@ static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { struct gfs2_meta_header *mh; struct gfs2_trans *tr; + enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); tr = current->journal_info; tr->tr_touched = 1; @@ -205,6 +210,10 @@ static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) (unsigned long long)bd->bd_bh->b_blocknr); BUG(); } + if (unlikely(state == SFS_FROZEN)) { + printk(KERN_INFO "GFS2:adding buf while frozen\n"); + gfs2_assert_withdraw(sdp, 0); + } gfs2_pin(sdp, bd->bd_bh); mh->__pad0 = cpu_to_be64(0); mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 4338ff32959d..5f2755117ce7 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -548,10 +548,11 @@ struct hppfs_dirent { struct dentry *dentry; }; -static int hppfs_filldir(void *d, const char *name, int size, +static int hppfs_filldir(struct dir_context *ctx, const char *name, int size, loff_t offset, u64 inode, unsigned int type) { - struct hppfs_dirent *dirent = d; + struct hppfs_dirent *dirent = + container_of(ctx, struct hppfs_dirent, ctx); if (file_removed(dirent->dentry, name)) return 0; diff --git a/fs/inode.c b/fs/inode.c index 26753ba7b6d6..2ed95f7caa4f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -143,9 +143,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; -#ifdef CONFIG_QUOTA - memset(&inode->i_dquot, 0, sizeof(inode->i_dquot)); -#endif inode->i_pipe = NULL; inode->i_bdev = NULL; inode->i_cdev = NULL; diff --git a/fs/ioctl.c b/fs/ioctl.c index 8ac3fad36192..77c9a7812542 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -518,10 +518,12 @@ static int ioctl_fsfreeze(struct file *filp) return -EPERM; /* If filesystem doesn't support freeze feature, return. */ - if (sb->s_op->freeze_fs == NULL) + if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL) return -EOPNOTSUPP; /* Freeze */ + if (sb->s_op->freeze_super) + return sb->s_op->freeze_super(sb); return freeze_super(sb); } @@ -533,6 +535,8 @@ static int ioctl_fsthaw(struct file *filp) return -EPERM; /* Thaw */ + if (sb->s_op->thaw_super) + return sb->s_op->thaw_super(sb); return thaw_super(sb); } diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index aab8549591e7..c46a79adb6ad 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -1373,8 +1373,7 @@ int journal_destroy(journal_t *journal) } mutex_unlock(&journal->j_checkpoint_mutex); - if (journal->j_inode) - iput(journal->j_inode); + iput(journal->j_inode); if (journal->j_revoke) journal_destroy_revoke(journal); kfree(journal->j_wbuf); diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index cf47f09e8ac8..fa7e795bd8ae 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -94,6 +94,9 @@ struct jfs_inode_info { unchar _inline_ea[128]; /* 128: inline extended attr */ } link; } u; +#ifdef CONFIG_QUOTA + struct dquot *i_dquot[MAXQUOTAS]; +#endif u32 dev; /* will die when we get wide dev_t */ struct inode vfs_inode; }; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index d59c7defb1ef..38fdc533f4ec 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -84,7 +84,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode, struct inode *iplist[2]; struct tblock *tblk; - jfs_info("jfs_create: dip:0x%p name:%s", dip, dentry->d_name.name); + jfs_info("jfs_create: dip:0x%p name:%pd", dip, dentry); dquot_initialize(dip); @@ -216,7 +216,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode) struct inode *iplist[2]; struct tblock *tblk; - jfs_info("jfs_mkdir: dip:0x%p name:%s", dip, dentry->d_name.name); + jfs_info("jfs_mkdir: dip:0x%p name:%pd", dip, dentry); dquot_initialize(dip); @@ -352,7 +352,7 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry) struct inode *iplist[2]; struct tblock *tblk; - jfs_info("jfs_rmdir: dip:0x%p name:%s", dip, dentry->d_name.name); + jfs_info("jfs_rmdir: dip:0x%p name:%pd", dip, dentry); /* Init inode for quota operations. */ dquot_initialize(dip); @@ -480,7 +480,7 @@ static int jfs_unlink(struct inode *dip, struct dentry *dentry) s64 new_size = 0; int commit_flag; - jfs_info("jfs_unlink: dip:0x%p name:%s", dip, dentry->d_name.name); + jfs_info("jfs_unlink: dip:0x%p name:%pd", dip, dentry); /* Init inode for quota operations. */ dquot_initialize(dip); @@ -797,8 +797,7 @@ static int jfs_link(struct dentry *old_dentry, struct btstack btstack; struct inode *iplist[2]; - jfs_info("jfs_link: %s %s", old_dentry->d_name.name, - dentry->d_name.name); + jfs_info("jfs_link: %pd %pd", old_dentry, dentry); dquot_initialize(dir); @@ -1082,8 +1081,7 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, int commit_flag; - jfs_info("jfs_rename: %s %s", old_dentry->d_name.name, - new_dentry->d_name.name); + jfs_info("jfs_rename: %pd %pd", old_dentry, new_dentry); dquot_initialize(old_dir); dquot_initialize(new_dir); @@ -1355,7 +1353,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry, if (!new_valid_dev(rdev)) return -EINVAL; - jfs_info("jfs_mknod: %s", dentry->d_name.name); + jfs_info("jfs_mknod: %pd", dentry); dquot_initialize(dir); @@ -1444,7 +1442,7 @@ static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, unsig struct component_name key; int rc; - jfs_info("jfs_lookup: name = %s", dentry->d_name.name); + jfs_info("jfs_lookup: name = %pd", dentry); if ((rc = get_UCSname(&key, dentry))) return ERR_PTR(rc); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 93e897e588a8..16c3a9556634 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -117,6 +117,9 @@ static struct inode *jfs_alloc_inode(struct super_block *sb) jfs_inode = kmem_cache_alloc(jfs_inode_cachep, GFP_NOFS); if (!jfs_inode) return NULL; +#ifdef CONFIG_QUOTA + memset(&jfs_inode->i_dquot, 0, sizeof(jfs_inode->i_dquot)); +#endif return &jfs_inode->vfs_inode; } @@ -537,6 +540,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->dq_op = &dquot_operations; sb->s_qcop = &dquot_quotactl_ops; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; #endif /* @@ -836,6 +840,10 @@ out: return len - towrite; } +static struct dquot **jfs_get_dquots(struct inode *inode) +{ + return JFS_IP(inode)->i_dquot; +} #endif static const struct super_operations jfs_super_operations = { @@ -854,6 +862,7 @@ static const struct super_operations jfs_super_operations = { #ifdef CONFIG_QUOTA .quota_read = jfs_quota_read, .quota_write = jfs_quota_write, + .get_dquots = jfs_get_dquots, #endif }; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 1c771931bb60..37989f02a226 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -807,7 +807,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, } /* instantiate and hash dentry */ - ret = d_materialise_unique(dentry, inode); + ret = d_splice_alias(inode, dentry); out_unlock: mutex_unlock(&kernfs_mutex); return ret; diff --git a/fs/libfs.c b/fs/libfs.c index 171d2846f2a3..005843ce5dbd 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -114,18 +114,18 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) spin_lock(&dentry->d_lock); /* d_lock not required for cursor */ - list_del(&cursor->d_u.d_child); + list_del(&cursor->d_child); p = dentry->d_subdirs.next; while (n && p != &dentry->d_subdirs) { struct dentry *next; - next = list_entry(p, struct dentry, d_u.d_child); + next = list_entry(p, struct dentry, d_child); spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(next)) n--; spin_unlock(&next->d_lock); p = p->next; } - list_add_tail(&cursor->d_u.d_child, p); + list_add_tail(&cursor->d_child, p); spin_unlock(&dentry->d_lock); } } @@ -150,7 +150,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *p, *q = &cursor->d_u.d_child; + struct list_head *p, *q = &cursor->d_child; if (!dir_emit_dots(file, ctx)) return 0; @@ -159,7 +159,7 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) list_move(q, &dentry->d_subdirs); for (p = q->next; p != &dentry->d_subdirs; p = p->next) { - struct dentry *next = list_entry(p, struct dentry, d_u.d_child); + struct dentry *next = list_entry(p, struct dentry, d_child); spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED); if (!simple_positive(next)) { spin_unlock(&next->d_lock); @@ -287,7 +287,7 @@ int simple_empty(struct dentry *dentry) int ret = 0; spin_lock(&dentry->d_lock); - list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dentry->d_subdirs, d_child) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 13db95f54176..56598742dde4 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -53,7 +53,7 @@ static const struct rpc_call_ops nlmsvc_grant_ops; static LIST_HEAD(nlm_blocked); static DEFINE_SPINLOCK(nlm_blocked_lock); -#ifdef LOCKD_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie) { /* diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index b6f3b84b6e99..d12ff4e2dbe7 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -408,7 +408,7 @@ nlmsvc_match_sb(void *datap, struct nlm_file *file) { struct super_block *sb = datap; - return sb == file->f_file->f_path.dentry->d_sb; + return sb == file_inode(file->f_file)->i_sb; } /** diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index 7cb751dfbeef..008960101520 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -198,8 +198,8 @@ ncp_single_volume(struct ncp_server *server) static inline int ncp_is_server_root(struct inode *inode) { - return (!ncp_single_volume(NCP_SERVER(inode)) && - inode == inode->i_sb->s_root->d_inode); + return !ncp_single_volume(NCP_SERVER(inode)) && + is_root_inode(inode); } @@ -403,7 +403,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos) /* If a pointer is invalid, we search the dentry. */ spin_lock(&parent->d_lock); - list_for_each_entry(dent, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(dent, &parent->d_subdirs, d_child) { if ((unsigned long)dent->d_fsdata == fpos) { if (dent->d_inode) dget(dent); @@ -685,8 +685,7 @@ static void ncp_read_volume_list(struct file *file, struct dir_context *ctx, struct ncp_cache_control *ctl) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(file); struct ncp_server *server = NCP_SERVER(inode); struct ncp_volume_info info; struct ncp_entry_info entry; @@ -721,8 +720,7 @@ static void ncp_do_readdir(struct file *file, struct dir_context *ctx, struct ncp_cache_control *ctl) { - struct dentry *dentry = file->f_path.dentry; - struct inode *dir = dentry->d_inode; + struct inode *dir = file_inode(file); struct ncp_server *server = NCP_SERVER(dir); struct nw_search_sequence seq; struct ncp_entry_info entry; diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c index 77640a8bfb87..1dd7007f974d 100644 --- a/fs/ncpfs/file.c +++ b/fs/ncpfs/file.c @@ -100,8 +100,7 @@ out: static ssize_t ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(file); size_t already_read = 0; off_t pos; size_t bufsize; @@ -109,7 +108,7 @@ ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) void* freepage; size_t freelen; - ncp_dbg(1, "enter %pd2\n", dentry); + ncp_dbg(1, "enter %pD2\n", file); pos = *ppos; @@ -167,7 +166,7 @@ ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) file_accessed(file); - ncp_dbg(1, "exit %pd2\n", dentry); + ncp_dbg(1, "exit %pD2\n", file); outrel: ncp_inode_close(inode); return already_read ? already_read : error; @@ -176,15 +175,14 @@ outrel: static ssize_t ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(file); size_t already_written = 0; off_t pos; size_t bufsize; int errno; void* bouncebuffer; - ncp_dbg(1, "enter %pd2\n", dentry); + ncp_dbg(1, "enter %pD2\n", file); if ((ssize_t) count < 0) return -EINVAL; pos = *ppos; @@ -263,7 +261,7 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t * i_size_write(inode, pos); mutex_unlock(&inode->i_mutex); } - ncp_dbg(1, "exit %pd2\n", dentry); + ncp_dbg(1, "exit %pD2\n", file); outrel: ncp_inode_close(inode); return already_written ? already_written : errno; diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index b359d12eb359..33b873b259a8 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -30,9 +30,7 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area, struct vm_fault *vmf) { - struct file *file = area->vm_file; - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(area->vm_file); char *pg_addr; unsigned int already_read; unsigned int count; diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h index 52cb19d66ecb..b785f74bfe3c 100644 --- a/fs/ncpfs/ncplib_kernel.h +++ b/fs/ncpfs/ncplib_kernel.h @@ -191,7 +191,7 @@ ncp_renew_dentries(struct dentry *parent) struct dentry *dentry; spin_lock(&parent->d_lock); - list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(dentry, &parent->d_subdirs, d_child) { if (dentry->d_fsdata == NULL) ncp_age_dentry(server, dentry); else @@ -207,7 +207,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent) struct dentry *dentry; spin_lock(&parent->d_lock); - list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) { + list_for_each_entry(dentry, &parent->d_subdirs, d_child) { dentry->d_fsdata = NULL; ncp_age_dentry(server, dentry); } diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 4f46f7a05289..77fec6a55f57 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -812,7 +812,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) /* Optimize common case that writes from 0 to end of file */ end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); - if (end != NFS_I(inode)->npages) { + if (end != inode->i_mapping->nrpages) { rcu_read_lock(); end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c index acbf9ca4018c..dbe5839cdeba 100644 --- a/fs/nfs/blocklayout/rpc_pipefs.c +++ b/fs/nfs/blocklayout/rpc_pipefs.c @@ -112,7 +112,7 @@ out_unlock: static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { - struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info, + struct nfs_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info, nfs_net_id); if (mlen != sizeof (struct bl_dev_msg)) diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 73466b934090..e36a9d78ea49 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -49,7 +49,7 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args, goto out_iput; res->size = i_size_read(inode); res->change_attr = delegation->change_attr; - if (nfsi->npages != 0) + if (nfsi->nrequests != 0) res->change_attr++; res->ctime = inode->i_ctime; res->mtime = inode->i_mtime; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 6e62155abf26..9b0c55cb2a2e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -133,7 +133,7 @@ out: static int nfs_closedir(struct inode *inode, struct file *filp) { - put_nfs_open_dir_context(filp->f_path.dentry->d_inode, filp->private_data); + put_nfs_open_dir_context(file_inode(filp), filp->private_data); return 0; } @@ -499,7 +499,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) if (IS_ERR(inode)) goto out; - alias = d_materialise_unique(dentry, inode); + alias = d_splice_alias(inode, dentry); if (IS_ERR(alias)) goto out; else if (alias) { @@ -1393,7 +1393,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in nfs_advise_use_readdirplus(dir); no_entry: - res = d_materialise_unique(dentry, inode); + res = d_splice_alias(inode, dentry); if (res != NULL) { if (IS_ERR(res)) goto out_unblock_sillyrename; diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 9bb806a76d99..bfecac781f19 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -204,8 +204,7 @@ destroy_ds(struct nfs4_pnfs_ds *ds) ifdebug(FACILITY) print_ds(ds); - if (ds->ds_clp) - nfs_put_client(ds->ds_clp); + nfs_put_client(ds->ds_clp); while (!list_empty(&ds->ds_addrs)) { da = list_first_entry(&ds->ds_addrs, diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 3ef01f0ba0bc..d63bea8bbfbb 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -269,8 +269,8 @@ int nfs_fscache_release_page(struct page *page, gfp_t gfp) if (!fscache_maybe_release_page(cookie, page, gfp)) return 0; - nfs_add_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED, 1); + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); } return 1; @@ -293,8 +293,8 @@ void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode) BUG_ON(!PageLocked(page)); fscache_uncache_page(cookie, page); - nfs_add_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED, 1); + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); } /* @@ -343,19 +343,19 @@ int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, case 0: /* read BIO submitted (page in fscache) */ dfprintk(FSCACHE, "NFS: readpage_from_fscache: BIO submitted\n"); - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, 1); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); return ret; case -ENOBUFS: /* inode not in cache */ case -ENODATA: /* page not in cache */ - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); return 1; default: dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); } return ret; } @@ -429,11 +429,11 @@ void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) if (ret != 0) { fscache_uncache_page(nfs_i_fscache(inode), page); - nfs_add_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, 1); - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED, 1); + nfs_inc_fscache_stats(inode, + NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); } else { - nfs_add_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK, 1); + nfs_inc_fscache_stats(inode, + NFSIOS_FSCACHE_PAGES_WRITTEN_OK); } } diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 880618a8b048..9ac3846cb59e 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -51,14 +51,14 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i /* * Ensure that this dentry is invisible to d_find_alias(). * Otherwise, it may be spliced into the tree by - * d_materialise_unique if a parent directory from the same + * d_splice_alias if a parent directory from the same * filesystem gets mounted at a later time. * This again causes shrink_dcache_for_umount_subtree() to * Oops, since the test for IS_ROOT() will fail. */ spin_lock(&sb->s_root->d_inode->i_lock); spin_lock(&sb->s_root->d_lock); - hlist_del_init(&sb->s_root->d_alias); + hlist_del_init(&sb->s_root->d_u.d_alias); spin_unlock(&sb->s_root->d_lock); spin_unlock(&sb->s_root->d_inode->i_lock); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 00689a8a85e4..4bffe637ea32 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -192,6 +192,7 @@ void nfs_zap_caches(struct inode *inode) nfs_zap_caches_locked(inode); spin_unlock(&inode->i_lock); } +EXPORT_SYMBOL_GPL(nfs_zap_caches); void nfs_zap_mapping(struct inode *inode, struct address_space *mapping) { @@ -1149,7 +1150,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) - && nfsi->npages == 0) { + && nfsi->nrequests == 0) { i_size_write(inode, nfs_size_to_loff_t(fattr->size)); ret |= NFS_INO_INVALID_ATTR; } @@ -1192,7 +1193,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); - if (cur_size != new_isize && nfsi->npages == 0) + if (cur_size != new_isize && nfsi->nrequests == 0) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; } @@ -1619,7 +1620,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (new_isize != cur_isize) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ - if ((nfsi->npages == 0) || new_isize > cur_isize) { + if ((nfsi->nrequests == 0) || new_isize > cur_isize) { i_size_write(inode, new_isize); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; invalid &= ~NFS_INO_REVAL_PAGECACHE; @@ -1784,7 +1785,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); INIT_LIST_HEAD(&nfsi->commit_info.list); - nfsi->npages = 0; + nfsi->nrequests = 0; nfsi->commit_info.ncommit = 0; atomic_set(&nfsi->commit_info.rpcs_out, 0); atomic_set(&nfsi->silly_count, 1); diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h index c5832487c456..0cb806fbd4c4 100644 --- a/fs/nfs/iostat.h +++ b/fs/nfs/iostat.h @@ -55,6 +55,11 @@ static inline void nfs_add_fscache_stats(struct inode *inode, { this_cpu_add(NFS_SERVER(inode)->io_stats->fscache[stat], addend); } +static inline void nfs_inc_fscache_stats(struct inode *inode, + enum nfs_stat_fscachecounters stat) +{ + this_cpu_inc(NFS_SERVER(inode)->io_stats->fscache[stat]); +} #endif static inline struct nfs_iostats __percpu *nfs_alloc_iostats(void) diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index d10333a197bf..7afb8947dfdf 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -6,6 +6,8 @@ #define __LINUX_FS_NFS_NFS4_2_H /* nfs4.2proc.c */ +int nfs42_proc_allocate(struct file *, loff_t, loff_t); +int nfs42_proc_deallocate(struct file *, loff_t, loff_t); loff_t nfs42_proc_llseek(struct file *, loff_t, int); /* nfs4.2xdr.h */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 0886f1db5917..cb170722769c 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -32,6 +32,81 @@ static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file, return ret; } +static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, + loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(filep); + struct nfs42_falloc_args args = { + .falloc_fh = NFS_FH(inode), + .falloc_offset = offset, + .falloc_length = len, + }; + struct nfs42_falloc_res res; + struct nfs_server *server = NFS_SERVER(inode); + int status; + + msg->rpc_argp = &args; + msg->rpc_resp = &res; + + status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE); + if (status) + return status; + + return nfs4_call_sync(server->client, server, msg, + &args.seq_args, &res.seq_res, 0); +} + +static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, + loff_t offset, loff_t len) +{ + struct nfs_server *server = NFS_SERVER(file_inode(filep)); + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs42_proc_fallocate(msg, filep, offset, len); + if (err == -ENOTSUPP) + return -EOPNOTSUPP; + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + + return err; +} + +int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], + }; + struct inode *inode = file_inode(filep); + int err; + + if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) + return -EOPNOTSUPP; + + err = nfs42_proc_fallocate(&msg, filep, offset, len); + if (err == -EOPNOTSUPP) + NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE; + return err; +} + +int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DEALLOCATE], + }; + struct inode *inode = file_inode(filep); + int err; + + if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE)) + return -EOPNOTSUPP; + + err = nfs42_proc_fallocate(&msg, filep, offset, len); + if (err == -EOPNOTSUPP) + NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE; + return err; +} + loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct inode *inode = file_inode(filep); @@ -50,7 +125,7 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) struct nfs_server *server = NFS_SERVER(inode); int status; - if (!