diff options
234 files changed, 30096 insertions, 1609 deletions
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 3c384c0cf86..4dc28cc9350 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -34,6 +34,8 @@ ext2.txt - info, mount options and specifications for the Ext2 filesystem. ext3.txt - info, mount options and specifications for the Ext3 filesystem. +ext4.txt + - info, mount options and specifications for the Ext4 filesystem. files.txt - info on file management in the Linux kernel. fuse.txt diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt new file mode 100644 index 00000000000..6a4adcae9f9 --- /dev/null +++ b/Documentation/filesystems/ext4.txt @@ -0,0 +1,236 @@ + +Ext4 Filesystem +=============== + +This is a development version of the ext4 filesystem, an advanced level +of the ext3 filesystem which incorporates scalability and reliability +enhancements for supporting large filesystems (64 bit) in keeping with +increasing disk capacities and state-of-the-art feature requirements. + +Mailing list: linux-ext4@vger.kernel.org + + +1. Quick usage instructions: +=========================== + + - Grab updated e2fsprogs from + ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs-interim/ + This is a patchset on top of e2fsprogs-1.39, which can be found at + ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/ + + - It's still mke2fs -j /dev/hda1 + + - mount /dev/hda1 /wherever -t ext4dev + + - To enable extents, + + mount /dev/hda1 /wherever -t ext4dev -o extents + + - The filesystem is compatible with the ext3 driver until you add a file + which has extents (ie: `mount -o extents', then create a file). + + NOTE: The "extents" mount flag is temporary. It will soon go away and + extents will be enabled by the "-o extents" flag to mke2fs or tune2fs + + - When comparing performance with other filesystems, remember that + ext3/4 by default offers higher data integrity guarantees than most. So + when comparing with a metadata-only journalling filesystem, use `mount -o + data=writeback'. And you might as well use `mount -o nobh' too along + with it. Making the journal larger than the mke2fs default often helps + performance with metadata-intensive workloads. + +2. Features +=========== + +2.1 Currently available + +* ability to use filesystems > 16TB +* extent format reduces metadata overhead (RAM, IO for access, transactions) +* extent format more robust in face of on-disk corruption due to magics, +* internal redunancy in tree + +2.1 Previously available, soon to be enabled by default by "mkefs.ext4": + +* dir_index and resize inode will be on by default +* large inodes will be used by default for fast EAs, nsec timestamps, etc + +2.2 Candidate features for future inclusion + +There are several under discussion, whether they all make it in is +partly a function of how much time everyone has to work on them: + +* improved file allocation (multi-block alloc, delayed alloc; basically done) +* fix 32000 subdirectory limit (patch exists, needs some e2fsck work) +* nsec timestamps for mtime, atime, ctime, create time (patch exists, + needs some e2fsck work) +* inode version field on disk (NFSv4, Lustre; prototype exists) +* reduced mke2fs/e2fsck time via uninitialized groups (prototype exists) +* journal checksumming for robustness, performance (prototype exists) +* persistent file preallocation (e.g for streaming media, databases) + +Features like metadata checksumming have been discussed and planned for +a bit but no patches exist yet so I'm not sure they're in the near-term +roadmap. + +The big performance win will come with mballoc and delalloc. CFS has +been using mballoc for a few years already with Lustre, and IBM + Bull +did a lot of benchmarking on it. The reason it isn't in the first set of +patches is partly a manageability issue, and partly because it doesn't +directly affect the on-disk format (outside of much better allocation) +so it isn't critical to get into the first round of changes. I believe +Alex is working on a new set of patches right now. + +3. Options +========== + +When mounting an ext4 filesystem, the following option are accepted: +(*) == default + +extents ext4 will use extents to address file data. The + file system will no longer be mountable by ext3. + +journal=update Update the ext4 file system's journal to the current + format. + +journal=inum When a journal already exists, this option is ignored. + Otherwise, it specifies the number of the inode which + will represent the ext4 file system's journal file. + +journal_dev=devnum When the external journal device's major/minor numbers + have changed, this option allows the user to specify + the new journal location. The journal device is + identified through its new major/minor numbers encoded + in devnum. + +noload Don't load the journal on mounting. + +data=journal All data are committed into the journal prior to being + written into the main file system. + +data=ordered (*) All data are forced directly out to the main file + system prior to its metadata being committed to the + journal. + +data=writeback Data ordering is not preserved, data may be written + into the main file system after its metadata has been + committed to the journal. + +commit=nrsec (*) Ext4 can be told to sync all its data and metadata + every 'nrsec' seconds. The default value is 5 seconds. + This means that if you lose your power, you will lose + as much as the latest 5 seconds of work (your + filesystem will not be damaged though, thanks to the + journaling). This default value (or any low value) + will hurt performance, but it's good for data-safety. + Setting it to 0 will have the same effect as leaving + it at the default (5 seconds). + Setting it to very large values will improve + performance. + +barrier=1 This enables/disables barriers. barrier=0 disables + it, barrier=1 enables it. + +orlov (*) This enables the new Orlov block allocator. It is + enabled by default. + +oldalloc This disables the Orlov block allocator and enables + the old block allocator. Orlov should have better + performance - we'd like to get some feedback if it's + the contrary for you. + +user_xattr Enables Extended User Attributes. Additionally, you + need to have extended attribute support enabled in the + kernel configuration (CONFIG_EXT4_FS_XATTR). See the + attr(5) manual page and http://acl.bestbits.at/ to + learn more about extended attributes. + +nouser_xattr Disables Extended User Attributes. + +acl Enables POSIX Access Control Lists support. + Additionally, you need to have ACL support enabled in + the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL). + See the acl(5) manual page and http://acl.bestbits.at/ + for more information. + +noacl This option disables POSIX Access Control List + support. + +reservation + +noreservation + +bsddf (*) Make 'df' act like BSD. +minixdf Make 'df' act like Minix. + +check=none Don't do extra checking of bitmaps on mount. +nocheck + +debug Extra debugging information is sent to syslog. + +errors=remount-ro(*) Remount the filesystem read-only on an error. +errors=continue Keep going on a filesystem error. +errors=panic Panic and halt the machine if an error occurs. + +grpid Give objects the same group ID as their creator. +bsdgroups + +nogrpid (*) New objects have the group ID of their creator. +sysvgroups + +resgid=n The group ID which may use the reserved blocks. + +resuid=n The user ID which may use the reserved blocks. + +sb=n Use alternate superblock at this location. + +quota +noquota +grpquota +usrquota + +bh (*) ext4 associates buffer heads to data pages to +nobh (a) cache disk block mapping information + (b) link pages into transaction to provide + ordering guarantees. + "bh" option forces use of buffer heads. + "nobh" option tries to avoid associating buffer + heads (supported only for "writeback" mode). + + +Data Mode +--------- +There are 3 different data modes: + +* writeback mode +In data=writeback mode, ext4 does not journal data at all. This mode provides +a similar level of journaling as that of XFS, JFS, and ReiserFS in its default +mode - metadata journaling. A crash+recovery can cause incorrect data to +appear in files which were written shortly before the crash. This mode will +typically provide the best ext4 performance. + +* ordered mode +In data=ordered mode, ext4 only officially journals metadata, but it logically +groups metadata and data blocks into a single unit called a transaction. When +it's time to write the new metadata out to disk, the associated data blocks +are written first. In general, this mode performs slightly slower than +writeback but significantly faster than journal mode. + +* journal mode +data=journal mode provides full data and metadata journaling. All new data is +written to the journal first, and then to its final location. +In the event of a crash, the journal can be replayed, bringing both data and +metadata into a consistent state. This mode is the slowest except when data +needs to be read from and written to disk at the same time where it +outperforms all others modes. + +References +========== + +kernel source: <file:fs/ext4/> + <file:fs/jbd2/> + +programs: http://e2fsprogs.sourceforge.net/ + http://ext2resize.sourceforge.net + +useful links: http://fedoraproject.org/wiki/ext3-devel + http://www.bullopensource.org/ext4/ diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt index dab123db5a4..48877301815 100644 --- a/Documentation/lockdep-design.txt +++ b/Documentation/lockdep-design.txt @@ -50,10 +50,10 @@ The bit position indicates hardirq, softirq, hardirq-read, softirq-read respectively, and the character displayed in each indicates: - '.' acquired while irqs enabled + '.' acquired while irqs disabled '+' acquired in irq context - '-' acquired in process context with irqs disabled - '?' read-acquired both with irqs enabled and in irq context + '-' acquired with irqs enabled + '?' read acquired in irq context with irqs enabled. Unused mutexes cannot be part of the cause of an error. diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 89bf8c20a58..0bc7f1e3c9e 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -86,7 +86,7 @@ valid for 30 seconds. core_pattern: core_pattern is used to specify a core dumpfile pattern name. -. max length 64 characters; default value is "core" +. max length 128 characters; default value is "core" . core_pattern is used as a pattern template for the output filename; certain string patterns (beginning with '%') are substituted with their actual values. @@ -105,6 +105,9 @@ core_pattern is used to specify a core dumpfile pattern name. %h hostname %e executable filename %<OTHER> both are dropped +. If the first character of the pattern is a '|', the kernel will treat + the rest of the pattern as a command to run. The core dump will be + written to the standard input of that program instead of to a file. ============================================================== @@ -741,6 +741,9 @@ endif # ifdef CONFIG_KALLSYMS # vmlinux image - including updated kernel symbols vmlinux: $(vmlinux-lds) $(vmlinux-init) $(vmlinux-main) $(kallsyms.o) FORCE +ifdef CONFIG_HEADERS_CHECK + $(Q)$(MAKE) headers_check +endif $(call if_changed_rule,vmlinux__) $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost $@ $(Q)rm -f .old_version diff --git a/arch/alpha/kernel/alpha_ksyms.c b/arch/alpha/kernel/alpha_ksyms.c index 8b02420f732..692809e4aec 100644 --- a/arch/alpha/kernel/alpha_ksyms.c +++ b/arch/alpha/kernel/alpha_ksyms.c @@ -6,41 +6,14 @@ */ #include <linux/module.h> -#include <linux/string.h> -#include <linux/user.h> -#include <linux/elfcore.h> -#include <linux/socket.h> -#include <linux/syscalls.h> -#include <linux/in.h> -#include <linux/in6.h> -#include <linux/pci.h> -#include <linux/screen_info.h> -#include <linux/tty.h> -#include <linux/mm.h> -#include <linux/delay.h> -#include <linux/dma-mapping.h> - -#include <asm/io.h> #include <asm/console.h> -#include <asm/hwrpb.h> #include <asm/uaccess.h> -#include <asm/processor.h> #include <asm/checksum.h> -#include <linux/interrupt.h> #include <asm/fpu.h> -#include <asm/irq.h> #include <asm/machvec.h> -#include <asm/pgalloc.h> -#include <asm/semaphore.h> -#include <asm/tlbflush.h> -#include <asm/cacheflush.h> -#include <asm/vga.h> #include <asm/unistd.h> -extern struct hwrpb_struct *hwrpb; -extern spinlock_t rtc_lock; - /* these are C runtime functions with special calling conventions: */ extern void __divl (void); extern void __reml (void); @@ -52,14 +25,9 @@ extern void __divqu (void); extern void __remqu (void); EXPORT_SYMBOL(alpha_mv); -EXPORT_SYMBOL(screen_info); -EXPORT_SYMBOL(perf_irq); EXPORT_SYMBOL(callback_getenv); EXPORT_SYMBOL(callback_setenv); EXPORT_SYMBOL(callback_save_env); -#ifdef CONFIG_ALPHA_GENERIC -EXPORT_SYMBOL(alpha_using_srm); -#endif /* CONFIG_ALPHA_GENERIC */ /* platform dependent support */ EXPORT_SYMBOL(strcat); @@ -77,47 +45,14 @@ EXPORT_SYMBOL(__constant_c_memset); EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); -EXPORT_SYMBOL(__direct_map_base); -EXPORT_SYMBOL(__direct_map_size); - -#ifdef CONFIG_PCI -EXPORT_SYMBOL(pci_alloc_consistent); -EXPORT_SYMBOL(pci_free_consistent); -EXPORT_SYMBOL(pci_map_single); -EXPORT_SYMBOL(pci_map_page); -EXPORT_SYMBOL(pci_unmap_single); -EXPORT_SYMBOL(pci_unmap_page); -EXPORT_SYMBOL(pci_map_sg); -EXPORT_SYMBOL(pci_unmap_sg); -EXPORT_SYMBOL(pci_dma_supported); -EXPORT_SYMBOL(pci_dac_dma_supported); -EXPORT_SYMBOL(pci_dac_page_to_dma); -EXPORT_SYMBOL(pci_dac_dma_to_page); -EXPORT_SYMBOL(pci_dac_dma_to_offset); -EXPORT_SYMBOL(alpha_gendev_to_pci); -#endif -EXPORT_SYMBOL(dma_set_mask); - -EXPORT_SYMBOL(dump_thread); -EXPORT_SYMBOL(dump_elf_thread); -EXPORT_SYMBOL(dump_elf_task); -EXPORT_SYMBOL(dump_elf_task_fp); -EXPORT_SYMBOL(hwrpb); -EXPORT_SYMBOL(start_thread); EXPORT_SYMBOL(alpha_read_fp_reg); EXPORT_SYMBOL(alpha_read_fp_reg_s); EXPORT_SYMBOL(alpha_write_fp_reg); EXPORT_SYMBOL(alpha_write_fp_reg_s); -/* In-kernel system calls. */ +/* entry.S */ EXPORT_SYMBOL(kernel_thread); -EXPORT_SYMBOL(sys_dup); -EXPORT_SYMBOL(sys_exit); -EXPORT_SYMBOL(sys_write); -EXPORT_SYMBOL(sys_lseek); EXPORT_SYMBOL(kernel_execve); -EXPORT_SYMBOL(sys_setsid); -EXPORT_SYMBOL(sys_wait4); /* Networking helper routines. */ EXPORT_SYMBOL(csum_tcpudp_magic); @@ -134,10 +69,6 @@ EXPORT_SYMBOL(alpha_fp_emul_imprecise); EXPORT_SYMBOL(alpha_fp_emul); #endif -#ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK -EXPORT_SYMBOL(__min_ipl); -#endif - /* * The following are specially called from the uaccess assembly stubs. */ @@ -160,27 +91,10 @@ EXPORT_SYMBOL(up); */ #ifdef CONFIG_SMP -EXPORT_SYMBOL(flush_tlb_mm); -EXPORT_SYMBOL(flush_tlb_range); -EXPORT_SYMBOL(flush_tlb_page); -EXPORT_SYMBOL(smp_imb); -EXPORT_SYMBOL(cpu_data); -EXPORT_SYMBOL(smp_num_cpus); -EXPORT_SYMBOL(smp_call_function); -EXPORT_SYMBOL(smp_call_function_on_cpu); EXPORT_SYMBOL(_atomic_dec_and_lock); #endif /* CONFIG_SMP */ /* - * NUMA specific symbols - */ -#ifdef CONFIG_DISCONTIGMEM -EXPORT_SYMBOL(node_data); -#endif /* CONFIG_DISCONTIGMEM */ - -EXPORT_SYMBOL(rtc_lock); - -/* * The following are special because they're not called * explicitly (the C compiler or assembler generates them in * response to division operations). Fortunately, their @@ -200,8 +114,3 @@ EXPORT_SYMBOL(__remqu); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memchr); - -#ifdef CONFIG_ALPHA_IRONGATE -EXPORT_SYMBOL(irongate_ioremap); -EXPORT_SYMBOL(irongate_iounmap); -#endif diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index 138d497d1cc..e4a0bcf1d28 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -404,6 +404,7 @@ irongate_ioremap(unsigned long addr, unsigned long size) #endif return (void __iomem *)vaddr; } +EXPORT_SYMBOL(irongate_ioremap); void irongate_iounmap(volatile void __iomem *xaddr) @@ -414,3 +415,4 @@ irongate_iounmap(volatile void __iomem *xaddr) if (addr) return vfree((void *)(PAGE_MASK & addr)); } +EXPORT_SYMBOL(irongate_iounmap); diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 6dd126b8be8..e16aeb6e79e 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/irq.h> #include <linux/kernel_stat.h> +#include <linux/module.h> #include <asm/machvec.h> #include <asm/dma.h> @@ -16,6 +17,7 @@ /* Hack minimum IPL during interrupt processing for broken hardware. */ #ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK int __min_ipl; +EXPORT_SYMBOL(__min_ipl); #endif /* @@ -30,6 +32,7 @@ dummy_perf(unsigned long vector, struct pt_regs *regs) } void (*perf_irq)(unsigned long, struct pt_regs *) = dummy_perf; +EXPORT_SYMBOL(perf_irq); /* * The main interrupt entry point. diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c index fff5cf93e81..174b729c504 100644 --- a/arch/alpha/kernel/pci-noop.c +++ b/arch/alpha/kernel/pci-noop.c @@ -201,6 +201,7 @@ dma_set_mask(struct device *dev, u64 mask) return 0; } +EXPORT_SYMBOL(dma_set_mask); void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen) { diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index c468e312e5f..6e7d1fe6e93 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -300,6 +300,7 @@ pci_map_single(struct pci_dev *pdev, void *cpu_addr, size_t size, int dir) dac_allowed = pdev ? pci_dac_dma_supported(pdev, pdev->dma_mask) : 0; return pci_map_single_1(pdev, cpu_addr, size, dac_allowed); } +EXPORT_SYMBOL(pci_map_single); dma_addr_t pci_map_page(struct pci_dev *pdev, struct page *page, unsigned long offset, @@ -314,6 +315,7 @@ pci_map_page(struct pci_dev *pdev, struct page *page, unsigned long offset, return pci_map_single_1(pdev, (char *)page_address(page) + offset, size, dac_allowed); } +EXPORT_SYMBOL(pci_map_page); /* Unmap a single streaming mode DMA translation. The DMA_ADDR and SIZE must match what was provided for in a previous pci_map_single @@ -379,6 +381,7 @@ pci_unmap_single(struct pci_dev *pdev, dma_addr_t dma_addr, size_t size, DBGA2("pci_unmap_single: sg [%lx,%lx] np %ld from %p\n", dma_addr, size, npages, __builtin_return_address(0)); } +EXPORT_SYMBOL(pci_unmap_single); void pci_unmap_page(struct pci_dev *pdev, dma_addr_t dma_addr, @@ -386,6 +389,7 @@ pci_unmap_page(struct pci_dev *pdev, dma_addr_t dma_addr, { pci_unmap_single(pdev, dma_addr, size, direction); } +EXPORT_SYMBOL(pci_unmap_page); /* Allocate and map kernel buffer using consistent mode DMA for PCI device. Returns non-NULL cpu-view pointer to the buffer if @@ -427,6 +431,7 @@ try_again: return cpu_addr; } +EXPORT_SYMBOL(pci_alloc_consistent); /* Free and unmap a consistent DMA buffer. CPU_ADDR and DMA_ADDR must be values that were returned from pci_alloc_consistent. SIZE must @@ -444,7 +449,7 @@ pci_free_consistent(struct pci_dev *pdev, size_t size, void *cpu_addr, DBGA2("pci_free_consistent: [%x,%lx] from %p\n", dma_addr, size, __builtin_return_address(0)); } - +EXPORT_SYMBOL(pci_free_consistent); /* Classify the elements of the scatterlist. Write dma_address of each element with: @@ -672,6 +677,7 @@ pci_map_sg(struct pci_dev *pdev, struct scatterlist *sg, int nents, pci_unmap_sg(pdev, start, out - start, direction); return 0; } +EXPORT_SYMBOL(pci_map_sg); /* Unmap a set of streaming mode DMA translations. Again, cpu read rules concerning calls here are the same as for pci_unmap_single() @@ -752,6 +758,7 @@ pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sg, int nents, DBGA("pci_unmap_sg: %ld entries\n", nents - (end - sg)); } +EXPORT_SYMBOL(pci_unmap_sg); /* Return whether the given PCI device DMA address mask can be @@ -786,6 +793,7 @@ pci_dma_supported(struct pci_dev *pdev, u64 mask) return 0; } +EXPORT_SYMBOL(pci_dma_supported); /* @@ -908,6 +916,7 @@ pci_dac_dma_supported(struct pci_dev *dev, u64 mask) return ok; } +EXPORT_SYMBOL(pci_dac_dma_supported); dma64_addr_t pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, @@ -917,6 +926,7 @@ pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, + __pa(page_address(page)) + (dma64_addr_t) offset); } +EXPORT_SYMBOL(pci_dac_page_to_dma); struct page * pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr) @@ -924,13 +934,14 @@ pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr) unsigned long paddr = (dma_addr & PAGE_MASK) - alpha_mv.pci_dac_offset; return virt_to_page(__va(paddr)); } +EXPORT_SYMBOL(pci_dac_dma_to_page); unsigned long pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr) { return (dma_addr & ~PAGE_MASK); } - +EXPORT_SYMBOL(pci_dac_dma_to_offset); /* Helper for generic DMA-mapping functions. */ @@ -957,6 +968,7 @@ alpha_gendev_to_pci(struct device *dev) /* This assumes ISA bus master with dma_mask 0xffffff. */ return NULL; } +EXPORT_SYMBOL(alpha_gendev_to_pci); int dma_set_mask(struct device *dev, u64 mask) @@ -969,3 +981,4 @@ dma_set_mask(struct device *dev, u64 mask) return 0; } +EXPORT_SYMBOL(dma_set_mask); diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index b3a8a298036..3370e6faeae 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -205,6 +205,7 @@ start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) regs->ps = 8; wrusp(sp); } +EXPORT_SYMBOL(start_thread); /* * Free current thread data structures etc.. @@ -376,6 +377,7 @@ dump_thread(struct pt_regs * pt, struct user * dump) dump->regs[EF_A2] = pt->r18; memcpy((char *)dump->regs + EF_SIZE, sw->fp, 32 * 8); } +EXPORT_SYMBOL(dump_thread); /* * Fill in the user structure for a ELF core dump. @@ -424,6 +426,7 @@ dump_elf_thread(elf_greg_t *dest, struct pt_regs *pt, struct thread_info *ti) useful value of the thread's UNIQUE field. */ dest[32] = ti->pcb.unique; } +EXPORT_SYMBOL(dump_elf_thread); int dump_elf_task(elf_greg_t *dest, struct task_struct *task) @@ -431,6 +434,7 @@ dump_elf_task(elf_greg_t *dest, struct task_struct *task) dump_elf_thread(dest, task_pt_regs(task), task_thread_info(task)); return 1; } +EXPORT_SYMBOL(dump_elf_task); int dump_elf_task_fp(elf_fpreg_t *dest, struct task_struct *task) @@ -439,6 +443,7 @@ dump_elf_task_fp(elf_fpreg_t *dest, struct task_struct *task) memcpy(dest, sw->fp, 32 * 8); return 1; } +EXPORT_SYMBOL(dump_elf_task_fp); /* * sys_execve() executes a new program. diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index a94e6d93e2e..1aea7c7c683 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -66,6 +66,7 @@ static struct notifier_block alpha_panic_block = { struct hwrpb_struct *hwrpb; +EXPORT_SYMBOL(hwrpb); unsigned long srm_hae; int alpha_l1i_cacheshape; @@ -111,6 +112,7 @@ unsigned long alpha_agpgart_size = DEFAULT_AGP_APER_SIZE; #ifdef CONFIG_ALPHA_GENERIC struct alpha_machine_vector alpha_mv; int alpha_using_srm; +EXPORT_SYMBOL(alpha_using_srm); #endif static struct alpha_machine_vector *get_sysvec(unsigned long, unsigned long, @@ -137,6 +139,8 @@ struct screen_info screen_info = { .orig_video_points = 16 }; +EXPORT_SYMBOL(screen_info); + /* * The direct map I/O window, if any. This should be the same * for all busses, since it's used by virt_to_bus. @@ -144,6 +148,8 @@ struct screen_info screen_info = { unsigned long __direct_map_base; unsigned long __direct_map_size; +EXPORT_SYMBOL(__direct_map_base); +EXPORT_SYMBOL(__direct_map_size); /* * Declare all of the machine vectors. diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 596780e2c7d..d1ec4f51df1 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -52,6 +52,7 @@ /* A collection of per-processor data. */ struct cpuinfo_alpha cpu_data[NR_CPUS]; +EXPORT_SYMBOL(cpu_data); /* A collection of single bit ipi messages. */ static struct { @@ -74,6 +75,7 @@ EXPORT_SYMBOL(cpu_online_map); int smp_num_probed; /* Internal processor count */ int smp_num_cpus = 1; /* Number that came online. */ +EXPORT_SYMBOL(smp_num_cpus); extern void calibrate_delay(void); @@ -790,6 +792,7 @@ smp_call_function_on_cpu (void (*func) (void *info), void *info, int retry, return 0; } +EXPORT_SYMBOL(smp_call_function_on_cpu); int smp_call_function (void (*func) (void *info), void *info, int retry, int wait) @@ -797,6 +800,7 @@ smp_call_function (void (*func) (void *info), void *info, int retry, int wait) return smp_call_function_on_cpu (func, info, retry, wait, cpu_online_map); } +EXPORT_SYMBOL(smp_call_function); static void ipi_imb(void *ignored) @@ -811,6 +815,7 @@ smp_imb(void) if (on_each_cpu(ipi_imb, NULL, 1, 1)) printk(KERN_CRIT "smp_imb: timed out\n"); } +EXPORT_SYMBOL(smp_imb); static void ipi_flush_tlb_all(void *ignored) @@ -866,6 +871,7 @@ flush_tlb_mm(struct mm_struct *mm) preempt_enable(); } +EXPORT_SYMBOL(flush_tlb_mm); struct flush_tlb_page_struct { struct vm_area_struct *vma; @@ -918,6 +924,7 @@ flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) preempt_enable(); } +EXPORT_SYMBOL(flush_tlb_page); void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) @@ -925,6 +932,7 @@ flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long e /* On the Alpha we always flush the whole user tlb. */ flush_tlb_mm(vma->vm_mm); } +EXPORT_SYMBOL(flush_tlb_range); static void ipi_flush_icache_page(void *x) diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index cf066652398..d7053eb4ffc 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -57,6 +57,7 @@ static int set_rtc_mmss(unsigned long); DEFINE_SPINLOCK(rtc_lock); +EXPORT_SYMBOL(rtc_lock); #define TICK_SIZE (tick_nsec / 1000) diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index b826f58c6e7..e3e3806a6f2 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -13,12 +13,14 @@ #include <linux/swap.h> #include <linux/initrd.h> #include <linux/pfn.h> +#include <linux/module.h> #include <asm/hwrpb.h> #include <asm/pgalloc.h> pg_data_t node_data[MAX_NUMNODES]; bootmem_data_t node_bdata[MAX_NUMNODES]; +EXPORT_SYMBOL(node_data); #undef DEBUG_DISCONTIG #ifdef DEBUG_DISCONTIG diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index da69e660574..4779f474f91 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -178,9 +178,3 @@ EXPORT_SYMBOL(_find_next_zero_bit_be); EXPORT_SYMBOL(_find_first_bit_be); EXPORT_SYMBOL(_find_next_bit_be); #endif - - /* syscalls */ -EXPORT_SYMBOL(sys_write); -EXPORT_SYMBOL(sys_lseek); -EXPORT_SYMBOL(sys_exit); -EXPORT_SYMBOL(sys_wait4); diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c index 2aa150b57ba..3b8576111c1 100644 --- a/arch/arm/mach-versatile/core.c +++ b/arch/arm/mach-versatile/core.c @@ -188,12 +188,12 @@ static struct map_desc versatile_io_desc[] __initdata = { .length = SZ_4K, .type = MT_DEVICE }, { - .virtual = VERSATILE_PCI_VIRT_BASE, + .virtual = (unsigned long)VERSATILE_PCI_VIRT_BASE, .pfn = __phys_to_pfn(VERSATILE_PCI_BASE), .length = VERSATILE_PCI_BASE_SIZE, .type = MT_DEVICE }, { - .virtual = VERSATILE_PCI_CFG_VIRT_BASE, + .virtual = (unsigned long)VERSATILE_PCI_CFG_VIRT_BASE, .pfn = __phys_to_pfn(VERSATILE_PCI_CFG_BASE), .length = VERSATILE_PCI_CFG_BASE_SIZE, .type = MT_DEVICE diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c index 13bbd08ff84..5cd0b5d9e7e 100644 --- a/arch/arm/mach-versatile/pci.c +++ b/arch/arm/mach-versatile/pci.c @@ -40,14 +40,15 @@ * Cfg 42000000 - 42FFFFFF PCI config * */ -#define SYS_PCICTL IO_ADDRESS(VERSATILE_SYS_PCICTL) -#define PCI_IMAP0 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0) -#define PCI_IMAP1 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4) -#define PCI_IMAP2 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8) -#define PCI_SMAP0 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10) -#define PCI_SMAP1 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14) -#define PCI_SMAP2 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18) -#define PCI_SELFID IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc) +#define __IO_ADDRESS(n) ((void __iomem *)(unsigned long)IO_ADDRESS(n)) +#define SYS_PCICTL __IO_ADDRESS(VERSATILE_SYS_PCICTL) +#define PCI_IMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0) +#define PCI_IMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4) +#define PCI_IMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8) +#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10) +#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14) +#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18) +#define PCI_SELFID __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc) #define DEVICE_ID_OFFSET 0x00 #define CSR_OFFSET 0x04 @@ -76,7 +77,7 @@ static int __init versatile_pci_slot_ignore(char *str) __setup("pci_slot_ignore=", versatile_pci_slot_ignore); -static unsigned long __pci_addr(struct pci_bus *bus, +static void __iomem *__pci_addr(struct pci_bus *bus, unsigned int devfn, int offset) { unsigned int busnr = bus->number; @@ -91,14 +92,14 @@ static unsigned long __pci_addr(struct pci_bus *bus, if (devfn > 255) BUG(); - return (VERSATILE_PCI_CFG_VIRT_BASE | (busnr << 16) | + return VERSATILE_PCI_CFG_VIRT_BASE + ((busnr << 16) | (PCI_SLOT(devfn) << 11) | (PCI_FUNC(devfn) << 8) | offset); } static int versatile_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - unsigned long addr = __pci_addr(bus, devfn, where); + void __iomem *addr = __pci_addr(bus, devfn, where & ~3); u32 v; int slot = PCI_SLOT(devfn); @@ -121,13 +122,12 @@ static int versatile_read_config(struct pci_bus *bus, unsigned int devfn, int wh break; case 2: - v = __raw_readl(addr & ~3); - if (addr & 2) v >>= 16; + v = __raw_readl(addr); + if (where & 2) v >>= 16; v &= 0xffff; break; default: - addr &= ~3; v = __raw_readl(addr); break; } @@ -140,7 +140,7 @@ static int versatile_read_config(struct pci_bus *bus, unsigned int devfn, int wh static int versatile_write_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - unsigned long addr = __pci_addr(bus, devfn, where); + void __iomem *addr = __pci_addr(bus, devfn, where); int slot = PCI_SLOT(devfn); if (pci_slot_ignore & (1 << slot)) { @@ -279,7 +279,7 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys) printk("PCI core found (slot %d)\n",myslot); __raw_writel(myslot, PCI_SELFID); - local_pci_cfg_base = (void *) VERSATILE_PCI_CFG_VIRT_BASE + (myslot << 11); + local_pci_cfg_base = VERSATILE_PCI_CFG_VIRT_BASE + (myslot << 11); val = __raw_readl(local_pci_cfg_base + CSR_OFFSET); val |= PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER | PCI_COMMAND_INVALIDATE; diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index dedbb449632..a657a28f08d 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -90,7 +90,7 @@ void vfp_raise_sigfpe(unsigned int sicode, struct pt_regs *regs) info.si_signo = SIGFPE; info.si_code = sicode; - info.si_addr = (void *)(instruction_pointer(regs) - 4); + info.si_addr = (void __user *)(instruction_pointer(regs) - 4); /* * This is the same as NWFPE, because it's not clear what diff --git a/arch/arm26/kernel/armksyms.c b/arch/arm26/kernel/armksyms.c index 07907b6ecb6..93293d04b30 100644 --- a/arch/arm26/kernel/armksyms.c +++ b/arch/arm26/kernel/armksyms.c @@ -202,14 +202,6 @@ EXPORT_SYMBOL(_find_next_zero_bit_le); EXPORT_SYMBOL(elf_platform); EXPORT_SYMBOL(elf_hwcap); - /* syscalls */ -EXPORT_SYMBOL(sys_write); -EXPORT_SYMBOL(sys_read); -EXPORT_SYMBOL(sys_lseek); -EXPORT_SYMBOL(sys_open); -EXPORT_SYMBOL(sys_exit); -EXPORT_SYMBOL(sys_wait4); - #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(kernel_flag); #endif diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c index 3e56b9f4358..5a247ba71a7 100644 --- a/arch/avr32/kernel/time.c +++ b/arch/avr32/kernel/time.c @@ -124,15 +124,15 @@ unsigned long long sched_clock(void) * * In UP mode, it is invoked from the (global) timer_interrupt. */ -static void local_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) +static void local_timer_interrupt(int irq, void *dev_id) { if (current->pid) - profile_tick(CPU_PROFILING, regs); - update_process_times(user_mode(regs)); + profile_tick(CPU_PROFILING); + update_process_times(user_mode(get_irq_regs())); } static irqreturn_t -timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) +timer_interrupt(int irq, void *dev_id) { unsigned int count; @@ -157,7 +157,7 @@ timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) * * SMP is not supported yet. */ - local_timer_interrupt(irq, dev_id, regs); + local_timer_interrupt(irq, dev_id); return IRQ_HANDLED; } diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c index 7da9c5f7a0e..4dff1f98890 100644 --- a/arch/avr32/mach-at32ap/extint.c +++ b/arch/avr32/mach-at32ap/extint.c @@ -102,8 +102,7 @@ struct irq_chip eim_chip = { .set_type = eim_set_irq_type, }; -static void demux_eim_irq(unsigned int irq, struct irq_desc *desc, - struct pt_regs *regs) +static void demux_eim_irq(unsigned int irq, struct irq_desc *desc) { struct at32_sm *sm = desc->handler_data; struct irq_desc *ext_desc; @@ -121,7 +120,7 @@ static void demux_eim_irq(unsigned int irq, struct irq_desc *desc, ext_irq = i + sm->eim_first_irq; ext_desc = irq_desc + ext_irq; - ext_desc->handle_irq(ext_irq, ext_desc, regs); + ext_desc->handle_irq(ext_irq, ext_desc); } spin_unlock(&sm->lock); diff --git a/arch/avr32/mach-at32ap/intc.c b/arch/avr32/mach-at32ap/intc.c index 74f8c9f2f03..eb87a18ad7b 100644 --- a/arch/avr32/mach-at32ap/intc.c +++ b/arch/avr32/mach-at32ap/intc.c @@ -52,16 +52,19 @@ static struct intc intc0 = { asmlinkage void do_IRQ(int level, struct pt_regs *regs) { struct irq_desc *desc; + struct pt_regs *old_regs; unsigned int irq; unsigned long status_reg; local_irq_disable(); + old_regs = set_irq_regs(regs); + irq_enter(); irq = intc_readl(&intc0, INTCAUSE0 - 4 * level); desc = irq_desc + irq; - desc->handle_irq(irq, desc, regs); + desc->handle_irq(irq, desc); /* * Clear all interrupt level masks so that we may handle @@ -75,6 +78,8 @@ asmlinkage void do_IRQ(int level, struct pt_regs *regs) sysreg_write(SR, status_reg); irq_exit(); + + set_irq_regs(old_regs); } void __init init_IRQ(void) diff --git a/arch/i386/Kconfig.cpu b/arch/i386/Kconfig.cpu index 21c9a4e7110..fc4f2abccf0 100644 --- a/arch/i386/Kconfig.cpu +++ b/arch/i386/Kconfig.cpu @@ -7,6 +7,7 @@ choice config M386 bool "386" + depends on !UML ---help--- This is the processor type of your CPU. This information is used for optimizing purposes. In order to compile a kernel that can run on @@ -301,7 +302,7 @@ config X86_USE_PPRO_CHECKSUM config X86_USE_3DNOW bool - depends on MCYRIXIII || MK7 || MGEODE_LX + depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML default y config X86_OOSTORE diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index cd082c36ca0..27bceaf5ce4 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -2594,7 +2594,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask) } #endif -static struct hw_interrupt_type ht_irq_chip = { +static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .mask = mask_ht_irq, .unmask = unmask_ht_irq, diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c index 9b9479768d5..c4d0291b519 100644 --- a/arch/i386/kernel/microcode.c +++ b/arch/i386/kernel/microcode.c @@ -656,14 +656,18 @@ static struct attribute_group mc_attr_group = { static int mc_sysdev_add(struct sys_device *sys_dev) { - int cpu = sys_dev->id; + int err, cpu = sys_dev->id; struct ucode_cpu_info *uci = ucode_cpu_info + cpu; if (!cpu_online(cpu)) return 0; + pr_debug("Microcode:CPU %d added\n", cpu); memset(uci, 0, sizeof(*uci)); - sysfs_create_group(&sys_dev->kobj, &mc_attr_group); + + err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group); + if (err) + return err; microcode_init_cpu(cpu); return 0; diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 000cf03751f..519e63c3c13 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -1083,16 +1083,15 @@ static unsigned long __init setup_memory(void) void __init zone_sizes_init(void) { + unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + max_zone_pfns[ZONE_DMA] = + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM - unsigned long max_zone_pfns[MAX_NR_ZONES] = { - virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, - max_low_pfn, - highend_pfn}; + max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; add_active_range(0, 0, highend_pfn); #else - unsigned long max_zone_pfns[MAX_NR_ZONES] = { - virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, - max_low_pfn}; add_active_range(0, 0, max_low_pfn); #endif diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S index 7e639f78b0b..2697e9210e9 100644 --- a/arch/i386/kernel/syscall_table.S +++ b/arch/i386/kernel/syscall_table.S @@ -318,3 +318,4 @@ ENTRY(sys_call_table) .long sys_vmsplice .long sys_move_pages .long sys_getcpu + .long sys_epoll_pwait diff --git a/arch/i386/lib/usercopy.c b/arch/i386/lib/usercopy.c index 08502fc6d0c..258df6b4d7d 100644 --- a/arch/i386/lib/usercopy.c +++ b/arch/i386/lib/usercopy.c @@ -179,7 +179,7 @@ __clear_user(void __user *to, unsigned long n) EXPORT_SYMBOL(__clear_user); /** - * strlen_user: - Get the size of a string in user space. + * strnlen_user: - Get the size of a string in user space. * @s: The string to measure. * @n: The maximum valid length * diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index 455597db84d..ddbdb0336f2 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -356,11 +356,12 @@ void __init numa_kva_reserve(void) void __init zone_sizes_init(void) { int nid; - unsigned long max_zone_pfns[MAX_NR_ZONES] = { - virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, - max_low_pfn, - highend_pfn - }; + unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + max_zone_pfns[ZONE_DMA] = + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; + max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; /* If SRAT has not registered memory, register it now */ if (find_max_pfn_with_active_regions() == 0) { diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index daf977ff292..82deaa3a7c4 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -233,6 +233,7 @@ paging_init (void) efi_memmap_walk(count_pages, &num_physpages); max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = max_dma; max_zone_pfns[ZONE_NORMAL] = max_low_pfn; diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index d497b6b0f5b..96722cb1b49 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -709,6 +709,7 @@ void __init paging_init(void) max_pfn = mem_data[node].max_pfn; } + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = max_dma; max_zone_pfns[ZONE_NORMAL] = max_pfn; free_area_init_nodes(max_zone_pfns); diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index 3f35ab3d2dc..0e7778be33c 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -369,10 +369,10 @@ static void c_stop(struct seq_file *m, void *v) } struct seq_operations cpuinfo_op = { - start: c_start, - next: c_next, - stop: c_stop, - show: show_cpuinfo, + .start = c_start, + .next = c_next, + .stop = c_stop, + .show = show_cpuinfo, }; #endif /* CONFIG_PROC_FS */ diff --git a/arch/m32r/kernel/setup_mappi.c b/arch/m32r/kernel/setup_mappi.c index 67dbbdc9d11..6b2d77da068 100644 --- a/arch/m32r/kernel/setup_mappi.c +++ b/arch/m32r/kernel/setup_mappi.c @@ -86,7 +86,7 @@ void __init init_IRQ(void) /* INT0 : LAN controller (RTL8019AS) */ irq_desc[M32R_IRQ_INT0].status = IRQ_DISABLED; irq_desc[M32R_IRQ_INT0].chip = &mappi_irq_type; - irq_desc[M32R_IRQ_INT0].action = 0; + irq_desc[M32R_IRQ_INT0].action = NULL; irq_desc[M32R_IRQ_INT0].depth = 1; icu_data[M32R_IRQ_INT0].icucr = M32R_ICUCR_IEN|M32R_ICUCR_ISMOD10; disable_mappi_irq(M32R_IRQ_INT0); @@ -95,7 +95,7 @@ void __init init_IRQ(void) /* MFT2 : system timer */ irq_desc[M32R_IRQ_MFT2].status = IRQ_DISABLED; irq_desc[M32R_IRQ_MFT2].chip = &mappi_irq_type; - irq_desc[M32R_IRQ_MFT2].action = 0; + irq_desc[M32R_IRQ_MFT2].action = NULL; irq_desc[M32R_IRQ_MFT2].depth = 1; icu_data[M32R_IRQ_MFT2].icucr = M32R_ICUCR_IEN; disable_mappi_irq(M32R_IRQ_MFT2); @@ -104,7 +104,7 @@ void __init init_IRQ(void) /* SIO0_R : uart receive data */ irq_desc[M32R_IRQ_SIO0_R].status = IRQ_DISABLED; irq_desc[M32R_IRQ_SIO0_R].chip = &mappi_irq_type; - irq_desc[M32R_IRQ_SIO0_R].action = 0; + irq_desc[M32R_IRQ_SIO0_R].action = NULL; irq_desc[M32R_IRQ_SIO0_R].depth = 1; icu_data[M32R_IRQ_SIO0_R].icucr = 0; disable_mappi_irq(M32R_IRQ_SIO0_R); @@ -112,7 +112,7 @@ void __init init_IRQ(void) /* SIO0_S : uart send data */ irq_desc[M32R_IRQ_SIO0_S].status = IRQ_DISABLED; irq_desc[M32R_IRQ_SIO0_S].chip = &mappi_irq_type; - irq_desc[M32R_IRQ_SIO0_S].action = 0; + irq_desc[M32R_IRQ_SIO0_S].action = NULL; irq_desc[M32R_IRQ_SIO0_S].depth = 1; icu_data[M32R_IRQ_SIO0_S].icucr = 0; disable_mappi_irq(M32R_IRQ_SIO0_S); @@ -120,7 +120,7 @@ void __init init_IRQ(void) /* SIO1_R : uart receive data */ irq_desc[M32R_IRQ_SIO1_R].status = IRQ_DISABLED; irq_desc[M32R_IRQ_SIO1_R].chip = &mappi_irq_type; - irq_desc[M32R_IRQ_SIO1_R].action = 0; + irq_desc[M32R_IRQ_SIO1_R].action = NULL; irq_desc[M32R_IRQ_SIO1_R].depth = 1; icu_data[M32R_IRQ_SIO1_R].icucr = 0; disable_mappi_irq(M32R_IRQ_SIO1_R); @@ -128,7 +128,7 @@ void __init init_IRQ(void) /* SIO1_S : uart send data */ irq_desc[M32R_IRQ_SIO1_S].status = IRQ_DISABLED; irq_desc[M32R_IRQ_SIO1_S].chip = &mappi_irq_type; - irq_desc[M32R_IRQ_SIO1_S].action = 0; + irq_desc[M32R_IRQ_SIO1_S].action = NULL; irq_desc[M32R_IRQ_SIO1_S].depth = 1; icu_data[M32R_IRQ_SIO1_S].icucr = 0; disable_mappi_irq(M32R_IRQ_SIO1_S); @@ -138,7 +138,7 @@ void __init init_IRQ(void) /* INT1 : pccard0 interrupt */ irq_desc[M32R_IRQ_INT1].status = IRQ_DISABLED; irq_desc[M32R_IRQ_INT1].chip = &mappi_irq_type; - irq_desc[M32R_IRQ_INT1].action = 0; + irq_desc[M32R_IRQ_INT1].action = NULL; irq_desc[M32R_IRQ_INT1].depth = 1; icu_data[M32R_IRQ_INT1].icucr = M32R_ICUCR_IEN | M32R_ICUCR_ISMOD00; disable_mappi_irq(M32R_IRQ_INT1); @@ -146,7 +146,7 @@ void __init init_IRQ(void) /* INT2 : pccard1 interrupt */ irq_desc[M32R_IRQ_INT2].status = IRQ_DISABLED; irq_desc[M32R_IRQ_INT2].chip = &mappi_irq_type; - irq_desc[M32R_IRQ_INT2].action = 0; + irq_desc[M32R_IRQ_INT2].action = NULL; irq_desc[M32R_IRQ_INT2].depth = 1; icu_data[M32R_IRQ_INT2].icucr = M32R_ICUCR_IEN | M32R_ICUCR_ISMOD00; disable_mappi_irq(M32R_IRQ_INT2); diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c index a9174efe80c..b60cea4aeba 100644 --- a/arch/m32r/kernel/signal.c +++ b/arch/m32r/kernel/signal.c @@ -33,7 +33,7 @@ int do_signal(struct pt_regs *, sigset_t *); asmlinkage int -sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize, +sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, unsigned long r2, unsigned long r3, unsigned long r4, unsigned long r5, unsigned long r6, struct pt_regs *regs) { @@ -78,8 +78,8 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, struct rt_sigframe { int sig; - struct siginfo *pinfo; - void *puc; + struct siginfo __user *pinfo; + void __user *puc; struct siginfo info; struct ucontext uc; // struct _fpstate fpstate; diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index 722e21f556d..360129174b2 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -231,7 +231,7 @@ void smp_flush_tlb_all(void) local_irq_save(flags); __flush_tlb_all(); local_irq_restore(flags); - smp_call_function(flush_tlb_all_ipi, 0, 1, 1); + smp_call_function(flush_tlb_all_ipi, NULL, 1, 1); preempt_enable(); } diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c index b567351f3c5..b4e7bcb4354 100644 --- a/arch/m32r/kernel/sys_m32r.c +++ b/arch/m32r/kernel/sys_m32r.c @@ -31,7 +31,7 @@ /* * sys_tas() - test-and-set */ -asmlinkage int sys_tas(int *addr) +asmlinkage int sys_tas(int __user *addr) { int oldval; @@ -90,7 +90,7 @@ sys_pipe(unsigned long r0, unsigned long r1, unsigned long r2, error = do_pipe(fd); if (!error) { - if (copy_to_user((void *)r0, (void *)fd, 2*sizeof(int))) + if (copy_to_user((void __user *)r0, fd, 2*sizeof(int))) error = -EFAULT; } return error; @@ -201,7 +201,7 @@ asmlinkage int sys_ipc(uint call, int first, int second, } } -asmlinkage int sys_uname(struct old_utsname * name) +asmlinkage int sys_uname(struct old_utsname __user * name) { int err; if (!name) diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c index c1daf2c40c7..97e0b1c0830 100644 --- a/arch/m32r/kernel/traps.c +++ b/arch/m32r/kernel/traps.c @@ -268,7 +268,7 @@ static __inline__ void do_trap(int trapnr, int signr, const char * str, #define DO_ERROR(trapnr, signr, str, name) \ asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ { \ - do_trap(trapnr, signr, 0, regs, error_code, NULL); \ + do_trap(trapnr, signr, NULL, regs, error_code, NULL); \ } #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ diff --git a/arch/m68k/kernel/m68k_ksyms.c b/arch/m68k/kernel/m68k_ksyms.c index f9636e84e6a..6fc69c74fe2 100644 --- a/arch/m68k/kernel/m68k_ksyms.c +++ b/arch/m68k/kernel/m68k_ksyms.c @@ -1,61 +1,10 @@ #include <linux/module.h> -#include <linux/linkage.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/user.h> -#include <linux/elfcore.h> -#include <linux/in6.h> -#include <linux/interrupt.h> - -#include <asm/setup.h> -#include <asm/machdep.h> -#include <asm/pgalloc.h> -#include <asm/irq.h> -#include <asm/io.h> #include <asm/semaphore.h> -#include <asm/checksum.h> asmlinkage long long __ashldi3 (long long, int); asmlinkage long long __ashrdi3 (long long, int); asmlinkage long long __lshrdi3 (long long, int); asmlinkage long long __muldi3 (long long, long long); -extern char m68k_debug_device[]; - -/* platform dependent support */ - -EXPORT_SYMBOL(m68k_machtype); -EXPORT_SYMBOL(m68k_cputype); -EXPORT_SYMBOL(m68k_is040or060); -EXPORT_SYMBOL(m68k_realnum_memory); -EXPORT_SYMBOL(m68k_memory); -#ifndef CONFIG_SUN3 -EXPORT_SYMBOL(cache_push); -EXPORT_SYMBOL(cache_clear); -#ifndef CONFIG_SINGLE_MEMORY_CHUNK -EXPORT_SYMBOL(mm_vtop); -EXPORT_SYMBOL(mm_ptov); -EXPORT_SYMBOL(mm_end_of_chunk); -#else -EXPORT_SYMBOL(m68k_memoffset); -#endif /* !CONFIG_SINGLE_MEMORY_CHUNK */ -EXPORT_SYMBOL(__ioremap); -EXPORT_SYMBOL(iounmap); -EXPORT_SYMBOL(kernel_set_cachemode); -#endif /* !CONFIG_SUN3 */ -EXPORT_SYMBOL(m68k_debug_device); -EXPORT_SYMBOL(mach_hwclk); -EXPORT_SYMBOL(mach_get_ss); -EXPORT_SYMBOL(mach_get_rtc_pll); -EXPORT_SYMBOL(mach_set_rtc_pll); -#ifdef CONFIG_INPUT_M68K_BEEP_MODULE -EXPORT_SYMBOL(mach_beep); -#endif -EXPORT_SYMBOL(dump_fpu); -EXPORT_SYMBOL(dump_thread); -EXPORT_SYMBOL(kernel_thread); -#ifdef CONFIG_VME -EXPORT_SYMBOL(vme_brdtype); -#endif /* The following are special because they're not called explicitly (the C compiler generates them). Fortunately, diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 45a46646c1b..99fc1226f7f 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -187,6 +187,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) set_fs (fs); return pid; } +EXPORT_SYMBOL(kernel_thread); void flush_thread(void) { @@ -221,13 +222,13 @@ asmlinkage int m68k_clone(struct pt_regs *regs) { unsigned long clone_flags; unsigned long newsp; - int *parent_tidptr, *child_tidptr; + int __user *parent_tidptr, *child_tidptr; /* syscall2 puts clone_flags in d1 and usp in d2 */ clone_flags = regs->d1; newsp = regs->d2; - parent_tidptr = (int *)regs->d3; - child_tidptr = (int *)regs->d4; + parent_tidptr = (int __user *)regs->d3; + child_tidptr = (int __user *)regs->d4; if (!newsp) newsp = rdusp(); return do_fork(clone_flags, newsp, regs, 0, @@ -311,6 +312,7 @@ int dump_fpu (struct pt_regs *regs, struct user_m68kfp_struct *fpu) : "memory"); return 1; } +EXPORT_SYMBOL(dump_fpu); /* * fill in the user structure for a core dump.. @@ -357,11 +359,12 @@ void dump_thread(struct pt_regs * regs, struct user * dump) /* dump floating point stuff */ dump->u_fpvalid = dump_fpu (regs, &dump->m68kfp); } +EXPORT_SYMBOL(dump_thread); /* * sys_execve() executes a new program. */ -asmlinkage int sys_execve(char *name, char **argv, char **envp) +asmlinkage int sys_execve(char __user *name, char __user * __user *argv, char __user * __user *envp) { int error; char * filename; diff --git a/arch/m68k/kernel/setup.c b/arch/m68k/kernel/setup.c index 42d5b85f335..9af3ee0e555 100644 --- a/arch/m68k/kernel/setup.c +++ b/arch/m68k/kernel/setup.c @@ -42,27 +42,37 @@ unsigned long m68k_machtype; unsigned long m68k_cputype; +EXPORT_SYMBOL(m68k_machtype); +EXPORT_SYMBOL(m68k_cputype); unsigned long m68k_fputype; unsigned long m68k_mmutype; #ifdef CONFIG_VME unsigned long vme_brdtype; +EXPORT_SYMBOL(vme_brdtype); #endif int m68k_is040or060; +EXPORT_SYMBOL(m68k_is040or060); extern int end; extern unsigned long availmem; int m68k_num_memory; int m68k_realnum_memory; +EXPORT_SYMBOL(m68k_realnum_memory); +#ifdef CONFIG_SINGLE_MEMORY_CHUNK unsigned long m68k_memoffset; +EXPORT_SYMBOL(m68k_memoffset); +#endif struct mem_info m68k_memory[NUM_MEMINFO]; +EXPORT_SYMBOL(m68k_memory); static struct mem_info m68k_ramdisk; static char m68k_command_line[CL_SIZE]; char m68k_debug_device[6] = ""; +EXPORT_SYMBOL(m68k_debug_device); void (*mach_sched_init) (irq_handler_t handler) __initdata = NULL; /* machine dependent irq functions */ @@ -72,10 +82,14 @@ int (*mach_get_hardware_list) (char *buffer); /* machine dependent timer functions */ unsigned long (*mach_gettimeoffset) (void); int (*mach_hwclk) (int, struct rtc_time*); +EXPORT_SYMBOL(mach_hwclk); int (*mach_set_clock_mmss) (unsigned long); unsigned int (*mach_get_ss)(void); int (*mach_get_rtc_pll)(struct rtc_pll_info *); int (*mach_set_rtc_pll)(struct rtc_pll_info *); +EXPORT_SYMBOL(mach_get_ss); +EXPORT_SYMBOL(mach_get_rtc_pll); +EXPORT_SYMBOL(mach_set_rtc_pll); void (*mach_reset)( void ); void (*mach_halt)( void ); void (*mach_power_off)( void ); @@ -89,6 +103,7 @@ void (*mach_l2_flush) (int); #endif #if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE) void (*mach_beep)(unsigned int, unsigned int); +EXPORT_SYMBOL(mach_beep); #endif #if defined(CONFIG_ISA) && defined(MULTI_ISA) int isa_type; diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 4569406a2e1..759fa244e6c 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -326,13 +326,13 @@ static inline int do_040writeback1(unsigned short wbs, unsigned long wba, switch (wbs & WBSIZ_040) { case BA_SIZE_BYTE: - res = put_user(wbd & 0xff, (char *)wba); + res = put_user(wbd & 0xff, (char __user *)wba); break; case BA_SIZE_WORD: - res = put_user(wbd & 0xffff, (short *)wba); + res = put_user(wbd & 0xffff, (short __user *)wba); break; case BA_SIZE_LONG: - res = put_user(wbd, (int *)wba); + res = put_user(wbd, (int __user *)wba); break; } diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c index f46f049d29f..b54ef1726c5 100644 --- a/arch/m68k/mm/kmap.c +++ b/arch/m68k/mm/kmap.c @@ -7,6 +7,7 @@ * used by other architectures /Roman Zippel */ +#include <linux/module.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/string.h> @@ -219,6 +220,7 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla return (void __iomem *)retaddr; } +EXPORT_SYMBOL(__ioremap); /* * Unmap a ioremap()ed region again @@ -234,6 +236,7 @@ void iounmap(void __iomem *addr) free_io_area((__force void *)addr); #endif } +EXPORT_SYMBOL(iounmap); /* * __iounmap unmaps nearly everything, so be careful @@ -360,3 +363,4 @@ void kernel_set_cachemode(void *addr, unsigned long size, int cmode) flush_tlb_all(); } +EXPORT_SYMBOL(kernel_set_cachemode); diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c index a0c095e1722..0f88812822b 100644 --- a/arch/m68k/mm/memory.c +++ b/arch/m68k/mm/memory.c @@ -4,6 +4,7 @@ * Copyright (C) 1995 Hamish Macdonald */ +#include <linux/module.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/string.h> @@ -157,9 +158,8 @@ unsigned long mm_vtop(unsigned long vaddr) return -1; } -#endif +EXPORT_SYMBOL(mm_vtop); -#ifndef CONFIG_SINGLE_MEMORY_CHUNK unsigned long mm_ptov (unsigned long paddr) { int i = 0; @@ -185,6 +185,7 @@ unsigned long mm_ptov (unsigned long paddr) #endif return -1; } +EXPORT_SYMBOL(mm_ptov); #endif /* invalidate page in both caches */ @@ -298,6 +299,7 @@ void cache_clear (unsigned long paddr, int len) mach_l2_flush(0); #endif } +EXPORT_SYMBOL(cache_clear); /* probably can be unexported */ /* @@ -350,6 +352,7 @@ void cache_push (unsigned long paddr, int len) mach_l2_flush(1); #endif } +EXPORT_SYMBOL(cache_push); /* probably can be unexported */ #ifndef CONFIG_SINGLE_MEMORY_CHUNK int mm_end_of_chunk (unsigned long addr, int len) @@ -361,4 +364,5 @@ int mm_end_of_chunk (unsigned long addr, int len) return 1; return 0; } +EXPORT_SYMBOL(mm_end_of_chunk); #endif diff --git a/arch/m68k/mm/sun3kmap.c b/arch/m68k/mm/sun3kmap.c index 7f0d86f3fe7..1af24cb5bfe 100644 --- a/arch/m68k/mm/sun3kmap.c +++ b/arch/m68k/mm/sun3kmap.c @@ -8,6 +8,7 @@ * for more details. */ +#include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> @@ -59,7 +60,7 @@ static inline void do_pmeg_mapin(unsigned long phys, unsigned long virt, } } -void *sun3_ioremap(unsigned long phys, unsigned long size, +void __iomem *sun3_ioremap(unsigned long phys, unsigned long size, unsigned long type) { struct vm_struct *area; @@ -101,22 +102,24 @@ void *sun3_ioremap(unsigned long phys, unsigned long size, virt += seg_pages * PAGE_SIZE; } - return (void *)ret; + return (void __iomem *)ret; } -void *__ioremap(unsigned long phys, unsigned long size, int cache) +void __iomem *__ioremap(unsigned long phys, unsigned long size, int cache) { return sun3_ioremap(phys, size, SUN3_PAGE_TYPE_IO); } +EXPORT_SYMBOL(__ioremap); -void iounmap(void *addr) +void iounmap(void __iomem *addr) { vfree((void *)(PAGE_MASK & (unsigned long)addr)); } +EXPORT_SYMBOL(iounmap); /* sun3_map_test(addr, val) -- Reads a byte from addr, storing to val, * trapping the potential read fault. Returns 0 if the access faulted, diff --git a/arch/m68k/sun3/Makefile b/arch/m68k/sun3/Makefile index 4d4f0695d98..be1a8470d63 100644 --- a/arch/m68k/sun3/Makefile +++ b/arch/m68k/sun3/Makefile @@ -2,6 +2,6 @@ # Makefile for Linux arch/m68k/sun3 source directory # -obj-y := sun3_ksyms.o sun3ints.o sun3dvma.o sbus.o idprom.o +obj-y := sun3ints.o sun3dvma.o sbus.o idprom.o obj-$(CONFIG_SUN3) += config.o mmu_emu.o leds.o dvma.o intersil.o diff --git a/arch/m68k/sun3/idprom.c b/arch/m68k/sun3/idprom.c index 02c1fee6fe7..dca6ab6a4ed 100644 --- a/arch/m68k/sun3/idprom.c +++ b/arch/m68k/sun3/idprom.c @@ -6,6 +6,7 @@ * Sun3/3x models added by David Monro (davidm@psrg.cs.usyd.edu.au) */ +#include <linux/module.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> @@ -16,6 +17,8 @@ #include <asm/machines.h> /* Fun with Sun released architectures. */ struct idprom *idprom; +EXPORT_SYMBOL(idprom); + static struct idprom idprom_buffer; /* Here is the master table of Sun machines which use some implementation diff --git a/arch/m68k/sun3/sun3_ksyms.c b/arch/m68k/sun3/sun3_ksyms.c deleted file mode 100644 index 43e5a9af8ab..00000000000 --- a/arch/m68k/sun3/sun3_ksyms.c +++ /dev/null @@ -1,13 +0,0 @@ -#include <linux/module.h> -#include <linux/types.h> -#include <asm/dvma.h> -#include <asm/idprom.h> - -/* - * Add things here when you find the need for it. - */ -EXPORT_SYMBOL(dvma_map_align); -EXPORT_SYMBOL(dvma_unmap); -EXPORT_SYMBOL(dvma_malloc_align); -EXPORT_SYMBOL(dvma_free); -EXPORT_SYMBOL(idprom); diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c index a2bc2da7f8f..8709677fa02 100644 --- a/arch/m68k/sun3/sun3dvma.c +++ b/arch/m68k/sun3/sun3dvma.c @@ -6,6 +6,7 @@ * Contains common routines for sun3/sun3x DVMA management. */ +#include <linux/module.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/list.h> @@ -312,6 +313,7 @@ inline unsigned long dvma_map_align(unsigned long kaddr, int len, int align) BUG(); return 0; } +EXPORT_SYMBOL(dvma_map_align); void dvma_unmap(void *baddr) { @@ -327,7 +329,7 @@ void dvma_unmap(void *baddr) return; } - +EXPORT_SYMBOL(dvma_unmap); void *dvma_malloc_align(unsigned long len, unsigned long align) { @@ -367,6 +369,7 @@ void *dvma_malloc_align(unsigned long len, unsigned long align) return (void *)vaddr; } +EXPORT_SYMBOL(dvma_malloc_align); void dvma_free(void *vaddr) { @@ -374,3 +377,4 @@ void dvma_free(void *vaddr) return; } +EXPORT_SYMBOL(dvma_free); diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 6d57553d8ef..8f6a0b312f7 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -69,10 +69,6 @@ EXPORT_SYMBOL(memcpy_toio); EXPORT_SYMBOL(memcpy_fromio); EXPORT_SYMBOL(memset_io); -#include <asm/unistd.h> -EXPORT_SYMBOL(sys_lseek); -EXPORT_SYMBOL(sys_write); - #include <asm/semaphore.h> EXPORT_SYMBOL(__up); EXPORT_SYMBOL(__down_interruptible); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 16fe027bbc1..d1c0758c561 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -307,11 +307,12 @@ void __init paging_init(void) top_of_ram, total_ram); printk(KERN_DEBUG "Memory hole size: %ldMB\n", (top_of_ram - total_ram) >> 20); + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); #ifdef CONFIG_HIGHMEM - max_zone_pfns[0] = total_lowmem >> PAGE_SHIFT; - max_zone_pfns[1] = top_of_ram >> PAGE_SHIFT; + max_zone_pfns[ZONE_DMA] = total_lowmem >> PAGE_SHIFT; + max_zone_pfns[ZONE_HIGHMEM] = top_of_ram >> PAGE_SHIFT; #else - max_zone_pfns[0] = top_of_ram >> PAGE_SHIFT; + max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT; #endif free_area_init_nodes(max_zone_pfns); } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 43c272075e1..9da01dc8cfd 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -617,9 +617,9 @@ void __init do_init_bootmem(void) void __init paging_init(void) { - unsigned long max_zone_pfns[MAX_NR_ZONES] = { - lmb_end_of_DRAM() >> PAGE_SHIFT - }; + unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + max_zone_pfns[ZONE_DMA] = lmb_end_of_DRAM() >> PAGE_SHIFT; free_area_init_nodes(max_zone_pfns); } diff --git a/arch/ppc/mm/init.c b/arch/ppc/mm/init.c index 410200046af..c374e53ae03 100644 --- a/arch/ppc/mm/init.c +++ b/arch/ppc/mm/init.c @@ -374,11 +374,12 @@ void __init paging_init(void) end_pfn = start_pfn + (total_memory >> PAGE_SHIFT); add_active_range(0, start_pfn, end_pfn); + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); #ifdef CONFIG_HIGHMEM - max_zone_pfns[0] = total_lowmem >> PAGE_SHIFT; - max_zone_pfns[1] = total_memory >> PAGE_SHIFT; + max_zone_pfns[ZONE_DMA] = total_lowmem >> PAGE_SHIFT; + max_zone_pfns[ZONE_HIGHMEM] = total_memory >> PAGE_SHIFT; #else - max_zone_pfns[0] = total_memory >> PAGE_SHIFT; + max_zone_pfns[ZONE_DMA] = total_memory >> PAGE_SHIFT; #endif /* CONFIG_HIGHMEM */ free_area_init_nodes(max_zone_pfns); } diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c index 9f19e833a56..90b5ef529eb 100644 --- a/arch/s390/kernel/s390_ksyms.c +++ b/arch/s390/kernel/s390_ksyms.c @@ -51,4 +51,3 @@ EXPORT_SYMBOL(csum_fold); EXPORT_SYMBOL(console_mode); EXPORT_SYMBOL(console_devno); EXPORT_SYMBOL(console_irq); -EXPORT_SYMBOL(sys_wait4); diff --git a/arch/um/Kconfig b/arch/um/Kconfig index d75307589d7..78fb619bdb7 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -25,6 +25,19 @@ config PCI config PCMCIA bool +# Yet to do! +config TRACE_IRQFLAGS_SUPPORT + bool + default n + +config LOCKDEP_SUPPORT + bool + default y + +config STACKTRACE_SUPPORT + bool + default y + config GENERIC_CALIBRATE_DELAY bool default y @@ -37,13 +50,15 @@ config IRQ_RELEASE_METHOD menu "UML-specific options" config MODE_TT - bool "Tracing thread support" + bool "Tracing thread support (DEPRECATED)" default n help This option controls whether tracing thread support is compiled - into UML. This option is largely obsolete, given that skas0 provides + into UML. This option is largely obsolete, given that skas0 provides skas security and performance without needing to patch the host. - It is safe to say 'N' here. + It is safe to say 'N' here; saying 'Y' may cause additional problems + with the resulting binary even if you run UML in SKAS mode, and running + in TT mode is strongly *NOT RECOMMENDED*. config STATIC_LINK bool "Force a static link" @@ -56,6 +71,9 @@ config STATIC_LINK for use in a chroot jail. So, if you intend to run UML inside a chroot, and you disable CONFIG_MODE_TT, you probably want to say Y here. + Additionally, this option enables using higher memory spaces (up to + 2.75G) for UML - disabling CONFIG_MODE_TT and enabling this option leads + to best results for this. config KERNEL_HALF_GIGS int "Kernel address space size (in .5G units)" @@ -72,10 +90,13 @@ config MODE_SKAS default y help This option controls whether skas (separate kernel address space) - support is compiled in. If you have applied the skas patch to the - host, then you certainly want to say Y here (and consider saying N - to CONFIG_MODE_TT). Otherwise, it is safe to say Y. Disabling this - option will shrink the UML binary slightly. + support is compiled in. + Unless you have specific needs to use TT mode (which applies almost only + to developers), you should say Y here. + SKAS mode will make use of the SKAS3 patch if it is applied on the host + (and your UML will run in SKAS3 mode), but if no SKAS patch is applied + on the host it will run in SKAS0 mode, which is anyway faster than TT + mode. source "arch/um/Kconfig.arch" source "mm/Kconfig" diff --git a/arch/um/Kconfig.i386 b/arch/um/Kconfig.i386 index f6eb72d117b..f191a550a07 100644 --- a/arch/um/Kconfig.i386 +++ b/arch/um/Kconfig.i386 @@ -16,23 +16,42 @@ config SEMAPHORE_SLEEPERS bool default y -config HOST_2G_2G - bool "2G/2G host address space split" - default n - help - This is needed when the host on which you run has a 2G/2G memory - split, instead of the customary 3G/1G. - - Note that to enable such a host - configuration, which makes sense only in some cases, you need special - host patches. - - So, if you do not know what to do here, say 'N'. +choice + prompt "Host memory split" + default HOST_VMSPLIT_3G + ---help--- + This is needed when the host kernel on which you run has a non-default + (like 2G/2G) memory split, instead of the customary 3G/1G. If you did + not recompile your own kernel but use the default distro's one, you can + safely accept the "Default split" option. + + It can be enabled on recent (>=2.6.16-rc2) vanilla kernels via + CONFIG_VM_SPLIT_*, or on previous kernels with special patches (-ck + patchset by Con Kolivas, or other ones) - option names match closely the + host CONFIG_VM_SPLIT_* ones. + + A lower setting (where 1G/3G is lowest and 3G/1G is higher) will + tolerate even more "normal" host kernels, but an higher setting will be + stricter. + + So, if you do not know what to do here, say 'Default split'. + + config HOST_VMSPLIT_3G + bool "Default split (3G/1G user/kernel host split)" + config HOST_VMSPLIT_3G_OPT + bool "3G/1G user/kernel host split (for full 1G low memory)" + config HOST_VMSPLIT_2G + bool "2G/2G user/kernel host split" + config HOST_VMSPLIT_1G + bool "1G/3G user/kernel host split" +endchoice config TOP_ADDR - hex - default 0xc0000000 if !HOST_2G_2G - default 0x80000000 if HOST_2G_2G + hex + default 0xB0000000 if HOST_VMSPLIT_3G_OPT + default 0x78000000 if HOST_VMSPLIT_2G + default 0x40000000 if HOST_VMSPLIT_1G + default 0xC0000000 config 3_LEVEL_PGTABLES bool "Three-level pagetables (EXPERIMENTAL)" diff --git a/arch/um/Makefile-x86_64 b/arch/um/Makefile-x86_64 index 11154b6773e..d278682dd79 100644 --- a/arch/um/Makefile-x86_64 +++ b/arch/um/Makefile-x86_64 @@ -1,10 +1,10 @@ # Copyright 2003 - 2004 Pathscale, Inc # Released under the GPL -core-y += arch/um/sys-x86_64/ +core-y += arch/um/sys-x86_64/ arch/x86_64/crypto/ START := 0x60000000 -_extra_flags_ = -fno-builtin -m64 -mcmodel=kernel +_extra_flags_ = -fno-builtin -m64 #We #undef __x86_64__ for kernelspace, not for userspace where #it's needed for headers to work! diff --git a/arch/um/include/common-offsets.h b/arch/um/include/common-offsets.h index 356390d1f8b..461175f8b1d 100644 --- a/arch/um/include/common-offsets.h +++ b/arch/um/include/common-offsets.h @@ -1,9 +1,16 @@ /* for use by sys-$SUBARCH/kernel-offsets.c */ +DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE); +#ifdef CONFIG_MODE_TT +OFFSET(HOST_TASK_EXTERN_PID, task_struct, thread.mode.tt.extern_pid); +#endif + OFFSET(HOST_TASK_REGS, task_struct, thread.regs); OFFSET(HOST_TASK_PID, task_struct, pid); + DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE); DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC); + DEFINE_STR(UM_KERN_EMERG, KERN_EMERG); DEFINE_STR(UM_KERN_ALERT, KERN_ALERT); DEFINE_STR(UM_KERN_CRIT, KERN_CRIT); @@ -12,6 +19,10 @@ DEFINE_STR(UM_KERN_WARNING, KERN_WARNING); DEFINE_STR(UM_KERN_NOTICE, KERN_NOTICE); DEFINE_STR(UM_KERN_INFO, KERN_INFO); DEFINE_STR(UM_KERN_DEBUG, KERN_DEBUG); + DEFINE(UM_ELF_CLASS, ELF_CLASS); DEFINE(UM_ELFCLASS32, ELFCLASS32); DEFINE(UM_ELFCLASS64, ELFCLASS64); + +/* For crypto assembler code. */ +DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx)); diff --git a/arch/um/include/longjmp.h b/arch/um/include/longjmp.h index e93c6d3e893..e860bc5848e 100644 --- a/arch/um/include/longjmp.h +++ b/arch/um/include/longjmp.h @@ -12,7 +12,8 @@ extern void longjmp(jmp_buf, int); } while(0) #define UML_SETJMP(buf) ({ \ - int n, enable; \ + int n; \ + volatile int enable; \ enable = get_signals(); \ n = setjmp(*buf); \ if(n != 0) \ diff --git a/arch/um/include/os.h b/arch/um/include/os.h index 120ca21a513..6516f6dca96 100644 --- a/arch/um/include/os.h +++ b/arch/um/include/os.h @@ -201,6 +201,7 @@ extern int os_getpgrp(void); #ifdef UML_CONFIG_MODE_TT extern void init_new_thread_stack(void *sig_stack, void (*usr1_handler)(int)); +extern void stop(void); #endif extern void init_new_thread_signals(void); extern int run_kernel_thread(int (*fn)(void *), void *arg, void **jmp_ptr); diff --git a/arch/um/include/sysdep-i386/kernel-offsets.h b/arch/um/include/sysdep-i386/kernel-offsets.h index 2c13de321f2..97ec9d894d7 100644 --- a/arch/um/include/sysdep-i386/kernel-offsets.h +++ b/arch/um/include/sysdep-i386/kernel-offsets.h @@ -1,6 +1,7 @@ #include <linux/stddef.h> #include <linux/sched.h> #include <linux/elf.h> +#include <linux/crypto.h> #include <asm/mman.h> #define DEFINE(sym, val) \ @@ -17,9 +18,5 @@ void foo(void) { OFFSET(HOST_TASK_DEBUGREGS, task_struct, thread.arch.debugregs); - DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE); -#ifdef CONFIG_MODE_TT - OFFSET(HOST_TASK_EXTERN_PID, task_struct, thread.mode.tt.extern_pid); -#endif #include <common-offsets.h> } diff --git a/arch/um/include/sysdep-x86_64/kernel-offsets.h b/arch/um/include/sysdep-x86_64/kernel-offsets.h index 91d129fb393..a307237b796 100644 --- a/arch/um/include/sysdep-x86_64/kernel-offsets.h +++ b/arch/um/include/sysdep-x86_64/kernel-offsets.h @@ -2,6 +2,7 @@ #include <linux/sched.h> #include <linux/time.h> #include <linux/elf.h> +#include <linux/crypto.h> #include <asm/page.h> #include <asm/mman.h> @@ -18,9 +19,5 @@ void foo(void) { - DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE); -#ifdef CONFIG_MODE_TT - OFFSET(HOST_TASK_EXTERN_PID, task_struct, thread.mode.tt.extern_pid); -#endif #include <common-offsets.h> } diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c index c17eddcf89b..2c6d090a2e8 100644 --- a/arch/um/kernel/skas/mmu.c +++ b/arch/um/kernel/skas/mmu.c @@ -60,10 +60,7 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc, #endif *pte = mk_pte(virt_to_page(kernel), __pgprot(_PAGE_PRESENT)); - /* This is wrong for the code page, but it doesn't matter since the - * stub is mapped by hand with the correct permissions. - */ - *pte = pte_mkwrite(*pte); + *pte = pte_mkread(*pte); return(0); out_pmd: diff --git a/arch/um/kernel/tt/uaccess_user.c b/arch/um/kernel/tt/uaccess_user.c index 6c92bbccb49..ed1abcf4d05 100644 --- a/arch/um/kernel/tt/uaccess_user.c +++ b/arch/um/kernel/tt/uaccess_user.c @@ -4,13 +4,13 @@ * Licensed under the GPL */ -#include <setjmp.h> #include <string.h> #include "user_util.h" #include "uml_uaccess.h" #include "task.h" #include "kern_util.h" #include "os.h" +#include "longjmp.h" int __do_copy_from_user(void *to, const void *from, int n, void **fault_addr, void **fault_catcher) @@ -80,10 +80,10 @@ int __do_strnlen_user(const char *str, unsigned long n, struct tt_regs save = TASK_REGS(get_current())->tt; int ret; unsigned long *faddrp = (unsigned long *)fault_addr; - sigjmp_buf jbuf; + jmp_buf jbuf; *fault_catcher = &jbuf; - if(sigsetjmp(jbuf, 1) == 0) + if(UML_SETJMP(&jbuf) == 0) ret = strlen(str) + 1; else ret = *faddrp - (unsigned long) str; diff --git a/arch/um/os-Linux/tt.c b/arch/um/os-Linux/tt.c index 5461a065bbb..3dc3a02d626 100644 --- a/arch/um/os-Linux/tt.c +++ b/arch/um/os-Linux/tt.c @@ -10,7 +10,6 @@ #include <errno.h> #include <stdarg.h> #include <stdlib.h> -#include <setjmp.h> #include <sys/time.h> #include <sys/ptrace.h> #include <linux/ptrace.h> diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index 3f5b1514e8a..56b8a50e8bc 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -80,11 +80,18 @@ void setup_machinename(char *machine_out) struct utsname host; uname(&host); -#if defined(UML_CONFIG_UML_X86) && !defined(UML_CONFIG_64BIT) +#ifdef UML_CONFIG_UML_X86 +# ifndef UML_CONFIG_64BIT if (!strcmp(host.machine, "x86_64")) { strcpy(machine_out, "i686"); return; } +# else + if (!strcmp(host.machine, "i686")) { + strcpy(machine_out, "x86_64"); + return; + } +# endif #endif strcpy(machine_out, host.machine); } diff --git a/arch/um/sys-x86_64/ksyms.c b/arch/um/sys-x86_64/ksyms.c index 85927380820..12c593607c5 100644 --- a/arch/um/sys-x86_64/ksyms.c +++ b/arch/um/sys-x86_64/ksyms.c @@ -14,6 +14,3 @@ EXPORT_SYMBOL(__up_wakeup); /*XXX: we need them because they would be exported by x86_64 */ EXPORT_SYMBOL(__memcpy); - -/* Networking helper routines. */ -EXPORT_SYMBOL(ip_compute_csum); diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c index 771bcf77daf..c3cdcab2968 100644 --- a/arch/x86_64/kernel/io_apic.c +++ b/arch/x86_64/kernel/io_apic.c @@ -1897,7 +1897,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask) } #endif -static struct hw_interrupt_type ht_irq_chip = { +static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .mask = mask_ht_irq, .unmask = unmask_ht_irq, diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index 19c72520a86..971dc1181e6 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -406,9 +406,12 @@ void __cpuinit zap_low_mappings(int cpu) #ifndef CONFIG_NUMA void __init paging_init(void) { - unsigned long max_zone_pfns[MAX_NR_ZONES] = {MAX_DMA_PFN, - MAX_DMA32_PFN, - end_pfn}; + unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; + max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; + max_zone_pfns[ZONE_NORMAL] = end_pfn; + memory_present(0, 0, end_pfn); sparse_init(); free_area_init_nodes(max_zone_pfns); diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index 829a008bd39..2ee2e003606 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -338,9 +338,11 @@ static void __init arch_sparse_init(void) void __init paging_init(void) { int i; - unsigned long max_zone_pfns[MAX_NR_ZONES] = { MAX_DMA_PFN, - MAX_DMA32_PFN, - end_pfn}; + unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; + max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; + max_zone_pfns[ZONE_NORMAL] = end_pfn; arch_sparse_init(); diff --git a/drivers/block/DAC960.h b/drivers/block/DAC960.h index cec539e601f..6148073532b 100644 --- a/drivers/block/DAC960.h +++ b/drivers/block/DAC960.h @@ -4379,8 +4379,8 @@ static inline void DAC960_P_To_PD_TranslateEnquiry(void *Enquiry) static inline void DAC960_P_To_PD_TranslateDeviceState(void *DeviceState) { memcpy(DeviceState + 2, DeviceState + 3, 1); - memcpy(DeviceState + 4, DeviceState + 5, 2); - memcpy(DeviceState + 6, DeviceState + 8, 4); + memmove(DeviceState + 4, DeviceState + 5, 2); + memmove(DeviceState + 6, DeviceState + 8, 4); } static inline diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 5d254b71450..5d656217153 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1709,10 +1709,13 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data) return get_disk(unit[drive].gendisk); } -int __init amiga_floppy_init(void) +static int __init amiga_floppy_init(void) { int i, ret; + if (!MACH_IS_AMIGA) + return -ENXIO; + if (!AMIGAHW_PRESENT(AMI_FLOPPY)) return -ENXIO; @@ -1809,15 +1812,9 @@ out_blkdev: return ret; } +module_init(amiga_floppy_init); #ifdef MODULE -int init_module(void) -{ - if (!MACH_IS_AMIGA) - return -ENXIO; - return amiga_floppy_init(); -} - #if 0 /* not safe to unload */ void cleanup_module(void) { diff --git a/drivers/block/xd.c b/drivers/block/xd.c index 10cc38783bd..0d97b7eb818 100644 --- a/drivers/block/xd.c +++ b/drivers/block/xd.c @@ -48,9 +48,9 @@ #include <linux/blkdev.h> #include <linux/blkpg.h> #include <linux/delay.h> +#include <linux/io.h> #include <asm/system.h> -#include <asm/io.h> #include <asm/uaccess.h> #include <asm/dma.h> diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 82ddbdd7bd4..7cc2685ca84 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -329,7 +329,7 @@ static struct kobject *z2_find(dev_t dev, int *part, void *data) static struct request_queue *z2_queue; -int __init +static int __init z2_init(void) { int ret; @@ -370,26 +370,7 @@ err: return ret; } -#if defined(MODULE) - -MODULE_LICENSE("GPL"); - -int -init_module( void ) -{ - int error; - - error = z2_init(); - if ( error == 0 ) - { - printk( KERN_INFO DEVICE_NAME ": loaded as module\n" ); - } - - return error; -} - -void -cleanup_module( void ) +static void __exit z2_exit(void) { int i, j; blk_unregister_region(MKDEV(Z2RAM_MAJOR, 0), 256); @@ -425,4 +406,7 @@ cleanup_module( void ) return; } -#endif + +module_init(z2_init); +module_exit(z2_exit); +MODULE_LICENSE("GPL"); diff --git a/drivers/char/ip2/i2lib.c b/drivers/char/ip2/i2lib.c index fc944d375be..54d93f0345e 100644 --- a/drivers/char/ip2/i2lib.c +++ b/drivers/char/ip2/i2lib.c @@ -1007,7 +1007,7 @@ i2InputAvailable(i2ChanStrPtr pCh) // applications that one cannot break out of. //****************************************************************************** static int -i2Output(i2ChanStrPtr pCh, const char *pSource, int count, int user ) +i2Output(i2ChanStrPtr pCh, const char *pSource, int count) { i2eBordStrPtr pB; unsigned char *pInsert; @@ -1020,7 +1020,7 @@ i2Output(i2ChanStrPtr pCh, const char *pSource, int count, int user ) int bailout = 10; - ip2trace (CHANN, ITRC_OUTPUT, ITRC_ENTER, 2, count, user ); + ip2trace (CHANN, ITRC_OUTPUT, ITRC_ENTER, 2, count, 0 ); // Ensure channel structure seems real if ( !i2Validate ( pCh ) ) @@ -1087,12 +1087,7 @@ i2Output(i2ChanStrPtr pCh, const char *pSource, int count, int user ) DATA_COUNT_OF(pInsert) = amountToMove; // Move the data - if ( user ) { - rc = copy_from_user((char*)(DATA_OF(pInsert)), pSource, - amountToMove ); - } else { - memcpy( (char*)(DATA_OF(pInsert)), pSource, amountToMove ); - } + memcpy( (char*)(DATA_OF(pInsert)), pSource, amountToMove ); // Adjust pointers and indices pSource += amountToMove; pCh->Obuf_char_count += amountToMove; diff --git a/drivers/char/ip2/i2lib.h b/drivers/char/ip2/i2lib.h index 952e113ccd8..e559e9bac06 100644 --- a/drivers/char/ip2/i2lib.h +++ b/drivers/char/ip2/i2lib.h @@ -332,7 +332,7 @@ static int i2QueueCommands(int, i2ChanStrPtr, int, int, cmdSyntaxPtr,...); static int i2GetStatus(i2ChanStrPtr, int); static int i2Input(i2ChanStrPtr); static int i2InputFlush(i2ChanStrPtr); -static int i2Output(i2ChanStrPtr, const char *, int, int); +static int i2Output(i2ChanStrPtr, const char *, int); static int i2OutputFree(i2ChanStrPtr); static int i2ServiceBoard(i2eBordStrPtr); static void i2DrainOutput(i2ChanStrPtr, int); diff --git a/drivers/char/ip2/ip2main.c b/drivers/char/ip2/ip2main.c index 858ba5432c9..a3f32d46d2f 100644 --- a/drivers/char/ip2/ip2main.c +++ b/drivers/char/ip2/ip2main.c @@ -1704,7 +1704,7 @@ ip2_write( PTTY tty, const unsigned char *pData, int count) /* This is the actual move bit. Make sure it does what we need!!!!! */ WRITE_LOCK_IRQSAVE(&pCh->Pbuf_spinlock,flags); - bytesSent = i2Output( pCh, pData, count, 0 ); + bytesSent = i2Output( pCh, pData, count); WRITE_UNLOCK_IRQRESTORE(&pCh->Pbuf_spinlock,flags); ip2trace (CHANN, ITRC_WRITE, ITRC_RETURN, 1, bytesSent ); @@ -1764,7 +1764,7 @@ ip2_flush_chars( PTTY tty ) // // We may need to restart i2Output if it does not fullfill this request // - strip = i2Output( pCh, pCh->Pbuf, pCh->Pbuf_stuff, 0 ); + strip = i2Output( pCh, pCh->Pbuf, pCh->Pbuf_stuff); if ( strip != pCh->Pbuf_stuff ) { memmove( pCh->Pbuf, &pCh->Pbuf[strip], pCh->Pbuf_stuff - strip ); } diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 2455e8d478a..34a4fd13fa8 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -1928,13 +1928,8 @@ static ssize_t guid_show(struct device *dev, struct device_attribute *attr, (long long) bmc->guid[8]); } -static void -cleanup_bmc_device(struct kref *ref) +static void remove_files(struct bmc_device *bmc) { - struct bmc_device *bmc; - - bmc = container_of(ref, struct bmc_device, refcount); - device_remove_file(&bmc->dev->dev, &bmc->device_id_attr); device_remove_file(&bmc->dev->dev, @@ -1951,12 +1946,23 @@ cleanup_bmc_device(struct kref *ref) &bmc->manufacturer_id_attr); device_remove_file(&bmc->dev->dev, &bmc->product_id_attr); + if (bmc->id.aux_firmware_revision_set) device_remove_file(&bmc->dev->dev, &bmc->aux_firmware_rev_attr); if (bmc->guid_set) device_remove_file(&bmc->dev->dev, &bmc->guid_attr); +} + +static void +cleanup_bmc_device(struct kref *ref) +{ + struct bmc_device *bmc; + + bmc = container_of(ref, struct bmc_device, refcount); + + remove_files(bmc); platform_device_unregister(bmc->dev); kfree(bmc); } @@ -1977,6 +1983,79 @@ static void ipmi_bmc_unregister(ipmi_smi_t intf) mutex_unlock(&ipmidriver_mutex); } +static int create_files(struct bmc_device *bmc) +{ + int err; + + err = device_create_file(&bmc->dev->dev, + &bmc->device_id_attr); + if (err) goto out; + err = device_create_file(&bmc->dev->dev, + &bmc->provides_dev_sdrs_attr); + if (err) goto out_devid; + err = device_create_file(&bmc->dev->dev, + &bmc->revision_attr); + if (err) goto out_sdrs; + err = device_create_file(&bmc->dev->dev, + &bmc->firmware_rev_attr); + if (err) goto out_rev; + err = device_create_file(&bmc->dev->dev, + &bmc->version_attr); + if (err) goto out_firm; + err = device_create_file(&bmc->dev->dev, + &bmc->add_dev_support_attr); + if (err) goto out_version; + err = device_create_file(&bmc->dev->dev, + &bmc->manufacturer_id_attr); + if (err) goto out_add_dev; + err = device_create_file(&bmc->dev->dev, + &bmc->product_id_attr); + if (err) goto out_manu; + if (bmc->id.aux_firmware_revision_set) { + err = device_create_file(&bmc->dev->dev, + &bmc->aux_firmware_rev_attr); + if (err) goto out_prod_id; + } + if (bmc->guid_set) { + err = device_create_file(&bmc->dev->dev, + &bmc->guid_attr); + if (err) goto out_aux_firm; + } + + return 0; + +out_aux_firm: + if (bmc->id.aux_firmware_revision_set) + device_remove_file(&bmc->dev->dev, + &bmc->aux_firmware_rev_attr); +out_prod_id: + device_remove_file(&bmc->dev->dev, + &bmc->product_id_attr); +out_manu: + device_remove_file(&bmc->dev->dev, + &bmc->manufacturer_id_attr); +out_add_dev: + device_remove_file(&bmc->dev->dev, + &bmc->add_dev_support_attr); +out_version: + device_remove_file(&bmc->dev->dev, + &bmc->version_attr); +out_firm: + device_remove_file(&bmc->dev->dev, + &bmc->firmware_rev_attr); +out_rev: + device_remove_file(&bmc->dev->dev, + &bmc->revision_attr); +out_sdrs: + device_remove_file(&bmc->dev->dev, + &bmc->provides_dev_sdrs_attr); +out_devid: + device_remove_file(&bmc->dev->dev, + &bmc->device_id_attr); +out: + return err; +} + static int ipmi_bmc_register(ipmi_smi_t intf) { int rv; @@ -2051,7 +2130,6 @@ static int ipmi_bmc_register(ipmi_smi_t intf) bmc->provides_dev_sdrs_attr.attr.mode = S_IRUGO; bmc->provides_dev_sdrs_attr.show = provides_dev_sdrs_show; - bmc->revision_attr.attr.name = "revision"; bmc->revision_attr.attr.owner = THIS_MODULE; bmc->revision_attr.attr.mode = S_IRUGO; @@ -2093,28 +2171,14 @@ static int ipmi_bmc_register(ipmi_smi_t intf) bmc->aux_firmware_rev_attr.attr.mode = S_IRUGO; bmc->aux_firmware_rev_attr.show = aux_firmware_rev_show; - device_create_file(&bmc->dev->dev, - &bmc->device_id_attr); - device_create_file(&bmc->dev->dev, - &bmc->provides_dev_sdrs_attr); - device_create_file(&bmc->dev->dev, - &bmc->revision_attr); - device_create_file(&bmc->dev->dev, - &bmc->firmware_rev_attr); - device_create_file(&bmc->dev->dev, - &bmc->version_attr); - device_create_file(&bmc->dev->dev, - &bmc->add_dev_support_attr); - device_create_file(&bmc->dev->dev, - &bmc->manufacturer_id_attr); - device_create_file(&bmc->dev->dev, - &bmc->product_id_attr); - if (bmc->id.aux_firmware_revision_set) - device_create_file(&bmc->dev->dev, - &bmc->aux_firmware_rev_attr); - if (bmc->guid_set) - device_create_file(&bmc->dev->dev, - &bmc->guid_attr); + rv = create_files(bmc); + if (rv) { + mutex_lock(&ipmidriver_mutex); + platform_device_unregister(bmc->dev); + mutex_unlock(&ipmidriver_mutex); + + return rv; + } printk(KERN_INFO "ipmi: Found new BMC (man_id: 0x%6.6x, " diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c index a082a2e3425..6ad2d3bb945 100644 --- a/drivers/char/tpm/tpm.c +++ b/drivers/char/tpm/tpm.c @@ -1153,7 +1153,14 @@ struct tpm_chip *tpm_register_hardware(struct device *dev, const struct tpm_vend spin_unlock(&driver_lock); - sysfs_create_group(&dev->kobj, chip->vendor.attr_group); + if (sysfs_create_group(&dev->kobj, chip->vendor.attr_group)) { + list_del(&chip->list); + put_device(dev); + clear_bit(chip->dev_num, dev_mask); + kfree(chip); + kfree(devname); + return NULL; + } chip->bios_dir = tpm_bios_log_setup(devname); diff --git a/drivers/char/tpm/tpm_atmel.c b/drivers/char/tpm/tpm_atmel.c index ad8ffe49256..1ab0896070b 100644 --- a/drivers/char/tpm/tpm_atmel.c +++ b/drivers/char/tpm/tpm_atmel.c @@ -184,7 +184,9 @@ static int __init init_atmel(void) unsigned long base; struct tpm_chip *chip; - driver_register(&atml_drv); + rc = driver_register(&atml_drv); + if (rc) + return rc; if ((iobase = atmel_get_base_addr(&base, ®ion_size)) == NULL) { rc = -ENODEV; @@ -195,10 +197,8 @@ static int __init init_atmel(void) (atmel_request_region (tpm_atmel.base, region_size, "tpm_atmel0") == NULL) ? 0 : 1; - - if (IS_ERR - (pdev = - platform_device_register_simple("tpm_atmel", -1, NULL, 0))) { + pdev = platform_device_register_simple("tpm_atmel", -1, NULL, 0); + if (IS_ERR(pdev)) { rc = PTR_ERR(pdev); goto err_rel_reg; } diff --git a/drivers/char/tpm/tpm_nsc.c b/drivers/char/tpm/tpm_nsc.c index 26287aace87..608f73071be 100644 --- a/drivers/char/tpm/tpm_nsc.c +++ b/drivers/char/tpm/tpm_nsc.c @@ -284,7 +284,7 @@ static struct device_driver nsc_drv = { static int __init init_nsc(void) { int rc = 0; - int lo, hi; + int lo, hi, err; int nscAddrBase = TPM_ADDR; struct tpm_chip *chip; unsigned long base; @@ -297,7 +297,9 @@ static int __init init_nsc(void) return -ENODEV; } - driver_register(&nsc_drv); + err = driver_register(&nsc_drv); + if (err) + return err; hi = tpm_read_index(nscAddrBase, TPM_NSC_BASE0_HI); lo = tpm_read_index(nscAddrBase, TPM_NSC_BASE0_LO); diff --git a/drivers/eisa/eisa-bus.c b/drivers/eisa/eisa-bus.c index 3a365e159d8..d944647c82c 100644 --- a/drivers/eisa/eisa-bus.c +++ b/drivers/eisa/eisa-bus.c @@ -226,14 +226,26 @@ static int __init eisa_init_device (struct eisa_root_device *root, static int __init eisa_register_device (struct eisa_device *edev) { - if (device_register (&edev->dev)) - return -1; + int rc = device_register (&edev->dev); + if (rc) + return rc; - device_create_file (&edev->dev, &dev_attr_signature); - device_create_file (&edev->dev, &dev_attr_enabled); - device_create_file (&edev->dev, &dev_attr_modalias); + rc = device_create_file (&edev->dev, &dev_attr_signature); + if (rc) goto err_devreg; + rc = device_create_file (&edev->dev, &dev_attr_enabled); + if (rc) goto err_sig; + rc = device_create_file (&edev->dev, &dev_attr_modalias); + if (rc) goto err_enab; return 0; + +err_enab: + device_remove_file (&edev->dev, &dev_attr_enabled); +err_sig: + device_remove_file (&edev->dev, &dev_attr_signature); +err_devreg: + device_unregister(&edev->dev); + return rc; } static int __init eisa_request_resources (struct eisa_root_device *root, diff --git a/drivers/firmware/dell_rbu.c b/drivers/firmware/dell_rbu.c index fc17599c905..08b16179844 100644 --- a/drivers/firmware/dell_rbu.c +++ b/drivers/firmware/dell_rbu.c @@ -249,7 +249,7 @@ static int packetize_data(void *data, size_t length) if ((rc = create_packet(temp, packet_length))) return rc; - pr_debug("%p:%lu\n", temp, (end - temp)); + pr_debug("%p:%td\n", temp, (end - temp)); temp += packet_length; } @@ -718,14 +718,27 @@ static int __init dcdrbu_init(void) return -EIO; } - sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_data_attr); - sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_image_type_attr); - sysfs_create_bin_file(&rbu_device->dev.kobj, + rc = sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_data_attr); + if (rc) + goto out_devreg; + rc = sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_image_type_attr); + if (rc) + goto out_data; + rc = sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_packet_size_attr); + if (rc) + goto out_imtype; rbu_data.entry_created = 0; - return rc; + return 0; +out_imtype: + sysfs_remove_bin_file(&rbu_device->dev.kobj, &rbu_image_type_attr); +out_data: + sysfs_remove_bin_file(&rbu_device->dev.kobj, &rbu_data_attr); +out_devreg: + platform_device_unregister(rbu_device); + return rc; } static __exit void dcdrbu_exit(void) diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index 8ebce1c03ad..5ab5e393b88 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -639,7 +639,12 @@ efivar_create_sysfs_entry(unsigned long variable_name_size, kobject_set_name(&new_efivar->kobj, "%s", short_name); kobj_set_kset_s(new_efivar, vars_subsys); - kobject_register(&new_efivar->kobj); + i = kobject_register(&new_efivar->kobj); + if (i) { + kfree(short_name); + kfree(new_efivar); + return 1; + } kfree(short_name); short_name = NULL; diff --git a/drivers/ide/pci/generic.c b/drivers/ide/pci/generic.c index 965c43659e3..5b77a5bcbf0 100644 --- a/drivers/ide/pci/generic.c +++ b/drivers/ide/pci/generic.c @@ -237,10 +237,12 @@ static int __devinit generic_init_one(struct pci_dev *dev, const struct pci_devi if (dev->vendor == PCI_VENDOR_ID_JMICRON && PCI_FUNC(dev->devfn) != 1) goto out; - pci_read_config_word(dev, PCI_COMMAND, &command); - if (!(command & PCI_COMMAND_IO)) { - printk(KERN_INFO "Skipping disabled %s IDE controller.\n", d->name); - goto out; + if (dev->vendor != PCI_VENDOR_ID_JMICRON) { + pci_read_config_word(dev, PCI_COMMAND, &command); + if (!(command & PCI_COMMAND_IO)) { + printk(KERN_INFO "Skipping disabled %s IDE controller.\n", d->name); + goto out; + } } ret = ide_setup_pci_device(dev, d); out: diff --git a/drivers/input/misc/wistron_btns.c b/drivers/input/misc/wistron_btns.c index 4639537336f..7b9d1c1da41 100644 --- a/drivers/input/misc/wistron_btns.c +++ b/drivers/input/misc/wistron_btns.c @@ -17,7 +17,7 @@ * with this program; if not, write to the Free Software Foundation, Inc., * 59 Temple Place Suite 330, Boston, MA 02111-1307, USA. */ -#include <asm/io.h> +#include <linux/io.h> #include <linux/dmi.h> #include <linux/init.h> #include <linux/input.h> diff --git a/drivers/isdn/pcbit/layer2.c b/drivers/isdn/pcbit/layer2.c index 13e7d219d1c..937fd212038 100644 --- a/drivers/isdn/pcbit/layer2.c +++ b/drivers/isdn/pcbit/layer2.c @@ -311,6 +311,7 @@ pcbit_deliver(void *data) dev->read_queue = frame->next; spin_unlock_irqrestore(&dev->lock, flags); + msg = 0; SET_MSG_CPU(msg, 0); SET_MSG_PROC(msg, 0); SET_MSG_CMD(msg, frame->skb->data[2]); diff --git a/drivers/isdn/sc/init.c b/drivers/isdn/sc/init.c index 222ca7c08ba..06c9872e8c6 100644 --- a/drivers/isdn/sc/init.c +++ b/drivers/isdn/sc/init.c @@ -98,13 +98,14 @@ static int __init sc_init(void) * Confirm the I/O Address with a test */ if(io[b] == 0) { - pr_debug("I/O Address 0x%x is in use.\n"); + pr_debug("I/O Address invalid.\n"); continue; } outb(0x18, io[b] + 0x400 * EXP_PAGE0); if(inb(io[b] + 0x400 * EXP_PAGE0) != 0x18) { - pr_debug("I/O Base 0x%x fails test\n"); + pr_debug("I/O Base 0x%x fails test\n", + io[b] + 0x400 * EXP_PAGE0); continue; } } @@ -158,8 +159,8 @@ static int __init sc_init(void) outb(0xFF, io[b] + RESET_OFFSET); msleep_interruptible(10000); } - pr_debug("RAM Base for board %d is 0x%x, %s probe\n", b, ram[b], - ram[b] == 0 ? "will" : "won't"); + pr_debug("RAM Base for board %d is 0x%lx, %s probe\n", b, + ram[b], ram[b] == 0 ? "will" : "won't"); if(ram[b]) { /* @@ -168,7 +169,7 @@ static int __init sc_init(void) * board model */ if(request_region(ram[b], SRAM_PAGESIZE, "sc test")) { - pr_debug("request_region for RAM base 0x%x succeeded\n", ram[b]); + pr_debug("request_region for RAM base 0x%lx succeeded\n", ram[b]); model = identify_board(ram[b], io[b]); release_region(ram[b], SRAM_PAGESIZE); } @@ -204,7 +205,7 @@ static int __init sc_init(void) * Nope, there was no place in RAM for the * board, or it couldn't be identified */ - pr_debug("Failed to find an adapter at 0x%x\n", ram[b]); + pr_debug("Failed to find an adapter at 0x%lx\n", ram[b]); continue; } @@ -451,7 +452,7 @@ static int identify_board(unsigned long rambase, unsigned int iobase) HWConfig_pl hwci; int x; - pr_debug("Attempting to identify adapter @ 0x%x io 0x%x\n", + pr_debug("Attempting to identify adapter @ 0x%lx io 0x%x\n", rambase, iobase); /* @@ -490,7 +491,7 @@ static int identify_board(unsigned long rambase, unsigned int iobase) outb(PRI_BASEPG_VAL, pgport); msleep_interruptible(1000); sig = readl(rambase + SIG_OFFSET); - pr_debug("Looking for a signature, got 0x%x\n", sig); + pr_debug("Looking for a signature, got 0x%lx\n", sig); if(sig == SIGNATURE) return PRI_BOARD; @@ -500,7 +501,7 @@ static int identify_board(unsigned long rambase, unsigned int iobase) outb(BRI_BASEPG_VAL, pgport); msleep_interruptible(1000); sig = readl(rambase + SIG_OFFSET); - pr_debug("Looking for a signature, got 0x%x\n", sig); + pr_debug("Looking for a signature, got 0x%lx\n", sig); if(sig == SIGNATURE) return BRI_BOARD; @@ -510,7 +511,7 @@ static int identify_board(unsigned long rambase, unsigned int iobase) * Try to spot a card */ sig = readl(rambase + SIG_OFFSET); - pr_debug("Looking for a signature, got 0x%x\n", sig); + pr_debug("Looking for a signature, got 0x%lx\n", sig); if(sig != SIGNATURE) return -1; @@ -540,7 +541,7 @@ static int identify_board(unsigned long rambase, unsigned int iobase) memcpy_fromio(&rcvmsg, &(dpm->rsp_queue[dpm->rsp_tail]), MSG_LEN); pr_debug("Got HWConfig response, status = 0x%x\n", rcvmsg.rsp_status); memcpy(&hwci, &(rcvmsg.msg_data.HWCresponse), sizeof(HWConfig_pl)); - pr_debug("Hardware Config: Interface: %s, RAM Size: %d, Serial: %s\n" + pr_debug("Hardware Config: Interface: %s, RAM Size: %ld, Serial: %s\n" " Part: %s, Rev: %s\n", hwci.st_u_sense ? "S/T" : "U", hwci.ram_size, hwci.serial_no, hwci.part_no, hwci.rev_no); diff --git a/drivers/isdn/sc/packet.c b/drivers/isdn/sc/packet.c index f50defc38ae..1e04676b016 100644 --- a/drivers/isdn/sc/packet.c +++ b/drivers/isdn/sc/packet.c @@ -44,7 +44,7 @@ int sndpkt(int devId, int channel, struct sk_buff *data) return -ENODEV; } - pr_debug("%s: sndpkt: frst = 0x%x nxt = %d f = %d n = %d\n", + pr_debug("%s: sndpkt: frst = 0x%lx nxt = %d f = %d n = %d\n", sc_adapter[card]->devicename, sc_adapter[card]->channel[channel].first_sendbuf, sc_adapter[card]->channel[channel].next_sendbuf, @@ -66,7 +66,7 @@ int sndpkt(int devId, int channel, struct sk_buff *data) ReqLnkWrite.buff_offset = sc_adapter[card]->channel[channel].next_sendbuf * BUFFER_SIZE + sc_adapter[card]->channel[channel].first_sendbuf; ReqLnkWrite.msg_len = data->len; /* sk_buff size */ - pr_debug("%s: writing %d bytes to buffer offset 0x%x\n", + pr_debug("%s: writing %d bytes to buffer offset 0x%lx\n", sc_adapter[card]->devicename, ReqLnkWrite.msg_len, ReqLnkWrite.buff_offset); memcpy_toshmem(card, (char *)ReqLnkWrite.buff_offset, data->data, ReqLnkWrite.msg_len); @@ -74,7 +74,7 @@ int sndpkt(int devId, int channel, struct sk_buff *data) /* * sendmessage */ - pr_debug("%s: sndpkt size=%d, buf_offset=0x%x buf_indx=%d\n", + pr_debug("%s: sndpkt size=%d, buf_offset=0x%lx buf_indx=%d\n", sc_adapter[card]->devicename, ReqLnkWrite.msg_len, ReqLnkWrite.buff_offset, sc_adapter[card]->channel[channel].next_sendbuf); @@ -124,7 +124,7 @@ void rcvpkt(int card, RspMessage *rcvmsg) return; } skb_put(skb, rcvmsg->msg_data.response.msg_len); - pr_debug("%s: getting data from offset: 0x%x\n", + pr_debug("%s: getting data from offset: 0x%lx\n", sc_adapter[card]->devicename, rcvmsg->msg_data.response.buff_offset); memcpy_fromshmem(card, @@ -143,7 +143,7 @@ void rcvpkt(int card, RspMessage *rcvmsg) /* memset_shmem(card, rcvmsg->msg_data.response.buff_offset, 0, BUFFER_SIZE); */ newll.buff_offset = rcvmsg->msg_data.response.buff_offset; newll.msg_len = BUFFER_SIZE; - pr_debug("%s: recycled buffer at offset 0x%x size %d\n", + pr_debug("%s: recycled buffer at offset 0x%lx size %d\n", sc_adapter[card]->devicename, newll.buff_offset, newll.msg_len); sendmessage(card, CEPID, ceReqTypeLnk, ceReqClass1, ceReqLnkRead, @@ -186,7 +186,7 @@ int setup_buffers(int card, int c) sc_adapter[card]->channel[c-1].num_sendbufs = nBuffers / 2; sc_adapter[card]->channel[c-1].free_sendbufs = nBuffers / 2; sc_adapter[card]->channel[c-1].next_sendbuf = 0; - pr_debug("%s: send buffer setup complete: first=0x%x n=%d f=%d, nxt=%d\n", + pr_debug("%s: send buffer setup complete: first=0x%lx n=%d f=%d, nxt=%d\n", sc_adapter[card]->devicename, sc_adapter[card]->channel[c-1].first_sendbuf, sc_adapter[card]->channel[c-1].num_sendbufs, @@ -203,7 +203,7 @@ int setup_buffers(int card, int c) ((sc_adapter[card]->channel[c-1].first_sendbuf + (nBuffers / 2) * buffer_size) + (buffer_size * i)); RcvBuffOffset.msg_len = buffer_size; - pr_debug("%s: adding RcvBuffer #%d offset=0x%x sz=%d bufsz:%d\n", + pr_debug("%s: adding RcvBuffer #%d offset=0x%lx sz=%d bufsz:%d\n", sc_adapter[card]->devicename, i + 1, RcvBuffOffset.buff_offset, RcvBuffOffset.msg_len,buffer_size); diff --git a/drivers/isdn/sc/shmem.c b/drivers/isdn/sc/shmem.c index 24854826ca4..6f58862992d 100644 --- a/drivers/isdn/sc/shmem.c +++ b/drivers/isdn/sc/shmem.c @@ -61,7 +61,7 @@ void memcpy_toshmem(int card, void *dest, const void *src, size_t n) spin_unlock_irqrestore(&sc_adapter[card]->lock, flags); pr_debug("%s: set page to %#x\n",sc_adapter[card]->devicename, ((sc_adapter[card]->shmem_magic + ch * SRAM_PAGESIZE)>>14)|0x80); - pr_debug("%s: copying %d bytes from %#x to %#x\n", + pr_debug("%s: copying %d bytes from %#lx to %#lx\n", sc_adapter[card]->devicename, n, (unsigned long) src, sc_adapter[card]->rambase + ((unsigned long) dest %0x4000)); diff --git a/drivers/mca/mca-bus.c b/drivers/mca/mca-bus.c index 09baa43b259..da862e4632d 100644 --- a/drivers/mca/mca-bus.c +++ b/drivers/mca/mca-bus.c @@ -100,6 +100,7 @@ static DEVICE_ATTR(pos, S_IRUGO, mca_show_pos, NULL); int __init mca_register_device(int bus, struct mca_device *mca_dev) { struct mca_bus *mca_bus = mca_root_busses[bus]; + int rc; mca_dev->dev.parent = &mca_bus->dev; mca_dev->dev.bus = &mca_bus_type; @@ -108,13 +109,23 @@ int __init mca_register_device(int bus, struct mca_device *mca_dev) mca_dev->dev.dma_mask = &mca_dev->dma_mask; mca_dev->dev.coherent_dma_mask = mca_dev->dma_mask; - if (device_register(&mca_dev->dev)) - return 0; + rc = device_register(&mca_dev->dev); + if (rc) + goto err_out; - device_create_file(&mca_dev->dev, &dev_attr_id); - device_create_file(&mca_dev->dev, &dev_attr_pos); + rc = device_create_file(&mca_dev->dev, &dev_attr_id); + if (rc) goto err_out_devreg; + rc = device_create_file(&mca_dev->dev, &dev_attr_pos); + if (rc) goto err_out_id; return 1; + +err_out_id: + device_remove_file(&mca_dev->dev, &dev_attr_id); +err_out_devreg: + device_unregister(&mca_dev->dev); +err_out: + return 0; } /* */ @@ -130,13 +141,16 @@ struct mca_bus * __devinit mca_attach_bus(int bus) return NULL; } - mca_bus = kmalloc(sizeof(struct mca_bus), GFP_KERNEL); + mca_bus = kzalloc(sizeof(struct mca_bus), GFP_KERNEL); if (!mca_bus) return NULL; - memset(mca_bus, 0, sizeof(struct mca_bus)); + sprintf(mca_bus->dev.bus_id,"mca%d",bus); sprintf(mca_bus->name,"Host %s MCA Bridge", bus ? "Secondary" : "Primary"); - device_register(&mca_bus->dev); + if (device_register(&mca_bus->dev)) { + kfree(mca_bus); + return NULL; + } mca_root_busses[bus] = mca_bus; diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 8e67634e79a..d47d38ac71b 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1413,7 +1413,7 @@ int bitmap_create(mddev_t *mddev) int err; sector_t start; - BUG_ON(sizeof(bitmap_super_t) != 256); + BUILD_BUG_ON(sizeof(bitmap_super_t) != 256); if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */ return 0; diff --git a/drivers/net/b44.c b/drivers/net/b44.c index b124eee4eb1..1ec217433b4 100644 --- a/drivers/net/b44.c +++ b/drivers/net/b44.c @@ -1706,14 +1706,15 @@ static void __b44_set_rx_mode(struct net_device *dev) __b44_set_mac_addr(bp); - if (dev->flags & IFF_ALLMULTI) + if ((dev->flags & IFF_ALLMULTI) || + (dev->mc_count > B44_MCAST_TABLE_SIZE)) val |= RXCONFIG_ALLMULTI; else i = __b44_load_mcast(bp, dev); - for (; i < 64; i++) { + for (; i < 64; i++) __b44_cam_write(bp, zero, i); - } + bw32(bp, B44_RXCONFIG, val); val = br32(bp, B44_CAM_CTRL); bw32(bp, B44_CAM_CTRL, val | CAM_CTRL_ENABLE); @@ -2055,7 +2056,7 @@ static int b44_read_eeprom(struct b44 *bp, u8 *data) u16 *ptr = (u16 *) data; for (i = 0; i < 128; i += 2) - ptr[i / 2] = readw(bp->regs + 4096 + i); + ptr[i / 2] = cpu_to_le16(readw(bp->regs + 4096 + i)); return 0; } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index e83bc825f6a..32923162179 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1433,7 +1433,7 @@ void bond_alb_monitor(struct bonding *bond) * write lock to protect from other code that also * sets the promiscuity. */ - write_lock(&bond->curr_slave_lock); + write_lock_bh(&bond->curr_slave_lock); if (bond_info->primary_is_promisc && (++bond_info->rlb_promisc_timeout_counter >= RLB_PROMISC_TIMEOUT)) { @@ -1448,7 +1448,7 @@ void bond_alb_monitor(struct bonding *bond) bond_info->primary_is_promisc = 0; } - write_unlock(&bond->curr_slave_lock); + write_unlock_bh(&bond->curr_slave_lock); if (bond_info->rlb_rebalance) { bond_info->rlb_rebalance = 0; diff --git a/drivers/net/ehea/ehea.h b/drivers/net/ehea/ehea.h index 23b451a8ae1..b40724fc6b7 100644 --- a/drivers/net/ehea/ehea.h +++ b/drivers/net/ehea/ehea.h @@ -39,7 +39,7 @@ #include <asm/io.h> #define DRV_NAME "ehea" -#define DRV_VERSION "EHEA_0028" +#define DRV_VERSION "EHEA_0034" #define EHEA_MSG_DEFAULT (NETIF_MSG_LINK | NETIF_MSG_TIMER \ | NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR) @@ -50,6 +50,7 @@ #define EHEA_MAX_ENTRIES_SQ 32767 #define EHEA_MIN_ENTRIES_QP 127 +#define EHEA_SMALL_QUEUES #define EHEA_NUM_TX_QP 1 #ifdef EHEA_SMALL_QUEUES @@ -59,11 +60,11 @@ #define EHEA_DEF_ENTRIES_RQ2 1023 #define EHEA_DEF_ENTRIES_RQ3 1023 #else -#define EHEA_MAX_CQE_COUNT 32000 -#define EHEA_DEF_ENTRIES_SQ 16000 -#define EHEA_DEF_ENTRIES_RQ1 32080 -#define EHEA_DEF_ENTRIES_RQ2 4020 -#define EHEA_DEF_ENTRIES_RQ3 4020 +#define EHEA_MAX_CQE_COUNT 4080 +#define EHEA_DEF_ENTRIES_SQ 4080 +#define EHEA_DEF_ENTRIES_RQ1 8160 +#define EHEA_DEF_ENTRIES_RQ2 2040 +#define EHEA_DEF_ENTRIES_RQ3 2040 #endif #define EHEA_MAX_ENTRIES_EQ 20 diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c index c6b31775e26..eb7d44de59f 100644 --- a/drivers/net/ehea/ehea_main.c +++ b/drivers/net/ehea/ehea_main.c @@ -766,7 +766,7 @@ static void ehea_parse_eqe(struct ehea_adapter *adapter, u64 eqe) if (EHEA_BMASK_GET(NEQE_PORT_UP, eqe)) { if (!netif_carrier_ok(port->netdev)) { ret = ehea_sense_port_attr( - adapter->port[portnum]); + port); if (ret) { ehea_error("failed resensing port " "attributes"); @@ -818,7 +818,7 @@ static void ehea_parse_eqe(struct ehea_adapter *adapter, u64 eqe) netif_stop_queue(port->netdev); break; default: - ehea_error("unknown event code %x", ec); + ehea_error("unknown event code %x, eqe=0x%lX", ec, eqe); break; } } @@ -1841,7 +1841,7 @@ static int ehea_start_xmit(struct sk_buff *skb, struct net_device *dev) if (netif_msg_tx_queued(port)) { ehea_info("post swqe on QP %d", pr->qp->init_attr.qp_nr); - ehea_dump(swqe, sizeof(*swqe), "swqe"); + ehea_dump(swqe, 512, "swqe"); } ehea_post_swqe(pr->qp, swqe); diff --git a/drivers/net/ehea/ehea_phyp.c b/drivers/net/ehea/ehea_phyp.c index 4a85aca4c7e..0b51a8cea07 100644 --- a/drivers/net/ehea/ehea_phyp.c +++ b/drivers/net/ehea/ehea_phyp.c @@ -44,71 +44,99 @@ static inline u16 get_order_of_qentries(u16 queue_entries) #define H_ALL_RES_TYPE_MR 5 #define H_ALL_RES_TYPE_MW 6 -static long ehea_hcall_9arg_9ret(unsigned long opcode, - unsigned long arg1, unsigned long arg2, - unsigned long arg3, unsigned long arg4, - unsigned long arg5, unsigned long arg6, - unsigned long arg7, unsigned long arg8, - unsigned long arg9, unsigned long *out1, - unsigned long *out2,unsigned long *out3, - unsigned long *out4,unsigned long *out5, - unsigned long *out6,unsigned long *out7, - unsigned long *out8,unsigned long *out9) +static long ehea_plpar_hcall_norets(unsigned long opcode, + unsigned long arg1, + unsigned long arg2, + unsigned long arg3, + unsigned long arg4, + unsigned long arg5, + unsigned long arg6, + unsigned long arg7) { - long hret; + long ret; int i, sleep_msecs; for (i = 0; i < 5; i++) { - hret = plpar_hcall_9arg_9ret(opcode,arg1, arg2, arg3, arg4, - arg5, arg6, arg7, arg8, arg9, out1, - out2, out3, out4, out5, out6, out7, - out8, out9); - if (H_IS_LONG_BUSY(hret)) { - sleep_msecs = get_longbusy_msecs(hret); + ret = plpar_hcall_norets(opcode, arg1, arg2, arg3, arg4, + arg5, arg6, arg7); + + if (H_IS_LONG_BUSY(ret)) { + sleep_msecs = get_longbusy_msecs(ret); msleep_interruptible(sleep_msecs); continue; } - if (hret < H_SUCCESS) - ehea_error("op=%lx hret=%lx " - "i1=%lx i2=%lx i3=%lx i4=%lx i5=%lx i6=%lx " - "i7=%lx i8=%lx i9=%lx " - "o1=%lx o2=%lx o3=%lx o4=%lx o5=%lx o6=%lx " - "o7=%lx o8=%lx o9=%lx", - opcode, hret, arg1, arg2, arg3, arg4, arg5, - arg6, arg7, arg8, arg9, *out1, *out2, *out3, - *out4, *out5, *out6, *out7, *out8, *out9); - return hret; + if (ret < H_SUCCESS) + ehea_error("opcode=%lx ret=%lx" + " arg1=%lx arg2=%lx arg3=%lx arg4=%lx" + " arg5=%lx arg6=%lx arg7=%lx ", + opcode, ret, + arg1, arg2, arg3, arg4, arg5, + arg6, arg7); + + return ret; } + return H_BUSY; } -u64 ehea_h_query_ehea_qp(const u64 adapter_handle, const u8 qp_category, - const u64 qp_handle, const u64 sel_mask, void *cb_addr) +static long ehea_plpar_hcall9(unsigned long opcode, + unsigned long *outs, /* array of 9 outputs */ + unsigned long arg1, + unsigned long arg2, + unsigned long arg3, + unsigned long arg4, + unsigned long arg5, + unsigned long arg6, + unsigned long arg7, + unsigned long arg8, + unsigned long arg9) { - u64 dummy; + long ret; + int i, sleep_msecs; - if ((((u64)cb_addr) & (PAGE_SIZE - 1)) != 0) { - ehea_error("not on pageboundary"); - return H_PARAMETER; + for (i = 0; i < 5; i++) { + ret = plpar_hcall9(opcode, outs, + arg1, arg2, arg3, arg4, arg5, + arg6, arg7, arg8, arg9); + + if (H_IS_LONG_BUSY(ret)) { + sleep_msecs = get_longbusy_msecs(ret); + msleep_interruptible(sleep_msecs); + continue; + } + + if (ret < H_SUCCESS) + ehea_error("opcode=%lx ret=%lx" + " arg1=%lx arg2=%lx arg3=%lx arg4=%lx" + " arg5=%lx arg6=%lx arg7=%lx arg8=%lx" + " arg9=%lx" + " out1=%lx out2=%lx out3=%lx out4=%lx" + " out5=%lx out6=%lx out7=%lx out8=%lx" + " out9=%lx", + opcode, ret, + arg1, arg2, arg3, arg4, arg5, + arg6, arg7, arg8, arg9, + outs[0], outs[1], outs[2], outs[3], + outs[4], outs[5], outs[6], outs[7], + outs[8]); + + return ret; } - return ehea_hcall_9arg_9ret(H_QUERY_HEA_QP, - adapter_handle, /* R4 */ - qp_category, /* R5 */ - qp_handle, /* R6 */ - sel_mask, /* R7 */ - virt_to_abs(cb_addr), /* R8 */ - 0, 0, 0, 0, /* R9-R12 */ - &dummy, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ + return H_BUSY; +} + +u64 ehea_h_query_ehea_qp(const u64 adapter_handle, const u8 qp_category, + const u64 qp_handle, const u64 sel_mask, void *cb_addr) +{ + return ehea_plpar_hcall_norets(H_QUERY_HEA_QP, + adapter_handle, /* R4 */ + qp_category, /* R5 */ + qp_handle, /* R6 */ + sel_mask, /* R7 */ + virt_to_abs(cb_addr), /* R8 */ + 0, 0); } /* input param R5 */ @@ -180,6 +208,7 @@ u64 ehea_h_alloc_resource_qp(const u64 adapter_handle, u64 *qp_handle, struct h_epas *h_epas) { u64 hret; + u64 outs[PLPAR_HCALL9_BUFSIZE]; u64 allocate_controls = EHEA_BMASK_SET(H_ALL_RES_QP_EQPO, init_attr->low_lat_rq1 ? 1 : 0) @@ -219,45 +248,29 @@ u64 ehea_h_alloc_resource_qp(const u64 adapter_handle, EHEA_BMASK_SET(H_ALL_RES_QP_TH_RQ2, init_attr->rq2_threshold) | EHEA_BMASK_SET(H_ALL_RES_QP_TH_RQ3, init_attr->rq3_threshold); - u64 r5_out = 0; - u64 r6_out = 0; - u64 r7_out = 0; - u64 r8_out = 0; - u64 r9_out = 0; - u64 g_la_user_out = 0; - u64 r11_out = 0; - u64 r12_out = 0; - - hret = ehea_hcall_9arg_9ret(H_ALLOC_HEA_RESOURCE, - adapter_handle, /* R4 */ - allocate_controls, /* R5 */ - init_attr->send_cq_handle, /* R6 */ - init_attr->recv_cq_handle, /* R7 */ - init_attr->aff_eq_handle, /* R8 */ - r9_reg, /* R9 */ - max_r10_reg, /* R10 */ - r11_in, /* R11 */ - threshold, /* R12 */ - qp_handle, /* R4 */ - &r5_out, /* R5 */ - &r6_out, /* R6 */ - &r7_out, /* R7 */ - &r8_out, /* R8 */ - &r9_out, /* R9 */ - &g_la_user_out, /* R10 */ - &r11_out, /* R11 */ - &r12_out); /* R12 */ - - init_attr->qp_nr = (u32)r5_out; + hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE, + outs, + adapter_handle, /* R4 */ + allocate_controls, /* R5 */ + init_attr->send_cq_handle, /* R6 */ + init_attr->recv_cq_handle, /* R7 */ + init_attr->aff_eq_handle, /* R8 */ + r9_reg, /* R9 */ + max_r10_reg, /* R10 */ + r11_in, /* R11 */ + threshold); /* R12 */ + + *qp_handle = outs[0]; + init_attr->qp_nr = (u32)outs[1]; init_attr->act_nr_send_wqes = - (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_SWQE, r6_out); + (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_SWQE, outs[2]); init_attr->act_nr_rwqes_rq1 = - (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R1WQE, r6_out); + (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R1WQE, outs[2]); init_attr->act_nr_rwqes_rq2 = - (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R2WQE, r6_out); + (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R2WQE, outs[2]); init_attr->act_nr_rwqes_rq3 = - (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R3WQE, r6_out); + (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R3WQE, outs[2]); init_attr->act_wqe_size_enc_sq = init_attr->wqe_size_enc_sq; init_attr->act_wqe_size_enc_rq1 = init_attr->wqe_size_enc_rq1; @@ -265,25 +278,25 @@ u64 ehea_h_alloc_resource_qp(const u64 adapter_handle, init_attr->act_wqe_size_enc_rq3 = init_attr->wqe_size_enc_rq3; init_attr->nr_sq_pages = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_SQ, r8_out); + (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_SQ, outs[4]); init_attr->nr_rq1_pages = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ1, r8_out); + (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ1, outs[4]); init_attr->nr_rq2_pages = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ2, r9_out); + (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ2, outs[5]); init_attr->nr_rq3_pages = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ3, r9_out); + (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ3, outs[5]); init_attr->liobn_sq = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_SQ, r11_out); + (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_SQ, outs[7]); init_attr->liobn_rq1 = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ1, r11_out); + (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ1, outs[7]); init_attr->liobn_rq2 = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ2, r12_out); + (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ2, outs[8]); init_attr->liobn_rq3 = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ3, r12_out); + (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ3, outs[8]); if (!hret) - hcp_epas_ctor(h_epas, g_la_user_out, g_la_user_out); + hcp_epas_ctor(h_epas, outs[6], outs[6]); return hret; } @@ -292,31 +305,24 @@ u64 ehea_h_alloc_resource_cq(const u64 adapter_handle, struct ehea_cq_attr *cq_attr, u64 *cq_handle, struct h_epas *epas) { - u64 hret, dummy, act_nr_of_cqes_out, act_pages_out; - u64 g_la_privileged_out, g_la_user_out; - - hret = ehea_hcall_9arg_9ret(H_ALLOC_HEA_RESOURCE, - adapter_handle, /* R4 */ - H_ALL_RES_TYPE_CQ, /* R5 */ - cq_attr->eq_handle, /* R6 */ - cq_attr->cq_token, /* R7 */ - cq_attr->max_nr_of_cqes, /* R8 */ - 0, 0, 0, 0, /* R9-R12 */ - cq_handle, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &act_nr_of_cqes_out, /* R7 */ - &act_pages_out, /* R8 */ - &g_la_privileged_out, /* R9 */ - &g_la_user_out, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ - - cq_attr->act_nr_of_cqes = act_nr_of_cqes_out; - cq_attr->nr_pages = act_pages_out; + u64 hret; + u64 outs[PLPAR_HCALL9_BUFSIZE]; + + hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE, + outs, + adapter_handle, /* R4 */ + H_ALL_RES_TYPE_CQ, /* R5 */ + cq_attr->eq_handle, /* R6 */ + cq_attr->cq_token, /* R7 */ + cq_attr->max_nr_of_cqes, /* R8 */ + 0, 0, 0, 0); /* R9-R12 */ + + *cq_handle = outs[0]; + cq_attr->act_nr_of_cqes = outs[3]; + cq_attr->nr_pages = outs[4]; if (!hret) - hcp_epas_ctor(epas, g_la_privileged_out, g_la_user_out); + hcp_epas_ctor(epas, outs[5], outs[6]); return hret; } @@ -361,9 +367,8 @@ u64 ehea_h_alloc_resource_cq(const u64 adapter_handle, u64 ehea_h_alloc_resource_eq(const u64 adapter_handle, struct ehea_eq_attr *eq_attr, u64 *eq_handle) { - u64 hret, dummy, eq_liobn, allocate_controls; - u64 ist1_out, ist2_out, ist3_out, ist4_out; - u64 act_nr_of_eqes_out, act_pages_out; + u64 hret, allocate_controls; + u64 outs[PLPAR_HCALL9_BUFSIZE]; /* resource type */ allocate_controls = @@ -372,27 +377,20 @@ u64 ehea_h_alloc_resource_eq(const u64 adapter_handle, | EHEA_BMASK_SET(H_ALL_RES_EQ_INH_EQE_GEN, !eq_attr->eqe_gen) | EHEA_BMASK_SET(H_ALL_RES_EQ_NON_NEQ_ISN, 1); - hret = ehea_hcall_9arg_9ret(H_ALLOC_HEA_RESOURCE, - adapter_handle, /* R4 */ - allocate_controls, /* R5 */ - eq_attr->max_nr_of_eqes, /* R6 */ - 0, 0, 0, 0, 0, 0, /* R7-R10 */ - eq_handle, /* R4 */ - &dummy, /* R5 */ - &eq_liobn, /* R6 */ - &act_nr_of_eqes_out, /* R7 */ - &act_pages_out, /* R8 */ - &ist1_out, /* R9 */ - &ist2_out, /* R10 */ - &ist3_out, /* R11 */ - &ist4_out); /* R12 */ - - eq_attr->act_nr_of_eqes = act_nr_of_eqes_out; - eq_attr->nr_pages = act_pages_out; - eq_attr->ist1 = ist1_out; - eq_attr->ist2 = ist2_out; - eq_attr->ist3 = ist3_out; - eq_attr->ist4 = ist4_out; + hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE, + outs, + adapter_handle, /* R4 */ + allocate_controls, /* R5 */ + eq_attr->max_nr_of_eqes, /* R6 */ + 0, 0, 0, 0, 0, 0); /* R7-R10 */ + + *eq_handle = outs[0]; + eq_attr->act_nr_of_eqes = outs[3]; + eq_attr->nr_pages = outs[4]; + eq_attr->ist1 = outs[5]; + eq_attr->ist2 = outs[6]; + eq_attr->ist3 = outs[7]; + eq_attr->ist4 = outs[8]; return hret; } @@ -402,31 +400,22 @@ u64 ehea_h_modify_ehea_qp(const u64 adapter_handle, const u8 cat, void *cb_addr, u64 *inv_attr_id, u64 *proc_mask, u16 *out_swr, u16 *out_rwr) { - u64 hret, dummy, act_out_swr, act_out_rwr; - - if ((((u64)cb_addr) & (PAGE_SIZE - 1)) != 0) { - ehea_error("not on page boundary"); - return H_PARAMETER; - } - - hret = ehea_hcall_9arg_9ret(H_MODIFY_HEA_QP, - adapter_handle, /* R4 */ - (u64) cat, /* R5 */ - qp_handle, /* R6 */ - sel_mask, /* R7 */ - virt_to_abs(cb_addr), /* R8 */ - 0, 0, 0, 0, /* R9-R12 */ - inv_attr_id, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &act_out_swr, /* R7 */ - &act_out_rwr, /* R8 */ - proc_mask, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ - *out_swr = act_out_swr; - *out_rwr = act_out_rwr; + u64 hret; + u64 outs[PLPAR_HCALL9_BUFSIZE]; + + hret = ehea_plpar_hcall9(H_MODIFY_HEA_QP, + outs, + adapter_handle, /* R4 */ + (u64) cat, /* R5 */ + qp_handle, /* R6 */ + sel_mask, /* R7 */ + virt_to_abs(cb_addr), /* R8 */ + 0, 0, 0, 0); /* R9-R12 */ + + *inv_attr_id = outs[0]; + *out_swr = outs[3]; + *out_rwr = outs[4]; + *proc_mask = outs[5]; return hret; } @@ -435,122 +424,81 @@ u64 ehea_h_register_rpage(const u64 adapter_handle, const u8 pagesize, const u8 queue_type, const u64 resource_handle, const u64 log_pageaddr, u64 count) { - u64 dummy, reg_control; + u64 reg_control; reg_control = EHEA_BMASK_SET(H_REG_RPAGE_PAGE_SIZE, pagesize) | EHEA_BMASK_SET(H_REG_RPAGE_QT, queue_type); - return ehea_hcall_9arg_9ret(H_REGISTER_HEA_RPAGES, - adapter_handle, /* R4 */ - reg_control, /* R5 */ - resource_handle, /* R6 */ - log_pageaddr, /* R7 */ - count, /* R8 */ - 0, 0, 0, 0, /* R9-R12 */ - &dummy, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ + return ehea_plpar_hcall_norets(H_REGISTER_HEA_RPAGES, + adapter_handle, /* R4 */ + reg_control, /* R5 */ + resource_handle, /* R6 */ + log_pageaddr, /* R7 */ + count, /* R8 */ + 0, 0); /* R9-R10 */ } u64 ehea_h_register_smr(const u64 adapter_handle, const u64 orig_mr_handle, const u64 vaddr_in, const u32 access_ctrl, const u32 pd, struct ehea_mr *mr) { - u64 hret, dummy, lkey_out; - - hret = ehea_hcall_9arg_9ret(H_REGISTER_SMR, - adapter_handle , /* R4 */ - orig_mr_handle, /* R5 */ - vaddr_in, /* R6 */ - (((u64)access_ctrl) << 32ULL), /* R7 */ - pd, /* R8 */ - 0, 0, 0, 0, /* R9-R12 */ - &mr->handle, /* R4 */ - &dummy, /* R5 */ - &lkey_out, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ - mr->lkey = (u32)lkey_out; + u64 hret; + u64 outs[PLPAR_HCALL9_BUFSIZE]; + + hret = ehea_plpar_hcall9(H_REGISTER_SMR, + outs, + adapter_handle , /* R4 */ + orig_mr_handle, /* R5 */ + vaddr_in, /* R6 */ + (((u64)access_ctrl) << 32ULL), /* R7 */ + pd, /* R8 */ + 0, 0, 0, 0); /* R9-R12 */ + + mr->handle = outs[0]; + mr->lkey = (u32)outs[2]; return hret; } u64 ehea_h_disable_and_get_hea(const u64 adapter_handle, const u64 qp_handle) { - u64 hret, dummy, ladr_next_sq_wqe_out; - u64 ladr_next_rq1_wqe_out, ladr_next_rq2_wqe_out, ladr_next_rq3_wqe_out; - - hret = ehea_hcall_9arg_9ret(H_DISABLE_AND_GET_HEA, - adapter_handle, /* R4 */ - H_DISABLE_GET_EHEA_WQE_P, /* R5 */ - qp_handle, /* R6 */ - 0, 0, 0, 0, 0, 0, /* R7-R12 */ - &ladr_next_sq_wqe_out, /* R4 */ - &ladr_next_rq1_wqe_out, /* R5 */ - &ladr_next_rq2_wqe_out, /* R6 */ - &ladr_next_rq3_wqe_out, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ - return hret; + u64 outs[PLPAR_HCALL9_BUFSIZE]; + + return ehea_plpar_hcall9(H_DISABLE_AND_GET_HEA, + outs, + adapter_handle, /* R4 */ + H_DISABLE_GET_EHEA_WQE_P, /* R5 */ + qp_handle, /* R6 */ + 0, 0, 0, 0, 0, 0); /* R7-R12 */ } u64 ehea_h_free_resource(const u64 adapter_handle, const u64 res_handle) { - u64 dummy; - - return ehea_hcall_9arg_9ret(H_FREE_RESOURCE, - adapter_handle, /* R4 */ - res_handle, /* R5 */ - 0, 0, 0, 0, 0, 0, 0, /* R6-R12 */ - &dummy, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ + return ehea_plpar_hcall_norets(H_FREE_RESOURCE, + adapter_handle, /* R4 */ + res_handle, /* R5 */ + 0, 0, 0, 0, 0); /* R6-R10 */ } u64 ehea_h_alloc_resource_mr(const u64 adapter_handle, const u64 vaddr, const u64 length, const u32 access_ctrl, const u32 pd, u64 *mr_handle, u32 *lkey) { - u64 hret, dummy, lkey_out; - - hret = ehea_hcall_9arg_9ret(H_ALLOC_HEA_RESOURCE, - adapter_handle, /* R4 */ - 5, /* R5 */ - vaddr, /* R6 */ - length, /* R7 */ - (((u64) access_ctrl) << 32ULL),/* R8 */ - pd, /* R9 */ - 0, 0, 0, /* R10-R12 */ - mr_handle, /* R4 */ - &dummy, /* R5 */ - &lkey_out, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ - *lkey = (u32) lkey_out; - + u64 hret; + u64 outs[PLPAR_HCALL9_BUFSIZE]; + + hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE, + outs, + adapter_handle, /* R4 */ + 5, /* R5 */ + vaddr, /* R6 */ + length, /* R7 */ + (((u64) access_ctrl) << 32ULL), /* R8 */ + pd, /* R9 */ + 0, 0, 0); /* R10-R12 */ + + *mr_handle = outs[0]; + *lkey = (u32)outs[2]; return hret; } @@ -570,23 +518,14 @@ u64 ehea_h_register_rpage_mr(const u64 adapter_handle, const u64 mr_handle, u64 ehea_h_query_ehea(const u64 adapter_handle, void *cb_addr) { - u64 hret, dummy, cb_logaddr; + u64 hret, cb_logaddr; cb_logaddr = virt_to_abs(cb_addr); - hret = ehea_hcall_9arg_9ret(H_QUERY_HEA, - adapter_handle, /* R4 */ - cb_logaddr, /* R5 */ - 0, 0, 0, 0, 0, 0, 0, /* R6-R12 */ - &dummy, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ + hret = ehea_plpar_hcall_norets(H_QUERY_HEA, + adapter_handle, /* R4 */ + cb_logaddr, /* R5 */ + 0, 0, 0, 0, 0); /* R6-R10 */ #ifdef DEBUG ehea_dmp(cb_addr, sizeof(struct hcp_query_ehea), "hcp_query_ehea"); #endif @@ -597,36 +536,28 @@ u64 ehea_h_query_ehea_port(const u64 adapter_handle, const u16 port_num, const u8 cb_cat, const u64 select_mask, void *cb_addr) { - u64 port_info, dummy; + u64 port_info; u64 cb_logaddr = virt_to_abs(cb_addr); u64 arr_index = 0; port_info = EHEA_BMASK_SET(H_MEHEAPORT_CAT, cb_cat) | EHEA_BMASK_SET(H_MEHEAPORT_PN, port_num); - return ehea_hcall_9arg_9ret(H_QUERY_HEA_PORT, - adapter_handle, /* R4 */ - port_info, /* R5 */ - select_mask, /* R6 */ - arr_index, /* R7 */ - cb_logaddr, /* R8 */ - 0, 0, 0, 0, /* R9-R12 */ - &dummy, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ + return ehea_plpar_hcall_norets(H_QUERY_HEA_PORT, + adapter_handle, /* R4 */ + port_info, /* R5 */ + select_mask, /* R6 */ + arr_index, /* R7 */ + cb_logaddr, /* R8 */ + 0, 0); /* R9-R10 */ } u64 ehea_h_modify_ehea_port(const u64 adapter_handle, const u16 port_num, const u8 cb_cat, const u64 select_mask, void *cb_addr) { - u64 port_info, dummy, inv_attr_ident, proc_mask; + u64 outs[PLPAR_HCALL9_BUFSIZE]; + u64 port_info; u64 arr_index = 0; u64 cb_logaddr = virt_to_abs(cb_addr); @@ -635,29 +566,21 @@ u64 ehea_h_modify_ehea_port(const u64 adapter_handle, const u16 port_num, #ifdef DEBUG ehea_dump(cb_addr, sizeof(struct hcp_ehea_port_cb0), "Before HCALL"); #endif - return ehea_hcall_9arg_9ret(H_MODIFY_HEA_PORT, - adapter_handle, /* R4 */ - port_info, /* R5 */ - select_mask, /* R6 */ - arr_index, /* R7 */ - cb_logaddr, /* R8 */ - 0, 0, 0, 0, /* R9-R12 */ - &inv_attr_ident, /* R4 */ - &proc_mask, /* R5 */ - &dummy, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ + return ehea_plpar_hcall9(H_MODIFY_HEA_PORT, + outs, + adapter_handle, /* R4 */ + port_info, /* R5 */ + select_mask, /* R6 */ + arr_index, /* R7 */ + cb_logaddr, /* R8 */ + 0, 0, 0, 0); /* R9-R12 */ } u64 ehea_h_reg_dereg_bcmc(const u64 adapter_handle, const u16 port_num, const u8 reg_type, const u64 mc_mac_addr, const u16 vlan_id, const u32 hcall_id) { - u64 r5_port_num, r6_reg_type, r7_mc_mac_addr, r8_vlan_id, dummy; + u64 r5_port_num, r6_reg_type, r7_mc_mac_addr, r8_vlan_id; u64 mac_addr = mc_mac_addr >> 16; r5_port_num = EHEA_BMASK_SET(H_REGBCMC_PN, port_num); @@ -665,41 +588,21 @@ u64 ehea_h_reg_dereg_bcmc(const u64 adapter_handle, const u16 port_num, r7_mc_mac_addr = EHEA_BMASK_SET(H_REGBCMC_MACADDR, mac_addr); r8_vlan_id = EHEA_BMASK_SET(H_REGBCMC_VLANID, vlan_id); - return ehea_hcall_9arg_9ret(hcall_id, - adapter_handle, /* R4 */ - r5_port_num, /* R5 */ - r6_reg_type, /* R6 */ - r7_mc_mac_addr, /* R7 */ - r8_vlan_id, /* R8 */ - 0, 0, 0, 0, /* R9-R12 */ - &dummy, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ + return ehea_plpar_hcall_norets(hcall_id, + adapter_handle, /* R4 */ + r5_port_num, /* R5 */ + r6_reg_type, /* R6 */ + r7_mc_mac_addr, /* R7 */ + r8_vlan_id, /* R8 */ + 0, 0); /* R9-R12 */ } u64 ehea_h_reset_events(const u64 adapter_handle, const u64 neq_handle, const u64 event_mask) { - u64 dummy; - - return ehea_hcall_9arg_9ret(H_RESET_EVENTS, - adapter_handle, /* R4 */ - neq_handle, /* R5 */ - event_mask, /* R6 */ - 0, 0, 0, 0, 0, 0, /* R7-R12 */ - &dummy, /* R4 */ - &dummy, /* R5 */ - &dummy, /* R6 */ - &dummy, /* R7 */ - &dummy, /* R8 */ - &dummy, /* R9 */ - &dummy, /* R10 */ - &dummy, /* R11 */ - &dummy); /* R12 */ + return ehea_plpar_hcall_norets(H_RESET_EVENTS, + adapter_handle, /* R4 */ + neq_handle, /* R5 */ + event_mask, /* R6 */ + 0, 0, 0, 0); /* R7-R12 */ } diff --git a/drivers/net/eth16i.c b/drivers/net/eth16i.c index 8cc3c331aca..b7b8bc2a630 100644 --- a/drivers/net/eth16i.c +++ b/drivers/net/eth16i.c @@ -162,9 +162,9 @@ static char *version = #include <linux/skbuff.h> #include <linux/bitops.h> #include <linux/jiffies.h> +#include <linux/io.h> #include <asm/system.h> -#include <asm/io.h> #include <asm/dma.h> diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index 99b7a411db2..c5ed635bce3 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -2497,6 +2497,7 @@ static irqreturn_t nv_nic_irq_tx(int foo, void *data) u8 __iomem *base = get_hwbase(dev); u32 events; int i; + unsigned long flags; dprintk(KERN_DEBUG "%s: nv_nic_irq_tx\n", dev->name); @@ -2508,16 +2509,16 @@ static irqreturn_t nv_nic_irq_tx(int foo, void *data) if (!(events & np->irqmask)) break; - spin_lock_irq(&np->lock); + spin_lock_irqsave(&np->lock, flags); nv_tx_done(dev); - spin_unlock_irq(&np->lock); + spin_unlock_irqrestore(&np->lock, flags); if (events & (NVREG_IRQ_TX_ERR)) { dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n", dev->name, events); } if (i > max_interrupt_work) { - spin_lock_irq(&np->lock); + spin_lock_irqsave(&np->lock, flags); /* disable interrupts on the nic */ writel(NVREG_IRQ_TX_ALL, base + NvRegIrqMask); pci_push(base); @@ -2527,7 +2528,7 @@ static irqreturn_t nv_nic_irq_tx(int foo, void *data) mod_timer(&np->nic_poll, jiffies + POLL_WAIT); } printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_tx.\n", dev->name, i); - spin_unlock_irq(&np->lock); + spin_unlock_irqrestore(&np->lock, flags); break; } @@ -2601,6 +2602,7 @@ static irqreturn_t nv_nic_irq_rx(int foo, void *data) u8 __iomem *base = get_hwbase(dev); u32 events; int i; + unsigned long flags; dprintk(KERN_DEBUG "%s: nv_nic_irq_rx\n", dev->name); @@ -2614,14 +2616,14 @@ static irqreturn_t nv_nic_irq_rx(int foo, void *data) nv_rx_process(dev, dev->weight); if (nv_alloc_rx(dev)) { - spin_lock_irq(&np->lock); + spin_lock_irqsave(&np->lock, flags); if (!np->in_shutdown) mod_timer(&np->oom_kick, jiffies + OOM_REFILL); - spin_unlock_irq(&np->lock); + spin_unlock_irqrestore(&np->lock, flags); } if (i > max_interrupt_work) { - spin_lock_irq(&np->lock); + spin_lock_irqsave(&np->lock, flags); /* disable interrupts on the nic */ writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask); pci_push(base); @@ -2631,7 +2633,7 @@ static irqreturn_t nv_nic_irq_rx(int foo, void *data) mod_timer(&np->nic_poll, jiffies + POLL_WAIT); } printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_rx.\n", dev->name, i); - spin_unlock_irq(&np->lock); + spin_unlock_irqrestore(&np->lock, flags); break; } } @@ -2648,6 +2650,7 @@ static irqreturn_t nv_nic_irq_other(int foo, void *data) u8 __iomem *base = get_hwbase(dev); u32 events; int i; + unsigned long flags; dprintk(KERN_DEBUG "%s: nv_nic_irq_other\n", dev->name); @@ -2660,14 +2663,14 @@ static irqreturn_t nv_nic_irq_other(int foo, void *data) break; if (events & NVREG_IRQ_LINK) { - spin_lock_irq(&np->lock); + spin_lock_irqsave(&np->lock, flags); nv_link_irq(dev); - spin_unlock_irq(&np->lock); + spin_unlock_irqrestore(&np->lock, flags); } if (np->need_linktimer && time_after(jiffies, np->link_timeout)) { - spin_lock_irq(&np->lock); + spin_lock_irqsave(&np->lock, flags); nv_linkchange(dev); - spin_unlock_irq(&np->lock); + spin_unlock_irqrestore(&np->lock, flags); np->link_timeout = jiffies + LINK_TIMEOUT; } if (events & (NVREG_IRQ_UNKNOWN)) { @@ -2675,7 +2678,7 @@ static irqreturn_t nv_nic_irq_other(int foo, void *data) dev->name, events); } if (i > max_interrupt_work) { - spin_lock_irq(&np->lock); + spin_lock_irqsave(&np->lock, flags); /* disable interrupts on the nic */ writel(NVREG_IRQ_OTHER, base + NvRegIrqMask); pci_push(base); @@ -2685,7 +2688,7 @@ static irqreturn_t nv_nic_irq_other(int foo, void *data) mod_timer(&np->nic_poll, jiffies + POLL_WAIT); } printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_other.