(server->caps & NFS_CAP_SEEK)) + if (!nfs_server_capable(inode, NFS_CAP_SEEK)) return -ENOTSUPP; status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ); diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index c90469b604b8..038a7e1521fa 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -4,6 +4,15 @@ #ifndef __LINUX_FS_NFS_NFS4_2XDR_H #define __LINUX_FS_NFS_NFS4_2XDR_H +#define encode_fallocate_maxsz (encode_stateid_maxsz + \ + 2 /* offset */ + \ + 2 /* length */) +#define encode_allocate_maxsz (op_encode_hdr_maxsz + \ + encode_fallocate_maxsz) +#define decode_allocate_maxsz (op_decode_hdr_maxsz) +#define encode_deallocate_maxsz (op_encode_hdr_maxsz + \ + encode_fallocate_maxsz) +#define decode_deallocate_maxsz (op_decode_hdr_maxsz) #define encode_seek_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + \ 2 /* offset */ + \ @@ -14,6 +23,18 @@ 2 /* offset */ + \ 2 /* length */) +#define NFS4_enc_allocate_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_allocate_maxsz) +#define NFS4_dec_allocate_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_allocate_maxsz) +#define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_deallocate_maxsz) +#define NFS4_dec_deallocate_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_deallocate_maxsz) #define NFS4_enc_seek_sz (compound_encode_hdr_maxsz + \ encode_putfh_maxsz + \ encode_seek_maxsz) @@ -22,6 +43,30 @@ decode_seek_maxsz) +static void encode_fallocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + encode_nfs4_stateid(xdr, &args->falloc_stateid); + encode_uint64(xdr, args->falloc_offset); + encode_uint64(xdr, args->falloc_length); +} + +static void encode_allocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_ALLOCATE, decode_allocate_maxsz, hdr); + encode_fallocate(xdr, args); +} + +static void encode_deallocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DEALLOCATE, decode_deallocate_maxsz, hdr); + encode_fallocate(xdr, args); +} + static void encode_seek(struct xdr_stream *xdr, struct nfs42_seek_args *args, struct compound_hdr *hdr) @@ -33,6 +78,42 @@ static void encode_seek(struct xdr_stream *xdr, } /* + * Encode ALLOCATE request + */ +static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->falloc_fh, &hdr); + encode_allocate(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* + * Encode DEALLOCATE request + */ +static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->falloc_fh, &hdr); + encode_deallocate(xdr, args, &hdr); + encode_nops(&hdr); +} + +/* * Encode SEEK request */ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, @@ -50,6 +131,16 @@ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, encode_nops(&hdr); } +static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) +{ + return decode_op_hdr(xdr, OP_ALLOCATE); +} + +static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) +{ + return decode_op_hdr(xdr, OP_DEALLOCATE); +} + static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res) { int status; @@ -73,6 +164,54 @@ out_overflow: } /* + * Decode ALLOCATE request + */ +static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_falloc_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_allocate(xdr, res); +out: + return status; +} + +/* + * Decode DEALLOCATE request + */ +static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_falloc_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_deallocate(xdr, res); +out: + return status; +} + +/* * Decode SEEK request */ static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index be6cac37ea10..a08178764cf9 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -226,6 +226,7 @@ int nfs4_replace_transport(struct nfs_server *server, const struct nfs4_fs_locations *locations); /* nfs4proc.c */ +extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *); extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *, struct rpc_message *, struct nfs4_sequence_args *, struct nfs4_sequence_res *, int); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index ffdb28d86cf8..03311259b0c4 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -241,28 +241,25 @@ void nfs4_free_client(struct nfs_client *clp) */ static int nfs4_init_callback(struct nfs_client *clp) { + struct rpc_xprt *xprt; int error; - if (clp->rpc_ops->version == 4) { - struct rpc_xprt *xprt; + xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt); - xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt); - - if (nfs4_has_session(clp)) { - error = xprt_setup_backchannel(xprt, - NFS41_BC_MIN_CALLBACKS); - if (error < 0) - return error; - } - - error = nfs_callback_up(clp->cl_mvops->minor_version, xprt); - if (error < 0) { - dprintk("%s: failed to start callback. Error = %d\n", - __func__, error); + if (nfs4_has_session(clp)) { + error = xprt_setup_backchannel(xprt, NFS41_BC_MIN_CALLBACKS); + if (error < 0) return error; - } - __set_bit(NFS_CS_CALLBACK, &clp->cl_res_state); } + + error = nfs_callback_up(clp->cl_mvops->minor_version, xprt); + if (error < 0) { + dprintk("%s: failed to start callback. Error = %d\n", + __func__, error); + return error; + } + __set_bit(NFS_CS_CALLBACK, &clp->cl_res_state); + return 0; } @@ -498,8 +495,7 @@ int nfs40_walk_client_list(struct nfs_client *new, atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); prev = pos; status = nfs_wait_client_init_complete(pos); @@ -517,8 +513,7 @@ int nfs40_walk_client_list(struct nfs_client *new, atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); prev = pos; status = nfs4_proc_setclientid_confirm(pos, &clid, cred); @@ -549,8 +544,7 @@ int nfs40_walk_client_list(struct nfs_client *new, /* No match found. The server lost our clientid */ out: - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); dprintk("NFS: <-- %s status = %d\n", __func__, status); return status; } @@ -641,8 +635,7 @@ int nfs41_walk_client_list(struct nfs_client *new, atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); prev = pos; status = nfs_wait_client_init_complete(pos); @@ -675,8 +668,7 @@ int nfs41_walk_client_list(struct nfs_client *new, /* No matching nfs_client found. */ spin_unlock(&nn->nfs_client_lock); dprintk("NFS: <-- %s status = %d\n", __func__, status); - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); return status; } #endif /* CONFIG_NFS_V4_1 */ diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index c51fb4db9bfe..8b46389c4c5b 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -3,6 +3,8 @@ * * Copyright (C) 1992 Rick Sladkey */ +#include <linux/fs.h> +#include <linux/falloc.h> #include <linux/nfs_fs.h> #include "internal.h" #include "fscache.h" @@ -134,6 +136,32 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) return nfs_file_llseek(filep, offset, whence); } } + +static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(filep); + long ret; + + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + if ((mode != 0) && (mode != (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE))) + return -EOPNOTSUPP; + + ret = inode_newsize_ok(inode, offset + len); + if (ret < 0) + return ret; + + mutex_lock(&inode->i_mutex); + if (mode & FALLOC_FL_PUNCH_HOLE) + ret = nfs42_proc_deallocate(filep, offset, len); + else + ret = nfs42_proc_allocate(filep, offset, len); + mutex_unlock(&inode->i_mutex); + + nfs_zap_caches(inode); + return ret; +} #endif /* CONFIG_NFS_V4_2 */ const struct file_operations nfs4_file_operations = { @@ -155,6 +183,9 @@ const struct file_operations nfs4_file_operations = { .flock = nfs_flock, .splice_read = nfs_file_splice_read, .splice_write = iter_file_splice_write, +#ifdef CONFIG_NFS_V4_2 + .fallocate = nfs42_fallocate, +#endif /* CONFIG_NFS_V4_2 */ .check_flags = nfs_check_flags, .setlease = simple_nosetlease, }; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 69dc20a743f9..e7f8d5ff2581 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -158,8 +158,6 @@ static int nfs4_map_errors(int err) return -EACCES; case -NFS4ERR_MINOR_VERS_MISMATCH: return -EPROTONOSUPPORT; - case -NFS4ERR_ACCESS: - return -EACCES; case -NFS4ERR_FILE_OPEN: return -EBUSY; default: @@ -344,7 +342,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) /* This is the error handling routine for processes that are allowed * to sleep. */ -static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) +int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) { struct nfs_client *clp = server->nfs_client; struct nfs4_state *state = exception->state; @@ -7704,6 +7702,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) dprintk("--> %s\n", __func__); + /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ + pnfs_get_layout_hdr(NFS_I(inode)->layout); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); if (!lgp->args.layout.pages) { nfs4_layoutget_release(lgp); @@ -7716,9 +7717,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) lgp->res.seq_res.sr_slot = NULL; nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); - /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ - pnfs_get_layout_hdr(NFS_I(inode)->layout); - task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return ERR_CAST(task); @@ -8426,6 +8424,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1 + | NFS_CAP_ALLOCATE + | NFS_CAP_DEALLOCATE | NFS_CAP_SEEK, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 206c08a60c7f..cb4376b78ed9 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -141,13 +141,15 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_VERIFIER_SIZE) + \ XDR_QUADLEN(NFS4_SETCLIENTID_NAMELEN) + \ 1 /* sc_prog */ + \ - XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \ - XDR_QUADLEN(RPCBIND_MAXUADDRLEN) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN) + \ 1) /* sc_cb_ident */ #define decode_setclientid_maxsz \ (op_decode_hdr_maxsz + \ - 2 + \ - 1024) /* large value for CLID_INUSE */ + 2 /* clientid */ + \ + XDR_QUADLEN(NFS4_VERIFIER_SIZE) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) #define encode_setclientid_confirm_maxsz \ (op_encode_hdr_maxsz + \ 3 + (NFS4_VERIFIER_SIZE >> 2)) @@ -7394,6 +7396,8 @@ struct rpc_procinfo nfs4_procedures[] = { #endif /* CONFIG_NFS_V4_1 */ #ifdef CONFIG_NFS_V4_2 PROC(SEEK, enc_seek, dec_seek), + PROC(ALLOCATE, enc_allocate, dec_allocate), + PROC(DEALLOCATE, enc_deallocate, dec_deallocate), #endif /* CONFIG_NFS_V4_2 */ }; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ed0db61f8543..2b5e769beb16 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -258,6 +258,7 @@ bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit) static inline void nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) { + struct inode *inode; WARN_ON_ONCE(prev == req); if (!prev) { @@ -276,12 +277,16 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) * nfs_page_group_destroy is called */ kref_get(&req->wb_head->wb_kref); - /* grab extra ref if head request has extra ref from - * the write/commit path to handle handoff between write - * and commit lists */ + /* grab extra ref and bump the request count if head request + * has extra ref from the write/commit path to handle handoff + * between write and commit lists. */ if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) { + inode = page_file_mapping(req->wb_page)->host; set_bit(PG_INODE_REF, &req->wb_flags); kref_get(&req->wb_kref); + spin_lock(&inode->i_lock); + NFS_I(inode)->nrequests++; + spin_unlock(&inode->i_lock); } } } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index beff2769c5c5..c91a4799c562 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -269,7 +269,7 @@ int nfs_readpage(struct file *file, struct page *page) dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", page, PAGE_CACHE_SIZE, page_file_index(page)); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); - nfs_add_stats(inode, NFSIOS_READPAGES, 1); + nfs_inc_stats(inode, NFSIOS_READPAGES); /* * Try to flush any pending writes to the file.. diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f83b02dc9166..af3af685a9e3 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -575,7 +575,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st int ret; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); - nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); + nfs_inc_stats(inode, NFSIOS_WRITEPAGES); nfs_pageio_cond_complete(pgio, page_file_index(page)); ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); @@ -670,7 +670,8 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) nfs_lock_request(req); spin_lock(&inode->i_lock); - if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) + if (!nfsi->nrequests && + NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) inode->i_version++; /* * Swap-space should not get truncated. Hence no need to plug the race @@ -681,9 +682,11 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) SetPagePrivate(req->wb_page); set_page_private(req->wb_page, (unsigned long)req); } - nfsi->npages++; + nfsi->nrequests++; /* this a head request for a page group - mark it as having an - * extra reference so sub groups can follow suit */ + * extra reference so sub groups can follow suit. + * This flag also informs pgio layer when to bump nrequests when + * adding subrequests. */ WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags)); kref_get(&req->wb_kref); spin_unlock(&inode->i_lock); @@ -709,7 +712,11 @@ static void nfs_inode_remove_request(struct nfs_page *req) wake_up_page(head->wb_page, PG_private); clear_bit(PG_MAPPED, &head->wb_flags); } - nfsi->npages--; + nfsi->nrequests--; + spin_unlock(&inode->i_lock); + } else { + spin_lock(&inode->i_lock); + nfsi->nrequests--; spin_unlock(&inode->i_lock); } @@ -1735,7 +1742,7 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ - if (nfsi->commit_info.ncommit <= (nfsi->npages >> 1)) + if (nfsi->commit_info.ncommit <= (nfsi->nrequests >> 1)) goto out_mark_dirty; /* don't wait for the COMMIT response */ diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index a25490ae6c62..cc6a76072009 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -245,10 +245,11 @@ struct nfs4_dir_ctx { }; static int -nfsd4_build_namelist(void *arg, const char *name, int namlen, +nfsd4_build_namelist(struct dir_context *__ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct nfs4_dir_ctx *ctx = arg; + struct nfs4_dir_ctx *ctx = + container_of(__ctx, struct nfs4_dir_ctx, ctx); struct name_list *entry; if (namlen != HEXDIR_LEN - 1) @@ -704,7 +705,7 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) struct cld_upcall *tmp, *cup; struct cld_msg __user *cmsg = (struct cld_msg __user *)src; uint32_t xid; - struct nfsd_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info, + struct nfsd_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info, nfsd_net_id); struct cld_net *cn = nn->cld_net; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index eeea7a90eb87..b1eed4dd2eab 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1886,7 +1886,7 @@ static __be32 nfsd4_encode_path(struct xdr_stream *xdr, goto out_free; } p = xdr_encode_opaque(p, dentry->d_name.name, len); - dprintk("/%s", dentry->d_name.name); + dprintk("/%pd", dentry); spin_unlock(&dentry->d_lock); dput(dentry); ncomponents--; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index ca73ca79a0ee..9506ea565610 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -231,6 +231,10 @@ static struct file_operations reply_cache_stats_operations = { * payload - write methods */ +static inline struct net *netns(struct file *file) +{ + return file_inode(file)->i_sb->s_fs_info; +} /** * write_unlock_ip - Release all locks used by a client @@ -252,7 +256,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) struct sockaddr *sap = (struct sockaddr *)&address; size_t salen = sizeof(address); char *fo_path; - struct net *net = file->f_dentry->d_sb->s_fs_info; + struct net *net = netns(file); /* sanity check */ if (size == 0) @@ -350,7 +354,6 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) int len; struct auth_domain *dom; struct knfsd_fh fh; - struct net *net = file->f_dentry->d_sb->s_fs_info; if (size == 0) return -EINVAL; @@ -385,7 +388,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) if (!dom) return -ENOMEM; - len = exp_rootfh(net, dom, path, &fh, maxsize); + len = exp_rootfh(netns(file), dom, path, &fh, maxsize); auth_domain_put(dom); if (len) return len; @@ -429,7 +432,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) { char *mesg = buf; int rv; - struct net *net = file->f_dentry->d_sb->s_fs_info; + struct net *net = netns(file); if (size > 0) { int newthreads; @@ -480,7 +483,7 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) int len; int npools; int *nthreads; - struct net *net = file->f_dentry->d_sb->s_fs_info; + struct net *net = netns(file); mutex_lock(&nfsd_mutex); npools = nfsd_nrpools(net); @@ -543,8 +546,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) unsigned minor; ssize_t tlen = 0; char *sep; - struct net *net = file->f_dentry->d_sb->s_fs_info; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); if (size>0) { if (nn->nfsd_serv) @@ -830,10 +832,9 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size, static ssize_t write_ports(struct file *file, char *buf, size_t size) { ssize_t rv; - struct net *net = file->f_dentry->d_sb->s_fs_info; mutex_lock(&nfsd_mutex); - rv = __write_ports(file, buf, size, net); + rv = __write_ports(file, buf, size, netns(file)); mutex_unlock(&nfsd_mutex); return rv; } @@ -865,8 +866,7 @@ int nfsd_max_blksize; static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) { char *mesg = buf; - struct net *net = file->f_dentry->d_sb->s_fs_info; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); if (size > 0) { int bsize; @@ -915,8 +915,7 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) static ssize_t write_maxconn(struct file *file, char *buf, size_t size) { char *mesg = buf; - struct net *net = file->f_dentry->d_sb->s_fs_info; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); unsigned int maxconn = nn->max_connections; if (size > 0) { @@ -997,8 +996,7 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, */ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) { - struct net *net = file->f_dentry->d_sb->s_fs_info; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn); } @@ -1014,8 +1012,7 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) */ static ssize_t write_gracetime(struct file *file, char *buf, size_t size) { - struct net *net = file->f_dentry->d_sb->s_fs_info; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn); } @@ -1071,8 +1068,7 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size, static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) { ssize_t rv; - struct net *net = file->f_dentry->d_sb->s_fs_info; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); mutex_lock(&nfsd_mutex); rv = __write_recoverydir(file, buf, size, nn); @@ -1102,8 +1098,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) */ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) { - struct net *net = file->f_dentry->d_sb->s_fs_info; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); if (size > 0) { switch(buf[0]) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 989129e2d6ea..0a82e3c033ee 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -930,7 +930,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, unsigned long *cnt, int *stablep) { struct svc_export *exp; - struct dentry *dentry; struct inode *inode; mm_segment_t oldfs; __be32 err = 0; @@ -949,8 +948,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, */ current->flags |= PF_LESS_THROTTLE; - dentry = file->f_path.dentry; - inode = dentry->d_inode; + inode = file_inode(file); exp = fhp->fh_export; use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp); @@ -1819,10 +1817,12 @@ struct readdir_data { int full; }; -static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, - loff_t offset, u64 ino, unsigned int d_type) +static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { - struct readdir_data *buf = __buf; + struct readdir_data *buf = + container_of(ctx, struct readdir_data, ctx); struct buffered_dirent *de = (void *)(buf->dirent + buf->used); unsigned int reclen; @@ -1842,7 +1842,7 @@ static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, return 0; } -static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func, +static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, struct readdir_cd *cdp, loff_t *offsetp) { struct buffered_dirent *de; @@ -1926,7 +1926,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func, */ __be32 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, - struct readdir_cd *cdp, filldir_t func) + struct readdir_cd *cdp, nfsd_filldir_t func) { __be32 err; struct file *file; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index c2ff3f14e5f6..b1796d6ee538 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -36,7 +36,7 @@ /* * Callback function for readdir */ -typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); +typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned); /* nfsd/vfs.c */ int nfsd_racache_init(int); @@ -95,7 +95,7 @@ __be32 nfsd_rename(struct svc_rqst *, __be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type, char *name, int len); __be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *, - loff_t *, struct readdir_cd *, filldir_t); + loff_t *, struct readdir_cd *, nfsd_filldir_t); __be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, struct kstatfs *, int access); diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 9d7e2b9659cb..6ffd220eb14d 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -20,25 +20,24 @@ #if defined(CONFIG_INOTIFY_USER) || defined(CONFIG_FANOTIFY) -static int show_fdinfo(struct seq_file *m, struct file *f, - int (*show)(struct seq_file *m, struct fsnotify_mark *mark)) +static void show_fdinfo(struct seq_file *m, struct file *f, + void (*show)(struct seq_file *m, + struct fsnotify_mark *mark)) { struct fsnotify_group *group = f->private_data; struct fsnotify_mark *mark; - int ret = 0; mutex_lock(&group->mark_mutex); list_for_each_entry(mark, &group->marks_list, g_list) { - ret = show(m, mark); - if (ret) + show(m, mark); + if (seq_has_overflowed(m)) break; } mutex_unlock(&group->mark_mutex); - return ret; } #if defined(CONFIG_EXPORTFS) -static int show_mark_fhandle(struct seq_file *m, struct inode *inode) +static void show_mark_fhandle(struct seq_file *m, struct inode *inode) { struct { struct file_handle handle; @@ -52,71 +51,62 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode) ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0); if ((ret == FILEID_INVALID) || (ret < 0)) { WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); - return 0; + return; } f.handle.handle_type = ret; f.handle.handle_bytes = size * sizeof(u32); - ret = seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:", - f.handle.handle_bytes, f.handle.handle_type); + seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:", + f.handle.handle_bytes, f.handle.handle_type); for (i = 0; i < f.handle.handle_bytes; i++) - ret |= seq_printf(m, "%02x", (int)f.handle.f_handle[i]); - - return ret; + seq_printf(m, "%02x", (int)f.handle.f_handle[i]); } #else -static int show_mark_fhandle(struct seq_file *m, struct inode *inode) +static void show_mark_fhandle(struct seq_file *m, struct inode *inode) { - return 0; } #endif #ifdef CONFIG_INOTIFY_USER -static int inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) +static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) { struct inotify_inode_mark *inode_mark; struct inode *inode; - int ret = 0; if (!(mark->flags & (FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_INODE))) - return 0; + return; inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark); inode = igrab(mark->i.inode); if (inode) { - ret = seq_printf(m, "inotify wd:%x ino:%lx sdev:%x " - "mask:%x ignored_mask:%x ", - inode_mark->wd, inode->i_ino, - inode->i_sb->s_dev, - mark->mask, mark->ignored_mask); - ret |= show_mark_fhandle(m, inode); - ret |= seq_putc(m, '\n'); + seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ", + inode_mark->wd, inode->i_ino, inode->i_sb->s_dev, + mark->mask, mark->ignored_mask); + show_mark_fhandle(m, inode); + seq_putc(m, '\n'); iput(inode); } - - return ret; } -int inotify_show_fdinfo(struct seq_file *m, struct file *f) +void inotify_show_fdinfo(struct seq_file *m, struct file *f) { - return show_fdinfo(m, f, inotify_fdinfo); + show_fdinfo(m, f, inotify_fdinfo); } #endif /* CONFIG_INOTIFY_USER */ #ifdef CONFIG_FANOTIFY -static int fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) +static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) { unsigned int mflags = 0; struct inode *inode; - int ret = 0; if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) - return 0; + return; if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) mflags |= FAN_MARK_IGNORED_SURV_MODIFY; @@ -124,26 +114,22 @@ static int fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) { inode = igrab(mark->i.inode); if (!inode) - goto out; - ret = seq_printf(m, "fanotify ino:%lx sdev:%x " - "mflags:%x mask:%x ignored_mask:%x ", - inode->i_ino, inode->i_sb->s_dev, - mflags, mark->mask, mark->ignored_mask); - ret |= show_mark_fhandle(m, inode); - ret |= seq_putc(m, '\n'); + return; + seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ", + inode->i_ino, inode->i_sb->s_dev, + mflags, mark->mask, mark->ignored_mask); + show_mark_fhandle(m, inode); + seq_putc(m, '\n'); iput(inode); } else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT) { struct mount *mnt = real_mount(mark->m.mnt); - ret = seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x " - "ignored_mask:%x\n", mnt->mnt_id, mflags, - mark->mask, mark->ignored_mask); + seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n", + mnt->mnt_id, mflags, mark->mask, mark->ignored_mask); } -out: - return ret; } -int fanotify_show_fdinfo(struct seq_file *m, struct file *f) +void fanotify_show_fdinfo(struct seq_file *m, struct file *f) { struct fsnotify_group *group = f->private_data; unsigned int flags = 0; @@ -169,7 +155,7 @@ int fanotify_show_fdinfo(struct seq_file *m, struct file *f) seq_printf(m, "fanotify flags:%x event-flags:%x\n", flags, group->fanotify_data.f_flags); - return show_fdinfo(m, f, fanotify_fdinfo); + show_fdinfo(m, f, fanotify_fdinfo); } #endif /* CONFIG_FANOTIFY */ diff --git a/fs/notify/fdinfo.h b/fs/notify/fdinfo.h index 556afda990e9..9664c4904d6b 100644 --- a/fs/notify/fdinfo.h +++ b/fs/notify/fdinfo.h @@ -10,11 +10,11 @@ struct file; #ifdef CONFIG_PROC_FS #ifdef CONFIG_INOTIFY_USER -extern int inotify_show_fdinfo(struct seq_file *m, struct file *f); +void inotify_show_fdinfo(struct seq_file *m, struct file *f); #endif #ifdef CONFIG_FANOTIFY -extern int fanotify_show_fdinfo(struct seq_file *m, struct file *f); +void fanotify_show_fdinfo(struct seq_file *m, struct file *f); #endif #else /* CONFIG_PROC_FS */ diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 89326acd4561..41e39102743a 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -63,14 +63,14 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ - hlist_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); - list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &alias->d_subdirs, d_child) { if (!child->d_inode) continue; diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 436f36037e09..b3973c2fd190 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -111,8 +111,8 @@ static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent, unsigned long dent_ino; int uname_len; - ntfs_debug("Looking up %s in directory inode 0x%lx.", - dent->d_name.name, dir_ino->i_ino); + ntfs_debug("Looking up %pd in directory inode 0x%lx.", + dent, dir_ino->i_ino); /* Convert the name of the dentry to Unicode. */ uname_len = ntfs_nlstoucs(vol, dent->d_name.name, dent->d_name.len, &uname); diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index e2e05a106beb..4fda7a5f3088 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -172,7 +172,7 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, struct dentry *dentry; spin_lock(&inode->i_lock); - hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) { trace_ocfs2_find_local_alias(dentry->d_name.len, @@ -251,8 +251,8 @@ int ocfs2_dentry_attach_lock(struct dentry *dentry, if (dl) { mlog_bug_on_msg(dl->dl_parent_blkno != parent_blkno, - " \"%.*s\": old parent: %llu, new: %llu\n", - dentry->d_name.len, dentry->d_name.name, + " \"%pd\": old parent: %llu, new: %llu\n", + dentry, (unsigned long long)parent_blkno, (unsigned long long)dl->dl_parent_blkno); return 0; @@ -277,8 +277,8 @@ int ocfs2_dentry_attach_lock(struct dentry *dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno); mlog_bug_on_msg(dl->dl_parent_blkno != parent_blkno, - " \"%.*s\": old parent: %llu, new: %llu\n", - dentry->d_name.len, dentry->d_name.name, + " \"%pd\": old parent: %llu, new: %llu\n", + dentry, (unsigned long long)parent_blkno, (unsigned long long)dl->dl_parent_blkno); @@ -406,17 +406,15 @@ static void ocfs2_dentry_iput(struct dentry *dentry, struct inode *inode) if (inode) ino = (unsigned long long)OCFS2_I(inode)->ip_blkno; mlog(ML_ERROR, "Dentry is missing cluster lock. " - "inode: %llu, d_flags: 0x%x, d_name: %.*s\n", - ino, dentry->d_flags, dentry->d_name.len, - dentry->d_name.name); + "inode: %llu, d_flags: 0x%x, d_name: %pd\n", + ino, dentry->d_flags, dentry); } goto out; } - mlog_bug_on_msg(dl->dl_count == 0, "dentry: %.*s, count: %u\n", - dentry->d_name.len, dentry->d_name.name, - dl->dl_count); + mlog_bug_on_msg(dl->dl_count == 0, "dentry: %pd, count: %u\n", + dentry, dl->dl_count); ocfs2_dentry_lock_put(OCFS2_SB(dentry->d_sb), dl); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index e6dc0288dbb9..79d56dc981bc 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -2073,10 +2073,12 @@ struct ocfs2_empty_dir_priv { unsigned seen_other; unsigned dx_dir; }; -static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len, - loff_t pos, u64 ino, unsigned type) +static int ocfs2_empty_dir_filldir(struct dir_context *ctx, const char *name, + int name_len, loff_t pos, u64 ino, + unsigned type) { - struct ocfs2_empty_dir_priv *p = priv; + struct ocfs2_empty_dir_priv *p = + container_of(ctx, struct ocfs2_empty_dir_priv, ctx); /* * Check the positions of "." and ".." records to be sure diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 09b7d9dac71d..57c40e34f56f 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -565,8 +565,8 @@ static int dlmfs_unlink(struct inode *dir, * to acquire a lock, this basically destroys our lockres. */ status = user_dlm_destroy_lock(&DLMFS_I(inode)->ip_lockres); if (status < 0) { - mlog(ML_ERROR, "unlink %.*s, error %d from destroy\n", - dentry->d_name.len, dentry->d_name.name, status); + mlog(ML_ERROR, "unlink %pd, error %d from destroy\n", + dentry, status); goto bail; } status = simple_unlink(dir, dentry); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 953f4eb75fa7..1c423af04c69 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3750,8 +3750,7 @@ static int ocfs2_dentry_convert_worker(struct ocfs2_lock_res *lockres, break; spin_unlock(&dentry_attach_lock); - mlog(0, "d_delete(%.*s);\n", dentry->d_name.len, - dentry->d_name.name); + mlog(0, "d_delete(%pd);\n", dentry); /* * The following dcache calls may do an diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index a9b76de46047..ca3431ee7f24 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -80,6 +80,8 @@ struct ocfs2_inode_info */ tid_t i_sync_tid; tid_t i_datasync_tid; + + struct dquot *i_dquot[MAXQUOTAS]; }; /* diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 4b0c68849b36..4f502382180f 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1982,10 +1982,12 @@ struct ocfs2_orphan_filldir_priv { struct ocfs2_super *osb; }; -static int ocfs2_orphan_filldir(void *priv, const char *name, int name_len, - loff_t pos, u64 ino, unsigned type) +static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name, + int name_len, loff_t pos, u64 ino, + unsigned type) { - struct ocfs2_orphan_filldir_priv *p = priv; + struct ocfs2_orphan_filldir_priv *p = + container_of(ctx, struct ocfs2_orphan_filldir_priv, ctx); struct inode *iter; if (name_len == 1 && !strncmp(".", name, 1)) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 8e3ac25efb9f..83723179e1ec 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -143,6 +143,11 @@ static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend); static int ocfs2_enable_quotas(struct ocfs2_super *osb); static void ocfs2_disable_quotas(struct ocfs2_super *osb); +static struct dquot **ocfs2_get_dquots(struct inode *inode) +{ + return OCFS2_I(inode)->i_dquot; +} + static const struct super_operations ocfs2_sops = { .statfs = ocfs2_statfs, .alloc_inode = ocfs2_alloc_inode, @@ -155,6 +160,7 @@ static const struct super_operations ocfs2_sops = { .show_options = ocfs2_show_options, .quota_read = ocfs2_quota_read, .quota_write = ocfs2_quota_write, + .get_dquots = ocfs2_get_dquots, }; enum { @@ -563,6 +569,7 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb) oi->i_sync_tid = 0; oi->i_datasync_tid = 0; + memset(&oi->i_dquot, 0, sizeof(oi->i_dquot)); jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode); return &oi->vfs_inode; @@ -2074,6 +2081,7 @@ static int ocfs2_initialize_super(struct super_block *sb, sb->s_export_op = &ocfs2_export_ops; sb->s_qcop = &ocfs2_quotactl_ops; sb->dq_op = &ocfs2_quota_operations; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; sb->s_xattr = ocfs2_xattr_handlers; sb->s_time_gran = 1; sb->s_flags |= MS_NOATIME; diff --git a/fs/open.c b/fs/open.c index de92c13b58be..b1bf3d542d5d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -516,7 +516,7 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) int err = -EBADF; if (f.file) { - audit_inode(NULL, f.file->f_path.dentry, 0); + audit_file(f.file); err = chmod_common(&f.file->f_path, mode); fdput(f); } @@ -642,7 +642,7 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) error = mnt_want_write_file(f.file); if (error) goto out_fput; - audit_inode(NULL, f.file->f_path.dentry, 0); + audit_file(f.file); error = chown_common(&f.file->f_path, user, group); mnt_drop_write_file(f.file); out_fput: diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index ab1e3dcbed95..c0205990a9f5 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -180,10 +180,12 @@ static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry) } } -static int ovl_fill_merge(void *buf, const char *name, int namelen, - loff_t offset, u64 ino, unsigned int d_type) +static int ovl_fill_merge(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, + unsigned int d_type) { - struct ovl_readdir_data *rdd = buf; + struct ovl_readdir_data *rdd = + container_of(ctx, struct ovl_readdir_data, ctx); rdd->count++; if (!rdd->is_merge) diff --git a/fs/proc/base.c b/fs/proc/base.c index e7b04a321cc1..590aeda5af12 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2792,7 +2792,7 @@ retry: int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct tgid_iter iter; - struct pid_namespace *ns = file->f_dentry->d_sb->s_fs_info; + struct pid_namespace *ns = file_inode(file)->i_sb->s_fs_info; loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) @@ -3098,7 +3098,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. */ - ns = file->f_dentry->d_sb->s_fs_info; + ns = inode->i_sb->s_fs_info; tid = (int)file->f_version; file->f_version = 0; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index e11d7c590bb0..8e5ad83b629a 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -53,7 +53,8 @@ static int seq_show(struct seq_file *m, void *v) (long long)file->f_pos, f_flags, real_mount(file->f_path.mnt)->mnt_id); if (file->f_op->show_fdinfo) - ret = file->f_op->show_fdinfo(m, file); + file->f_op->show_fdinfo(m, file); + ret = seq_has_overflowed(m); fput(file); } diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index fafb7a02a5d6..50416602774d 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -36,6 +36,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/uaccess.h> +#include <linux/syslog.h> #include "internal.h" @@ -120,6 +121,18 @@ static const struct seq_operations pstore_ftrace_seq_ops = { .show = pstore_ftrace_seq_show, }; +static int pstore_check_syslog_permissions(struct pstore_private *ps) +{ + switch (ps->type) { + case PSTORE_TYPE_DMESG: + case PSTORE_TYPE_CONSOLE: + return check_syslog_permissions(SYSLOG_ACTION_READ_ALL, + SYSLOG_FROM_READER); + default: + return 0; + } +} + static ssize_t pstore_file_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -138,6 +151,10 @@ static int pstore_file_open(struct inode *inode, struct file *file) int err; const struct seq_operations *sops = NULL; + err = pstore_check_syslog_permissions(ps); + if (err) + return err; + if (ps->type == PSTORE_TYPE_FTRACE) sops = &pstore_ftrace_seq_ops; @@ -174,6 +191,11 @@ static const struct file_operations pstore_file_operations = { static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = dentry->d_inode->i_private; + int err; + + err = pstore_check_syslog_permissions(p); + if (err) + return err; if (p->psi->erase) p->psi->erase(p->type, p->id, p->count, diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 3b5744306ed8..ec881b312700 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -135,25 +135,27 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, return prz; } -static void ramoops_read_kmsg_hdr(char *buffer, struct timespec *time, +static int ramoops_read_kmsg_hdr(char *buffer, struct timespec *time, bool *compressed) { char data_type; + int header_length = 0; - if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n", - &time->tv_sec, &time->tv_nsec, &data_type) == 3) { + if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n%n", &time->tv_sec, + &time->tv_nsec, &data_type, &header_length) == 3) { if (data_type == 'C') *compressed = true; else *compressed = false; - } else if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu\n", - &time->tv_sec, &time->tv_nsec) == 2) { + } else if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu\n%n", + &time->tv_sec, &time->tv_nsec, &header_length) == 2) { *compressed = false; } else { time->tv_sec = 0; time->tv_nsec = 0; *compressed = false; } + return header_length; } static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, @@ -165,6 +167,7 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, ssize_t ecc_notice_size; struct ramoops_context *cxt = psi->data; struct persistent_ram_zone *prz; + int header_length; prz = ramoops_get_next_prz(cxt->przs, &cxt->dump_read_cnt, cxt->max_dump_cnt, id, type, @@ -178,7 +181,13 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, if (!prz) return 0; + if (!persistent_ram_old(prz)) + return 0; + size = persistent_ram_old_size(prz); + header_length = ramoops_read_kmsg_hdr(persistent_ram_old(prz), time, + compressed); + size -= header_length; /* ECC correction notice */ ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0); @@ -187,8 +196,7 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, if (*buf == NULL) return -ENOMEM; - memcpy(*buf, persistent_ram_old(prz), size); - ramoops_read_kmsg_hdr(*buf, time, compressed); + memcpy(*buf, (char *)persistent_ram_old(prz) + header_length, size); persistent_ram_ecc_string(prz, *buf + size, ecc_notice_size + 1); return size + ecc_notice_size; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 6b4527216a7f..8f0acef3d184 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -893,6 +893,11 @@ out: } EXPORT_SYMBOL(dqget); +static inline struct dquot **i_dquot(struct inode *inode) +{ + return inode->i_sb->s_op->get_dquots(inode); +} + static int dqinit_needed(struct inode *inode, int type) { int cnt; @@ -900,9 +905,9 @@ static int dqinit_needed(struct inode *inode, int type) if (IS_NOQUOTA(inode)) return 0; if (type != -1) - return !inode->i_dquot[type]; + return !i_dquot(inode)[type]; for (cnt = 0; cnt < MAXQUOTAS; cnt++) - if (!inode->i_dquot[cnt]) + if (!i_dquot(inode)[cnt]) return 1; return 0; } @@ -965,9 +970,9 @@ static void add_dquot_ref(struct super_block *sb, int type) static void remove_inode_dquot_ref(struct inode *inode, int type, struct list_head *tofree_head) { - struct dquot *dquot = inode->i_dquot[type]; + struct dquot *dquot = i_dquot(inode)[type]; - inode->i_dquot[type] = NULL; + i_dquot(inode)[type] = NULL; if (!dquot) return; @@ -1402,7 +1407,7 @@ static void __dquot_initialize(struct inode *inode, int type) * we check it without locking here to avoid unnecessary * dqget()/dqput() calls. */ - if (inode->i_dquot[cnt]) + if (i_dquot(inode)[cnt]) continue; init_needed = 1; @@ -1433,8 +1438,8 @@ static void __dquot_initialize(struct inode *inode, int type) /* We could race with quotaon or dqget() could have failed */ if (!got[cnt]) continue; - if (!inode->i_dquot[cnt]) { - inode->i_dquot[cnt] = got[cnt]; + if (!i_dquot(inode)[cnt]) { + i_dquot(inode)[cnt] = got[cnt]; got[cnt] = NULL; /* * Make quota reservation system happy if someone @@ -1442,7 +1447,7 @@ static void __dquot_initialize(struct inode *inode, int type) */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) - dquot_resv_space(inode->i_dquot[cnt], rsv); + dquot_resv_space(i_dquot(inode)[cnt], rsv); } } out_err: @@ -1472,8 +1477,8 @@ static void __dquot_drop(struct inode *inode) spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - put[cnt] = inode->i_dquot[cnt]; - inode->i_dquot[cnt] = NULL; + put[cnt] = i_dquot(inode)[cnt]; + i_dquot(inode)[cnt] = NULL; } spin_unlock(&dq_data_lock); dqput_all(put); @@ -1494,7 +1499,7 @@ void dquot_drop(struct inode *inode) * add quota pointers back anyway. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (inode->i_dquot[cnt]) + if (i_dquot(inode)[cnt]) break; } @@ -1595,7 +1600,7 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots = inode->i_dquot; + struct dquot **dquots = i_dquot(inode); int reserve = flags & DQUOT_SPACE_RESERVE; if (!dquot_active(inode)) { @@ -1643,11 +1648,11 @@ EXPORT_SYMBOL(__dquot_alloc_space); /* * This operation can block, but only after everything is updated */ -int dquot_alloc_inode(const struct inode *inode) +int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots = inode->i_dquot; + struct dquot * const *dquots = i_dquot(inode); if (!dquot_active(inode)) return 0; @@ -1696,14 +1701,14 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&dq_data_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (inode->i_dquot[cnt]) - dquot_claim_reserved_space(inode->i_dquot[cnt], + if (i_dquot(inode)[cnt]) + dquot_claim_reserved_space(i_dquot(inode)[cnt], number); } /* Update inode bytes */ inode_claim_rsv_space(inode, number); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(inode->i_dquot); + mark_all_dquot_dirty(i_dquot(inode)); srcu_read_unlock(&dquot_srcu, index); return 0; } @@ -1725,14 +1730,14 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&dq_data_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (inode->i_dquot[cnt]) - dquot_reclaim_reserved_space(inode->i_dquot[cnt], + if (i_dquot(inode)[cnt]) + dquot_reclaim_reserved_space(i_dquot(inode)[cnt], number); } /* Update inode bytes */ inode_reclaim_rsv_space(inode, number); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(inode->i_dquot); + mark_all_dquot_dirty(i_dquot(inode)); srcu_read_unlock(&dquot_srcu, index); return; } @@ -1745,7 +1750,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots = inode->i_dquot; + struct dquot **dquots = i_dquot(inode); int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!dquot_active(inode)) { @@ -1784,11 +1789,11 @@ EXPORT_SYMBOL(__dquot_free_space); /* * This operation can block, but only after everything is updated */ -void dquot_free_inode(const struct inode *inode) +void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots = inode->i_dquot; + struct dquot * const *dquots = i_dquot(inode); int index; if (!dquot_active(inode)) @@ -1865,7 +1870,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; - transfer_from[cnt] = inode->i_dquot[cnt]; + transfer_from[cnt] = i_dquot(inode)[cnt]; ret = check_idq(transfer_to[cnt], 1, &warn_to[cnt]); if (ret) goto over_quota; @@ -1901,7 +1906,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) dquot_incr_space(transfer_to[cnt], cur_space); dquot_resv_space(transfer_to[cnt], rsv_space); - inode->i_dquot[cnt] = transfer_to[cnt]; + i_dquot(inode)[cnt] = transfer_to[cnt]; } spin_unlock(&dq_data_lock); @@ -2743,8 +2748,8 @@ static int __init dquot_init(void) for (i = 0; i < nr_hash; i++) INIT_HLIST_HEAD(dquot_hash + i); - printk("Dquot-cache hash table entries: %ld (order %ld, %ld bytes)\n", - nr_hash, order, (PAGE_SIZE << order)); + pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld," + " %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); register_shrinker(&dqcache_shrinker); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 75621649dbd7..2aa4151f99d2 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -47,8 +47,11 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd, static void quota_sync_one(struct super_block *sb, void *arg) { - if (sb->s_qcop && sb->s_qcop->quota_sync) - sb->s_qcop->quota_sync(sb, *(int *)arg); + int type = *(int *)arg; + + if (sb->s_qcop && sb->s_qcop->quota_sync && + (sb->s_quota_types & (1 << type))) + sb->s_qcop->quota_sync(sb, type); } static int quota_sync_all(int type) @@ -297,8 +300,14 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, if (type >= (XQM_COMMAND(cmd) ? XQM_MAXQUOTAS : MAXQUOTAS)) return -EINVAL; + /* + * Quota not supported on this fs? Check this before s_quota_types + * since they needn't be set if quota is not supported at all. + */ if (!sb->s_qcop) return -ENOSYS; + if (!(sb->s_quota_types & (1 << type))) + return -EINVAL; ret = check_quotactl_permission(sb, type, cmd, id); if (ret < 0) diff --git a/fs/readdir.c b/fs/readdir.c index 33fd92208cb7..ced679179cac 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -74,10 +74,11 @@ struct readdir_callback { int result; }; -static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int fillonedir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { - struct readdir_callback *buf = (struct readdir_callback *) __buf; + struct readdir_callback *buf = + container_of(ctx, struct readdir_callback, ctx); struct old_linux_dirent __user * dirent; unsigned long d_ino; @@ -148,11 +149,12 @@ struct getdents_callback { int error; }; -static int filldir(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { struct linux_dirent __user * dirent; - struct getdents_callback * buf = (struct getdents_callback *) __buf; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); unsigned long d_ino; int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); @@ -232,11 +234,12 @@ struct getdents_callback64 { int error; }; -static int filldir64(void * __buf, const char * name, int namlen, loff_t offset, - u64 ino, unsigned int d_type) +static int filldir64(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { struct linux_dirent64 __user *dirent; - struct getdents_callback64 * buf = (struct getdents_callback64 *) __buf; + struct getdents_callback64 *buf = + container_of(ctx, struct getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 1894d96ccb7c..bb79cddf0a1f 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -97,6 +97,10 @@ struct reiserfs_inode_info { #ifdef CONFIG_REISERFS_FS_XATTR struct rw_semaphore i_xattr_sem; #endif +#ifdef CONFIG_QUOTA + struct dquot *i_dquot[MAXQUOTAS]; +#endif + struct inode vfs_inode; }; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index f1376c92cf74..ea63ab13ef92 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -594,6 +594,10 @@ static struct inode *reiserfs_alloc_inode(struct super_block *sb) return NULL; atomic_set(&ei->openers, 0); mutex_init(&ei->tailpack); +#ifdef CONFIG_QUOTA + memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); +#endif + return &ei->vfs_inode; } @@ -750,6 +754,11 @@ static ssize_t reiserfs_quota_write(struct super_block *, int, const char *, size_t, loff_t); static ssize_t reiserfs_quota_read(struct super_block *, int, char *, size_t, loff_t); + +static struct dquot **reiserfs_get_dquots(struct inode *inode) +{ + return REISERFS_I(inode)->i_dquot; +} #endif static const struct super_operations reiserfs_sops = { @@ -768,6 +777,7 @@ static const struct super_operations reiserfs_sops = { #ifdef CONFIG_QUOTA .quota_read = reiserfs_quota_read, .quota_write = reiserfs_quota_write, + .get_dquots = reiserfs_get_dquots, #endif }; @@ -1633,6 +1643,7 @@ static int read_super_block(struct super_block *s, int offset) #ifdef CONFIG_QUOTA s->s_qcop = &reiserfs_qctl_operations; s->dq_op = &reiserfs_quota_operations; + s->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; #endif /* diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 7c36898af402..04b06146bae2 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -188,10 +188,11 @@ struct reiserfs_dentry_buf { }; static int -fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset, - u64 ino, unsigned int d_type) +fill_with_dentries(struct dir_context *ctx, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) { - struct reiserfs_dentry_buf *dbuf = buf; + struct reiserfs_dentry_buf *dbuf = + container_of(ctx, struct reiserfs_dentry_buf, ctx); struct dentry *dentry; WARN_ON_ONCE(!mutex_is_locked(&dbuf->xadir->d_inode->i_mutex)); @@ -209,9 +210,9 @@ fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset, } else if (!dentry->d_inode) { /* A directory entry exists, but no file? */ reiserfs_error(dentry->d_sb, "xattr-20003", - "Corrupted directory: xattr %s listed but " - "not found for file %s.\n", - dentry->d_name.name, dbuf->xadir->d_name.name); + "Corrupted directory: xattr %pd listed but " + "not found for file %pd.