\n", dev->name, i); - spin_unlock_irq(&np->lock); + spin_unlock_irqrestore(&np->lock, flags); break; } diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index 4bac3cd8f23..2802db23d3c 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -213,6 +213,7 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struc } free_index = pool->consumer_index++ % pool->size; + pool->consumer_index = free_index; index = pool->free_map[free_index]; ibmveth_assert(index != IBM_VETH_INVALID_MAP); @@ -238,7 +239,10 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struc if(lpar_rc != H_SUCCESS) { pool->free_map[free_index] = index; pool->skbuff[index] = NULL; - pool->consumer_index--; + if (pool->consumer_index == 0) + pool->consumer_index = pool->size - 1; + else + pool->consumer_index--; dma_unmap_single(&adapter->vdev->dev, pool->dma_addr[index], pool->buff_size, DMA_FROM_DEVICE); @@ -326,6 +330,7 @@ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, u64 DMA_FROM_DEVICE); free_index = adapter->rx_buff_pool[pool].producer_index++ % adapter->rx_buff_pool[pool].size; + adapter->rx_buff_pool[pool].producer_index = free_index; adapter->rx_buff_pool[pool].free_map[free_index] = index; mb(); @@ -437,6 +442,31 @@ static void ibmveth_cleanup(struct ibmveth_adapter *adapter) &adapter->rx_buff_pool[i]); } +static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter, + union ibmveth_buf_desc rxq_desc, u64 mac_address) +{ + int rc, try_again = 1; + + /* After a kexec the adapter will still be open, so our attempt to + * open it will fail. So if we get a failure we free the adapter and + * try again, but only once. */ +retry: + rc = h_register_logical_lan(adapter->vdev->unit_address, + adapter->buffer_list_dma, rxq_desc.desc, + adapter->filter_list_dma, mac_address); + + if (rc != H_SUCCESS && try_again) { + do { + rc = h_free_logical_lan(adapter->vdev->unit_address); + } while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY)); + + try_again = 0; + goto retry; + } + + return rc; +} + static int ibmveth_open(struct net_device *netdev) { struct ibmveth_adapter *adapter = netdev->priv; @@ -502,12 +532,9 @@ static int ibmveth_open(struct net_device *netdev) ibmveth_debug_printk("filter list @ 0x%p\n", adapter->filter_list_addr); ibmveth_debug_printk("receive q @ 0x%p\n", adapter->rx_queue.queue_addr); + h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE); - lpar_rc = h_register_logical_lan(adapter->vdev->unit_address, - adapter->buffer_list_dma, - rxq_desc.desc, - adapter->filter_list_dma, - mac_address); + lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address); if(lpar_rc != H_SUCCESS) { ibmveth_error_printk("h_register_logical_lan failed with %ld\n", lpar_rc); @@ -905,6 +932,14 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } +#ifdef CONFIG_NET_POLL_CONTROLLER +static void ibmveth_poll_controller(struct net_device *dev) +{ + ibmveth_replenish_task(dev->priv); + ibmveth_interrupt(dev->irq, dev); +} +#endif + static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) { int rc, i; @@ -977,6 +1012,9 @@ static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_ netdev->ethtool_ops = &netdev_ethtool_ops; netdev->change_mtu = ibmveth_change_mtu; SET_NETDEV_DEV(netdev, &dev->dev); +#ifdef CONFIG_NET_POLL_CONTROLLER + netdev->poll_controller = ibmveth_poll_controller; +#endif netdev->features |= NETIF_F_LLTX; spin_lock_init(&adapter->stats_lock); @@ -1132,7 +1170,9 @@ static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter) { struct proc_dir_entry *entry; if (ibmveth_proc_dir) { - entry = create_proc_entry(adapter->netdev->name, S_IFREG, ibmveth_proc_dir); + char u_addr[10]; + sprintf(u_addr, "%x", adapter->vdev->unit_address); + entry = create_proc_entry(u_addr, S_IFREG, ibmveth_proc_dir); if (!entry) { ibmveth_error_printk("Cannot create adapter proc entry"); } else { @@ -1147,7 +1187,9 @@ static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter) static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter) { if (ibmveth_proc_dir) { - remove_proc_entry(adapter->netdev->name, ibmveth_proc_dir); + char u_addr[10]; + sprintf(u_addr, "%x", adapter->vdev->unit_address); + remove_proc_entry(u_addr, ibmveth_proc_dir); } } diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c index 2ffa3a59e70..9997081c6da 100644 --- a/drivers/net/mv643xx_eth.c +++ b/drivers/net/mv643xx_eth.c @@ -2155,7 +2155,7 @@ static void eth_update_mib_counters(struct mv643xx_private *mp) for (offset = ETH_MIB_BAD_OCTETS_RECEIVED; offset <= ETH_MIB_FRAMES_1024_TO_MAX_OCTETS; offset += 4) - *(u32 *)((char *)p + offset) = read_mib(mp, offset); + *(u32 *)((char *)p + offset) += read_mib(mp, offset); p->good_octets_sent += read_mib(mp, ETH_MIB_GOOD_OCTETS_SENT_LOW); p->good_octets_sent += @@ -2164,7 +2164,7 @@ static void eth_update_mib_counters(struct mv643xx_private *mp) for (offset = ETH_MIB_GOOD_FRAMES_SENT; offset <= ETH_MIB_LATE_COLLISION; offset += 4) - *(u32 *)((char *)p + offset) = read_mib(mp, offset); + *(u32 *)((char *)p + offset) += read_mib(mp, offset); } /* diff --git a/drivers/net/skge.c b/drivers/net/skge.c index a4a58e4e93a..e7e414928f8 100644 --- a/drivers/net/skge.c +++ b/drivers/net/skge.c @@ -43,7 +43,7 @@ #include "skge.h" #define DRV_NAME "skge" -#define DRV_VERSION "1.8" +#define DRV_VERSION "1.9" #define PFX DRV_NAME " " #define DEFAULT_TX_RING_SIZE 128 @@ -197,8 +197,8 @@ static u32 skge_supported_modes(const struct skge_hw *hw) else if (hw->chip_id == CHIP_ID_YUKON) supported &= ~SUPPORTED_1000baseT_Half; } else - supported = SUPPORTED_1000baseT_Full | SUPPORTED_FIBRE - | SUPPORTED_Autoneg; + supported = SUPPORTED_1000baseT_Full | SUPPORTED_1000baseT_Half + | SUPPORTED_FIBRE | SUPPORTED_Autoneg; return supported; } @@ -487,31 +487,37 @@ static void skge_get_pauseparam(struct net_device *dev, { struct skge_port *skge = netdev_priv(dev); - ecmd->tx_pause = (skge->flow_control == FLOW_MODE_LOC_SEND) - || (skge->flow_control == FLOW_MODE_SYMMETRIC); - ecmd->rx_pause = (skge->flow_control == FLOW_MODE_REM_SEND) - || (skge->flow_control == FLOW_MODE_SYMMETRIC); + ecmd->rx_pause = (skge->flow_control == FLOW_MODE_SYMMETRIC) + || (skge->flow_control == FLOW_MODE_SYM_OR_REM); + ecmd->tx_pause = ecmd->rx_pause || (skge->flow_control == FLOW_MODE_LOC_SEND); - ecmd->autoneg = skge->autoneg; + ecmd->autoneg = ecmd->rx_pause || ecmd->tx_pause; } static int skge_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *ecmd) { struct skge_port *skge = netdev_priv(dev); + struct ethtool_pauseparam old; - skge->autoneg = ecmd->autoneg; - if (ecmd->rx_pause && ecmd->tx_pause) - skge->flow_control = FLOW_MODE_SYMMETRIC; - else if (ecmd->rx_pause && !ecmd->tx_pause) - skge->flow_control = FLOW_MODE_REM_SEND; - else if (!ecmd->rx_pause && ecmd->tx_pause) - skge->flow_control = FLOW_MODE_LOC_SEND; - else - skge->flow_control = FLOW_MODE_NONE; + skge_get_pauseparam(dev, &old); + + if (ecmd->autoneg != old.autoneg) + skge->flow_control = ecmd->autoneg ? FLOW_MODE_NONE : FLOW_MODE_SYMMETRIC; + else { + if (ecmd->rx_pause && ecmd->tx_pause) + skge->flow_control = FLOW_MODE_SYMMETRIC; + else if (ecmd->rx_pause && !ecmd->tx_pause) + skge->flow_control = FLOW_MODE_SYM_OR_REM; + else if (!ecmd->rx_pause && ecmd->tx_pause) + skge->flow_control = FLOW_MODE_LOC_SEND; + else + skge->flow_control = FLOW_MODE_NONE; + } if (netif_running(dev)) skge_phy_reset(skge); + return 0; } @@ -854,6 +860,23 @@ static int skge_rx_fill(struct net_device *dev) return 0; } +static const char *skge_pause(enum pause_status status) +{ + switch(status) { + case FLOW_STAT_NONE: + return "none"; + case FLOW_STAT_REM_SEND: + return "rx only"; + case FLOW_STAT_LOC_SEND: + return "tx_only"; + case FLOW_STAT_SYMMETRIC: /* Both station may send PAUSE */ + return "both"; + default: + return "indeterminated"; + } +} + + static void skge_link_up(struct skge_port *skge) { skge_write8(skge->hw, SK_REG(skge->port, LNK_LED_REG), @@ -862,16 +885,13 @@ static void skge_link_up(struct skge_port *skge) netif_carrier_on(skge->netdev); netif_wake_queue(skge->netdev); - if (netif_msg_link(skge)) + if (netif_msg_link(skge)) { printk(KERN_INFO PFX "%s: Link is up at %d Mbps, %s duplex, flow control %s\n", skge->netdev->name, skge->speed, skge->duplex == DUPLEX_FULL ? "full" : "half", - (skge->flow_control == FLOW_MODE_NONE) ? "none" : - (skge->flow_control == FLOW_MODE_LOC_SEND) ? "tx only" : - (skge->flow_control == FLOW_MODE_REM_SEND) ? "rx only" : - (skge->flow_control == FLOW_MODE_SYMMETRIC) ? "tx and rx" : - "unknown"); + skge_pause(skge->flow_status)); + } } static void skge_link_down(struct skge_port *skge) @@ -884,6 +904,29 @@ static void skge_link_down(struct skge_port *skge) printk(KERN_INFO PFX "%s: Link is down.\n", skge->netdev->name); } + +static void xm_link_down(struct skge_hw *hw, int port) +{ + struct net_device *dev = hw->dev[port]; + struct skge_port *skge = netdev_priv(dev); + u16 cmd, msk; + + if (hw->phy_type == SK_PHY_XMAC) { + msk = xm_read16(hw, port, XM_IMSK); + msk |= XM_IS_INP_ASS | XM_IS_LIPA_RC | XM_IS_RX_PAGE | XM_IS_AND; + xm_write16(hw, port, XM_IMSK, msk); + } + + cmd = xm_read16(hw, port, XM_MMU_CMD); + cmd &= ~(XM_MMU_ENA_RX | XM_MMU_ENA_TX); + xm_write16(hw, port, XM_MMU_CMD, cmd); + /* dummy read to ensure writing */ + (void) xm_read16(hw, port, XM_MMU_CMD); + + if (netif_carrier_ok(dev)) + skge_link_down(skge); +} + static int __xm_phy_read(struct skge_hw *hw, int port, u16 reg, u16 *val) { int i; @@ -992,7 +1035,15 @@ static const u16 phy_pause_map[] = { [FLOW_MODE_NONE] = 0, [FLOW_MODE_LOC_SEND] = PHY_AN_PAUSE_ASYM, [FLOW_MODE_SYMMETRIC] = PHY_AN_PAUSE_CAP, - [FLOW_MODE_REM_SEND] = PHY_AN_PAUSE_CAP | PHY_AN_PAUSE_ASYM, + [FLOW_MODE_SYM_OR_REM] = PHY_AN_PAUSE_CAP | PHY_AN_PAUSE_ASYM, +}; + +/* special defines for FIBER (88E1011S only) */ +static const u16 fiber_pause_map[] = { + [FLOW_MODE_NONE] = PHY_X_P_NO_PAUSE, + [FLOW_MODE_LOC_SEND] = PHY_X_P_ASYM_MD, + [FLOW_MODE_SYMMETRIC] = PHY_X_P_SYM_MD, + [FLOW_MODE_SYM_OR_REM] = PHY_X_P_BOTH_MD, }; @@ -1008,14 +1059,7 @@ static void bcom_check_link(struct skge_hw *hw, int port) status = xm_phy_read(hw, port, PHY_BCOM_STAT); if ((status & PHY_ST_LSYNC) == 0) { - u16 cmd = xm_read16(hw, port, XM_MMU_CMD); - cmd &= ~(XM_MMU_ENA_RX | XM_MMU_ENA_TX); - xm_write16(hw, port, XM_MMU_CMD, cmd); - /* dummy read to ensure writing */ - (void) xm_read16(hw, port, XM_MMU_CMD); - - if (netif_carrier_ok(dev)) - skge_link_down(skge); + xm_link_down(hw, port); return; } @@ -1048,20 +1092,19 @@ static void bcom_check_link(struct skge_hw *hw, int port) return; } - /* We are using IEEE 802.3z/D5.0 Table 37-4 */ switch (aux & PHY_B_AS_PAUSE_MSK) { case PHY_B_AS_PAUSE_MSK: - skge->flow_control = FLOW_MODE_SYMMETRIC; + skge->flow_status = FLOW_STAT_SYMMETRIC; break; case PHY_B_AS_PRR: - skge->flow_control = FLOW_MODE_REM_SEND; + skge->flow_status = FLOW_STAT_REM_SEND; break; case PHY_B_AS_PRT: - skge->flow_control = FLOW_MODE_LOC_SEND; + skge->flow_status = FLOW_STAT_LOC_SEND; break; default: - skge->flow_control = FLOW_MODE_NONE; + skge->flow_status = FLOW_STAT_NONE; } skge->speed = SPEED_1000; } @@ -1191,17 +1234,7 @@ static void xm_phy_init(struct skge_port *skge) if (skge->advertising & ADVERTISED_1000baseT_Full) ctrl |= PHY_X_AN_FD; - switch(skge->flow_control) { - case FLOW_MODE_NONE: - ctrl |= PHY_X_P_NO_PAUSE; - break; - case FLOW_MODE_LOC_SEND: - ctrl |= PHY_X_P_ASYM_MD; - break; - case FLOW_MODE_SYMMETRIC: - ctrl |= PHY_X_P_BOTH_MD; - break; - } + ctrl |= fiber_pause_map[skge->flow_control]; xm_phy_write(hw, port, PHY_XMAC_AUNE_ADV, ctrl); @@ -1235,14 +1268,7 @@ static void xm_check_link(struct net_device *dev) status = xm_phy_read(hw, port, PHY_XMAC_STAT); if ((status & PHY_ST_LSYNC) == 0) { - u16 cmd = xm_read16(hw, port, XM_MMU_CMD); - cmd &= ~(XM_MMU_ENA_RX | XM_MMU_ENA_TX); - xm_write16(hw, port, XM_MMU_CMD, cmd); - /* dummy read to ensure writing */ - (void) xm_read16(hw, port, XM_MMU_CMD); - - if (netif_carrier_ok(dev)) - skge_link_down(skge); + xm_link_down(hw, port); return; } @@ -1276,15 +1302,20 @@ static void xm_check_link(struct net_device *dev) } /* We are using IEEE 802.3z/D5.0 Table 37-4 */ - if (lpa & PHY_X_P_SYM_MD) - skge->flow_control = FLOW_MODE_SYMMETRIC; - else if ((lpa & PHY_X_RS_PAUSE) == PHY_X_P_ASYM_MD) - skge->flow_control = FLOW_MODE_REM_SEND; - else if ((lpa & PHY_X_RS_PAUSE) == PHY_X_P_BOTH_MD) - skge->flow_control = FLOW_MODE_LOC_SEND; + if ((skge->flow_control == FLOW_MODE_SYMMETRIC || + skge->flow_control == FLOW_MODE_SYM_OR_REM) && + (lpa & PHY_X_P_SYM_MD)) + skge->flow_status = FLOW_STAT_SYMMETRIC; + else if (skge->flow_control == FLOW_MODE_SYM_OR_REM && + (lpa & PHY_X_RS_PAUSE) == PHY_X_P_ASYM_MD) + /* Enable PAUSE receive, disable PAUSE transmit */ + skge->flow_status = FLOW_STAT_REM_SEND; + else if (skge->flow_control == FLOW_MODE_LOC_SEND && + (lpa & PHY_X_RS_PAUSE) == PHY_X_P_BOTH_MD) + /* Disable PAUSE receive, enable PAUSE transmit */ + skge->flow_status = FLOW_STAT_LOC_SEND; else - skge->flow_control = FLOW_MODE_NONE; - + skge->flow_status = FLOW_STAT_NONE; skge->speed = SPEED_1000; } @@ -1568,6 +1599,10 @@ static void genesis_mac_intr(struct skge_hw *hw, int port) printk(KERN_DEBUG PFX "%s: mac interrupt status 0x%x\n", skge->netdev->name, status); + if (hw->phy_type == SK_PHY_XMAC && + (status & (XM_IS_INP_ASS | XM_IS_LIPA_RC))) + xm_link_down(hw, port); + if (status & XM_IS_TXF_UR) { xm_write32(hw, port, XM_MODE, XM_MD_FTF); ++skge->net_stats.tx_fifo_errors; @@ -1582,7 +1617,7 @@ static void genesis_link_up(struct skge_port *skge) { struct skge_hw *hw = skge->hw; int port = skge->port; - u16 cmd; + u16 cmd, msk; u32 mode; cmd = xm_read16(hw, port, XM_MMU_CMD); @@ -1591,8 +1626,8 @@ static void genesis_link_up(struct skge_port *skge) * enabling pause frame reception is required for 1000BT * because the XMAC is not reset if the link is going down */ - if (skge->flow_control == FLOW_MODE_NONE || - skge->flow_control == FLOW_MODE_LOC_SEND) + if (skge->flow_status == FLOW_STAT_NONE || + skge->flow_status == FLOW_STAT_LOC_SEND) /* Disable Pause Frame Reception */ cmd |= XM_MMU_IGN_PF; else @@ -1602,8 +1637,8 @@ static void genesis_link_up(struct skge_port *skge) xm_write16(hw, port, XM_MMU_CMD, cmd); mode = xm_read32(hw, port, XM_MODE); - if (skge->flow_control == FLOW_MODE_SYMMETRIC || - skge->flow_control == FLOW_MODE_LOC_SEND) { + if (skge->flow_status== FLOW_STAT_SYMMETRIC || + skge->flow_status == FLOW_STAT_LOC_SEND) { /* * Configure Pause Frame Generation * Use internal and external Pause Frame Generation. @@ -1631,7 +1666,11 @@ static void genesis_link_up(struct skge_port *skge) } xm_write32(hw, port, XM_MODE, mode); - xm_write16(hw, port, XM_IMSK, XM_DEF_MSK); + msk = XM_DEF_MSK; + if (hw->phy_type != SK_PHY_XMAC) + msk |= XM_IS_INP_ASS; /* disable GP0 interrupt bit */ + + xm_write16(hw, port, XM_IMSK, msk); xm_read16(hw, port, XM_ISRC); /* get MMU Command Reg. */ @@ -1779,11 +1818,17 @@ static void yukon_init(struct skge_hw *hw, int port) adv |= PHY_M_AN_10_FD; if (skge->advertising & ADVERTISED_10baseT_Half) adv |= PHY_M_AN_10_HD; - } else /* special defines for FIBER (88E1011S only) */ - adv |= PHY_M_AN_1000X_AHD | PHY_M_AN_1000X_AFD; - /* Set Flow-control capabilities */ - adv |= phy_pause_map[skge->flow_control]; + /* Set Flow-control capabilities */ + adv |= phy_pause_map[skge->flow_control]; + } else { + if (skge->advertising & ADVERTISED_1000baseT_Full) + adv |= PHY_M_AN_1000X_AFD; + if (skge->advertising & ADVERTISED_1000baseT_Half) + adv |= PHY_M_AN_1000X_AHD; + + adv |= fiber_pause_map[skge->flow_control]; + } /* Restart Auto-negotiation */ ctrl |= PHY_CT_ANE | PHY_CT_RE_CFG; @@ -1917,6 +1962,11 @@ static void yukon_mac_init(struct skge_hw *hw, int port) case FLOW_MODE_LOC_SEND: /* disable Rx flow-control */ reg |= GM_GPCR_FC_RX_DIS | GM_GPCR_AU_FCT_DIS; + break; + case FLOW_MODE_SYMMETRIC: + case FLOW_MODE_SYM_OR_REM: + /* enable Tx & Rx flow-control */ + break; } gma_write16(hw, port, GM_GP_CTRL, reg); @@ -2111,13 +2161,11 @@ static void yukon_link_down(struct skge_port *skge) ctrl &= ~(GM_GPCR_RX_ENA | GM_GPCR_TX_ENA); gma_write16(hw, port, GM_GP_CTRL, ctrl); - if (skge->flow_control == FLOW_MODE_REM_SEND) { + if (skge->flow_status == FLOW_STAT_REM_SEND) { + ctrl = gm_phy_read(hw, port, PHY_MARV_AUNE_ADV); + ctrl |= PHY_M_AN_ASP; /* restore Asymmetric Pause bit */ - gm_phy_write(hw, port, PHY_MARV_AUNE_ADV, - gm_phy_read(hw, port, - PHY_MARV_AUNE_ADV) - | PHY_M_AN_ASP); - + gm_phy_write(hw, port, PHY_MARV_AUNE_ADV, ctrl); } yukon_reset(hw, port); @@ -2164,19 +2212,19 @@ static void yukon_phy_intr(struct skge_port *skge) /* We are using IEEE 802.3z/D5.0 Table 37-4 */ switch (phystat & PHY_M_PS_PAUSE_MSK) { case PHY_M_PS_PAUSE_MSK: - skge->flow_control = FLOW_MODE_SYMMETRIC; + skge->flow_status = FLOW_STAT_SYMMETRIC; break; case PHY_M_PS_RX_P_EN: - skge->flow_control = FLOW_MODE_REM_SEND; + skge->flow_status = FLOW_STAT_REM_SEND; break; case PHY_M_PS_TX_P_EN: - skge->flow_control = FLOW_MODE_LOC_SEND; + skge->flow_status = FLOW_STAT_LOC_SEND; break; default: - skge->flow_control = FLOW_MODE_NONE; + skge->flow_status = FLOW_STAT_NONE; } - if (skge->flow_control == FLOW_MODE_NONE || + if (skge->flow_status == FLOW_STAT_NONE || (skge->speed < SPEED_1000 && skge->duplex == DUPLEX_HALF)) skge_write8(hw, SK_REG(port, GMAC_CTRL), GMC_PAUSE_OFF); else @@ -3399,7 +3447,7 @@ static struct net_device *skge_devinit(struct skge_hw *hw, int port, /* Auto speed and flow control */ skge->autoneg = AUTONEG_ENABLE; - skge->flow_control = FLOW_MODE_SYMMETRIC; + skge->flow_control = FLOW_MODE_SYM_OR_REM; skge->duplex = -1; skge->speed = -1; skge->advertising = skge_supported_modes(hw); diff --git a/drivers/net/skge.h b/drivers/net/skge.h index d0b47d46cf9..537c0aaa1db 100644 --- a/drivers/net/skge.h +++ b/drivers/net/skge.h @@ -2195,7 +2195,8 @@ enum { XM_IS_RX_COMP = 1<<0, /* Bit 0: Frame Rx Complete */ }; -#define XM_DEF_MSK (~(XM_IS_RXC_OV | XM_IS_TXC_OV | XM_IS_RXF_OV | XM_IS_TXF_UR)) +#define XM_DEF_MSK (~(XM_IS_INP_ASS | XM_IS_LIPA_RC | \ + XM_IS_RXF_OV | XM_IS_TXF_UR)) /* XM_HW_CFG 16 bit r/w Hardware Config Register */ @@ -2426,13 +2427,24 @@ struct skge_hw { struct mutex phy_mutex; }; -enum { - FLOW_MODE_NONE = 0, /* No Flow-Control */ - FLOW_MODE_LOC_SEND = 1, /* Local station sends PAUSE */ - FLOW_MODE_REM_SEND = 2, /* Symmetric or just remote */ +enum pause_control { + FLOW_MODE_NONE = 1, /* No Flow-Control */ + FLOW_MODE_LOC_SEND = 2, /* Local station sends PAUSE */ FLOW_MODE_SYMMETRIC = 3, /* Both stations may send PAUSE */ + FLOW_MODE_SYM_OR_REM = 4, /* Both stations may send PAUSE or + * just the remote station may send PAUSE + */ +}; + +enum pause_status { + FLOW_STAT_INDETERMINATED=0, /* indeterminated */ + FLOW_STAT_NONE, /* No Flow Control */ + FLOW_STAT_REM_SEND, /* Remote Station sends PAUSE */ + FLOW_STAT_LOC_SEND, /* Local station sends PAUSE */ + FLOW_STAT_SYMMETRIC, /* Both station may send PAUSE */ }; + struct skge_port { u32 msg_enable; struct skge_hw *hw; @@ -2445,9 +2457,10 @@ struct skge_port { struct net_device_stats net_stats; struct work_struct link_thread; + enum pause_control flow_control; + enum pause_status flow_status; u8 rx_csum; u8 blink_on; - u8 flow_control; u8 wol; u8 autoneg; /* AUTONEG_ENABLE, AUTONEG_DISABLE */ u8 duplex; /* DUPLEX_HALF, DUPLEX_FULL */ diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index 459c845d664..c10e7f5faa5 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -683,7 +683,7 @@ static void sky2_mac_init(struct sky2_hw *hw, unsigned port) sky2_write16(hw, SK_REG(port, TX_GMF_CTRL_T), GMF_OPER_ON); if (hw->chip_id == CHIP_ID_YUKON_EC_U) { - sky2_write8(hw, SK_REG(port, RX_GMF_LP_THR), 768/8); + sky2_write8(hw, SK_REG(port, RX_GMF_LP_THR), 512/8); sky2_write8(hw, SK_REG(port, RX_GMF_UP_THR), 1024/8); if (hw->dev[port]->mtu > ETH_DATA_LEN) { /* set Tx GMAC FIFO Almost Empty Threshold */ @@ -1907,7 +1907,7 @@ static struct sk_buff *receive_copy(struct sky2_port *sky2, pci_dma_sync_single_for_device(sky2->hw->pdev, re->data_addr, length, PCI_DMA_FROMDEVICE); re->skb->ip_summed = CHECKSUM_NONE; - __skb_put(skb, length); + skb_put(skb, length); } return skb; } @@ -1970,7 +1970,7 @@ static struct sk_buff *receive_new(struct sky2_port *sky2, if (skb_shinfo(skb)->nr_frags) skb_put_frags(skb, hdr_space, length); else - skb_put(skb, hdr_space); + skb_put(skb, length); return skb; } @@ -2220,8 +2220,7 @@ static void sky2_hw_intr(struct sky2_hw *hw) /* PCI-Express uncorrectable Error occurred */ u32 pex_err; - pex_err = sky2_pci_read32(hw, - hw->err_cap + PCI_ERR_UNCOR_STATUS); + pex_err = sky2_pci_read32(hw, PEX_UNC_ERR_STAT); if (net_ratelimit()) printk(KERN_ERR PFX "%s: pci express error (0x%x)\n", @@ -2229,20 +2228,15 @@ static void sky2_hw_intr(struct sky2_hw *hw) /* clear the interrupt */ sky2_write32(hw, B2_TST_CTRL1, TST_CFG_WRITE_ON); - sky2_pci_write32(hw, - hw->err_cap + PCI_ERR_UNCOR_STATUS, - 0xffffffffUL); + sky2_pci_write32(hw, PEX_UNC_ERR_STAT, + 0xffffffffUL); sky2_write32(hw, B2_TST_CTRL1, TST_CFG_WRITE_OFF); - - /* In case of fatal error mask off to keep from getting stuck */ - if (pex_err & (PCI_ERR_UNC_POISON_TLP | PCI_ERR_UNC_FCP - | PCI_ERR_UNC_DLP)) { + if (pex_err & PEX_FATAL_ERRORS) { u32 hwmsk = sky2_read32(hw, B0_HWE_IMSK); hwmsk &= ~Y2_IS_PCI_EXP; sky2_write32(hw, B0_HWE_IMSK, hwmsk); } - } if (status & Y2_HWE_L1_MASK) @@ -2423,7 +2417,6 @@ static int sky2_reset(struct sky2_hw *hw) u16 status; u8 t8; int i; - u32 msk; sky2_write8(hw, B0_CTST, CS_RST_CLR); @@ -2464,13 +2457,9 @@ static int sky2_reset(struct sky2_hw *hw) sky2_write8(hw, B0_CTST, CS_MRST_CLR); /* clear any PEX errors */ - if (pci_find_capability(hw->pdev, PCI_CAP_ID_EXP)) { - hw->err_cap = pci_find_ext_capability(hw->pdev, PCI_EXT_CAP_ID_ERR); - if (hw->err_cap) - sky2_pci_write32(hw, - hw->err_cap + PCI_ERR_UNCOR_STATUS, - 0xffffffffUL); - } + if (pci_find_capability(hw->pdev, PCI_CAP_ID_EXP)) + sky2_pci_write32(hw, PEX_UNC_ERR_STAT, 0xffffffffUL); + hw->pmd_type = sky2_read8(hw, B2_PMD_TYP); hw->ports = 1; @@ -2527,10 +2516,7 @@ static int sky2_reset(struct sky2_hw *hw) sky2_write8(hw, RAM_BUFFER(i, B3_RI_RTO_XS2), SK_RI_TO_53); } - msk = Y2_HWE_ALL_MASK; - if (!hw->err_cap) - msk &= ~Y2_IS_PCI_EXP; - sky2_write32(hw, B0_HWE_IMSK, msk); + sky2_write32(hw, B0_HWE_IMSK, Y2_HWE_ALL_MASK); for (i = 0; i < hw->ports; i++) sky2_gmac_reset(hw, i); diff --git a/drivers/net/sky2.h b/drivers/net/sky2.h index f66109a96d9..43d2accf60e 100644 --- a/drivers/net/sky2.h +++ b/drivers/net/sky2.h @@ -6,15 +6,24 @@ #define ETH_JUMBO_MTU 9000 /* Maximum MTU supported */ -/* PCI device specific config registers */ +/* PCI config registers */ enum { PCI_DEV_REG1 = 0x40, PCI_DEV_REG2 = 0x44, + PCI_DEV_STATUS = 0x7c, PCI_DEV_REG3 = 0x80, PCI_DEV_REG4 = 0x84, PCI_DEV_REG5 = 0x88, }; +enum { + PEX_DEV_CAP = 0xe4, + PEX_DEV_CTRL = 0xe8, + PEX_DEV_STA = 0xea, + PEX_LNK_STAT = 0xf2, + PEX_UNC_ERR_STAT= 0x104, +}; + /* Yukon-2 */ enum pci_dev_reg_1 { PCI_Y2_PIG_ENA = 1<<31, /* Enable Plug-in-Go (YUKON-2) */ @@ -63,6 +72,39 @@ enum pci_dev_reg_4 { PCI_STATUS_REC_MASTER_ABORT | \ PCI_STATUS_REC_TARGET_ABORT | \ PCI_STATUS_PARITY) + +enum pex_dev_ctrl { + PEX_DC_MAX_RRS_MSK = 7<<12, /* Bit 14..12: Max. Read Request Size */ + PEX_DC_EN_NO_SNOOP = 1<<11,/* Enable No Snoop */ + PEX_DC_EN_AUX_POW = 1<<10,/* Enable AUX Power */ + PEX_DC_EN_PHANTOM = 1<<9, /* Enable Phantom Functions */ + PEX_DC_EN_EXT_TAG = 1<<8, /* Enable Extended Tag Field */ + PEX_DC_MAX_PLS_MSK = 7<<5, /* Bit 7.. 5: Max. Payload Size Mask */ + PEX_DC_EN_REL_ORD = 1<<4, /* Enable Relaxed Ordering */ + PEX_DC_EN_UNS_RQ_RP = 1<<3, /* Enable Unsupported Request Reporting */ + PEX_DC_EN_FAT_ER_RP = 1<<2, /* Enable Fatal Error Reporting */ + PEX_DC_EN_NFA_ER_RP = 1<<1, /* Enable Non-Fatal Error Reporting */ + PEX_DC_EN_COR_ER_RP = 1<<0, /* Enable Correctable Error Reporting */ +}; +#define PEX_DC_MAX_RD_RQ_SIZE(x) (((x)<<12) & PEX_DC_MAX_RRS_MSK) + +/* PEX_UNC_ERR_STAT PEX Uncorrectable Errors Status Register (Yukon-2) */ +enum pex_err { + PEX_UNSUP_REQ = 1<<20, /* Unsupported Request Error */ + + PEX_MALFOR_TLP = 1<<18, /* Malformed TLP */ + + PEX_UNEXP_COMP = 1<<16, /* Unexpected Completion */ + + PEX_COMP_TO = 1<<14, /* Completion Timeout */ + PEX_FLOW_CTRL_P = 1<<13, /* Flow Control Protocol Error */ + PEX_POIS_TLP = 1<<12, /* Poisoned TLP */ + + PEX_DATA_LINK_P = 1<<4, /* Data Link Protocol Error */ + PEX_FATAL_ERRORS= (PEX_MALFOR_TLP | PEX_FLOW_CTRL_P | PEX_DATA_LINK_P), +}; + + enum csr_regs { B0_RAP = 0x0000, B0_CTST = 0x0004, @@ -1836,7 +1878,6 @@ struct sky2_hw { struct net_device *dev[2]; int pm_cap; - int err_cap; u8 chip_id; u8 chip_rev; u8 pmd_type; diff --git a/drivers/net/smc91x.h b/drivers/net/smc91x.h index 636dbfcdf8c..0c9f1e7dab2 100644 --- a/drivers/net/smc91x.h +++ b/drivers/net/smc91x.h @@ -398,6 +398,24 @@ static inline void LPD7_SMC_outsw (unsigned char* a, int r, #define SMC_IRQ_FLAGS (0) +#elif defined(CONFIG_ARCH_VERSATILE) + +#define SMC_CAN_USE_8BIT 1 +#define SMC_CAN_USE_16BIT 1 +#define SMC_CAN_USE_32BIT 1 +#define SMC_NOWAIT 1 + +#define SMC_inb(a, r) readb((a) + (r)) +#define SMC_inw(a, r) readw((a) + (r)) +#define SMC_inl(a, r) readl((a) + (r)) +#define SMC_outb(v, a, r) writeb(v, (a) + (r)) +#define SMC_outw(v, a, r) writew(v, (a) + (r)) +#define SMC_outl(v, a, r) writel(v, (a) + (r)) +#define SMC_insl(a, r, p, l) readsl((a) + (r), p, l) +#define SMC_outsl(a, r, p, l) writesl((a) + (r), p, l) + +#define SMC_IRQ_FLAGS (0) + #else #define SMC_CAN_USE_8BIT 1 diff --git a/drivers/net/spider_net.c b/drivers/net/spider_net.c index 46a009085f7..418138dd6c6 100644 --- a/drivers/net/spider_net.c +++ b/drivers/net/spider_net.c @@ -55,12 +55,13 @@ MODULE_AUTHOR("Utz Bacher <utz.bacher@de.ibm.com> and Jens Osterkamp " \ "<Jens.Osterkamp@de.ibm.com>"); MODULE_DESCRIPTION("Spider Southbridge Gigabit Ethernet driver"); MODULE_LICENSE("GPL"); +MODULE_VERSION(VERSION); static int rx_descriptors = SPIDER_NET_RX_DESCRIPTORS_DEFAULT; static int tx_descriptors = SPIDER_NET_TX_DESCRIPTORS_DEFAULT; -module_param(rx_descriptors, int, 0644); -module_param(tx_descriptors, int, 0644); +module_param(rx_descriptors, int, 0444); +module_param(tx_descriptors, int, 0444); MODULE_PARM_DESC(rx_descriptors, "number of descriptors used " \ "in rx chains"); @@ -300,7 +301,7 @@ static int spider_net_init_chain(struct spider_net_card *card, struct spider_net_descr_chain *chain, struct spider_net_descr *start_descr, - int direction, int no) + int no) { int i; struct spider_net_descr *descr; @@ -315,7 +316,7 @@ spider_net_init_chain(struct spider_net_card *card, buf = pci_map_single(card->pdev, descr, SPIDER_NET_DESCR_SIZE, - direction); + PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(buf)) goto iommu_error; @@ -329,11 +330,6 @@ spider_net_init_chain(struct spider_net_card *card, (descr-1)->next = start_descr; start_descr->prev = descr-1; - descr = start_descr; - if (direction == PCI_DMA_FROMDEVICE) - for (i=0; i < no; i++, descr++) - descr->next_descr_addr = descr->next->bus_addr; - spin_lock_init(&chain->lock); chain->head = start_descr; chain->tail = start_descr; @@ -346,7 +342,7 @@ iommu_error: if (descr->bus_addr) pci_unmap_single(card->pdev, descr->bus_addr, SPIDER_NET_DESCR_SIZE, - direction); + PCI_DMA_BIDIRECTIONAL); return -ENOMEM; } @@ -362,15 +358,15 @@ spider_net_free_rx_chain_contents(struct spider_net_card *card) struct spider_net_descr *descr; descr = card->rx_chain.head; - while (descr->next != card->rx_chain.head) { + do { if (descr->skb) { dev_kfree_skb(descr->skb); pci_unmap_single(card->pdev, descr->buf_addr, SPIDER_NET_MAX_FRAME, - PCI_DMA_FROMDEVICE); + PCI_DMA_BIDIRECTIONAL); } descr = descr->next; - } + } while (descr != card->rx_chain.head); } /** @@ -645,26 +641,41 @@ static int spider_net_prepare_tx_descr(struct spider_net_card *card, struct sk_buff *skb) { - struct spider_net_descr *descr = card->tx_chain.head; + struct spider_net_descr *descr; dma_addr_t buf; + unsigned long flags; + int length; - buf = pci_map_single(card->pdev, skb->data, skb->len, PCI_DMA_TODEVICE); + length = skb->len; + if (length < ETH_ZLEN) { + if (skb_pad(skb, ETH_ZLEN-length)) + return 0; + length = ETH_ZLEN; + } + + buf = pci_map_single(card->pdev, skb->data, length, PCI_DMA_TODEVICE); if (pci_dma_mapping_error(buf)) { if (netif_msg_tx_err(card) && net_ratelimit()) pr_err("could not iommu-map packet (%p, %i). " - "Dropping packet\n", skb->data, skb->len); + "Dropping packet\n", skb->data, length); card->spider_stats.tx_iommu_map_error++; return -ENOMEM; } + spin_lock_irqsave(&card->tx_chain.lock, flags); + descr = card->tx_chain.head; + card->tx_chain.head = descr->next; + descr->buf_addr = buf; - descr->buf_size = skb->len; + descr->buf_size = length; descr->next_descr_addr = 0; descr->skb = skb; descr->data_status = 0; descr->dmac_cmd_status = SPIDER_NET_DESCR_CARDOWNED | SPIDER_NET_DMAC_NOCS; + spin_unlock_irqrestore(&card->tx_chain.lock, flags); + if (skb->protocol == htons(ETH_P_IP)) switch (skb->nh.iph->protocol) { case IPPROTO_TCP: @@ -675,32 +686,51 @@ spider_net_prepare_tx_descr(struct spider_net_card *card, break; } + /* Chain the bus address, so that the DMA engine finds this descr. */ descr->prev->next_descr_addr = descr->bus_addr; + card->netdev->trans_start = jiffies; /* set netdev watchdog timer */ return 0; } -/** - * spider_net_release_tx_descr - processes a used tx descriptor - * @card: card structure - * @descr: descriptor to release - * - * releases a used tx descriptor (unmapping, freeing of skb) - */ -static inline void -spider_net_release_tx_descr(struct spider_net_card *card) +static int +spider_net_set_low_watermark(struct spider_net_card *card) { + unsigned long flags; + int status; + int cnt=0; + int i; struct spider_net_descr *descr = card->tx_chain.tail; - struct sk_buff *skb; - card->tx_chain.tail = card->tx_chain.tail->next; - descr->dmac_cmd_status |= SPIDER_NET_DESCR_NOT_IN_USE; + /* Measure the length of the queue. Measurement does not + * need to be precise -- does not need a lock. */ + while (descr != card->tx_chain.head) { + status = descr->dmac_cmd_status & SPIDER_NET_DESCR_NOT_IN_USE; + if (status == SPIDER_NET_DESCR_NOT_IN_USE) + break; + descr = descr->next; + cnt++; + } - /* unmap the skb */ - skb = descr->skb; - pci_unmap_single(card->pdev, descr->buf_addr, skb->len, - PCI_DMA_TODEVICE); - dev_kfree_skb_any(skb); + /* If TX queue is short, don't even bother with interrupts */ + if (cnt < card->num_tx_desc/4) + return cnt; + + /* Set low-watermark 3/4th's of the way into the queue. */ + descr = card->tx_chain.tail; + cnt = (cnt*3)/4; + for (i=0;i<cnt; i++) + descr = descr->next; + + /* Set the new watermark, clear the old watermark */ + spin_lock_irqsave(&card->tx_chain.lock, flags); + descr->dmac_cmd_status |= SPIDER_NET_DESCR_TXDESFLG; + if (card->low_watermark && card->low_watermark != descr) + card->low_watermark->dmac_cmd_status = + card->low_watermark->dmac_cmd_status & ~SPIDER_NET_DESCR_TXDESFLG; + card->low_watermark = descr; + spin_unlock_irqrestore(&card->tx_chain.lock, flags); + return cnt; } /** @@ -719,21 +749,29 @@ static int spider_net_release_tx_chain(struct spider_net_card *card, int brutal) { struct spider_net_descr_chain *chain = &card->tx_chain; + struct spider_net_descr *descr; + struct sk_buff *skb; + u32 buf_addr; + unsigned long flags; int status; - spider_net_read_reg(card, SPIDER_NET_GDTDMACCNTR); - while (chain->tail != chain->head) { - status = spider_net_get_descr_status(chain->tail); + spin_lock_irqsave(&chain->lock, flags); + descr = chain->tail; + + status = spider_net_get_descr_status(descr); switch (status) { case SPIDER_NET_DESCR_COMPLETE: card->netdev_stats.tx_packets++; - card->netdev_stats.tx_bytes += chain->tail->skb->len; + card->netdev_stats.tx_bytes += descr->skb->len; break; case SPIDER_NET_DESCR_CARDOWNED: - if (!brutal) + if (!brutal) { + spin_unlock_irqrestore(&chain->lock, flags); return 1; + } + /* fallthrough, if we release the descriptors * brutally (then we don't care about * SPIDER_NET_DESCR_CARDOWNED) */ @@ -750,11 +788,25 @@ spider_net_release_tx_chain(struct spider_net_card *card, int brutal) default: card->netdev_stats.tx_dropped++; - return 1; + if (!brutal) { + spin_unlock_irqrestore(&chain->lock, flags); + return 1; + } } - spider_net_release_tx_descr(card); - } + chain->tail = descr->next; + descr->dmac_cmd_status |= SPIDER_NET_DESCR_NOT_IN_USE; + skb = descr->skb; + buf_addr = descr->buf_addr; + spin_unlock_irqrestore(&chain->lock, flags); + + /* unmap the skb */ + if (skb) { + int len = skb->len < ETH_ZLEN ? ETH_ZLEN : skb->len; + pci_unmap_single(card->pdev, buf_addr, len, PCI_DMA_TODEVICE); + dev_kfree_skb(skb); + } + } return 0; } @@ -763,8 +815,12 @@ spider_net_release_tx_chain(struct spider_net_card *card, int brutal) * @card: card structure * @descr: descriptor address to enable TX processing at * - * spider_net_kick_tx_dma writes the current tx chain head as start address - * of the tx descriptor chain and enables the transmission DMA engine + * This routine will start the transmit DMA running if + * it is not already running. This routine ned only be + * called when queueing a new packet to an empty tx queue. + * Writes the current tx chain head as start address + * of the tx descriptor chain and enables the transmission + * DMA engine. */ static inline void spider_net_kick_tx_dma(struct spider_net_card *card) @@ -804,65 +860,43 @@ out: static int spider_net_xmit(struct sk_buff *skb, struct net_device *netdev) { + int cnt; struct spider_net_card *card = netdev_priv(netdev); struct spider_net_descr_chain *chain = &card->tx_chain; - struct spider_net_descr *descr = chain->head; - unsigned long flags; - int result; - - spin_lock_irqsave(&chain->lock, flags); spider_net_release_tx_chain(card, 0); - if (chain->head->next == chain->tail->prev) { - card->netdev_stats.tx_dropped++; - result = NETDEV_TX_LOCKED; - goto out; - } + if ((chain->head->next == chain->tail->prev) || + (spider_net_prepare_tx_descr(card, skb) != 0)) { - if (spider_net_get_descr_status(descr) != SPIDER_NET_DESCR_NOT_IN_USE) { card->netdev_stats.tx_dropped++; - result = NETDEV_TX_LOCKED; - goto out; + netif_stop_queue(netdev); + return NETDEV_TX_BUSY; } - if (spider_net_prepare_tx_descr(card, skb) != 0) { - card->netdev_stats.tx_dropped++; - result = NETDEV_TX_BUSY; - goto out; - } - - result = NETDEV_TX_OK; - - spider_net_kick_tx_dma(card); - card->tx_chain.head = card->tx_chain.head->next; - -out: - spin_unlock_irqrestore(&chain->lock, flags); - netif_wake_queue(netdev); - return result; + cnt = spider_net_set_low_watermark(card); + if (cnt < 5) + spider_net_kick_tx_dma(card); + return NETDEV_TX_OK; } /** * spider_net_cleanup_tx_ring - cleans up the TX ring * @card: card structure * - * spider_net_cleanup_tx_ring is called by the tx_timer (as we don't use - * interrupts to cleanup our TX ring) and returns sent packets to the stack - * by freeing them + * spider_net_cleanup_tx_ring is called by either the tx_timer + * or from the NAPI polling routine. + * This routine releases resources associted with transmitted + * packets, including updating the queue tail pointer. */ static void spider_net_cleanup_tx_ring(struct spider_net_card *card) { - unsigned long flags; - - spin_lock_irqsave(&card->tx_chain.lock, flags); - if ((spider_net_release_tx_chain(card, 0) != 0) && - (card->netdev->flags & IFF_UP)) + (card->netdev->flags & IFF_UP)) { spider_net_kick_tx_dma(card); - - spin_unlock_irqrestore(&card->tx_chain.lock, flags); + netif_wake_queue(card->netdev); + } } /** @@ -1053,6 +1087,7 @@ spider_net_poll(struct net_device *netdev, int *budget) int packets_to_do, packets_done = 0; int no_more_packets = 0; + spider_net_cleanup_tx_ring(card); packets_to_do = min(*budget, netdev->quota); while (packets_to_do) { @@ -1243,12 +1278,15 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg) case SPIDER_NET_PHYINT: case SPIDER_NET_GMAC2INT: case SPIDER_NET_GMAC1INT: - case SPIDER_NET_GIPSINT: case SPIDER_NET_GFIFOINT: case SPIDER_NET_DMACINT: case SPIDER_NET_GSYSINT: break; */ + case SPIDER_NET_GIPSINT: + show_error = 0; + break; + case SPIDER_NET_GPWOPCMPINT: /* PHY write operation completed */ show_error = 0; @@ -1307,9 +1345,10 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg) case SPIDER_NET_GDTDCEINT: /* chain end. If a descriptor should be sent, kick off * tx dma - if (card->tx_chain.tail == card->tx_chain.head) + if (card->tx_chain.tail != card->tx_chain.head) spider_net_kick_tx_dma(card); - show_error = 0; */ + */ + show_error = 0; break; /* case SPIDER_NET_G1TMCNTINT: not used. print a message */ @@ -1354,7 +1393,7 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg) if (netif_msg_intr(card)) pr_err("got descriptor chain end interrupt, " "restarting DMAC %c.\n", - 'D'+i-SPIDER_NET_GDDDCEINT); + 'D'-(i-SPIDER_NET_GDDDCEINT)/3); spider_net_refill_rx_chain(card); spider_net_enable_rxdmac(card); show_error = 0; @@ -1423,8 +1462,9 @@ spider_net_handle_error_irq(struct spider_net_card *card, u32 status_reg) } if ((show_error) && (netif_msg_intr(card))) - pr_err("Got error interrupt, GHIINT0STS = 0x%08x, " + pr_err("Got error interrupt on %s, GHIINT0STS = 0x%08x, " "GHIINT1STS = 0x%08x, GHIINT2STS = 0x%08x\n", + card->netdev->name, status_reg, error_reg1, error_reg2); /* clear interrupt sources */ @@ -1460,6 +1500,8 @@ spider_net_interrupt(int irq, void *ptr) spider_net_rx_irq_off(card); netif_rx_schedule(netdev); } + if (status_reg & SPIDER_NET_TXINT) + netif_rx_schedule(netdev); if (status_reg & SPIDER_NET_ERRINT ) spider_net_handle_error_irq(card, status_reg); @@ -1599,7 +1641,7 @@ spider_net_enable_card(struct spider_net_card *card) SPIDER_NET_INT2_MASK_VALUE); spider_net_write_reg(card, SPIDER_NET_GDTDMACCNTR, - SPIDER_NET_GDTDCEIDIS); + SPIDER_NET_GDTBSTA | SPIDER_NET_GDTDCEIDIS); } /** @@ -1615,17 +1657,26 @@ int spider_net_open(struct net_device *netdev) { struct spider_net_card *card = netdev_priv(netdev); - int result; + struct spider_net_descr *descr; + int i, result; result = -ENOMEM; if (spider_net_init_chain(card, &card->tx_chain, card->descr, - PCI_DMA_TODEVICE, card->tx_desc)) + card->num_tx_desc)) goto alloc_tx_failed; + + card->low_watermark = NULL; + + /* rx_chain is after tx_chain, so offset is descr + tx_count */ if (spider_net_init_chain(card, &card->rx_chain, - card->descr + card->rx_desc, - PCI_DMA_FROMDEVICE, card->rx_desc)) + card->descr + card->num_tx_desc, + card->num_rx_desc)) goto alloc_rx_failed; + descr = card->rx_chain.head; + for (i=0; i < card->num_rx_desc; i++, descr++) + descr->next_descr_addr = descr->next->bus_addr; + /* allocate rx skbs */ if (spider_net_alloc_rx_skbs(card)) goto alloc_skbs_failed; @@ -1878,10 +1929,7 @@ spider_net_stop(struct net_device *netdev) spider_net_disable_rxdmac(card); /* release chains */ - if (spin_trylock(&card->tx_chain.lock)) { - spider_net_release_tx_chain(card, 1); - spin_unlock(&card->tx_chain.lock); - } + spider_net_release_tx_chain(card, 1); spider_net_free_chain(card, &card->tx_chain); spider_net_free_chain(card, &card->rx_chain); @@ -2012,8 +2060,8 @@ spider_net_setup_netdev(struct spider_net_card *card) card->options.rx_csum = SPIDER_NET_RX_CSUM_DEFAULT; - card->tx_desc = tx_descriptors; - card->rx_desc = rx_descriptors; + card->num_tx_desc = tx_descriptors; + card->num_rx_desc = rx_descriptors; spider_net_setup_netdev_ops(netdev); @@ -2252,6 +2300,8 @@ static struct pci_driver spider_net_driver = { */ static int __init spider_net_init(void) { + printk(KERN_INFO "Spidernet version %s.\n", VERSION); + if (rx_descriptors < SPIDER_NET_RX_DESCRIPTORS_MIN) { rx_descriptors = SPIDER_NET_RX_DESCRIPTORS_MIN; pr_info("adjusting rx descriptors to %i.\n", rx_descriptors); diff --git a/drivers/net/spider_net.h b/drivers/net/spider_net.h index a59deda2f95..b3b46119b42 100644 --- a/drivers/net/spider_net.h +++ b/drivers/net/spider_net.h @@ -24,6 +24,8 @@ #ifndef _SPIDER_NET_H #define _SPIDER_NET_H +#define VERSION "1.1 A" + #include "sungem_phy.h" extern int spider_net_stop(struct net_device *netdev); @@ -47,7 +49,7 @@ extern char spider_net_driver_name[]; #define SPIDER_NET_TX_DESCRIPTORS_MIN 16 #define SPIDER_NET_TX_DESCRIPTORS_MAX 512 -#define SPIDER_NET_TX_TIMER 20 +#define SPIDER_NET_TX_TIMER (HZ/5) #define SPIDER_NET_RX_CSUM_DEFAULT 1 @@ -189,7 +191,9 @@ extern char spider_net_driver_name[]; #define SPIDER_NET_MACMODE_VALUE 0x00000001 #define SPIDER_NET_BURSTLMT_VALUE 0x00000200 /* about 16 us */ -/* 1(0) enable r/tx dma +/* DMAC control register GDMACCNTR + * + * 1(0) enable r/tx dma * 0000000 fixed to 0 * * 000000 fixed to 0 @@ -198,6 +202,7 @@ extern char spider_net_driver_name[]; * * 000000 fixed to 0 * 00 burst alignment: 128 bytes + * 11 burst alignment: 1024 bytes * * 00000 fixed to 0 * 0 descr writeback size 32 bytes @@ -208,10 +213,13 @@ extern char spider_net_driver_name[]; #define SPIDER_NET_DMA_RX_VALUE 0x80000000 #define SPIDER_NET_DMA_RX_FEND_VALUE 0x00030003 /* to set TX_DMA_EN */ -#define SPIDER_NET_TX_DMA_EN 0x80000000 -#define SPIDER_NET_GDTDCEIDIS 0x00000002 -#define SPIDER_NET_DMA_TX_VALUE SPIDER_NET_TX_DMA_EN | \ - SPIDER_NET_GDTDCEIDIS +#define SPIDER_NET_TX_DMA_EN 0x80000000 +#define SPIDER_NET_GDTBSTA 0x00000300 +#define SPIDER_NET_GDTDCEIDIS 0x00000002 +#define SPIDER_NET_DMA_TX_VALUE SPIDER_NET_TX_DMA_EN | \ + SPIDER_NET_GDTBSTA | \ + SPIDER_NET_GDTDCEIDIS + #define SPIDER_NET_DMA_TX_FEND_VALUE 0x00030003 /* SPIDER_NET_UA_DESCR_VALUE is OR'ed with the unicast address */ @@ -320,13 +328,10 @@ enum spider_net_int2_status { SPIDER_NET_GRISPDNGINT }; -#define SPIDER_NET_TXINT ( (1 << SPIDER_NET_GTTEDINT) | \ - (1 << SPIDER_NET_GDTDCEINT) | \ - (1 << SPIDER_NET_GDTFDCINT) ) +#define SPIDER_NET_TXINT ( (1 << SPIDER_NET_GDTFDCINT) ) -/* we rely on flagged descriptor interrupts*/ -#define SPIDER_NET_RXINT ( (1 << SPIDER_NET_GDAFDCINT) | \ - (1 << SPIDER_NET_GRMFLLINT) ) +/* We rely on flagged descriptor interrupts */ +#define SPIDER_NET_RXINT ( (1 << SPIDER_NET_GDAFDCINT) ) #define SPIDER_NET_ERRINT ( 0xffffffff & \ (~SPIDER_NET_TXINT) & \ @@ -349,6 +354,7 @@ enum spider_net_int2_status { #define SPIDER_NET_DESCR_FORCE_END 0x50000000 /* used in rx and tx */ #define SPIDER_NET_DESCR_CARDOWNED 0xA0000000 /* used in rx and tx */ #define SPIDER_NET_DESCR_NOT_IN_USE 0xF0000000 +#define SPIDER_NET_DESCR_TXDESFLG 0x00800000 struct spider_net_descr { /* as defined by the hardware */ @@ -433,6 +439,7 @@ struct spider_net_card { struct spider_net_descr_chain tx_chain; struct spider_net_descr_chain rx_chain; + struct spider_net_descr *low_watermark; struct net_device_stats netdev_stats; @@ -448,8 +455,8 @@ struct spider_net_card { /* for ethtool */ int msg_enable; - int rx_desc; - int tx_desc; + int num_rx_desc; + int num_tx_desc; struct spider_net_extra_stats spider_stats; struct spider_net_descr descr[0]; diff --git a/drivers/net/spider_net_ethtool.c b/drivers/net/spider_net_ethtool.c index 589e43658de..91b99510291 100644 --- a/drivers/net/spider_net_ethtool.c +++ b/drivers/net/spider_net_ethtool.c @@ -76,7 +76,7 @@ spider_net_ethtool_get_drvinfo(struct net_device *netdev, /* clear and fill out info */ memset(drvinfo, 0, sizeof(struct ethtool_drvinfo)); strncpy(drvinfo->driver, spider_net_driver_name, 32); - strncpy(drvinfo->version, "0.1", 32); + strncpy(drvinfo->version, VERSION, 32); strcpy(drvinfo->fw_version, "no information"); strncpy(drvinfo->bus_info, pci_name(card->pdev), 32); } @@ -158,9 +158,9 @@ spider_net_ethtool_get_ringparam(struct net_device *netdev, struct spider_net_card *card = netdev->priv; ering->tx_max_pending = SPIDER_NET_TX_DESCRIPTORS_MAX; - ering->tx_pending = card->tx_desc; + ering->tx_pending = card->num_tx_desc; ering->rx_max_pending = SPIDER_NET_RX_DESCRIPTORS_MAX; - ering->rx_pending = card->rx_desc; + ering->rx_pending = card->num_rx_desc; } static int spider_net_get_stats_count(struct net_device *netdev) diff --git a/drivers/net/sun3_82586.c b/drivers/net/sun3_82586.c index d1d1885b029..a3220a96524 100644 --- a/drivers/net/sun3_82586.c +++ b/drivers/net/sun3_82586.c @@ -330,7 +330,7 @@ out2: out1: free_netdev(dev); out: - iounmap((void *)ioaddr); + iounmap((void __iomem *)ioaddr); return ERR_PTR(err); } diff --git a/drivers/net/sun3lance.c b/drivers/net/sun3lance.c index 91c76544e4d..b865db363ba 100644 --- a/drivers/net/sun3lance.c +++ b/drivers/net/sun3lance.c @@ -286,7 +286,7 @@ struct net_device * __init sun3lance_probe(int unit) out1: #ifdef CONFIG_SUN3 - iounmap((void *)dev->base_addr); + iounmap((void __iomem *)dev->base_addr); #endif out: free_netdev(dev); @@ -326,7 +326,7 @@ static int __init lance_probe( struct net_device *dev) ioaddr_probe[1] = tmp2; #ifdef CONFIG_SUN3 - iounmap((void *)ioaddr); + iounmap((void __iomem *)ioaddr); #endif return 0; } @@ -956,7 +956,7 @@ void cleanup_module(void) { unregister_netdev(sun3lance_dev); #ifdef CONFIG_SUN3 - iounmap((void *)sun3lance_dev->base_addr); + iounmap((void __iomem *)sun3lance_dev->base_addr); #endif free_netdev(sun3lance_dev); } diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c index 2cfd9634895..f6b3a94e97b 100644 --- a/drivers/net/tulip/de2104x.c +++ b/drivers/net/tulip/de2104x.c @@ -1730,7 +1730,7 @@ static void __init de21040_get_media_info(struct de_private *de) } /* Note: this routine returns extra data bits for size detection. */ -static unsigned __init tulip_read_eeprom(void __iomem *regs, int location, int addr_len) +static unsigned __devinit tulip_read_eeprom(void __iomem *regs, int location, int addr_len) { int i; unsigned retval = 0; @@ -1926,7 +1926,7 @@ bad_srom: goto fill_defaults; } -static int __init de_init_one (struct pci_dev *pdev, +static int __devinit de_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *dev; @@ -2082,7 +2082,7 @@ err_out_free: return rc; } -static void __exit de_remove_one (struct pci_dev *pdev) +static void __devexit de_remove_one (struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); struct de_private *de = dev->priv; @@ -2164,7 +2164,7 @@ static struct pci_driver de_driver = { .name = DRV_NAME, .id_table = de_pci_tbl, .probe = de_init_one, - .remove = __exit_p(de_remove_one), + .remove = __devexit_p(de_remove_one), #ifdef CONFIG_PM .suspend = de_suspend, .resume = de_resume, diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 30294127a0a..ecc50db8585 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -55,7 +55,7 @@ config PCI_DEBUG config HT_IRQ bool "Interrupts on hypertransport devices" default y - depends on X86_LOCAL_APIC && X86_IO_APIC + depends on PCI && X86_LOCAL_APIC && X86_IO_APIC help This allows native hypertransport devices to use interrupts. diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c index a0d1cee0be7..306f46b85a5 100644 --- a/drivers/scsi/aha152x.c +++ b/drivers/scsi/aha152x.c @@ -238,7 +238,7 @@ #include <linux/module.h> #include <linux/sched.h> #include <asm/irq.h> -#include <asm/io.h> +#include <linux/io.h> #include <linux/blkdev.h> #include <asm/system.h> #include <linux/errno.h> diff --git a/drivers/scsi/dtc.c b/drivers/scsi/dtc.c index 0d5713dfa20..54756722dd5 100644 --- a/drivers/scsi/dtc.c +++ b/drivers/scsi/dtc.c @@ -82,7 +82,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/interrupt.h> -#include <asm/io.h> +#include <linux/io.h> #include "scsi.h" #include <scsi/scsi_host.h> #include "dtc.h" diff --git a/drivers/scsi/fdomain.c b/drivers/scsi/fdomain.c index 41b05fc4538..72794a7b6dc 100644 --- a/drivers/scsi/fdomain.c +++ b/drivers/scsi/fdomain.c @@ -278,9 +278,9 @@ #include <linux/pci.h> #include <linux/stat.h> #include <linux/delay.h> +#include <linux/io.h> #include <scsi/scsicam.h> -#include <asm/io.h> #include <asm/system.h> #include <scsi/scsi.h> diff --git a/drivers/scsi/seagate.c b/drivers/scsi/seagate.c index 8ff1f2866f7..5ffec2721b2 100644 --- a/drivers/scsi/seagate.c +++ b/drivers/scsi/seagate.c @@ -97,8 +97,8 @@ #include <linux/blkdev.h> #include <linux/stat.h> #include <linux/delay.h> +#include <linux/io.h> -#include <asm/io.h> #include <asm/system.h> #include <asm/uaccess.h> diff --git a/drivers/scsi/t128.c b/drivers/scsi/t128.c index 2df6747cb76..0b7a70f61e0 100644 --- a/drivers/scsi/t128.c +++ b/drivers/scsi/t128.c @@ -109,7 +109,7 @@ #include <asm/system.h> #include <linux/signal.h> #include <linux/sched.h> -#include <asm/io.h> +#include <linux/io.h> #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/stat.h> diff --git a/drivers/scsi/wd7000.c b/drivers/scsi/wd7000.c index 331e1cf159b..30be76514c4 100644 --- a/drivers/scsi/wd7000.c +++ b/drivers/scsi/wd7000.c @@ -178,10 +178,10 @@ #include <linux/blkdev.h> #include <linux/init.h> #include <linux/stat.h> +#include <linux/io.h> #include <asm/system.h> #include <asm/dma.h> -#include <asm/io.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index daaa486159c..7a43020fa58 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -701,7 +701,6 @@ config FB_NVIDIA depends on FB && PCI select I2C_ALGOBIT if FB_NVIDIA_I2C select I2C if FB_NVIDIA_I2C - select FB_DDC if FB_NVIDIA_I2C select FB_MODE_HELPERS select FB_CFB_FILLRECT select FB_CFB_COPYAREA diff --git a/drivers/video/nvidia/nv_i2c.c b/drivers/video/nvidia/nv_i2c.c index e48de3c9fd1..19eef3a0902 100644 --- a/drivers/video/nvidia/nv_i2c.c +++ b/drivers/video/nvidia/nv_i2c.c @@ -160,12 +160,51 @@ void nvidia_delete_i2c_busses(struct nvidia_par *par) } +static u8 *nvidia_do_probe_i2c_edid(struct nvidia_i2c_chan *chan) +{ + u8 start = 0x0; + struct i2c_msg msgs[] = { + { + .addr = 0x50, + .len = 1, + .buf = &start, + }, { + .addr = 0x50, + .flags = I2C_M_RD, + .len = EDID_LENGTH, + }, + }; + u8 *buf; + + if (!chan->par) + return NULL; + + buf = kmalloc(EDID_LENGTH, GFP_KERNEL); + if (!buf) { + dev_warn(&chan->par->pci_dev->dev, "Out of memory!\n"); + return NULL; + } + msgs[1].buf = buf; + + if (i2c_transfer(&chan->adapter, msgs, 2) == 2) + return buf; + dev_dbg(&chan->par->pci_dev->dev, "Unable to read EDID block.\n"); + kfree(buf); + return NULL; +} + int nvidia_probe_i2c_connector(struct fb_info *info, int conn, u8 **out_edid) { struct nvidia_par *par = info->par; - u8 *edid; - - edid = fb_ddc_read(&par->chan[conn - 1].adapter); + u8 *edid = NULL; + int i; + + for (i = 0; i < 3; i++) { + /* Do the real work */ + edid = nvidia_do_probe_i2c_edid(&par->chan[conn - 1]); + if (edid) + break; + } if (!edid && conn == 1) { /* try to get from firmware */ diff --git a/fs/Kconfig b/fs/Kconfig index 599de54451a..db4d13324c3 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -140,6 +140,73 @@ config EXT3_FS_SECURITY If you are not using a security module that requires using extended attributes for file security labels, say N. +config EXT4DEV_FS + tristate "Ext4dev/ext4 extended fs support development (EXPERIMENTAL)" + depends on EXPERIMENTAL + select JBD2 + help + Ext4dev is a predecessor filesystem of the next generation + extended fs ext4, based on ext3 filesystem code. It will be + renamed ext4 fs later, once ext4dev is mature and stabilized. + + Unlike the change from ext2 filesystem to ext3 filesystem, + the on-disk format of ext4dev is not the same as ext3 any more: + it is based on extent maps and it supports 48-bit physical block + numbers. These combined on-disk format changes will allow + ext4dev/ext4 to handle more than 16 TB filesystem volumes -- + a hard limit that ext3 cannot overcome without changing the + on-disk format. + + Other than extent maps and 48-bit block numbers, ext4dev also is + likely to have other new features such as persistent preallocation, + high resolution time stamps, and larger file support etc. These + features will be added to ext4dev gradually. + + To compile this file system support as a module, choose M here. The + module will be called ext4dev. Be aware, however, that the filesystem + of your root partition (the one containing the directory /) cannot + be compiled as a module, and so this could be dangerous. + + If unsure, say N. + +config EXT4DEV_FS_XATTR + bool "Ext4dev extended attributes" + depends on EXT4DEV_FS + default y + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + <http://acl.bestbits.at/> for details). + + If unsure, say N. + + You need this for POSIX ACL support on ext4dev/ext4. + +config EXT4DEV_FS_POSIX_ACL + bool "Ext4dev POSIX Access Control Lists" + depends on EXT4DEV_FS_XATTR + select FS_POSIX_ACL + help + POSIX Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the POSIX ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N + +config EXT4DEV_FS_SECURITY + bool "Ext4dev Security Labels" + depends on EXT4DEV_FS_XATTR + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the ext4dev/ext4 filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. + config JBD tristate help @@ -172,12 +239,44 @@ config JBD_DEBUG generated. To turn debugging off again, do "echo 0 > /proc/sys/fs/jbd-debug". +config JBD2 + tristate + help + This is a generic journaling layer for block devices that support + both 32-bit and 64-bit block numbers. It is currently used by + the ext4dev/ext4 filesystem, but it could also be used to add + journal support to other file systems or block devices such + as RAID or LVM. + + If you are using ext4dev/ext4, you need to say Y here. If you are not + using ext4dev/ext4 then you will probably want to say N. + + To compile this device as a module, choose M here. The module will be + called jbd2. If you are compiling ext4dev/ext4 into the kernel, + you cannot compile this code as a module. + +config JBD2_DEBUG + bool "JBD2 (ext4dev/ext4) debugging support" + depends on JBD2 + help + If you are using the ext4dev/ext4 journaled file system (or + potentially any other filesystem/device using JBD2), this option + allows you to enable debugging output while the system is running, + in order to help track down any problems you are having. + By default, the debugging output will be turned off. + + If you select Y here, then you will be able to turn on debugging + with "echo N > /proc/sys/fs/jbd2-debug", where N is a number between + 1 and 5. The higher the number, the more debugging output is + generated. To turn debugging off again, do + "echo 0 > /proc/sys/fs/jbd2-debug". + config FS_MBCACHE -# Meta block cache for Extended Attributes (ext2/ext3) +# Meta block cache for Extended Attributes (ext2/ext3/ext4) tristate - depends on EXT2_FS_XATTR || EXT3_FS_XATTR - default y if EXT2_FS=y || EXT3_FS=y - default m if EXT2_FS=m || EXT3_FS=m + depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4DEV_FS_XATTR + default y if EXT2_FS=y || EXT3_FS=y || EXT4DEV_FS=y + default m if EXT2_FS=m || EXT3_FS=m || EXT4DEV_FS=m config REISERFS_FS tristate "Reiserfs support" diff --git a/fs/Makefile b/fs/Makefile index df614eacee8..9a5ce9323bf 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -62,7 +62,9 @@ obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line obj-$(CONFIG_REISERFS_FS) += reiserfs/ obj-$(CONFIG_EXT3_FS) += ext3/ # Before ext2 so root fs can be ext3 +obj-$(CONFIG_EXT4DEV_FS) += ext4/ # Before ext2 so root fs can be ext4dev obj-$(CONFIG_JBD) += jbd/ +obj-$(CONFIG_JBD2) += jbd2/ obj-$(CONFIG_EXT2_FS) += ext2/ obj-$(CONFIG_CRAMFS) += cramfs/ obj-$(CONFIG_RAMFS) += ramfs/ diff --git a/fs/afs/dir.c b/fs/afs/dir.c index cf8a2cb2850..a6ec75c56fc 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -211,8 +211,8 @@ static int afs_dir_open(struct inode *inode, struct file *file) { _enter("{%lu}", inode->i_ino); - BUG_ON(sizeof(union afs_dir_block) != 2048); - BUG_ON(sizeof(union afs_dirent) != 32); + BUILD_BUG_ON(sizeof(union afs_dir_block) != 2048); + BUILD_BUG_ON(sizeof(union afs_dirent) != 32); if (AFS_FS_I(inode)->flags & AFS_VNODE_DELETED) return -ENOENT; @@ -446,8 +446,8 @@ static struct dentry *afs_dir_lookup(struct inode *dir, struct dentry *dentry, _enter("{%lu},%p{%s}", dir->i_ino, dentry, dentry->d_name.name); /* insanity checks first */ - BUG_ON(sizeof(union afs_dir_block) != 2048); - BUG_ON(sizeof(union afs_dirent) != 32); + BUILD_BUG_ON(sizeof(union afs_dir_block) != 2048); + BUILD_BUG_ON(sizeof(union afs_dirent) != 32); if (dentry->d_name.len > 255) { _leave(" = -ENAMETOOLONG"); diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index 480ab178cba..b13f32c8aee 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -94,7 +94,6 @@ struct autofs_wait_queue { struct autofs_sb_info { u32 magic; - struct dentry *root; int pipefd; struct file *pipe; pid_t oz_pgrp; @@ -229,4 +228,4 @@ out: } void autofs4_dentry_release(struct dentry *); - +extern void autofs4_kill_sb(struct super_block *); diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c index 5d9193332be..723a1c5e361 100644 --- a/fs/autofs4/init.c +++ b/fs/autofs4/init.c @@ -24,7 +24,7 @@ static struct file_system_type autofs_fs_type = { .owner = THIS_MODULE, .name = "autofs", .get_sb = autofs_get_sb, - .kill_sb = kill_anon_super, + .kill_sb = autofs4_kill_sb, }; static int __init init_autofs4_fs(void) diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 800ce876cae..51fd8595bf8 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -96,7 +96,7 @@ void autofs4_free_ino(struct autofs_info *ino) */ static void autofs4_force_release(struct autofs_sb_info *sbi) { - struct dentry *this_parent = sbi->root; + struct dentry *this_parent = sbi->sb->s_root; struct list_head *next; spin_lock(&dcache_lock); @@ -127,7 +127,7 @@ resume: spin_lock(&dcache_lock); } - if (this_parent != sbi->root) { + if (this_parent != sbi->sb->s_root) { struct dentry *dentry = this_parent; next = this_parent->d_u.d_child.next; @@ -140,15 +140,9 @@ resume: goto resume; } spin_unlock(&dcache_lock); - - dput(sbi->root); - sbi->root = NULL; - shrink_dcache_sb(sbi->sb); - - return; } -static void autofs4_put_super(struct super_block *sb) +void autofs4_kill_sb(struct super_block *sb) { struct autofs_sb_info *sbi = autofs4_sbi(sb); @@ -163,6 +157,7 @@ static void autofs4_put_super(struct super_block *sb) kfree(sbi); DPRINTK("shutting down"); + kill_anon_super(sb); } static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt) @@ -189,7 +184,6 @@ static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt) } static struct super_operations autofs4_sops = { - .put_super = autofs4_put_super, .statfs = simple_statfs, .show_options = autofs4_show_options, }; @@ -315,7 +309,6 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) s->s_fs_info = sbi; sbi->magic = AUTOFS_SBI_MAGIC; - sbi->root = NULL; sbi->pipefd = -1; sbi->catatonic = 0; sbi->exp_timeout = 0; @@ -397,13 +390,6 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->pipefd = pipefd; /* - * Take a reference to the root dentry so we get a chance to - * clean up the dentry tree on umount. - * See autofs4_force_release. - */ - sbi->root = dget(root); - - /* * Success! Install the root dentry now to indicate completion. */ s->s_root = root; diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index ce103e7b0bc..c0a6c8d445c 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -45,7 +45,6 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi) fput(sbi->pipe); /* Close the pipe */ sbi->pipe = NULL; } - shrink_dcache_sb(sbi->sb); } static int autofs4_write(struct file *file, const void *addr, int bytes) @@ -79,7 +79,6 @@ static struct bio_set *fs_bio_set; static inline struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs) { struct bio_vec *bvl; - struct biovec_slab *bp; /* * see comment near bvec_array define! @@ -98,10 +97,12 @@ static inline struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned lon * idx now points to the pool we want to allocate from */ - bp = bvec_slabs + *idx; bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask); - if (bvl) + if (bvl) { + struct biovec_slab *bp = bvec_slabs + *idx; + memset(bvl, 0, bp->nr_vecs * sizeof(struct bio_vec)); + } return bvl; } @@ -166,7 +167,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs) bio_init(bio); if (likely(nr_iovecs)) { - unsigned long idx; + unsigned long idx = 0; /* shut up gcc */ bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs); if (unlikely(!bvl)) { diff --git a/fs/buffer.c b/fs/buffer.c index eeb8ac1aa85..f65ef8821c7 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1042,8 +1042,21 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) } while ((size << sizebits) < PAGE_SIZE); index = block >> sizebits; - block = index << sizebits; + /* + * Check for a block which wants to lie outside our maximum possible + * pagecache index. (this comparison is done using sector_t types). + */ + if (unlikely(index != block >> sizebits)) { + char b[BDEVNAME_SIZE]; + + printk(KERN_ERR "%s: requested out-of-range block %llu for " + "device %s\n", + __FUNCTION__, (unsigned long long)block, + bdevname(bdev, b)); + return -EIO; + } + block = index << sizebits; /* Create a page with the proper size buffers.. */ page = grow_dev_page(bdev, block, index, size); if (!page) @@ -1070,12 +1083,16 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) for (;;) { struct buffer_head * bh; + int ret; bh = __find_get_block(bdev, block, size); if (bh) return bh; - if (!grow_buffers(bdev, block, size)) + ret = grow_buffers(bdev, block, size); + if (ret < 0) + return NULL; + if (ret == 0) free_more_memory(); } } @@ -1837,6 +1854,7 @@ static int __block_prepare_write(struct inode *inode, struct page *page, clear_buffer_new(bh); kaddr = kmap_atomic(page, KM_USER0); memset(kaddr+block_start, 0, bh->b_size); + flush_dcache_page(page); kunmap_atomic(kaddr, KM_USER0); set_buffer_uptodate(bh); mark_buffer_dirty(bh); @@ -2343,6 +2361,7 @@ failed: */ kaddr = kmap_atomic(page, KM_USER0); memset(kaddr, 0, PAGE_CACHE_SIZE); + flush_dcache_page(page); kunmap_atomic(kaddr, KM_USER0); SetPageUptodate(page); set_page_dirty(page); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 27ca1aa3056..a91f2628c98 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -2438,13 +2438,17 @@ HANDLE_IOCTL(0x1260, broken_blkgetsize) HANDLE_IOCTL(BLKFRAGET, w_long) HANDLE_IOCTL(BLKSECTGET, w_long) HANDLE_IOCTL(BLKPG, blkpg_ioctl_trans) -HANDLE_IOCTL(HDIO_GET_KEEPSETTINGS, hdio_ioctl_trans) HANDLE_IOCTL(HDIO_GET_UNMASKINTR, hdio_ioctl_trans) -HANDLE_IOCTL(HDIO_GET_DMA, hdio_ioctl_trans) -HANDLE_IOCTL(HDIO_GET_32BIT, hdio_ioctl_trans) HANDLE_IOCTL(HDIO_GET_MULTCOUNT, hdio_ioctl_trans) +HANDLE_IOCTL(HDIO_GET_KEEPSETTINGS, hdio_ioctl_trans) +HANDLE_IOCTL(HDIO_GET_32BIT, hdio_ioctl_trans) HANDLE_IOCTL(HDIO_GET_NOWERR, hdio_ioctl_trans) +HANDLE_IOCTL(HDIO_GET_DMA, hdio_ioctl_trans) HANDLE_IOCTL(HDIO_GET_NICE, hdio_ioctl_trans) +HANDLE_IOCTL(HDIO_GET_WCACHE, hdio_ioctl_trans) +HANDLE_IOCTL(HDIO_GET_ACOUSTIC, hdio_ioctl_trans) +HANDLE_IOCTL(HDIO_GET_ADDRESS, hdio_ioctl_trans) +HANDLE_IOCTL(HDIO_GET_BUSSTATE, hdio_ioctl_trans) HANDLE_IOCTL(FDSETPRM32, fd_ioctl_trans) HANDLE_IOCTL(FDDEFPRM32, fd_ioctl_trans) HANDLE_IOCTL(FDGETPRM32, fd_ioctl_trans) diff --git a/fs/dcache.c b/fs/dcache.c index 2355bddad8d..2bac4ba1d1d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -549,6 +549,136 @@ repeat: } /* + * destroy a single subtree of dentries for unmount + * - see the comments on shrink_dcache_for_umount() for a description of the + * locking + */ +static void shrink_dcache_for_umount_subtree(struct dentry *dentry) +{ + struct dentry *parent; + + BUG_ON(!IS_ROOT(dentry)); + + /* detach this root from the system */ + spin_lock(&dcache_lock); + if (!list_empty(&dentry->d_lru)) { + dentry_stat.nr_unused--; + list_del_init(&dentry->d_lru); + } + __d_drop(dentry); + spin_unlock(&dcache_lock); + + for (;;) { + /* descend to the first leaf in the current subtree */ + while (!list_empty(&dentry->d_subdirs)) { + struct dentry *loop; + + /* this is a branch with children - detach all of them + * from the system in one go */ + spin_lock(&dcache_lock); + list_for_each_entry(loop, &dentry->d_subdirs, + d_u.d_child) { + if (!list_empty(&loop->d_lru)) { + dentry_stat.nr_unused--; + list_del_init(&loop->d_lru); + } + + __d_drop(loop); + cond_resched_lock(&dcache_lock); + } + spin_unlock(&dcache_lock); + + /* move to the first child */ + dentry = list_entry(dentry->d_subdirs.next, + struct dentry, d_u.d_child); + } + + /* consume the dentries from this leaf up through its parents + * until we find one with children or run out altogether */ + do { + struct inode *inode; + + if (atomic_read(&dentry->d_count) != 0) { + printk(KERN_ERR + "BUG: Dentry %p{i=%lx,n=%s}" + " still in use (%d)" + " [unmount of %s %s]\n", + dentry, + dentry->d_inode ? + dentry->d_inode->i_ino : 0UL, + dentry->d_name.name, + atomic_read(&dentry->d_count), + dentry->d_sb->s_type->name, + dentry->d_sb->s_id); + BUG(); + } + + parent = dentry->d_parent; + if (parent == dentry) + parent = NULL; + else + atomic_dec(&parent->d_count); + + list_del(&dentry->d_u.d_child); + dentry_stat.nr_dentry--; /* For d_free, below */ + + inode = dentry->d_inode; + if (inode) { + dentry->d_inode = NULL; + list_del_init(&dentry->d_alias); + if (dentry->d_op && dentry->d_op->d_iput) + dentry->d_op->d_iput(dentry, inode); + else + iput(inode); + } + + d_free(dentry); + + /* finished when we fall off the top of the tree, + * otherwise we ascend to the parent and move to the + * next sibling if there is one */ + if (!parent) + return; + + dentry = parent; + + } while (list_empty(&dentry->d_subdirs)); + + dentry = list_entry(dentry->d_subdirs.next, + struct dentry, d_u.d_child); + } +} + +/* + * destroy the dentries attached to a superblock on unmounting + * - we don't need to use dentry->d_lock, and only need dcache_lock when + * removing the dentry from the system lists and hashes because: + * - the superblock is detached from all mountings and open files, so the + * dentry trees will not be rearranged by the VFS + * - s_umount is write-locked, so the memory pressure shrinker will ignore + * any dentries belonging to this superblock that it comes across + * - the filesystem itself is no longer permitted to rearrange the dentries + * in this superblock + */ +void shrink_dcache_for_umount(struct super_block *sb) +{ + struct dentry *dentry; + + if (down_read_trylock(&sb->s_umount)) + BUG(); + + dentry = sb->s_root; + sb->s_root = NULL; + atomic_dec(&dentry->d_count); + shrink_dcache_for_umount_subtree(dentry); + + while (!hlist_empty(&sb->s_anon)) { + dentry = hlist_entry(sb->s_anon.first, struct dentry, d_hash); + shrink_dcache_for_umount_subtree(dentry); + } +} + +/* * Search for at least 1 mount point in the dentry's subdirs. * We descend to the next level whenever the d_subdirs * list is non-empty and continue searching. diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 557d5b614fa..ae228ec54e9 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -105,6 +105,8 @@ /* Maximum msec timeout value storeable in a long int */ #define EP_MAX_MSTIMEO min(1000ULL * MAX_SCHEDULE_TIMEOUT / HZ, (LONG_MAX - 999ULL) / HZ) +#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) + struct epoll_filefd { struct file *file; @@ -497,7 +499,7 @@ void eventpoll_release_file(struct file *file) */ asmlinkage long sys_epoll_create(int size) { - int error, fd; + int error, fd = -1; struct eventpoll *ep; struct inode *inode; struct file *file; @@ -640,7 +642,6 @@ eexit_1: return error; } -#define MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) /* * Implement the event wait interface for the eventpoll file. It is the kernel @@ -657,7 +658,7 @@ asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, current, epfd, events, maxevents, timeout)); /* The maximum number of event must be greater than zero */ - if (maxevents <= 0 || maxevents > MAX_EVENTS) + if (maxevents <= 0 || maxevents > EP_MAX_EVENTS) return -EINVAL; /* Verify that the area passed by the user is writeable */ @@ -699,6 +700,55 @@ eexit_1: } +#ifdef TIF_RESTORE_SIGMASK + +/* + * Implement the event wait interface for the eventpoll file. It is the kernel + * part of the user space epoll_pwait(2). + */ +asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout, const sigset_t __user *sigmask, + size_t sigsetsize) +{ + int error; + sigset_t ksigmask, sigsaved; + + /* + * If the caller wants a certain signal mask to be set during the wait, + * we apply it here. + */ + if (sigmask) { + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask))) + return -EFAULT; + sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + error = sys_epoll_wait(epfd, events, maxevents, timeout); + + /* + * If we changed the signal mask, we need to restore the original one. + * In case we've got a signal while waiting, we do not restore the + * signal mask yet, and we allow do_signal() to deliver the signal on + * the way back to userspace, before the signal mask is restored. + */ + if (sigmask) { + if (error == -EINTR) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_thread_flag(TIF_RESTORE_SIGMASK); + } else + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + } + + return error; +} + +#endif /* #ifdef TIF_RESTORE_SIGMASK */ + + /* * Creates the file descriptor to be used by the epoll interface. */ diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 513cd421ac0..d8b9abd95d0 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -364,7 +364,6 @@ static int parse_options (char * options, { char * p; substring_t args[MAX_OPT_ARGS]; - unsigned long kind = EXT2_MOUNT_ERRORS_CONT; int option; if (!options) @@ -404,13 +403,19 @@ static int parse_options (char * options, /* *sb_block = match_int(&args[0]); */ break; case Opt_err_panic: - kind = EXT2_MOUNT_ERRORS_PANIC; + clear_opt (sbi->s_mount_opt, ERRORS_CONT); + clear_opt (sbi->s_mount_opt, ERRORS_RO); + set_opt (sbi->s_mount_opt, ERRORS_PANIC); break; case Opt_err_ro: - kind = EXT2_MOUNT_ERRORS_RO; + clear_opt (sbi->s_mount_opt, ERRORS_CONT); + clear_opt (sbi->s_mount_opt, ERRORS_PANIC); + set_opt (sbi->s_mount_opt, ERRORS_RO); break; case Opt_err_cont: - kind = EXT2_MOUNT_ERRORS_CONT; + clear_opt (sbi->s_mount_opt, ERRORS_RO); + clear_opt (sbi->s_mount_opt, ERRORS_PANIC); + set_opt (sbi->s_mount_opt, ERRORS_CONT); break; case Opt_nouid32: set_opt (sbi->s_mount_opt, NO_UID32); @@ -489,7 +494,6 @@ static int parse_options (char * options, return 0; } } - sbi->s_mount_opt |= kind; return 1; } @@ -715,6 +719,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) set_opt(sbi->s_mount_opt, ERRORS_PANIC); else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_RO) set_opt(sbi->s_mount_opt, ERRORS_RO); + else + set_opt(sbi->s_mount_opt, ERRORS_CONT); sbi->s_resuid = le16_to_cpu(es->s_def_resuid); sbi->s_resgid = le16_to_cpu(es->s_def_resgid); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 8bfd56ef18c..afc2d4f42d7 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1470,6 +1470,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) set_opt(sbi->s_mount_opt, ERRORS_PANIC); else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO) set_opt(sbi->s_mount_opt, ERRORS_RO); + else + set_opt(sbi->s_mount_opt, ERRORS_CONT); sbi->s_resuid = le16_to_cpu(es->s_def_resuid); sbi->s_resgid = le16_to_cpu(es->s_def_resgid); diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile new file mode 100644 index 00000000000..a6acb96ebeb --- /dev/null +++ b/fs/ext4/Makefile @@ -0,0 +1,12 @@ +# +# Makefile for the linux ext4-filesystem routines. +# + +obj-$(CONFIG_EXT4DEV_FS) += ext4dev.o + +ext4dev-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ + ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o + +ext4dev-$(CONFIG_EXT4DEV_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o +ext4dev-$(CONFIG_EXT4DEV_FS_POSIX_ACL) += acl.o +ext4dev-$(CONFIG_EXT4DEV_FS_SECURITY) += xattr_security.o diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c new file mode 100644 index 00000000000..9e882546d91 --- /dev/null +++ b/fs/ext4/acl.c @@ -0,0 +1,551 @@ +/* + * linux/fs/ext4/acl.c + * + * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> + */ + +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/capability.h> +#include <linux/fs.h> +#include <linux/ext4_jbd2.h> +#include <linux/ext4_fs.h> +#include "xattr.h" +#include "acl.h" + +/* + * Convert from filesystem to in-memory representation. + */ +static struct posix_acl * +ext4_acl_from_disk(const void *value, size_t size) +{ + const char *end = (char *)value + size; + int n, count; + struct posix_acl *acl; + + if (!value) + return NULL; + if (size < sizeof(ext4_acl_header)) + return ERR_PTR(-EINVAL); + if (((ext4_acl_header *)value)->a_version != + cpu_to_le32(EXT4_ACL_VERSION)) + return ERR_PTR(-EINVAL); + value = (char *)value + sizeof(ext4_acl_header); + count = ext4_acl_count(size); + if (count < 0) + return ERR_PTR(-EINVAL); + if (count == 0) + return NULL; + acl = posix_acl_alloc(count, GFP_KERNEL); + if (!acl) + return ERR_PTR(-ENOMEM); + for (n=0; n < count; n++) { + ext4_acl_entry *entry = + (ext4_acl_entry *)value; + if ((char *)value + sizeof(ext4_acl_entry_short) > end) + goto fail; + acl->a_entries[n].e_tag = le16_to_cpu(entry->e_tag); + acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm); + switch(acl->a_entries[n].e_tag) { + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + value = (char *)value + + sizeof(ext4_acl_entry_short); + acl->a_entries[n].e_id = ACL_UNDEFINED_ID; + break; + + case ACL_USER: + case ACL_GROUP: + value = (char *)value + sizeof(ext4_acl_entry); + if ((char *)value > end) + goto fail; + acl->a_entries[n].e_id = + le32_to_cpu(entry->e_id); + break; + + default: + goto fail; + } + } + if (value != end) + goto fail; + return acl; + +fail: + posix_acl_release(acl); + return ERR_PTR(-EINVAL); +} + +/* + * Convert from in-memory to filesystem representation. + */ +static void * +ext4_acl_to_disk(const struct posix_acl *acl, size_t *size) +{ + ext4_acl_header *ext_acl; + char *e; + size_t n; + + *size = ext4_acl_size(acl->a_count); + ext_acl = kmalloc(sizeof(ext4_acl_header) + acl->a_count * + sizeof(ext4_acl_entry), GFP_KERNEL); + if (!ext_acl) + return ERR_PTR(-ENOMEM); + ext_acl->a_version = cpu_to_le32(EXT4_ACL_VERSION); + e = (char *)ext_acl + sizeof(ext4_acl_header); + for (n=0; n < acl->a_count; n++) { + ext4_acl_entry *entry = (ext4_acl_entry *)e; + entry->e_tag = cpu_to_le16(acl->a_entries[n].e_tag); + entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm); + switch(acl->a_entries[n].e_tag) { + case ACL_USER: + case ACL_GROUP: + entry->e_id = + cpu_to_le32(acl->a_entries[n].e_id); + e += sizeof(ext4_acl_entry); + break; + + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + e += sizeof(ext4_acl_entry_short); + break; + + default: + goto fail; + } + } + return (char *)ext_acl; + +fail: + kfree(ext_acl); + return ERR_PTR(-EINVAL); +} + +static inline struct posix_acl * +ext4_iget_acl(struct inode *inode, struct posix_acl **i_acl) +{ + struct posix_acl *acl = EXT4_ACL_NOT_CACHED; + + spin_lock(&inode->i_lock); + if (*i_acl != EXT4_ACL_NOT_CACHED) + acl = posix_acl_dup(*i_acl); + spin_unlock(&inode->i_lock); + + return acl; +} + +static inline void +ext4_iset_acl(struct inode *inode, struct posix_acl **i_acl, + struct posix_acl *acl) +{ + spin_lock(&inode->i_lock); + if (*i_acl != EXT4_ACL_NOT_CACHED) + posix_acl_release(*i_acl); + *i_acl = posix_acl_dup(acl); + spin_unlock(&inode->i_lock); +} + +/* + * Inode operation get_posix_acl(). + * + * inode->i_mutex: don't care + */ +static struct posix_acl * +ext4_get_acl(struct inode *inode, int type) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + int name_index; + char *value = NULL; + struct posix_acl *acl; + int retval; + + if (!test_opt(inode->i_sb, POSIX_ACL)) + return NULL; + + switch(type) { + case ACL_TYPE_ACCESS: + acl = ext4_iget_acl(inode, &ei->i_acl); + if (acl != EXT4_ACL_NOT_CACHED) + return acl; + name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; + break; + + case ACL_TYPE_DEFAULT: + acl = ext4_iget_acl(inode, &ei->i_default_acl); + if (acl != EXT4_ACL_NOT_CACHED) + return acl; + name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT; + break; + + default: + return ERR_PTR(-EINVAL); + } + retval = ext4_xattr_get(inode, name_index, "", NULL, 0); + if (retval > 0) { + value = kmalloc(retval, GFP_KERNEL); + if (!value) + return ERR_PTR(-ENOMEM); + retval = ext4_xattr_get(inode, name_index, "", value, retval); + } + if (retval > 0) + acl = ext4_acl_from_disk(value, retval); + else if (retval == -ENODATA || retval == -ENOSYS) + acl = NULL; + else + acl = ERR_PTR(retval); + kfree(value); + + if (!IS_ERR(acl)) { + switch(type) { + case ACL_TYPE_ACCESS: + ext4_iset_acl(inode, &ei->i_acl, acl); + break; + + case ACL_TYPE_DEFAULT: + ext4_iset_acl(inode, &ei->i_default_acl, acl); + break; + } + } + return acl; +} + +/* + * Set the access or default ACL of an inode. + * + * inode->i_mutex: down unless called from ext4_new_inode + */ +static int +ext4_set_acl(handle_t *handle, struct inode *inode, int type, + struct posix_acl *acl) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + int name_index; + void *value = NULL; + size_t size = 0; + int error; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + switch(type) { + case ACL_TYPE_ACCESS: + name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; + if (acl) { + mode_t mode = inode->i_mode; + error = posix_acl_equiv_mode(acl, &mode); + if (error < 0) + return error; + else { + inode->i_mode = mode; + ext4_mark_inode_dirty(handle, inode); + if (error == 0) + acl = NULL; + } + } + break; + + case ACL_TYPE_DEFAULT: + name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT; + if (!S_ISDIR(inode->i_mode)) + return acl ? -EACCES : 0; + break; + + default: + return -EINVAL; + } + if (acl) { + value = ext4_acl_to_disk(acl, &size); + if (IS_ERR(value)) + return (int)PTR_ERR(value); + } + + error = ext4_xattr_set_handle(handle, inode, name_index, "", + value, size, 0); + + kfree(value); + if (!error) { + switch(type) { + case ACL_TYPE_ACCESS: + ext4_iset_acl(inode, &ei->i_acl, acl); + break; + + case ACL_TYPE_DEFAULT: + ext4_iset_acl(inode, &ei->i_default_acl, acl); + break; + } + } + return error; +} + +static int +ext4_check_acl(struct inode *inode, int mask) +{ + struct posix_acl *acl = ext4_get_acl(inode, ACL_TYPE_ACCESS); + + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl) { + int error = posix_acl_permission(inode, acl, mask); + posix_acl_release(acl); + return error; + } + + return -EAGAIN; +} + +int +ext4_permission(struct inode *inode, int mask, struct nameidata *nd) +{ + return generic_permission(inode, mask, ext4_check_acl); +} + +/* + * Initialize the ACLs of a new inode. Called from ext4_new_inode. + * + * dir->i_mutex: down + * inode->i_mutex: up (access to inode is still exclusive) + */ +int +ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) +{ + struct posix_acl *acl = NULL; + int error = 0; + + if (!S_ISLNK(inode->i_mode)) { + if (test_opt(dir->i_sb, POSIX_ACL)) { + acl = ext4_get_acl(dir, ACL_TYPE_DEFAULT); + if (IS_ERR(acl)) + return PTR_ERR(acl); + } + if (!acl) + inode->i_mode &= ~current->fs->umask; + } + if (test_opt(inode->i_sb, POSIX_ACL) && acl) { + struct posix_acl *clone; + mode_t mode; + + if (S_ISDIR(inode->i_mode)) { + error = ext4_set_acl(handle, inode, + ACL_TYPE_DEFAULT, acl); + if (error) + goto cleanup; + } + clone = posix_acl_clone(acl, GFP_KERNEL); + error = -ENOMEM; + if (!clone) + goto cleanup; + + mode = inode->i_mode; + error = posix_acl_create_masq(clone, &mode); + if (error >= 0) { + inode->i_mode = mode; + if (error > 0) { + /* This is an extended ACL */ + error = ext4_set_acl(handle, inode, + ACL_TYPE_ACCESS, clone); + } + } + posix_acl_release(clone); + } +cleanup: + posix_acl_release(acl); + return error; +} + +/* + * Does chmod for an inode that may have an Access Control List. The + * inode->i_mode field must be updated to the desired value by the caller + * before calling this function. + * Returns 0 on success, or a negative error number. + * + * We change the ACL rather than storing some ACL entries in the file + * mode permission bits (which would be more efficient), because that + * would break once additional permissions (like ACL_APPEND, ACL_DELETE + * for directories) are added. There are no more bits available in the + * file mode. + * + * inode->i_mutex: down + */ +int +ext4_acl_chmod(struct inode *inode) +{ + struct posix_acl *acl, *clone; + int error; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + if (!test_opt(inode->i_sb, POSIX_ACL)) + return 0; + acl = ext4_get_acl(inode, ACL_TYPE_ACCESS); + if (IS_ERR(acl) || !acl) + return PTR_ERR(acl); + clone = posix_acl_clone(acl, GFP_KERNEL); + posix_acl_release(acl); + if (!clone) + return -ENOMEM; + error = posix_acl_chmod_masq(clone, inode->i_mode); + if (!error) { + handle_t *handle; + int retries = 0; + + retry: + handle = ext4_journal_start(inode, + EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + ext4_std_error(inode->i_sb, error); + goto out; + } + error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, clone); + ext4_journal_stop(handle); + if (error == -ENOSPC && + ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + } +out: + posix_acl_release(clone); + return error; +} + +/* + * Extended attribute handlers + */ +static size_t +ext4_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len, + const char *name, size_t name_len) +{ + const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS); + + if (!test_opt(inode->i_sb, POSIX_ACL)) + return 0; + if (list && size <= list_len) + memcpy(list, POSIX_ACL_XATTR_ACCESS, size); + return size; +} + +static size_t +ext4_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len, + const char *name, size_t name_len) +{ + const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT); + + if (!test_opt(inode->i_sb, POSIX_ACL)) + return 0; + if (list && size <= list_len) + memcpy(list, POSIX_ACL_XATTR_DEFAULT, size); + return size; +} + +static int +ext4_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size) +{ + struct posix_acl *acl; + int error; + + if (!test_opt(inode->i_sb, POSIX_ACL)) + return -EOPNOTSUPP; + + acl = ext4_get_acl(inode, type); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl == NULL) + return -ENODATA; + error = posix_acl_to_xattr(acl, buffer, size); + posix_acl_release(acl); + + return error; +} + +static int +ext4_xattr_get_acl_access(struct inode *inode, const char *name, + void *buffer, size_t size) +{ + if (strcmp(name, "") != 0) + return -EINVAL; + return ext4_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size); +} + +static int +ext4_xattr_get_acl_default(struct inode *inode, const char *name, + void *buffer, size_t size) +{ + if (strcmp(name, "") != 0) + return -EINVAL; + return ext4_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size); +} + +static int +ext4_xattr_set_acl(struct inode *inode, int type, const void *value, + size_t size) +{ + handle_t *handle; + struct posix_acl *acl; + int error, retries = 0; + + if (!test_opt(inode->i_sb, POSIX_ACL)) + return -EOPNOTSUPP; + if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + return -EPERM; + + if (value) { + acl = posix_acl_from_xattr(value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + else if (acl) { + error = posix_acl_valid(acl); + if (error) + goto release_and_out; + } + } else + acl = NULL; + +retry: + handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + error = ext4_set_acl(handle, inode, type, acl); + ext4_journal_stop(handle); + if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + +release_and_out: + posix_acl_release(acl); + return error; +} + +static int +ext4_xattr_set_acl_access(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + if (strcmp(name, "") != 0) + return -EINVAL; + return ext4_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size); +} + +static int +ext4_xattr_set_acl_default(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + if (strcmp(name, "") != 0) + return -EINVAL; + return ext4_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size); +} + +struct xattr_handler ext4_xattr_acl_access_handler = { + .prefix = POSIX_ACL_XATTR_ACCESS, + .list = ext4_xattr_list_acl_access, + .get = ext4_xattr_get_acl_access, + .set = ext4_xattr_set_acl_access, +}; + +struct xattr_handler ext4_xattr_acl_default_handler = { + .prefix = POSIX_ACL_XATTR_DEFAULT, + .list = ext4_xattr_list_acl_default, + .get = ext4_xattr_get_acl_default, + .set = ext4_xattr_set_acl_default, +}; diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h new file mode 100644 index 00000000000..26a5c1abf14 --- /dev/null +++ b/fs/ext4/acl.h @@ -0,0 +1,81 @@ +/* + File: fs/ext4/acl.h + + (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> +*/ + +#include <linux/posix_acl_xattr.h> + +#define EXT4_ACL_VERSION 0x0001 + +typedef struct { + __le16 e_tag; + __le16 e_perm; + __le32 e_id; +} ext4_acl_entry; + +typedef struct { + __le16 e_tag; + __le16 e_perm; +} ext4_acl_entry_short; + +typedef struct { + __le32 a_version; +} ext4_acl_header; + +static inline size_t ext4_acl_size(int count) +{ + if (count <= 4) { + return sizeof(ext4_acl_header) + + count * sizeof(ext4_acl_entry_short); + } else { + return sizeof(ext4_acl_header) + + 4 * sizeof(ext4_acl_entry_short) + + (count - 4) * sizeof(ext4_acl_entry); + } +} + +static inline int ext4_acl_count(size_t size) +{ + ssize_t s; + size -= sizeof(ext4_acl_header); + s = size - 4 * sizeof(ext4_acl_entry_short); + if (s < 0) { + if (size % sizeof(ext4_acl_entry_short)) + return -1; + return size / sizeof(ext4_acl_entry_short); + } else { + if (s % sizeof(ext4_acl_entry)) + return -1; + return s / sizeof(ext4_acl_entry) + 4; + } +} + +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + +/* Value for inode->u.ext4_i.i_acl and inode->u.ext4_i.i_default_acl + if the ACL has not been cached */ +#define EXT4_ACL_NOT_CACHED ((void *)-1) + +/* acl.c */ +extern int ext4_permission (struct inode *, int, struct nameidata *); +extern int ext4_acl_chmod (struct inode *); +extern int ext4_init_acl (handle_t *, struct inode *, struct inode *); + +#else /* CONFIG_EXT4DEV_FS_POSIX_ACL */ +#include <linux/sched.h> +#define ext4_permission NULL + +static inline int +ext4_acl_chmod(struct inode *inode) +{ + return 0; +} + +static inline int +ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) +{ + return 0; +} +#endif /* CONFIG_EXT4DEV_FS_POSIX_ACL */ + diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c new file mode 100644 index 00000000000..5d45582f951 --- /dev/null +++ b/fs/ext4/balloc.c @@ -0,0 +1,1833 @@ +/* + * linux/fs/ext4/balloc.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * Enhanced block allocation by Stephen Tweedie (sct@redhat.com), 1993 + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + */ + +#include <linux/time.h> +#include <linux/capability.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/ext4_jbd2.h> +#include <linux/quotaops.h> +#include <linux/buffer_head.h> + +/* + * balloc.c contains the blocks allocation and deallocation routines + */ + +/* + * Calculate the block group number and offset, given a block number + */ +void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, + unsigned long *blockgrpp, ext4_grpblk_t *offsetp) +{ + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + ext4_grpblk_t offset; + + blocknr = blocknr - le32_to_cpu(es->s_first_data_block); + offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)); + if (offsetp) + *offsetp = offset; + if (blockgrpp) + *blockgrpp = blocknr; + +} + +/* + * The free blocks are managed by bitmaps. A file system contains several + * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap + * block for inodes, N blocks for the inode table and data blocks. + * + * The file system contains group descriptors which are located after the + * super block. Each descriptor contains the number of the bitmap block and + * the free blocks count in the block. The descriptors are loaded in memory + * when a file system is mounted (see ext4_read_super). + */ + + +#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) + +/** + * ext4_get_group_desc() -- load group descriptor from disk + * @sb: super block + * @block_group: given block group + * @bh: pointer to the buffer head to store the block + * group descriptor + */ +struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, + unsigned int block_group, + struct buffer_head ** bh) +{ + unsigned long group_desc; + unsigned long offset; + struct ext4_group_desc * desc; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (block_group >= sbi->s_groups_count) { + ext4_error (sb, "ext4_get_group_desc", + "block_group >= groups_count - " + "block_group = %d, groups_count = %lu", + block_group, sbi->s_groups_count); + + return NULL; + } + smp_rmb(); + + group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); + offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); + if (!sbi->s_group_desc[group_desc]) { + ext4_error (sb, "ext4_get_group_desc", + "Group descriptor not loaded - " + "block_group = %d, group_desc = %lu, desc = %lu", + block_group, group_desc, offset); + return NULL; + } + + desc = (struct ext4_group_desc *)( + (__u8 *)sbi->s_group_desc[group_desc]->b_data + + offset * EXT4_DESC_SIZE(sb)); + if (bh) + *bh = sbi->s_group_desc[group_desc]; + return desc; +} + +/** + * read_block_bitmap() + * @sb: super block + * @block_group: given block group + * + * Read the bitmap for a given block_group, reading into the specified + * slot in the superblock's bitmap cache. + * + * Return buffer_head on success or NULL in case of failure. + */ +static struct buffer_head * +read_block_bitmap(struct super_block *sb, unsigned int block_group) +{ + struct ext4_group_desc * desc; + struct buffer_head * bh = NULL; + + desc = ext4_get_group_desc (sb, block_group, NULL); + if (!desc) + goto error_out; + bh = sb_bread(sb, ext4_block_bitmap(sb, desc)); + if (!bh) + ext4_error (sb, "read_block_bitmap", + "Cannot read block bitmap - " + "block_group = %d, block_bitmap = %llu", + block_group, + ext4_block_bitmap(sb, desc)); +error_out: + return bh; +} +/* + * The reservation window structure operations + * -------------------------------------------- + * Operations include: + * dump, find, add, remove, is_empty, find_next_reservable_window, etc. + * + * We use a red-black tree to represent per-filesystem reservation + * windows. + * + */ + +/** + * __rsv_window_dump() -- Dump the filesystem block allocation reservation map + * @rb_root: root of per-filesystem reservation rb tree + * @verbose: verbose mode + * @fn: function which wishes to dump the reservation map + * + * If verbose is turned on, it will print the whole block reservation + * windows(start, end). Otherwise, it will only print out the "bad" windows, + * those windows that overlap with their immediate neighbors. + */ +#if 1 +static void __rsv_window_dump(struct rb_root *root, int verbose, + const char *fn) +{ + struct rb_node *n; + struct ext4_reserve_window_node *rsv, *prev; + int bad; + +restart: + n = rb_first(root); + bad = 0; + prev = NULL; + + printk("Block Allocation Reservation Windows Map (%s):\n", fn); + while (n) { + rsv = list_entry(n, struct ext4_reserve_window_node, rsv_node); + if (verbose) + printk("reservation window 0x%p " + "start: %llu, end: %llu\n", + rsv, rsv->rsv_start, rsv->rsv_end); + if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) { + printk("Bad reservation %p (start >= end)\n", + rsv); + bad = 1; + } + if (prev && prev->rsv_end >= rsv->rsv_start) { + printk("Bad reservation %p (prev->end >= start)\n", + rsv); + bad = 1; + } + if (bad) { + if (!verbose) { + printk("Restarting reservation walk in verbose mode\n"); + verbose = 1; + goto restart; + } + } + n = rb_next(n); + prev = rsv; + } + printk("Window map complete.\n"); + if (bad) + BUG(); +} +#define rsv_window_dump(root, verbose) \ + __rsv_window_dump((root), (verbose), __FUNCTION__) +#else +#define rsv_window_dump(root, verbose) do {} while (0) +#endif + +/** + * goal_in_my_reservation() + * @rsv: inode's reservation window + * @grp_goal: given goal block relative to the allocation block group + * @group: the current allocation block group + * @sb: filesystem super block + * + * Test if the given goal block (group relative) is within the file's + * own block reservation window range. + * + * If the reservation window is outside the goal allocation group, return 0; + * grp_goal (given goal block) could be -1, which means no specific + * goal block. In this case, always return 1. + * If the goal block is within the reservation window, return 1; + * otherwise, return 0; + */ +static int +goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal, + unsigned int group, struct super_block * sb) +{ + ext4_fsblk_t group_first_block, group_last_block; + + group_first_block = ext4_group_first_block_no(sb, group); + group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); + + if ((rsv->_rsv_start > group_last_block) || + (rsv->_rsv_end < group_first_block)) + return 0; + if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start) + || (grp_goal + group_first_block > rsv->_rsv_end))) + return 0; + return 1; +} + +/** + * search_reserve_window() + * @rb_root: root of reservation tree + * @goal: target allocation block + * + * Find the reserved window which includes the goal, or the previous one + * if the goal is not in any window. + * Returns NULL if there are no windows or if all windows start after the goal. + */ +static struct ext4_reserve_window_node * +search_reserve_window(struct rb_root *root, ext4_fsblk_t goal) +{ + struct rb_node *n = root->rb_node; + struct ext4_reserve_window_node *rsv; + + if (!n) + return NULL; + + do { + rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node); + + if (goal < rsv->rsv_start) + n = n->rb_left; + else if (goal > rsv->rsv_end) + n = n->rb_right; + else + return rsv; + } while (n); + /* + * We've fallen off the end of the tree: the goal wasn't inside + * any particular node. OK, the previous node must be to one + * side of the interval containing the goal. If it's the RHS, + * we need to back up one. + */ + if (rsv->rsv_start > goal) { + n = rb_prev(&rsv->rsv_node); + rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node); + } + return rsv; +} + +/** + * ext4_rsv_window_add() -- Insert a window to the block reservation rb tree. + * @sb: super block + * @rsv: reservation window to add + * + * Must be called with rsv_lock hold. + */ +void ext4_rsv_window_add(struct super_block *sb, + struct ext4_reserve_window_node *rsv) +{ + struct rb_root *root = &EXT4_SB(sb)->s_rsv_window_root; + struct rb_node *node = &rsv->rsv_node; + ext4_fsblk_t start = rsv->rsv_start; + + struct rb_node ** p = &root->rb_node; + struct rb_node * parent = NULL; + struct ext4_reserve_window_node *this; + + while (*p) + { + parent = *p; + this = rb_entry(parent, struct ext4_reserve_window_node, rsv_node); + + if (start < this->rsv_start) + p = &(*p)->rb_left; + else if (start > this->rsv_end) + p = &(*p)->rb_right; + else { + rsv_window_dump(root, 1); + BUG(); + } + } + + rb_link_node(node, parent, p); + rb_insert_color(node, root); +} + +/** + * ext4_rsv_window_remove() -- unlink a window from the reservation rb tree + * @sb: super block + * @rsv: reservation window to remove + * + * Mark the block reservation window as not allocated, and unlink it + * from the filesystem reservation window rb tree. Must be called with + * rsv_lock hold. + */ +static void rsv_window_remove(struct super_block *sb, + struct ext4_reserve_window_node *rsv) +{ + rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED; + rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED; + rsv->rsv_alloc_hit = 0; + rb_erase(&rsv->rsv_node, &EXT4_SB(sb)->s_rsv_window_root); +} + +/* + * rsv_is_empty() -- Check if the reservation window is allocated. + * @rsv: given reservation window to check + * + * returns 1 if the end block is EXT4_RESERVE_WINDOW_NOT_ALLOCATED. + */ +static inline int rsv_is_empty(struct ext4_reserve_window *rsv) +{ + /* a valid reservation end block could not be 0 */ + return rsv->_rsv_end == EXT4_RESERVE_WINDOW_NOT_ALLOCATED; +} + +/** + * ext4_init_block_alloc_info() + * @inode: file inode structure + * + * Allocate and initialize the reservation window structure, and + * link the window to the ext4 inode structure at last + * + * The reservation window structure is only dynamically allocated + * and linked to ext4 inode the first time the open file + * needs a new block. So, before every ext4_new_block(s) call, for + * regular files, we should check whether the reservation window + * structure exists or not. In the latter case, this function is called. + * Fail to do so will result in block reservation being turned off for that + * open file. + * + * This function is called from ext4_get_blocks_handle(), also called + * when setting the reservation window size through ioctl before the file + * is open for write (needs block allocation). + * + * Needs truncate_mutex protection prior to call this function. + */ +void ext4_init_block_alloc_info(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info; + struct super_block *sb = inode->i_sb; + + block_i = kmalloc(sizeof(*block_i), GFP_NOFS); + if (block_i) { + struct ext4_reserve_window_node *rsv = &block_i->rsv_window_node; + + rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED; + rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED; + + /* + * if filesystem is mounted with NORESERVATION, the goal + * reservation window size is set to zero to indicate + * block reservation is off + */ + if (!test_opt(sb, RESERVATION)) + rsv->rsv_goal_size = 0; + else + rsv->rsv_goal_size = EXT4_DEFAULT_RESERVE_BLOCKS; + rsv->rsv_alloc_hit = 0; + block_i->last_alloc_logical_block = 0; + block_i->last_alloc_physical_block = 0; + } + ei->i_block_alloc_info = block_i; +} + +/** + * ext4_discard_reservation() + * @inode: inode + * + * Discard(free) block reservation window on last file close, or truncate + * or at last iput(). + * + * It is being called in three cases: + * ext4_release_file(): last writer close the file + * ext4_clear_inode(): last iput(), when nobody link to this file. + * ext4_truncate(): when the block indirect map is about to change. + * + */ +void ext4_discard_reservation(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info; + struct ext4_reserve_window_node *rsv; + spinlock_t *rsv_lock = &EXT4_SB(inode->i_sb)->s_rsv_window_lock; + + if (!block_i) + return; + + rsv = &block_i->rsv_window_node; + if (!rsv_is_empty(&rsv->rsv_window)) { + spin_lock(rsv_lock); + if (!rsv_is_empty(&rsv->rsv_window)) + rsv_window_remove(inode->i_sb, rsv); + spin_unlock(rsv_lock); + } +} + +/** + * ext4_free_blocks_sb() -- Free given blocks and update quota + * @handle: handle to this transaction + * @sb: super block + * @block: start physcial block to free + * @count: number of blocks to free + * @pdquot_freed_blocks: pointer to quota + */ +void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb, + ext4_fsblk_t block, unsigned long count, + unsigned long *pdquot_freed_blocks) +{ + struct buffer_head *bitmap_bh = NULL; + struct buffer_head *gd_bh; + unsigned long block_group; + ext4_grpblk_t bit; + unsigned long i; + unsigned long overflow; + struct ext4_group_desc * desc; + struct ext4_super_block * es; + struct ext4_sb_info *sbi; + int err = 0, ret; + ext4_grpblk_t group_freed; + + *pdquot_freed_blocks = 0; + sbi = EXT4_SB(sb); + es = sbi->s_es; + if (block < le32_to_cpu(es->s_first_data_block) || + block + count < block || + block + count > ext4_blocks_count(es)) { + ext4_error (sb, "ext4_free_blocks", + "Freeing blocks not in datazone - " + "block = %llu, count = %lu", block, count); + goto error_return; + } + + ext4_debug ("freeing block(s) %llu-%llu\n", block, block + count - 1); + +do_more: + overflow = 0; + ext4_get_group_no_and_offset(sb, block, &block_group, &bit); + /* + * Check to see if we are freeing blocks across a group + * boundary. + */ + if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) { + overflow = bit + count - EXT4_BLOCKS_PER_GROUP(sb); + count -= overflow; + } + brelse(bitmap_bh); + bitmap_bh = read_block_bitmap(sb, block_group); + if (!bitmap_bh) + goto error_return; + desc = ext4_get_group_desc (sb, block_group, &gd_bh); + if (!desc) + goto error_return; + + if (in_range(ext4_block_bitmap(sb, desc), block, count) || + in_range(ext4_inode_bitmap(sb, desc), block, count) || + in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || + in_range(block + count - 1, ext4_inode_table(sb, desc), + sbi->s_itb_per_group)) + ext4_error (sb, "ext4_free_blocks", + "Freeing blocks in system zones - " + "Block = %llu, count = %lu", + block, count); + + /* + * We are about to start releasing blocks in the bitmap, + * so we need undo access. + */ + /* @@@ check errors */ + BUFFER_TRACE(bitmap_bh, "getting undo access"); + err = ext4_journal_get_undo_access(handle, bitmap_bh); + if (err) + goto error_return; + + /* + * We are about to modify some metadata. Call the journal APIs + * to unshare ->b_data if a currently-committing transaction is + * using it + */ + BUFFER_TRACE(gd_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, gd_bh); + if (err) + goto error_return; + + jbd_lock_bh_state(bitmap_bh); + + for (i = 0, group_freed = 0; i < count; i++) { + /* + * An HJ special. This is expensive... + */ +#ifdef CONFIG_JBD_DEBUG + jbd_unlock_bh_state(bitmap_bh); + { + struct buffer_head *debug_bh; + debug_bh = sb_find_get_block(sb, block + i); + if (debug_bh) { + BUFFER_TRACE(debug_bh, "Deleted!"); + if (!bh2jh(bitmap_bh)->b_committed_data) + BUFFER_TRACE(debug_bh, + "No commited data in bitmap"); + BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap"); + __brelse(debug_bh); + } + } + jbd_lock_bh_state(bitmap_bh); +#endif + if (need_resched()) { + jbd_unlock_bh_state(bitmap_bh); + cond_resched(); + jbd_lock_bh_state(bitmap_bh); + } + /* @@@ This prevents newly-allocated data from being + * freed and then reallocated within the same + * transaction. + * + * Ideally we would want to allow that to happen, but to + * do so requires making jbd2_journal_forget() capable of + * revoking the queued write of a data block, which + * implies blocking on the journal lock. *forget() + * cannot block due to truncate races. + * + * Eventually we can fix this by making jbd2_journal_forget() + * return a status indicating whether or not it was able + * to revoke the buffer. On successful revoke, it is + * safe not to set the allocation bit in the committed + * bitmap, because we know that there is no outstanding + * activity on the buffer any more and so it is safe to + * reallocate it. + */ + BUFFER_TRACE(bitmap_bh, "set in b_committed_data"); + J_ASSERT_BH(bitmap_bh, + bh2jh(bitmap_bh)->b_committed_data != NULL); + ext4_set_bit_atomic(sb_bgl_lock(sbi, block_group), bit + i, + bh2jh(bitmap_bh)->b_committed_data); + + /* + * We clear the bit in the bitmap after setting the committed + * data bit, because this is the reverse order to that which + * the allocator uses. + */ + BUFFER_TRACE(bitmap_bh, "clear bit"); + if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), + bit + i, bitmap_bh->b_data)) { + jbd_unlock_bh_state(bitmap_bh); + ext4_error(sb, __FUNCTION__, + "bit already cleared for block %llu", + (ext4_fsblk_t)(block + i)); + jbd_lock_bh_state(bitmap_bh); + BUFFER_TRACE(bitmap_bh, "bit already cleared"); + } else { + group_freed++; + } + } + jbd_unlock_bh_state(bitmap_bh); + + spin_lock(sb_bgl_lock(sbi, block_group)); + desc->bg_free_blocks_count = + cpu_to_le16(le16_to_cpu(desc->bg_free_blocks_count) + + group_freed); + spin_unlock(sb_bgl_lock(sbi, block_group)); + percpu_counter_mod(&sbi->s_freeblocks_counter, count); + + /* We dirtied the bitmap block */ + BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); + err = ext4_journal_dirty_metadata(handle, bitmap_bh); + + /* And the group descriptor block */ + BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); + ret = ext4_journal_dirty_metadata(handle, gd_bh); + if (!err) err = ret; + *pdquot_freed_blocks += group_freed; + + if (overflow && !err) { + block += count; + count = overflow; + goto do_more; + } + sb->s_dirt = 1; +error_return: + brelse(bitmap_bh); + ext4_std_error(sb, err); + return; +} + +/** + * ext4_free_blocks() -- Free given blocks and update quota + * @handle: handle for this transaction + * @inode: inode + * @block: start physical block to free + * @count: number of blocks to count + */ +void ext4_free_blocks(handle_t *handle, struct inode *inode, + ext4_fsblk_t block, unsigned long count) +{ + struct super_block * sb; + unsigned long dquot_freed_blocks; + + sb = inode->i_sb; + if (!sb) { + printk ("ext4_free_blocks: nonexistent device"); + return; + } + ext4_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks); + if (dquot_freed_blocks) + DQUOT_FREE_BLOCK(inode, dquot_freed_blocks); + return; +} + +/** + * ext4_test_allocatable() + * @nr: given allocation block group + * @bh: bufferhead contains the bitmap of the given block group + * + * For ext4 allocations, we must not reuse any blocks which are + * allocated in the bitmap buffer's "last committed data" copy. This + * prevents deletes from freeing up the page for reuse until we have + * committed the delete transaction. + * + * If we didn't do this, then deleting something and reallocating it as + * data would allow the old block to be overwritten before the + * transaction committed (because we force data to disk before commit). + * This would lead to corruption if we crashed between overwriting the + * data and committing the delete. + * + * @@@ We may want to make this allocation behaviour conditional on + * data-writes at some point, and disable it for metadata allocations or + * sync-data inodes. + */ +static int ext4_test_allocatable(ext4_grpblk_t nr, struct buffer_head *bh) +{ + int ret; + struct journal_head *jh = bh2jh(bh); + + if (ext4_test_bit(nr, bh->b_data)) + return 0; + + jbd_lock_bh_state(bh); + if (!jh->b_committed_data) + ret = 1; + else + ret = !ext4_test_bit(nr, jh->b_committed_data); + jbd_unlock_bh_state(bh); + return ret; +} + +/** + * bitmap_search_next_usable_block() + * @start: the starting block (group relative) of the search + * @bh: bufferhead contains the block group bitmap + * @maxblocks: the ending block (group relative) of the reservation + * + * The bitmap search --- search forward alternately through the actual + * bitmap on disk and the last-committed copy in journal, until we find a + * bit free in both bitmaps. + */ +static ext4_grpblk_t +bitmap_search_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh, + ext4_grpblk_t maxblocks) +{ + ext4_grpblk_t next; + struct journal_head *jh = bh2jh(bh); + + while (start < maxblocks) { + next = ext4_find_next_zero_bit(bh->b_data, maxblocks, start); + if (next >= maxblocks) + return -1; + if (ext4_test_allocatable(next, bh)) + return next; + jbd_lock_bh_state(bh); + if (jh->b_committed_data) + start = ext4_find_next_zero_bit(jh->b_committed_data, + maxblocks, next); + jbd_unlock_bh_state(bh); + } + return -1; +} + +/** + * find_next_usable_block() + * @start: the starting block (group relative) to find next + * allocatable block in bitmap. + * @bh: bufferhead contains the block group bitmap + * @maxblocks: the ending block (group relative) for the search + * + * Find an allocatable block in a bitmap. We honor both the bitmap and + * its last-committed copy (if that exists), and perform the "most + * appropriate allocation" algorithm of looking for a free block near + * the initial goal; then for a free byte somewhere in the bitmap; then + * for any free bit in the bitmap. + */ +static ext4_grpblk_t +find_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh, + ext4_grpblk_t maxblocks) +{ + ext4_grpblk_t here, next; + char *p, *r; + + if (start > 0) { + /* + * The goal was occupied; search forward for a free + * block within the next XX blocks. + * + * end_goal is more or less random, but it has to be + * less than EXT4_BLOCKS_PER_GROUP. Aligning up to the + * next 64-bit boundary is simple.. + */ + ext4_grpblk_t end_goal = (start + 63) & ~63; + if (end_goal > maxblocks) + end_goal = maxblocks; + here = ext4_find_next_zero_bit(bh->b_data, end_goal, start); + if (here < end_goal && ext4_test_allocatable(here, bh)) + return here; + ext4_debug("Bit not found near goal\n"); + } + + here = start; + if (here < 0) + here = 0; + + p = ((char *)bh->b_data) + (here >> 3); + r = memscan(p, 0, (maxblocks - here + 7) >> 3); + next = (r - ((char *)bh->b_data)) << 3; + + if (next < maxblocks && next >= start && ext4_test_allocatable(next, bh)) + return next; + + /* + * The bitmap search --- search forward alternately through the actual + * bitmap and the last-committed copy until we find a bit free in + * both + */ + here = bitmap_search_next_usable_block(here, bh, maxblocks); + return here; +} + +/** + * claim_block() + * @block: the free block (group relative) to allocate + * @bh: the bufferhead containts the block group bitmap + * + * We think we can allocate this block in this bitmap. Try to set the bit. + * If that succeeds then check that nobody has allocated and then freed the + * block since we saw that is was not marked in b_committed_data. If it _was_ + * allocated and freed then clear the bit in the bitmap again and return + * zero (failure). + */ +static inline int +claim_block(spinlock_t *lock, ext4_grpblk_t block, struct buffer_head *bh) +{ + struct journal_head *jh = bh2jh(bh); + int ret; + + if (ext4_set_bit_atomic(lock, block, bh->b_data)) + return 0; + jbd_lock_bh_state(bh); + if (jh->b_committed_data && ext4_test_bit(block,jh->b_committed_data)) { + ext4_clear_bit_atomic(lock, block, bh->b_data); + ret = 0; + } else { + ret = 1; + } + jbd_unlock_bh_state(bh); + return ret; +} + +/** + * ext4_try_to_allocate() + * @sb: superblock + * @handle: handle to this transaction + * @group: given allocation block group + * @bitmap_bh: bufferhead holds the block bitmap + * @grp_goal: given target block within the group + * @count: target number of blocks to allocate + * @my_rsv: reservation window + * + * Attempt to allocate blocks within a give range. Set the range of allocation + * first, then find the first free bit(s) from the bitmap (within the range), + * and at last, allocate the blocks by claiming the found free bit as allocated. + * + * To set the range of this allocation: + * if there is a reservation window, only try to allocate block(s) from the + * file's own reservation window; + * Otherwise, the allocation range starts from the give goal block, ends at + * the block group's last block. + * + * If we failed to allocate the desired block then we may end up crossing to a + * new bitmap. In that case we must release write access to the old one via + * ext4_journal_release_buffer(), else we'll run out of credits. + */ +static ext4_grpblk_t +ext4_try_to_allocate(struct super_block *sb, handle_t *handle, int group, + struct buffer_head *bitmap_bh, ext4_grpblk_t grp_goal, + unsigned long *count, struct ext4_reserve_window *my_rsv) +{ + ext4_fsblk_t group_first_block; + ext4_grpblk_t start, end; + unsigned long num = 0; + + /* we do allocation within the reservation window if we have a window */ + if (my_rsv) { + group_first_block = ext4_group_first_block_no(sb, group); + if (my_rsv->_rsv_start >= group_first_block) + start = my_rsv->_rsv_start - group_first_block; + else + /* reservation window cross group boundary */ + start = 0; + end = my_rsv->_rsv_end - group_first_block + 1; + if (end > EXT4_BLOCKS_PER_GROUP(sb)) + /* reservation window crosses group boundary */ + end = EXT4_BLOCKS_PER_GROUP(sb); + if ((start <= grp_goal) && (grp_goal < end)) + start = grp_goal; + else + grp_goal = -1; + } else { + if (grp_goal > 0) + start = grp_goal; + else + start = 0; + end = EXT4_BLOCKS_PER_GROUP(sb); + } + + BUG_ON(start > EXT4_BLOCKS_PER_GROUP(sb)); + +repeat: + if (grp_goal < 0 || !ext4_test_allocatable(grp_goal, bitmap_bh)) { + grp_goal = find_next_usable_block(start, bitmap_bh, end); + if (grp_goal < 0) + goto fail_access; + if (!my_rsv) { + int i; + + for (i = 0; i < 7 && grp_goal > start && + ext4_test_allocatable(grp_goal - 1, + bitmap_bh); + i++, grp_goal--) + ; + } + } + start = grp_goal; + + if (!claim_block(sb_bgl_lock(EXT4_SB(sb), group), + grp_goal, bitmap_bh)) { + /* + * The block was allocated by another thread, or it was + * allocated and then freed by another thread + */ + start++; + grp_goal++; + if (start >= end) + goto fail_access; + goto repeat; + } + num++; + grp_goal++; + while (num < *count && grp_goal < end + && ext4_test_allocatable(grp_goal, bitmap_bh) + && claim_block(sb_bgl_lock(EXT4_SB(sb), group), + grp_goal, bitmap_bh)) { + num++; + grp_goal++; + } + *count = num; + return grp_goal - num; +fail_access: + *count = num; + return -1; +} + +/** + * find_next_reservable_window(): + * find a reservable space within the given range. + * It does not allocate the reservation window for now: + * alloc_new_reservation() will do the work later. + * + * @search_head: the head of the searching list; + * This is not necessarily the list head of the whole filesystem + * + * We have both head and start_block to assist the search + * for the reservable space. The list starts from head, + * but we will shift to the place where start_block is, + * then start from there, when looking for a reservable space. + * + * @size: the target new reservation window size + * + * @group_first_block: the first block we consider to start + * the real search from + * + * @last_block: + * the maximum block number that our goal reservable space + * could start from. This is normally the last block in this + * group. The search will end when we found the start of next + * possible reservable space is out of this boundary. + * This could handle the cross boundary reservation window + * request. + * + * basically we search from the given range, rather than the whole + * reservation double linked list, (start_block, last_block) + * to find a free region that is of my size and has not + * been reserved. + * + */ +static int find_next_reservable_window( + struct ext4_reserve_window_node *search_head, + struct ext4_reserve_window_node *my_rsv, + struct super_block * sb, + ext4_fsblk_t start_block, + ext4_fsblk_t last_block) +{ + struct rb_node *next; + struct ext4_reserve_window_node *rsv, *prev; + ext4_fsblk_t cur; + int size = my_rsv->rsv_goal_size; + + /* TODO: make the start of the reservation window byte-aligned */ + /* cur = *start_block & ~7;*/ + cur = start_block; + rsv = search_head; + if (!rsv) + return -1; + + while (1) { + if (cur <= rsv->rsv_end) + cur = rsv->rsv_end + 1; + + /* TODO? + * in the case we could not find a reservable space + * that is what is expected, during the re-search, we could + * remember what's the largest reservable space we could have + * and return that one. + * + * For now it will fail if we could not find the reservable + * space with expected-size (or more)... + */ + if (cur > last_block) + return -1; /* fail */ + + prev = rsv; + next = rb_next(&rsv->rsv_node); + rsv = list_entry(next,struct ext4_reserve_window_node,rsv_node); + + /* + * Reached the last reservation, we can just append to the + * previous one. + */ + if (!next) + break; + + if (cur + size <= rsv->rsv_start) { + /* + * Found a reserveable space big enough. We could + * have a reservation across the group boundary here + */ + break; + } + } + /* + * we come here either : + * when we reach the end of the whole list, + * and there is empty reservable space after last entry in the list. + * append it to the end of the list. + * + * or we found one reservable space in the middle of the list, + * return the reservation window that we could append to. + * succeed. + */ + + if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window))) + rsv_window_remove(sb, my_rsv); + + /* + * Let's book the whole avaliable window for now. We will check the + * disk bitmap later and then, if there are free blocks then we adjust + * the window size if it's larger than requested. + * Otherwise, we will remove this node from the tree next time + * call find_next_reservable_window. + */ + my_rsv->rsv_start = cur; + my_rsv->rsv_end = cur + size - 1; + my_rsv->rsv_alloc_hit = 0; + + if (prev != my_rsv) + ext4_rsv_window_add(sb, my_rsv); + + return 0; +} + +/** + * alloc_new_reservation()--allocate a new reservation window + * + * To make a new reservation, we search part of the filesystem + * reservation list (the list that inside the group). We try to + * allocate a new reservation window near the allocation goal, + * or the beginning of the group, if there is no goal. + * + * We first find a reservable space after the goal, then from + * there, we check the bitmap for the first free block after + * it. If there is no free block until the end of group, then the + * whole group is full, we failed. Otherwise, check if the free + * block is inside the expected reservable space, if so, we + * succeed. + * If the first free block is outside the reservable space, then + * start from the first free block, we search for next available + * space, and go on. + * + * on succeed, a new reservation will be found and inserted into the list + * It contains at least one free block, and it does not overlap with other + * reservation windows. + * + * failed: we failed to find a reservation window in this group + * + * @rsv: the reservation + * + * @grp_goal: The goal (group-relative). It is where the search for a + * free reservable space should start from. + * if we have a grp_goal(grp_goal >0 ), then start from there, + * no grp_goal(grp_goal = -1), we start from the first block + * of the group. + * + * @sb: the super block + * @group: the group we are trying to allocate in + * @bitmap_bh: the block group block bitmap + * + */ +static int alloc_new_reservation(struct ext4_reserve_window_node *my_rsv, + ext4_grpblk_t grp_goal, struct super_block *sb, + unsigned int group, struct buffer_head *bitmap_bh) +{ + struct ext4_reserve_window_node *search_head; + ext4_fsblk_t group_first_block, group_end_block, start_block; + ext4_grpblk_t first_free_block; + struct rb_root *fs_rsv_root = &EXT4_SB(sb)->s_rsv_window_root; + unsigned long size; + int ret; + spinlock_t *rsv_lock = &EXT4_SB(sb)->s_rsv_window_lock; + + group_first_block = ext4_group_first_block_no(sb, group); + group_end_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); + + if (grp_goal < 0) + start_block = group_first_block; + else + start_block = grp_goal + group_first_block; + + size = my_rsv->rsv_goal_size; + + if (!rsv_is_empty(&my_rsv->rsv_window)) { + /* + * if the old reservation is cross group boundary + * and if the goal is inside the old reservation window, + * we will come here when we just failed to allocate from + * the first part of the window. We still have another part + * that belongs to the next group. In this case, there is no + * point to discard our window and try to allocate a new one + * in this group(which will fail). we should + * keep the reservation window, just simply move on. + * + * Maybe we could shift the start block of the reservation + * window to the first block of next group. + */ + + if ((my_rsv->rsv_start <= group_end_block) && + (my_rsv->rsv_end > group_end_block) && + (start_block >= my_rsv->rsv_start)) + return -1; + + if ((my_rsv->rsv_alloc_hit > + (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) { + /* + * if the previously allocation hit ratio is + * greater than 1/2, then we double the size of + * the reservation window the next time, + * otherwise we keep the same size window + */ + size = size * 2; + if (size > EXT4_MAX_RESERVE_BLOCKS) + size = EXT4_MAX_RESERVE_BLOCKS; + my_rsv->rsv_goal_size= size; + } + } + + spin_lock(rsv_lock); + /* + * shift the search start to the window near the goal block + */ + search_head = search_reserve_window(fs_rsv_root, start_block); + + /* + * find_next_reservable_window() simply finds a reservable window + * inside the given range(start_block, group_end_block). + * + * To make sure the reservation window has a free bit inside it, we + * need to check the bitmap after we found a reservable window. + */ +retry: + ret = find_next_reservable_window(search_head, my_rsv, sb, + start_block, group_end_block); + + if (ret == -1) { + if (!rsv_is_empty(&my_rsv->rsv_window)) + rsv_window_remove(sb, my_rsv); + spin_unlock(rsv_lock); + return -1; + } + + /* + * On success, find_next_reservable_window() returns the + * reservation window where there is a reservable space after it. + * Before we reserve this reservable space, we need + * to make sure there is at least a free block inside this region. + * + * searching the first free bit on the block bitmap and copy of + * last committed bitmap alternatively, until we found a allocatable + * block. Search start from the start block of the reservable space + * we just found. + */ + spin_unlock(rsv_lock); + first_free_block = bitmap_search_next_usable_block( + my_rsv->rsv_start - group_first_block, + bitmap_bh, group_end_block - group_first_block + 1); + + if (first_free_block < 0) { + /* + * no free block left on the bitmap, no point + * to reserve the space. return failed. + */ + spin_lock(rsv_lock); + if (!rsv_is_empty(&my_rsv->rsv_window)) + rsv_window_remove(sb, my_rsv); + spin_unlock(rsv_lock); + return -1; /* failed */ + } + + start_block = first_free_block + group_first_block; + /* + * check if the first free block is within the + * free space we just reserved + */ + if (start_block >= my_rsv->rsv_start && start_block < my_rsv->rsv_end) + return 0; /* success */ + /* + * if the first free bit we found is out of the reservable space + * continue search for next reservable space, + * start from where the free block is, + * we also shift the list head to where we stopped last time + */ + search_head = my_rsv; + spin_lock(rsv_lock); + goto retry; +} + +/** + * try_to_extend_reservation() + * @my_rsv: given reservation window + * @sb: super block + * @size: the delta to extend + * + * Attempt to expand the reservation window large enough to have + * required number of free blocks + * + * Since ext4_try_to_allocate() will always allocate blocks within + * the reservation window range, if the window size is too small, + * multiple blocks allocation has to stop at the end of the reservation + * window. To make this more efficient, given the total number of + * blocks needed and the current size of the window, we try to + * expand the reservation window size if necessary on a best-effort + * basis before ext4_new_blocks() tries to allocate blocks, + */ +static void try_to_extend_reservation(struct ext4_reserve_window_node *my_rsv, + struct super_block *sb, int size) +{ + struct ext4_reserve_window_node *next_rsv; + struct rb_node *next; + spinlock_t *rsv_lock = &EXT4_SB(sb)->s_rsv_window_lock; + + if (!spin_trylock(rsv_lock)) + return; + + next = rb_next(&my_rsv->rsv_node); + + if (!next) + my_rsv->rsv_end += size; + else { + next_rsv = list_entry(next, struct ext4_reserve_window_node, rsv_node); + + if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size) + my_rsv->rsv_end += size; + else + my_rsv->rsv_end = next_rsv->rsv_start - 1; + } + spin_unlock(rsv_lock); +} + +/** + * ext4_try_to_allocate_with_rsv() + * @sb: superblock + * @handle: handle to this transaction + * @group: given allocation block group + * @bitmap_bh: bufferhead holds the block bitmap + * @grp_goal: given target block within the group + * @count: target number of blocks to allocate + * @my_rsv: reservation window + * @errp: pointer to store the error code + * + * This is the main function used to allocate a new block and its reservation + * window. + * + * Each time when a new block allocation is need, first try to allocate from + * its own reservation. If it does not have a reservation window, instead of + * looking for a free bit on bitmap first, then look up the reservation list to + * see if it is inside somebody else's reservation window, we try to allocate a + * reservation window for it starting from the goal first. Then do the block + * allocation within the reservation window. + * + * This will avoid keeping on searching the reservation list again and + * again when somebody is looking for a free block (without + * reservation), and there are lots of free blocks, but they are all + * being reserved. + * + * We use a red-black tree for the per-filesystem reservation list. + * + */ +static ext4_grpblk_t +ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle, + unsigned int group, struct buffer_head *bitmap_bh, + ext4_grpblk_t grp_goal, + struct ext4_reserve_window_node * my_rsv, + unsigned long *count, int *errp) +{ + ext4_fsblk_t group_first_block, group_last_block; + ext4_grpblk_t ret = 0; + int fatal; + unsigned long num = *count; + + *errp = 0; + + /* + * Make sure we use undo access for the bitmap, because it is critical + * that we do the frozen_data COW on bitmap buffers in all cases even + * if the buffer is in BJ_Forget state in the committing transaction. + */ + BUFFER_TRACE(bitmap_bh, "get undo access for new block"); + fatal = ext4_journal_get_undo_access(handle, bitmap_bh); + if (fatal) { + *errp = fatal; + return -1; + } + + /* + * we don't deal with reservation when + * filesystem is mounted without reservation + * or the file is not a regular file + * or last attempt to allocate a block with reservation turned on failed + */ + if (my_rsv == NULL ) { + ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh, + grp_goal, count, NULL); + goto out; + } + /* + * grp_goal is a group relative block number (if there is a goal) + * 0 < grp_goal < EXT4_BLOCKS_PER_GROUP(sb) + * first block is a filesystem wide block number + * first block is the block number of the first block in this group + */ + group_first_block = ext4_group_first_block_no(sb, group); + group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); + + /* + * Basically we will allocate a new block from inode's reservation + * window. + * + * We need to allocate a new reservation window, if: + * a) inode does not have a reservation window; or + * b) last attempt to allocate a block from existing reservation + * failed; or + * c) we come here with a goal and with a reservation window + * + * We do not need to allocate a new reservation window if we come here + * at the beginning with a goal and the goal is inside the window, or + * we don't have a goal but already have a reservation window. + * then we could go to allocate from the reservation window directly. + */ + while (1) { + if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) || + !goal_in_my_reservation(&my_rsv->rsv_window, + grp_goal, group, sb)) { + if (my_rsv->rsv_goal_size < *count) + my_rsv->rsv_goal_size = *count; + ret = alloc_new_reservation(my_rsv, grp_goal, sb, + group, bitmap_bh); + if (ret < 0) + break; /* failed */ + + if (!goal_in_my_reservation(&my_rsv->rsv_window, + grp_goal, group, sb)) + grp_goal = -1; + } else if (grp_goal > 0 && + (my_rsv->rsv_end-grp_goal+1) < *count) + try_to_extend_reservation(my_rsv, sb, + *count-my_rsv->rsv_end + grp_goal - 1); + + if ((my_rsv->rsv_start > group_last_block) || + (my_rsv->rsv_end < group_first_block)) { + rsv_window_dump(&EXT4_SB(sb)->s_rsv_window_root, 1); + BUG(); + } + ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh, + grp_goal, &num, &my_rsv->rsv_window); + if (ret >= 0) { + my_rsv->rsv_alloc_hit += num; + *count = num; + break; /* succeed */ + } + num = *count; + } +out: + if (ret >= 0) { + BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for " + "bitmap block"); + fatal = ext4_journal_dirty_metadata(handle, bitmap_bh); + if (fatal) { + *errp = fatal; + return -1; + } + return ret; + } + + BUFFER_TRACE(bitmap_bh, "journal_release_buffer"); + ext4_journal_release_buffer(handle, bitmap_bh); + return ret; +} + +/** + * ext4_has_free_blocks() + * @sbi: in-core super block structure. + * + * Check if filesystem has at least 1 free block available for allocation. + */ +static int ext4_has_free_blocks(struct ext4_sb_info *sbi) +{ + ext4_fsblk_t free_blocks, root_blocks; + + free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); + root_blocks = ext4_r_blocks_count(sbi->s_es); + if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) && + sbi->s_resuid != current->fsuid && + (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) { + return 0; + } + return 1; +} + +/** + * ext4_should_retry_alloc() + * @sb: super block + * @retries number of attemps has been made + * + * ext4_should_retry_alloc() is called when ENOSPC is returned, and if + * it is profitable to retry the operation, this function will wait + * for the current or commiting transaction to complete, and then + * return TRUE. + * + * if the total number of retries exceed three times, return FALSE. + */ +int ext4_should_retry_alloc(struct super_block *sb, int *retries) +{ + if (!ext4_has_free_blocks(EXT4_SB(sb)) || (*retries)++ > 3) + return 0; + + jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id); + + return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal); +} + +/** + * ext4_new_blocks() -- core block(s) allocation function + * @handle: handle to this transaction + * @inode: file inode + * @goal: given target block(filesystem wide) + * @count: target number of blocks to allocate + * @errp: error code + * + * ext4_new_blocks uses a goal block to assist allocation. It tries to + * allocate block(s) from the block group contains the goal block first. If that + * fails, it will try to allocate block(s) from other block groups without + * any specific goal block. + * + */ +ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, unsigned long *count, int *errp) +{ + struct buffer_head *bitmap_bh = NULL; + struct buffer_head *gdp_bh; + unsigned long group_no; + int goal_group; + ext4_grpblk_t grp_target_blk; /* blockgroup relative goal block */ + ext4_grpblk_t grp_alloc_blk; /* blockgroup-relative allocated block*/ + ext4_fsblk_t ret_block; /* filesyetem-wide allocated block */ + int bgi; /* blockgroup iteration index */ + int fatal = 0, err; + int performed_allocation = 0; + ext4_grpblk_t free_blocks; /* number of free blocks in a group */ + struct super_block *sb; + struct ext4_group_desc *gdp; + struct ext4_super_block *es; + struct ext4_sb_info *sbi; + struct ext4_reserve_window_node *my_rsv = NULL; + struct ext4_block_alloc_info *block_i; + unsigned short windowsz = 0; +#ifdef EXT4FS_DEBUG + static int goal_hits, goal_attempts; +#endif + unsigned long ngroups; + unsigned long num = *count; + + *errp = -ENOSPC; + sb = inode->i_sb; + if (!sb) { + printk("ext4_new_block: nonexistent device"); + return 0; + } + + /* + * Check quota for allocation of this block. + */ + if (DQUOT_ALLOC_BLOCK(inode, num)) { + *errp = -EDQUOT; + return 0; + } + + sbi = EXT4_SB(sb); + es = EXT4_SB(sb)->s_es; + ext4_debug("goal=%lu.