\n", + dentry, dbuf->xadir); dput(dentry); return -EIO; } @@ -824,10 +825,12 @@ struct listxattr_buf { struct dentry *dentry; }; -static int listxattr_filler(void *buf, const char *name, int namelen, - loff_t offset, u64 ino, unsigned int d_type) +static int listxattr_filler(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, + unsigned int d_type) { - struct listxattr_buf *b = (struct listxattr_buf *)buf; + struct listxattr_buf *b = + container_of(ctx, struct listxattr_buf, ctx); size_t size; if (name[0] != '.' || diff --git a/fs/seq_file.c b/fs/seq_file.c index 3857b720cb1b..353948ba1c5b 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -16,17 +16,6 @@ #include <asm/uaccess.h> #include <asm/page.h> - -/* - * seq_files have a buffer which can may overflow. When this happens a larger - * buffer is reallocated and all the data will be printed again. - * The overflow state is true when m->count == m->size. - */ -static bool seq_overflow(struct seq_file *m) -{ - return m->count == m->size; -} - static void seq_set_overflow(struct seq_file *m) { m->count = m->size; @@ -124,7 +113,7 @@ static int traverse(struct seq_file *m, loff_t offset) error = 0; m->count = 0; } - if (seq_overflow(m)) + if (seq_has_overflowed(m)) goto Eoverflow; if (pos + m->count > offset) { m->from = offset - pos; @@ -267,7 +256,7 @@ Fill: break; } err = m->op->show(m, p); - if (seq_overflow(m) || err) { + if (seq_has_overflowed(m) || err) { m->count = offs; if (likely(err <= 0)) break; diff --git a/fs/signalfd.c b/fs/signalfd.c index 424b7b65321f..7e412ad74836 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -230,7 +230,7 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, } #ifdef CONFIG_PROC_FS -static int signalfd_show_fdinfo(struct seq_file *m, struct file *f) +static void signalfd_show_fdinfo(struct seq_file *m, struct file *f) { struct signalfd_ctx *ctx = f->private_data; sigset_t sigmask; @@ -238,8 +238,6 @@ static int signalfd_show_fdinfo(struct seq_file *m, struct file *f) sigmask = ctx->sigmask; signotset(&sigmask); render_sigset_t(m, "sigmask:\t", &sigmask); - - return 0; } #endif diff --git a/fs/sync.c b/fs/sync.c index bdc729d80e5e..01d9f18a70b5 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -154,7 +154,7 @@ SYSCALL_DEFINE1(syncfs, int, fd) if (!f.file) return -EBADF; - sb = f.file->f_dentry->d_sb; + sb = f.file->f_path.dentry->d_sb; down_read(&sb->s_umount); ret = sync_filesystem(sb); diff --git a/fs/timerfd.c b/fs/timerfd.c index b46ffa94372a..b94fa6c3c6eb 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -288,7 +288,7 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count, } #ifdef CONFIG_PROC_FS -static int timerfd_show(struct seq_file *m, struct file *file) +static void timerfd_show(struct seq_file *m, struct file *file) { struct timerfd_ctx *ctx = file->private_data; struct itimerspec t; @@ -298,18 +298,19 @@ static int timerfd_show(struct seq_file *m, struct file *file) t.it_interval = ktime_to_timespec(ctx->tintv); spin_unlock_irq(&ctx->wqh.lock); - return seq_printf(m, - "clockid: %d\n" - "ticks: %llu\n" - "settime flags: 0%o\n" - "it_value: (%llu, %llu)\n" - "it_interval: (%llu, %llu)\n", - ctx->clockid, (unsigned long long)ctx->ticks, - ctx->settime_flags, - (unsigned long long)t.it_value.tv_sec, - (unsigned long long)t.it_value.tv_nsec, - (unsigned long long)t.it_interval.tv_sec, - (unsigned long long)t.it_interval.tv_nsec); + seq_printf(m, + "clockid: %d\n" + "ticks: %llu\n" + "settime flags: 0%o\n" + "it_value: (%llu, %llu)\n" + "it_interval: (%llu, %llu)\n", + ctx->clockid, + (unsigned long long)ctx->ticks, + ctx->settime_flags, + (unsigned long long)t.it_value.tv_sec, + (unsigned long long)t.it_value.tv_nsec, + (unsigned long long)t.it_interval.tv_sec, + (unsigned long long)t.it_interval.tv_nsec); } #else #define timerfd_show NULL diff --git a/fs/udf/super.c b/fs/udf/super.c index e229315bbf7a..3ccb2f11fc76 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -2082,12 +2082,12 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) mutex_init(&sbi->s_alloc_mutex); if (!udf_parse_options((char *)options, &uopt, false)) - goto error_out; + goto parse_options_failure; if (uopt.flags & (1 << UDF_FLAG_UTF8) && uopt.flags & (1 << UDF_FLAG_NLS_MAP)) { udf_err(sb, "utf8 cannot be combined with iocharset\n"); - goto error_out; + goto parse_options_failure; } #ifdef CONFIG_UDF_NLS if ((uopt.flags & (1 << UDF_FLAG_NLS_MAP)) && !uopt.nls_map) { @@ -2237,8 +2237,8 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) return 0; error_out: - if (sbi->s_vat_inode) - iput(sbi->s_vat_inode); + iput(sbi->s_vat_inode); +parse_options_failure: #ifdef CONFIG_UDF_NLS if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) unload_nls(sbi->s_nls_map); @@ -2291,8 +2291,7 @@ static void udf_put_super(struct super_block *sb) sbi = UDF_SB(sb); - if (sbi->s_vat_inode) - iput(sbi->s_vat_inode); + iput(sbi->s_vat_inode); #ifdef CONFIG_UDF_NLS if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) unload_nls(sbi->s_nls_map); diff --git a/fs/xattr.c b/fs/xattr.c index 64e83efb742d..4ef698549e31 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -405,16 +405,14 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, const void __user *,value, size_t, size, int, flags) { struct fd f = fdget(fd); - struct dentry *dentry; int error = -EBADF; if (!f.file) return error; - dentry = f.file->f_path.dentry; - audit_inode(NULL, dentry, 0); + audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { - error = setxattr(dentry, name, value, size, flags); + error = setxattr(f.file->f_path.dentry, name, value, size, flags); mnt_drop_write_file(f.file); } fdput(f); @@ -509,7 +507,7 @@ SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, if (!f.file) return error; - audit_inode(NULL, f.file->f_path.dentry, 0); + audit_file(f.file); error = getxattr(f.file->f_path.dentry, name, value, size); fdput(f); return error; @@ -590,7 +588,7 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) if (!f.file) return error; - audit_inode(NULL, f.file->f_path.dentry, 0); + audit_file(f.file); error = listxattr(f.file->f_path.dentry, list, size); fdput(f); return error; @@ -651,16 +649,14 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { struct fd f = fdget(fd); - struct dentry *dentry; int error = -EBADF; if (!f.file) return error; - dentry = f.file->f_path.dentry; - audit_inode(NULL, dentry, 0); + audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { - error = removexattr(dentry, name); + error = removexattr(f.file->f_path.dentry, name); mnt_drop_write_file(f.file); } fdput(f); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 9f622feda6a4..206b97fd1d8a 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1425,6 +1425,7 @@ xfs_fs_fill_super( sb->s_export_op = &xfs_export_operations; #ifdef CONFIG_XFS_QUOTA sb->s_qcop = &xfs_quotactl_operations; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif sb->s_op = &xfs_super_operations; diff --git a/include/linux/audit.h b/include/linux/audit.h index e58fe7df8b9c..0c04917c2f12 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -130,6 +130,7 @@ extern void audit_putname(struct filename *name); #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); +extern void __audit_file(const struct file *); extern void __audit_inode_child(const struct inode *parent, const struct dentry *dentry, const unsigned char type); @@ -183,6 +184,11 @@ static inline void audit_inode(struct filename *name, __audit_inode(name, dentry, flags); } } +static inline void audit_file(struct file *file) +{ + if (unlikely(!audit_dummy_context())) + __audit_file(file); +} static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { @@ -357,6 +363,9 @@ static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int parent) { } +static inline void audit_file(struct file *file) +{ +} static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9f96b25965c2..641e56494a92 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -393,8 +393,8 @@ struct css_set { * struct cftype: handler definitions for cgroup control files * * When reading/writing to a file: - * - the cgroup to use is file->f_dentry->d_parent->d_fsdata - * - the 'cftype' of the file is file->f_dentry->d_fsdata + * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata + * - the 'cftype' of the file is file->f_path.dentry->d_fsdata */ /* cftype->flags */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index b2a2a08523bf..5a813988e6d4 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -124,15 +124,15 @@ struct dentry { void *d_fsdata; /* fs-specific data */ struct list_head d_lru; /* LRU list */ + struct list_head d_child; /* child of parent list */ + struct list_head d_subdirs; /* our children */ /* - * d_child and d_rcu can share memory + * d_alias and d_rcu can share memory */ union { - struct list_head d_child; /* child of parent list */ + struct hlist_node d_alias; /* inode alias list */ struct rcu_head d_rcu; } d_u; - struct list_head d_subdirs; /* our children */ - struct hlist_node d_alias; /* inode alias list */ }; /* @@ -230,7 +230,6 @@ extern seqlock_t rename_lock; */ extern void d_instantiate(struct dentry *, struct inode *); extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); -extern struct dentry * d_materialise_unique(struct dentry *, struct inode *); extern int d_instantiate_no_diralias(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 4d0b4d1aa132..d84f8c254a87 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -92,8 +92,8 @@ struct dentry *debugfs_create_regset32(const char *name, umode_t mode, struct dentry *parent, struct debugfs_regset32 *regset); -int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, - int nregs, void __iomem *base, char *prefix); +void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, + int nregs, void __iomem *base, char *prefix); struct dentry *debugfs_create_u32_array(const char *name, umode_t mode, struct dentry *parent, @@ -233,10 +233,9 @@ static inline struct dentry *debugfs_create_regset32(const char *name, return ERR_PTR(-ENODEV); } -static inline int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, +static inline void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix) { - return 0; } static inline bool debugfs_initialized(void) diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 860313a33a43..87f14e90e984 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -33,7 +33,8 @@ #define F2FS_META_INO(sbi) (sbi->meta_ino_num) /* This flag is used by node and meta inodes, and by recovery */ -#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO) +#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO) +#define GFP_F2FS_HIGH_ZERO (GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM) /* * For further optimization on multi-head logs, on-disk layout supports maximum @@ -170,14 +171,12 @@ struct f2fs_extent { #define F2FS_INLINE_XATTR 0x01 /* file inline xattr flag */ #define F2FS_INLINE_DATA 0x02 /* file inline data flag */ +#define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */ +#define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */ #define MAX_INLINE_DATA (sizeof(__le32) * (DEF_ADDRS_PER_INODE - \ F2FS_INLINE_XATTR_ADDRS - 1)) -#define INLINE_DATA_OFFSET (PAGE_CACHE_SIZE - sizeof(struct node_footer) -\ - sizeof(__le32) * (DEF_ADDRS_PER_INODE + \ - DEF_NIDS_PER_INODE - 1)) - struct f2fs_inode { __le16 i_mode; /* file mode */ __u8 i_advise; /* file hints */ @@ -435,6 +434,24 @@ struct f2fs_dentry_block { __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; +/* for inline dir */ +#define NR_INLINE_DENTRY (MAX_INLINE_DATA * BITS_PER_BYTE / \ + ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ + BITS_PER_BYTE + 1)) +#define INLINE_DENTRY_BITMAP_SIZE ((NR_INLINE_DENTRY + \ + BITS_PER_BYTE - 1) / BITS_PER_BYTE) +#define INLINE_RESERVED_SIZE (MAX_INLINE_DATA - \ + ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ + NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE)) + +/* inline directory entry structure */ +struct f2fs_inline_dentry { + __u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE]; + __u8 reserved[INLINE_RESERVED_SIZE]; + struct f2fs_dir_entry dentry[NR_INLINE_DENTRY]; + __u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN]; +} __packed; + /* file types used in inode_info->flags */ enum { F2FS_FT_UNKNOWN, diff --git a/include/linux/fs.h b/include/linux/fs.h index 9ab779e8a63c..bb29b02d9bb6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -606,9 +606,6 @@ struct inode { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct file_lock *i_flock; struct address_space i_data; -#ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; -#endif struct list_head i_devices; union { struct pipe_inode_info *i_pipe; @@ -789,7 +786,6 @@ struct file { struct rcu_head fu_rcuhead; } f_u; struct path f_path; -#define f_dentry f_path.dentry struct inode *f_inode; /* cached value */ const struct file_operations *f_op; @@ -1224,6 +1220,7 @@ struct super_block { struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; + unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; @@ -1467,7 +1464,10 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. */ -typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned); +struct dir_context; +typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, + unsigned); + struct dir_context { const filldir_t actor; loff_t pos; @@ -1513,7 +1513,7 @@ struct file_operations { int (*setlease)(struct file *, long, struct file_lock **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); - int (*show_fdinfo)(struct seq_file *m, struct file *f); + void (*show_fdinfo)(struct seq_file *m, struct file *f); }; struct inode_operations { @@ -1577,7 +1577,9 @@ struct super_operations { void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); + int (*freeze_super) (struct super_block *); int (*freeze_fs) (struct super_block *); + int (*thaw_super) (struct super_block *); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); @@ -1590,6 +1592,7 @@ struct super_operations { #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); + struct dquot **(*get_dquots)(struct inode *); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, int); @@ -2786,6 +2789,11 @@ static inline void inode_has_no_xattr(struct inode *inode) inode->i_flags |= S_NOSEC; } +static inline bool is_root_inode(struct inode *inode) +{ + return inode == inode->i_sb->s_root->d_inode; +} + static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) diff --git a/include/linux/lockd/debug.h b/include/linux/lockd/debug.h index 257d3779f2ab..0ca8109934e4 100644 --- a/include/linux/lockd/debug.h +++ b/include/linux/lockd/debug.h @@ -17,12 +17,8 @@ * Enable lockd debugging. * Requires RPC_DEBUG. */ -#ifdef RPC_DEBUG -# define LOCKD_DEBUG 1 -#endif - #undef ifdebug -#if defined(RPC_DEBUG) && defined(LOCKD_DEBUG) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define ifdebug(flag) if (unlikely(nlm_debug & NLMDBG_##flag)) #else # define ifdebug(flag) if (0) diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 356acc2846fd..022b761dbf0a 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -490,6 +490,8 @@ enum { /* nfs42 */ NFSPROC4_CLNT_SEEK, + NFSPROC4_CLNT_ALLOCATE, + NFSPROC4_CLNT_DEALLOCATE, }; /* nfs41 types */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c72d1ad41ad4..6d627b92df53 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -163,7 +163,7 @@ struct nfs_inode { */ __be32 cookieverf[2]; - unsigned long npages; + unsigned long nrequests; struct nfs_mds_commit_info commit_info; /* Open contexts for shared mmap writes */ @@ -520,7 +520,7 @@ extern void nfs_commit_free(struct nfs_commit_data *data); static inline int nfs_have_writebacks(struct inode *inode) { - return NFS_I(inode)->npages != 0; + return NFS_I(inode)->nrequests != 0; } /* diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a32ba0d7a98f..1e37fbb78f7a 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -231,5 +231,7 @@ struct nfs_server { #define NFS_CAP_ATOMIC_OPEN_V1 (1U << 17) #define NFS_CAP_SECURITY_LABEL (1U << 18) #define NFS_CAP_SEEK (1U << 19) +#define NFS_CAP_ALLOCATE (1U << 20) +#define NFS_CAP_DEALLOCATE (1U << 21) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 47ebb4fafd87..467c84efb596 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1243,6 +1243,20 @@ nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) #endif /* CONFIG_NFS_V4_1 */ #ifdef CONFIG_NFS_V4_2 +struct nfs42_falloc_args { + struct nfs4_sequence_args seq_args; + + struct nfs_fh *falloc_fh; + nfs4_stateid falloc_stateid; + u64 falloc_offset; + u64 falloc_length; +}; + +struct nfs42_falloc_res { + struct nfs4_sequence_res seq_res; + unsigned int status; +}; + struct nfs42_seek_args { struct nfs4_sequence_args seq_args; diff --git a/include/linux/quota.h b/include/linux/quota.h index 80d345a3524c..50978b781a19 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -56,6 +56,11 @@ enum quota_type { PRJQUOTA = 2, /* element used for project quotas */ }; +/* Masks for quota types when used as a bitmask */ +#define QTYPE_MASK_USR (1 << USRQUOTA) +#define QTYPE_MASK_GRP (1 << GRPQUOTA) +#define QTYPE_MASK_PRJ (1 << PRJQUOTA) + typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */ typedef long long qsize_t; /* Type in which we store sizes */ diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 1d3eee594cd6..f23538a6e411 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -64,10 +64,10 @@ void dquot_destroy(struct dquot *dquot); int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags); void __dquot_free_space(struct inode *inode, qsize_t number, int flags); -int dquot_alloc_inode(const struct inode *inode); +int dquot_alloc_inode(struct inode *inode); int dquot_claim_space_nodirty(struct inode *inode, qsize_t number); -void dquot_free_inode(const struct inode *inode); +void dquot_free_inode(struct inode *inode); void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number); int dquot_disable(struct super_block *sb, int type, unsigned int flags); @@ -213,12 +213,12 @@ static inline void dquot_drop(struct inode *inode) { } -static inline int dquot_alloc_inode(const struct inode *inode) +static inline int dquot_alloc_inode(struct inode *inode) { return 0; } -static inline void dquot_free_inode(const struct inode *inode) +static inline void dquot_free_inode(struct inode *inode) { } diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 52e0097f61f0..cf6a9daaaf6d 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -43,6 +43,21 @@ struct seq_operations { #define SEQ_SKIP 1 /** + * seq_has_overflowed - check if the buffer has overflowed + * @m: the seq_file handle + * + * seq_files have a buffer which may overflow. When this happens a larger + * buffer is reallocated and all the data will be printed again. + * The overflow state is true when m->count == m->size. + * + * Returns true if the buffer received more than it can hold. + */ +static inline bool seq_has_overflowed(struct seq_file *m) +{ + return m->count == m->size; +} + +/** * seq_get_buf - get buffer to write arbitrary data to * @m: the seq_file handle * @bufp: the beginning of the buffer is stored here diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 8e030075fe79..a7cbb570cc5c 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -53,7 +53,7 @@ struct rpc_cred { struct rcu_head cr_rcu; struct rpc_auth * cr_auth; const struct rpc_credops *cr_ops; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) unsigned long cr_magic; /* 0x0f4aa4f0 */ #endif unsigned long cr_expire; /* when to gc */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 70736b98c721..d86acc63b25f 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -63,6 +63,9 @@ struct rpc_clnt { struct rpc_rtt cl_rtt_default; struct rpc_timeout cl_timeout_default; const struct rpc_program *cl_program; +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) + struct dentry *cl_debugfs; /* debugfs directory */ +#endif }; /* @@ -176,5 +179,6 @@ size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); int rpc_localaddr(struct rpc_clnt *, struct sockaddr *, size_t); +const char *rpc_proc_name(const struct rpc_task *task); #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h index 9385bd74c860..c57d8ea0716c 100644 --- a/include/linux/sunrpc/debug.h +++ b/include/linux/sunrpc/debug.h @@ -10,22 +10,10 @@ #include <uapi/linux/sunrpc/debug.h> - -/* - * Enable RPC debugging/profiling. - */ -#ifdef CONFIG_SUNRPC_DEBUG -#define RPC_DEBUG -#endif -#ifdef CONFIG_TRACEPOINTS -#define RPC_TRACEPOINTS -#endif -/* #define RPC_PROFILE */ - /* * Debugging macros etc */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) extern unsigned int rpc_debug; extern unsigned int nfs_debug; extern unsigned int nfsd_debug; @@ -36,7 +24,7 @@ extern unsigned int nlm_debug; #define dprintk_rcu(args...) dfprintk_rcu(FACILITY, ## args) #undef ifdebug -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define ifdebug(fac) if (unlikely(rpc_debug & RPCDBG_##fac)) # define dfprintk(fac, args...) \ @@ -65,9 +53,55 @@ extern unsigned int nlm_debug; /* * Sysctl interface for RPC debugging */ -#ifdef RPC_DEBUG + +struct rpc_clnt; +struct rpc_xprt; + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) void rpc_register_sysctl(void); void rpc_unregister_sysctl(void); +int sunrpc_debugfs_init(void); +void sunrpc_debugfs_exit(void); +int rpc_clnt_debugfs_register(struct rpc_clnt *); +void rpc_clnt_debugfs_unregister(struct rpc_clnt *); +int rpc_xprt_debugfs_register(struct rpc_xprt *); +void rpc_xprt_debugfs_unregister(struct rpc_xprt *); +#else +static inline int +sunrpc_debugfs_init(void) +{ + return 0; +} + +static inline void +sunrpc_debugfs_exit(void) +{ + return; +} + +static inline int +rpc_clnt_debugfs_register(struct rpc_clnt *clnt) +{ + return 0; +} + +static inline void +rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt) +{ + return; +} + +static inline int +rpc_xprt_debugfs_register(struct rpc_xprt *xprt) +{ + return 0; +} + +static inline void +rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt) +{ + return; +} #endif #endif /* _LINUX_SUNRPC_DEBUG_H_ */ diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index 1565bbe86d51..eecb5a71e6c0 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -27,10 +27,13 @@ #include <linux/seq_file.h> #include <linux/ktime.h> +#include <linux/spinlock.h> #define RPC_IOSTATS_VERS "1.0" struct rpc_iostats { + spinlock_t om_lock; + /* * These counters give an idea about how many request * transmissions are required, on average, to complete that diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 1a8959944c5f..5f1e6bd4c316 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -79,7 +79,7 @@ struct rpc_task { unsigned short tk_flags; /* misc flags */ unsigned short tk_timeouts; /* maj timeouts */ -#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) unsigned short tk_pid; /* debugging aid */ #endif unsigned char tk_priority : 2,/* Task priority */ @@ -187,7 +187,7 @@ struct rpc_wait_queue { unsigned char nr; /* # tasks remaining for cookie */ unsigned short qlen; /* total # tasks waiting in queue */ struct rpc_timer timer_list; -#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) const char * name; #endif }; @@ -237,7 +237,7 @@ void rpc_free(void *); int rpciod_up(void); void rpciod_down(void); int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct net; void rpc_show_tasks(struct net *); #endif @@ -251,7 +251,7 @@ static inline int rpc_wait_for_completion_task(struct rpc_task *task) return __rpc_wait_for_completion_task(task, NULL); } -#if defined(RPC_DEBUG) || defined (RPC_TRACEPOINTS) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static inline const char * rpc_qname(const struct rpc_wait_queue *q) { return ((q && q->name) ? q->name : "unknown"); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index cf391eef2e6d..9d27ac45b909 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -239,6 +239,9 @@ struct rpc_xprt { struct net *xprt_net; const char *servername; const char *address_strings[RPC_DISPLAY_MAX]; +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) + struct dentry *debugfs; /* debugfs directory */ +#endif }; #if defined(CONFIG_SUNRPC_BACKCHANNEL) diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 1ad36cc25b2e..7591788e9fbf 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -17,6 +17,65 @@ void cleanup_socket_xprt(void); #define RPC_DEF_MIN_RESVPORT (665U) #define RPC_DEF_MAX_RESVPORT (1023U) +struct sock_xprt { + struct rpc_xprt xprt; + + /* + * Network layer + */ + struct socket * sock; + struct sock * inet; + + /* + * State of TCP reply receive + */ + __be32 tcp_fraghdr, + tcp_xid, + tcp_calldir; + + u32 tcp_offset, + tcp_reclen; + + unsigned long tcp_copied, + tcp_flags; + + /* + * Connection of transports + */ + struct delayed_work connect_worker; + struct sockaddr_storage srcaddr; + unsigned short srcport; + + /* + * UDP socket buffer size parameters + */ + size_t rcvsize, + sndsize; + + /* + * Saved socket callback addresses + */ + void (*old_data_ready)(struct sock *); + void (*old_state_change)(struct sock *); + void (*old_write_space)(struct sock *); + void (*old_error_report)(struct sock *); +}; + +/* + * TCP receive state flags + */ +#define TCP_RCV_LAST_FRAG (1UL << 0) +#define TCP_RCV_COPY_FRAGHDR (1UL << 1) +#define TCP_RCV_COPY_XID (1UL << 2) +#define TCP_RCV_COPY_DATA (1UL << 3) +#define TCP_RCV_READ_CALLDIR (1UL << 4) +#define TCP_RCV_COPY_CALLDIR (1UL << 5) + +/* + * TCP RPC flags + */ +#define TCP_RPC_REPLY (1UL << 6) + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ diff --git a/include/linux/syslog.h b/include/linux/syslog.h index 98a3153c0f96..4b7b875a7ce1 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -49,4 +49,13 @@ int do_syslog(int type, char __user *buf, int count, bool from_file); +#ifdef CONFIG_PRINTK +int check_syslog_permissions(int type, bool from_file); +#else +static inline int check_syslog_permissions(int type, bool from_file) +{ + return 0; +} +#endif + #endif /* _LINUX_SYSLOG_H */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 9b1581414cd4..bd8569a14c4a 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -31,6 +31,7 @@ struct iov_iter { size_t count; union { const struct iovec *iov; + const struct kvec *kvec; const struct bio_vec *bvec; }; unsigned long nr_segs; @@ -82,10 +83,13 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i); size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); +size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); +void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *iov, + unsigned long nr_segs, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, @@ -123,6 +127,8 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } +size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); +size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index cc0c18827602..f2f0fa3bb150 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -72,7 +72,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) return ret; } -int +void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *proto); diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index adc1fa3dd7ab..cdc920b4c4c2 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -38,8 +38,8 @@ struct nf_conntrack_l3proto { const struct nf_conntrack_tuple *orig); /* Print out the per-protocol part of the tuple. */ - int (*print_tuple)(struct seq_file *s, - const struct nf_conntrack_tuple *); + void (*print_tuple)(struct seq_file *s, + const struct nf_conntrack_tuple *); /* * Called before tracking. diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 4c8d573830b7..1f7061313d54 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -56,11 +56,11 @@ struct nf_conntrack_l4proto { u_int8_t pf, unsigned int hooknum); /* Print out the per-protocol part of the tuple. Return like seq_* */ - int (*print_tuple)(struct seq_file *s, - const struct nf_conntrack_tuple *); + void (*print_tuple)(struct seq_file *s, + const struct nf_conntrack_tuple *); /* Print out the private part of the conntrack. */ - int (*print_conntrack)(struct seq_file *s, struct nf_conn *); + void (*print_conntrack)(struct seq_file *s, struct nf_conn *); /* Return the array of timeouts for this protocol. */ unsigned int *(*get_timeouts)(struct net *net); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 1fef3e6e9436..171ca4ff6d99 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -6,6 +6,8 @@ #include <linux/sunrpc/sched.