\n", goal); + /* + * Allocate a block from reservation only when + * filesystem is mounted with reservation(default,-o reservation), and + * it's a regular file, and + * the desired window size is greater than 0 (One could use ioctl + * command EXT4_IOC_SETRSVSZ to set the window size to 0 to turn off + * reservation on that particular file) + */ + block_i = EXT4_I(inode)->i_block_alloc_info; + if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0)) + my_rsv = &block_i->rsv_window_node; + + if (!ext4_has_free_blocks(sbi)) { + *errp = -ENOSPC; + goto out; + } + + /* + * First, test whether the goal block is free. + */ + if (goal < le32_to_cpu(es->s_first_data_block) || + goal >= ext4_blocks_count(es)) + goal = le32_to_cpu(es->s_first_data_block); + ext4_get_group_no_and_offset(sb, goal, &group_no, &grp_target_blk); + goal_group = group_no; +retry_alloc: + gdp = ext4_get_group_desc(sb, group_no, &gdp_bh); + if (!gdp) + goto io_error; + + free_blocks = le16_to_cpu(gdp->bg_free_blocks_count); + /* + * if there is not enough free blocks to make a new resevation + * turn off reservation for this allocation + */ + if (my_rsv && (free_blocks < windowsz) + && (rsv_is_empty(&my_rsv->rsv_window))) + my_rsv = NULL; + + if (free_blocks > 0) { + bitmap_bh = read_block_bitmap(sb, group_no); + if (!bitmap_bh) + goto io_error; + grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle, + group_no, bitmap_bh, grp_target_blk, + my_rsv, &num, &fatal); + if (fatal) + goto out; + if (grp_alloc_blk >= 0) + goto allocated; + } + + ngroups = EXT4_SB(sb)->s_groups_count; + smp_rmb(); + + /* + * Now search the rest of the groups. We assume that + * i and gdp correctly point to the last group visited. + */ + for (bgi = 0; bgi < ngroups; bgi++) { + group_no++; + if (group_no >= ngroups) + group_no = 0; + gdp = ext4_get_group_desc(sb, group_no, &gdp_bh); + if (!gdp) { + *errp = -EIO; + goto out; + } + free_blocks = le16_to_cpu(gdp->bg_free_blocks_count); + /* + * skip this group if the number of + * free blocks is less than half of the reservation + * window size. + */ + if (free_blocks <= (windowsz/2)) + continue; + + brelse(bitmap_bh); + bitmap_bh = read_block_bitmap(sb, group_no); + if (!bitmap_bh) + goto io_error; + /* + * try to allocate block(s) from this group, without a goal(-1). + */ + grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle, + group_no, bitmap_bh, -1, my_rsv, + &num, &fatal); + if (fatal) + goto out; + if (grp_alloc_blk >= 0) + goto allocated; + } + /* + * We may end up a bogus ealier ENOSPC error due to + * filesystem is "full" of reservations, but + * there maybe indeed free blocks avaliable on disk + * In this case, we just forget about the reservations + * just do block allocation as without reservations. + */ + if (my_rsv) { + my_rsv = NULL; + group_no = goal_group; + goto retry_alloc; + } + /* No space left on the device */ + *errp = -ENOSPC; + goto out; + +allocated: + + ext4_debug("using block group %d(%d)\n", + group_no, gdp->bg_free_blocks_count); + + BUFFER_TRACE(gdp_bh, "get_write_access"); + fatal = ext4_journal_get_write_access(handle, gdp_bh); + if (fatal) + goto out; + + ret_block = grp_alloc_blk + ext4_group_first_block_no(sb, group_no); + + if (in_range(ext4_block_bitmap(sb, gdp), ret_block, num) || + in_range(ext4_block_bitmap(sb, gdp), ret_block, num) || + in_range(ret_block, ext4_inode_table(sb, gdp), + EXT4_SB(sb)->s_itb_per_group) || + in_range(ret_block + num - 1, ext4_inode_table(sb, gdp), + EXT4_SB(sb)->s_itb_per_group)) + ext4_error(sb, "ext4_new_block", + "Allocating block in system zone - " + "blocks from %llu, length %lu", + ret_block, num); + + performed_allocation = 1; + +#ifdef CONFIG_JBD_DEBUG + { + struct buffer_head *debug_bh; + + /* Record bitmap buffer state in the newly allocated block */ + debug_bh = sb_find_get_block(sb, ret_block); + if (debug_bh) { + BUFFER_TRACE(debug_bh, "state when allocated"); + BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap state"); + brelse(debug_bh); + } + } + jbd_lock_bh_state(bitmap_bh); + spin_lock(sb_bgl_lock(sbi, group_no)); + if (buffer_jbd(bitmap_bh) && bh2jh(bitmap_bh)->b_committed_data) { + int i; + + for (i = 0; i < num; i++) { + if (ext4_test_bit(grp_alloc_blk+i, + bh2jh(bitmap_bh)->b_committed_data)) { + printk("%s: block was unexpectedly set in " + "b_committed_data\n", __FUNCTION__); + } + } + } + ext4_debug("found bit %d\n", grp_alloc_blk); + spin_unlock(sb_bgl_lock(sbi, group_no)); + jbd_unlock_bh_state(bitmap_bh); +#endif + + if (ret_block + num - 1 >= ext4_blocks_count(es)) { + ext4_error(sb, "ext4_new_block", + "block(%llu) >= blocks count(%llu) - " + "block_group = %lu, es == %p ", ret_block, + ext4_blocks_count(es), group_no, es); + goto out; + } + + /* + * It is up to the caller to add the new buffer to a journal + * list of some description. We don't know in advance whether + * the caller wants to use it as metadata or data. + */ + ext4_debug("allocating block %lu. Goal hits %d of %d.\n", + ret_block, goal_hits, goal_attempts); + + spin_lock(sb_bgl_lock(sbi, group_no)); + gdp->bg_free_blocks_count = + cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count)-num); + spin_unlock(sb_bgl_lock(sbi, group_no)); + percpu_counter_mod(&sbi->s_freeblocks_counter, -num); + + BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor"); + err = ext4_journal_dirty_metadata(handle, gdp_bh); + if (!fatal) + fatal = err; + + sb->s_dirt = 1; + if (fatal) + goto out; + + *errp = 0; + brelse(bitmap_bh); + DQUOT_FREE_BLOCK(inode, *count-num); + *count = num; + return ret_block; + +io_error: + *errp = -EIO; +out: + if (fatal) { + *errp = fatal; + ext4_std_error(sb, fatal); + } + /* + * Undo the block allocation + */ + if (!performed_allocation) + DQUOT_FREE_BLOCK(inode, *count); + brelse(bitmap_bh); + return 0; +} + +ext4_fsblk_t ext4_new_block(handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, int *errp) +{ + unsigned long count = 1; + + return ext4_new_blocks(handle, inode, goal, &count, errp); +} + +/** + * ext4_count_free_blocks() -- count filesystem free blocks + * @sb: superblock + * + * Adds up the number of free blocks from each block group. + */ +ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) +{ + ext4_fsblk_t desc_count; + struct ext4_group_desc *gdp; + int i; + unsigned long ngroups = EXT4_SB(sb)->s_groups_count; +#ifdef EXT4FS_DEBUG + struct ext4_super_block *es; + ext4_fsblk_t bitmap_count; + unsigned long x; + struct buffer_head *bitmap_bh = NULL; + + es = EXT4_SB(sb)->s_es; + desc_count = 0; + bitmap_count = 0; + gdp = NULL; + + smp_rmb(); + for (i = 0; i < ngroups; i++) { + gdp = ext4_get_group_desc(sb, i, NULL); + if (!gdp) + continue; + desc_count += le16_to_cpu(gdp->bg_free_blocks_count); + brelse(bitmap_bh); + bitmap_bh = read_block_bitmap(sb, i); + if (bitmap_bh == NULL) + continue; + + x = ext4_count_free(bitmap_bh, sb->s_blocksize); + printk("group %d: stored = %d, counted = %lu\n", + i, le16_to_cpu(gdp->bg_free_blocks_count), x); + bitmap_count += x; + } + brelse(bitmap_bh); + printk("ext4_count_free_blocks: stored = %llu" + ", computed = %llu, %llu\n", + EXT4_FREE_BLOCKS_COUNT(es), + desc_count, bitmap_count); + return bitmap_count; +#else + desc_count = 0; + smp_rmb(); + for (i = 0; i < ngroups; i++) { + gdp = ext4_get_group_desc(sb, i, NULL); + if (!gdp) + continue; + desc_count += le16_to_cpu(gdp->bg_free_blocks_count); + } + + return desc_count; +#endif +} + +static inline int +block_in_use(ext4_fsblk_t block, struct super_block *sb, unsigned char *map) +{ + ext4_grpblk_t offset; + + ext4_get_group_no_and_offset(sb, block, NULL, &offset); + return ext4_test_bit (offset, map); +} + +static inline int test_root(int a, int b) +{ + int num = b; + + while (a > num) + num *= b; + return num == a; +} + +static int ext4_group_sparse(int group) +{ + if (group <= 1) + return 1; + if (!(group & 1)) + return 0; + return (test_root(group, 7) || test_root(group, 5) || + test_root(group, 3)); +} + +/** + * ext4_bg_has_super - number of blocks used by the superblock in group + * @sb: superblock for filesystem + * @group: group number to check + * + * Return the number of blocks used by the superblock (primary or backup) + * in this group. Currently this will be only 0 or 1. + */ +int ext4_bg_has_super(struct super_block *sb, int group) +{ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) && + !ext4_group_sparse(group)) + return 0; + return 1; +} + +static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, int group) +{ + unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb); + unsigned long first = metagroup * EXT4_DESC_PER_BLOCK(sb); + unsigned long last = first + EXT4_DESC_PER_BLOCK(sb) - 1; + + if (group == first || group == first + 1 || group == last) + return 1; + return 0; +} + +static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, int group) +{ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) && + !ext4_group_sparse(group)) + return 0; + return EXT4_SB(sb)->s_gdb_count; +} + +/** + * ext4_bg_num_gdb - number of blocks used by the group table in group + * @sb: superblock for filesystem + * @group: group number to check + * + * Return the number of blocks used by the group descriptor table + * (primary or backup) in this group. In the future there may be a + * different number of descriptor blocks in each group. + */ +unsigned long ext4_bg_num_gdb(struct super_block *sb, int group) +{ + unsigned long first_meta_bg = + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); + unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb); + + if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) || + metagroup < first_meta_bg) + return ext4_bg_num_gdb_nometa(sb,group); + + return ext4_bg_num_gdb_meta(sb,group); + +} diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c new file mode 100644 index 00000000000..11e93c169bc --- /dev/null +++ b/fs/ext4/bitmap.c @@ -0,0 +1,32 @@ +/* + * linux/fs/ext4/bitmap.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + */ + +#include <linux/buffer_head.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> + +#ifdef EXT4FS_DEBUG + +static int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0}; + +unsigned long ext4_count_free (struct buffer_head * map, unsigned int numchars) +{ + unsigned int i; + unsigned long sum = 0; + + if (!map) + return (0); + for (i = 0; i < numchars; i++) + sum += nibblemap[map->b_data[i] & 0xf] + + nibblemap[(map->b_data[i] >> 4) & 0xf]; + return (sum); +} + +#endif /* EXT4FS_DEBUG */ + diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c new file mode 100644 index 00000000000..f8595787a70 --- /dev/null +++ b/fs/ext4/dir.c @@ -0,0 +1,518 @@ +/* + * linux/fs/ext4/dir.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/dir.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * ext4 directory handling functions + * + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + * + * Hash Tree Directory indexing (c) 2001 Daniel Phillips + * + */ + +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/buffer_head.h> +#include <linux/smp_lock.h> +#include <linux/slab.h> +#include <linux/rbtree.h> + +static unsigned char ext4_filetype_table[] = { + DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK +}; + +static int ext4_readdir(struct file *, void *, filldir_t); +static int ext4_dx_readdir(struct file * filp, + void * dirent, filldir_t filldir); +static int ext4_release_dir (struct inode * inode, + struct file * filp); + +const struct file_operations ext4_dir_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .readdir = ext4_readdir, /* we take BKL. needed?*/ + .ioctl = ext4_ioctl, /* BKL held */ +#ifdef CONFIG_COMPAT + .compat_ioctl = ext4_compat_ioctl, +#endif + .fsync = ext4_sync_file, /* BKL held */ +#ifdef CONFIG_EXT4_INDEX + .release = ext4_release_dir, +#endif +}; + + +static unsigned char get_dtype(struct super_block *sb, int filetype) +{ + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) || + (filetype >= EXT4_FT_MAX)) + return DT_UNKNOWN; + + return (ext4_filetype_table[filetype]); +} + + +int ext4_check_dir_entry (const char * function, struct inode * dir, + struct ext4_dir_entry_2 * de, + struct buffer_head * bh, + unsigned long offset) +{ + const char * error_msg = NULL; + const int rlen = le16_to_cpu(de->rec_len); + + if (rlen < EXT4_DIR_REC_LEN(1)) + error_msg = "rec_len is smaller than minimal"; + else if (rlen % 4 != 0) + error_msg = "rec_len % 4 != 0"; + else if (rlen < EXT4_DIR_REC_LEN(de->name_len)) + error_msg = "rec_len is too small for name_len"; + else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize) + error_msg = "directory entry across blocks"; + else if (le32_to_cpu(de->inode) > + le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)) + error_msg = "inode out of bounds"; + + if (error_msg != NULL) + ext4_error (dir->i_sb, function, + "bad entry in directory #%lu: %s - " + "offset=%lu, inode=%lu, rec_len=%d, name_len=%d", + dir->i_ino, error_msg, offset, + (unsigned long) le32_to_cpu(de->inode), + rlen, de->name_len); + return error_msg == NULL ? 1 : 0; +} + +static int ext4_readdir(struct file * filp, + void * dirent, filldir_t filldir) +{ + int error = 0; + unsigned long offset; + int i, stored; + struct ext4_dir_entry_2 *de; + struct super_block *sb; + int err; + struct inode *inode = filp->f_dentry->d_inode; + int ret = 0; + + sb = inode->i_sb; + +#ifdef CONFIG_EXT4_INDEX + if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_COMPAT_DIR_INDEX) && + ((EXT4_I(inode)->i_flags & EXT4_INDEX_FL) || + ((inode->i_size >> sb->s_blocksize_bits) == 1))) { + err = ext4_dx_readdir(filp, dirent, filldir); + if (err != ERR_BAD_DX_DIR) { + ret = err; + goto out; + } + /* + * We don't set the inode dirty flag since it's not + * critical that it get flushed back to the disk. + */ + EXT4_I(filp->f_dentry->d_inode)->i_flags &= ~EXT4_INDEX_FL; + } +#endif + stored = 0; + offset = filp->f_pos & (sb->s_blocksize - 1); + + while (!error && !stored && filp->f_pos < inode->i_size) { + unsigned long blk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb); + struct buffer_head map_bh; + struct buffer_head *bh = NULL; + + map_bh.b_state = 0; + err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, 0, 0); + if (err > 0) { + page_cache_readahead(sb->s_bdev->bd_inode->i_mapping, + &filp->f_ra, + filp, + map_bh.b_blocknr >> + (PAGE_CACHE_SHIFT - inode->i_blkbits), + 1); + bh = ext4_bread(NULL, inode, blk, 0, &err); + } + + /* + * We ignore I/O errors on directories so users have a chance + * of recovering data when there's a bad sector + */ + if (!bh) { + ext4_error (sb, "ext4_readdir", + "directory #%lu contains a hole at offset %lu", + inode->i_ino, (unsigned long)filp->f_pos); + filp->f_pos += sb->s_blocksize - offset; + continue; + } + +revalidate: + /* If the dir block has changed since the last call to + * readdir(2), then we might be pointing to an invalid + * dirent right now. Scan from the start of the block + * to make sure. */ + if (filp->f_version != inode->i_version) { + for (i = 0; i < sb->s_blocksize && i < offset; ) { + de = (struct ext4_dir_entry_2 *) + (bh->b_data + i); + /* It's too expensive to do a full + * dirent test each time round this + * loop, but we do have to test at + * least that it is non-zero. A + * failure will be detected in the + * dirent test below. */ + if (le16_to_cpu(de->rec_len) < + EXT4_DIR_REC_LEN(1)) + break; + i += le16_to_cpu(de->rec_len); + } + offset = i; + filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1)) + | offset; + filp->f_version = inode->i_version; + } + + while (!error && filp->f_pos < inode->i_size + && offset < sb->s_blocksize) { + de = (struct ext4_dir_entry_2 *) (bh->b_data + offset); + if (!ext4_check_dir_entry ("ext4_readdir", inode, de, + bh, offset)) { + /* + * On error, skip the f_pos to the next block + */ + filp->f_pos = (filp->f_pos | + (sb->s_blocksize - 1)) + 1; + brelse (bh); + ret = stored; + goto out; + } + offset += le16_to_cpu(de->rec_len); + if (le32_to_cpu(de->inode)) { + /* We might block in the next section + * if the data destination is + * currently swapped out. So, use a + * version stamp to detect whether or + * not the directory has been modified + * during the copy operation. + */ + unsigned long version = filp->f_version; + + error = filldir(dirent, de->name, + de->name_len, + filp->f_pos, + le32_to_cpu(de->inode), + get_dtype(sb, de->file_type)); + if (error) + break; + if (version != filp->f_version) + goto revalidate; + stored ++; + } + filp->f_pos += le16_to_cpu(de->rec_len); + } + offset = 0; + brelse (bh); + } +out: + return ret; +} + +#ifdef CONFIG_EXT4_INDEX +/* + * These functions convert from the major/minor hash to an f_pos + * value. + * + * Currently we only use major hash numer. This is unfortunate, but + * on 32-bit machines, the same VFS interface is used for lseek and + * llseek, so if we use the 64 bit offset, then the 32-bit versions of + * lseek/telldir/seekdir will blow out spectacularly, and from within + * the ext2 low-level routine, we don't know if we're being called by + * a 64-bit version of the system call or the 32-bit version of the + * system call. Worse yet, NFSv2 only allows for a 32-bit readdir + * cookie. Sigh. + */ +#define hash2pos(major, minor) (major >> 1) +#define pos2maj_hash(pos) ((pos << 1) & 0xffffffff) +#define pos2min_hash(pos) (0) + +/* + * This structure holds the nodes of the red-black tree used to store + * the directory entry in hash order. + */ +struct fname { + __u32 hash; + __u32 minor_hash; + struct rb_node rb_hash; + struct fname *next; + __u32 inode; + __u8 name_len; + __u8 file_type; + char name[0]; +}; + +/* + * This functoin implements a non-recursive way of freeing all of the + * nodes in the red-black tree. + */ +static void free_rb_tree_fname(struct rb_root *root) +{ + struct rb_node *n = root->rb_node; + struct rb_node *parent; + struct fname *fname; + + while (n) { + /* Do the node's children first */ + if ((n)->rb_left) { + n = n->rb_left; + continue; + } + if (n->rb_right) { + n = n->rb_right; + continue; + } + /* + * The node has no children; free it, and then zero + * out parent's link to it. Finally go to the + * beginning of the loop and try to free the parent + * node. + */ + parent = rb_parent(n); + fname = rb_entry(n, struct fname, rb_hash); + while (fname) { + struct fname * old = fname; + fname = fname->next; + kfree (old); + } + if (!parent) + root->rb_node = NULL; + else if (parent->rb_left == n) + parent->rb_left = NULL; + else if (parent->rb_right == n) + parent->rb_right = NULL; + n = parent; + } + root->rb_node = NULL; +} + + +static struct dir_private_info *create_dir_info(loff_t pos) +{ + struct dir_private_info *p; + + p = kmalloc(sizeof(struct dir_private_info), GFP_KERNEL); + if (!p) + return NULL; + p->root.rb_node = NULL; + p->curr_node = NULL; + p->extra_fname = NULL; + p->last_pos = 0; + p->curr_hash = pos2maj_hash(pos); + p->curr_minor_hash = pos2min_hash(pos); + p->next_hash = 0; + return p; +} + +void ext4_htree_free_dir_info(struct dir_private_info *p) +{ + free_rb_tree_fname(&p->root); + kfree(p); +} + +/* + * Given a directory entry, enter it into the fname rb tree. + */ +int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, + __u32 minor_hash, + struct ext4_dir_entry_2 *dirent) +{ + struct rb_node **p, *parent = NULL; + struct fname * fname, *new_fn; + struct dir_private_info *info; + int len; + + info = (struct dir_private_info *) dir_file->private_data; + p = &info->root.rb_node; + + /* Create and allocate the fname structure */ + len = sizeof(struct fname) + dirent->name_len + 1; + new_fn = kzalloc(len, GFP_KERNEL); + if (!new_fn) + return -ENOMEM; + new_fn->hash = hash; + new_fn->minor_hash = minor_hash; + new_fn->inode = le32_to_cpu(dirent->inode); + new_fn->name_len = dirent->name_len; + new_fn->file_type = dirent->file_type; + memcpy(new_fn->name, dirent->name, dirent->name_len); + new_fn->name[dirent->name_len] = 0; + + while (*p) { + parent = *p; + fname = rb_entry(parent, struct fname, rb_hash); + + /* + * If the hash and minor hash match up, then we put + * them on a linked list. This rarely happens... + */ + if ((new_fn->hash == fname->hash) && + (new_fn->minor_hash == fname->minor_hash)) { + new_fn->next = fname->next; + fname->next = new_fn; + return 0; + } + + if (new_fn->hash < fname->hash) + p = &(*p)->rb_left; + else if (new_fn->hash > fname->hash) + p = &(*p)->rb_right; + else if (new_fn->minor_hash < fname->minor_hash) + p = &(*p)->rb_left; + else /* if (new_fn->minor_hash > fname->minor_hash) */ + p = &(*p)->rb_right; + } + + rb_link_node(&new_fn->rb_hash, parent, p); + rb_insert_color(&new_fn->rb_hash, &info->root); + return 0; +} + + + +/* + * This is a helper function for ext4_dx_readdir. It calls filldir + * for all entres on the fname linked list. (Normally there is only + * one entry on the linked list, unless there are 62 bit hash collisions.) + */ +static int call_filldir(struct file * filp, void * dirent, + filldir_t filldir, struct fname *fname) +{ + struct dir_private_info *info = filp->private_data; + loff_t curr_pos; + struct inode *inode = filp->f_dentry->d_inode; + struct super_block * sb; + int error; + + sb = inode->i_sb; + + if (!fname) { + printk("call_filldir: called with null fname?!?\n"); + return 0; + } + curr_pos = hash2pos(fname->hash, fname->minor_hash); + while (fname) { + error = filldir(dirent, fname->name, + fname->name_len, curr_pos, + fname->inode, + get_dtype(sb, fname->file_type)); + if (error) { + filp->f_pos = curr_pos; + info->extra_fname = fname->next; + return error; + } + fname = fname->next; + } + return 0; +} + +static int ext4_dx_readdir(struct file * filp, + void * dirent, filldir_t filldir) +{ + struct dir_private_info *info = filp->private_data; + struct inode *inode = filp->f_dentry->d_inode; + struct fname *fname; + int ret; + + if (!info) { + info = create_dir_info(filp->f_pos); + if (!info) + return -ENOMEM; + filp->private_data = info; + } + + if (filp->f_pos == EXT4_HTREE_EOF) + return 0; /* EOF */ + + /* Some one has messed with f_pos; reset the world */ + if (info->last_pos != filp->f_pos) { + free_rb_tree_fname(&info->root); + info->curr_node = NULL; + info->extra_fname = NULL; + info->curr_hash = pos2maj_hash(filp->f_pos); + info->curr_minor_hash = pos2min_hash(filp->f_pos); + } + + /* + * If there are any leftover names on the hash collision + * chain, return them first. + */ + if (info->extra_fname && + call_filldir(filp, dirent, filldir, info->extra_fname)) + goto finished; + + if (!info->curr_node) + info->curr_node = rb_first(&info->root); + + while (1) { + /* + * Fill the rbtree if we have no more entries, + * or the inode has changed since we last read in the + * cached entries. + */ + if ((!info->curr_node) || + (filp->f_version != inode->i_version)) { + info->curr_node = NULL; + free_rb_tree_fname(&info->root); + filp->f_version = inode->i_version; + ret = ext4_htree_fill_tree(filp, info->curr_hash, + info->curr_minor_hash, + &info->next_hash); + if (ret < 0) + return ret; + if (ret == 0) { + filp->f_pos = EXT4_HTREE_EOF; + break; + } + info->curr_node = rb_first(&info->root); + } + + fname = rb_entry(info->curr_node, struct fname, rb_hash); + info->curr_hash = fname->hash; + info->curr_minor_hash = fname->minor_hash; + if (call_filldir(filp, dirent, filldir, fname)) + break; + + info->curr_node = rb_next(info->curr_node); + if (!info->curr_node) { + if (info->next_hash == ~0) { + filp->f_pos = EXT4_HTREE_EOF; + break; + } + info->curr_hash = info->next_hash; + info->curr_minor_hash = 0; + } + } +finished: + info->last_pos = filp->f_pos; + return 0; +} + +static int ext4_release_dir (struct inode * inode, struct file * filp) +{ + if (filp->private_data) + ext4_htree_free_dir_info(filp->private_data); + + return 0; +} + +#endif diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c new file mode 100644 index 00000000000..2608dce18f3 --- /dev/null +++ b/fs/ext4/extents.c @@ -0,0 +1,2152 @@ +/* + * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com + * Written by Alex Tomas <alex@clusterfs.com> + * + * Architecture independence: + * Copyright (c) 2005, Bull S.A. + * Written by Pierre Peiffer <pierre.peiffer@bull.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public Licens + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111- + */ + +/* + * Extents support for EXT4 + * + * TODO: + * - ext4*_error() should be used in some situations + * - analyze all BUG()/BUG_ON(), use -EIO where appropriate + * - smart tree reduction + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/time.h> +#include <linux/ext4_jbd2.h> +#include <linux/jbd.h> +#include <linux/smp_lock.h> +#include <linux/highuid.h> +#include <linux/pagemap.h> +#include <linux/quotaops.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/ext4_fs_extents.h> +#include <asm/uaccess.h> + + +/* + * ext_pblock: + * combine low and high parts of physical block number into ext4_fsblk_t + */ +static inline ext4_fsblk_t ext_pblock(struct ext4_extent *ex) +{ + ext4_fsblk_t block; + + block = le32_to_cpu(ex->ee_start); + block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1; + return block; +} + +/* + * idx_pblock: + * combine low and high parts of a leaf physical block number into ext4_fsblk_t + */ +static inline ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix) +{ + ext4_fsblk_t block; + + block = le32_to_cpu(ix->ei_leaf); + block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1; + return block; +} + +/* + * ext4_ext_store_pblock: + * stores a large physical block number into an extent struct, + * breaking it into parts + */ +static inline void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb) +{ + ex->ee_start = cpu_to_le32((unsigned long) (pb & 0xffffffff)); + ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); +} + +/* + * ext4_idx_store_pblock: + * stores a large physical block number into an index struct, + * breaking it into parts + */ +static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb) +{ + ix->ei_leaf = cpu_to_le32((unsigned long) (pb & 0xffffffff)); + ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); +} + +static int ext4_ext_check_header(const char *function, struct inode *inode, + struct ext4_extent_header *eh) +{ + const char *error_msg = NULL; + + if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) { + error_msg = "invalid magic"; + goto corrupted; + } + if (unlikely(eh->eh_max == 0)) { + error_msg = "invalid eh_max"; + goto corrupted; + } + if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) { + error_msg = "invalid eh_entries"; + goto corrupted; + } + return 0; + +corrupted: + ext4_error(inode->i_sb, function, + "bad header in inode #%lu: %s - magic %x, " + "entries %u, max %u, depth %u", + inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic), + le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), + le16_to_cpu(eh->eh_depth)); + + return -EIO; +} + +static handle_t *ext4_ext_journal_restart(handle_t *handle, int needed) +{ + int err; + + if (handle->h_buffer_credits > needed) + return handle; + if (!ext4_journal_extend(handle, needed)) + return handle; + err = ext4_journal_restart(handle, needed); + + return handle; +} + +/* + * could return: + * - EROFS + * - ENOMEM + */ +static int ext4_ext_get_access(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) +{ + if (path->p_bh) { + /* path points to block */ + return ext4_journal_get_write_access(handle, path->p_bh); + } + /* path points to leaf/index in inode body */ + /* we use in-core data, no need to protect them */ + return 0; +} + +/* + * could return: + * - EROFS + * - ENOMEM + * - EIO + */ +static int ext4_ext_dirty(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) +{ + int err; + if (path->p_bh) { + /* path points to block */ + err = ext4_journal_dirty_metadata(handle, path->p_bh); + } else { + /* path points to leaf/index in inode body */ + err = ext4_mark_inode_dirty(handle, inode); + } + return err; +} + +static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, + struct ext4_ext_path *path, + ext4_fsblk_t block) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + ext4_fsblk_t bg_start; + ext4_grpblk_t colour; + int depth; + + if (path) { + struct ext4_extent *ex; + depth = path->p_depth; + + /* try to predict block placement */ + if ((ex = path[depth].p_ext)) + return ext_pblock(ex)+(block-le32_to_cpu(ex->ee_block)); + + /* it looks like index is empty; + * try to find starting block from index itself */ + if (path[depth].p_bh) + return path[depth].p_bh->b_blocknr; + } + + /* OK. use inode's group */ + bg_start = (ei->i_block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) + + le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block); + colour = (current->pid % 16) * + (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); + return bg_start + colour + block; +} + +static ext4_fsblk_t +ext4_ext_new_block(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *ex, int *err) +{ + ext4_fsblk_t goal, newblock; + + goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block)); + newblock = ext4_new_block(handle, inode, goal, err); + return newblock; +} + +static inline int ext4_ext_space_block(struct inode *inode) +{ + int size; + + size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) + / sizeof(struct ext4_extent); +#ifdef AGRESSIVE_TEST + if (size > 6) + size = 6; +#endif + return size; +} + +static inline int ext4_ext_space_block_idx(struct inode *inode) +{ + int size; + + size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) + / sizeof(struct ext4_extent_idx); +#ifdef AGRESSIVE_TEST + if (size > 5) + size = 5; +#endif + return size; +} + +static inline int ext4_ext_space_root(struct inode *inode) +{ + int size; + + size = sizeof(EXT4_I(inode)->i_data); + size -= sizeof(struct ext4_extent_header); + size /= sizeof(struct ext4_extent); +#ifdef AGRESSIVE_TEST + if (size > 3) + size = 3; +#endif + return size; +} + +static inline int ext4_ext_space_root_idx(struct inode *inode) +{ + int size; + + size = sizeof(EXT4_I(inode)->i_data); + size -= sizeof(struct ext4_extent_header); + size /= sizeof(struct ext4_extent_idx); +#ifdef AGRESSIVE_TEST + if (size > 4) + size = 4; +#endif + return size; +} + +#ifdef EXT_DEBUG +static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) +{ + int k, l = path->p_depth; + + ext_debug("path:"); + for (k = 0; k <= l; k++, path++) { + if (path->p_idx) { + ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block), + idx_pblock(path->p_idx)); + } else if (path->p_ext) { + ext_debug(" %d:%d:%llu ", + le32_to_cpu(path->p_ext->ee_block), + le16_to_cpu(path->p_ext->ee_len), + ext_pblock(path->p_ext)); + } else + ext_debug(" []"); + } + ext_debug("\n"); +} + +static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) +{ + int depth = ext_depth(inode); + struct ext4_extent_header *eh; + struct ext4_extent *ex; + int i; + + if (!path) + return; + + eh = path[depth].p_hdr; + ex = EXT_FIRST_EXTENT(eh); + + for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { + ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block), + le16_to_cpu(ex->ee_len), ext_pblock(ex)); + } + ext_debug("\n"); +} +#else +#define ext4_ext_show_path(inode,path) +#define ext4_ext_show_leaf(inode,path) +#endif + +static void ext4_ext_drop_refs(struct ext4_ext_path *path) +{ + int depth = path->p_depth; + int i; + + for (i = 0; i <= depth; i++, path++) + if (path->p_bh) { + brelse(path->p_bh); + path->p_bh = NULL; + } +} + +/* + * ext4_ext_binsearch_idx: + * binary search for the closest index of the given block + */ +static void +ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int block) +{ + struct ext4_extent_header *eh = path->p_hdr; + struct ext4_extent_idx *r, *l, *m; + + BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC); + BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max)); + BUG_ON(le16_to_cpu(eh->eh_entries) <= 0); + + ext_debug("binsearch for %d(idx): ", block); + + l = EXT_FIRST_INDEX(eh) + 1; + r = EXT_FIRST_INDEX(eh) + le16_to_cpu(eh->eh_entries) - 1; + while (l <= r) { + m = l + (r - l) / 2; + if (block < le32_to_cpu(m->ei_block)) + r = m - 1; + else + l = m + 1; + ext_debug("%p(%u):%p(%u):%p(%u) ", l, l->ei_block, + m, m->ei_block, r, r->ei_block); + } + + path->p_idx = l - 1; + ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block), + idx_block(path->p_idx)); + +#ifdef CHECK_BINSEARCH + { + struct ext4_extent_idx *chix, *ix; + int k; + + chix = ix = EXT_FIRST_INDEX(eh); + for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) { + if (k != 0 && + le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) { + printk("k=%d, ix=0x%p, first=0x%p\n", k, + ix, EXT_FIRST_INDEX(eh)); + printk("%u <= %u\n", + le32_to_cpu(ix->ei_block), + le32_to_cpu(ix[-1].ei_block)); + } + BUG_ON(k && le32_to_cpu(ix->ei_block) + <= le32_to_cpu(ix[-1].ei_block)); + if (block < le32_to_cpu(ix->ei_block)) + break; + chix = ix; + } + BUG_ON(chix != path->p_idx); + } +#endif + +} + +/* + * ext4_ext_binsearch: + * binary search for closest extent of the given block + */ +static void +ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block) +{ + struct ext4_extent_header *eh = path->p_hdr; + struct ext4_extent *r, *l, *m; + + BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC); + BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max)); + + if (eh->eh_entries == 0) { + /* + * this leaf is empty: + * we get such a leaf in split/add case + */ + return; + } + + ext_debug("binsearch for %d: ", block); + + l = EXT_FIRST_EXTENT(eh) + 1; + r = EXT_FIRST_EXTENT(eh) + le16_to_cpu(eh->eh_entries) - 1; + + while (l <= r) { + m = l + (r - l) / 2; + if (block < le32_to_cpu(m->ee_block)) + r = m - 1; + else + l = m + 1; + ext_debug("%p(%u):%p(%u):%p(%u) ", l, l->ee_block, + m, m->ee_block, r, r->ee_block); + } + + path->p_ext = l - 1; + ext_debug(" -> %d:%llu:%d ", + le32_to_cpu(path->p_ext->ee_block), + ext_pblock(path->p_ext), + le16_to_cpu(path->p_ext->ee_len)); + +#ifdef CHECK_BINSEARCH + { + struct ext4_extent *chex, *ex; + int k; + + chex = ex = EXT_FIRST_EXTENT(eh); + for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) { + BUG_ON(k && le32_to_cpu(ex->ee_block) + <= le32_to_cpu(ex[-1].ee_block)); + if (block < le32_to_cpu(ex->ee_block)) + break; + chex = ex; + } + BUG_ON(chex != path->p_ext); + } +#endif + +} + +int ext4_ext_tree_init(handle_t *handle, struct inode *inode) +{ + struct ext4_extent_header *eh; + + eh = ext_inode_hdr(inode); + eh->eh_depth = 0; + eh->eh_entries = 0; + eh->eh_magic = EXT4_EXT_MAGIC; + eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode)); + ext4_mark_inode_dirty(handle, inode); + ext4_ext_invalidate_cache(inode); + return 0; +} + +struct ext4_ext_path * +ext4_ext_find_extent(struct inode *inode, int block, struct ext4_ext_path *path) +{ + struct ext4_extent_header *eh; + struct buffer_head *bh; + short int depth, i, ppos = 0, alloc = 0; + + eh = ext_inode_hdr(inode); + BUG_ON(eh == NULL); + if (ext4_ext_check_header(__FUNCTION__, inode, eh)) + return ERR_PTR(-EIO); + + i = depth = ext_depth(inode); + + /* account possible depth increase */ + if (!path) { + path = kmalloc(sizeof(struct ext4_ext_path) * (depth + 2), + GFP_NOFS); + if (!path) + return ERR_PTR(-ENOMEM); + alloc = 1; + } + memset(path, 0, sizeof(struct ext4_ext_path) * (depth + 1)); + path[0].p_hdr = eh; + + /* walk through the tree */ + while (i) { + ext_debug("depth %d: num %d, max %d\n", + ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); + ext4_ext_binsearch_idx(inode, path + ppos, block); + path[ppos].p_block = idx_pblock(path[ppos].p_idx); + path[ppos].p_depth = i; + path[ppos].p_ext = NULL; + + bh = sb_bread(inode->i_sb, path[ppos].p_block); + if (!bh) + goto err; + + eh = ext_block_hdr(bh); + ppos++; + BUG_ON(ppos > depth); + path[ppos].p_bh = bh; + path[ppos].p_hdr = eh; + i--; + + if (ext4_ext_check_header(__FUNCTION__, inode, eh)) + goto err; + } + + path[ppos].p_depth = i; + path[ppos].p_hdr = eh; + path[ppos].p_ext = NULL; + path[ppos].p_idx = NULL; + + if (ext4_ext_check_header(__FUNCTION__, inode, eh)) + goto err; + + /* find extent */ + ext4_ext_binsearch(inode, path + ppos, block); + + ext4_ext_show_path(inode, path); + + return path; + +err: + ext4_ext_drop_refs(path); + if (alloc) + kfree(path); + return ERR_PTR(-EIO); +} + +/* + * ext4_ext_insert_index: + * insert new index [@logical;@ptr] into the block at @curp; + * check where to insert: before @curp or after @curp + */ +static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, + struct ext4_ext_path *curp, + int logical, ext4_fsblk_t ptr) +{ + struct ext4_extent_idx *ix; + int len, err; + + if ((err = ext4_ext_get_access(handle, inode, curp))) + return err; + + BUG_ON(logical == le32_to_cpu(curp->p_idx->ei_block)); + len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx; + if (logical > le32_to_cpu(curp->p_idx->ei_block)) { + /* insert after */ + if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) { + len = (len - 1) * sizeof(struct ext4_extent_idx); + len = len < 0 ? 0 : len; + ext_debug("insert new index %d after: %d. " + "move %d from 0x%p to 0x%p\n", + logical, ptr, len, + (curp->p_idx + 1), (curp->p_idx + 2)); + memmove(curp->p_idx + 2, curp->p_idx + 1, len); + } + ix = curp->p_idx + 1; + } else { + /* insert before */ + len = len * sizeof(struct ext4_extent_idx); + len = len < 0 ? 0 : len; + ext_debug("insert new index %d before: %d. " + "move %d from 0x%p to 0x%p\n", + logical, ptr, len, + curp->p_idx, (curp->p_idx + 1)); + memmove(curp->p_idx + 1, curp->p_idx, len); + ix = curp->p_idx; + } + + ix->ei_block = cpu_to_le32(logical); + ext4_idx_store_pblock(ix, ptr); + curp->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(curp->p_hdr->eh_entries)+1); + + BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries) + > le16_to_cpu(curp->p_hdr->eh_max)); + BUG_ON(ix > EXT_LAST_INDEX(curp->p_hdr)); + + err = ext4_ext_dirty(handle, inode, curp); + ext4_std_error(inode->i_sb, err); + + return err; +} + +/* + * ext4_ext_split: + * inserts new subtree into the path, using free index entry + * at depth @at: + * - allocates all needed blocks (new leaf and all intermediate index blocks) + * - makes decision where to split + * - moves remaining extents and index entries (right to the split point) + * into the newly allocated blocks + * - initializes subtree + */ +static int ext4_ext_split(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *newext, int at) +{ + struct buffer_head *bh = NULL; + int depth = ext_depth(inode); + struct ext4_extent_header *neh; + struct ext4_extent_idx *fidx; + struct ext4_extent *ex; + int i = at, k, m, a; + ext4_fsblk_t newblock, oldblock; + __le32 border; + ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ + int err = 0; + + /* make decision: where to split? */ + /* FIXME: now decision is simplest: at current extent */ + + /* if current leaf will be split, then we should use + * border from split point */ + BUG_ON(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr)); + if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) { + border = path[depth].p_ext[1].ee_block; + ext_debug("leaf will be split." + " next leaf starts at %d\n", + le32_to_cpu(border)); + } else { + border = newext->ee_block; + ext_debug("leaf will be added." + " next leaf starts at %d\n", + le32_to_cpu(border)); + } + + /* + * If error occurs, then we break processing + * and mark filesystem read-only. index won't + * be inserted and tree will be in consistent + * state. Next mount will repair buffers too. + */ + + /* + * Get array to track all allocated blocks. + * We need this to handle errors and free blocks + * upon them. + */ + ablocks = kmalloc(sizeof(ext4_fsblk_t) * depth, GFP_NOFS); + if (!ablocks) + return -ENOMEM; + memset(ablocks, 0, sizeof(ext4_fsblk_t) * depth); + + /* allocate all needed blocks */ + ext_debug("allocate %d blocks for indexes/leaf\n", depth - at); + for (a = 0; a < depth - at; a++) { + newblock = ext4_ext_new_block(handle, inode, path, newext, &err); + if (newblock == 0) + goto cleanup; + ablocks[a] = newblock; + } + + /* initialize new leaf */ + newblock = ablocks[--a]; + BUG_ON(newblock == 0); + bh = sb_getblk(inode->i_sb, newblock); + if (!bh) { + err = -EIO; + goto cleanup; + } + lock_buffer(bh); + + if ((err = ext4_journal_get_create_access(handle, bh))) + goto cleanup; + + neh = ext_block_hdr(bh); + neh->eh_entries = 0; + neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode)); + neh->eh_magic = EXT4_EXT_MAGIC; + neh->eh_depth = 0; + ex = EXT_FIRST_EXTENT(neh); + + /* move remainder of path[depth] to the new leaf */ + BUG_ON(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max); + /* start copy from next extent */ + /* TODO: we could do it by single memmove */ + m = 0; + path[depth].p_ext++; + while (path[depth].p_ext <= + EXT_MAX_EXTENT(path[depth].p_hdr)) { + ext_debug("move %d:%llu:%d in new leaf %llu\n", + le32_to_cpu(path[depth].p_ext->ee_block), + ext_pblock(path[depth].p_ext), + le16_to_cpu(path[depth].p_ext->ee_len), + newblock); + /*memmove(ex++, path[depth].p_ext++, + sizeof(struct ext4_extent)); + neh->eh_entries++;*/ + path[depth].p_ext++; + m++; + } + if (m) { + memmove(ex, path[depth].p_ext-m, sizeof(struct ext4_extent)*m); + neh->eh_entries = cpu_to_le16(le16_to_cpu(neh->eh_entries)+m); + } + + set_buffer_uptodate(bh); + unlock_buffer(bh); + + if ((err = ext4_journal_dirty_metadata(handle, bh))) + goto cleanup; + brelse(bh); + bh = NULL; + + /* correct old leaf */ + if (m) { + if ((err = ext4_ext_get_access(handle, inode, path + depth))) + goto cleanup; + path[depth].p_hdr->eh_entries = + cpu_to_le16(le16_to_cpu(path[depth].p_hdr->eh_entries)-m); + if ((err = ext4_ext_dirty(handle, inode, path + depth))) + goto cleanup; + + } + + /* create intermediate indexes */ + k = depth - at - 1; + BUG_ON(k < 0); + if (k) + ext_debug("create %d intermediate indices\n", k); + /* insert new index into current index block */ + /* current depth stored in i var */ + i = depth - 1; + while (k--) { + oldblock = newblock; + newblock = ablocks[--a]; + bh = sb_getblk(inode->i_sb, (ext4_fsblk_t)newblock); + if (!bh) { + err = -EIO; + goto cleanup; + } + lock_buffer(bh); + + if ((err = ext4_journal_get_create_access(handle, bh))) + goto cleanup; + + neh = ext_block_hdr(bh); + neh->eh_entries = cpu_to_le16(1); + neh->eh_magic = EXT4_EXT_MAGIC; + neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode)); + neh->eh_depth = cpu_to_le16(depth - i); + fidx = EXT_FIRST_INDEX(neh); + fidx->ei_block = border; + ext4_idx_store_pblock(fidx, oldblock); + + ext_debug("int.index at %d (block %llu): %lu -> %llu\n", i, + newblock, (unsigned long) le32_to_cpu(border), + oldblock); + /* copy indexes */ + m = 0; + path[i].p_idx++; + + ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx, + EXT_MAX_INDEX(path[i].p_hdr)); + BUG_ON(EXT_MAX_INDEX(path[i].p_hdr) != + EXT_LAST_INDEX(path[i].p_hdr)); + while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) { + ext_debug("%d: move %d:%d in new index %llu\n", i, + le32_to_cpu(path[i].p_idx->ei_block), + idx_pblock(path[i].p_idx), + newblock); + /*memmove(++fidx, path[i].p_idx++, + sizeof(struct ext4_extent_idx)); + neh->eh_entries++; + BUG_ON(neh->eh_entries > neh->eh_max);*/ + path[i].p_idx++; + m++; + } + if (m) { + memmove(++fidx, path[i].p_idx - m, + sizeof(struct ext4_extent_idx) * m); + neh->eh_entries = + cpu_to_le16(le16_to_cpu(neh->eh_entries) + m); + } + set_buffer_uptodate(bh); + unlock_buffer(bh); + + if ((err = ext4_journal_dirty_metadata(handle, bh))) + goto cleanup; + brelse(bh); + bh = NULL; + + /* correct old index */ + if (m) { + err = ext4_ext_get_access(handle, inode, path + i); + if (err) + goto cleanup; + path[i].p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(path[i].p_hdr->eh_entries)-m); + err = ext4_ext_dirty(handle, inode, path + i); + if (err) + goto cleanup; + } + + i--; + } + + /* insert new index */ + if (err) + goto cleanup; + + err = ext4_ext_insert_index(handle, inode, path + at, + le32_to_cpu(border), newblock); + +cleanup: + if (bh) { + if (buffer_locked(bh)) + unlock_buffer(bh); + brelse(bh); + } + + if (err) { + /* free all allocated blocks in error case */ + for (i = 0; i < depth; i++) { + if (!ablocks[i]) + continue; + ext4_free_blocks(handle, inode, ablocks[i], 1); + } + } + kfree(ablocks); + + return err; +} + +/* + * ext4_ext_grow_indepth: + * implements tree growing procedure: + * - allocates new block + * - moves top-level data (index block or leaf) into the new block + * - initializes new top-level, creating index that points to the + * just created block + */ +static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *newext) +{ + struct ext4_ext_path *curp = path; + struct ext4_extent_header *neh; + struct ext4_extent_idx *fidx; + struct buffer_head *bh; + ext4_fsblk_t newblock; + int err = 0; + + newblock = ext4_ext_new_block(handle, inode, path, newext, &err); + if (newblock == 0) + return err; + + bh = sb_getblk(inode->i_sb, newblock); + if (!bh) { + err = -EIO; + ext4_std_error(inode->i_sb, err); + return err; + } + lock_buffer(bh); + + if ((err = ext4_journal_get_create_access(handle, bh))) { + unlock_buffer(bh); + goto out; + } + + /* move top-level index/leaf into new block */ + memmove(bh->b_data, curp->p_hdr, sizeof(EXT4_I(inode)->i_data)); + + /* set size of new block */ + neh = ext_block_hdr(bh); + /* old root could have indexes or leaves + * so calculate e_max right way */ + if (ext_depth(inode)) + neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode)); + else + neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode)); + neh->eh_magic = EXT4_EXT_MAGIC; + set_buffer_uptodate(bh); + unlock_buffer(bh); + + if ((err = ext4_journal_dirty_metadata(handle, bh))) + goto out; + + /* create index in new top-level index: num,max,pointer */ + if ((err = ext4_ext_get_access(handle, inode, curp))) + goto out; + + curp->p_hdr->eh_magic = EXT4_EXT_MAGIC; + curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode)); + curp->p_hdr->eh_entries = cpu_to_le16(1); + curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr); + /* FIXME: it works, but actually path[0] can be index */ + curp->p_idx->ei_block = EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block; + ext4_idx_store_pblock(curp->p_idx, newblock); + + neh = ext_inode_hdr(inode); + fidx = EXT_FIRST_INDEX(neh); + ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n", + le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max), + le32_to_cpu(fidx->ei_block), idx_pblock(fidx)); + + neh->eh_depth = cpu_to_le16(path->p_depth + 1); + err = ext4_ext_dirty(handle, inode, curp); +out: + brelse(bh); + + return err; +} + +/* + * ext4_ext_create_new_leaf: + * finds empty index and adds new leaf. + * if no free index is found, then it requests in-depth growing. + */ +static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *newext) +{ + struct ext4_ext_path *curp; + int depth, i, err = 0; + +repeat: + i = depth = ext_depth(inode); + + /* walk up to the tree and look for free index entry */ + curp = path + depth; + while (i > 0 && !EXT_HAS_FREE_INDEX(curp)) { + i--; + curp--; + } + + /* we use already allocated block for index block, + * so subsequent data blocks should be contiguous */ + if (EXT_HAS_FREE_INDEX(curp)) { + /* if we found index with free entry, then use that + * entry: create all needed subtree and add new leaf */ + err = ext4_ext_split(handle, inode, path, newext, i); + + /* refill path */ + ext4_ext_drop_refs(path); + path = ext4_ext_find_extent(inode, + le32_to_cpu(newext->ee_block), + path); + if (IS_ERR(path)) + err = PTR_ERR(path); + } else { + /* tree is full, time to grow in depth */ + err = ext4_ext_grow_indepth(handle, inode, path, newext); + if (err) + goto out; + + /* refill path */ + ext4_ext_drop_refs(path); + path = ext4_ext_find_extent(inode, + le32_to_cpu(newext->ee_block), + path); + if (IS_ERR(path)) { + err = PTR_ERR(path); + goto out; + } + + /* + * only first (depth 0 -> 1) produces free space; + * in all other cases we have to split the grown tree + */ + depth = ext_depth(inode); + if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) { + /* now we need to split */ + goto repeat; + } + } + +out: + return err; +} + +/* + * ext4_ext_next_allocated_block: + * returns allocated block in subsequent extent or EXT_MAX_BLOCK. + * NOTE: it considers block number from index entry as + * allocated block. Thus, index entries have to be consistent + * with leaves. + */ +static unsigned long +ext4_ext_next_allocated_block(struct ext4_ext_path *path) +{ + int depth; + + BUG_ON(path == NULL); + depth = path->p_depth; + + if (depth == 0 && path->p_ext == NULL) + return EXT_MAX_BLOCK; + + while (depth >= 0) { + if (depth == path->p_depth) { + /* leaf */ + if (path[depth].p_ext != + EXT_LAST_EXTENT(path[depth].p_hdr)) + return le32_to_cpu(path[depth].p_ext[1].ee_block); + } else { + /* index */ + if (path[depth].p_idx != + EXT_LAST_INDEX(path[depth].p_hdr)) + return le32_to_cpu(path[depth].p_idx[1].ei_block); + } + depth--; + } + + return EXT_MAX_BLOCK; +} + +/* + * ext4_ext_next_leaf_block: + * returns first allocated block from next leaf or EXT_MAX_BLOCK + */ +static unsigned ext4_ext_next_leaf_block(struct inode *inode, + struct ext4_ext_path *path) +{ + int depth; + + BUG_ON(path == NULL); + depth = path->p_depth; + + /* zero-tree has no leaf blocks at all */ + if (depth == 0) + return EXT_MAX_BLOCK; + + /* go to index block */ + depth--; + + while (depth >= 0) { + if (path[depth].p_idx != + EXT_LAST_INDEX(path[depth].p_hdr)) + return le32_to_cpu(path[depth].p_idx[1].ei_block); + depth--; + } + + return EXT_MAX_BLOCK; +} + +/* + * ext4_ext_correct_indexes: + * if leaf gets modified and modified extent is first in the leaf, + * then we have to correct all indexes above. + * TODO: do we need to correct tree in all cases? + */ +int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) +{ + struct ext4_extent_header *eh; + int depth = ext_depth(inode); + struct ext4_extent *ex; + __le32 border; + int k, err = 0; + + eh = path[depth].p_hdr; + ex = path[depth].p_ext; + BUG_ON(ex == NULL); + BUG_ON(eh == NULL); + + if (depth == 0) { + /* there is no tree at all */ + return 0; + } + + if (ex != EXT_FIRST_EXTENT(eh)) { + /* we correct tree if first leaf got modified only */ + return 0; + } + + /* + * TODO: we need correction if border is smaller than current one + */ + k = depth - 1; + border = path[depth].p_ext->ee_block; + if ((err = ext4_ext_get_access(handle, inode, path + k))) + return err; + path[k].p_idx->ei_block = border; + if ((err = ext4_ext_dirty(handle, inode, path + k))) + return err; + + while (k--) { + /* change all left-side indexes */ + if (path[k+1].p_idx != EXT_FIRST_INDEX(path[k+1].p_hdr)) + break; + if ((err = ext4_ext_get_access(handle, inode, path + k))) + break; + path[k].p_idx->ei_block = border; + if ((err = ext4_ext_dirty(handle, inode, path + k))) + break; + } + + return err; +} + +static int inline +ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, + struct ext4_extent *ex2) +{ + if (le32_to_cpu(ex1->ee_block) + le16_to_cpu(ex1->ee_len) != + le32_to_cpu(ex2->ee_block)) + return 0; + + /* + * To allow future support for preallocated extents to be added + * as an RO_COMPAT feature, refuse to merge to extents if + * this can result in the top bit of ee_len being set. + */ + if (le16_to_cpu(ex1->ee_len) + le16_to_cpu(ex2->ee_len) > EXT_MAX_LEN) + return 0; +#ifdef AGRESSIVE_TEST + if (le16_to_cpu(ex1->ee_len) >= 4) + return 0; +#endif + + if (ext_pblock(ex1) + le16_to_cpu(ex1->ee_len) == ext_pblock(ex2)) + return 1; + return 0; +} + +/* + * ext4_ext_insert_extent: + * tries to merge requsted extent into the existing extent or + * inserts requested extent as new one into the tree, + * creating new leaf in the no-space case. + */ +int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *newext) +{ + struct ext4_extent_header * eh; + struct ext4_extent *ex, *fex; + struct ext4_extent *nearex; /* nearest extent */ + struct ext4_ext_path *npath = NULL; + int depth, len, err, next; + + BUG_ON(newext->ee_len == 0); + depth = ext_depth(inode); + ex = path[depth].p_ext; + BUG_ON(path[depth].p_hdr == NULL); + + /* try to insert block into found extent and return */ + if (ex && ext4_can_extents_be_merged(inode, ex, newext)) { + ext_debug("append %d block to %d:%d (from %llu)\n", + le16_to_cpu(newext->ee_len), + le32_to_cpu(ex->ee_block), + le16_to_cpu(ex->ee_len), ext_pblock(ex)); + if ((err = ext4_ext_get_access(handle, inode, path + depth))) + return err; + ex->ee_len = cpu_to_le16(le16_to_cpu(ex->ee_len) + + le16_to_cpu(newext->ee_len)); + eh = path[depth].p_hdr; + nearex = ex; + goto merge; + } + +repeat: + depth = ext_depth(inode); + eh = path[depth].p_hdr; + if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) + goto has_space; + + /* probably next leaf has space for us? */ + fex = EXT_LAST_EXTENT(eh); + next = ext4_ext_next_leaf_block(inode, path); + if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block) + && next != EXT_MAX_BLOCK) { + ext_debug("next leaf block - %d\n", next); + BUG_ON(npath != NULL); + npath = ext4_ext_find_extent(inode, next, NULL); + if (IS_ERR(npath)) + return PTR_ERR(npath); + BUG_ON(npath->p_depth != path->p_depth); + eh = npath[depth].p_hdr; + if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) { + ext_debug("next leaf isnt full(%d)\n", + le16_to_cpu(eh->eh_entries)); + path = npath; + goto repeat; + } + ext_debug("next leaf has no free space(%d,%d)\n", + le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); + } + + /* + * There is no free space in the found leaf. + * We're gonna add a new leaf in the tree. + */ + err = ext4_ext_create_new_leaf(handle, inode, path, newext); + if (err) + goto cleanup; + depth = ext_depth(inode); + eh = path[depth].p_hdr; + +has_space: + nearex = path[depth].p_ext; + + if ((err = ext4_ext_get_access(handle, inode, path + depth))) + goto cleanup; + + if (!nearex) { + /* there is no extent in this leaf, create first one */ + ext_debug("first extent in the leaf: %d:%llu:%d\n", + le32_to_cpu(newext->ee_block), + ext_pblock(newext), + le16_to_cpu(newext->ee_len)); + path[depth].p_ext = EXT_FIRST_EXTENT(eh); + } else if (le32_to_cpu(newext->ee_block) + > le32_to_cpu(nearex->ee_block)) { +/* BUG_ON(newext->ee_block == nearex->ee_block); */ + if (nearex != EXT_LAST_EXTENT(eh)) { + len = EXT_MAX_EXTENT(eh) - nearex; + len = (len - 1) * sizeof(struct ext4_extent); + len = len < 0 ? 0 : len; + ext_debug("insert %d:%llu:%d after: nearest 0x%p, " + "move %d from 0x%p to 0x%p\n", + le32_to_cpu(newext->ee_block), + ext_pblock(newext), + le16_to_cpu(newext->ee_len), + nearex, len, nearex + 1, nearex + 2); + memmove(nearex + 2, nearex + 1, len); + } + path[depth].p_ext = nearex + 1; + } else { + BUG_ON(newext->ee_block == nearex->ee_block); + len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent); + len = len < 0 ? 0 : len; + ext_debug("insert %d:%llu:%d before: nearest 0x%p, " + "move %d from 0x%p to 0x%p\n", + le32_to_cpu(newext->ee_block), + ext_pblock(newext), + le16_to_cpu(newext->ee_len), + nearex, len, nearex + 1, nearex + 2); + memmove(nearex + 1, nearex, len); + path[depth].p_ext = nearex; + } + + eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)+1); + nearex = path[depth].p_ext; + nearex->ee_block = newext->ee_block; + nearex->ee_start = newext->ee_start; + nearex->ee_start_hi = newext->ee_start_hi; + nearex->ee_len = newext->ee_len; + +merge: + /* try to merge extents to the right */ + while (nearex < EXT_LAST_EXTENT(eh)) { + if (!ext4_can_extents_be_merged(inode, nearex, nearex + 1)) + break; + /* merge with next extent! */ + nearex->ee_len = cpu_to_le16(le16_to_cpu(nearex->ee_len) + + le16_to_cpu(nearex[1].ee_len)); + if (nearex + 1 < EXT_LAST_EXTENT(eh)) { + len = (EXT_LAST_EXTENT(eh) - nearex - 1) + * sizeof(struct ext4_extent); + memmove(nearex + 1, nearex + 2, len); + } + eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)-1); + BUG_ON(eh->eh_entries == 0); + } + + /* try to merge extents to the left */ + + /* time to correct all indexes above */ + err = ext4_ext_correct_indexes(handle, inode, path); + if (err) + goto cleanup; + + err = ext4_ext_dirty(handle, inode, path + depth); + +cleanup: + if (npath) { + ext4_ext_drop_refs(npath); + kfree(npath); + } + ext4_ext_tree_changed(inode); + ext4_ext_invalidate_cache(inode); + return err; +} + +int ext4_ext_walk_space(struct inode *inode, unsigned long block, + unsigned long num, ext_prepare_callback func, + void *cbdata) +{ + struct ext4_ext_path *path = NULL; + struct ext4_ext_cache cbex; + struct ext4_extent *ex; + unsigned long next, start = 0, end = 0; + unsigned long last = block + num; + int depth, exists, err = 0; + + BUG_ON(func == NULL); + BUG_ON(inode == NULL); + + while (block < last && block != EXT_MAX_BLOCK) { + num = last - block; + /* find extent for this block */ + path = ext4_ext_find_extent(inode, block, path); + if (IS_ERR(path)) { + err = PTR_ERR(path); + path = NULL; + break; + } + + depth = ext_depth(inode); + BUG_ON(path[depth].p_hdr == NULL); + ex = path[depth].p_ext; + next = ext4_ext_next_allocated_block(path); + + exists = 0; + if (!ex) { + /* there is no extent yet, so try to allocate + * all requested space */ + start = block; + end = block + num; + } else if (le32_to_cpu(ex->ee_block) > block) { + /* need to allocate space before found extent */ + start = block; + end = le32_to_cpu(ex->ee_block); + if (block + num < end) + end = block + num; + } else if (block >= + le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len)) { + /* need to allocate space after found extent */ + start = block; + end = block + num; + if (end >= next) + end = next; + } else if (block >= le32_to_cpu(ex->ee_block)) { + /* + * some part of requested space is covered + * by found extent + */ + start = block; + end = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len); + if (block + num < end) + end = block + num; + exists = 1; + } else { + BUG(); + } + BUG_ON(end <= start); + + if (!exists) { + cbex.ec_block = start; + cbex.ec_len = end - start; + cbex.ec_start = 0; + cbex.ec_type = EXT4_EXT_CACHE_GAP; + } else { + cbex.ec_block = le32_to_cpu(ex->ee_block); + cbex.ec_len = le16_to_cpu(ex->ee_len); + cbex.ec_start = ext_pblock(ex); + cbex.ec_type = EXT4_EXT_CACHE_EXTENT; + } + + BUG_ON(cbex.ec_len == 0); + err = func(inode, path, &cbex, cbdata); + ext4_ext_drop_refs(path); + + if (err < 0) + break; + if (err == EXT_REPEAT) + continue; + else if (err == EXT_BREAK) { + err = 0; + break; + } + + if (ext_depth(inode) != depth) { + /* depth was changed. we have to realloc path */ + kfree(path); + path = NULL; + } + + block = cbex.ec_block + cbex.ec_len; + } + + if (path) { + ext4_ext_drop_refs(path); + kfree(path); + } + + return err; +} + +static inline void +ext4_ext_put_in_cache(struct inode *inode, __u32 block, + __u32 len, __u32 start, int type) +{ + struct ext4_ext_cache *cex; + BUG_ON(len == 0); + cex = &EXT4_I(inode)->i_cached_extent; + cex->ec_type = type; + cex->ec_block = block; + cex->ec_len = len; + cex->ec_start = start; +} + +/* + * ext4_ext_put_gap_in_cache: + * calculate boundaries of the gap that the requested block fits into + * and cache this gap + */ +static inline void +ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, + unsigned long block) +{ + int depth = ext_depth(inode); + unsigned long lblock, len; + struct ext4_extent *ex; + + ex = path[depth].p_ext; + if (ex == NULL) { + /* there is no extent yet, so gap is [0;-] */ + lblock = 0; + len = EXT_MAX_BLOCK; + ext_debug("cache gap(whole file):"); + } else if (block < le32_to_cpu(ex->ee_block)) { + lblock = block; + len = le32_to_cpu(ex->ee_block) - block; + ext_debug("cache gap(before): %lu [%lu:%lu]", + (unsigned long) block, + (unsigned long) le32_to_cpu(ex->ee_block), + (unsigned long) le16_to_cpu(ex->ee_len)); + } else if (block >= le32_to_cpu(ex->ee_block) + + le16_to_cpu(ex->ee_len)) { + lblock = le32_to_cpu(ex->ee_block) + + le16_to_cpu(ex->ee_len); + len = ext4_ext_next_allocated_block(path); + ext_debug("cache gap(after): [%lu:%lu] %lu", + (unsigned long) le32_to_cpu(ex->ee_block), + (unsigned long) le16_to_cpu(ex->ee_len), + (unsigned long) block); + BUG_ON(len == lblock); + len = len - lblock; + } else { + lblock = len = 0; + BUG(); + } + + ext_debug(" -> %lu:%lu\n", (unsigned long) lblock, len); + ext4_ext_put_in_cache(inode, lblock, len, 0, EXT4_EXT_CACHE_GAP); +} + +static inline int +ext4_ext_in_cache(struct inode *inode, unsigned long block, + struct ext4_extent *ex) +{ + struct ext4_ext_cache *cex; + + cex = &EXT4_I(inode)->i_cached_extent; + + /* has cache valid data? */ + if (cex->ec_type == EXT4_EXT_CACHE_NO) + return EXT4_EXT_CACHE_NO; + + BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP && + cex->ec_type != EXT4_EXT_CACHE_EXTENT); + if (block >= cex->ec_block && block < cex->ec_block + cex->ec_len) { + ex->ee_block = cpu_to_le32(cex->ec_block); + ext4_ext_store_pblock(ex, cex->ec_start); + ex->ee_len = cpu_to_le16(cex->ec_len); + ext_debug("%lu cached by %lu:%lu:%llu\n", + (unsigned long) block, + (unsigned long) cex->ec_block, + (unsigned long) cex->ec_len, + cex->ec_start); + return cex->ec_type; + } + + /* not in cache */ + return EXT4_EXT_CACHE_NO; +} + +/* + * ext4_ext_rm_idx: + * removes index from the index block. + * It's used in truncate case only, thus all requests are for + * last index in the block only. + */ +int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) +{ + struct buffer_head *bh; + int err; + ext4_fsblk_t leaf; + + /* free index block */ + path--; + leaf = idx_pblock(path->p_idx); + BUG_ON(path->p_hdr->eh_entries == 0); + if ((err = ext4_ext_get_access(handle, inode, path))) + return err; + path->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(path->p_hdr->eh_entries)-1); + if ((err = ext4_ext_dirty(handle, inode, path))) + return err; + ext_debug("index is empty, remove it, free block %llu\n", leaf); + bh = sb_find_get_block(inode->i_sb, leaf); + ext4_forget(handle, 1, inode, bh, leaf); + ext4_free_blocks(handle, inode, leaf, 1); + return err; +} + +/* + * ext4_ext_calc_credits_for_insert: + * This routine returns max. credits that the extent tree can consume. + * It should be OK for low-performance paths like ->writepage() + * To allow many writing processes to fit into a single transaction, + * the caller should calculate credits under truncate_mutex and + * pass the actual path. + */ +int inline ext4_ext_calc_credits_for_insert(struct inode *inode, + struct ext4_ext_path *path) +{ + int depth, needed; + + if (path) { + /* probably there is space in leaf? */ + depth = ext_depth(inode); + if (le16_to_cpu(path[depth].p_hdr->eh_entries) + < le16_to_cpu(path[depth].p_hdr->eh_max)) + return 1; + } + + /* + * given 32-bit logical block (4294967296 blocks), max. tree + * can be 4 levels in depth -- 4 * 340^4 == 53453440000. + * Let's also add one more level for imbalance. + */ + depth = 5; + + /* allocation of new data block(s) */ + needed = 2; + + /* + * tree can be full, so it would need to grow in depth: + * allocation + old root + new root + */ + needed += 2 + 1 + 1; + + /* + * Index split can happen, we would need: + * allocate intermediate indexes (bitmap + group) + * + change two blocks at each level, but root (already included) + */ + needed = (depth * 2) + (depth * 2); + + /* any allocation modifies superblock */ + needed += 1; + + return needed; +} + +static int ext4_remove_blocks(handle_t *handle, struct inode *inode, + struct ext4_extent *ex, + unsigned long from, unsigned long to) +{ + struct buffer_head *bh; + int i; + +#ifdef EXTENTS_STATS + { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + unsigned short ee_len = le16_to_cpu(ex->ee_len); + spin_lock(&sbi->s_ext_stats_lock); + sbi->s_ext_blocks += ee_len; + sbi->s_ext_extents++; + if (ee_len < sbi->s_ext_min) + sbi->s_ext_min = ee_len; + if (ee_len > sbi->s_ext_max) + sbi->s_ext_max = ee_len; + if (ext_depth(inode) > sbi->s_depth_max) + sbi->s_depth_max = ext_depth(inode); + spin_unlock(&sbi->s_ext_stats_lock); + } +#endif + if (from >= le32_to_cpu(ex->ee_block) + && to == le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) { + /* tail removal */ + unsigned long num; + ext4_fsblk_t start; + num = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - from; + start = ext_pblock(ex) + le16_to_cpu(ex->ee_len) - num; + ext_debug("free last %lu blocks starting %llu\n", num, start); + for (i = 0; i < num; i++) { + bh = sb_find_get_block(inode->i_sb, start + i); + ext4_forget(handle, 0, inode, bh, start + i); + } + ext4_free_blocks(handle, inode, start, num); + } else if (from == le32_to_cpu(ex->ee_block) + && to <= le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) { + printk("strange request: removal %lu-%lu from %u:%u\n", + from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len)); + } else { + printk("strange request: removal(2) %lu-%lu from %u:%u\n", + from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len)); + } + return 0; +} + +static int +ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, unsigned long start) +{ + int err = 0, correct_index = 0; + int depth = ext_depth(inode), credits; + struct ext4_extent_header *eh; + unsigned a, b, block, num; + unsigned long ex_ee_block; + unsigned short ex_ee_len; + struct ext4_extent *ex; + + ext_debug("truncate since %lu in leaf\n", start); + if (!path[depth].p_hdr) + path[depth].p_hdr = ext_block_hdr(path[depth].p_bh); + eh = path[depth].p_hdr; + BUG_ON(eh == NULL); + BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max)); + BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC); + + /* find where to start removing */ + ex = EXT_LAST_EXTENT(eh); + + ex_ee_block = le32_to_cpu(ex->ee_block); + ex_ee_len = le16_to_cpu(ex->ee_len); + + while (ex >= EXT_FIRST_EXTENT(eh) && + ex_ee_block + ex_ee_len > start) { + ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len); + path[depth].p_ext = ex; + + a = ex_ee_block > start ? ex_ee_block : start; + b = ex_ee_block + ex_ee_len - 1 < EXT_MAX_BLOCK ? + ex_ee_block + ex_ee_len - 1 : EXT_MAX_BLOCK; + + ext_debug(" border %u:%u\n", a, b); + + if (a != ex_ee_block && b != ex_ee_block + ex_ee_len - 1) { + block = 0; + num = 0; + BUG(); + } else if (a != ex_ee_block) { + /* remove tail of the extent */ + block = ex_ee_block; + num = a - block; + } else if (b != ex_ee_block + ex_ee_len - 1) { + /* remove head of the extent */ + block = a; + num = b - a; + /* there is no "make a hole" API yet */ + BUG(); + } else { + /* remove whole extent: excellent! */ + block = ex_ee_block; + num = 0; + BUG_ON(a != ex_ee_block); + BUG_ON(b != ex_ee_block + ex_ee_len - 1); + } + + /* at present, extent can't cross block group: */ + /* leaf + bitmap + group desc + sb + inode */ + credits = 5; + if (ex == EXT_FIRST_EXTENT(eh)) { + correct_index = 1; + credits += (ext_depth(inode)) + 1; + } +#ifdef CONFIG_QUOTA + credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); +#endif + + handle = ext4_ext_journal_restart(handle, credits); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out; + } + + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + + err = ext4_remove_blocks(handle, inode, ex, a, b); + if (err) + goto out; + + if (num == 0) { + /* this extent is removed; mark slot entirely unused */ + ext4_ext_store_pblock(ex, 0); + eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)-1); + } + + ex->ee_block = cpu_to_le32(block); + ex->ee_len = cpu_to_le16(num); + + err = ext4_ext_dirty(handle, inode, path + depth); + if (err) + goto out; + + ext_debug("new extent: %u:%u:%llu\n", block, num, + ext_pblock(ex)); + ex--; + ex_ee_block = le32_to_cpu(ex->ee_block); + ex_ee_len = le16_to_cpu(ex->ee_len); + } + + if (correct_index && eh->eh_entries) + err = ext4_ext_correct_indexes(handle, inode, path); + + /* if this leaf is free, then we should + * remove it from index block above */ + if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL) + err = ext4_ext_rm_idx(handle, inode, path + depth); + +out: + return err; +} + +/* + * ext4_ext_more_to_rm: + * returns 1 if current index has to be freed (even partial) + */ +static int inline +ext4_ext_more_to_rm(struct ext4_ext_path *path) +{ + BUG_ON(path->p_idx == NULL); + + if (path->p_idx < EXT_FIRST_INDEX(path->p_hdr)) + return 0; + + /* + * if truncate on deeper level happened, it wasn't partial, + * so we have to consider current index for truncation + */ + if (le16_to_cpu(path->p_hdr->eh_entries) == path->p_block) + return 0; + return 1; +} + +int ext4_ext_remove_space(struct inode *inode, unsigned long start) +{ + struct super_block *sb = inode->i_sb; + int depth = ext_depth(inode); + struct ext4_ext_path *path; + handle_t *handle; + int i = 0, err = 0; + + ext_debug("truncate since %lu\n", start); + + /* probably first extent we're gonna free will be last in block */ + handle = ext4_journal_start(inode, depth + 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + ext4_ext_invalidate_cache(inode); + + /* + * We start scanning from right side, freeing all the blocks + * after i_size and walking into the tree depth-wise. + */ + path = kmalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_KERNEL); + if (path == NULL) { + ext4_journal_stop(handle); + return -ENOMEM; + } + memset(path, 0, sizeof(struct ext4_ext_path) * (depth + 1)); + path[0].p_hdr = ext_inode_hdr(inode); + if (ext4_ext_check_header(__FUNCTION__, inode, path[0].p_hdr)) { + err = -EIO; + goto out; + } + path[0].p_depth = depth; + + while (i >= 0 && err == 0) { + if (i == depth) { + /* this is leaf block */ + err = ext4_ext_rm_leaf(handle, inode, path, start); + /* root level has p_bh == NULL, brelse() eats this */ + brelse(path[i].p_bh); + path[i].p_bh = NULL; + i--; + continue; + } + + /* this is index block */ + if (!path[i].p_hdr) { + ext_debug("initialize header\n"); + path[i].p_hdr = ext_block_hdr(path[i].p_bh); + if (ext4_ext_check_header(__FUNCTION__, inode, + path[i].p_hdr)) { + err = -EIO; + goto out; + } + } + + BUG_ON(le16_to_cpu(path[i].p_hdr->eh_entries) + > le16_to_cpu(path[i].p_hdr->eh_max)); + BUG_ON(path[i].p_hdr->eh_magic != EXT4_EXT_MAGIC); + + if (!path[i].p_idx) { + /* this level hasn't been touched yet */ + path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr); + path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1; + ext_debug("init index ptr: hdr 0x%p, num %d\n", + path[i].p_hdr, + le16_to_cpu(path[i].p_hdr->eh_entries)); + } else { + /* we were already here, see at next index */ + path[i].p_idx--; + } + + ext_debug("level %d - index, first 0x%p, cur 0x%p\n", + i, EXT_FIRST_INDEX(path[i].p_hdr), + path[i].p_idx); + if (ext4_ext_more_to_rm(path + i)) { + /* go to the next level */ + ext_debug("move to level %d (block %llu)\n", + i + 1, idx_pblock(path[i].p_idx)); + memset(path + i + 1, 0, sizeof(*path)); + path[i+1].p_bh = + sb_bread(sb, idx_pblock(path[i].p_idx)); + if (!path[i+1].p_bh) { + /* should we reset i_size? */ + err = -EIO; + break; + } + + /* save actual number of indexes since this + * number is changed at the next iteration */ + path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries); + i++; + } else { + /* we finished processing this index, go up */ + if (path[i].p_hdr->eh_entries == 0 && i > 0) { + /* index is empty, remove it; + * handle must be already prepared by the + * truncatei_leaf() */ + err = ext4_ext_rm_idx(handle, inode, path + i); + } + /* root level has p_bh == NULL, brelse() eats this */ + brelse(path[i].p_bh); + path[i].p_bh = NULL; + i--; + ext_debug("return to level %d\n", i); + } + } + + /* TODO: flexible tree reduction should be here */ + if (path->p_hdr->eh_entries == 0) { + /* + * truncate to zero freed all the tree, + * so we need to correct eh_depth + */ + err = ext4_ext_get_access(handle, inode, path); + if (err == 0) { + ext_inode_hdr(inode)->eh_depth = 0; + ext_inode_hdr(inode)->eh_max = + cpu_to_le16(ext4_ext_space_root(inode)); + err = ext4_ext_dirty(handle, inode, path); + } + } +out: + ext4_ext_tree_changed(inode); + ext4_ext_drop_refs(path); + kfree(path); + ext4_journal_stop(handle); + + return err; +} + +/* + * called at mount time + */ +void ext4_ext_init(struct super_block *sb) +{ + /* + * possible initialization would be here + */ + + if (test_opt(sb, EXTENTS)) { + printk("EXT4-fs: file extents enabled"); +#ifdef AGRESSIVE_TEST + printk(", agressive tests"); +#endif +#ifdef CHECK_BINSEARCH + printk(", check binsearch"); +#endif +#ifdef EXTENTS_STATS + printk(", stats"); +#endif + printk("\n"); +#ifdef EXTENTS_STATS + spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock); + EXT4_SB(sb)->s_ext_min = 1 << 30; + EXT4_SB(sb)->s_ext_max = 0; +#endif + } +} + +/* + * called at umount time + */ +void ext4_ext_release(struct super_block *sb) +{ + if (!test_opt(sb, EXTENTS)) + return; + +#ifdef EXTENTS_STATS + if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) { + struct ext4_sb_info *sbi = EXT4_SB(sb); + printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n", + sbi->s_ext_blocks, sbi->s_ext_extents, + sbi->s_ext_blocks / sbi->s_ext_extents); + printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n", + sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max); + } +#endif +} + +int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, + ext4_fsblk_t iblock, + unsigned long max_blocks, struct buffer_head *bh_result, + int create, int extend_disksize) +{ + struct ext4_ext_path *path = NULL; + struct ext4_extent newex, *ex; + ext4_fsblk_t goal, newblock; + int err = 0, depth; + unsigned long allocated = 0; + + __clear_bit(BH_New, &bh_result->b_state); + ext_debug("blocks %d/%lu requested for inode %u\n", (int) iblock, + max_blocks, (unsigned) inode->i_ino); + mutex_lock(&EXT4_I(inode)->truncate_mutex); + + /* check in cache */ + if ((goal = ext4_ext_in_cache(inode, iblock, &newex))) { + if (goal == EXT4_EXT_CACHE_GAP) { + if (!create) { + /* block isn't allocated yet and + * user doesn't want to allocate it */ + goto out2; + } + /* we should allocate requested block */ + } else if (goal == EXT4_EXT_CACHE_EXTENT) { + /* block is already allocated */ + newblock = iblock + - le32_to_cpu(newex.ee_block) + + ext_pblock(&newex); + /* number of remaining blocks in the extent */ + allocated = le16_to_cpu(newex.ee_len) - + (iblock - le32_to_cpu(newex.ee_block)); + goto out; + } else { + BUG(); + } + } + + /* find extent for this block */ + path = ext4_ext_find_extent(inode, iblock, NULL); + if (IS_ERR(path)) { + err = PTR_ERR(path); + path = NULL; + goto out2; + } + + depth = ext_depth(inode); + + /* + * consistent leaf must not be empty; + * this situation is possible, though, _during_ tree modification; + * this is why assert can't be put in ext4_ext_find_extent() + */ + BUG_ON(path[depth].p_ext == NULL && depth != 0); + + if ((ex = path[depth].p_ext)) { + unsigned long ee_block = le32_to_cpu(ex->ee_block); + ext4_fsblk_t ee_start = ext_pblock(ex); + unsigned short ee_len = le16_to_cpu(ex->ee_len); + + /* + * Allow future support for preallocated extents to be added + * as an RO_COMPAT feature: + * Uninitialized extents are treated as holes, except that + * we avoid (fail) allocating new blocks during a write. + */ + if (ee_len > EXT_MAX_LEN) + goto out2; + /* if found extent covers block, simply return it */ + if (iblock >= ee_block && iblock < ee_block + ee_len) { + newblock = iblock - ee_block + ee_start; + /* number of remaining blocks in the extent */ + allocated = ee_len - (iblock - ee_block); + ext_debug("%d fit into %lu:%d -> %llu\n", (int) iblock, + ee_block, ee_len, newblock); + ext4_ext_put_in_cache(inode, ee_block, ee_len, + ee_start, EXT4_EXT_CACHE_EXTENT); + goto out; + } + } + + /* + * requested block isn't allocated yet; + * we couldn't try to create block if create flag is zero + */ + if (!create) { + /* put just found gap into cache to speed up + * subsequent requests */ + ext4_ext_put_gap_in_cache(inode, path, iblock); + goto out2; + } + /* + * Okay, we need to do block allocation. Lazily initialize the block + * allocation info here if necessary. + */ + if (S_ISREG(inode->i_mode) && (!EXT4_I(inode)->i_block_alloc_info)) + ext4_init_block_alloc_info(inode); + + /* allocate new block */ + goal = ext4_ext_find_goal(inode, path, iblock); + allocated = max_blocks; + newblock = ext4_new_blocks(handle, inode, goal, &allocated, &err); + if (!newblock) + goto out2; + ext_debug("allocate new block: goal %llu, found %llu/%lu\n", + goal, newblock, allocated); + + /* try to insert new extent into found leaf and return */ + newex.ee_block = cpu_to_le32(iblock); + ext4_ext_store_pblock(&newex, newblock); + newex.ee_len = cpu_to_le16(allocated); + err = ext4_ext_insert_extent(handle, inode, path, &newex); + if (err) + goto out2; + + if (extend_disksize && inode->i_size > EXT4_I(inode)->i_disksize) + EXT4_I(inode)->i_disksize = inode->i_size; + + /* previous routine could use block we allocated */ + newblock = ext_pblock(&newex); + __set_bit(BH_New, &bh_result->b_state); + + ext4_ext_put_in_cache(inode, iblock, allocated, newblock, + EXT4_EXT_CACHE_EXTENT); +out: + if (allocated > max_blocks) + allocated = max_blocks; + ext4_ext_show_leaf(inode, path); + __set_bit(BH_Mapped, &bh_result->b_state); + bh_result->b_bdev = inode->i_sb->s_bdev; + bh_result->b_blocknr = newblock; +out2: + if (path) { + ext4_ext_drop_refs(path); + kfree(path); + } + mutex_unlock(&EXT4_I(inode)->truncate_mutex); + + return err ? err : allocated; +} + +void ext4_ext_truncate(struct inode * inode, struct page *page) +{ + struct address_space *mapping = inode->i_mapping; + struct super_block *sb = inode->i_sb; + unsigned long last_block; + handle_t *handle; + int err = 0; + + /* + * probably first extent we're gonna free will be last in block + */ + err = ext4_writepage_trans_blocks(inode) + 3; + handle = ext4_journal_start(inode, err); + if (IS_ERR(handle)) { + if (page) { + clear_highpage(page); + flush_dcache_page(page); + unlock_page(page); + page_cache_release(page); + } + return; + } + + if (page) + ext4_block_truncate_page(handle, page, mapping, inode->i_size); + + mutex_lock(&EXT4_I(inode)->truncate_mutex); + ext4_ext_invalidate_cache(inode); + + /* + * TODO: optimization is possible here. + * Probably we need not scan at all, + * because page truncation is enough. + */ + if (ext4_orphan_add(handle, inode)) + goto out_stop; + + /* we have to know where to truncate from in crash case */ + EXT4_I(inode)->i_disksize = inode->i_size; + ext4_mark_inode_dirty(handle, inode); + + last_block = (inode->i_size + sb->s_blocksize - 1) + >> EXT4_BLOCK_SIZE_BITS(sb); + err = ext4_ext_remove_space(inode, last_block); + + /* In a multi-transaction truncate, we only make the final + * transaction synchronous. */ + if (IS_SYNC(inode)) + handle->h_sync = 1; + +out_stop: + /* + * If this was a simple ftruncate() and the file will remain alive, + * then we need to clear up the orphan record which we created above. + * However, if this was a real unlink then we were called by + * ext4_delete_inode(), and we allow that function to clean up the + * orphan info for us. + */ + if (inode->i_nlink) + ext4_orphan_del(handle, inode); + + mutex_unlock(&EXT4_I(inode)->truncate_mutex); + ext4_journal_stop(handle); +} + +/* + * ext4_ext_writepage_trans_blocks: + * calculate max number of blocks we could modify + * in order to allocate new block for an inode + */ +int ext4_ext_writepage_trans_blocks(struct inode *inode, int num) +{ + int needed; + + needed = ext4_ext_calc_credits_for_insert(inode, NULL); + + /* caller wants to allocate num blocks, but note it includes sb */ + needed = needed * num - (num - 1); + +#ifdef CONFIG_QUOTA + needed += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); +#endif + + return needed; +} + +EXPORT_SYMBOL(ext4_mark_inode_dirty); +EXPORT_SYMBOL(ext4_ext_invalidate_cache); +EXPORT_SYMBOL(ext4_ext_insert_extent); +EXPORT_SYMBOL(ext4_ext_walk_space); +EXPORT_SYMBOL(ext4_ext_find_goal); +EXPORT_SYMBOL(ext4_ext_calc_credits_for_insert); + diff --git a/fs/ext4/file.c b/fs/ext4/file.c new file mode 100644 index 00000000000..0b622c0624b --- /dev/null +++ b/fs/ext4/file.c @@ -0,0 +1,139 @@ +/* + * linux/fs/ext4/file.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/file.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * ext4 fs regular file handling primitives + * + * 64-bit file support on 64-bit platforms by Jakub Jelinek + * (jj@sunsite.ms.mff.cuni.cz) + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/ext4_jbd2.h> +#include "xattr.h" +#include "acl.h" + +/* + * Called when an inode is released. Note that this is different + * from ext4_file_open: open gets called at every open, but release + * gets called only when /all/ the files are closed. + */ +static int ext4_release_file (struct inode * inode, struct file * filp) +{ + /* if we are the last writer on the inode, drop the block reservation */ + if ((filp->f_mode & FMODE_WRITE) && + (atomic_read(&inode->i_writecount) == 1)) + { + mutex_lock(&EXT4_I(inode)->truncate_mutex); + ext4_discard_reservation(inode); + mutex_unlock(&EXT4_I(inode)->truncate_mutex); + } + if (is_dx(inode) && filp->private_data) + ext4_htree_free_dir_info(filp->private_data); + + return 0; +} + +static ssize_t +ext4_file_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_dentry->d_inode; + ssize_t ret; + int err; + + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); + + /* + * Skip flushing if there was an error, or if nothing was written. + */ + if (ret <= 0) + return ret; + + /* + * If the inode is IS_SYNC, or is O_SYNC and we are doing data + * journalling then we need to make sure that we force the transaction + * to disk to keep all metadata uptodate synchronously. + */ + if (file->f_flags & O_SYNC) { + /* + * If we are non-data-journaled, then the dirty data has + * already been flushed to backing store by generic_osync_inode, + * and the inode has been flushed too if there have been any + * modifications other than mere timestamp updates. + * + * Open question --- do we care about flushing timestamps too + * if the inode is IS_SYNC? + */ + if (!ext4_should_journal_data(inode)) + return ret; + + goto force_commit; + } + + /* + * So we know that there has been no forced data flush. If the inode + * is marked IS_SYNC, we need to force one ourselves. + */ + if (!IS_SYNC(inode)) + return ret; + + /* + * Open question #2 --- should we force data to disk here too? If we + * don't, the only impact is that data=writeback filesystems won't + * flush data to disk automatically on IS_SYNC, only metadata (but + * historically, that is what ext2 has done.) + */ + +force_commit: + err = ext4_force_commit(inode->i_sb); + if (err) + return err; + return ret; +} + +const struct file_operations ext4_file_operations = { + .llseek = generic_file_llseek, + .read = do_sync_read, + .write = do_sync_write, + .aio_read = generic_file_aio_read, + .aio_write = ext4_file_write, + .ioctl = ext4_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ext4_compat_ioctl, +#endif + .mmap = generic_file_mmap, + .open = generic_file_open, + .release = ext4_release_file, + .fsync = ext4_sync_file, + .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, + .splice_write = generic_file_splice_write, +}; + +struct inode_operations ext4_file_inode_operations = { + .truncate = ext4_truncate, + .setattr = ext4_setattr, +#ifdef CONFIG_EXT4DEV_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext4_listxattr, + .removexattr = generic_removexattr, +#endif + .permission = ext4_permission, +}; + diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c new file mode 100644 index 00000000000..2a167d7131f --- /dev/null +++ b/fs/ext4/fsync.c @@ -0,0 +1,88 @@ +/* + * linux/fs/ext4/fsync.c + * + * Copyright (C) 1993 Stephen Tweedie (sct@redhat.com) + * from + * Copyright (C) 1992 Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * from + * linux/fs/minix/truncate.c Copyright (C) 1991, 1992 Linus Torvalds + * + * ext4fs fsync primitive + * + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + * + * Removed unnecessary code duplication for little endian machines + * and excessive __inline__s. + * Andi Kleen, 1997 + * + * Major simplications and cleanup - we only need to do the metadata, because + * we can depend on generic_block_fdatasync() to sync the data blocks. + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/sched.h> +#include <linux/writeback.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/ext4_jbd2.h> + +/* + * akpm: A new design for ext4_sync_file(). + * + * This is only called from sys_fsync(), sys_fdatasync() and sys_msync(). + * There cannot be a transaction open by this task. + * Another task could have dirtied this inode. Its data can be in any + * state in the journalling system. + * + * What we do is just kick off a commit and wait on it. This will snapshot the + * inode to disk. + */ + +int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync) +{ + struct inode *inode = dentry->d_inode; + int ret = 0; + + J_ASSERT(ext4_journal_current_handle() == 0); + + /* + * data=writeback: + * The caller's filemap_fdatawrite()/wait will sync the data. + * sync_inode() will sync the metadata + * + * data=ordered: + * The caller's filemap_fdatawrite() will write the data and + * sync_inode() will write the inode if it is dirty. Then the caller's + * filemap_fdatawait() will wait on the pages. + * + * data=journal: + * filemap_fdatawrite won't do anything (the buffers are clean). + * ext4_force_commit will write the file data into the journal and + * will wait on that. + * filemap_fdatawait() will encounter a ton of newly-dirtied pages + * (they were dirtied by commit). But that's OK - the blocks are + * safe in-journal, which is all fsync() needs to ensure. + */ + if (ext4_should_journal_data(inode)) { + ret = ext4_force_commit(inode->i_sb); + goto out; + } + + /* + * The VFS has written the file data. If the inode is unaltered + * then we need not start a commit. + */ + if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, /* sys_fsync did this */ + }; + ret = sync_inode(inode, &wbc); + } +out: + return ret; +} diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c new file mode 100644 index 00000000000..a67966385e0 --- /dev/null +++ b/fs/ext4/hash.c @@ -0,0 +1,152 @@ +/* + * linux/fs/ext4/hash.c + * + * Copyright (C) 2002 by Theodore Ts'o + * + * This file is released under the GPL v2. + * + * This file may be redistributed under the terms of the GNU Public + * License. + */ + +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/sched.h> +#include <linux/ext4_fs.h> +#include <linux/cryptohash.h> + +#define DELTA 0x9E3779B9 + +static void TEA_transform(__u32 buf[4], __u32 const in[]) +{ + __u32 sum = 0; + __u32 b0 = buf[0], b1 = buf[1]; + __u32 a = in[0], b = in[1], c = in[2], d = in[3]; + int n = 16; + + do { + sum += DELTA; + b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b); + b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d); + } while(--n); + + buf[0] += b0; + buf[1] += b1; +} + + +/* The old legacy hash */ +static __u32 dx_hack_hash (const char *name, int len) +{ + __u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9; + while (len--) { + __u32 hash = hash1 + (hash0 ^ (*name++ * 7152373)); + + if (hash & 0x80000000) hash -= 0x7fffffff; + hash1 = hash0; + hash0 = hash; + } + return (hash0 << 1); +} + +static void str2hashbuf(const char *msg, int len, __u32 *buf, int num) +{ + __u32 pad, val; + int i; + + pad = (__u32)len | ((__u32)len << 8); + pad |= pad << 16; + + val = pad; + if (len > num*4) + len = num * 4; + for (i=0; i < len; i++) { + if ((i % 4) == 0) + val = pad; + val = msg[i] + (val << 8); + if ((i % 4) == 3) { + *buf++ = val; + val = pad; + num--; + } + } + if (--num >= 0) + *buf++ = val; + while (--num >= 0) + *buf++ = pad; +} + +/* + * Returns the hash of a filename. If len is 0 and name is NULL, then + * this function can be used to test whether or not a hash version is + * supported. + * + * The seed is an 4 longword (32 bits) "secret" which can be used to + * uniquify a hash. If the seed is all zero's, then some default seed + * may be used. + * + * A particular hash version specifies whether or not the seed is + * represented, and whether or not the returned hash is 32 bits or 64 + * bits. 32 bit hashes will return 0 for the minor hash. + */ +int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo) +{ + __u32 hash; + __u32 minor_hash = 0; + const char *p; + int i; + __u32 in[8], buf[4]; + + /* Initialize the default seed for the hash checksum functions */ + buf[0] = 0x67452301; + buf[1] = 0xefcdab89; + buf[2] = 0x98badcfe; + buf[3] = 0x10325476; + + /* Check to see if the seed is all zero's */ + if (hinfo->seed) { + for (i=0; i < 4; i++) { + if (hinfo->seed[i]) + break; + } + if (i < 4) + memcpy(buf, hinfo->seed, sizeof(buf)); + } + + switch (hinfo->hash_version) { + case DX_HASH_LEGACY: + hash = dx_hack_hash(name, len); + break; + case DX_HASH_HALF_MD4: + p = name; + while (len > 0) { + str2hashbuf(p, len, in, 8); + half_md4_transform(buf, in); + len -= 32; + p += 32; + } + minor_hash = buf[2]; + hash = buf[1]; + break; + case DX_HASH_TEA: + p = name; + while (len > 0) { + str2hashbuf(p, len, in, 4); + TEA_transform(buf, in); + len -= 16; + p += 16; + } + hash = buf[0]; + minor_hash = buf[1]; + break; + default: + hinfo->hash = 0; + return -1; + } + hash = hash & ~1; + if (hash == (EXT4_HTREE_EOF << 1)) + hash = (EXT4_HTREE_EOF-1) << 1; + hinfo->hash = hash; + hinfo->minor_hash = minor_hash; + return 0; +} diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c new file mode 100644 index 00000000000..c88b439ba5c --- /dev/null +++ b/fs/ext4/ialloc.c @@ -0,0 +1,772 @@ +/* + * linux/fs/ext4/ialloc.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * BSD ufs-inspired inode and directory allocation by + * Stephen Tweedie (sct@redhat.com), 1993 + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/ext4_jbd2.h> +#include <linux/stat.h> +#include <linux/string.h> +#include <linux/quotaops.h> +#include <linux/buffer_head.h> +#include <linux/random.h> +#include <linux/bitops.h> +#include <linux/blkdev.h> +#include <asm/byteorder.h> + +#include "xattr.h" +#include "acl.h" + +/* + * ialloc.c contains the inodes allocation and deallocation routines + */ + +/* + * The free inodes are managed by bitmaps. A file system contains several + * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap + * block for inodes, N blocks for the inode table and data blocks. + * + * The file system contains group descriptors which are located after the + * super block. Each descriptor contains the number of the bitmap block and + * the free blocks count in the block. + */ + + +/* + * Read the inode allocation bitmap for a given block_group, reading + * into the specified slot in the superblock's bitmap cache. + * + * Return buffer_head of bitmap on success or NULL. + */ +static struct buffer_head * +read_inode_bitmap(struct super_block * sb, unsigned long block_group) +{ + struct ext4_group_desc *desc; + struct buffer_head *bh = NULL; + + desc = ext4_get_group_desc(sb, block_group, NULL); + if (!desc) + goto error_out; + + bh = sb_bread(sb, ext4_inode_bitmap(sb, desc)); + if (!bh) + ext4_error(sb, "read_inode_bitmap", + "Cannot read inode bitmap - " + "block_group = %lu, inode_bitmap = %llu", + block_group, ext4_inode_bitmap(sb, desc)); +error_out: + return bh; +} + +/* + * NOTE! When we get the inode, we're the only people + * that have access to it, and as such there are no + * race conditions we have to worry about. The inode + * is not on the hash-lists, and it cannot be reached + * through the filesystem because the directory entry + * has been deleted earlier. + * + * HOWEVER: we must make sure that we get no aliases, + * which means that we have to call "clear_inode()" + * _before_ we mark the inode not in use in the inode + * bitmaps. Otherwise a newly created file might use + * the same inode number (not actually the same pointer + * though), and then we'd have two inodes sharing the + * same inode number and space on the harddisk. + */ +void ext4_free_inode (handle_t *handle, struct inode * inode) +{ + struct super_block * sb = inode->i_sb; + int is_directory; + unsigned long ino; + struct buffer_head *bitmap_bh = NULL; + struct buffer_head *bh2; + unsigned long block_group; + unsigned long bit; + struct ext4_group_desc * gdp; + struct ext4_super_block * es; + struct ext4_sb_info *sbi; + int fatal = 0, err; + + if (atomic_read(&inode->i_count) > 1) { + printk ("ext4_free_inode: inode has count=%d\n", + atomic_read(&inode->i_count)); + return; + } + if (inode->i_nlink) { + printk ("ext4_free_inode: inode has nlink=%d\n", + inode->i_nlink); + return; + } + if (!sb) { + printk("ext4_free_inode: inode on nonexistent device\n"); + return; + } + sbi = EXT4_SB(sb); + + ino = inode->i_ino; + ext4_debug ("freeing inode %lu\n", ino); + + /* + * Note: we must free any quota before locking the superblock, + * as writing the quota to disk may need the lock as well. + */ + DQUOT_INIT(inode); + ext4_xattr_delete_inode(handle, inode); + DQUOT_FREE_INODE(inode); + DQUOT_DROP(inode); + + is_directory = S_ISDIR(inode->i_mode); + + /* Do this BEFORE marking the inode not in use or returning an error */ + clear_inode (inode); + + es = EXT4_SB(sb)->s_es; + if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { + ext4_error (sb, "ext4_free_inode", + "reserved or nonexistent inode %lu", ino); + goto error_return; + } + block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); + bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); + bitmap_bh = read_inode_bitmap(sb, block_group); + if (!bitmap_bh) + goto error_return; + + BUFFER_TRACE(bitmap_bh, "get_write_access"); + fatal = ext4_journal_get_write_access(handle, bitmap_bh); + if (fatal) + goto error_return; + + /* Ok, now we can actually update the inode bitmaps.. */ + if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group), + bit, bitmap_bh->b_data)) + ext4_error (sb, "ext4_free_inode", + "bit already cleared for inode %lu", ino); + else { + gdp = ext4_get_group_desc (sb, block_group, &bh2); + + BUFFER_TRACE(bh2, "get_write_access"); + fatal = ext4_journal_get_write_access(handle, bh2); + if (fatal) goto error_return; + + if (gdp) { + spin_lock(sb_bgl_lock(sbi, block_group)); + gdp->bg_free_inodes_count = cpu_to_le16( + le16_to_cpu(gdp->bg_free_inodes_count) + 1); + if (is_directory) + gdp->bg_used_dirs_count = cpu_to_le16( + le16_to_cpu(gdp->bg_used_dirs_count) - 1); + spin_unlock(sb_bgl_lock(sbi, block_group)); + percpu_counter_inc(&sbi->s_freeinodes_counter); + if (is_directory) + percpu_counter_dec(&sbi->s_dirs_counter); + + } + BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, bh2); + if (!fatal) fatal = err; + } + BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, bitmap_bh); + if (!fatal) + fatal = err; + sb->s_dirt = 1; +error_return: + brelse(bitmap_bh); + ext4_std_error(sb, fatal); +} + +/* + * There are two policies for allocating an inode. If the new inode is + * a directory, then a forward search is made for a block group with both + * free space and a low directory-to-inode ratio; if that fails, then of + * the groups with above-average free space, that group with the fewest + * directories already is chosen. + * + * For other inodes, search forward from the parent directory\'s block + * group to find a free inode. + */ +static int find_group_dir(struct super_block *sb, struct inode *parent) +{ + int ngroups = EXT4_SB(sb)->s_groups_count; + unsigned int freei, avefreei; + struct ext4_group_desc *desc, *best_desc = NULL; + struct buffer_head *bh; + int group, best_group = -1; + + freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter); + avefreei = freei / ngroups; + + for (group = 0; group < ngroups; group++) { + desc = ext4_get_group_desc (sb, group, &bh); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) + continue; + if (!best_desc || + (le16_to_cpu(desc->bg_free_blocks_count) > + le16_to_cpu(best_desc->bg_free_blocks_count))) { + best_group = group; + best_desc = desc; + } + } + return best_group; +} + +/* + * Orlov's allocator for directories. + * + * We always try to spread first-level directories. + * + * If there are blockgroups with both free inodes and free blocks counts + * not worse than average we return one with smallest directory count. + * Otherwise we simply return a random group. + * + * For the rest rules look so: + * + * It's OK to put directory into a group unless + * it has too many directories already (max_dirs) or + * it has too few free inodes left (min_inodes) or + * it has too few free blocks left (min_blocks) or + * it's already running too large debt (max_debt). + * Parent's group is prefered, if it doesn't satisfy these + * conditions we search cyclically through the rest. If none + * of the groups look good we just look for a group with more + * free inodes than average (starting at parent's group). + * + * Debt is incremented each time we allocate a directory and decremented + * when we allocate an inode, within 0--255. + */ + +#define INODE_COST 64 +#define BLOCK_COST 256 + +static int find_group_orlov(struct super_block *sb, struct inode *parent) +{ + int parent_group = EXT4_I(parent)->i_block_group; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + int ngroups = sbi->s_groups_count; + int inodes_per_group = EXT4_INODES_PER_GROUP(sb); + unsigned int freei, avefreei; + ext4_fsblk_t freeb, avefreeb; + ext4_fsblk_t blocks_per_dir; + unsigned int ndirs; + int max_debt, max_dirs, min_inodes; + ext4_grpblk_t min_blocks; + int group = -1, i; + struct ext4_group_desc *desc; + struct buffer_head *bh; + + freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); + avefreei = freei / ngroups; + freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter); + avefreeb = freeb; + do_div(avefreeb, ngroups); + ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); + + if ((parent == sb->s_root->d_inode) || + (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) { + int best_ndir = inodes_per_group; + int best_group = -1; + + get_random_bytes(&group, sizeof(group)); + parent_group = (unsigned)group % ngroups; + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext4_get_group_desc (sb, group, &bh); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) + continue; + if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb) + continue; + best_group = group; + best_ndir = le16_to_cpu(desc->bg_used_dirs_count); + } + if (best_group >= 0) + return best_group; + goto fallback; + } + + blocks_per_dir = ext4_blocks_count(es) - freeb; + do_div(blocks_per_dir, ndirs); + + max_dirs = ndirs / ngroups + inodes_per_group / 16; + min_inodes = avefreei - inodes_per_group / 4; + min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb) / 4; + + max_debt = EXT4_BLOCKS_PER_GROUP(sb); + max_debt /= max_t(int, blocks_per_dir, BLOCK_COST); + if (max_debt * INODE_COST > inodes_per_group) + max_debt = inodes_per_group / INODE_COST; + if (max_debt > 255) + max_debt = 255; + if (max_debt == 0) + max_debt = 1; + + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext4_get_group_desc (sb, group, &bh); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes) + continue; + if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks) + continue; + return group; + } + +fallback: + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext4_get_group_desc (sb, group, &bh); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei) + return group; + } + + if (avefreei) { + /* + * The free-inodes counter is approximate, and for really small + * filesystems the above test can fail to find any blockgroups + */ + avefreei = 0; + goto fallback; + } + + return -1; +} + +static int find_group_other(struct super_block *sb, struct inode *parent) +{ + int parent_group = EXT4_I(parent)->i_block_group; + int ngroups = EXT4_SB(sb)->s_groups_count; + struct ext4_group_desc *desc; + struct buffer_head *bh; + int group, i; + + /* + * Try to place the inode in its parent directory + */ + group = parent_group; + desc = ext4_get_group_desc (sb, group, &bh); + if (desc && le16_to_cpu(desc->bg_free_inodes_count) && + le16_to_cpu(desc->bg_free_blocks_count)) + return group; + + /* + * We're going to place this inode in a different blockgroup from its + * parent. We want to cause files in a common directory to all land in + * the same blockgroup. But we want files which are in a different + * directory which shares a blockgroup with our parent to land in a + * different blockgroup. + * + * So add our directory's i_ino into the starting point for the hash. + */ + group = (group + parent->i_ino) % ngroups; + + /* + * Use a quadratic hash to find a group with a free inode and some free + * blocks. + */ + for (i = 1; i < ngroups; i <<= 1) { + group += i; + if (group >= ngroups) + group -= ngroups; + desc = ext4_get_group_desc (sb, group, &bh); + if (desc && le16_to_cpu(desc->bg_free_inodes_count) && + le16_to_cpu(desc->bg_free_blocks_count)) + return group; + } + + /* + * That failed: try linear search for a free inode, even if that group + * has no free blocks. + */ + group = parent_group; + for (i = 0; i < ngroups; i++) { + if (++group >= ngroups) + group = 0; + desc = ext4_get_group_desc (sb, group, &bh); + if (desc && le16_to_cpu(desc->bg_free_inodes_count)) + return group; + } + + return -1; +} + +/* + * There are two policies for allocating an inode. If the new inode is + * a directory, then a forward search is made for a block group with both + * free space and a low directory-to-inode ratio; if that fails, then of + * the groups with above-average free space, that group with the fewest + * directories already is chosen. + * + * For other inodes, search forward from the parent directory's block + * group to find a free inode. + */ +struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode) +{ + struct super_block *sb; + struct buffer_head *bitmap_bh = NULL; + struct buffer_head *bh2; + int group; + unsigned long ino = 0; + struct inode * inode; + struct ext4_group_desc * gdp = NULL; + struct ext4_super_block * es; + struct ext4_inode_info *ei; + struct ext4_sb_info *sbi; + int err = 0; + struct inode *ret; + int i; + + /* Cannot create files in a deleted directory */ + if (!dir || !dir->i_nlink) + return ERR_PTR(-EPERM); + + sb = dir->i_sb; + inode = new_inode(sb); + if (!inode) + return ERR_PTR(-ENOMEM); + ei = EXT4_I(inode); + + sbi = EXT4_SB(sb); + es = sbi->s_es; + if (S_ISDIR(mode)) { + if (test_opt (sb, OLDALLOC)) + group = find_group_dir(sb, dir); + else + group = find_group_orlov(sb, dir); + } else + group = find_group_other(sb, dir); + + err = -ENOSPC; + if (group == -1) + goto out; + + for (i = 0; i < sbi->s_groups_count; i++) { + err = -EIO; + + gdp = ext4_get_group_desc(sb, group, &bh2); + if (!gdp) + goto fail; + + brelse(bitmap_bh); + bitmap_bh = read_inode_bitmap(sb, group); + if (!bitmap_bh) + goto fail; + + ino = 0; + +repeat_in_this_group: + ino = ext4_find_next_zero_bit((unsigned long *) + bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino); + if (ino < EXT4_INODES_PER_GROUP(sb)) { + + BUFFER_TRACE(bitmap_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, bitmap_bh); + if (err) + goto fail; + + if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group), + ino, bitmap_bh->b_data)) { + /* we won it */ + BUFFER_TRACE(bitmap_bh, + "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, + bitmap_bh); + if (err) + goto fail; + goto got; + } + /* we lost it */ + jbd2_journal_release_buffer(handle, bitmap_bh); + + if (++ino < EXT4_INODES_PER_GROUP(sb)) + goto repeat_in_this_group; + } + + /* + * This case is possible in concurrent environment. It is very + * rare. We cannot repeat the find_group_xxx() call because + * that will simply return the same blockgroup, because the + * group descriptor metadata has not yet been updated. + * So we just go onto the next blockgroup. + */ + if (++group == sbi->s_groups_count) + group = 0; + } + err = -ENOSPC; + goto out; + +got: + ino += group * EXT4_INODES_PER_GROUP(sb) + 1; + if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { + ext4_error (sb, "ext4_new_inode", + "reserved inode or inode > inodes count - " + "block_group = %d, inode=%lu", group, ino); + err = -EIO; + goto fail; + } + + BUFFER_TRACE(bh2, "get_write_access"); + err = ext4_journal_get_write_access(handle, bh2); + if (err) goto fail; + spin_lock(sb_bgl_lock(sbi, group)); + gdp->bg_free_inodes_count = + cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1); + if (S_ISDIR(mode)) { + gdp->bg_used_dirs_count = + cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1); + } + spin_unlock(sb_bgl_lock(sbi, group)); + BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, bh2); + if (err) goto fail; + + percpu_counter_dec(&sbi->s_freeinodes_counter); + if (S_ISDIR(mode)) + percpu_counter_inc(&sbi->s_dirs_counter); + sb->s_dirt = 1; + + inode->i_uid = current->fsuid; + if (test_opt (sb, GRPID)) + inode->i_gid = dir->i_gid; + else if (dir->i_mode & S_ISGID) { + inode->i_gid = dir->i_gid; + if (S_ISDIR(mode)) + mode |= S_ISGID; + } else + inode->i_gid = current->fsgid; + inode->i_mode = mode; + + inode->i_ino = ino; + /* This is the optimal IO size (for stat), not the fs block size */ + inode->i_blocks = 0; + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; + + memset(ei->i_data, 0, sizeof(ei->i_data)); + ei->i_dir_start_lookup = 0; + ei->i_disksize = 0; + + ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL; + if (S_ISLNK(mode)) + ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL); + /* dirsync only applies to directories */ + if (!S_ISDIR(mode)) + ei->i_flags &= ~EXT4_DIRSYNC_FL; +#ifdef EXT4_FRAGMENTS + ei->i_faddr = 0; + ei->i_frag_no = 0; + ei->i_frag_size = 0; +#endif + ei->i_file_acl = 0; + ei->i_dir_acl = 0; + ei->i_dtime = 0; + ei->i_block_alloc_info = NULL; + ei->i_block_group = group; + + ext4_set_inode_flags(inode); + if (IS_DIRSYNC(inode)) + handle->h_sync = 1; + insert_inode_hash(inode); + spin_lock(&sbi->s_next_gen_lock); + inode->i_generation = sbi->s_next_generation++; + spin_unlock(&sbi->s_next_gen_lock); + + ei->i_state = EXT4_STATE_NEW; + ei->i_extra_isize = + (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) ? + sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE : 0; + + ret = inode; + if(DQUOT_ALLOC_INODE(inode)) { + err = -EDQUOT; + goto fail_drop; + } + + err = ext4_init_acl(handle, inode, dir); + if (err) + goto fail_free_drop; + + err = ext4_init_security(handle,inode, dir); + if (err) + goto fail_free_drop; + + err = ext4_mark_inode_dirty(handle, inode); + if (err) { + ext4_std_error(sb, err); + goto fail_free_drop; + } + if (test_opt(sb, EXTENTS)) { + EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL; + ext4_ext_tree_init(handle, inode); + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { + err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); + if (err) goto fail; + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS); + BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh); + } + } + + ext4_debug("allocating inode %lu\n", inode->i_ino); + goto really_out; +fail: + ext4_std_error(sb, err); +out: + iput(inode); + ret = ERR_PTR(err); +really_out: + brelse(bitmap_bh); + return ret; + +fail_free_drop: + DQUOT_FREE_INODE(inode); + +fail_drop: + DQUOT_DROP(inode); + inode->i_flags |= S_NOQUOTA; + inode->i_nlink = 0; + iput(inode); + brelse(bitmap_bh); + return ERR_PTR(err); +} + +/* Verify that we are loading a valid orphan from disk */ +struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) +{ + unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count); + unsigned long block_group; + int bit; + struct buffer_head *bitmap_bh = NULL; + struct inode *inode = NULL; + + /* Error cases - e2fsck has already cleaned up for us */ + if (ino > max_ino) { + ext4_warning(sb, __FUNCTION__, + "bad orphan ino %lu! e2fsck was run?", ino); + goto out; + } + + block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); + bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); + bitmap_bh = read_inode_bitmap(sb, block_group); + if (!bitmap_bh) { + ext4_warning(sb, __FUNCTION__, + "inode bitmap error for orphan %lu", ino); + goto out; + } + + /* Having the inode bit set should be a 100% indicator that this + * is a valid orphan (no e2fsck run on fs). Orphans also include + * inodes that were being truncated, so we can't check i_nlink==0. + */ + if (!ext4_test_bit(bit, bitmap_bh->b_data) || + !(inode = iget(sb, ino)) || is_bad_inode(inode) || + NEXT_ORPHAN(inode) > max_ino) { + ext4_warning(sb, __FUNCTION__, + "bad orphan inode %lu! e2fsck was run?", ino); + printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n", + bit, (unsigned long long)bitmap_bh->b_blocknr, + ext4_test_bit(bit, bitmap_bh->b_data)); + printk(KERN_NOTICE "inode=%p\n", inode); + if (inode) { + printk(KERN_NOTICE "is_bad_inode(inode)=%d\n", + is_bad_inode(inode)); + printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n", + NEXT_ORPHAN(inode)); + printk(KERN_NOTICE "max_ino=%lu\n", max_ino); + } + /* Avoid freeing blocks if we got a bad deleted inode */ + if (inode && inode->i_nlink == 0) + inode->i_blocks = 0; + iput(inode); + inode = NULL; + } +out: + brelse(bitmap_bh); + return inode; +} + +unsigned long ext4_count_free_inodes (struct super_block * sb) +{ + unsigned long desc_count; + struct ext4_group_desc *gdp; + int i; +#ifdef EXT4FS_DEBUG + struct ext4_super_block *es; + unsigned long bitmap_count, x; + struct buffer_head *bitmap_bh = NULL; + + es = EXT4_SB(sb)->s_es; + desc_count = 0; + bitmap_count = 0; + gdp = NULL; + for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + gdp = ext4_get_group_desc (sb, i, NULL); + if (!gdp) + continue; + desc_count += le16_to_cpu(gdp->bg_free_inodes_count); + brelse(bitmap_bh); + bitmap_bh = read_inode_bitmap(sb, i); + if (!bitmap_bh) + continue; + + x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); + printk("group %d: stored = %d, counted = %lu\n", + i, le16_to_cpu(gdp->bg_free_inodes_count), x); + bitmap_count += x; + } + brelse(bitmap_bh); + printk("ext4_count_free_inodes: stored = %u, computed = %lu, %lu\n", + le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count); + return desc_count; +#else + desc_count = 0; + for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + gdp = ext4_get_group_desc (sb, i, NULL); + if (!gdp) + continue; + desc_count += le16_to_cpu(gdp->bg_free_inodes_count); + cond_resched(); + } + return desc_count; +#endif +} + +/* Called at mount-time, super-block is locked */ +unsigned long ext4_count_dirs (struct super_block * sb) +{ + unsigned long count = 0; + int i; + + for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) { + struct ext4_group_desc *gdp = ext4_get_group_desc (sb, i, NULL); + if (!gdp) + continue; + count += le16_to_cpu(gdp->bg_used_dirs_count); + } + return count; +} + diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c new file mode 100644 index 00000000000..0a60ec5a16d --- /dev/null +++ b/fs/ext4/inode.c @@ -0,0 +1,3233 @@ +/* + * linux/fs/ext4/inode.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/inode.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Goal-directed block allocation by Stephen Tweedie + * (sct@redhat.com), 1993, 1998 + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + * 64-bit file support on 64-bit platforms by Jakub Jelinek + * (jj@sunsite.ms.mff.cuni.cz) + * + * Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000 + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/time.h> +#include <linux/ext4_jbd2.h> +#include <linux/jbd2.h> +#include <linux/smp_lock.h> +#include <linux/highuid.h> +#include <linux/pagemap.h> +#include <linux/quotaops.h> +#include <linux/string.h> +#include <linux/buffer_head.h> +#include <linux/writeback.h> +#include <linux/mpage.h> +#include <linux/uio.h> +#include <linux/bio.h> +#include "xattr.h" +#include "acl.h" + +/* + * Test whether an inode is a fast symlink. + */ +static int ext4_inode_is_fast_symlink(struct inode *inode) +{ + int ea_blocks = EXT4_I(inode)->i_file_acl ? + (inode->i_sb->s_blocksize >> 9) : 0; + + return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); +} + +/* + * The ext4 forget function must perform a revoke if we are freeing data + * which has been journaled. Metadata (eg. indirect blocks) must be + * revoked in all cases. + * + * "bh" may be NULL: a metadata block may have been freed from memory + * but there may still be a record of it in the journal, and that record + * still needs to be revoked. + */ +int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t blocknr) +{ + int err; + + might_sleep(); + + BUFFER_TRACE(bh, "enter"); + + jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, " + "data mode %lx\n", + bh, is_metadata, inode->i_mode, + test_opt(inode->i_sb, DATA_FLAGS)); + + /* Never use the revoke function if we are doing full data + * journaling: there is no need to, and a V1 superblock won't + * support it. Otherwise, only skip the revoke on un-journaled + * data blocks. */ + + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA || + (!is_metadata && !ext4_should_journal_data(inode))) { + if (bh) { + BUFFER_TRACE(bh, "call jbd2_journal_forget"); + return ext4_journal_forget(handle, bh); + } + return 0; + } + + /* + * data!=journal && (is_metadata || should_journal_data(inode)) + */ + BUFFER_TRACE(bh, "call ext4_journal_revoke"); + err = ext4_journal_revoke(handle, blocknr, bh); + if (err) + ext4_abort(inode->i_sb, __FUNCTION__, + "error %d when attempting revoke", err); + BUFFER_TRACE(bh, "exit"); + return err; +} + +/* + * Work out how many blocks we need to proceed with the next chunk of a + * truncate transaction. + */ +static unsigned long blocks_for_truncate(struct inode *inode) +{ + unsigned long needed; + + needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9); + + /* Give ourselves just enough room to cope with inodes in which + * i_blocks is corrupt: we've seen disk corruptions in the past + * which resulted in random data in an inode which looked enough + * like a regular file for ext4 to try to delete it. Things + * will go a bit crazy if that happens, but at least we should + * try not to panic the whole kernel. */ + if (needed < 2) + needed = 2; + + /* But we need to bound the transaction so we don't overflow the + * journal. */ + if (needed > EXT4_MAX_TRANS_DATA) + needed = EXT4_MAX_TRANS_DATA; + + return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed; +} + +/* + * Truncate transactions can be complex and absolutely huge. So we need to + * be able to restart the transaction at a conventient checkpoint to make + * sure we don't overflow the journal. + * + * start_transaction gets us a new handle for a truncate transaction, + * and extend_transaction tries to extend the existing one a bit. If + * extend fails, we need to propagate the failure up and restart the + * transaction in the top-level truncate loop. --sct + */ +static handle_t *start_transaction(struct inode *inode) +{ + handle_t *result; + + result = ext4_journal_start(inode, blocks_for_truncate(inode)); + if (!IS_ERR(result)) + return result; + + ext4_std_error(inode->i_sb, PTR_ERR(result)); + return result; +} + +/* + * Try to extend this transaction for the purposes of truncation. + * + * Returns 0 if we managed to create more room. If we can't create more + * room, and the transaction must be restarted we return 1. + */ +static int try_to_extend_transaction(handle_t *handle, struct inode *inode) +{ + if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS) + return 0; + if (!ext4_journal_extend(handle, blocks_for_truncate(inode))) + return 0; + return 1; +} + +/* + * Restart the transaction associated with *handle. This does a commit, + * so before we call here everything must be consistently dirtied against + * this transaction. + */ +static int ext4_journal_test_restart(handle_t *handle, struct inode *inode) +{ + jbd_debug(2, "restarting handle %p\n", handle); + return ext4_journal_restart(handle, blocks_for_truncate(inode)); +} + +/* + * Called at the last iput() if i_nlink is zero. + */ +void ext4_delete_inode (struct inode * inode) +{ + handle_t *handle; + + truncate_inode_pages(&inode->i_data, 0); + + if (is_bad_inode(inode)) + goto no_delete; + + handle = start_transaction(inode); + if (IS_ERR(handle)) { + /* + * If we're going to skip the normal cleanup, we still need to + * make sure that the in-core orphan linked list is properly + * cleaned up. + */ + ext4_orphan_del(NULL, inode); + goto no_delete; + } + + if (IS_SYNC(inode)) + handle->h_sync = 1; + inode->i_size = 0; + if (inode->i_blocks) + ext4_truncate(inode); + /* + * Kill off the orphan record which ext4_truncate created. + * AKPM: I think this can be inside the above `if'. + * Note that ext4_orphan_del() has to be able to cope with the + * deletion of a non-existent orphan - this is because we don't + * know if ext4_truncate() actually created an orphan record. + * (Well, we could do this if we need to, but heck - it works) + */ + ext4_orphan_del(handle, inode); + EXT4_I(inode)->i_dtime = get_seconds(); + + /* + * One subtle ordering requirement: if anything has gone wrong + * (transaction abort, IO errors, whatever), then we can still + * do these next steps (the fs will already have been marked as + * having errors), but we can't free the inode if the mark_dirty + * fails. + */ + if (ext4_mark_inode_dirty(handle, inode)) + /* If that failed, just do the required in-core inode clear. */ + clear_inode(inode); + else + ext4_free_inode(handle, inode); + ext4_journal_stop(handle); + return; +no_delete: + clear_inode(inode); /* We must guarantee clearing of inode... */ +} + +typedef struct { + __le32 *p; + __le32 key; + struct buffer_head *bh; +} Indirect; + +static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v) +{ + p->key = *(p->p = v); + p->bh = bh; +} + +static int verify_chain(Indirect *from, Indirect *to) +{ + while (from <= to && from->key == *from->p) + from++; + return (from > to); +} + +/** + * ext4_block_to_path - parse the block number into array of offsets + * @inode: inode in question (we are only interested in its superblock) + * @i_block: block number to be parsed + * @offsets: array to store the offsets in + * @boundary: set this non-zero if the referred-to block is likely to be + * followed (on disk) by an indirect block. + * + * To store the locations of file's data ext4 uses a data structure common + * for UNIX filesystems - tree of pointers anchored in the inode, with + * data blocks at leaves and indirect blocks in intermediate nodes. + * This function translates the block number into path in that tree - + * return value is the path length and @offsets[n] is the offset of + * pointer to (n+1)th node in the nth one. If @block is out of range + * (negative or too large) warning is printed and zero returned. + * + * Note: function doesn't find node addresses, so no IO is needed. All + * we need to know is the capacity of indirect blocks (taken from the + * inode->i_sb). + */ + +/* + * Portability note: the last comparison (check that we fit into triple + * indirect block) is spelled differently, because otherwise on an + * architecture with 32-bit longs and 8Kb pages we might get into trouble + * if our filesystem had 8Kb blocks. We might use long long, but that would + * kill us on x86. Oh, well, at least the sign propagation does not matter - + * i_block would have to be negative in the very beginning, so we would not + * get there at all. + */ + +static int ext4_block_to_path(struct inode *inode, + long i_block, int offsets[4], int *boundary) +{ + int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb); + int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb); + const long direct_blocks = EXT4_NDIR_BLOCKS, + indirect_blocks = ptrs, + double_blocks = (1 << (ptrs_bits * 2)); + int n = 0; + int final = 0; + + if (i_block < 0) { + ext4_warning (inode->i_sb, "ext4_block_to_path", "block < 0"); + } else if (i_block < direct_blocks) { + offsets[n++] = i_block; + final = direct_blocks; + } else if ( (i_block -= direct_blocks) < indirect_blocks) { + offsets[n++] = EXT4_IND_BLOCK; + offsets[n++] = i_block; + final = ptrs; + } else if ((i_block -= indirect_blocks) < double_blocks) { + offsets[n++] = EXT4_DIND_BLOCK; + offsets[n++] = i_block >> ptrs_bits; + offsets[n++] = i_block & (ptrs - 1); + final = ptrs; + } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) { + offsets[n++] = EXT4_TIND_BLOCK; + offsets[n++] = i_block >> (ptrs_bits * 2); + offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1); + offsets[n++] = i_block & (ptrs - 1); + final = ptrs; + } else { + ext4_warning(inode->i_sb, "ext4_block_to_path", "block > big"); + } + if (boundary) + *boundary = final - 1 - (i_block & (ptrs - 1)); + return n; +} + +/** + * ext4_get_branch - read the chain of indirect blocks leading to data + * @inode: inode in question + * @depth: depth of the chain (1 - direct pointer, etc.) + * @offsets: offsets of pointers in inode/indirect blocks + * @chain: place to store the result + * @err: here we store the error value + * + * Function fills the array of triples <key, p, bh> and returns %NULL + * if everything went OK or the pointer to the last filled triple + * (incomplete one) otherwise. Upon the return chain[i].key contains + * the number of (i+1)-th block in the chain (as it is stored in memory, + * i.e. little-endian 32-bit), chain[i].p contains the address of that + * number (it points into struct inode for i==0 and into the bh->b_data + * for i>0) and chain[i].bh points to the buffer_head of i-th indirect + * block for i>0 and NULL for i==0. In other words, it holds the block + * numbers of the chain, addresses they were taken from (and where we can + * verify that chain did not change) and buffer_heads hosting these + * numbers. + * + * Function stops when it stumbles upon zero pointer (absent block) + * (pointer to last triple returned, *@err == 0) + * or when it gets an IO error reading an indirect block + * (ditto, *@err == -EIO) + * or when it notices that chain had been changed while it was reading + * (ditto, *@err == -EAGAIN) + * or when it reads all @depth-1 indirect blocks successfully and finds + * the whole chain, all way to the data (returns %NULL, *err == 0). + */ +static Indirect *ext4_get_branch(struct inode *inode, int depth, int *offsets, + Indirect chain[4], int *err) +{ + struct super_block *sb = inode->i_sb; + Indirect *p = chain; + struct buffer_head *bh; + + *err = 0; + /* i_data is not going away, no lock needed */ + add_chain (chain, NULL, EXT4_I(inode)->i_data + *offsets); + if (!p->key) + goto no_block; + while (--depth) { + bh = sb_bread(sb, le32_to_cpu(p->key)); + if (!bh) + goto failure; + /* Reader: pointers */ + if (!verify_chain(chain, p)) + goto changed; + add_chain(++p, bh, (__le32*)bh->b_data + *++offsets); + /* Reader: end */ + if (!p->key) + goto no_block; + } + return NULL; + +changed: + brelse(bh); + *err = -EAGAIN; + goto no_block; +failure: + *err = -EIO; +no_block: + return p; +} + +/** + * ext4_find_near - find a place for allocation with sufficient locality + * @inode: owner + * @ind: descriptor of indirect block. + * + * This function returns the prefered place for block allocation. + * It is used when heuristic for sequential allocation fails. + * Rules are: + * + if there is a block to the left of our position - allocate near it. + * + if pointer will live in indirect block - allocate near that block. + * + if pointer will live in inode - allocate in the same + * cylinder group. + * + * In the latter case we colour the starting block by the callers PID to + * prevent it from clashing with concurrent allocations for a different inode + * in the same block group. The PID is used here so that functionally related + * files will be close-by on-disk. + * + * Caller must make sure that @ind is valid and will stay that way. + */ +static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + __le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data; + __le32 *p; + ext4_fsblk_t bg_start; + ext4_grpblk_t colour; + + /* Try to find previous block */ + for (p = ind->p - 1; p >= start; p--) { + if (*p) + return le32_to_cpu(*p); + } + + /* No such thing, so let's try location of indirect block */ + if (ind->bh) + return ind->bh->b_blocknr; + + /* + * It is going to be referred to from the inode itself? OK, just put it + * into the same cylinder group then. + */ + bg_start = ext4_group_first_block_no(inode->i_sb, ei->i_block_group); + colour = (current->pid % 16) * + (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); + return bg_start + colour; +} + +/** + * ext4_find_goal - find a prefered place for allocation. + * @inode: owner + * @block: block we want + * @chain: chain of indirect blocks + * @partial: pointer to the last triple within a chain + * @goal: place to store the result. + * + * Normally this function find the prefered place for block allocation, + * stores it in *@goal and returns zero. + */ + +static ext4_fsblk_t ext4_find_goal(struct inode *inode, long block, + Indirect chain[4], Indirect *partial) +{ + struct ext4_block_alloc_info *block_i; + + block_i = EXT4_I(inode)->i_block_alloc_info; + + /* + * try the heuristic for sequential allocation, + * failing that at least try to get decent locality. + */ + if (block_i && (block == block_i->last_alloc_logical_block + 1) + && (block_i->last_alloc_physical_block != 0)) { + return block_i->last_alloc_physical_block + 1; + } + + return ext4_find_near(inode, partial); +} + +/** + * ext4_blks_to_allocate: Look up the block map and count the number + * of direct blocks need to be allocated for the given branch. + * + * @branch: chain of indirect blocks + * @k: number of blocks need for indirect blocks + * @blks: number of data blocks to be mapped. + * @blocks_to_boundary: the offset in the indirect block + * + * return the total number of blocks to be allocate, including the + * direct and indirect blocks. + */ +static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned long blks, + int blocks_to_boundary) +{ + unsigned long count = 0; + + /* + * Simple case, [t,d]Indirect block(s) has not allocated yet + * then it's clear blocks on that path have not allocated + */ + if (k > 0) { + /* right now we don't handle cross boundary allocation */ + if (blks < blocks_to_boundary + 1) + count += blks; + else + count += blocks_to_boundary + 1; + return count; + } + + count++; + while (count < blks && count <= blocks_to_boundary && + le32_to_cpu(*(branch[0].p + count)) == 0) { + count++; + } + return count; +} + +/** + * ext4_alloc_blocks: multiple allocate blocks needed for a branch + * @indirect_blks: the number of blocks need to allocate for indirect + * blocks + * + * @new_blocks: on return it will store the new block numbers for + * the indirect blocks(if needed) and the first direct block, + * @blks: on return it will store the total number of allocated + * direct blocks + */ +static int ext4_alloc_blocks(handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, int indirect_blks, int blks, + ext4_fsblk_t new_blocks[4], int *err) +{ + int target, i; + unsigned long count = 0; + int index = 0; + ext4_fsblk_t current_block = 0; + int ret = 0; + + /* + * Here we try to allocate the requested multiple blocks at once, + * on a best-effort basis. + * To build a branch, we should allocate blocks for + * the indirect blocks(if not allocated yet), and at least + * the first direct block of this branch. That's the + * minimum number of blocks need to allocate(required) + */ + target = blks + indirect_blks; + + while (1) { + count = target; + /* allocating blocks for indirect blocks and direct blocks */ + current_block = ext4_new_blocks(handle,inode,goal,&count,err); + if (*err) + goto failed_out; + + target -= count; + /* allocate blocks for indirect blocks */ + while (index < indirect_blks && count) { + new_blocks[index++] = current_block++; + count--; + } + + if (count > 0) + break; + } + + /* save the new block number for the first direct block */ + new_blocks[index] = current_block; + + /* total number of blocks allocated for direct blocks */ + ret = count; + *err = 0; + return ret; +failed_out: + for (i = 0; i <index; i++) + ext4_free_blocks(handle, inode, new_blocks[i], 1); + return ret; +} + +/** + * ext4_alloc_branch - allocate and set up a chain of blocks. + * @inode: owner + * @indirect_blks: number of allocated indirect blocks + * @blks: number of allocated direct blocks + * @offsets: offsets (in the blocks) to store the pointers to next. + * @branch: place to store the chain in. + * + * This function allocates blocks, zeroes out all but the last one, + * links them into chain and (if we are synchronous) writes them to disk. + * In other words, it prepares a branch that can be spliced onto the + * inode. It stores the information about that chain in the branch[], in + * the same format as ext4_get_branch() would do. We are calling it after + * we had read the existing part of chain and partial points to the last + * triple of that (one with zero ->key). Upon the exit we have the same + * picture as after the successful ext4_get_block(), except that in one + * place chain is disconnected - *branch->p is still zero (we did not + * set the last link), but branch->key contains the number that should + * be placed into *branch->p to fill that gap. + * + * If allocation fails we free all blocks we've allocated (and forget + * their buffer_heads) and return the error value the from failed + * ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain + * as described above and return 0. + */ +static int ext4_alloc_branch(handle_t *handle, struct inode *inode, + int indirect_blks, int *blks, ext4_fsblk_t goal, + int *offsets, Indirect *branch) +{ + int blocksize = inode->i_sb->s_blocksize; + int i, n = 0; + int err = 0; + struct buffer_head *bh; + int num; + ext4_fsblk_t new_blocks[4]; + ext4_fsblk_t current_block; + + num = ext4_alloc_blocks(handle, inode, goal, indirect_blks, + *blks, new_blocks, &err); + if (err) + return err; + + branch[0].key = cpu_to_le32(new_blocks[0]); + /* + * metadata blocks and data blocks are allocated. + */ + for (n = 1; n <= indirect_blks; n++) { + /* + * Get buffer_head for parent block, zero it out + * and set the pointer to new one, then send + * parent to disk. + */ + bh = sb_getblk(inode->i_sb, new_blocks[n-1]); + branch[n].bh = bh; + lock_buffer(bh); + BUFFER_TRACE(bh, "call get_create_access"); + err = ext4_journal_get_create_access(handle, bh); + if (err) { + unlock_buffer(bh); + brelse(bh); + goto failed; + } + + memset(bh->b_data, 0, blocksize); + branch[n].p = (__le32 *) bh->b_data + offsets[n]; + branch[n].key = cpu_to_le32(new_blocks[n]); + *branch[n].p = branch[n].key; + if ( n == indirect_blks) { + current_block = new_blocks[n]; + /* + * End of chain, update the last new metablock of + * the chain to point to the new allocated + * data blocks numbers + */ + for (i=1; i < num; i++) + *(branch[n].p + i) = cpu_to_le32(++current_block); + } + BUFFER_TRACE(bh, "marking uptodate"); + set_buffer_uptodate(bh); + unlock_buffer(bh); + + BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, bh); + if (err) + goto failed; + } + *blks = num; + return err; +failed: + /* Allocation failed, free what we already allocated */ + for (i = 1; i <= n ; i++) { + BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget"); + ext4_journal_forget(handle, branch[i].bh); + } + for (i = 0; i <indirect_blks; i++) + ext4_free_blocks(handle, inode, new_blocks[i], 1); + + ext4_free_blocks(handle, inode, new_blocks[i], num); + + return err; +} + +/** + * ext4_splice_branch - splice the allocated branch onto inode. + * @inode: owner + * @block: (logical) number of block we are adding + * @chain: chain of indirect blocks (with a missing link - see + * ext4_alloc_branch) + * @where: location of missing link + * @num: number of indirect blocks we are adding + * @blks: number of direct blocks we are adding + * + * This function fills the missing link and does all housekeeping needed in + * inode (->i_blocks, etc.). In case of success we end up with the full + * chain to new block and return 0. + */ +static int ext4_splice_branch(handle_t *handle, struct inode *inode, + long block, Indirect *where, int num, int blks) +{ + int i; + int err = 0; + struct ext4_block_alloc_info *block_i; + ext4_fsblk_t current_block; + + block_i = EXT4_I(inode)->i_block_alloc_info; + /* + * If we're splicing into a [td]indirect block (as opposed to the + * inode) then we need to get write access to the [td]indirect block + * before the splice. + */ + if (where->bh) { + BUFFER_TRACE(where->bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, where->bh); + if (err) + goto err_out; + } + /* That's it */ + + *where->p = where->key; + + /* + * Update the host buffer_head or inode to point to more just allocated + * direct blocks blocks + */ + if (num == 0 && blks > 1) { + current_block = le32_to_cpu(where->key) + 1; + for (i = 1; i < blks; i++) + *(where->p + i ) = cpu_to_le32(current_block++); + } + + /* + * update the most recently allocated logical & physical block + * in i_block_alloc_info, to assist find the proper goal block for next + * allocation + */ + if (block_i) { + block_i->last_alloc_logical_block = block + blks - 1; + block_i->last_alloc_physical_block = + le32_to_cpu(where[num].key) + blks - 1; + } + + /* We are done with atomic stuff, now do the rest of housekeeping */ + + inode->i_ctime = CURRENT_TIME_SEC; + ext4_mark_inode_dirty(handle, inode); + + /* had we spliced it onto indirect block? */ + if (where->bh) { + /* + * If we spliced it onto an indirect block, we haven't + * altered the inode. Note however that if it is being spliced + * onto an indirect block at the very end of the file (the + * file is growing) then we *will* alter the inode to reflect + * the new i_size. But that is not done here - it is done in + * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode. + */ + jbd_debug(5, "splicing indirect only\n"); + BUFFER_TRACE(where->bh, "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, where->bh); + if (err) + goto err_out; + } else { + /* + * OK, we spliced it into the inode itself on a direct block. + * Inode was dirtied above. + */ + jbd_debug(5, "splicing direct\n"); + } + return err; + +err_out: + for (i = 1; i <= num; i++) { + BUFFER_TRACE(where[i].bh, "call jbd2_journal_forget"); + ext4_journal_forget(handle, where[i].bh); + ext4_free_blocks(handle,inode,le32_to_cpu(where[i-1].key),1); + } + ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks); + + return err; +} + +/* + * Allocation strategy is simple: if we have to allocate something, we will + * have to go the whole way to leaf. So let's do it before attaching anything + * to tree, set linkage between the newborn blocks, write them if sync is + * required, recheck the path, free and repeat if check fails, otherwise + * set the last missing link (that will protect us from any truncate-generated + * removals - all blocks on the path are immune now) and possibly force the + * write on the parent block. + * That has a nice additional property: no special recovery from the failed + * allocations is needed - we simply release blocks and do not touch anything + * reachable from inode. + * + * `handle' can be NULL if create == 0. + * + * The BKL may not be held on entry here. Be sure to take it early. + * return > 0, # of blocks mapped or allocated. + * return = 0, if plain lookup failed. + * return < 0, error case. + */ +int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, + sector_t iblock, unsigned long maxblocks, + struct buffer_head *bh_result, + int create, int extend_disksize) +{ + int err = -EIO; + int offsets[4]; + Indirect chain[4]; + Indirect *partial; + ext4_fsblk_t goal; + int indirect_blks; + int blocks_to_boundary = 0; + int depth; + struct ext4_inode_info *ei = EXT4_I(inode); + int count = 0; + ext4_fsblk_t first_block = 0; + + + J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)); + J_ASSERT(handle != NULL || create == 0); + depth = ext4_block_to_path(inode,iblock,offsets,&blocks_to_boundary); + + if (depth == 0) + goto out; + + partial = ext4_get_branch(inode, depth, offsets, chain, &err); + + /* Simplest case - block found, no allocation needed */ + if (!partial) { + first_block = le32_to_cpu(chain[depth - 1].key); + clear_buffer_new(bh_result); + count++; + /*map more blocks*/ + while (count < maxblocks && count <= blocks_to_boundary) { + ext4_fsblk_t blk; + + if (!verify_chain(chain, partial)) { + /* + * Indirect block might be removed by + * truncate while we were reading it. + * Handling of that case: forget what we've + * got now. Flag the err as EAGAIN, so it + * will reread. + */ + err = -EAGAIN; + count = 0; + break; + } + blk = le32_to_cpu(*(chain[depth-1].p + count)); + + if (blk == first_block + count) + count++; + else + break; + } + if (err != -EAGAIN) + goto got_it; + } + + /* Next simple case - plain lookup or failed read of indirect block */ + if (!create || err == -EIO) + goto cleanup; + + mutex_lock(&ei->truncate_mutex); + + /* + * If the indirect block is missing while we are reading + * the chain(ext4_get_branch() returns -EAGAIN err), or + * if the chain has been changed after we grab the semaphore, + * (either because another process truncated this branch, or + * another get_block allocated this branch) re-grab the chain to see if + * the request block has been allocated or not. + * + * Since we already block the truncate/other get_block + * at this point, we will have the current copy of the chain when we + * splice the branch into the tree. + */ + if (err == -EAGAIN || !verify_chain(chain, partial)) { + while (partial > chain) { + brelse(partial->bh); + partial--; + } + partial = ext4_get_branch(inode, depth, offsets, chain, &err); + if (!partial) { + count++; + mutex_unlock(&ei->truncate_mutex); + if (err) + goto cleanup; + clear_buffer_new(bh_result); + goto got_it; + } + } + + /* + * Okay, we need to do block allocation. Lazily initialize the block + * allocation info here if necessary + */ + if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) + ext4_init_block_alloc_info(inode); + + goal = ext4_find_goal(inode, iblock, chain, partial); + + /* the number of blocks need to allocate for [d,t]indirect blocks */ + indirect_blks = (chain + depth) - partial - 1; + + /* + * Next look up the indirect map to count the totoal number of + * direct blocks to allocate for this branch. + */ + count = ext4_blks_to_allocate(partial, indirect_blks, + maxblocks, blocks_to_boundary); + /* + * Block out ext4_truncate while we alter the tree + */ + err = ext4_alloc_branch(handle, inode, indirect_blks, &count, goal, + offsets + (partial - chain), partial); + + /* + * The ext4_splice_branch call will free and forget any buffers + * on the new chain if there is a failure, but that risks using + * up transaction credits, especially for bitmaps where the + * credits cannot be returned. Can we handle this somehow? We + * may need to return -EAGAIN upwards in the worst case. --sct + */ + if (!err) + err = ext4_splice_branch(handle, inode, iblock, + partial, indirect_blks, count); + /* + * i_disksize growing is protected by truncate_mutex. Don't forget to + * protect it if you're about to implement concurrent + * ext4_get_block() -bzzz + */ + if (!err && extend_disksize && inode->i_size > ei->i_disksize) + ei->i_disksize = inode->i_size; + mutex_unlock(&ei->truncate_mutex); + if (err) + goto cleanup; + + set_buffer_new(bh_result); +got_it: + map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key)); + if (count > blocks_to_boundary) + set_buffer_boundary(bh_result); + err = count; + /* Clean up and exit */ + partial = chain + depth - 1; /* the whole chain */ +cleanup: + while (partial > chain) { + BUFFER_TRACE(partial->bh, "call brelse"); + brelse(partial->bh); + partial--; + } + BUFFER_TRACE(bh_result, "returned"); +out: + return err; +} + +#define DIO_CREDITS (EXT4_RESERVE_TRANS_BLOCKS + 32) + +static int ext4_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + handle_t *handle = journal_current_handle(); + int ret = 0; + unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + + if (!create) + goto get_block; /* A read */ + + if (max_blocks == 1) + goto get_block; /* A single block get */ + + if (handle->h_transaction->t_state == T_LOCKED) { + /* + * Huge direct-io writes can hold off commits for long + * periods of time. Let this commit run. + */ + ext4_journal_stop(handle); + handle = ext4_journal_start(inode, DIO_CREDITS); + if (IS_ERR(handle)) + ret = PTR_ERR(handle); + goto get_block; + } + + if (handle->h_buffer_credits <= EXT4_RESERVE_TRANS_BLOCKS) { + /* + * Getting low on buffer credits... + */ + ret = ext4_journal_extend(handle, DIO_CREDITS); + if (ret > 0) { + /* + * Couldn't extend the transaction. Start a new one. + */ + ret = ext4_journal_restart(handle, DIO_CREDITS); + } + } + +get_block: + if (ret == 0) { + ret = ext4_get_blocks_wrap(handle, inode, iblock, + max_blocks, bh_result, create, 0); + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; + } + } + return ret; +} + +/* + * `handle' can be NULL if create is zero + */ +struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, + long block, int create, int *errp) +{ + struct buffer_head dummy; + int fatal = 0, err; + + J_ASSERT(handle != NULL || create == 0); + + dummy.b_state = 0; + dummy.b_blocknr = -1000; + buffer_trace_init(&dummy.b_history); + err = ext4_get_blocks_wrap(handle, inode, block, 1, + &dummy, create, 1); + /* + * ext4_get_blocks_handle() returns number of blocks + * mapped. 0 in case of a HOLE. + */ + if (err > 0) { + if (err > 1) + WARN_ON(1); + err = 0; + } + *errp = err; + if (!err && buffer_mapped(&dummy)) { + struct buffer_head *bh; + bh = sb_getblk(inode->i_sb, dummy.b_blocknr); + if (!bh) { + *errp = -EIO; + goto err; + } + if (buffer_new(&dummy)) { + J_ASSERT(create != 0); + J_ASSERT(handle != 0); + + /* + * Now that we do not always journal data, we should + * keep in mind whether this should always journal the + * new buffer as metadata. For now, regular file + * writes use ext4_get_block instead, so it's not a + * problem. + */ + lock_buffer(bh); + BUFFER_TRACE(bh, "call get_create_access"); + fatal = ext4_journal_get_create_access(handle, bh); + if (!fatal && !buffer_uptodate(bh)) { + memset(bh->b_data,0,inode->i_sb->s_blocksize); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); + BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, bh); + if (!fatal) + fatal = err; + } else { + BUFFER_TRACE(bh, "not a new buffer"); + } + if (fatal) { + *errp = fatal; + brelse(bh); + bh = NULL; + } + return bh; + } +err: + return NULL; +} + +struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, + int block, int create, int *err) +{ + struct buffer_head * bh; + + bh = ext4_getblk(handle, inode, block, create, err); + if (!bh) + return bh; + if (buffer_uptodate(bh)) + return bh; + ll_rw_block(READ_META, 1, &bh); + wait_on_buffer(bh); + if (buffer_uptodate(bh)) + return bh; + put_bh(bh); + *err = -EIO; + return NULL; +} + +static int walk_page_buffers( handle_t *handle, + struct buffer_head *head, + unsigned from, + unsigned to, + int *partial, + int (*fn)( handle_t *handle, + struct buffer_head *bh)) +{ + struct buffer_head *bh; + unsigned block_start, block_end; + unsigned blocksize = head->b_size; + int err, ret = 0; + struct buffer_head *next; + + for ( bh = head, block_start = 0; + ret == 0 && (bh != head || !block_start); + block_start = block_end, bh = next) + { + next = bh->b_this_page; + block_end = block_start + blocksize; + if (block_end <= from || block_start >= to) { + if (partial && !buffer_uptodate(bh)) + *partial = 1; + continue; + } + err = (*fn)(handle, bh); + if (!ret) + ret = err; + } + return ret; +} + +/* + * To preserve ordering, it is essential that the hole instantiation and + * the data write be encapsulated in a single transaction. We cannot + * close off a transaction and start a new one between the ext4_get_block() + * and the commit_write(). So doing the jbd2_journal_start at the start of + * prepare_write() is the right place. + * + * Also, this function can nest inside ext4_writepage() -> + * block_write_full_page(). In that case, we *know* that ext4_writepage() + * has generated enough buffer credits to do the whole page. So we won't + * block on the journal in that case, which is good, because the caller may + * be PF_MEMALLOC. + * + * By accident, ext4 can be reentered when a transaction is open via + * quota file writes. If we were to commit the transaction while thus + * reentered, there can be a deadlock - we would be holding a quota + * lock, and the commit would never complete if another thread had a + * transaction open and was blocking on the quota lock - a ranking + * violation. + * + * So what we do is to rely on the fact that jbd2_journal_stop/journal_start + * will _not_ run commit under these circumstances because handle->h_ref + * is elevated. We'll still have enough credits for the tiny quotafile + * write. + */ +static int do_journal_get_write_access(handle_t *handle, + struct buffer_head *bh) +{ + if (!buffer_mapped(bh) || buffer_freed(bh)) + return 0; + return ext4_journal_get_write_access(handle, bh); +} + +static int ext4_prepare_write(struct file *file, struct page *page, + unsigned from, unsigned to) +{ + struct inode *inode = page->mapping->host; + int ret, needed_blocks = ext4_writepage_trans_blocks(inode); + handle_t *handle; + int retries = 0; + +retry: + handle = ext4_journal_start(inode, needed_blocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) + ret = nobh_prepare_write(page, from, to, ext4_get_block); + else + ret = block_prepare_write(page, from, to, ext4_get_block); + if (ret) + goto prepare_write_failed; + + if (ext4_should_journal_data(inode)) { + ret = walk_page_buffers(handle, page_buffers(page), + from, to, NULL, do_journal_get_write_access); + } +prepare_write_failed: + if (ret) + ext4_journal_stop(handle); + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; +out: + return ret; +} + +int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh) +{ + int err = jbd2_journal_dirty_data(handle, bh); + if (err) + ext4_journal_abort_handle(__FUNCTION__, __FUNCTION__, + bh, handle,err); + return err; +} + +/* For commit_write() in data=journal mode */ +static int commit_write_fn(handle_t *handle, struct buffer_head *bh) +{ + if (!buffer_mapped(bh) || buffer_freed(bh)) + return 0; + set_buffer_uptodate(bh); + return ext4_journal_dirty_metadata(handle, bh); +} + +/* + * We need to pick up the new inode size which generic_commit_write gave us + * `file' can be NULL - eg, when called from page_symlink(). + * + * ext4 never places buffers on inode->i_mapping->private_list. metadata + * buffers are managed internally. + */ +static int ext4_ordered_commit_write(struct file *file, struct page *page, + unsigned from, unsigned to) +{ + handle_t *handle = ext4_journal_current_handle(); + struct inode *inode = page->mapping->host; + int ret = 0, ret2; + + ret = walk_page_buffers(handle, page_buffers(page), + from, to, NULL, ext4_journal_dirty_data); + + if (ret == 0) { + /* + * generic_commit_write() will run mark_inode_dirty() if i_size + * changes. So let's piggyback the i_disksize mark_inode_dirty + * into that. + */ + loff_t new_i_size; + + new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; + if (new_i_size > EXT4_I(inode)->i_disksize) + EXT4_I(inode)->i_disksize = new_i_size; + ret = generic_commit_write(file, page, from, to); + } + ret2 = ext4_journal_stop(handle); + if (!ret) + ret = ret2; + return ret; +} + +static int ext4_writeback_commit_write(struct file *file, struct page *page, + unsigned from, unsigned to) +{ + handle_t *handle = ext4_journal_current_handle(); + struct inode *inode = page->mapping->host; + int ret = 0, ret2; + loff_t new_i_size; + + new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; + if (new_i_size > EXT4_I(inode)->i_disksize) + EXT4_I(inode)->i_disksize = new_i_size; + + if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) + ret = nobh_commit_write(file, page, from, to); + else + ret = generic_commit_write(file, page, from, to); + + ret2 = ext4_journal_stop(handle); + if (!ret) + ret = ret2; + return ret; +} + +static int ext4_journalled_commit_write(struct file *file, + struct page *page, unsigned from, unsigned to) +{ + handle_t *handle = ext4_journal_current_handle(); + struct inode *inode = page->mapping->host; + int ret = 0, ret2; + int partial = 0; + loff_t pos; + + /* + * Here we duplicate the generic_commit_write() functionality + */ + pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; + + ret = walk_page_buffers(handle, page_buffers(page), from, + to, &partial, commit_write_fn); + if (!partial) + SetPageUptodate(page); + if (pos > inode->i_size) + i_size_write(inode, pos); + EXT4_I(inode)->i_state |= EXT4_STATE_JDATA; + if (inode->i_size > EXT4_I(inode)->i_disksize) { + EXT4_I(inode)->i_disksize = inode->i_size; + ret2 = ext4_mark_inode_dirty(handle, inode); + if (!ret) + ret = ret2; + } + ret2 = ext4_journal_stop(handle); + if (!ret) + ret = ret2; + return ret; +} + +/* + * bmap() is special. It gets used by applications such as lilo and by + * the swapper to find the on-disk block of a specific piece of data. + * + * Naturally, this is dangerous if the block concerned is still in the + * journal. If somebody makes a swapfile on an ext4 data-journaling + * filesystem and enables swap, then they may get a nasty shock when the + * data getting swapped to that swapfile suddenly gets overwritten by + * the original zero's written out previously to the journal and + * awaiting writeback in the kernel's buffer cache. + * + * So, if we see any bmap calls here on a modified, data-journaled file, + * take extra steps to flush any blocks which might be in the cache. + */ +static sector_t ext4_bmap(struct address_space *mapping, sector_t block) +{ + struct inode *inode = mapping->host; + journal_t *journal; + int err; + + if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) { + /* + * This is a REALLY heavyweight approach, but the use of + * bmap on dirty files is expected to be extremely rare: + * only if we run lilo or swapon on a freshly made file + * do we expect this to happen. + * + * (bmap requires CAP_SYS_RAWIO so this does not + * represent an unprivileged user DOS attack --- we'd be + * in trouble if mortal users could trigger this path at + * will.) + * + * NB. EXT4_STATE_JDATA is not set on files other than + * regular files. If somebody wants to bmap a directory + * or symlink and gets confused because the buffer + * hasn't yet been flushed to disk, they deserve + * everything they get. + */ + + EXT4_I(inode)->i_state &= ~EXT4_STATE_JDATA; + journal = EXT4_JOURNAL(inode); + jbd2_journal_lock_updates(journal); + err = jbd2_journal_flush(journal); + jbd2_journal_unlock_updates(journal); + + if (err) + return 0; + } + + return generic_block_bmap(mapping,block,ext4_get_block); +} + +static int bget_one(handle_t *handle, struct buffer_head *bh) +{ + get_bh(bh); + return 0; +} + +static int bput_one(handle_t *handle, struct buffer_head *bh) +{ + put_bh(bh); + return 0; +} + +static int jbd2_journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh) +{ + if (buffer_mapped(bh)) + return ext4_journal_dirty_data(handle, bh); + return 0; +} + +/* + * Note that we always start a transaction even if we're not journalling + * data. This is to preserve ordering: any hole instantiation within + * __block_write_full_page -> ext4_get_block() should be journalled + * along with the data so we don't crash and then get metadata which + * refers to old data. + * + * In all journalling modes block_write_full_page() will start the I/O. + * + * Problem: + * + * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> + * ext4_writepage() + * + * Similar for: + * + * ext4_file_write() -> generic_file_write() -> __alloc_pages() -> ... + * + * Same applies to ext4_get_block(). We will deadlock on various things like + * lock_journal and i_truncate_mutex. + * + * Setting PF_MEMALLOC here doesn't work - too many internal memory + * allocations fail. + * + * 16May01: If we're reentered then journal_current_handle() will be + * non-zero. We simply *return*. + * + * 1 July 2001: @@@ FIXME: + * In journalled data mode, a data buffer may be metadata against the + * current transaction. But the same file is part of a shared mapping + * and someone does a writepage() on it. + * + * We will move the buffer onto the async_data list, but *after* it has + * been dirtied. So there's a small window where we have dirty data on + * BJ_Metadata. + * + * Note that this only applies to the last partial page in the file. The + * bit which block_write_full_page() uses prepare/commit for. (That's + * broken code anyway: it's wrong for msync()). + * + * It's a rare case: affects the final partial page, for journalled data + * where the file is subject to bith write() and writepage() in the same + * transction. To fix it we'll need a custom block_write_full_page(). + * We'll probably need that anyway for journalling writepage() output. + * + * We don't honour synchronous mounts for writepage(). That would be + * disastrous. Any write() or metadata operation will sync the fs for + * us. + * + * AKPM2: if all the page's buffers are mapped to disk and !data=journal, + * we don't need to open a transaction here. + */ +static int ext4_ordered_writepage(struct page *page, + struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + struct buffer_head *page_bufs; + handle_t *handle = NULL; + int ret = 0; + int err; + + J_ASSERT(PageLocked(page)); + + /* + * We give up here if we're reentered, because it might be for a + * different filesystem. + */ + if (ext4_journal_current_handle()) + goto out_fail; + + handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); + + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_fail; + } + + if (!page_has_buffers(page)) { + create_empty_buffers(page, inode->i_sb->s_blocksize, + (1 << BH_Dirty)|(1 << BH_Uptodate)); + } + page_bufs = page_buffers(page); + walk_page_buffers(handle, page_bufs, 0, + PAGE_CACHE_SIZE, NULL, bget_one); + + ret = block_write_full_page(page, ext4_get_block, wbc); + + /* + * The page can become unlocked at any point now, and + * truncate can then come in and change things. So we + * can't touch *page from now on. But *page_bufs is + * safe due to elevated refcount. + */ + + /* + * And attach them to the current transaction. But only if + * block_write_full_page() succeeded. Otherwise they are unmapped, + * and generally junk. + */ + if (ret == 0) { + err = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, + NULL, jbd2_journal_dirty_data_fn); + if (!ret) + ret = err; + } + walk_page_buffers(handle, page_bufs, 0, + PAGE_CACHE_SIZE, NULL, bput_one); + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; + +out_fail: + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return ret; +} + +static int ext4_writeback_writepage(struct page *page, + struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + handle_t *handle = NULL; + int ret = 0; + int err; + + if (ext4_journal_current_handle()) + goto out_fail; + + handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_fail; + } + + if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) + ret = nobh_writepage(page, ext4_get_block, wbc); + else + ret = block_write_full_page(page, ext4_get_block, wbc); + + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; + +out_fail: + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return ret; +} + +static int ext4_journalled_writepage(struct page *page, + struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + handle_t *handle = NULL; + int ret = 0; + int err; + + if (ext4_journal_current_handle()) + goto no_write; + + handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto no_write; + } + + if (!page_has_buffers(page) || PageChecked(page)) { + /* + * It's mmapped pagecache. Add buffers and journal it. There + * doesn't seem much point in redirtying the page here. + */ + ClearPageChecked(page); + ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, + ext4_get_block); + if (ret != 0) { + ext4_journal_stop(handle); + goto out_unlock; + } + ret = walk_page_buffers(handle, page_buffers(page), 0, + PAGE_CACHE_SIZE, NULL, do_journal_get_write_access); + + err = walk_page_buffers(handle, page_buffers(page), 0, + PAGE_CACHE_SIZE, NULL, commit_write_fn); + if (ret == 0) + ret = err; + EXT4_I(inode)->i_state |= EXT4_STATE_JDATA; + unlock_page(page); + } else { + /* + * It may be a page full of checkpoint-mode buffers. We don't + * really know unless we go poke around in the buffer_heads. + * But block_write_full_page will do the right thing. + */ + ret = block_write_full_page(page, ext4_get_block, wbc); + } + err = ext4_journal_stop(handle); + if (!ret) + ret = err; +out: + return ret; + +no_write: + redirty_page_for_writepage(wbc, page); +out_unlock: + unlock_page(page); + goto out; +} + +static int ext4_readpage(struct file *file, struct page *page) +{ + return mpage_readpage(page, ext4_get_block); +} + +static int +ext4_readpages(struct file *file, struct address_space *mapping, + struct list_head *pages, unsigned nr_pages) +{ + return mpage_readpages(mapping, pages, nr_pages, ext4_get_block); +} + +static void ext4_invalidatepage(struct page *page, unsigned long offset) +{ + journal_t *journal = EXT4_JOURNAL(page->mapping->host); + + /* + * If it's a full truncate we just forget about the pending dirtying + */ + if (offset == 0) + ClearPageChecked(page); + + jbd2_journal_invalidatepage(journal, page, offset); +} + +static int ext4_releasepage(struct page *page, gfp_t wait) +{ + journal_t *journal = EXT4_JOURNAL(page->mapping->host); + + WARN_ON(PageChecked(page)); + if (!page_has_buffers(page)) + return 0; + return jbd2_journal_try_to_free_buffers(journal, page, wait); +} + +/* + * If the O_DIRECT write will extend the file then add this inode to the + * orphan list. So recovery will truncate it back to the original size + * if the machine crashes during the write. + * + * If the O_DIRECT write is intantiating holes inside i_size and the machine + * crashes then stale disk data _may_ be exposed inside the file. + */ +static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, + const struct iovec *iov, loff_t offset, + unsigned long nr_segs) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + struct ext4_inode_info *ei = EXT4_I(inode); + handle_t *handle = NULL; + ssize_t ret; + int orphan = 0; + size_t count = iov_length(iov, nr_segs); + + if (rw == WRITE) { + loff_t final_size = offset + count; + + handle = ext4_journal_start(inode, DIO_CREDITS); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + if (final_size > inode->i_size) { + ret = ext4_orphan_add(handle, inode); + if (ret) + goto out_stop; + orphan = 1; + ei->i_disksize = inode->i_size; + } + } + + ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, + offset, nr_segs, + ext4_get_block, NULL); + + /* + * Reacquire the handle: ext4_get_block() can restart the transaction + */ + handle = journal_current_handle(); + +out_stop: + if (handle) { + int err; + + if (orphan && inode->i_nlink) + ext4_orphan_del(handle, inode); + if (orphan && ret > 0) { + loff_t end = offset + ret; + if (end > inode->i_size) { + ei->i_disksize = end; + i_size_write(inode, end); + /* + * We're going to return a positive `ret' + * here due to non-zero-length I/O, so there's + * no way of reporting error returns from + * ext4_mark_inode_dirty() to userspace. So + * ignore it. + */ + ext4_mark_inode_dirty(handle, inode); + } + } + err = ext4_journal_stop(handle); + if (ret == 0) + ret = err; + } +out: + return ret; +} + +/* + * Pages can be marked dirty completely asynchronously from ext4's journalling + * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do + * much here because ->set_page_dirty is called under VFS locks. The page is + * not necessarily locked. + * + * We cannot just dirty the page and leave attached buffers clean, because the + * buffers' dirty state is "definitive". We cannot just set the buffers dirty + * or jbddirty because all the journalling code will explode. + * + * So what we do is to mark the page "pending dirty" and next time writepage + * is called, propagate that into the buffers appropriately. + */ +static int ext4_journalled_set_page_dirty(struct page *page) +{ + SetPageChecked(page); + return __set_page_dirty_nobuffers(page); +} + +static const struct address_space_operations ext4_ordered_aops = { + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_ordered_writepage, + .sync_page = block_sync_page, + .prepare_write = ext4_prepare_write, + .commit_write = ext4_ordered_commit_write, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, +}; + +static const struct address_space_operations ext4_writeback_aops = { + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_writeback_writepage, + .sync_page = block_sync_page, + .prepare_write = ext4_prepare_write, + .commit_write = ext4_writeback_commit_write, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, +}; + +static const struct address_space_operations ext4_journalled_aops = { + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_journalled_writepage, + .sync_page = block_sync_page, + .prepare_write = ext4_prepare_write, + .commit_write = ext4_journalled_commit_write, + .set_page_dirty = ext4_journalled_set_page_dirty, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, +}; + +void ext4_set_aops(struct inode *inode) +{ + if (ext4_should_order_data(inode)) + inode->i_mapping->a_ops = &ext4_ordered_aops; + else if (ext4_should_writeback_data(inode)) + inode->i_mapping->a_ops = &ext4_writeback_aops; + else + inode->i_mapping->a_ops = &ext4_journalled_aops; +} + +/* + * ext4_block_truncate_page() zeroes out a mapping from file offset `from' + * up to the end of the block which corresponds to `from'. + * This required during truncate. We need to physically zero the tail end + * of that block so it doesn't yield old data if the file is later grown. + */ +int ext4_block_truncate_page(handle_t *handle, struct page *page, + struct address_space *mapping, loff_t from) +{ + ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT; + unsigned offset = from & (PAGE_CACHE_SIZE-1); + unsigned blocksize, iblock, length, pos; + struct inode *inode = mapping->host; + struct buffer_head *bh; + int err = 0; + void *kaddr; + + blocksize = inode->i_sb->s_blocksize; + length = blocksize - (offset & (blocksize - 1)); + iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); + + /* + * For "nobh" option, we can only work if we don't need to + * read-in the page - otherwise we create buffers to do the IO. + */ + if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) && + ext4_should_writeback_data(inode) && PageUptodate(page)) { + kaddr = kmap_atomic(page, KM_USER0); + memset(kaddr + offset, 0, length); + flush_dcache_page(page); + kunmap_atomic(kaddr, KM_USER0); + set_page_dirty(page); + goto unlock; + } + + if (!page_has_buffers(page)) + create_empty_buffers(page, blocksize, 0); + + /* Find the buffer that contains "offset" */ + bh = page_buffers(page); + pos = blocksize; + while (offset >= pos) { + bh = bh->b_this_page; + iblock++; + pos += blocksize; + } + + err = 0; + if (buffer_freed(bh)) { + BUFFER_TRACE(bh, "freed: skip"); + goto unlock; + } + + if (!buffer_mapped(bh)) { + BUFFER_TRACE(bh, "unmapped"); + ext4_get_block(inode, iblock, bh, 0); + /* unmapped? It's a hole - nothing to do */ + if (!buffer_mapped(bh)) { + BUFFER_TRACE(bh, "still unmapped"); + goto unlock; + } + } + + /* Ok, it's mapped. Make sure it's up-to-date */ + if (PageUptodate(page)) + set_buffer_uptodate(bh); + + if (!buffer_uptodate(bh)) { + err = -EIO; + ll_rw_block(READ, 1, &bh); + wait_on_buffer(bh); + /* Uhhuh. Read error. Complain and punt. */ + if (!buffer_uptodate(bh)) + goto unlock; + } + + if (ext4_should_journal_data(inode)) { + BUFFER_TRACE(bh, "get write access"); + err = ext4_journal_get_write_access(handle, bh); + if (err) + goto unlock; + } + + kaddr = kmap_atomic(page, KM_USER0); + memset(kaddr + offset, 0, length); + flush_dcache_page(page); + kunmap_atomic(kaddr, KM_USER0); + + BUFFER_TRACE(bh, "zeroed end of block"); + + err = 0; + if (ext4_should_journal_data(inode)) { + err = ext4_journal_dirty_metadata(handle, bh); + } else { + if (ext4_should_order_data(inode)) + err = ext4_journal_dirty_data(handle, bh); + mark_buffer_dirty(bh); + } + +unlock: + unlock_page(page); + page_cache_release(page); + return err; +} + +/* + * Probably it should be a library function... search for first non-zero word + * or memcmp with zero_page, whatever is better for particular architecture. + * Linus? + */ +static inline int all_zeroes(__le32 *p, __le32 *q) +{ + while (p < q) + if (*p++) + return 0; + return 1; +} + +/** + * ext4_find_shared - find the indirect blocks for partial truncation. + * @inode: inode in question + * @depth: depth of the affected branch + * @offsets: offsets of pointers in that branch (see ext4_block_to_path) + * @chain: place to store the pointers to partial indirect blocks + * @top: place to the (detached) top of branch + * + * This is a helper function used by ext4_truncate(). + * + * When we do truncate() we may have to clean the ends of several + * indirect blocks but leave the blocks themselves alive. Block is + * partially truncated if some data below the new i_size is refered + * from it (and it is on the path to the first completely truncated + * data block, indeed). We have to free the top of that path along + * with everything to the right of the path. Since no allocation + * past the truncation point is possible until ext4_truncate() + * finishes, we may safely do the latter, but top of branch may + * require special attention - pageout below the truncation point + * might try to populate it. + * + * We atomically detach the top of branch from the tree, store the + * block number of its root in *@top, pointers to buffer_heads of + * partially truncated blocks - in @chain[].bh and pointers to + * their last elements that should not be removed - in + * @chain[].p. Return value is the pointer to last filled element + * of @chain. + * + * The work left to caller to do the actual freeing of subtrees: + * a) free the subtree starting from *@top + * b) free the subtrees whose roots are stored in + * (@chain[i].p+1 .. end of @chain[i].bh->b_data) + * c) free the subtrees growing from the inode past the @chain[0]. + * (no partially truncated stuff there). */ + +static Indirect *ext4_find_shared(struct inode *inode, int depth, + int offsets[4], Indirect chain[4], __le32 *top) +{ + Indirect *partial, *p; + int k, err; + + *top = 0; + /* Make k index the deepest non-null offest + 1 */ + for (k = depth; k > 1 && !offsets[k-1]; k--) + ; + partial = ext4_get_branch(inode, k, offsets, chain, &err); + /* Writer: pointers */ + if (!partial) + partial = chain + k-1; + /* + * If the branch acquired continuation since we've looked at it - + * fine, it should all survive and (new) top doesn't belong to us. + */ + if (!partial->key && *partial->p) + /* Writer: end */ + goto no_top; + for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--) + ; + /* + * OK, we've found the last block that must survive. The rest of our + * branch should be detached before unlocking. However, if that rest + * of branch is all ours and does not grow immediately from the inode + * it's easier to cheat and just decrement partial->p. + */ + if (p == chain + k - 1 && p > chain) { + p->p--; + } else { + *top = *p->p; + /* Nope, don't do this in ext4. Must leave the tree intact */ +#if 0 + *p->p = 0; +#endif + } + /* Writer: end */ + + while(partial > p) { + brelse(partial->bh); + partial--; + } +no_top: + return partial; +} + +/* + * Zero a number of block pointers in either an inode or an indirect block. + * If we restart the transaction we must again get write access to the + * indirect block for further modification. + * + * We release `count' blocks on disk, but (last - first) may be greater + * than `count' because there can be holes in there. + */ +static void ext4_clear_blocks(handle_t *handle, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t block_to_free, + unsigned long count, __le32 *first, __le32 *last) +{ + __le32 *p; + if (try_to_extend_transaction(handle, inode)) { + if (bh) { + BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata"); + ext4_journal_dirty_metadata(handle, bh); + } + ext4_mark_inode_dirty(handle, inode); + ext4_journal_test_restart(handle, inode); + if (bh) { + BUFFER_TRACE(bh, "retaking write access"); + ext4_journal_get_write_access(handle, bh); + } + } + + /* + * Any buffers which are on the journal will be in memory. We find + * them on the hash table so jbd2_journal_revoke() will run jbd2_journal_forget() + * on them. We've already detached each block from the file, so + * bforget() in jbd2_journal_forget() should be safe. + * + * AKPM: turn on bforget in jbd2_journal_forget()!!! + */ + for (p = first; p < last; p++) { + u32 nr = le32_to_cpu(*p); + if (nr) { + struct buffer_head *bh; + + *p = 0; + bh = sb_find_get_block(inode->i_sb, nr); + ext4_forget(handle, 0, inode, bh, nr); + } + } + + ext4_free_blocks(handle, inode, block_to_free, count); +} + +/** + * ext4_free_data - free a list of data blocks + * @handle: handle for this transaction + * @inode: inode we are dealing with + * @this_bh: indirect buffer_head which contains *@first and *@last + * @first: array of block numbers + * @last: points immediately past the end of array + * + * We are freeing all blocks refered from that array (numbers are stored as + * little-endian 32-bit) and updating @inode->i_blocks appropriately. + * + * We accumulate contiguous runs of blocks to free. Conveniently, if these + * blocks are contiguous then releasing them at one time will only affect one + * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't + * actually use a lot of journal space. + * + * @this_bh will be %NULL if @first and @last point into the inode's direct + * block pointers. + */ +static void ext4_free_data(handle_t *handle, struct inode *inode, + struct buffer_head *this_bh, + __le32 *first, __le32 *last) +{ + ext4_fsblk_t block_to_free = 0; /* Starting block # of a run */ + unsigned long count = 0; /* Number of blocks in the run */ + __le32 *block_to_free_p = NULL; /* Pointer into inode/ind + corresponding to + block_to_free */ + ext4_fsblk_t nr; /* Current block # */ + __le32 *p; /* Pointer into inode/ind + for current block */ + int err; + + if (this_bh) { /* For indirect block */ + BUFFER_TRACE(this_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, this_bh); + /* Important: if we can't update the indirect pointers + * to the blocks, we can't free them. */ + if (err) + return; + } + + for (p = first; p < last; p++) { + nr = le32_to_cpu(*p); + if (nr) { + /* accumulate blocks to free if they're contiguous */ + if (count == 0) { + block_to_free = nr; + block_to_free_p = p; + count = 1; + } else if (nr == block_to_free + count) { + count++; + } else { + ext4_clear_blocks(handle, inode, this_bh, + block_to_free, + count, block_to_free_p, p); + block_to_free = nr; + block_to_free_p = p; + count = 1; + } + } + } + + if (count > 0) + ext4_clear_blocks(handle, inode, this_bh, block_to_free, + count, block_to_free_p, p); + + if (this_bh) { + BUFFER_TRACE(this_bh, "call ext4_journal_dirty_metadata"); + ext4_journal_dirty_metadata(handle, this_bh); + } +} + +/** + * ext4_free_branches - free an array of branches + * @handle: JBD handle for this transaction + * @inode: inode we are dealing with + * @parent_bh: the buffer_head which contains *@first and *@last + * @first: array of block numbers + * @last: pointer immediately past the end of array + * @depth: depth of the branches to free + * + * We are freeing all blocks refered from these branches (numbers are + * stored as little-endian 32-bit) and updating @inode->i_blocks + * appropriately. + */ +static void ext4_free_branches(handle_t *handle, struct inode *inode, + struct buffer_head *parent_bh, + __le32 *first, __le32 *last, int depth) +{ + ext4_fsblk_t nr; + __le32 *p; + + if (is_handle_aborted(handle)) + return; + + if (depth--) { + struct buffer_head *bh; + int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); + p = last; + while (--p >= first) { + nr = le32_to_cpu(*p); + if (!nr) + continue; /* A hole */ + + /* Go read the buffer for the next level down */ + bh = sb_bread(inode->i_sb, nr); + + /* + * A read failure? Report error and clear slot + * (should be rare). + */ + if (!bh) { + ext4_error(inode->i_sb, "ext4_free_branches", + "Read failure, inode=%lu, block=%llu", + inode->i_ino, nr); + continue; + } + + /* This zaps the entire block. Bottom up. */ + BUFFER_TRACE(bh, "free child branches"); + ext4_free_branches(handle, inode, bh, + (__le32*)bh->b_data, + (__le32*)bh->b_data + addr_per_block, + depth); + + /* + * We've probably journalled the indirect block several + * times during the truncate. But it's no longer + * needed and we now drop it from the transaction via + * jbd2_journal_revoke(). + * + * That's easy if it's exclusively part of this + * transaction. But if it's part of the committing + * transaction then jbd2_journal_forget() will simply + * brelse() it. That means that if the underlying + * block is reallocated in ext4_get_block(), + * unmap_underlying_metadata() will find this block + * and will try to get rid of it. damn, damn. + * + * If this block has already been committed to the + * journal, a revoke record will be written. And + * revoke records must be emitted *before* clearing + * this block's bit in the bitmaps. + */ + ext4_forget(handle, 1, inode, bh, bh->b_blocknr); + + /* + * Everything below this this pointer has been + * released. Now let this top-of-subtree go. + * + * We want the freeing of this indirect block to be + * atomic in the journal with the updating of the + * bitmap block which owns it. So make some room in + * the journal. + * + * We zero the parent pointer *after* freeing its + * pointee in the bitmaps, so if extend_transaction() + * for some reason fails to put the bitmap changes and + * the release into the same transaction, recovery + * will merely complain about releasing a free block, + * rather than leaking blocks. + */ + if (is_handle_aborted(handle)) + return; + if (try_to_extend_transaction(handle, inode)) { + ext4_mark_inode_dirty(handle, inode); + ext4_journal_test_restart(handle, inode); + } + + ext4_free_blocks(handle, inode, nr, 1); + + if (parent_bh) { + /* + * The block which we have just freed is + * pointed to by an indirect block: journal it + */ + BUFFER_TRACE(parent_bh, "get_write_access"); + if (!ext4_journal_get_write_access(handle, + parent_bh)){ + *p = 0; + BUFFER_TRACE(parent_bh, + "call ext4_journal_dirty_metadata"); + ext4_journal_dirty_metadata(handle, + parent_bh); + } + } + } + } else { + /* We have reached the bottom of the tree. */ + BUFFER_TRACE(parent_bh, "free data blocks"); + ext4_free_data(handle, inode, parent_bh, first, last); + } +} + +/* + * ext4_truncate() + * + * We block out ext4_get_block() block instantiations across the entire + * transaction, and VFS/VM ensures that ext4_truncate() cannot run + * simultaneously on behalf of the same inode. + * + * As we work through the truncate and commmit bits of it to the journal there + * is one core, guiding principle: the file's tree must always be consistent on + * disk. We must be able to restart the truncate after a crash. + * + * The file's tree may be transiently inconsistent in memory (although it + * probably isn't), but whenever we close off and commit a journal transaction, + * the contents of (the filesystem + the journal) must be consistent and + * restartable. It's pretty simple, really: bottom up, right to left (although + * left-to-right works OK too). + * + * Note that at recovery time, journal replay occurs *before* the restart of + * truncate against the orphan inode list. + * + * The committed inode has the new, desired i_size (which is the same as + * i_disksize in this case). After a crash, ext4_orphan_cleanup() will see + * that this inode's truncate did not complete and it will again call + * ext4_truncate() to have another go. So there will be instantiated blocks + * to the right of the truncation point in a crashed ext4 filesystem. But + * that's fine - as long as they are linked from the inode, the post-crash + * ext4_truncate() run will find them and release them. + */ +void ext4_truncate(struct inode *inode) +{ + handle_t *handle; + struct ext4_inode_info *ei = EXT4_I(inode); + __le32 *i_data = ei->i_data; + int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb); + struct address_space *mapping = inode->i_mapping; + int offsets[4]; + Indirect chain[4]; + Indirect *partial; + __le32 nr = 0; + int n; + long last_block; + unsigned blocksize = inode->i_sb->s_blocksize; + struct page *page; + + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return; + if (ext4_inode_is_fast_symlink(inode)) + return; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return; + + /* + * We have to lock the EOF page here, because lock_page() nests + * outside jbd2_journal_start(). + */ + if ((inode->i_size & (blocksize - 1)) == 0) { + /* Block boundary? Nothing to do */ + page = NULL; + } else { + page = grab_cache_page(mapping, + inode->i_size >> PAGE_CACHE_SHIFT); + if (!page) + return; + } + + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) + return ext4_ext_truncate(inode, page); + + handle = start_transaction(inode); + if (IS_ERR(handle)) { + if (page) { + clear_highpage(page); + flush_dcache_page(page); + unlock_page(page); + page_cache_release(page); + } + return; /* AKPM: return what? */ + } + + last_block = (inode->i_size + blocksize-1) + >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); + + if (page) + ext4_block_truncate_page(handle, page, mapping, inode->i_size); + + n = ext4_block_to_path(inode, last_block, offsets, NULL); + if (n == 0) + goto out_stop; /* error */ + + /* + * OK. This truncate is going to happen. We add the inode to the + * orphan list, so that if this truncate spans multiple transactions, + * and we crash, we will resume the truncate when the filesystem + * recovers. It also marks the inode dirty, to catch the new size. + * + * Implication: the file must always be in a sane, consistent + * truncatable state while each transaction commits. + */ + if (ext4_orphan_add(handle, inode)) + goto out_stop; + + /* + * The orphan list entry will now protect us from any crash which + * occurs before the truncate completes, so it is now safe to propagate + * the new, shorter inode size (held for now in i_size) into the + * on-disk inode. We do this via i_disksize, which is the value which + * ext4 *really* writes onto the disk inode. + */ + ei->i_disksize = inode->i_size; + + /* + * From here we block out all ext4_get_block() callers who want to + * modify the block allocation tree. + */ + mutex_lock(&ei->truncate_mutex); + + if (n == 1) { /* direct blocks */ + ext4_free_data(handle, inode, NULL, i_data+offsets[0], + i_data + EXT4_NDIR_BLOCKS); + goto do_indirects; + } + + partial = ext4_find_shared(inode, n, offsets, chain, &nr); + /* Kill the top of shared branch (not detached) */ + if (nr) { + if (partial == chain) { + /* Shared branch grows from the inode */ + ext4_free_branches(handle, inode, NULL, + &nr, &nr+1, (chain+n-1) - partial); + *partial->p = 0; + /* + * We mark the inode dirty prior to restart, + * and prior to stop. No need for it here. + */ + } else { + /* Shared branch grows from an indirect block */ + BUFFER_TRACE(partial->bh, "get_write_access"); + ext4_free_branches(handle, inode, partial->bh, + partial->p, + partial->p+1, (chain+n-1) - partial); + } + } + /* Clear the ends of indirect blocks on the shared branch */ + while (partial > chain) { + ext4_free_branches(handle, inode, partial->bh, partial->p + 1, + (__le32*)partial->bh->b_data+addr_per_block, + (chain+n-1) - partial); + BUFFER_TRACE(partial->bh, "call brelse"); + brelse (partial->bh); + partial--; + } +do_indirects: + /* Kill the remaining (whole) subtrees */ + switch (offsets[0]) { + default: + nr = i_data[EXT4_IND_BLOCK]; + if (nr) { + ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); + i_data[EXT4_IND_BLOCK] = 0; + } + case EXT4_IND_BLOCK: + nr = i_data[EXT4_DIND_BLOCK]; + if (nr) { + ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); + i_data[EXT4_DIND_BLOCK] = 0; + } + case EXT4_DIND_BLOCK: + nr = i_data[EXT4_TIND_BLOCK]; + if (nr) { + ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); + i_data[EXT4_TIND_BLOCK] = 0; + } + case EXT4_TIND_BLOCK: + ; + } + + ext4_discard_reservation(inode); + + mutex_unlock(&ei->truncate_mutex); + inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; + ext4_mark_inode_dirty(handle, inode); + + /* + * In a multi-transaction truncate, we only make the final transaction + * synchronous + */ + if (IS_SYNC(inode)) + handle->h_sync = 1; +out_stop: + /* + * If this was a simple ftruncate(), and the file will remain alive + * then we need to clear up the orphan record which we created above. + * However, if this was a real unlink then we were called by + * ext4_delete_inode(), and we allow that function to clean up the + * orphan info for us. + */ + if (inode->i_nlink) + ext4_orphan_del(handle, inode); + + ext4_journal_stop(handle); +} + +static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb, + unsigned long ino, struct ext4_iloc *iloc) +{ + unsigned long desc, group_desc, block_group; + unsigned long offset; + ext4_fsblk_t block; + struct buffer_head *bh; + struct ext4_group_desc * gdp; + + if (!ext4_valid_inum(sb, ino)) { + /* + * This error is already checked for in namei.c unless we are + * looking at an NFS filehandle, in which case no error + * report is needed + */ + return 0; + } + + block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); + if (block_group >= EXT4_SB(sb)->s_groups_count) { + ext4_error(sb,"ext4_get_inode_block","group >= groups count"); + return 0; + } + smp_rmb(); + group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); + desc = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); + bh = EXT4_SB(sb)->s_group_desc[group_desc]; + if (!bh) { + ext4_error (sb, "ext4_get_inode_block", + "Descriptor not loaded"); + return 0; + } + + gdp = (struct ext4_group_desc *)((__u8 *)bh->b_data + + desc * EXT4_DESC_SIZE(sb)); + /* + * Figure out the offset within the block group inode table + */ + offset = ((ino - 1) % EXT4_INODES_PER_GROUP(sb)) * + EXT4_INODE_SIZE(sb); + block = ext4_inode_table(sb, gdp) + + (offset >> EXT4_BLOCK_SIZE_BITS(sb)); + + iloc->block_group = block_group; + iloc->offset = offset & (EXT4_BLOCK_SIZE(sb) - 1); + return block; +} + +/* + * ext4_get_inode_loc returns with an extra refcount against the inode's + * underlying buffer_head on success. If 'in_mem' is true, we have all + * data in memory that is needed to recreate the on-disk version of this + * inode. + */ +static int __ext4_get_inode_loc(struct inode *inode, + struct ext4_iloc *iloc, int in_mem) +{ + ext4_fsblk_t block; + struct buffer_head *bh; + + block = ext4_get_inode_block(inode->i_sb, inode->i_ino, iloc); + if (!block) + return -EIO; + + bh = sb_getblk(inode->i_sb, block); + if (!bh) { + ext4_error (inode->i_sb, "ext4_get_inode_loc", + "unable to read inode block - " + "inode=%lu, block=%llu", + inode->i_ino, block); + return -EIO; + } + if (!buffer_uptodate(bh)) { + lock_buffer(bh); + if (buffer_uptodate(bh)) { + /* someone brought it uptodate while we waited */ + unlock_buffer(bh); + goto has_buffer; + } + + /* + * If we have all information of the inode in memory and this + * is the only valid inode in the block, we need not read the + * block. + */ + if (in_mem) { + struct buffer_head *bitmap_bh; + struct ext4_group_desc *desc; + int inodes_per_buffer; + int inode_offset, i; + int block_group; + int start; + + block_group = (inode->i_ino - 1) / + EXT4_INODES_PER_GROUP(inode->i_sb); + inodes_per_buffer = bh->b_size / + EXT4_INODE_SIZE(inode->i_sb); + inode_offset = ((inode->i_ino - 1) % + EXT4_INODES_PER_GROUP(inode->i_sb)); + start = inode_offset & ~(inodes_per_buffer - 1); + + /* Is the inode bitmap in cache? */ + desc = ext4_get_group_desc(inode->i_sb, + block_group, NULL); + if (!desc) + goto make_io; + + bitmap_bh = sb_getblk(inode->i_sb, + ext4_inode_bitmap(inode->i_sb, desc)); + if (!bitmap_bh) + goto make_io; + + /* + * If the inode bitmap isn't in cache then the + * optimisation may end up performing two reads instead + * of one, so skip it. + */ + if (!buffer_uptodate(bitmap_bh)) { + brelse(bitmap_bh); + goto make_io; + } + for (i = start; i < start + inodes_per_buffer; i++) { + if (i == inode_offset) + continue; + if (ext4_test_bit(i, bitmap_bh->b_data)) + break; + } + brelse(bitmap_bh); + if (i == start + inodes_per_buffer) { + /* all other inodes are free, so skip I/O */ + memset(bh->b_data, 0, bh->b_size); + set_buffer_uptodate(bh); + unlock_buffer(bh); + goto has_buffer; + } + } + +make_io: + /* + * There are other valid inodes in the buffer, this inode + * has in-inode xattrs, or we don't have this inode in memory. + * Read the block from disk. + */ + get_bh(bh); + bh->b_end_io = end_buffer_read_sync; + submit_bh(READ_META, bh); + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) { + ext4_error(inode->i_sb, "ext4_get_inode_loc", + "unable to read inode block - " + "inode=%lu, block=%llu", + inode->i_ino, block); + brelse(bh); + return -EIO; + } + } +has_buffer: + iloc->bh = bh; + return 0; +} + +int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) +{ + /* We have all inode data except xattrs in memory here. */ + return __ext4_get_inode_loc(inode, iloc, + !(EXT4_I(inode)->i_state & EXT4_STATE_XATTR)); +} + +void ext4_set_inode_flags(struct inode *inode) +{ + unsigned int flags = EXT4_I(inode)->i_flags; + + inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); + if (flags & EXT4_SYNC_FL) + inode->i_flags |= S_SYNC; + if (flags & EXT4_APPEND_FL) + inode->i_flags |= S_APPEND; + if (flags & EXT4_IMMUTABLE_FL) + inode->i_flags |= S_IMMUTABLE; + if (flags & EXT4_NOATIME_FL) + inode->i_flags |= S_NOATIME; + if (flags & EXT4_DIRSYNC_FL) + inode->i_flags |= S_DIRSYNC; +} + +void ext4_read_inode(struct inode * inode) +{ + struct ext4_iloc iloc; + struct ext4_inode *raw_inode; + struct ext4_inode_info *ei = EXT4_I(inode); + struct buffer_head *bh; + int block; + +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + ei->i_acl = EXT4_ACL_NOT_CACHED; + ei->i_default_acl = EXT4_ACL_NOT_CACHED; +#endif + ei->i_block_alloc_info = NULL; + + if (__ext4_get_inode_loc(inode, &iloc, 0)) + goto bad_inode; + bh = iloc.bh; + raw_inode = ext4_raw_inode(&iloc); + inode->i_mode = le16_to_cpu(raw_inode->i_mode); + inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + if(!