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/svc.h> +#include <linux/sunrpc/xprtsock.h> #include <net/tcp_states.h> #include <linux/net.h> #include <linux/tracepoint.h> @@ -306,6 +308,164 @@ DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection); DEFINE_RPC_SOCKET_EVENT(rpc_socket_close); DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown); +DECLARE_EVENT_CLASS(rpc_xprt_event, + TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), + + TP_ARGS(xprt, xid, status), + + TP_STRUCT__entry( + __field(__be32, xid) + __field(int, status) + __string(addr, xprt->address_strings[RPC_DISPLAY_ADDR]) + __string(port, xprt->address_strings[RPC_DISPLAY_PORT]) + ), + + TP_fast_assign( + __entry->xid = xid; + __entry->status = status; + __assign_str(addr, xprt->address_strings[RPC_DISPLAY_ADDR]); + __assign_str(port, xprt->address_strings[RPC_DISPLAY_PORT]); + ), + + TP_printk("peer=[%s]:%s xid=0x%x status=%d", __get_str(addr), + __get_str(port), be32_to_cpu(__entry->xid), + __entry->status) +); + +DEFINE_EVENT(rpc_xprt_event, xprt_lookup_rqst, + TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), + TP_ARGS(xprt, xid, status)); + +DEFINE_EVENT(rpc_xprt_event, xprt_transmit, + TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), + TP_ARGS(xprt, xid, status)); + +DEFINE_EVENT(rpc_xprt_event, xprt_complete_rqst, + TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), + TP_ARGS(xprt, xid, status)); + +TRACE_EVENT(xs_tcp_data_ready, + TP_PROTO(struct rpc_xprt *xprt, int err, unsigned int total), + + TP_ARGS(xprt, err, total), + + TP_STRUCT__entry( + __field(int, err) + __field(unsigned int, total) + __string(addr, xprt ? xprt->address_strings[RPC_DISPLAY_ADDR] : + "(null)") + __string(port, xprt ? xprt->address_strings[RPC_DISPLAY_PORT] : + "(null)") + ), + + TP_fast_assign( + __entry->err = err; + __entry->total = total; + __assign_str(addr, xprt ? + xprt->address_strings[RPC_DISPLAY_ADDR] : "(null)"); + __assign_str(port, xprt ? + xprt->address_strings[RPC_DISPLAY_PORT] : "(null)"); + ), + + TP_printk("peer=[%s]:%s err=%d total=%u", __get_str(addr), + __get_str(port), __entry->err, __entry->total) +); + +#define rpc_show_sock_xprt_flags(flags) \ + __print_flags(flags, "|", \ + { TCP_RCV_LAST_FRAG, "TCP_RCV_LAST_FRAG" }, \ + { TCP_RCV_COPY_FRAGHDR, "TCP_RCV_COPY_FRAGHDR" }, \ + { TCP_RCV_COPY_XID, "TCP_RCV_COPY_XID" }, \ + { TCP_RCV_COPY_DATA, "TCP_RCV_COPY_DATA" }, \ + { TCP_RCV_READ_CALLDIR, "TCP_RCV_READ_CALLDIR" }, \ + { TCP_RCV_COPY_CALLDIR, "TCP_RCV_COPY_CALLDIR" }, \ + { TCP_RPC_REPLY, "TCP_RPC_REPLY" }) + +TRACE_EVENT(xs_tcp_data_recv, + TP_PROTO(struct sock_xprt *xs), + + TP_ARGS(xs), + + TP_STRUCT__entry( + __string(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR]) + __string(port, xs->xprt.address_strings[RPC_DISPLAY_PORT]) + __field(__be32, xid) + __field(unsigned long, flags) + __field(unsigned long, copied) + __field(unsigned int, reclen) + __field(unsigned long, offset) + ), + + TP_fast_assign( + __assign_str(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR]); + __assign_str(port, xs->xprt.address_strings[RPC_DISPLAY_PORT]); + __entry->xid = xs->tcp_xid; + __entry->flags = xs->tcp_flags; + __entry->copied = xs->tcp_copied; + __entry->reclen = xs->tcp_reclen; + __entry->offset = xs->tcp_offset; + ), + + TP_printk("peer=[%s]:%s xid=0x%x flags=%s copied=%lu reclen=%u offset=%lu", + __get_str(addr), __get_str(port), be32_to_cpu(__entry->xid), + rpc_show_sock_xprt_flags(__entry->flags), + __entry->copied, __entry->reclen, __entry->offset) +); + +TRACE_EVENT(svc_recv, + TP_PROTO(struct svc_rqst *rqst, int status), + + TP_ARGS(rqst, status), + + TP_STRUCT__entry( + __field(struct sockaddr *, addr) + __field(__be32, xid) + __field(int, status) + ), + + TP_fast_assign( + __entry->addr = (struct sockaddr *)&rqst->rq_addr; + __entry->xid = status > 0 ? rqst->rq_xid : 0; + __entry->status = status; + ), + + TP_printk("addr=%pIScp xid=0x%x status=%d", __entry->addr, + be32_to_cpu(__entry->xid), __entry->status) +); + +DECLARE_EVENT_CLASS(svc_rqst_status, + + TP_PROTO(struct svc_rqst *rqst, int status), + + TP_ARGS(rqst, status), + + TP_STRUCT__entry( + __field(struct sockaddr *, addr) + __field(__be32, xid) + __field(int, dropme) + __field(int, status) + ), + + TP_fast_assign( + __entry->addr = (struct sockaddr *)&rqst->rq_addr; + __entry->xid = rqst->rq_xid; + __entry->dropme = (int)rqst->rq_dropme; + __entry->status = status; + ), + + TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d", + __entry->addr, be32_to_cpu(__entry->xid), __entry->dropme, + __entry->status) +); + +DEFINE_EVENT(svc_rqst_status, svc_process, + TP_PROTO(struct svc_rqst *rqst, int status), + TP_ARGS(rqst, status)); + +DEFINE_EVENT(svc_rqst_status, svc_send, + TP_PROTO(struct svc_rqst *rqst, int status), + TP_ARGS(rqst, status)); + #endif /* _TRACE_SUNRPC_H */ #include <trace/define_trace.h> diff --git a/include/uapi/linux/dlmconstants.h b/include/uapi/linux/dlmconstants.h index 47bf08dc7566..2857bdc5b27b 100644 --- a/include/uapi/linux/dlmconstants.h +++ b/include/uapi/linux/dlmconstants.h @@ -114,7 +114,7 @@ * * DLM_LKF_ORPHAN * - * not yet implemented + * Acquire an orphan lock. * * DLM_LKF_ALTPR * diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h index a6f453c740b8..1fdc95bb2375 100644 --- a/include/uapi/linux/nfsd/debug.h +++ b/include/uapi/linux/nfsd/debug.h @@ -15,7 +15,7 @@ * Enable debugging for nfsd. * Requires RPC_DEBUG. */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define NFSD_DEBUG 1 #endif diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 4fcf39af1776..7635a1cf99f3 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -990,7 +990,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, goto out_fput; } info = MQUEUE_I(inode); - audit_inode(NULL, f.file->f_path.dentry, 0); + audit_file(f.file); if (unlikely(!(f.file->f_mode & FMODE_WRITE))) { ret = -EBADF; @@ -1106,7 +1106,7 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr, goto out_fput; } info = MQUEUE_I(inode); - audit_inode(NULL, f.file->f_path.dentry, 0); + audit_file(f.file); if (unlikely(!(f.file->f_mode & FMODE_READ))) { ret = -EBADF; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index e420a0c41b5f..c75522a83678 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1897,6 +1897,11 @@ out: audit_copy_inode(n, dentry, inode); } +void __audit_file(const struct file *file) +{ + __audit_inode(NULL, file->f_path.dentry, 0); +} + /** * __audit_inode_child - collect inode info for created/removed objects * @parent: inode of dentry parent @@ -2373,7 +2378,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, ax->d.next = context->aux; context->aux = (void *)ax; - dentry = dget(bprm->file->f_dentry); + dentry = dget(bprm->file->f_path.dentry); get_vfs_caps_from_disk(dentry, &vcaps); dput(dentry); diff --git a/kernel/events/core.c b/kernel/events/core.c index 3e19d3ebc29c..113b837470cd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -614,7 +614,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, if (!f.file) return -EBADF; - css = css_tryget_online_from_dir(f.file->f_dentry, + css = css_tryget_online_from_dir(f.file->f_path.dentry, &perf_event_cgrp_subsys); if (IS_ERR(css)) { ret = PTR_ERR(css); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 218ea26d75b8..ea27c019655a 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -477,7 +477,7 @@ static int syslog_action_restricted(int type) type != SYSLOG_ACTION_SIZE_BUFFER; } -static int check_syslog_permissions(int type, bool from_file) +int check_syslog_permissions(int type, bool from_file) { /* * If this is from /proc/kmsg and we've already opened it, then we've diff --git a/kernel/taskstats.c b/kernel/taskstats.c index b312fcc73024..670fff88a961 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -459,7 +459,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) stats = nla_data(na); memset(stats, 0, sizeof(*stats)); - rc = cgroupstats_build(stats, f.file->f_dentry); + rc = cgroupstats_build(stats, f.file->f_path.dentry); if (rc < 0) { nlmsg_free(rep_skb); goto err; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 92f4a6cee172..426962b04183 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6417,7 +6417,7 @@ static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t m int ret; /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); if (WARN_ON_ONCE(parent != trace_instance_dir)) return -ENOENT; @@ -6444,7 +6444,7 @@ static int instance_rmdir(struct inode *inode, struct dentry *dentry) int ret; /* Paranoid: Make sure the parent is the "instances" directory */ - parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); + parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); if (WARN_ON_ONCE(parent != trace_instance_dir)) return -ENOENT; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 0cc51edde3a8..1b0df1e504f0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -461,7 +461,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file) if (dir) { spin_lock(&dir->d_lock); /* probably unneeded */ - list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) { + list_for_each_entry(child, &dir->d_subdirs, d_child) { if (child->d_inode) /* probably unneeded */ child->d_inode->i_private = NULL; } diff --git a/mm/iov_iter.c b/mm/iov_iter.c index e34a3cb6aad6..a1599ca4ab0e 100644 --- a/mm/iov_iter.c +++ b/mm/iov_iter.c @@ -3,95 +3,136 @@ #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/vmalloc.h> - -static size_t copy_to_iter_iovec(void *from, size_t bytes, struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - left = __copy_to_user(buf, from, copy); - copy -= left; - skip += copy; - from += copy; - bytes -= copy; - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_to_user(buf, from, copy); - copy -= left; - skip = copy; - from += copy; - bytes -= copy; - } - - if (skip == iov->iov_len) { - iov++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; -} - -static size_t copy_from_iter_iovec(void *to, size_t bytes, struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - left = __copy_from_user(to, buf, copy); - copy -= left; - skip += copy; - to += copy; - bytes -= copy; - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_from_user(to, buf, copy); - copy -= left; - skip = copy; - to += copy; - bytes -= copy; - } - - if (skip == iov->iov_len) { - iov++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; +#include <net/checksum.h> + +#define iterate_iovec(i, n, __v, __p, skip, STEP) { \ + size_t left; \ + size_t wanted = n; \ + __p = i->iov; \ + __v.iov_len = min(n, __p->iov_len - skip); \ + if (likely(__v.iov_len)) { \ + __v.iov_base = __p->iov_base + skip; \ + left = (STEP); \ + __v.iov_len -= left; \ + skip += __v.iov_len; \ + n -= __v.iov_len; \ + } else { \ + left = 0; \ + } \ + while (unlikely(!left && n)) { \ + __p++; \ + __v.iov_len = min(n, __p->iov_len); \ + if (unlikely(!__v.iov_len)) \ + continue; \ + __v.iov_base = __p->iov_base; \ + left = (STEP); \ + __v.iov_len -= left; \ + skip = __v.iov_len; \ + n -= __v.iov_len; \ + } \ + n = wanted - n; \ +} + +#define iterate_kvec(i, n, __v, __p, skip, STEP) { \ + size_t wanted = n; \ + __p = i->kvec; \ + __v.iov_len = min(n, __p->iov_len - skip); \ + if (likely(__v.iov_len)) { \ + __v.iov_base = __p->iov_base + skip; \ + (void)(STEP); \ + skip += __v.iov_len; \ + n -= __v.iov_len; \ + } \ + while (unlikely(n)) { \ + __p++; \ + __v.iov_len = min(n, __p->iov_len); \ + if (unlikely(!__v.iov_len)) \ + continue; \ + __v.iov_base = __p->iov_base; \ + (void)(STEP); \ + skip = __v.iov_len; \ + n -= __v.iov_len; \ + } \ + n = wanted; \ +} + +#define iterate_bvec(i, n, __v, __p, skip, STEP) { \ + size_t wanted = n; \ + __p = i->bvec; \ + __v.bv_len = min_t(size_t, n, __p->bv_len - skip); \ + if (likely(__v.bv_len)) { \ + __v.bv_page = __p->bv_page; \ + __v.bv_offset = __p->bv_offset + skip; \ + (void)(STEP); \ + skip += __v.bv_len; \ + n -= __v.bv_len; \ + } \ + while (unlikely(n)) { \ + __p++; \ + __v.bv_len = min_t(size_t, n, __p->bv_len); \ + if (unlikely(!__v.bv_len)) \ + continue; \ + __v.bv_page = __p->bv_page; \ + __v.bv_offset = __p->bv_offset; \ + (void)(STEP); \ + skip = __v.bv_len; \ + n -= __v.bv_len; \ + } \ + n = wanted; \ +} + +#define iterate_all_kinds(i, n, v, I, B, K) { \ + size_t skip = i->iov_offset; \ + if (unlikely(i->type & ITER_BVEC)) { \ + const struct bio_vec *bvec; \ + struct bio_vec v; \ + iterate_bvec(i, n, v, bvec, skip, (B)) \ + } else if (unlikely(i->type & ITER_KVEC)) { \ + const struct kvec *kvec; \ + struct kvec v; \ + iterate_kvec(i, n, v, kvec, skip, (K)) \ + } else { \ + const struct iovec *iov; \ + struct iovec v; \ + iterate_iovec(i, n, v, iov, skip, (I)) \ + } \ +} + +#define iterate_and_advance(i, n, v, I, B, K) { \ + size_t skip = i->iov_offset; \ + if (unlikely(i->type & ITER_BVEC)) { \ + const struct bio_vec *bvec; \ + struct bio_vec v; \ + iterate_bvec(i, n, v, bvec, skip, (B)) \ + if (skip == bvec->bv_len) { \ + bvec++; \ + skip = 0; \ + } \ + i->nr_segs -= bvec - i->bvec; \ + i->bvec = bvec; \ + } else if (unlikely(i->type & ITER_KVEC)) { \ + const struct kvec *kvec; \ + struct kvec v; \ + iterate_kvec(i, n, v, kvec, skip, (K)) \ + if (skip == kvec->iov_len) { \ + kvec++; \ + skip = 0; \ + } \ + i->nr_segs -= kvec - i->kvec; \ + i->kvec = kvec; \ + } else { \ + const struct iovec *iov; \ + struct iovec v; \ + iterate_iovec(i, n, v, iov, skip, (I)) \ + if (skip == iov->iov_len) { \ + iov++; \ + skip = 0; \ + } \ + i->nr_segs -= iov - i->iov; \ + i->iov = iov; \ + } \ + i->count -= n; \ + i->iov_offset = skip; \ } static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes, @@ -256,134 +297,6 @@ done: return wanted - bytes; } -static size_t zero_iovec(size_t bytes, struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - left = __clear_user(buf, copy); - copy -= left; - skip += copy; - bytes -= copy; - - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __clear_user(buf, copy); - copy -= left; - skip = copy; - bytes -= copy; - } - - if (skip == iov->iov_len) { - iov++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; -} - -static size_t __iovec_copy_from_user_inatomic(char *vaddr, - const struct iovec *iov, size_t base, size_t bytes) -{ - size_t copied = 0, left = 0; - - while (bytes) { - char __user *buf = iov->iov_base + base; - int copy = min(bytes, iov->iov_len - base); - - base = 0; - left = __copy_from_user_inatomic(vaddr, buf, copy); - copied += copy; - bytes -= copy; - vaddr += copy; - iov++; - - if (unlikely(left)) - break; - } - return copied - left; -} - -/* - * Copy as much as we can into the page and return the number of bytes which - * were successfully copied. If a fault is encountered then return the number of - * bytes which were copied. - */ -static size_t copy_from_user_atomic_iovec(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - kaddr = kmap_atomic(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap_atomic(kaddr); - - return copied; -} - -static void advance_iovec(struct iov_iter *i, size_t bytes) -{ - BUG_ON(i->count < bytes); - - if (likely(i->nr_segs == 1)) { - i->iov_offset += bytes; - i->count -= bytes; - } else { - const struct iovec *iov = i->iov; - size_t base = i->iov_offset; - unsigned long nr_segs = i->nr_segs; - - /* - * The !iov->iov_len check ensures we skip over unlikely - * zero-length segments (without overruning the iovec). - */ - while (bytes || unlikely(i->count && !iov->iov_len)) { - int copy; - - copy = min(bytes, iov->iov_len - base); - BUG_ON(!i->count || i->count < copy); - i->count -= copy; - bytes -= copy; - base += copy; - if (iov->iov_len == base) { - iov++; - nr_segs--; - base = 0; - } - } - i->iov = iov; - i->iov_offset = base; - i->nr_segs = nr_segs; - } -} - /* * Fault in the first iovec of the given iov_iter, to a maximum length * of bytes. Returns 0 on success, or non-zero if the memory could not be @@ -395,7 +308,7 @@ static void advance_iovec(struct iov_iter *i, size_t bytes) */ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { - if (!(i->type & ITER_BVEC)) { + if (!(i->type & (ITER_BVEC|ITER_KVEC))) { char __user *buf = i->iov->iov_base + i->iov_offset; bytes = min(bytes, i->iov->iov_len - i->iov_offset); return fault_in_pages_readable(buf, bytes); @@ -404,136 +317,25 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) } EXPORT_SYMBOL(iov_iter_fault_in_readable); -static unsigned long alignment_iovec(const struct iov_iter *i) -{ - const struct iovec *iov = i->iov; - unsigned long res; - size_t size = i->count; - size_t n; - - if (!size) - return 0; - - res = (unsigned long)iov->iov_base + i->iov_offset; - n = iov->iov_len - i->iov_offset; - if (n >= size) - return res | size; - size -= n; - res |= n; - while (size > (++iov)->iov_len) { - res |= (unsigned long)iov->iov_base | iov->iov_len; - size -= iov->iov_len; - } - res |= (unsigned long)iov->iov_base | size; - return res; -} - void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { /* It will get better. Eventually... */ - if (segment_eq(get_fs(), KERNEL_DS)) + if (segment_eq(get_fs(), KERNEL_DS)) { direction |= ITER_KVEC; - i->type = direction; - i->iov = iov; + i->type = direction; + i->kvec = (struct kvec *)iov; + } else { + i->type = direction; + i->iov = iov; + } i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_init); -static ssize_t get_pages_iovec(struct iov_iter *i, - struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start) -{ - size_t offset = i->iov_offset; - const struct iovec *iov = i->iov; - size_t len; - unsigned long addr; - int n; - int res; - - len = iov->iov_len - offset; - if (len > i->count) - len = i->count; - if (len > maxsize) - len = maxsize; - addr = (unsigned long)iov->iov_base + offset; - len += *start = addr & (PAGE_SIZE - 1); - if (len > maxpages * PAGE_SIZE) - len = maxpages * PAGE_SIZE; - addr &= ~(PAGE_SIZE - 1); - n = (len + PAGE_SIZE - 1) / PAGE_SIZE; - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); - if (unlikely(res < 0)) - return res; - return (res == n ? len : res * PAGE_SIZE) - *start; -} - -static ssize_t get_pages_alloc_iovec(struct iov_iter *i, - struct page ***pages, size_t maxsize, - size_t *start) -{ - size_t offset = i->iov_offset; - const struct iovec *iov = i->iov; - size_t len; - unsigned long addr; - void *p; - int n; - int res; - - len = iov->iov_len - offset; - if (len > i->count) - len = i->count; - if (len > maxsize) - len = maxsize; - addr = (unsigned long)iov->iov_base + offset; - len += *start = addr & (PAGE_SIZE - 1); - addr &= ~(PAGE_SIZE - 1); - n = (len + PAGE_SIZE - 1) / PAGE_SIZE; - - p = kmalloc(n * sizeof(struct page *), GFP_KERNEL); - if (!p) - p = vmalloc(n * sizeof(struct page *)); - if (!p) - return -ENOMEM; - - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); - if (unlikely(res < 0)) { - kvfree(p); - return res; - } - *pages = p; - return (res == n ? len : res * PAGE_SIZE) - *start; -} - -static int iov_iter_npages_iovec(const struct iov_iter *i, int maxpages) -{ - size_t offset = i->iov_offset; - size_t size = i->count; - const struct iovec *iov = i->iov; - int npages = 0; - int n; - - for (n = 0; size && n < i->nr_segs; n++, iov++) { - unsigned long addr = (unsigned long)iov->iov_base + offset; - size_t len = iov->iov_len - offset; - offset = 0; - if (unlikely(!len)) /* empty segment */ - continue; - if (len > size) - len = size; - npages += (addr + len + PAGE_SIZE - 1) / PAGE_SIZE - - addr / PAGE_SIZE; - if (npages >= maxpages) /* don't bother going further */ - return maxpages; - size -= len; - offset = 0; - } - return min(npages, maxpages); -} - static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_atomic(page); @@ -555,293 +357,78 @@ static void memzero_page(struct page *page, size_t offset, size_t len) kunmap_atomic(addr); } -static size_t copy_to_iter_bvec(void *from, size_t bytes, struct iov_iter *i) +size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i) { - size_t skip, copy, wanted; - const struct bio_vec *bvec; - + char *from = addr; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; - wanted = bytes; - bvec = i->bvec; - skip = i->iov_offset; - copy = min_t(size_t, bytes, bvec->bv_len - skip); + iterate_and_advance(i, bytes, v, + __copy_to_user(v.iov_base, (from += v.iov_len) - v.iov_len, + v.iov_len), + memcpy_to_page(v.bv_page, v.bv_offset, + (from += v.bv_len) - v.bv_len, v.bv_len), + memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len) + ) - memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy); - skip += copy; - from += copy; - bytes -= copy; - while (bytes) { - bvec++; - copy = min(bytes, (size_t)bvec->bv_len); - memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, copy); - skip = copy; - from += copy; - bytes -= copy; - } - if (skip == bvec->bv_len) { - bvec++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= bvec - i->bvec; - i->bvec = bvec; - i->iov_offset = skip; - return wanted - bytes; + return bytes; } +EXPORT_SYMBOL(copy_to_iter); -static size_t copy_from_iter_bvec(void *to, size_t bytes, struct iov_iter *i) +size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { - size_t skip, copy, wanted; - const struct bio_vec *bvec; - + char *to = addr; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; - wanted = bytes; - bvec = i->bvec; - skip = i->iov_offset; - - copy = min(bytes, bvec->bv_len - skip); + iterate_and_advance(i, bytes, v, + __copy_from_user((to += v.iov_len) - v.iov_len, v.iov_base, + v.iov_len), + memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len), + memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + ) - memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy); - - to += copy; - skip += copy; - bytes -= copy; - - while (bytes) { - bvec++; - copy = min(bytes, (size_t)bvec->bv_len); - memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, copy); - skip = copy; - to += copy; - bytes -= copy; - } - if (skip == bvec->bv_len) { - bvec++; - skip = 0; - } - i->count -= wanted; - i->nr_segs -= bvec - i->bvec; - i->bvec = bvec; - i->iov_offset = skip; - return wanted; -} - -static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, - size_t bytes, struct iov_iter *i) -{ - void *kaddr = kmap_atomic(page); - size_t wanted = copy_to_iter_bvec(kaddr + offset, bytes, i); - kunmap_atomic(kaddr); - return wanted; -} - -static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, - size_t bytes, struct iov_iter *i) -{ - void *kaddr = kmap_atomic(page); - size_t wanted = copy_from_iter_bvec(kaddr + offset, bytes, i); - kunmap_atomic(kaddr); - return wanted; + return bytes; } +EXPORT_SYMBOL(copy_from_iter); -static size_t zero_bvec(size_t bytes, struct iov_iter *i) +size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { - size_t skip, copy, wanted; - const struct bio_vec *bvec; - + char *to = addr; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; - wanted = bytes; - bvec = i->bvec; - skip = i->iov_offset; - copy = min_t(size_t, bytes, bvec->bv_len - skip); - - memzero_page(bvec->bv_page, skip + bvec->bv_offset, copy); - skip += copy; - bytes -= copy; - while (bytes) { - bvec++; - copy = min(bytes, (size_t)bvec->bv_len); - memzero_page(bvec->bv_page, bvec->bv_offset, copy); - skip = copy; - bytes -= copy; - } - if (skip == bvec->bv_len) { - bvec++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= bvec - i->bvec; - i->bvec = bvec; - i->iov_offset = skip; - return wanted - bytes; -} + iterate_and_advance(i, bytes, v, + __copy_from_user_nocache((to += v.iov_len) - v.iov_len, + v.iov_base, v.iov_len), + memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len), + memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + ) -static size_t copy_from_user_bvec(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t left; - const struct bio_vec *bvec; - size_t base = i->iov_offset; - - kaddr = kmap_atomic(page); - for (left = bytes, bvec = i->bvec; left; bvec++, base = 0) { - size_t copy = min(left, bvec->bv_len - base); - if (!bvec->bv_len) - continue; - memcpy_from_page(kaddr + offset, bvec->bv_page, - bvec->bv_offset + base, copy); - offset += copy; - left -= copy; - } - kunmap_atomic(kaddr); return bytes; } - -static void advance_bvec(struct iov_iter *i, size_t bytes) -{ - BUG_ON(i->count < bytes); - - if (likely(i->nr_segs == 1)) { - i->iov_offset += bytes; - i->count -= bytes; - } else { - const struct bio_vec *bvec = i->bvec; - size_t base = i->iov_offset; - unsigned long nr_segs = i->nr_segs; - - /* - * The !iov->iov_len check ensures we skip over unlikely - * zero-length segments (without overruning the iovec). - */ - while (bytes || unlikely(i->count && !bvec->bv_len)) { - int copy; - - copy = min(bytes, bvec->bv_len - base); - BUG_ON(!i->count || i->count < copy); - i->count -= copy; - bytes -= copy; - base += copy; - if (bvec->bv_len == base) { - bvec++; - nr_segs--; - base = 0; - } - } - i->bvec = bvec; - i->iov_offset = base; - i->nr_segs = nr_segs; - } -} - -static unsigned long alignment_bvec(const struct iov_iter *i) -{ - const struct bio_vec *bvec = i->bvec; - unsigned long res; - size_t size = i->count; - size_t n; - - if (!size) - return 0; - - res = bvec->bv_offset + i->iov_offset; - n = bvec->bv_len - i->iov_offset; - if (n >= size) - return res | size; - size -= n; - res |= n; - while (size > (++bvec)->bv_len) { - res |= bvec->bv_offset | bvec->bv_len; - size -= bvec->bv_len; - } - res |= bvec->bv_offset | size; - return res; -} - -static ssize_t get_pages_bvec(struct iov_iter *i, - struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start) -{ - const struct bio_vec *bvec = i->bvec; - size_t len = bvec->bv_len - i->iov_offset; - if (len > i->count) - len = i->count; - if (len > maxsize) - len = maxsize; - /* can't be more than PAGE_SIZE */ - *start = bvec->bv_offset + i->iov_offset; - - get_page(*pages = bvec->bv_page); - - return len; -} - -static ssize_t get_pages_alloc_bvec(struct iov_iter *i, - struct page ***pages, size_t maxsize, - size_t *start) -{ - const struct bio_vec *bvec = i->bvec; - size_t len = bvec->bv_len - i->iov_offset; - if (len > i->count) - len = i->count; - if (len > maxsize) - len = maxsize; - *start = bvec->bv_offset + i->iov_offset; - - *pages = kmalloc(sizeof(struct page *), GFP_KERNEL); - if (!*pages) - return -ENOMEM; - - get_page(**pages = bvec->bv_page); - - return len; -} - -static int iov_iter_npages_bvec(const struct iov_iter *i, int maxpages) -{ - size_t offset = i->iov_offset; - size_t size = i->count; - const struct bio_vec *bvec = i->bvec; - int npages = 0; - int n; - - for (n = 0; size && n < i->nr_segs; n++, bvec++) { - size_t len = bvec->bv_len - offset; - offset = 0; - if (unlikely(!len)) /* empty segment */ - continue; - if (len > size) - len = size; - npages++; - if (npages >= maxpages) /* don't bother going further */ - return maxpages; - size -= len; - offset = 0; - } - return min(npages, maxpages); -} +EXPORT_SYMBOL(copy_from_iter_nocache); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { - if (i->type & ITER_BVEC) - return copy_page_to_iter_bvec(page, offset, bytes, i); - else + if (i->type & (ITER_BVEC|ITER_KVEC)) { + void *kaddr = kmap_atomic(page); + size_t wanted = copy_to_iter(kaddr + offset, bytes, i); + kunmap_atomic(kaddr); + return wanted; + } else return copy_page_to_iter_iovec(page, offset, bytes, i); } EXPORT_SYMBOL(copy_page_to_iter); @@ -849,57 +436,53 @@ EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { - if (i->type & ITER_BVEC) - return copy_page_from_iter_bvec(page, offset, bytes, i); - else + if (i->type & (ITER_BVEC|ITER_KVEC)) { + void *kaddr = kmap_atomic(page); + size_t wanted = copy_from_iter(kaddr + offset, bytes, i); + kunmap_atomic(kaddr); + return wanted; + } else return copy_page_from_iter_iovec(page, offset, bytes, i); } EXPORT_SYMBOL(copy_page_from_iter); -size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i) +size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { - if (i->type & ITER_BVEC) - return copy_to_iter_bvec(addr, bytes, i); - else - return copy_to_iter_iovec(addr, bytes, i); -} -EXPORT_SYMBOL(copy_to_iter); + if (unlikely(bytes > i->count)) + bytes = i->count; -size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - if (i->type & ITER_BVEC) - return copy_from_iter_bvec(addr, bytes, i); - else - return copy_from_iter_iovec(addr, bytes, i); -} -EXPORT_SYMBOL(copy_from_iter); + if (unlikely(!bytes)) + return 0; -size_t iov_iter_zero(size_t bytes, struct iov_iter *i) -{ - if (i->type & ITER_BVEC) { - return zero_bvec(bytes, i); - } else { - return zero_iovec(bytes, i); - } + iterate_and_advance(i, bytes, v, + __clear_user(v.iov_base, v.iov_len), + memzero_page(v.bv_page, v.bv_offset, v.bv_len), + memset(v.iov_base, 0, v.iov_len) + ) + + return bytes; } EXPORT_SYMBOL(iov_iter_zero); size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes) { - if (i->type & ITER_BVEC) - return copy_from_user_bvec(page, i, offset, bytes); - else - return copy_from_user_atomic_iovec(page, i, offset, bytes); + char *kaddr = kmap_atomic(page), *p = kaddr + offset; + iterate_all_kinds(i, bytes, v, + __copy_from_user_inatomic((p += v.iov_len) - v.iov_len, + v.iov_base, v.iov_len), + memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len), + memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + ) + kunmap_atomic(kaddr); + return bytes; } EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); void iov_iter_advance(struct iov_iter *i, size_t size) { - if (i->type & ITER_BVEC) - advance_bvec(i, size); - else - advance_iovec(i, size); + iterate_and_advance(i, size, v, 0, 0, 0) } EXPORT_SYMBOL(iov_iter_advance); @@ -917,12 +500,33 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) } EXPORT_SYMBOL(iov_iter_single_seg_count); +void iov_iter_kvec(struct iov_iter *i, int direction, + const struct kvec *iov, unsigned long nr_segs, + size_t count) +{ + BUG_ON(!(direction & ITER_KVEC)); + i->type = direction; + i->kvec = (struct kvec *)iov; + i->nr_segs = nr_segs; + i->iov_offset = 0; + i->count = count; +} +EXPORT_SYMBOL(iov_iter_kvec); + unsigned long iov_iter_alignment(const struct iov_iter *i) { - if (i->type & ITER_BVEC) - return alignment_bvec(i); - else - return alignment_iovec(i); + unsigned long res = 0; + size_t size = i->count; + + if (!size) + return 0; + + iterate_all_kinds(i, size, v, + (res |= (unsigned long)v.iov_base | v.iov_len, 0), + res |= v.bv_offset | v.bv_len, + res |= (unsigned long)v.iov_base | v.iov_len + ) + return res; } EXPORT_SYMBOL(iov_iter_alignment); @@ -930,29 +534,207 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { - if (i->type & ITER_BVEC) - return get_pages_bvec(i, pages, maxsize, maxpages, start); - else - return get_pages_iovec(i, pages, maxsize, maxpages, start); + if (maxsize > i->count) + maxsize = i->count; + + if (!maxsize) + return 0; + + iterate_all_kinds(i, maxsize, v, ({ + unsigned long addr = (unsigned long)v.iov_base; + size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); + int n; + int res; + + if (len > maxpages * PAGE_SIZE) + len = maxpages * PAGE_SIZE; + addr &= ~(PAGE_SIZE - 1); + n = DIV_ROUND_UP(len, PAGE_SIZE); + res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); + if (unlikely(res < 0)) + return res; + return (res == n ? len : res * PAGE_SIZE) - *start; + 0;}),({ + /* can't be more than PAGE_SIZE */ + *start = v.bv_offset; + get_page(*pages = v.bv_page); + return v.bv_len; + }),({ + return -EFAULT; + }) + ) + return 0; } EXPORT_SYMBOL(iov_iter_get_pages); +static struct page **get_pages_array(size_t n) +{ + struct page **p = kmalloc(n * sizeof(struct page *), GFP_KERNEL); + if (!p) + p = vmalloc(n * sizeof(struct page *)); + return p; +} + ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { - if (i->type & ITER_BVEC) - return get_pages_alloc_bvec(i, pages, maxsize, start); - else - return get_pages_alloc_iovec(i, pages, maxsize, start); + struct page **p; + + if (maxsize > i->count) + maxsize = i->count; + + if (!maxsize) + return 0; + + iterate_all_kinds(i, maxsize, v, ({ + unsigned long addr = (unsigned long)v.iov_base; + size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); + int n; + int res; + + addr &= ~(PAGE_SIZE - 1); + n = DIV_ROUND_UP(len, PAGE_SIZE); + p = get_pages_array(n); + if (!p) + return -ENOMEM; + res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); + if (unlikely(res < 0)) { + kvfree(p); + return res; + } + *pages = p; + return (res == n ? len : res * PAGE_SIZE) - *start; + 0;}),({ + /* can't be more than PAGE_SIZE */ + *start = v.bv_offset; + *pages = p = get_pages_array(1); + if (!p) + return -ENOMEM; + get_page(*p = v.bv_page); + return v.bv_len; + }),({ + return -EFAULT; + }) + ) + return 0; } EXPORT_SYMBOL(iov_iter_get_pages_alloc); +size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, + struct iov_iter *i) +{ + char *to = addr; + __wsum sum, next; + size_t off = 0; + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + sum = *csum; + iterate_and_advance(i, bytes, v, ({ + int err = 0; + next = csum_and_copy_from_user(v.iov_base, + (to += v.iov_len) - v.iov_len, + v.iov_len, 0, &err); + if (!err) { + sum = csum_block_add(sum, next, off); + off += v.iov_len; + } + err ? v.iov_len : 0; + }), ({ + char *p = kmap_atomic(v.bv_page); + next = csum_partial_copy_nocheck(p + v.bv_offset, + (to += v.bv_len) - v.bv_len, + v.bv_len, 0); + kunmap_atomic(p); + sum = csum_block_add(sum, next, off); + off += v.bv_len; + }),({ + next = csum_partial_copy_nocheck(v.iov_base, + (to += v.iov_len) - v.iov_len, + v.iov_len, 0); + sum = csum_block_add(sum, next, off); + off += v.iov_len; + }) + ) + *csum = sum; + return bytes; +} +EXPORT_SYMBOL(csum_and_copy_from_iter); + +size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, + struct iov_iter *i) +{ + char *from = addr; + __wsum sum, next; + size_t off = 0; + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + sum = *csum; + iterate_and_advance(i, bytes, v, ({ + int err = 0; + next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len, + v.iov_base, + v.iov_len, 0, &err); + if (!err) { + sum = csum_block_add(sum, next, off); + off += v.iov_len; + } + err ? v.iov_len : 0; + }), ({ + char *p = kmap_atomic(v.bv_page); + next = csum_partial_copy_nocheck((from += v.bv_len) - v.bv_len, + p + v.bv_offset, + v.bv_len, 0); + kunmap_atomic(p); + sum = csum_block_add(sum, next, off); + off += v.bv_len; + }),({ + next = csum_partial_copy_nocheck((from += v.iov_len) - v.iov_len, + v.iov_base, + v.iov_len, 0); + sum = csum_block_add(sum, next, off); + off += v.iov_len; + }) + ) + *csum = sum; + return bytes; +} +EXPORT_SYMBOL(csum_and_copy_to_iter); + int iov_iter_npages(const struct iov_iter *i, int maxpages) { - if (i->type & ITER_BVEC) - return iov_iter_npages_bvec(i, maxpages); - else - return iov_iter_npages_iovec(i, maxpages); + size_t size = i->count; + int npages = 0; + + if (!size) + return 0; + + iterate_all_kinds(i, size, v, ({ + unsigned long p = (unsigned long)v.iov_base; + npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) + - p / PAGE_SIZE; + if (npages >= maxpages) + return maxpages; + 0;}),({ + npages++; + if (npages >= maxpages) + return maxpages; + }),({ + unsigned long p = (unsigned long)v.iov_base; + npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) + - p / PAGE_SIZE; + if (npages >= maxpages) + return maxpages; + }) + ) + return npages; } EXPORT_SYMBOL(iov_iter_npages); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1869cb64d089..85df503ec023 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4442,7 +4442,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * * DO NOT ADD NEW FILES. */ - name = cfile.file->f_dentry->d_name.name; + name = cfile.file->f_path.dentry->d_name.name; if (!strcmp(name, "memory.usage_in_bytes")) { event->register_event = mem_cgroup_usage_register_event; @@ -4466,7 +4466,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_online_from_dir(cfile.file->f_dentry->d_parent, + cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent, &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 84e7ded04321..e5ee0ca7ae85 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -860,7 +860,6 @@ static int page_action(struct page_state *ps, struct page *p, int count; result = ps->action(p, pfn); - action_result(pfn, ps->msg, result); count = page_count(p) - 1; if (ps->action == me_swapcache_dirty && result == DELAYED) @@ -871,6 +870,7 @@ static int page_action(struct page_state *ps, struct page *p, pfn, ps->msg, count); result = FAILED; } + action_result(pfn, ps->msg, result); /* Could do more checks here if page looks ok */ /* diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index a054fe083431..5c61328b7704 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -56,11 +56,11 @@ static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple, return true; } -static int ipv4_print_tuple(struct seq_file *s, +static void ipv4_print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "src=%pI4 dst=%pI4 ", - &tuple->src.u3.ip, &tuple->dst.u3.ip); + seq_printf(s, "src=%pI4 dst=%pI4 ", + &tuple->src.u3.ip, &tuple->dst.u3.ip); } static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 4c48e434bb1f..a460a87e14f8 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -94,7 +94,7 @@ static void ct_seq_stop(struct seq_file *s, void *v) } #ifdef CONFIG_NF_CONNTRACK_SECMARK -static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) +static void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { int ret; u32 len; @@ -102,17 +102,15 @@ static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) ret = security_secid_to_secctx(ct->secmark, &secctx, &len); if (ret) - return 0; + return; - ret = seq_printf(s, "secctx=%s ", secctx); + seq_printf(s, "secctx=%s ", secctx); security_release_secctx(secctx, len); - return ret; } #else -static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) +static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { - return 0; } #endif @@ -141,47 +139,52 @@ static int ct_seq_show(struct seq_file *s, void *v) NF_CT_ASSERT(l4proto); ret = -ENOSPC; - if (seq_printf(s, "%-8s %u %ld ", - l4proto->name, nf_ct_protonum(ct), - timer_pending(&ct->timeout) - ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0) - goto release; + seq_printf(s, "%-8s %u %ld ", + l4proto->name, nf_ct_protonum(ct), + timer_pending(&ct->timeout) + ? (long)(ct->timeout.expires - jiffies)/HZ : 0); + + if (l4proto->print_conntrack) + l4proto->print_conntrack(s, ct); - if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct)) + if (seq_has_overflowed(s)) goto release; - if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, - l3proto, l4proto)) + print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + l3proto, l4proto); + + if (seq_has_overflowed(s)) goto release; if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL)) goto release; if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) - if (seq_printf(s, "[UNREPLIED] ")) - goto release; + seq_printf(s, "[UNREPLIED] "); - if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, - l3proto, l4proto)) + print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + l3proto, l4proto); + + if (seq_has_overflowed(s)) goto release; if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) goto release; if (test_bit(IPS_ASSURED_BIT, &ct->status)) - if (seq_printf(s, "[ASSURED] ")) - goto release; + seq_printf(s, "[ASSURED] "); #ifdef CONFIG_NF_CONNTRACK_MARK - if (seq_printf(s, "mark=%u ", ct->mark)) - goto release; + seq_printf(s, "mark=%u ", ct->mark); #endif - if (ct_show_secctx(s, ct)) - goto release; + ct_show_secctx(s, ct); - if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) + seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)); + + if (seq_has_overflowed(s)) goto release; + ret = 0; release: nf_ct_put(ct); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index b91b2641adda..80d5554b9a88 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -72,13 +72,13 @@ static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Print out the per-protocol part of the tuple. */ -static int icmp_print_tuple(struct seq_file *s, +static void icmp_print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "type=%u code=%u id=%u ", - tuple->dst.u.icmp.type, - tuple->dst.u.icmp.code, - ntohs(tuple->src.u.icmp.id)); + seq_printf(s, "type=%u code=%u id=%u ", + tuple->dst.u.icmp.type, + tuple->dst.u.icmp.code, + ntohs(tuple->src.u.icmp.id)); } static unsigned int *icmp_get_timeouts(struct net *net) diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 4cbc6b290dd5..b68d0e59c1f8 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -60,11 +60,11 @@ static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple, return true; } -static int ipv6_print_tuple(struct seq_file *s, +static void ipv6_print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "src=%pI6 dst=%pI6 ", - tuple->src.u3.ip6, tuple->dst.u3.ip6); + seq_printf(s, "src=%pI6 dst=%pI6 ", + tuple->src.u3.ip6, tuple->dst.u3.ip6); } static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index b3807c5cb888..90388d606483 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -84,13 +84,13 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Print out the per-protocol part of the tuple. */ -static int icmpv6_print_tuple(struct seq_file *s, +static void icmpv6_print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "type=%u code=%u id=%u ", - tuple->dst.u.icmp.type, - tuple->dst.u.icmp.code, - ntohs(tuple->src.u.icmp.id)); + seq_printf(s, "type=%u code=%u id=%u ", + tuple->dst.u.icmp.type, + tuple->dst.u.icmp.code, + ntohs(tuple->src.u.icmp.id)); } static unsigned int *icmpv6_get_timeouts(struct net *net) diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c index e7eb807fe07d..cf9ace70bece 100644 --- a/net/netfilter/nf_conntrack_l3proto_generic.c +++ b/net/netfilter/nf_conntrack_l3proto_generic.c @@ -49,10 +49,9 @@ static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple, return true; } -static int generic_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) +static void generic_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) { - return 0; } static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index cb372f96f10d..6dd995c7c72b 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -618,17 +618,17 @@ out_invalid: return -NF_ACCEPT; } -static int dccp_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) +static void dccp_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "sport=%hu dport=%hu ", - ntohs(tuple->src.u.dccp.port), - ntohs(tuple->dst.u.dccp.port)); + seq_printf(s, "sport=%hu dport=%hu ", + ntohs(tuple->src.u.dccp.port), + ntohs(tuple->dst.u.dccp.port)); } -static int dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct) +static void dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { - return seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]); + seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 957c1db66652..60865f110309 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -63,10 +63,9 @@ static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Print out the per-protocol part of the tuple. */ -static int generic_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) +static void generic_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) { - return 0; } static unsigned int *generic_get_timeouts(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index d5665739e3b1..7648674f29c3 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -226,20 +226,20 @@ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, } /* print gre part of tuple */ -static int gre_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) +static void gre_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "srckey=0x%x dstkey=0x%x ", - ntohs(tuple->src.u.gre.key), - ntohs(tuple->dst.u.gre.key)); + seq_printf(s, "srckey=0x%x dstkey=0x%x ", + ntohs(tuple->src.u.gre.key), + ntohs(tuple->dst.u.gre.key)); } /* print private data for conntrack */ -static int gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) +static void gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) { - return seq_printf(s, "timeout=%u, stream_timeout=%u ", - (ct->proto.gre.timeout / HZ), - (ct->proto.gre.stream_timeout / HZ)); + seq_printf(s, "timeout=%u, stream_timeout=%u ", + (ct->proto.gre.timeout / HZ), + (ct->proto.gre.stream_timeout / HZ)); } static unsigned int *gre_get_timeouts(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 1314d33f6bcf..b45da90fad32 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -166,16 +166,16 @@ static bool sctp_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Print out the per-protocol part of the tuple. */ -static int sctp_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) +static void sctp_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "sport=%hu dport=%hu ", - ntohs(tuple->src.u.sctp.port), - ntohs(tuple->dst.u.sctp.port)); + seq_printf(s, "sport=%hu dport=%hu ", + ntohs(tuple->src.u.sctp.port), + ntohs(tuple->dst.u.sctp.port)); } /* Print out the private part of the conntrack. */ -static int sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) +static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { enum sctp_conntrack state; @@ -183,7 +183,7 @@ static int sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) state = ct->proto.sctp.state; spin_unlock_bh(&ct->lock); - return seq_printf(s, "%s ", sctp_conntrack_names[state]); + seq_printf(s, "%s ", sctp_conntrack_names[state]); } #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \ diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d87b6423ffb2..5caa0c41bf26 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -302,16 +302,16 @@ static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Print out the per-protocol part of the tuple. */ -static int tcp_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) +static void tcp_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "sport=%hu dport=%hu ", - ntohs(tuple->src.u.tcp.port), - ntohs(tuple->dst.u.tcp.port)); + seq_printf(s, "sport=%hu dport=%hu ", + ntohs(tuple->src.u.tcp.port), + ntohs(tuple->dst.u.tcp.port)); } /* Print out the private part of the conntrack. */ -static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) +static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { enum tcp_conntrack state; @@ -319,7 +319,7 @@ static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) state = ct->proto.tcp.state; spin_unlock_bh(&ct->lock); - return seq_printf(s, "%s ", tcp_conntrack_names[state]); + seq_printf(s, "%s ", tcp_conntrack_names[state]); } static unsigned int get_conntrack_index(const struct tcphdr *tcph) diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 9d7721cbce4b..6957281ffee5 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -63,12 +63,12 @@ static bool udp_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Print out the per-protocol part of the tuple. */ -static int udp_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) +static void udp_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "sport=%hu dport=%hu ", - ntohs(tuple->src.u.udp.port), - ntohs(tuple->dst.u.udp.port)); + seq_printf(s, "sport=%hu dport=%hu ", + ntohs(tuple->src.u.udp.port), + ntohs(tuple->dst.u.udp.port)); } static unsigned int *udp_get_timeouts(struct net *net) diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 2750e6c69f82..c5903d1649f9 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -71,12 +71,12 @@ static bool udplite_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Print out the per-protocol part of the tuple. */ -static int udplite_print_tuple(struct seq_file *s, - const struct nf_conntrack_tuple *tuple) +static void udplite_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "sport=%hu dport=%hu ", - ntohs(tuple->src.u.udp.port), - ntohs(tuple->dst.u.udp.port)); + seq_printf(s, "sport=%hu dport=%hu ", + ntohs(tuple->src.u.udp.port), + ntohs(tuple->dst.u.udp.port)); } static unsigned int *udplite_get_timeouts(struct net *net) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index cf65a1e040dd..fc823fa5dcf5 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -36,12 +36,13 @@ MODULE_LICENSE("GPL"); #ifdef CONFIG_NF_CONNTRACK_PROCFS -int +void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) { - return l3proto->print_tuple(s, tuple) || l4proto->print_tuple(s, tuple); + l3proto->print_tuple(s, tuple); + l4proto->print_tuple(s, tuple); } EXPORT_SYMBOL_GPL(print_tuple); @@ -119,7 +120,7 @@ static void ct_seq_stop(struct seq_file *s, void *v) } #ifdef CONFIG_NF_CONNTRACK_SECMARK -static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) +static void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { int ret; u32 len; @@ -127,22 +128,20 @@ static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) ret = security_secid_to_secctx(ct->secmark, &secctx, &len); if (ret) - return 0; + return; - ret = seq_printf(s, "secctx=%s ", secctx); + seq_printf(s, "secctx=%s ", secctx); security_release_secctx(secctx, len); - return ret; } #else -static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) +static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { - return 0; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP -static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) +static void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) { struct ct_iter_state *st = s->private; struct nf_conn_tstamp *tstamp; @@ -156,16 +155,15 @@ static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) else delta_time = 0; - return seq_printf(s, "delta-time=%llu ", - (unsigned long long)delta_time); + seq_printf(s, "delta-time=%llu ", + (unsigned long long)delta_time); } - return 0; + return; } #else -static inline int +static inline void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) { - return 0; } #endif @@ -192,55 +190,54 @@ static int ct_seq_show(struct seq_file *s, void *v) NF_CT_ASSERT(l4proto); ret = -ENOSPC; - if (seq_printf(s, "%-8s %u %-8s %u %ld ", - l3proto->name, nf_ct_l3num(ct), - l4proto->name, nf_ct_protonum(ct), - timer_pending(&ct->timeout) - ? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0) - goto release; + seq_printf(s, "%-8s %u %-8s %u %ld ", + l3proto->name, nf_ct_l3num(ct), + l4proto->name, nf_ct_protonum(ct), + timer_pending(&ct->timeout) + ? (long)(ct->timeout.expires - jiffies)/HZ : 0); - if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct)) - goto release; + if (l4proto->print_conntrack) + l4proto->print_conntrack(s, ct); + + print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + l3proto, l4proto); - if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, - l3proto, l4proto)) + if (seq_has_overflowed(s)) goto release; if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL)) goto release; if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) - if (seq_printf(s, "[UNREPLIED] ")) - goto release; + seq_printf(s, "[UNREPLIED] "); - if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, - l3proto, l4proto)) - goto release; + print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + l3proto, l4proto); if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) goto release; if (test_bit(IPS_ASSURED_BIT, &ct->status)) - if (seq_printf(s, "[ASSURED] ")) - goto release; + seq_printf(s, "[ASSURED] "); -#if defined(CONFIG_NF_CONNTRACK_MARK) - if (seq_printf(s, "mark=%u ", ct->mark)) + if (seq_has_overflowed(s)) goto release; + +#if defined(CONFIG_NF_CONNTRACK_MARK) + seq_printf(s, "mark=%u ", ct->mark); #endif - if (ct_show_secctx(s, ct)) - goto release; + ct_show_secctx(s, ct); #ifdef CONFIG_NF_CONNTRACK_ZONES - if (seq_printf(s, "zone=%u ", nf_ct_zone(ct))) - goto release; + seq_printf(s, "zone=%u ", nf_ct_zone(ct)); #endif - if (ct_show_delta_time(s, ct)) - goto release; + ct_show_delta_time(s, ct); + + seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)); - if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) + if (seq_has_overflowed(s)) goto release; ret = 0; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index d7197649dba6..6e3b9117db1f 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -294,19 +294,19 @@ static int seq_show(struct seq_file *s, void *v) { loff_t *pos = v; const struct nf_logger *logger; - int i, ret; + int i; struct net *net = seq_file_net(s); logger = rcu_dereference_protected(net->nf.nf_loggers[*pos], lockdep_is_held(&nf_log_mutex)); if (!logger) - ret = seq_printf(s, "%2lld NONE (", *pos); + seq_printf(s, "%2lld NONE (", *pos); else - ret = seq_printf(s, "%2lld %s (", *pos, logger->name); + seq_printf(s, "%2lld %s (", *pos, logger->name); - if (ret < 0) - return ret; + if (seq_has_overflowed(s)) + return -ENOSPC; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (loggers[*pos][i] == NULL) @@ -314,17 +314,19 @@ static int seq_show(struct seq_file *s, void *v) logger = rcu_dereference_protected(loggers[*pos][i], lockdep_is_held(&nf_log_mutex)); - ret = seq_printf(s, "%s", logger->name); - if (ret < 0) - return ret; - if (i == 0 && loggers[*pos][i + 1] != NULL) { - ret = seq_printf(s, ","); - if (ret < 0) - return ret; - } + seq_printf(s, "%s", logger->name); + if (i == 0 && loggers[*pos][i + 1] != NULL) + seq_printf(s, ","); + + if (seq_has_overflowed(s)) + return -ENOSPC; } - return seq_printf(s, ")\n"); + seq_printf(s, ")\n"); + + if (seq_has_overflowed(s)) + return -ENOSPC; + return 0; } static const struct seq_operations nflog_seq_ops = { diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 7c60ccd61a3e..0db8515e76da 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -1242,12 +1242,13 @@ static int seq_show(struct seq_file *s, void *v) { const struct nfqnl_instance *inst = v; - return seq_printf(s, "%5d %6d %5d %1d %5d %5d %5d %8d %2d\n", - inst->queue_num, - inst->peer_portid, inst->queue_total, - inst->copy_mode, inst->copy_range, - inst->queue_dropped, inst->queue_user_dropped, - inst->id_sequence, 1); + seq_printf(s, "%5d %6d %5d %1d %5d %5d %5d %8d %2d\n", + inst->queue_num, + inst->peer_portid, inst->queue_total, + inst->copy_mode, inst->copy_range, + inst->queue_dropped, inst->queue_user_dropped, + inst->id_sequence, 1); + return seq_has_overflowed(s); } static const struct seq_operations nfqnl_seq_ops = { diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 133eb4772f12..51a459c3c649 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -947,9 +947,10 @@ static int xt_table_seq_show(struct seq_file *seq, void *v) { struct xt_table *table = list_entry(v, struct xt_table, list); - if (strlen(table->name)) - return seq_printf(seq, "%s\n", table->name); - else + if (strlen(table->name)) { + seq_printf(seq, "%s\n", table->name); + return seq_has_overflowed(seq); + } else return 0; } @@ -1086,8 +1087,10 @@ static int xt_match_seq_show(struct seq_file *seq, void *v) if (trav->curr == trav->head) return 0; match = list_entry(trav->curr, struct xt_match, list); - return (*match->name == '\0') ? 0 : - seq_printf(seq, "%s\n", match->name); + if (*match->name == '\0') + return 0; + seq_printf(seq, "%s\n", match->name); + return seq_has_overflowed(seq); } return 0; } @@ -1139,8 +1142,10 @@ static int xt_target_seq_show(struct seq_file *seq, void *v) if (trav->curr == trav->head) return 0; target = list_entry(trav->curr, struct xt_target, list); - return (*target->name == '\0') ? 0 : - seq_printf(seq, "%s\n", target->name); + if (*target->name == '\0') + return 0; + seq_printf(seq, "%s\n", target->name); + return seq_has_overflowed(seq); } return 0; } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 05fbc2a0be46..178696852bde 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -789,7 +789,6 @@ static void dl_seq_stop(struct seq_file *s, void *v) static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - int res; const struct xt_hashlimit_htable *ht = s->private; spin_lock(&ent->lock); @@ -798,33 +797,32 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, switch (family) { case NFPROTO_IPV4: - res = seq_printf(s, "%ld %pI4:%u->%pI4:%u %u %u %u\n", - (long)(ent->expires - jiffies)/HZ, - &ent->dst.ip.src, - ntohs(ent->dst.src_port), - &ent->dst.ip.dst, - ntohs(ent->dst.dst_port), - ent->rateinfo.credit, ent->rateinfo.credit_cap, - ent->rateinfo.cost); + seq_printf(s, "%ld %pI4:%u->%pI4:%u %u %u %u\n", + (long)(ent->expires - jiffies)/HZ, + &ent->dst.ip.src, + ntohs(ent->dst.src_port), + &ent->dst.ip.dst, + ntohs(ent->dst.dst_port), + ent->rateinfo.credit, ent->rateinfo.credit_cap, + ent->rateinfo.cost); break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: - res = seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n", - (long)(ent->expires - jiffies)/HZ, - &ent->dst.ip6.src, - ntohs(ent->dst.src_port), - &ent->dst.ip6.dst, - ntohs(ent->dst.dst_port), - ent->rateinfo.credit, ent->rateinfo.credit_cap, - ent->rateinfo.cost); + seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n", + (long)(ent->expires - jiffies)/HZ, + &ent->dst.ip6.src, + ntohs(ent->dst.src_port), + &ent->dst.ip6.dst, + ntohs(ent->dst.dst_port), + ent->rateinfo.credit, ent->rateinfo.credit_cap, + ent->rateinfo.cost); break; #endif default: BUG(); - res = 0; } spin_unlock(&ent->lock); - return res; + return seq_has_overflowed(s); } static int dl_seq_show(struct seq_file *s, void *v) diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 0754d0f466d2..fb78117b896c 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -35,6 +35,7 @@ config RPCSEC_GSS_KRB5 config SUNRPC_DEBUG bool "RPC: Enable dprintk debugging" depends on SUNRPC && SYSCTL + select DEBUG_FS help This option enables a sysctl-based debugging interface that is be used by the 'rpcdebug' utility to turn on or off diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index e5a7a1cac8f3..15e6f6c23c5d 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -14,6 +14,7 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ svc_xprt.o +sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o bc_svc.o sunrpc-$(CONFIG_PROC_FS) += stats.o sunrpc-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 383eb919ac0b..47f38be4155f 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -16,7 +16,7 @@ #include <linux/sunrpc/gss_api.h> #include <linux/spinlock.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -646,7 +646,7 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred, cred->cr_auth = auth; cred->cr_ops = ops; cred->cr_expire = jiffies; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) cred->cr_magic = RPCAUTH_CRED_MAGIC; #endif cred->cr_uid = acred->uid; diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 6f6b829c9e8e..41248b1820c7 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -14,7 +14,7 @@ #include <linux/sunrpc/debug.h> #include <linux/sunrpc/sched.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 53ed8d3f8897..dace13d7638e 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -66,7 +66,7 @@ static unsigned int gss_expired_cred_retry_delay = GSS_RETRY_EXPIRED; #define GSS_KEY_EXPIRE_TIMEO 240 static unsigned int gss_key_expire_timeo = GSS_KEY_EXPIRE_TIMEO; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c index c586e92bcf76..254defe446a7 100644 --- a/net/sunrpc/auth_gss/gss_generic_token.c +++ b/net/sunrpc/auth_gss/gss_generic_token.c @@ -38,7 +38,7 @@ #include <linux/sunrpc/gss_asn1.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index f5ed9f6ece06..b5408e8a37f2 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -45,7 +45,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/sunrpc/xdr.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 24589bd2a4b6..234fa8d0fd9b 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -61,7 +61,7 @@ #include <linux/sunrpc/xdr.h> #include <linux/lcm.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 0d3c158ef8fa..28db442a0034 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -45,7 +45,7 @@ #include <linux/crypto.h> #include <linux/sunrpc/gss_krb5_enctypes.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 42768e5c3994..1d74d653e6c0 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -64,7 +64,7 @@ #include <linux/random.h> #include <linux/crypto.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index 62ac90c62cb1..20d55c793eb6 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -35,7 +35,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/crypto.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index 6c981ddc19f8..dcf9515d9aef 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -62,7 +62,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/crypto.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 4b614c604fe0..ca7e92a32f84 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -35,7 +35,7 @@ #include <linux/pagemap.h> #include <linux/crypto.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 92d5ab99fbf3..7063d856a598 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -46,7 +46,7 @@ #include <linux/sunrpc/gss_api.h> #include <linux/sunrpc/clnt.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 685a688f3d8a..9d88c6239f01 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -25,7 +25,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/xprtsock.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index c548ab213f76..de856ddf5fed 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -51,7 +51,7 @@ #include "gss_rpc_upcall.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index 712c123e04e9..c2a2b584a056 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -10,7 +10,7 @@ #include <linux/module.h> #include <linux/sunrpc/clnt.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -138,7 +138,7 @@ struct rpc_cred null_cred = { .cr_ops = &null_credops, .cr_count = ATOMIC_INIT(1), .cr_flags = 1UL << RPCAUTH_CRED_UPTODATE, -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) .cr_magic = RPCAUTH_CRED_MAGIC, #endif }; diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index d5d692366294..4feda2d0a833 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -25,7 +25,7 @@ struct unx_cred { #define UNX_WRITESLACK (21 + (UNX_MAXNODENAME >> 2)) -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 9761a0da964d..651f49ab601f 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -27,7 +27,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #include <linux/export.h> #include <linux/sunrpc/bc_xprt.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) #define RPCDBG_FACILITY RPCDBG_TRANS #endif diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 9acd6ce88db7..05da12a33945 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -42,7 +42,7 @@ #include "sunrpc.h" #include "netns.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_CALL #endif @@ -305,6 +305,10 @@ static int rpc_client_register(struct rpc_clnt *clnt, struct super_block *pipefs_sb; int err; + err = rpc_clnt_debugfs_register(clnt); + if (err) + return err; + pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { err = rpc_setup_pipedir(pipefs_sb, clnt); @@ -331,6 +335,7 @@ err_auth: out: if (pipefs_sb) rpc_put_sb_net(net); + rpc_clnt_debugfs_unregister(clnt); return err; } @@ -670,6 +675,7 @@ int rpc_switch_client_transport(struct rpc_clnt *clnt, rpc_unregister_client(clnt); __rpc_clnt_remove_pipedir(clnt); + rpc_clnt_debugfs_unregister(clnt); /* * A new transport was created. "clnt" therefore @@ -771,6 +777,7 @@ rpc_free_client(struct rpc_clnt *clnt) rcu_dereference(clnt->cl_xprt)->servername); if (clnt->cl_parent != clnt) parent = clnt->cl_parent; + rpc_clnt_debugfs_unregister(clnt); rpc_clnt_remove_pipedir(clnt); rpc_unregister_client(clnt); rpc_free_iostats(clnt->cl_metrics); @@ -1396,8 +1403,9 @@ rpc_restart_call(struct rpc_task *task) } EXPORT_SYMBOL_GPL(rpc_restart_call); -#ifdef RPC_DEBUG -static const char *rpc_proc_name(const struct rpc_task *task) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +const char +*rpc_proc_name(const struct rpc_task *task) { const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; @@ -2421,7 +2429,7 @@ struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int } EXPORT_SYMBOL_GPL(rpc_call_null); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static void rpc_show_header(void) { printk(KERN_INFO "-pid- flgs status -client- --rqstp- " diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c new file mode 100644 index 000000000000..e811f390f9f6 --- /dev/null +++ b/net/sunrpc/debugfs.c @@ -0,0 +1,292 @@ +/** + * debugfs interface for sunrpc + * + * (c) 2014 Jeff Layton <jlayton@primarydata.com> + */ + +#include <linux/debugfs.h> +#include <linux/sunrpc/sched.h> +#include <linux/sunrpc/clnt.h> +#include "netns.h" + +static struct dentry *topdir; +static struct dentry *rpc_clnt_dir; +static struct dentry *rpc_xprt_dir; + +struct rpc_clnt_iter { + struct rpc_clnt *clnt; + loff_t pos; +}; + +static int +tasks_show(struct seq_file *f, void *v) +{ + u32 xid = 0; + struct rpc_task *task = v; + struct rpc_clnt *clnt = task->tk_client; + const char *rpc_waitq = "none"; + + if (RPC_IS_QUEUED(task)) + rpc_waitq = rpc_qname(task->tk_waitqueue); + + if (task->tk_rqstp) + xid = be32_to_cpu(task->tk_rqstp->rq_xid); + + seq_printf(f, "%5u %04x %6d 0x%x 0x%x %8ld %ps %sv%u %s a:%ps q:%s\n", + task->tk_pid, task->tk_flags, task->tk_status, + clnt->cl_clid, xid, task->tk_timeout, task->tk_ops, + clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), + task->tk_action, rpc_waitq); + return 0; +} + +static void * +tasks_start(struct seq_file *f, loff_t *ppos) + __acquires(&clnt->cl_lock) +{ + struct rpc_clnt_iter *iter = f->private; + loff_t pos = *ppos; + struct rpc_clnt *clnt = iter->clnt; + struct rpc_task *task; + + iter->pos = pos + 1; + spin_lock(&clnt->cl_lock); + list_for_each_entry(task, &clnt->cl_tasks, tk_task) + if (pos-- == 0) + return task; + return NULL; +} + +static void * +tasks_next(struct seq_file *f, void *v, loff_t *pos) +{ + struct rpc_clnt_iter *iter = f->private; + struct rpc_clnt *clnt = iter->clnt; + struct rpc_task *task = v; + struct list_head *next = task->tk_task.next; + + ++iter->pos; + ++*pos; + + /* If there's another task on list, return it */ + if (next == &clnt->cl_tasks) + return NULL; + return list_entry(next, struct rpc_task, tk_task); +} + +static void +tasks_stop(struct seq_file *f, void *v) + __releases(&clnt->cl_lock) +{ + struct rpc_clnt_iter *iter = f->private; + struct rpc_clnt *clnt = iter->clnt; + + spin_unlock(&clnt->cl_lock); +} + +static const struct seq_operations tasks_seq_operations = { + .start = tasks_start, + .next = tasks_next, + .stop = tasks_stop, + .show = tasks_show, +}; + +static int tasks_open(struct inode *inode, struct file *filp) +{ + int ret = seq_open_private(filp, &tasks_seq_operations, + sizeof(struct rpc_clnt_iter)); + + if (!ret) { + struct seq_file *seq = filp->private_data; + struct rpc_clnt_iter *iter = seq->private; + + iter->clnt = inode->i_private; + + if (!atomic_inc_not_zero(&iter->clnt->cl_count)) { + seq_release_private(inode, filp); + ret = -EINVAL; + } + } + + return ret; +} + +static int +tasks_release(struct inode *inode, struct file *filp) +{ + struct seq_file *seq = filp->private_data; + struct rpc_clnt_iter *iter = seq->private; + + rpc_release_client(iter->clnt); + return seq_release_private(inode, filp); +} + +static const struct file_operations tasks_fops = { + .owner = THIS_MODULE, + .open = tasks_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tasks_release, +}; + +int +rpc_clnt_debugfs_register(struct rpc_clnt *clnt) +{ + int len, err; + char name[24]; /* enough for "../../rpc_xprt/ + 8 hex digits + NULL */ + + /* Already registered? */ + if (clnt->cl_debugfs) + return 0; + + len = snprintf(name, sizeof(name), "%x", clnt->cl_clid); + if (len >= sizeof(name)) + return -EINVAL; + + /* make the per-client dir */ + clnt->cl_debugfs = debugfs_create_dir(name, rpc_clnt_dir); + if (!clnt->cl_debugfs) + return -ENOMEM; + + /* make tasks file */ + err = -ENOMEM; + if (!debugfs_create_file("tasks", S_IFREG | S_IRUSR, clnt->cl_debugfs, + clnt, &tasks_fops)) + goto out_err; + + err = -EINVAL; + rcu_read_lock(); + len = snprintf(name, sizeof(name), "../../rpc_xprt/%s", + rcu_dereference(clnt->cl_xprt)->debugfs->d_name.name); + rcu_read_unlock(); + if (len >= sizeof(name)) + goto out_err; + + err = -ENOMEM; + if (!debugfs_create_symlink("xprt", clnt->cl_debugfs, name)) + goto out_err; + + return 0; +out_err: + debugfs_remove_recursive(clnt->cl_debugfs); + clnt->cl_debugfs = NULL; + return err; +} + +void +rpc_clnt_debugfs_unregister(struct rpc_clnt *clnt) +{ + debugfs_remove_recursive(clnt->cl_debugfs); + clnt->cl_debugfs = NULL; +} + +static int +xprt_info_show(struct seq_file *f, void *v) +{ + struct rpc_xprt *xprt = f->private; + + seq_printf(f, "netid: %s\n", xprt->address_strings[RPC_DISPLAY_NETID]); + seq_printf(f, "addr: %s\n", xprt->address_strings[RPC_DISPLAY_ADDR]); + seq_printf(f, "port: %s\n", xprt->address_strings[RPC_DISPLAY_PORT]); + seq_printf(f, "state: 0x%lx\n", xprt->state); + return 0; +} + +static int +xprt_info_open(struct inode *inode, struct file *filp) +{ + int ret; + struct rpc_xprt *xprt = inode->i_private; + + ret = single_open(filp, xprt_info_show, xprt); + + if (!ret) { + if (!xprt_get(xprt)) { + single_release(inode, filp); + ret = -EINVAL; + } + } + return ret; +} + +static int +xprt_info_release(struct inode *inode, struct file *filp) +{ + struct rpc_xprt *xprt = inode->i_private; + + xprt_put(xprt); + return single_release(inode, filp); +} + +static const struct file_operations xprt_info_fops = { + .owner = THIS_MODULE, + .open = xprt_info_open, + .read = seq_read, + .llseek = seq_lseek, + .release = xprt_info_release, +}; + +int +rpc_xprt_debugfs_register(struct rpc_xprt *xprt) +{ + int len, id; + static atomic_t cur_id; + char name[9]; /* 8 hex digits + NULL term */ + + id = (unsigned int)atomic_inc_return(&cur_id); + + len = snprintf(name, sizeof(name), "%x", id); + if (len >= sizeof(name)) + return -EINVAL; + + /* make the per-client dir */ + xprt->debugfs = debugfs_create_dir(name, rpc_xprt_dir); + if (!xprt->debugfs) + return -ENOMEM; + + /* make tasks file */ + if (!debugfs_create_file("info", S_IFREG | S_IRUSR, xprt->debugfs, + xprt, &xprt_info_fops)) { + debugfs_remove_recursive(xprt->debugfs); + xprt->debugfs = NULL; + return -ENOMEM; + } + + return 0; +} + +void +rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt) +{ + debugfs_remove_recursive(xprt->debugfs); + xprt->debugfs = NULL; +} + +void __exit +sunrpc_debugfs_exit(void) +{ + debugfs_remove_recursive(topdir); +} + +int __init +sunrpc_debugfs_init(void) +{ + topdir = debugfs_create_dir("sunrpc", NULL); + if (!topdir) + goto out; + + rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir); + if (!rpc_clnt_dir) + goto out_remove; + + rpc_xprt_dir = debugfs_create_dir("rpc_xprt", topdir); + if (!rpc_xprt_dir) + goto out_remove; + + return 0; +out_remove: + debugfs_remove_recursive(topdir); + topdir = NULL; +out: + return -ENOMEM; +} diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 1891a1022c17..05202012bcfc 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -32,7 +32,7 @@ #include "netns.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_BIND #endif diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index fe3441abdbe5..d20f2329eea3 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -24,7 +24,7 @@ #include "sunrpc.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) #define RPCDBG_FACILITY RPCDBG_SCHED #endif @@ -258,7 +258,7 @@ static int rpc_wait_bit_killable(struct wait_bit_key *key) return 0; } -#if defined(RPC_DEBUG) || defined(RPC_TRACEPOINTS) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static void rpc_task_set_debuginfo(struct rpc_task *task) { static atomic_t rpc_pid; diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 54530490944e..9711a155bc50 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -116,7 +116,15 @@ EXPORT_SYMBOL_GPL(svc_seq_show); */ struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { - return kcalloc(clnt->cl_maxproc, sizeof(struct rpc_iostats), GFP_KERNEL); + struct rpc_iostats *stats; + int i; + + stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL); + if (stats) { + for (i = 0; i < clnt->cl_maxproc; i++) + spin_lock_init(&stats[i].om_lock); + } + return stats; } EXPORT_SYMBOL_GPL(rpc_alloc_iostats); @@ -135,20 +143,21 @@ EXPORT_SYMBOL_GPL(rpc_free_iostats); * rpc_count_iostats - tally up per-task stats * @task: completed rpc_task * @stats: array of stat structures - * - * Relies on the caller for serialization. */ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_iostats *op_metrics; - ktime_t delta; + ktime_t delta, now; if (!stats || !req) return; + now = ktime_get(); op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx]; + spin_lock(&op_metrics->om_lock); + op_metrics->om_ops++; op_metrics->om_ntrans += req->rq_ntrans; op_metrics->om_timeouts += task->tk_timeouts; @@ -161,8 +170,10 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt); - delta = ktime_sub(ktime_get(), task->tk_start); + delta = ktime_sub(now, task->tk_start); op_metrics->om_execute = ktime_add(op_metrics->om_execute, delta); + + spin_unlock(&op_metrics->om_lock); } EXPORT_SYMBOL_GPL(rpc_count_iostats); diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index cd30120de9e4..e37fbed87956 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -97,13 +97,20 @@ init_sunrpc(void) err = register_rpc_pipefs(); if (err) goto out4; -#ifdef RPC_DEBUG + + err = sunrpc_debugfs_init(); + if (err) + goto out5; + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_register_sysctl(); #endif svc_init_xprt_sock(); /* svc sock transport */ init_socket_xprt(); /* clnt sock transport */ return 0; +out5: + unregister_rpc_pipefs(); out4: unregister_pernet_subsys(&sunrpc_net_ops); out3: @@ -120,10 +127,11 @@ cleanup_sunrpc(void) rpcauth_remove_module(); cleanup_socket_xprt(); svc_cleanup_xprt_sock(); + sunrpc_debugfs_exit(); unregister_rpc_pipefs(); rpc_destroy_mempool(); unregister_pernet_subsys(&sunrpc_net_ops); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_unregister_sysctl(); #endif rcu_barrier(); /* Wait for completion of call_rcu()'s */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index ca8a7958f4e6..2783fd80c229 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -28,6 +28,8 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/bc_xprt.h> +#include <trace/events/sunrpc.h> + #define RPCDBG_FACILITY RPCDBG_SVCDSP static void svc_unregister(const struct svc_serv *serv, struct net *net); @@ -1040,7 +1042,7 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net) /* * dprintk the given error with the address of the client that caused it. */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static __printf(2, 3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) { @@ -1314,24 +1316,25 @@ svc_process(struct svc_rqst *rqstp) rqstp->rq_res.tail[0].iov_base = NULL; rqstp->rq_res.tail[0].iov_len = 0; - rqstp->rq_xid = svc_getu32(argv); - dir = svc_getnl(argv); if (dir != 0) { /* direction != CALL */ svc_printk(rqstp, "bad direction %d, dropping request\n", dir); serv->sv_stats->rpcbadfmt++; - svc_drop(rqstp); - return 0; + goto out_drop; } /* Returns 1 for send, 0 for drop */ - if (svc_process_common(rqstp, argv, resv)) - return svc_send(rqstp); - else { - svc_drop(rqstp); - return 0; + if (likely(svc_process_common(rqstp, argv, resv))) { + int ret = svc_send(rqstp); + + trace_svc_process(rqstp, ret); + return ret; } +out_drop: + trace_svc_process(rqstp, 0); + svc_drop(rqstp); + return 0; } #if defined(CONFIG_SUNRPC_BACKCHANNEL) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index c179ca2a5aa4..bbb3b044b877 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -15,6 +15,7 @@ #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/xprt.h> #include <linux/module.h> +#include <trace/events/sunrpc.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -773,35 +774,43 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) err = svc_alloc_arg(rqstp); if (err) - return err; + goto out; try_to_freeze(); cond_resched(); + err = -EINTR; if (signalled() || kthread_should_stop()) - return -EINTR; + goto out; xprt = svc_get_next_xprt(rqstp, timeout); - if (IS_ERR(xprt)) - return PTR_ERR(xprt); + if (IS_ERR(xprt)) { + err = PTR_ERR(xprt); + goto out; + } len = svc_handle_xprt(rqstp, xprt); /* No data, incomplete (TCP) read, or accept() */ + err = -EAGAIN; if (len <= 0) - goto out; + goto out_release; clear_bit(XPT_OLD, &xprt->xpt_flags); rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp); rqstp->rq_chandle.defer = svc_defer; + rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]); if (serv->sv_stats) serv->sv_stats->netcnt++; + trace_svc_recv(rqstp, len); return len; -out: +out_release: rqstp->rq_res.len = 0; svc_xprt_release(rqstp); - return -EAGAIN; +out: + trace_svc_recv(rqstp, err); + return err; } EXPORT_SYMBOL_GPL(svc_recv); @@ -821,12 +830,12 @@ EXPORT_SYMBOL_GPL(svc_drop); int svc_send(struct svc_rqst *rqstp) { struct svc_xprt *xprt; - int len; + int len = -EFAULT; struct xdr_buf *xb; xprt = rqstp->rq_xprt; if (!xprt) - return -EFAULT; + goto out; /* release the receive skb before sending the reply */ rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp); @@ -849,7 +858,9 @@ int svc_send(struct svc_rqst *rqstp) svc_xprt_release(rqstp); if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN) - return 0; + len = 0; +out: + trace_svc_send(rqstp, len); return len; } diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index c99c58e2ee66..887f0183b4c6 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -37,7 +37,7 @@ EXPORT_SYMBOL_GPL(nfsd_debug); unsigned int nlm_debug; EXPORT_SYMBOL_GPL(nlm_debug); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static struct ctl_table_header *sunrpc_table_header; static struct ctl_table sunrpc_table[]; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 56e4e150e80e..ebbefad21a37 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -49,13 +49,15 @@ #include <linux/sunrpc/metrics.h> #include <linux/sunrpc/bc_xprt.h> +#include <trace/events/sunrpc.h> + #include "sunrpc.h" /* * Local variables */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_XPRT #endif @@ -772,11 +774,14 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) struct rpc_rqst *entry; list_for_each_entry(entry, &xprt->recv, rq_list) - if (entry->rq_xid == xid) + if (entry->rq_xid == xid) { + trace_xprt_lookup_rqst(xprt, xid, 0); return entry; + } dprintk("RPC: xprt_lookup_rqst did not find xid %08x\n", ntohl(xid)); + trace_xprt_lookup_rqst(xprt, xid, -ENOENT); xprt->stat.bad_xids++; return NULL; } @@ -810,6 +815,7 @@ void xprt_complete_rqst(struct rpc_task *task, int copied) dprintk("RPC: %5u xid %08x complete (%d bytes received)\n", task->tk_pid, ntohl(req->rq_xid), copied); + trace_xprt_complete_rqst(xprt, req->rq_xid, copied); xprt->stat.recvs++; req->rq_rtt = ktime_sub(ktime_get(), req->rq_xtime); @@ -926,6 +932,7 @@ void xprt_transmit(struct rpc_task *task) req->rq_xtime = ktime_get(); status = xprt->ops->send_request(task); + trace_xprt_transmit(xprt, req->rq_xid, status); if (status != 0) { task->tk_status = status; return; @@ -1296,6 +1303,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) */ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) { + int err; struct rpc_xprt *xprt; struct xprt_class *t; @@ -1336,6 +1344,12 @@ found: return ERR_PTR(-ENOMEM); } + err = rpc_xprt_debugfs_register(xprt); + if (err) { + xprt_destroy(xprt); + return ERR_PTR(err); + } + dprintk("RPC: created transport %p with %u slots\n", xprt, xprt->max_reqs); out: @@ -1352,6 +1366,7 @@ static void xprt_destroy(struct rpc_xprt *xprt) dprintk("RPC: destroying transport %p\n", xprt); del_timer_sync(&xprt->timer); + rpc_xprt_debugfs_unregister(xprt); rpc_destroy_wait_queue(&xprt->binding); rpc_destroy_wait_queue(&xprt->pending); rpc_destroy_wait_queue(&xprt->sending); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 6166c985fe24..df01d124936c 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -49,11 +49,11 @@ #include <linux/highmem.h> -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_TRANS #endif -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static const char transfertypes[][12] = { "pure inline", /* no chunks */ " read chunk", /* some argument via rdma read */ diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 6a4615dd0261..bbd6155d3e34 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -55,7 +55,7 @@ #include "xprt_rdma.h" -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_TRANS #endif @@ -73,9 +73,9 @@ static unsigned int xprt_rdma_max_inline_read = RPCRDMA_DEF_INLINE; static unsigned int xprt_rdma_max_inline_write = RPCRDMA_DEF_INLINE; static unsigned int xprt_rdma_inline_write_padding; static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR; - int xprt_rdma_pad_optimize = 0; + int xprt_rdma_pad_optimize = 1; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static unsigned int min_slot_table_size = RPCRDMA_MIN_SLOT_TABLE; static unsigned int max_slot_table_size = RPCRDMA_MAX_SLOT_TABLE; @@ -599,7 +599,7 @@ xprt_rdma_send_request(struct rpc_task *task) if (req->rl_niovs == 0) rc = rpcrdma_marshal_req(rqst); - else if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR) + else if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_ALLPHYSICAL) rc = rpcrdma_marshal_chunks(rqst, 0); if (rc < 0) goto failed_marshal; @@ -705,7 +705,7 @@ static void __exit xprt_rdma_cleanup(void) int rc; dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n"); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (sunrpc_table_header) { unregister_sysctl_table(sunrpc_table_header); sunrpc_table_header = NULL; @@ -736,7 +736,7 @@ static int __init xprt_rdma_init(void) dprintk("\tPadding %d\n\tMemreg %d\n", xprt_rdma_inline_write_padding, xprt_rdma_memreg_strategy); -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (!sunrpc_table_header) sunrpc_table_header = register_sysctl_table(sunrpc_table); #endif diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 61c41298b4ea..c98e40643910 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -57,11 +57,12 @@ * Globals/Macros */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_TRANS #endif static void rpcrdma_reset_frmrs(struct rpcrdma_ia *); +static void rpcrdma_reset_fmrs(struct rpcrdma_ia *); /* * internal functions @@ -105,13 +106,51 @@ rpcrdma_run_tasklet(unsigned long data) static DECLARE_TASKLET(rpcrdma_tasklet_g, rpcrdma_run_tasklet, 0UL); +static const char * const async_event[] = { + "CQ error", + "QP fatal error", + "QP request error", + "QP access error", + "communication established", + "send queue drained", + "path migration successful", + "path mig error", + "device fatal error", + "port active", + "port error", + "LID change", + "P_key change", + "SM change", + "SRQ error", + "SRQ limit reached", + "last WQE reached", + "client reregister", + "GID change", +}; + +#define ASYNC_MSG(status) \ + ((status) < ARRAY_SIZE(async_event) ? \ + async_event[(status)] : "unknown async error") + +static void +rpcrdma_schedule_tasklet(struct list_head *sched_list) +{ + unsigned long flags; + + spin_lock_irqsave(&rpcrdma_tk_lock_g, flags); + list_splice_tail(sched_list, &rpcrdma_tasklets_g); + spin_unlock_irqrestore(&rpcrdma_tk_lock_g, flags); + tasklet_schedule(&rpcrdma_tasklet_g); +} + static void rpcrdma_qp_async_error_upcall(struct ib_event *event, void *context) { struct rpcrdma_ep *ep = context; - dprintk("RPC: %s: QP error %X on device %s ep %p\n", - __func__, event->event, event->device->name, context); + pr_err("RPC: %s: %s on device %s ep %p\n", + __func__, ASYNC_MSG(event->event), + event->device->name, context); if (ep->rep_connected == 1) { ep->rep_connected = -EIO; ep->rep_func(ep); @@ -124,8 +163,9 @@ rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context) { struct rpcrdma_ep *ep = context; - dprintk("RPC: %s: CQ error %X on device %s ep %p\n", - __func__, event->event, event->device->name, context); + pr_err("RPC: %s: %s on device %s ep %p\n", + __func__, ASYNC_MSG(event->event), + event->device->name, context); if (ep->rep_connected == 1) { ep->rep_connected = -EIO; ep->rep_func(ep); @@ -243,7 +283,6 @@ rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep) struct list_head sched_list; struct ib_wc *wcs; int budget, count, rc; - unsigned long flags; INIT_LIST_HEAD(&sched_list); budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE; @@ -261,10 +300,7 @@ rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep) rc = 0; out_schedule: - spin_lock_irqsave(&rpcrdma_tk_lock_g, flags); - list_splice_tail(&sched_list, &rpcrdma_tasklets_g); - spin_unlock_irqrestore(&rpcrdma_tk_lock_g, flags); - tasklet_schedule(&rpcrdma_tasklet_g); + rpcrdma_schedule_tasklet(&sched_list); return rc; } @@ -309,11 +345,18 @@ rpcrdma_recvcq_upcall(struct ib_cq *cq, void *cq_context) static void rpcrdma_flush_cqs(struct rpcrdma_ep *ep) { - rpcrdma_recvcq_upcall(ep->rep_attr.recv_cq, ep); - rpcrdma_sendcq_upcall(ep->rep_attr.send_cq, ep); + struct ib_wc wc; + LIST_HEAD(sched_list); + + while (ib_poll_cq(ep->rep_attr.recv_cq, 1, &wc) > 0) + rpcrdma_recvcq_process_wc(&wc, &sched_list); + if (!list_empty(&sched_list)) + rpcrdma_schedule_tasklet(&sched_list); + while (ib_poll_cq(ep->rep_attr.send_cq, 1, &wc) > 0) + rpcrdma_sendcq_process_wc(&wc); } -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static const char * const conn[] = { "address resolved", "address error", @@ -344,7 +387,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) struct rpcrdma_xprt *xprt = id->context; struct rpcrdma_ia *ia = &xprt->rx_ia; struct rpcrdma_ep *ep = &xprt->rx_ep; -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct sockaddr_in *addr = (struct sockaddr_in *) &ep->rep_remote_addr; #endif struct ib_qp_attr attr; @@ -408,7 +451,7 @@ connected: break; } -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (connstate == 1) { int ird = attr.max_dest_rd_atomic; int tird = ep->rep_remote_cma.responder_resources; @@ -733,7 +776,9 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, /* set trigger for requesting send completion */ ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1; - if (ep->rep_cqinit <= 2) + if (ep->rep_cqinit > RPCRDMA_MAX_UNSIGNALED_SENDS) + ep->rep_cqinit = RPCRDMA_MAX_UNSIGNALED_SENDS; + else if (ep->rep_cqinit <= 2) ep->rep_cqinit = 0; INIT_CQCOUNT(ep); ep->rep_ia = ia; @@ -866,8 +911,19 @@ retry: rpcrdma_ep_disconnect(ep, ia); rpcrdma_flush_cqs(ep); - if (ia->ri_memreg_strategy == RPCRDMA_FRMR) + switch (ia->ri_memreg_strategy) { + case RPCRDMA_FRMR: rpcrdma_reset_frmrs(ia); + break; + case RPCRDMA_MTHCAFMR: + rpcrdma_reset_fmrs(ia); + break; + case RPCRDMA_ALLPHYSICAL: + break; + default: + rc = -EIO; + goto out; + } xprt = container_of(ia, struct rpcrdma_xprt, rx_ia); id = rpcrdma_create_id(xprt, ia, @@ -1287,6 +1343,34 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) kfree(buf->rb_pool); } +/* After a disconnect, unmap all FMRs. + * + * This is invoked only in the transport connect worker in order + * to serialize with rpcrdma_register_fmr_external(). + */ +static void +rpcrdma_reset_fmrs(struct rpcrdma_ia *ia) +{ + struct rpcrdma_xprt *r_xprt = + container_of(ia, struct rpcrdma_xprt, rx_ia); + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct list_head *pos; + struct rpcrdma_mw *r; + LIST_HEAD(l); + int rc; + + list_for_each(pos, &buf->rb_all) { + r = list_entry(pos, struct rpcrdma_mw, mw_all); + + INIT_LIST_HEAD(&l); + list_add(&r->r.fmr->list, &l); + rc = ib_unmap_fmr(&l); + if (rc) + dprintk("RPC: %s: ib_unmap_fmr failed %i\n", + __func__, rc); + } +} + /* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in * an unusable state. Find FRMRs in this state and dereg / reg * each. FRMRs that are VALID and attached to an rpcrdma_req are @@ -1918,10 +2002,10 @@ rpcrdma_register_external(struct rpcrdma_mr_seg *seg, break; default: - return -1; + return -EIO; } if (rc) - return -1; + return rc; return nsegs; } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index ac7fc9a31342..b799041b75bf 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -97,6 +97,12 @@ struct rpcrdma_ep { struct ib_wc rep_recv_wcs[RPCRDMA_POLLSIZE]; }; +/* + * Force a signaled SEND Work Request every so often, + * in case the provider needs to do some housekeeping. + */ +#define RPCRDMA_MAX_UNSIGNALED_SENDS (32) + #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 3b305ab17afe..87ce7e8bb8dc 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -75,7 +75,7 @@ static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; * someone else's file names! */ -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE; static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE; @@ -186,7 +186,7 @@ static struct ctl_table sunrpc_table[] = { */ #define XS_IDLE_DISC_TO (5U * 60 * HZ) -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # undef RPC_DEBUG_DATA # define RPCDBG_FACILITY RPCDBG_TRANS #endif @@ -216,65 +216,6 @@ static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count) } #endif -struct sock_xprt { - struct rpc_xprt xprt; - - /* - * Network layer - */ - struct socket * sock; - struct sock * inet; - - /* - * State of TCP reply receive - */ - __be32 tcp_fraghdr, - tcp_xid, - tcp_calldir; - - u32 tcp_offset, - tcp_reclen; - - unsigned long tcp_copied, - tcp_flags; - - /* - * Connection of transports - */ - struct delayed_work connect_worker; - struct sockaddr_storage srcaddr; - unsigned short srcport; - - /* - * UDP socket buffer size parameters - */ - size_t rcvsize, - sndsize; - - /* - * Saved socket callback addresses - */ - void (*old_data_ready)(struct sock *); - void (*old_state_change)(struct sock *); - void (*old_write_space)(struct sock *); - void (*old_error_report)(struct sock *); -}; - -/* - * TCP receive state flags - */ -#define TCP_RCV_LAST_FRAG (1UL << 0) -#define TCP_RCV_COPY_FRAGHDR (1UL << 1) -#define TCP_RCV_COPY_XID (1UL << 2) -#define TCP_RCV_COPY_DATA (1UL << 3) -#define TCP_RCV_READ_CALLDIR (1UL << 4) -#define TCP_RCV_COPY_CALLDIR (1UL << 5) - -/* - * TCP RPC flags - */ -#define TCP_RPC_REPLY (1UL << 6) - static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) { return (struct rpc_xprt *) sk->sk_user_data; @@ -1415,6 +1356,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns dprintk("RPC: xs_tcp_data_recv started\n"); do { + trace_xs_tcp_data_recv(transport); /* Read in a new fragment marker if necessary */ /* Can we ever really expect to get completely empty fragments? */ if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) { @@ -1439,6 +1381,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns /* Skip over any trailing bytes on short reads */ xs_tcp_read_discard(transport, &desc); } while (desc.count); + trace_xs_tcp_data_recv(transport); dprintk("RPC: xs_tcp_data_recv done\n"); return len - desc.count; } @@ -1454,12 +1397,15 @@ static void xs_tcp_data_ready(struct sock *sk) struct rpc_xprt *xprt; read_descriptor_t rd_desc; int read; + unsigned long total = 0; dprintk("RPC: xs_tcp_data_ready...\n"); read_lock_bh(&sk->sk_callback_lock); - if (!(xprt = xprt_from_sock(sk))) + if (!(xprt = xprt_from_sock(sk))) { + read = 0; goto out; + } /* Any data means we had a useful conversation, so * the we don't need to delay the next reconnect */ @@ -1471,8 +1417,11 @@ static void xs_tcp_data_ready(struct sock *sk) do { rd_desc.count = 65536; read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv); + if (read > 0) + total += read; } while (read > 0); out: + trace_xs_tcp_data_ready(xprt, read, total); read_unlock_bh(&sk->sk_callback_lock); } @@ -3042,7 +2991,7 @@ static struct xprt_class xs_bc_tcp_transport = { */ int init_socket_xprt(void) { -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (!sunrpc_table_header) sunrpc_table_header = register_sysctl_table(sunrpc_table); #endif @@ -3061,7 +3010,7 @@ int init_socket_xprt(void) */ void cleanup_socket_xprt(void) { -#ifdef RPC_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (sunrpc_table_header) { unregister_sysctl_table(sunrpc_table_header); sunrpc_table_header = NULL; diff --git a/security/commoncap.c b/security/commoncap.c index bab0611afc1e..2915d8503054 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -446,7 +446,7 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_c if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) return 0; - dentry = dget(bprm->file->f_dentry); + dentry = dget(bprm->file->f_path.dentry); rc = get_vfs_caps_from_disk(dentry, &vcaps); if (rc < 0) { diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index 86885979918c..f92be1b14089 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -196,7 +196,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, { const char *audit_cause = "failed"; struct inode *inode = file_inode(file); - const char *filename = file->f_dentry->d_name.name; + const char *filename = file->f_path.dentry->d_name.name; int result = 0; struct { struct ima_digest_data hdr; @@ -204,7 +204,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, } hash; if (xattr_value) - *xattr_len = ima_read_xattr(file->f_dentry, xattr_value); + *xattr_len = ima_read_xattr(file->f_path.dentry, xattr_value); if (!(iint->flags & IMA_COLLECTED)) { u64 i_version = file_inode(file)->i_version; diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 7c8f41e618b6..fffcdb0b31f0 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -189,7 +189,7 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint, { static const char op[] = "appraise_data"; char *cause = "unknown"; - struct dentry *dentry = file->f_dentry; + struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; enum integrity_status status = INTEGRITY_UNKNOWN; int rc = xattr_len, hash_start = 0; @@ -289,7 +289,7 @@ out: */ void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file) { - struct dentry *dentry = file->f_dentry; + struct dentry *dentry = file->f_path.dentry; int rc = 0; /* do not collect and update hash for digital signatures */ diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 1506f0248572..bcfc36cbde6a 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -284,7 +284,7 @@ static int ima_eventname_init_common(struct integrity_iint_cache *iint, } if (file) { - cur_filename = file->f_dentry->d_name.name; + cur_filename = file->f_path.dentry->d_name.name; cur_filename_len = strlen(cur_filename); } else /* diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index c71737f6d1cc..33db1ad4fd10 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1200,7 +1200,7 @@ static void sel_remove_entries(struct dentry *de) spin_lock(&de->d_lock); node = de->d_subdirs.next; while (node != &de->d_subdirs) { - struct dentry *d = list_entry(node, struct dentry, d_u.d_child); + struct dentry *d = list_entry(node, struct dentry, d_child); spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); list_del_init(node); @@ -1674,12 +1674,12 @@ static void sel_remove_classes(void) list_for_each(class_node, &class_dir->d_subdirs) { struct dentry *class_subdir = list_entry(class_node, - struct dentry, d_u.d_child); + struct dentry, d_child); struct list_head *class_subdir_node; list_for_each(class_subdir_node, &class_subdir->d_subdirs) { struct dentry *d = list_entry(class_subdir_node, - struct dentry, d_u.d_child); + struct dentry, d_child); if (d->d_inode) if (d->d_inode->i_mode & S_IFDIR) diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index d515ec25ae9f..433ae61e7f42 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -166,9 +166,9 @@ static int smk_bu_file(struct file *file, int mode, int rc) return rc; smk_bu_mode(mode, acc); - pr_info("Smack Bringup: (%s %s %s) file=(%s %ld %s) %s\n", + pr_info("Smack Bringup: (%s %s %s) file=(%s %ld %pD) %s\n", sskp->smk_known, (char *)file->f_security, acc, - inode->i_sb->s_id, inode->i_ino, file->f_dentry->d_name.name, + inode->i_sb->s_id, inode->i_ino, file, current->comm); return 0; } @@ -189,9 +189,9 @@ static int smk_bu_credfile(const struct cred *cred, struct file *file, return rc; smk_bu_mode(mode, acc); - pr_info("Smack Bringup: (%s %s %s) file=(%s %ld %s) %s\n", + pr_info("Smack Bringup: (%s %s %s) file=(%s %ld %pD) %s\n", sskp->smk_known, smk_of_inode(inode)->smk_known, acc, - inode->i_sb->s_id, inode->i_ino, file->f_dentry->d_name.name, + inode->i_sb->s_id, inode->i_ino, file, current->comm); return 0; } |