(test_opt (inode->i_sb, NO_UID32))) { + inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + } + inode->i_nlink = le16_to_cpu(raw_inode->i_links_count); + inode->i_size = le32_to_cpu(raw_inode->i_size); + inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime); + inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime); + inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime); + inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0; + + ei->i_state = 0; + ei->i_dir_start_lookup = 0; + ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); + /* We now have enough fields to check if the inode was active or not. + * This is needed because nfsd might try to access dead inodes + * the test is that same one that e2fsck uses + * NeilBrown 1999oct15 + */ + if (inode->i_nlink == 0) { + if (inode->i_mode == 0 || + !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) { + /* this inode is deleted */ + brelse (bh); + goto bad_inode; + } + /* The only unlinked inodes we let through here have + * valid i_mode and are being read by the orphan + * recovery code: that's fine, we're about to complete + * the process of deleting those. */ + } + inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); + ei->i_flags = le32_to_cpu(raw_inode->i_flags); +#ifdef EXT4_FRAGMENTS + ei->i_faddr = le32_to_cpu(raw_inode->i_faddr); + ei->i_frag_no = raw_inode->i_frag; + ei->i_frag_size = raw_inode->i_fsize; +#endif + ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl); + if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != + cpu_to_le32(EXT4_OS_HURD)) + ei->i_file_acl |= + ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; + if (!S_ISREG(inode->i_mode)) { + ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl); + } else { + inode->i_size |= + ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32; + } + ei->i_disksize = inode->i_size; + inode->i_generation = le32_to_cpu(raw_inode->i_generation); + ei->i_block_group = iloc.block_group; + /* + * NOTE! The in-memory inode i_data array is in little-endian order + * even on big-endian machines: we do NOT byteswap the block numbers! + */ + for (block = 0; block < EXT4_N_BLOCKS; block++) + ei->i_data[block] = raw_inode->i_block[block]; + INIT_LIST_HEAD(&ei->i_orphan); + + if (inode->i_ino >= EXT4_FIRST_INO(inode->i_sb) + 1 && + EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { + /* + * When mke2fs creates big inodes it does not zero out + * the unused bytes above EXT4_GOOD_OLD_INODE_SIZE, + * so ignore those first few inodes. + */ + ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); + if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > + EXT4_INODE_SIZE(inode->i_sb)) + goto bad_inode; + if (ei->i_extra_isize == 0) { + /* The extra space is currently unused. Use it. */ + ei->i_extra_isize = sizeof(struct ext4_inode) - + EXT4_GOOD_OLD_INODE_SIZE; + } else { + __le32 *magic = (void *)raw_inode + + EXT4_GOOD_OLD_INODE_SIZE + + ei->i_extra_isize; + if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) + ei->i_state |= EXT4_STATE_XATTR; + } + } else + ei->i_extra_isize = 0; + + if (S_ISREG(inode->i_mode)) { + inode->i_op = &ext4_file_inode_operations; + inode->i_fop = &ext4_file_operations; + ext4_set_aops(inode); + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = &ext4_dir_inode_operations; + inode->i_fop = &ext4_dir_operations; + } else if (S_ISLNK(inode->i_mode)) { + if (ext4_inode_is_fast_symlink(inode)) + inode->i_op = &ext4_fast_symlink_inode_operations; + else { + inode->i_op = &ext4_symlink_inode_operations; + ext4_set_aops(inode); + } + } else { + inode->i_op = &ext4_special_inode_operations; + if (raw_inode->i_block[0]) + init_special_inode(inode, inode->i_mode, + old_decode_dev(le32_to_cpu(raw_inode->i_block[0]))); + else + init_special_inode(inode, inode->i_mode, + new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); + } + brelse (iloc.bh); + ext4_set_inode_flags(inode); + return; + +bad_inode: + make_bad_inode(inode); + return; +} + +/* + * Post the struct inode info into an on-disk inode location in the + * buffer-cache. This gobbles the caller's reference to the + * buffer_head in the inode location struct. + * + * The caller must have write access to iloc->bh. + */ +static int ext4_do_update_inode(handle_t *handle, + struct inode *inode, + struct ext4_iloc *iloc) +{ + struct ext4_inode *raw_inode = ext4_raw_inode(iloc); + struct ext4_inode_info *ei = EXT4_I(inode); + struct buffer_head *bh = iloc->bh; + int err = 0, rc, block; + + /* For fields not not tracking in the in-memory inode, + * initialise them to zero for new inodes. */ + if (ei->i_state & EXT4_STATE_NEW) + memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); + + raw_inode->i_mode = cpu_to_le16(inode->i_mode); + if(!(test_opt(inode->i_sb, NO_UID32))) { + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid)); +/* + * Fix up interoperability with old kernels. Otherwise, old inodes get + * re-used with the upper 16 bits of the uid/gid intact + */ + if(!ei->i_dtime) { + raw_inode->i_uid_high = + cpu_to_le16(high_16_bits(inode->i_uid)); + raw_inode->i_gid_high = + cpu_to_le16(high_16_bits(inode->i_gid)); + } else { + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } + } else { + raw_inode->i_uid_low = + cpu_to_le16(fs_high2lowuid(inode->i_uid)); + raw_inode->i_gid_low = + cpu_to_le16(fs_high2lowgid(inode->i_gid)); + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } + raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); + raw_inode->i_size = cpu_to_le32(ei->i_disksize); + raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec); + raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec); + raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec); + raw_inode->i_blocks = cpu_to_le32(inode->i_blocks); + raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); + raw_inode->i_flags = cpu_to_le32(ei->i_flags); +#ifdef EXT4_FRAGMENTS + raw_inode->i_faddr = cpu_to_le32(ei->i_faddr); + raw_inode->i_frag = ei->i_frag_no; + raw_inode->i_fsize = ei->i_frag_size; +#endif + if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != + cpu_to_le32(EXT4_OS_HURD)) + raw_inode->i_file_acl_high = + cpu_to_le16(ei->i_file_acl >> 32); + raw_inode->i_file_acl = cpu_to_le32(ei->i_file_acl); + if (!S_ISREG(inode->i_mode)) { + raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl); + } else { + raw_inode->i_size_high = + cpu_to_le32(ei->i_disksize >> 32); + if (ei->i_disksize > 0x7fffffffULL) { + struct super_block *sb = inode->i_sb; + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_LARGE_FILE) || + EXT4_SB(sb)->s_es->s_rev_level == + cpu_to_le32(EXT4_GOOD_OLD_REV)) { + /* If this is the first large file + * created, add a flag to the superblock. + */ + err = ext4_journal_get_write_access(handle, + EXT4_SB(sb)->s_sbh); + if (err) + goto out_brelse; + ext4_update_dynamic_rev(sb); + EXT4_SET_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_LARGE_FILE); + sb->s_dirt = 1; + handle->h_sync = 1; + err = ext4_journal_dirty_metadata(handle, + EXT4_SB(sb)->s_sbh); + } + } + } + raw_inode->i_generation = cpu_to_le32(inode->i_generation); + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { + if (old_valid_dev(inode->i_rdev)) { + raw_inode->i_block[0] = + cpu_to_le32(old_encode_dev(inode->i_rdev)); + raw_inode->i_block[1] = 0; + } else { + raw_inode->i_block[0] = 0; + raw_inode->i_block[1] = + cpu_to_le32(new_encode_dev(inode->i_rdev)); + raw_inode->i_block[2] = 0; + } + } else for (block = 0; block < EXT4_N_BLOCKS; block++) + raw_inode->i_block[block] = ei->i_data[block]; + + if (ei->i_extra_isize) + raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize); + + BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata"); + rc = ext4_journal_dirty_metadata(handle, bh); + if (!err) + err = rc; + ei->i_state &= ~EXT4_STATE_NEW; + +out_brelse: + brelse (bh); + ext4_std_error(inode->i_sb, err); + return err; +} + +/* + * ext4_write_inode() + * + * We are called from a few places: + * + * - Within generic_file_write() for O_SYNC files. + * Here, there will be no transaction running. We wait for any running + * trasnaction to commit. + * + * - Within sys_sync(), kupdate and such. + * We wait on commit, if tol to. + * + * - Within prune_icache() (PF_MEMALLOC == true) + * Here we simply return. We can't afford to block kswapd on the + * journal commit. + * + * In all cases it is actually safe for us to return without doing anything, + * because the inode has been copied into a raw inode buffer in + * ext4_mark_inode_dirty(). This is a correctness thing for O_SYNC and for + * knfsd. + * + * Note that we are absolutely dependent upon all inode dirtiers doing the + * right thing: they *must* call mark_inode_dirty() after dirtying info in + * which we are interested. + * + * It would be a bug for them to not do this. The code: + * + * mark_inode_dirty(inode) + * stuff(); + * inode->i_size = expr; + * + * is in error because a kswapd-driven write_inode() could occur while + * `stuff()' is running, and the new i_size will be lost. Plus the inode + * will no longer be on the superblock's dirty inode list. + */ +int ext4_write_inode(struct inode *inode, int wait) +{ + if (current->flags & PF_MEMALLOC) + return 0; + + if (ext4_journal_current_handle()) { + jbd_debug(0, "called recursively, non-PF_MEMALLOC!\n"); + dump_stack(); + return -EIO; + } + + if (!wait) + return 0; + + return ext4_force_commit(inode->i_sb); +} + +/* + * ext4_setattr() + * + * Called from notify_change. + * + * We want to trap VFS attempts to truncate the file as soon as + * possible. In particular, we want to make sure that when the VFS + * shrinks i_size, we put the inode on the orphan list and modify + * i_disksize immediately, so that during the subsequent flushing of + * dirty pages and freeing of disk blocks, we can guarantee that any + * commit will leave the blocks being flushed in an unused state on + * disk. (On recovery, the inode will get truncated and the blocks will + * be freed, so we have a strong guarantee that no future commit will + * leave these blocks visible to the user.) + * + * Called with inode->sem down. + */ +int ext4_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = dentry->d_inode; + int error, rc = 0; + const unsigned int ia_valid = attr->ia_valid; + + error = inode_change_ok(inode, attr); + if (error) + return error; + + if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) || + (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) { + handle_t *handle; + + /* (user+group)*(old+new) structure, inode write (sb, + * inode block, ? - but truncate inode update has it) */ + handle = ext4_journal_start(inode, 2*(EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)+ + EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + goto err_out; + } + error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0; + if (error) { + ext4_journal_stop(handle); + return error; + } + /* Update corresponding info in inode so that everything is in + * one transaction */ + if (attr->ia_valid & ATTR_UID) + inode->i_uid = attr->ia_uid; + if (attr->ia_valid & ATTR_GID) + inode->i_gid = attr->ia_gid; + error = ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + } + + if (S_ISREG(inode->i_mode) && + attr->ia_valid & ATTR_SIZE && attr->ia_size < inode->i_size) { + handle_t *handle; + + handle = ext4_journal_start(inode, 3); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + goto err_out; + } + + error = ext4_orphan_add(handle, inode); + EXT4_I(inode)->i_disksize = attr->ia_size; + rc = ext4_mark_inode_dirty(handle, inode); + if (!error) + error = rc; + ext4_journal_stop(handle); + } + + rc = inode_setattr(inode, attr); + + /* If inode_setattr's call to ext4_truncate failed to get a + * transaction handle at all, we need to clean up the in-core + * orphan list manually. */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + + if (!rc && (ia_valid & ATTR_MODE)) + rc = ext4_acl_chmod(inode); + +err_out: + ext4_std_error(inode->i_sb, error); + if (!error) + error = rc; + return error; +} + + +/* + * How many blocks doth make a writepage()? + * + * With N blocks per page, it may be: + * N data blocks + * 2 indirect block + * 2 dindirect + * 1 tindirect + * N+5 bitmap blocks (from the above) + * N+5 group descriptor summary blocks + * 1 inode block + * 1 superblock. + * 2 * EXT4_SINGLEDATA_TRANS_BLOCKS for the quote files + * + * 3 * (N + 5) + 2 + 2 * EXT4_SINGLEDATA_TRANS_BLOCKS + * + * With ordered or writeback data it's the same, less the N data blocks. + * + * If the inode's direct blocks can hold an integral number of pages then a + * page cannot straddle two indirect blocks, and we can only touch one indirect + * and dindirect block, and the "5" above becomes "3". + * + * This still overestimates under most circumstances. If we were to pass the + * start and end offsets in here as well we could do block_to_path() on each + * block and work out the exact number of indirects which are touched. Pah. + */ + +int ext4_writepage_trans_blocks(struct inode *inode) +{ + int bpp = ext4_journal_blocks_per_page(inode); + int indirects = (EXT4_NDIR_BLOCKS % bpp) ? 5 : 3; + int ret; + + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) + return ext4_ext_writepage_trans_blocks(inode, bpp); + + if (ext4_should_journal_data(inode)) + ret = 3 * (bpp + indirects) + 2; + else + ret = 2 * (bpp + indirects) + 2; + +#ifdef CONFIG_QUOTA + /* We know that structure was already allocated during DQUOT_INIT so + * we will be updating only the data blocks + inodes */ + ret += 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); +#endif + + return ret; +} + +/* + * The caller must have previously called ext4_reserve_inode_write(). + * Give this, we know that the caller already has write access to iloc->bh. + */ +int ext4_mark_iloc_dirty(handle_t *handle, + struct inode *inode, struct ext4_iloc *iloc) +{ + int err = 0; + + /* the do_update_inode consumes one bh->b_count */ + get_bh(iloc->bh); + + /* ext4_do_update_inode() does jbd2_journal_dirty_metadata */ + err = ext4_do_update_inode(handle, inode, iloc); + put_bh(iloc->bh); + return err; +} + +/* + * On success, We end up with an outstanding reference count against + * iloc->bh. This _must_ be cleaned up later. + */ + +int +ext4_reserve_inode_write(handle_t *handle, struct inode *inode, + struct ext4_iloc *iloc) +{ + int err = 0; + if (handle) { + err = ext4_get_inode_loc(inode, iloc); + if (!err) { + BUFFER_TRACE(iloc->bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, iloc->bh); + if (err) { + brelse(iloc->bh); + iloc->bh = NULL; + } + } + } + ext4_std_error(inode->i_sb, err); + return err; +} + +/* + * What we do here is to mark the in-core inode as clean with respect to inode + * dirtiness (it may still be data-dirty). + * This means that the in-core inode may be reaped by prune_icache + * without having to perform any I/O. This is a very good thing, + * because *any* task may call prune_icache - even ones which + * have a transaction open against a different journal. + * + * Is this cheating? Not really. Sure, we haven't written the + * inode out, but prune_icache isn't a user-visible syncing function. + * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) + * we start and wait on commits. + * + * Is this efficient/effective? Well, we're being nice to the system + * by cleaning up our inodes proactively so they can be reaped + * without I/O. But we are potentially leaving up to five seconds' + * worth of inodes floating about which prune_icache wants us to + * write out. One way to fix that would be to get prune_icache() + * to do a write_super() to free up some memory. It has the desired + * effect. + */ +int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) +{ + struct ext4_iloc iloc; + int err; + + might_sleep(); + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (!err) + err = ext4_mark_iloc_dirty(handle, inode, &iloc); + return err; +} + +/* + * ext4_dirty_inode() is called from __mark_inode_dirty() + * + * We're really interested in the case where a file is being extended. + * i_size has been changed by generic_commit_write() and we thus need + * to include the updated inode in the current transaction. + * + * Also, DQUOT_ALLOC_SPACE() will always dirty the inode when blocks + * are allocated to the file. + * + * If the inode is marked synchronous, we don't honour that here - doing + * so would cause a commit on atime updates, which we don't bother doing. + * We handle synchronous inodes at the highest possible level. + */ +void ext4_dirty_inode(struct inode *inode) +{ + handle_t *current_handle = ext4_journal_current_handle(); + handle_t *handle; + + handle = ext4_journal_start(inode, 2); + if (IS_ERR(handle)) + goto out; + if (current_handle && + current_handle->h_transaction != handle->h_transaction) { + /* This task has a transaction open against a different fs */ + printk(KERN_EMERG "%s: transactions do not match!\n", + __FUNCTION__); + } else { + jbd_debug(5, "marking dirty. outer handle=%p\n", + current_handle); + ext4_mark_inode_dirty(handle, inode); + } + ext4_journal_stop(handle); +out: + return; +} + +#if 0 +/* + * Bind an inode's backing buffer_head into this transaction, to prevent + * it from being flushed to disk early. Unlike + * ext4_reserve_inode_write, this leaves behind no bh reference and + * returns no iloc structure, so the caller needs to repeat the iloc + * lookup to mark the inode dirty later. + */ +static int ext4_pin_inode(handle_t *handle, struct inode *inode) +{ + struct ext4_iloc iloc; + + int err = 0; + if (handle) { + err = ext4_get_inode_loc(inode, &iloc); + if (!err) { + BUFFER_TRACE(iloc.bh, "get_write_access"); + err = jbd2_journal_get_write_access(handle, iloc.bh); + if (!err) + err = ext4_journal_dirty_metadata(handle, + iloc.bh); + brelse(iloc.bh); + } + } + ext4_std_error(inode->i_sb, err); + return err; +} +#endif + +int ext4_change_inode_journal_flag(struct inode *inode, int val) +{ + journal_t *journal; + handle_t *handle; + int err; + + /* + * We have to be very careful here: changing a data block's + * journaling status dynamically is dangerous. If we write a + * data block to the journal, change the status and then delete + * that block, we risk forgetting to revoke the old log record + * from the journal and so a subsequent replay can corrupt data. + * So, first we make sure that the journal is empty and that + * nobody is changing anything. + */ + + journal = EXT4_JOURNAL(inode); + if (is_journal_aborted(journal) || IS_RDONLY(inode)) + return -EROFS; + + jbd2_journal_lock_updates(journal); + jbd2_journal_flush(journal); + + /* + * OK, there are no updates running now, and all cached data is + * synced to disk. We are now in a completely consistent state + * which doesn't have anything in the journal, and we know that + * no filesystem updates are running, so it is safe to modify + * the inode's in-core data-journaling state flag now. + */ + + if (val) + EXT4_I(inode)->i_flags |= EXT4_JOURNAL_DATA_FL; + else + EXT4_I(inode)->i_flags &= ~EXT4_JOURNAL_DATA_FL; + ext4_set_aops(inode); + + jbd2_journal_unlock_updates(journal); + + /* Finally we can mark the inode as dirty. */ + + handle = ext4_journal_start(inode, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + err = ext4_mark_inode_dirty(handle, inode); + handle->h_sync = 1; + ext4_journal_stop(handle); + ext4_std_error(inode->i_sb, err); + + return err; +} diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c new file mode 100644 index 00000000000..22a737c306c --- /dev/null +++ b/fs/ext4/ioctl.c @@ -0,0 +1,306 @@ +/* + * linux/fs/ext4/ioctl.c + * + * Copyright (C) 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + */ + +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/capability.h> +#include <linux/ext4_fs.h> +#include <linux/ext4_jbd2.h> +#include <linux/time.h> +#include <linux/compat.h> +#include <linux/smp_lock.h> +#include <asm/uaccess.h> + +int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, + unsigned long arg) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned int flags; + unsigned short rsv_window_size; + + ext4_debug ("cmd = %u, arg = %lu\n", cmd, arg); + + switch (cmd) { + case EXT4_IOC_GETFLAGS: + flags = ei->i_flags & EXT4_FL_USER_VISIBLE; + return put_user(flags, (int __user *) arg); + case EXT4_IOC_SETFLAGS: { + handle_t *handle = NULL; + int err; + struct ext4_iloc iloc; + unsigned int oldflags; + unsigned int jflag; + + if (IS_RDONLY(inode)) + return -EROFS; + + if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + return -EACCES; + + if (get_user(flags, (int __user *) arg)) + return -EFAULT; + + if (!S_ISDIR(inode->i_mode)) + flags &= ~EXT4_DIRSYNC_FL; + + mutex_lock(&inode->i_mutex); + oldflags = ei->i_flags; + + /* The JOURNAL_DATA flag is modifiable only by root */ + jflag = flags & EXT4_JOURNAL_DATA_FL; + + /* + * The IMMUTABLE and APPEND_ONLY flags can only be changed by + * the relevant capability. + * + * This test looks nicer. Thanks to Pauline Middelink + */ + if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) { + if (!capable(CAP_LINUX_IMMUTABLE)) { + mutex_unlock(&inode->i_mutex); + return -EPERM; + } + } + + /* + * The JOURNAL_DATA flag can only be changed by + * the relevant capability. + */ + if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { + if (!capable(CAP_SYS_RESOURCE)) { + mutex_unlock(&inode->i_mutex); + return -EPERM; + } + } + + + handle = ext4_journal_start(inode, 1); + if (IS_ERR(handle)) { + mutex_unlock(&inode->i_mutex); + return PTR_ERR(handle); + } + if (IS_SYNC(inode)) + handle->h_sync = 1; + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto flags_err; + + flags = flags & EXT4_FL_USER_MODIFIABLE; + flags |= oldflags & ~EXT4_FL_USER_MODIFIABLE; + ei->i_flags = flags; + + ext4_set_inode_flags(inode); + inode->i_ctime = CURRENT_TIME_SEC; + + err = ext4_mark_iloc_dirty(handle, inode, &iloc); +flags_err: + ext4_journal_stop(handle); + if (err) { + mutex_unlock(&inode->i_mutex); + return err; + } + + if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) + err = ext4_change_inode_journal_flag(inode, jflag); + mutex_unlock(&inode->i_mutex); + return err; + } + case EXT4_IOC_GETVERSION: + case EXT4_IOC_GETVERSION_OLD: + return put_user(inode->i_generation, (int __user *) arg); + case EXT4_IOC_SETVERSION: + case EXT4_IOC_SETVERSION_OLD: { + handle_t *handle; + struct ext4_iloc iloc; + __u32 generation; + int err; + + if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + return -EPERM; + if (IS_RDONLY(inode)) + return -EROFS; + if (get_user(generation, (int __user *) arg)) + return -EFAULT; + + handle = ext4_journal_start(inode, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err == 0) { + inode->i_ctime = CURRENT_TIME_SEC; + inode->i_generation = generation; + err = ext4_mark_iloc_dirty(handle, inode, &iloc); + } + ext4_journal_stop(handle); + return err; + } +#ifdef CONFIG_JBD_DEBUG + case EXT4_IOC_WAIT_FOR_READONLY: + /* + * This is racy - by the time we're woken up and running, + * the superblock could be released. And the module could + * have been unloaded. So sue me. + * + * Returns 1 if it slept, else zero. + */ + { + struct super_block *sb = inode->i_sb; + DECLARE_WAITQUEUE(wait, current); + int ret = 0; + + set_current_state(TASK_INTERRUPTIBLE); + add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait); + if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) { + schedule(); + ret = 1; + } + remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait); + return ret; + } +#endif + case EXT4_IOC_GETRSVSZ: + if (test_opt(inode->i_sb, RESERVATION) + && S_ISREG(inode->i_mode) + && ei->i_block_alloc_info) { + rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size; + return put_user(rsv_window_size, (int __user *)arg); + } + return -ENOTTY; + case EXT4_IOC_SETRSVSZ: { + + if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode)) + return -ENOTTY; + + if (IS_RDONLY(inode)) + return -EROFS; + + if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + return -EACCES; + + if (get_user(rsv_window_size, (int __user *)arg)) + return -EFAULT; + + if (rsv_window_size > EXT4_MAX_RESERVE_BLOCKS) + rsv_window_size = EXT4_MAX_RESERVE_BLOCKS; + + /* + * need to allocate reservation structure for this inode + * before set the window size + */ + mutex_lock(&ei->truncate_mutex); + if (!ei->i_block_alloc_info) + ext4_init_block_alloc_info(inode); + + if (ei->i_block_alloc_info){ + struct ext4_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node; + rsv->rsv_goal_size = rsv_window_size; + } + mutex_unlock(&ei->truncate_mutex); + return 0; + } + case EXT4_IOC_GROUP_EXTEND: { + ext4_fsblk_t n_blocks_count; + struct super_block *sb = inode->i_sb; + int err; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + if (IS_RDONLY(inode)) + return -EROFS; + + if (get_user(n_blocks_count, (__u32 __user *)arg)) + return -EFAULT; + + err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count); + jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); + jbd2_journal_flush(EXT4_SB(sb)->s_journal); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + + return err; + } + case EXT4_IOC_GROUP_ADD: { + struct ext4_new_group_data input; + struct super_block *sb = inode->i_sb; + int err; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + if (IS_RDONLY(inode)) + return -EROFS; + + if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg, + sizeof(input))) + return -EFAULT; + + err = ext4_group_add(sb, &input); + jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); + jbd2_journal_flush(EXT4_SB(sb)->s_journal); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + + return err; + } + + default: + return -ENOTTY; + } +} + +#ifdef CONFIG_COMPAT +long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct inode *inode = file->f_dentry->d_inode; + int ret; + + /* These are just misnamed, they actually get/put from/to user an int */ + switch (cmd) { + case EXT4_IOC32_GETFLAGS: + cmd = EXT4_IOC_GETFLAGS; + break; + case EXT4_IOC32_SETFLAGS: + cmd = EXT4_IOC_SETFLAGS; + break; + case EXT4_IOC32_GETVERSION: + cmd = EXT4_IOC_GETVERSION; + break; + case EXT4_IOC32_SETVERSION: + cmd = EXT4_IOC_SETVERSION; + break; + case EXT4_IOC32_GROUP_EXTEND: + cmd = EXT4_IOC_GROUP_EXTEND; + break; + case EXT4_IOC32_GETVERSION_OLD: + cmd = EXT4_IOC_GETVERSION_OLD; + break; + case EXT4_IOC32_SETVERSION_OLD: + cmd = EXT4_IOC_SETVERSION_OLD; + break; +#ifdef CONFIG_JBD_DEBUG + case EXT4_IOC32_WAIT_FOR_READONLY: + cmd = EXT4_IOC_WAIT_FOR_READONLY; + break; +#endif + case EXT4_IOC32_GETRSVSZ: + cmd = EXT4_IOC_GETRSVSZ; + break; + case EXT4_IOC32_SETRSVSZ: + cmd = EXT4_IOC_SETRSVSZ; + break; + case EXT4_IOC_GROUP_ADD: + break; + default: + return -ENOIOCTLCMD; + } + lock_kernel(); + ret = ext4_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg)); + unlock_kernel(); + return ret; +} +#endif diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c new file mode 100644 index 00000000000..8b1bd03d20f --- /dev/null +++ b/fs/ext4/namei.c @@ -0,0 +1,2395 @@ +/* + * linux/fs/ext4/namei.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/namei.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + * Directory entry file type support and forward compatibility hooks + * for B-tree directories by Theodore Ts'o (tytso@mit.edu), 1998 + * Hash Tree Directory indexing (c) + * Daniel Phillips, 2001 + * Hash Tree Directory indexing porting + * Christopher Li, 2002 + * Hash Tree Directory indexing cleanup + * Theodore Ts'o, 2002 + */ + +#include <linux/fs.h> +#include <linux/pagemap.h> +#include <linux/jbd2.h> +#include <linux/time.h> +#include <linux/ext4_fs.h> +#include <linux/ext4_jbd2.h> +#include <linux/fcntl.h> +#include <linux/stat.h> +#include <linux/string.h> +#include <linux/quotaops.h> +#include <linux/buffer_head.h> +#include <linux/bio.h> +#include <linux/smp_lock.h> + +#include "namei.h" +#include "xattr.h" +#include "acl.h" + +/* + * define how far ahead to read directories while searching them. + */ +#define NAMEI_RA_CHUNKS 2 +#define NAMEI_RA_BLOCKS 4 +#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS) +#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b)) + +static struct buffer_head *ext4_append(handle_t *handle, + struct inode *inode, + u32 *block, int *err) +{ + struct buffer_head *bh; + + *block = inode->i_size >> inode->i_sb->s_blocksize_bits; + + if ((bh = ext4_bread(handle, inode, *block, 1, err))) { + inode->i_size += inode->i_sb->s_blocksize; + EXT4_I(inode)->i_disksize = inode->i_size; + ext4_journal_get_write_access(handle,bh); + } + return bh; +} + +#ifndef assert +#define assert(test) J_ASSERT(test) +#endif + +#ifndef swap +#define swap(x, y) do { typeof(x) z = x; x = y; y = z; } while (0) +#endif + +#ifdef DX_DEBUG +#define dxtrace(command) command +#else +#define dxtrace(command) +#endif + +struct fake_dirent +{ + __le32 inode; + __le16 rec_len; + u8 name_len; + u8 file_type; +}; + +struct dx_countlimit +{ + __le16 limit; + __le16 count; +}; + +struct dx_entry +{ + __le32 hash; + __le32 block; +}; + +/* + * dx_root_info is laid out so that if it should somehow get overlaid by a + * dirent the two low bits of the hash version will be zero. Therefore, the + * hash version mod 4 should never be 0. Sincerely, the paranoia department. + */ + +struct dx_root +{ + struct fake_dirent dot; + char dot_name[4]; + struct fake_dirent dotdot; + char dotdot_name[4]; + struct dx_root_info + { + __le32 reserved_zero; + u8 hash_version; + u8 info_length; /* 8 */ + u8 indirect_levels; + u8 unused_flags; + } + info; + struct dx_entry entries[0]; +}; + +struct dx_node +{ + struct fake_dirent fake; + struct dx_entry entries[0]; +}; + + +struct dx_frame +{ + struct buffer_head *bh; + struct dx_entry *entries; + struct dx_entry *at; +}; + +struct dx_map_entry +{ + u32 hash; + u32 offs; +}; + +#ifdef CONFIG_EXT4_INDEX +static inline unsigned dx_get_block (struct dx_entry *entry); +static void dx_set_block (struct dx_entry *entry, unsigned value); +static inline unsigned dx_get_hash (struct dx_entry *entry); +static void dx_set_hash (struct dx_entry *entry, unsigned value); +static unsigned dx_get_count (struct dx_entry *entries); +static unsigned dx_get_limit (struct dx_entry *entries); +static void dx_set_count (struct dx_entry *entries, unsigned value); +static void dx_set_limit (struct dx_entry *entries, unsigned value); +static unsigned dx_root_limit (struct inode *dir, unsigned infosize); +static unsigned dx_node_limit (struct inode *dir); +static struct dx_frame *dx_probe(struct dentry *dentry, + struct inode *dir, + struct dx_hash_info *hinfo, + struct dx_frame *frame, + int *err); +static void dx_release (struct dx_frame *frames); +static int dx_make_map (struct ext4_dir_entry_2 *de, int size, + struct dx_hash_info *hinfo, struct dx_map_entry map[]); +static void dx_sort_map(struct dx_map_entry *map, unsigned count); +static struct ext4_dir_entry_2 *dx_move_dirents (char *from, char *to, + struct dx_map_entry *offsets, int count); +static struct ext4_dir_entry_2* dx_pack_dirents (char *base, int size); +static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block); +static int ext4_htree_next_block(struct inode *dir, __u32 hash, + struct dx_frame *frame, + struct dx_frame *frames, + __u32 *start_hash); +static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry, + struct ext4_dir_entry_2 **res_dir, int *err); +static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, + struct inode *inode); + +/* + * Future: use high four bits of block for coalesce-on-delete flags + * Mask them off for now. + */ + +static inline unsigned dx_get_block (struct dx_entry *entry) +{ + return le32_to_cpu(entry->block) & 0x00ffffff; +} + +static inline void dx_set_block (struct dx_entry *entry, unsigned value) +{ + entry->block = cpu_to_le32(value); +} + +static inline unsigned dx_get_hash (struct dx_entry *entry) +{ + return le32_to_cpu(entry->hash); +} + +static inline void dx_set_hash (struct dx_entry *entry, unsigned value) +{ + entry->hash = cpu_to_le32(value); +} + +static inline unsigned dx_get_count (struct dx_entry *entries) +{ + return le16_to_cpu(((struct dx_countlimit *) entries)->count); +} + +static inline unsigned dx_get_limit (struct dx_entry *entries) +{ + return le16_to_cpu(((struct dx_countlimit *) entries)->limit); +} + +static inline void dx_set_count (struct dx_entry *entries, unsigned value) +{ + ((struct dx_countlimit *) entries)->count = cpu_to_le16(value); +} + +static inline void dx_set_limit (struct dx_entry *entries, unsigned value) +{ + ((struct dx_countlimit *) entries)->limit = cpu_to_le16(value); +} + +static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize) +{ + unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - + EXT4_DIR_REC_LEN(2) - infosize; + return 0? 20: entry_space / sizeof(struct dx_entry); +} + +static inline unsigned dx_node_limit (struct inode *dir) +{ + unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0); + return 0? 22: entry_space / sizeof(struct dx_entry); +} + +/* + * Debug + */ +#ifdef DX_DEBUG +static void dx_show_index (char * label, struct dx_entry *entries) +{ + int i, n = dx_get_count (entries); + printk("%s index ", label); + for (i = 0; i < n; i++) { + printk("%x->%u ", i? dx_get_hash(entries + i) : + 0, dx_get_block(entries + i)); + } + printk("\n"); +} + +struct stats +{ + unsigned names; + unsigned space; + unsigned bcount; +}; + +static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_entry_2 *de, + int size, int show_names) +{ + unsigned names = 0, space = 0; + char *base = (char *) de; + struct dx_hash_info h = *hinfo; + + printk("names: "); + while ((char *) de < base + size) + { + if (de->inode) + { + if (show_names) + { + int len = de->name_len; + char *name = de->name; + while (len--) printk("%c", *name++); + ext4fs_dirhash(de->name, de->name_len, &h); + printk(":%x.%u ", h.hash, + ((char *) de - base)); + } + space += EXT4_DIR_REC_LEN(de->name_len); + names++; + } + de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len)); + } + printk("(%i)\n", names); + return (struct stats) { names, space, 1 }; +} + +struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir, + struct dx_entry *entries, int levels) +{ + unsigned blocksize = dir->i_sb->s_blocksize; + unsigned count = dx_get_count (entries), names = 0, space = 0, i; + unsigned bcount = 0; + struct buffer_head *bh; + int err; + printk("%i indexed blocks...\n", count); + for (i = 0; i < count; i++, entries++) + { + u32 block = dx_get_block(entries), hash = i? dx_get_hash(entries): 0; + u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash; + struct stats stats; + printk("%s%3u:%03u hash %8x/%8x ",levels?"":" ", i, block, hash, range); + if (!(bh = ext4_bread (NULL,dir, block, 0,&err))) continue; + stats = levels? + dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1): + dx_show_leaf(hinfo, (struct ext4_dir_entry_2 *) bh->b_data, blocksize, 0); + names += stats.names; + space += stats.space; + bcount += stats.bcount; + brelse (bh); + } + if (bcount) + printk("%snames %u, fullness %u (%u%%)\n", levels?"":" ", + names, space/bcount,(space/bcount)*100/blocksize); + return (struct stats) { names, space, bcount}; +} +#endif /* DX_DEBUG */ + +/* + * Probe for a directory leaf block to search. + * + * dx_probe can return ERR_BAD_DX_DIR, which means there was a format + * error in the directory index, and the caller should fall back to + * searching the directory normally. The callers of dx_probe **MUST** + * check for this error code, and make sure it never gets reflected + * back to userspace. + */ +static struct dx_frame * +dx_probe(struct dentry *dentry, struct inode *dir, + struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err) +{ + unsigned count, indirect; + struct dx_entry *at, *entries, *p, *q, *m; + struct dx_root *root; + struct buffer_head *bh; + struct dx_frame *frame = frame_in; + u32 hash; + + frame->bh = NULL; + if (dentry) + dir = dentry->d_parent->d_inode; + if (!(bh = ext4_bread (NULL,dir, 0, 0, err))) + goto fail; + root = (struct dx_root *) bh->b_data; + if (root->info.hash_version != DX_HASH_TEA && + root->info.hash_version != DX_HASH_HALF_MD4 && + root->info.hash_version != DX_HASH_LEGACY) { + ext4_warning(dir->i_sb, __FUNCTION__, + "Unrecognised inode hash code %d", + root->info.hash_version); + brelse(bh); + *err = ERR_BAD_DX_DIR; + goto fail; + } + hinfo->hash_version = root->info.hash_version; + hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; + if (dentry) + ext4fs_dirhash(dentry->d_name.name, dentry->d_name.len, hinfo); + hash = hinfo->hash; + + if (root->info.unused_flags & 1) { + ext4_warning(dir->i_sb, __FUNCTION__, + "Unimplemented inode hash flags: %#06x", + root->info.unused_flags); + brelse(bh); + *err = ERR_BAD_DX_DIR; + goto fail; + } + + if ((indirect = root->info.indirect_levels) > 1) { + ext4_warning(dir->i_sb, __FUNCTION__, + "Unimplemented inode hash depth: %#06x", + root->info.indirect_levels); + brelse(bh); + *err = ERR_BAD_DX_DIR; + goto fail; + } + + entries = (struct dx_entry *) (((char *)&root->info) + + root->info.info_length); + assert(dx_get_limit(entries) == dx_root_limit(dir, + root->info.info_length)); + dxtrace (printk("Look up %x", hash)); + while (1) + { + count = dx_get_count(entries); + assert (count && count <= dx_get_limit(entries)); + p = entries + 1; + q = entries + count - 1; + while (p <= q) + { + m = p + (q - p)/2; + dxtrace(printk(".")); + if (dx_get_hash(m) > hash) + q = m - 1; + else + p = m + 1; + } + + if (0) // linear search cross check + { + unsigned n = count - 1; + at = entries; + while (n--) + { + dxtrace(printk(",")); + if (dx_get_hash(++at) > hash) + { + at--; + break; + } + } + assert (at == p - 1); + } + + at = p - 1; + dxtrace(printk(" %x->%u\n", at == entries? 0: dx_get_hash(at), dx_get_block(at))); + frame->bh = bh; + frame->entries = entries; + frame->at = at; + if (!indirect--) return frame; + if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err))) + goto fail2; + at = entries = ((struct dx_node *) bh->b_data)->entries; + assert (dx_get_limit(entries) == dx_node_limit (dir)); + frame++; + } +fail2: + while (frame >= frame_in) { + brelse(frame->bh); + frame--; + } +fail: + return NULL; +} + +static void dx_release (struct dx_frame *frames) +{ + if (frames[0].bh == NULL) + return; + + if (((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels) + brelse(frames[1].bh); + brelse(frames[0].bh); +} + +/* + * This function increments the frame pointer to search the next leaf + * block, and reads in the necessary intervening nodes if the search + * should be necessary. Whether or not the search is necessary is + * controlled by the hash parameter. If the hash value is even, then + * the search is only continued if the next block starts with that + * hash value. This is used if we are searching for a specific file. + * + * If the hash value is HASH_NB_ALWAYS, then always go to the next block. + * + * This function returns 1 if the caller should continue to search, + * or 0 if it should not. If there is an error reading one of the + * index blocks, it will a negative error code. + * + * If start_hash is non-null, it will be filled in with the starting + * hash of the next page. + */ +static int ext4_htree_next_block(struct inode *dir, __u32 hash, + struct dx_frame *frame, + struct dx_frame *frames, + __u32 *start_hash) +{ + struct dx_frame *p; + struct buffer_head *bh; + int err, num_frames = 0; + __u32 bhash; + + p = frame; + /* + * Find the next leaf page by incrementing the frame pointer. + * If we run out of entries in the interior node, loop around and + * increment pointer in the parent node. When we break out of + * this loop, num_frames indicates the number of interior + * nodes need to be read. + */ + while (1) { + if (++(p->at) < p->entries + dx_get_count(p->entries)) + break; + if (p == frames) + return 0; + num_frames++; + p--; + } + + /* + * If the hash is 1, then continue only if the next page has a + * continuation hash of any value. This is used for readdir + * handling. Otherwise, check to see if the hash matches the + * desired contiuation hash. If it doesn't, return since + * there's no point to read in the successive index pages. + */ + bhash = dx_get_hash(p->at); + if (start_hash) + *start_hash = bhash; + if ((hash & 1) == 0) { + if ((bhash & ~1) != hash) + return 0; + } + /* + * If the hash is HASH_NB_ALWAYS, we always go to the next + * block so no check is necessary + */ + while (num_frames--) { + if (!(bh = ext4_bread(NULL, dir, dx_get_block(p->at), + 0, &err))) + return err; /* Failure */ + p++; + brelse (p->bh); + p->bh = bh; + p->at = p->entries = ((struct dx_node *) bh->b_data)->entries; + } + return 1; +} + + +/* + * p is at least 6 bytes before the end of page + */ +static inline struct ext4_dir_entry_2 *ext4_next_entry(struct ext4_dir_entry_2 *p) +{ + return (struct ext4_dir_entry_2 *)((char*)p + le16_to_cpu(p->rec_len)); +} + +/* + * This function fills a red-black tree with information from a + * directory block. It returns the number directory entries loaded + * into the tree. If there is an error it is returned in err. + */ +static int htree_dirblock_to_tree(struct file *dir_file, + struct inode *dir, int block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash) +{ + struct buffer_head *bh; + struct ext4_dir_entry_2 *de, *top; + int err, count = 0; + + dxtrace(printk("In htree dirblock_to_tree: block %d\n", block)); + if (!(bh = ext4_bread (NULL, dir, block, 0, &err))) + return err; + + de = (struct ext4_dir_entry_2 *) bh->b_data; + top = (struct ext4_dir_entry_2 *) ((char *) de + + dir->i_sb->s_blocksize - + EXT4_DIR_REC_LEN(0)); + for (; de < top; de = ext4_next_entry(de)) { + ext4fs_dirhash(de->name, de->name_len, hinfo); + if ((hinfo->hash < start_hash) || + ((hinfo->hash == start_hash) && + (hinfo->minor_hash < start_minor_hash))) + continue; + if (de->inode == 0) + continue; + if ((err = ext4_htree_store_dirent(dir_file, + hinfo->hash, hinfo->minor_hash, de)) != 0) { + brelse(bh); + return err; + } + count++; + } + brelse(bh); + return count; +} + + +/* + * This function fills a red-black tree with information from a + * directory. We start scanning the directory in hash order, starting + * at start_hash and start_minor_hash. + * + * This function returns the number of entries inserted into the tree, + * or a negative error code. + */ +int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, + __u32 start_minor_hash, __u32 *next_hash) +{ + struct dx_hash_info hinfo; + struct ext4_dir_entry_2 *de; + struct dx_frame frames[2], *frame; + struct inode *dir; + int block, err; + int count = 0; + int ret; + __u32 hashval; + + dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash, + start_minor_hash)); + dir = dir_file->f_dentry->d_inode; + if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) { + hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version; + hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; + count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo, + start_hash, start_minor_hash); + *next_hash = ~0; + return count; + } + hinfo.hash = start_hash; + hinfo.minor_hash = 0; + frame = dx_probe(NULL, dir_file->f_dentry->d_inode, &hinfo, frames, &err); + if (!frame) + return err; + + /* Add '.' and '..' from the htree header */ + if (!start_hash && !start_minor_hash) { + de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data; + if ((err = ext4_htree_store_dirent(dir_file, 0, 0, de)) != 0) + goto errout; + count++; + } + if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) { + de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data; + de = ext4_next_entry(de); + if ((err = ext4_htree_store_dirent(dir_file, 2, 0, de)) != 0) + goto errout; + count++; + } + + while (1) { + block = dx_get_block(frame->at); + ret = htree_dirblock_to_tree(dir_file, dir, block, &hinfo, + start_hash, start_minor_hash); + if (ret < 0) { + err = ret; + goto errout; + } + count += ret; + hashval = ~0; + ret = ext4_htree_next_block(dir, HASH_NB_ALWAYS, + frame, frames, &hashval); + *next_hash = hashval; + if (ret < 0) { + err = ret; + goto errout; + } + /* + * Stop if: (a) there are no more entries, or + * (b) we have inserted at least one entry and the + * next hash value is not a continuation + */ + if ((ret == 0) || + (count && ((hashval & 1) == 0))) + break; + } + dx_release(frames); + dxtrace(printk("Fill tree: returned %d entries, next hash: %x\n", + count, *next_hash)); + return count; +errout: + dx_release(frames); + return (err); +} + + +/* + * Directory block splitting, compacting + */ + +static int dx_make_map (struct ext4_dir_entry_2 *de, int size, + struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) +{ + int count = 0; + char *base = (char *) de; + struct dx_hash_info h = *hinfo; + + while ((char *) de < base + size) + { + if (de->name_len && de->inode) { + ext4fs_dirhash(de->name, de->name_len, &h); + map_tail--; + map_tail->hash = h.hash; + map_tail->offs = (u32) ((char *) de - base); + count++; + cond_resched(); + } + /* XXX: do we need to check rec_len == 0 case? -Chris */ + de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len)); + } + return count; +} + +static void dx_sort_map (struct dx_map_entry *map, unsigned count) +{ + struct dx_map_entry *p, *q, *top = map + count - 1; + int more; + /* Combsort until bubble sort doesn't suck */ + while (count > 2) { + count = count*10/13; + if (count - 9 < 2) /* 9, 10 -> 11 */ + count = 11; + for (p = top, q = p - count; q >= map; p--, q--) + if (p->hash < q->hash) + swap(*p, *q); + } + /* Garden variety bubble sort */ + do { + more = 0; + q = top; + while (q-- > map) { + if (q[1].hash >= q[0].hash) + continue; + swap(*(q+1), *q); + more = 1; + } + } while(more); +} + +static void dx_insert_block(struct dx_frame *frame, u32 hash, u32 block) +{ + struct dx_entry *entries = frame->entries; + struct dx_entry *old = frame->at, *new = old + 1; + int count = dx_get_count(entries); + + assert(count < dx_get_limit(entries)); + assert(old < entries + count); + memmove(new + 1, new, (char *)(entries + count) - (char *)(new)); + dx_set_hash(new, hash); + dx_set_block(new, block); + dx_set_count(entries, count + 1); +} +#endif + + +static void ext4_update_dx_flag(struct inode *inode) +{ + if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_COMPAT_DIR_INDEX)) + EXT4_I(inode)->i_flags &= ~EXT4_INDEX_FL; +} + +/* + * NOTE! unlike strncmp, ext4_match returns 1 for success, 0 for failure. + * + * `len <= EXT4_NAME_LEN' is guaranteed by caller. + * `de != NULL' is guaranteed by caller. + */ +static inline int ext4_match (int len, const char * const name, + struct ext4_dir_entry_2 * de) +{ + if (len != de->name_len) + return 0; + if (!de->inode) + return 0; + return !memcmp(name, de->name, len); +} + +/* + * Returns 0 if not found, -1 on failure, and 1 on success + */ +static inline int search_dirblock(struct buffer_head * bh, + struct inode *dir, + struct dentry *dentry, + unsigned long offset, + struct ext4_dir_entry_2 ** res_dir) +{ + struct ext4_dir_entry_2 * de; + char * dlimit; + int de_len; + const char *name = dentry->d_name.name; + int namelen = dentry->d_name.len; + + de = (struct ext4_dir_entry_2 *) bh->b_data; + dlimit = bh->b_data + dir->i_sb->s_blocksize; + while ((char *) de < dlimit) { + /* this code is executed quadratically often */ + /* do minimal checking `by hand' */ + + if ((char *) de + namelen <= dlimit && + ext4_match (namelen, name, de)) { + /* found a match - just to be sure, do a full check */ + if (!ext4_check_dir_entry("ext4_find_entry", + dir, de, bh, offset)) + return -1; + *res_dir = de; + return 1; + } + /* prevent looping on a bad block */ + de_len = le16_to_cpu(de->rec_len); + if (de_len <= 0) + return -1; + offset += de_len; + de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); + } + return 0; +} + + +/* + * ext4_find_entry() + * + * finds an entry in the specified directory with the wanted name. It + * returns the cache buffer in which the entry was found, and the entry + * itself (as a parameter - res_dir). It does NOT read the inode of the + * entry - you'll have to do that yourself if you want to. + * + * The returned buffer_head has ->b_count elevated. The caller is expected + * to brelse() it when appropriate. + */ +static struct buffer_head * ext4_find_entry (struct dentry *dentry, + struct ext4_dir_entry_2 ** res_dir) +{ + struct super_block * sb; + struct buffer_head * bh_use[NAMEI_RA_SIZE]; + struct buffer_head * bh, *ret = NULL; + unsigned long start, block, b; + int ra_max = 0; /* Number of bh's in the readahead + buffer, bh_use[] */ + int ra_ptr = 0; /* Current index into readahead + buffer */ + int num = 0; + int nblocks, i, err; + struct inode *dir = dentry->d_parent->d_inode; + int namelen; + const u8 *name; + unsigned blocksize; + + *res_dir = NULL; + sb = dir->i_sb; + blocksize = sb->s_blocksize; + namelen = dentry->d_name.len; + name = dentry->d_name.name; + if (namelen > EXT4_NAME_LEN) + return NULL; +#ifdef CONFIG_EXT4_INDEX + if (is_dx(dir)) { + bh = ext4_dx_find_entry(dentry, res_dir, &err); + /* + * On success, or if the error was file not found, + * return. Otherwise, fall back to doing a search the + * old fashioned way. + */ + if (bh || (err != ERR_BAD_DX_DIR)) + return bh; + dxtrace(printk("ext4_find_entry: dx failed, falling back\n")); + } +#endif + nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb); + start = EXT4_I(dir)->i_dir_start_lookup; + if (start >= nblocks) + start = 0; + block = start; +restart: + do { + /* + * We deal with the read-ahead logic here. + */ + if (ra_ptr >= ra_max) { + /* Refill the readahead buffer */ + ra_ptr = 0; + b = block; + for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) { + /* + * Terminate if we reach the end of the + * directory and must wrap, or if our + * search has finished at this block. + */ + if (b >= nblocks || (num && block == start)) { + bh_use[ra_max] = NULL; + break; + } + num++; + bh = ext4_getblk(NULL, dir, b++, 0, &err); + bh_use[ra_max] = bh; + if (bh) + ll_rw_block(READ_META, 1, &bh); + } + } + if ((bh = bh_use[ra_ptr++]) == NULL) + goto next; + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) { + /* read error, skip block & hope for the best */ + ext4_error(sb, __FUNCTION__, "reading directory #%lu " + "offset %lu", dir->i_ino, block); + brelse(bh); + goto next; + } + i = search_dirblock(bh, dir, dentry, + block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); + if (i == 1) { + EXT4_I(dir)->i_dir_start_lookup = block; + ret = bh; + goto cleanup_and_exit; + } else { + brelse(bh); + if (i < 0) + goto cleanup_and_exit; + } + next: + if (++block >= nblocks) + block = 0; + } while (block != start); + + /* + * If the directory has grown while we were searching, then + * search the last part of the directory before giving up. + */ + block = nblocks; + nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb); + if (block < nblocks) { + start = 0; + goto restart; + } + +cleanup_and_exit: + /* Clean up the read-ahead blocks */ + for (; ra_ptr < ra_max; ra_ptr++) + brelse (bh_use[ra_ptr]); + return ret; +} + +#ifdef CONFIG_EXT4_INDEX +static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry, + struct ext4_dir_entry_2 **res_dir, int *err) +{ + struct super_block * sb; + struct dx_hash_info hinfo; + u32 hash; + struct dx_frame frames[2], *frame; + struct ext4_dir_entry_2 *de, *top; + struct buffer_head *bh; + unsigned long block; + int retval; + int namelen = dentry->d_name.len; + const u8 *name = dentry->d_name.name; + struct inode *dir = dentry->d_parent->d_inode; + + sb = dir->i_sb; + /* NFS may look up ".." - look at dx_root directory block */ + if (namelen > 2 || name[0] != '.'||(name[1] != '.' && name[1] != '\0')){ + if (!(frame = dx_probe(dentry, NULL, &hinfo, frames, err))) + return NULL; + } else { + frame = frames; + frame->bh = NULL; /* for dx_release() */ + frame->at = (struct dx_entry *)frames; /* hack for zero entry*/ + dx_set_block(frame->at, 0); /* dx_root block is 0 */ + } + hash = hinfo.hash; + do { + block = dx_get_block(frame->at); + if (!(bh = ext4_bread (NULL,dir, block, 0, err))) + goto errout; + de = (struct ext4_dir_entry_2 *) bh->b_data; + top = (struct ext4_dir_entry_2 *) ((char *) de + sb->s_blocksize - + EXT4_DIR_REC_LEN(0)); + for (; de < top; de = ext4_next_entry(de)) + if (ext4_match (namelen, name, de)) { + if (!ext4_check_dir_entry("ext4_find_entry", + dir, de, bh, + (block<<EXT4_BLOCK_SIZE_BITS(sb)) + +((char *)de - bh->b_data))) { + brelse (bh); + goto errout; + } + *res_dir = de; + dx_release (frames); + return bh; + } + brelse (bh); + /* Check to see if we should continue to search */ + retval = ext4_htree_next_block(dir, hash, frame, + frames, NULL); + if (retval < 0) { + ext4_warning(sb, __FUNCTION__, + "error reading index page in directory #%lu", + dir->i_ino); + *err = retval; + goto errout; + } + } while (retval == 1); + + *err = -ENOENT; +errout: + dxtrace(printk("%s not found\n", name)); + dx_release (frames); + return NULL; +} +#endif + +static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +{ + struct inode * inode; + struct ext4_dir_entry_2 * de; + struct buffer_head * bh; + + if (dentry->d_name.len > EXT4_NAME_LEN) + return ERR_PTR(-ENAMETOOLONG); + + bh = ext4_find_entry(dentry, &de); + inode = NULL; + if (bh) { + unsigned long ino = le32_to_cpu(de->inode); + brelse (bh); + if (!ext4_valid_inum(dir->i_sb, ino)) { + ext4_error(dir->i_sb, "ext4_lookup", + "bad inode number: %lu", ino); + inode = NULL; + } else + inode = iget(dir->i_sb, ino); + + if (!inode) + return ERR_PTR(-EACCES); + } + return d_splice_alias(inode, dentry); +} + + +struct dentry *ext4_get_parent(struct dentry *child) +{ + unsigned long ino; + struct dentry *parent; + struct inode *inode; + struct dentry dotdot; + struct ext4_dir_entry_2 * de; + struct buffer_head *bh; + + dotdot.d_name.name = ".."; + dotdot.d_name.len = 2; + dotdot.d_parent = child; /* confusing, isn't it! */ + + bh = ext4_find_entry(&dotdot, &de); + inode = NULL; + if (!bh) + return ERR_PTR(-ENOENT); + ino = le32_to_cpu(de->inode); + brelse(bh); + + if (!ext4_valid_inum(child->d_inode->i_sb, ino)) { + ext4_error(child->d_inode->i_sb, "ext4_get_parent", + "bad inode number: %lu", ino); + inode = NULL; + } else + inode = iget(child->d_inode->i_sb, ino); + + if (!inode) + return ERR_PTR(-EACCES); + + parent = d_alloc_anon(inode); + if (!parent) { + iput(inode); + parent = ERR_PTR(-ENOMEM); + } + return parent; +} + +#define S_SHIFT 12 +static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { + [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, + [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR, + [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV, + [S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV, + [S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO, + [S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK, + [S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK, +}; + +static inline void ext4_set_de_type(struct super_block *sb, + struct ext4_dir_entry_2 *de, + umode_t mode) { + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE)) + de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; +} + +#ifdef CONFIG_EXT4_INDEX +static struct ext4_dir_entry_2 * +dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count) +{ + unsigned rec_len = 0; + + while (count--) { + struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + map->offs); + rec_len = EXT4_DIR_REC_LEN(de->name_len); + memcpy (to, de, rec_len); + ((struct ext4_dir_entry_2 *) to)->rec_len = + cpu_to_le16(rec_len); + de->inode = 0; + map++; + to += rec_len; + } + return (struct ext4_dir_entry_2 *) (to - rec_len); +} + +static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size) +{ + struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base; + unsigned rec_len = 0; + + prev = to = de; + while ((char*)de < base + size) { + next = (struct ext4_dir_entry_2 *) ((char *) de + + le16_to_cpu(de->rec_len)); + if (de->inode && de->name_len) { + rec_len = EXT4_DIR_REC_LEN(de->name_len); + if (de > to) + memmove(to, de, rec_len); + to->rec_len = cpu_to_le16(rec_len); + prev = to; + to = (struct ext4_dir_entry_2 *) (((char *) to) + rec_len); + } + de = next; + } + return prev; +} + +static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, + struct buffer_head **bh,struct dx_frame *frame, + struct dx_hash_info *hinfo, int *error) +{ + unsigned blocksize = dir->i_sb->s_blocksize; + unsigned count, continued; + struct buffer_head *bh2; + u32 newblock; + u32 hash2; + struct dx_map_entry *map; + char *data1 = (*bh)->b_data, *data2; + unsigned split; + struct ext4_dir_entry_2 *de = NULL, *de2; + int err; + + bh2 = ext4_append (handle, dir, &newblock, error); + if (!(bh2)) { + brelse(*bh); + *bh = NULL; + goto errout; + } + + BUFFER_TRACE(*bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, *bh); + if (err) { + journal_error: + brelse(*bh); + brelse(bh2); + *bh = NULL; + ext4_std_error(dir->i_sb, err); + goto errout; + } + BUFFER_TRACE(frame->bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, frame->bh); + if (err) + goto journal_error; + + data2 = bh2->b_data; + + /* create map in the end of data2 block */ + map = (struct dx_map_entry *) (data2 + blocksize); + count = dx_make_map ((struct ext4_dir_entry_2 *) data1, + blocksize, hinfo, map); + map -= count; + split = count/2; // need to adjust to actual middle + dx_sort_map (map, count); + hash2 = map[split].hash; + continued = hash2 == map[split - 1].hash; + dxtrace(printk("Split block %i at %x, %i/%i\n", + dx_get_block(frame->at), hash2, split, count-split)); + + /* Fancy dance to stay within two buffers */ + de2 = dx_move_dirents(data1, data2, map + split, count - split); + de = dx_pack_dirents(data1,blocksize); + de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de); + de2->rec_len = cpu_to_le16(data2 + blocksize - (char *) de2); + dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1)); + dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1)); + + /* Which block gets the new entry? */ + if (hinfo->hash >= hash2) + { + swap(*bh, bh2); + de = de2; + } + dx_insert_block (frame, hash2 + continued, newblock); + err = ext4_journal_dirty_metadata (handle, bh2); + if (err) + goto journal_error; + err = ext4_journal_dirty_metadata (handle, frame->bh); + if (err) + goto journal_error; + brelse (bh2); + dxtrace(dx_show_index ("frame", frame->entries)); +errout: + return de; +} +#endif + + +/* + * Add a new entry into a directory (leaf) block. If de is non-NULL, + * it points to a directory entry which is guaranteed to be large + * enough for new directory entry. If de is NULL, then + * add_dirent_to_buf will attempt search the directory block for + * space. It will return -ENOSPC if no space is available, and -EIO + * and -EEXIST if directory entry already exists. + * + * NOTE! bh is NOT released in the case where ENOSPC is returned. In + * all other cases bh is released. + */ +static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, + struct inode *inode, struct ext4_dir_entry_2 *de, + struct buffer_head * bh) +{ + struct inode *dir = dentry->d_parent->d_inode; + const char *name = dentry->d_name.name; + int namelen = dentry->d_name.len; + unsigned long offset = 0; + unsigned short reclen; + int nlen, rlen, err; + char *top; + + reclen = EXT4_DIR_REC_LEN(namelen); + if (!de) { + de = (struct ext4_dir_entry_2 *)bh->b_data; + top = bh->b_data + dir->i_sb->s_blocksize - reclen; + while ((char *) de <= top) { + if (!ext4_check_dir_entry("ext4_add_entry", dir, de, + bh, offset)) { + brelse (bh); + return -EIO; + } + if (ext4_match (namelen, name, de)) { + brelse (bh); + return -EEXIST; + } + nlen = EXT4_DIR_REC_LEN(de->name_len); + rlen = le16_to_cpu(de->rec_len); + if ((de->inode? rlen - nlen: rlen) >= reclen) + break; + de = (struct ext4_dir_entry_2 *)((char *)de + rlen); + offset += rlen; + } + if ((char *) de > top) + return -ENOSPC; + } + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, bh); + if (err) { + ext4_std_error(dir->i_sb, err); + brelse(bh); + return err; + } + + /* By now the buffer is marked for journaling */ + nlen = EXT4_DIR_REC_LEN(de->name_len); + rlen = le16_to_cpu(de->rec_len); + if (de->inode) { + struct ext4_dir_entry_2 *de1 = (struct ext4_dir_entry_2 *)((char *)de + nlen); + de1->rec_len = cpu_to_le16(rlen - nlen); + de->rec_len = cpu_to_le16(nlen); + de = de1; + } + de->file_type = EXT4_FT_UNKNOWN; + if (inode) { + de->inode = cpu_to_le32(inode->i_ino); + ext4_set_de_type(dir->i_sb, de, inode->i_mode); + } else + de->inode = 0; + de->name_len = namelen; + memcpy (de->name, name, namelen); + /* + * XXX shouldn't update any times until successful + * completion of syscall, but too many callers depend + * on this. + * + * XXX similarly, too many callers depend on + * ext4_new_inode() setting the times, but error + * recovery deletes the inode, so the worst that can + * happen is that the times are slightly out of date + * and/or different from the directory change time. + */ + dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; + ext4_update_dx_flag(dir); + dir->i_version++; + ext4_mark_inode_dirty(handle, dir); + BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata"); + err = ext4_journal_dirty_metadata(handle, bh); + if (err) + ext4_std_error(dir->i_sb, err); + brelse(bh); + return 0; +} + +#ifdef CONFIG_EXT4_INDEX +/* + * This converts a one block unindexed directory to a 3 block indexed + * directory, and adds the dentry to the indexed directory. + */ +static int make_indexed_dir(handle_t *handle, struct dentry *dentry, + struct inode *inode, struct buffer_head *bh) +{ + struct inode *dir = dentry->d_parent->d_inode; + const char *name = dentry->d_name.name; + int namelen = dentry->d_name.len; + struct buffer_head *bh2; + struct dx_root *root; + struct dx_frame frames[2], *frame; + struct dx_entry *entries; + struct ext4_dir_entry_2 *de, *de2; + char *data1, *top; + unsigned len; + int retval; + unsigned blocksize; + struct dx_hash_info hinfo; + u32 block; + struct fake_dirent *fde; + + blocksize = dir->i_sb->s_blocksize; + dxtrace(printk("Creating index\n")); + retval = ext4_journal_get_write_access(handle, bh); + if (retval) { + ext4_std_error(dir->i_sb, retval); + brelse(bh); + return retval; + } + root = (struct dx_root *) bh->b_data; + + bh2 = ext4_append (handle, dir, &block, &retval); + if (!(bh2)) { + brelse(bh); + return retval; + } + EXT4_I(dir)->i_flags |= EXT4_INDEX_FL; + data1 = bh2->b_data; + + /* The 0th block becomes the root, move the dirents out */ + fde = &root->dotdot; + de = (struct ext4_dir_entry_2 *)((char *)fde + le16_to_cpu(fde->rec_len)); + len = ((char *) root) + blocksize - (char *) de; + memcpy (data1, de, len); + de = (struct ext4_dir_entry_2 *) data1; + top = data1 + len; + while ((char *)(de2=(void*)de+le16_to_cpu(de->rec_len)) < top) + de = de2; + de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de); + /* Initialize the root; the dot dirents already exist */ + de = (struct ext4_dir_entry_2 *) (&root->dotdot); + de->rec_len = cpu_to_le16(blocksize - EXT4_DIR_REC_LEN(2)); + memset (&root->info, 0, sizeof(root->info)); + root->info.info_length = sizeof(root->info); + root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version; + entries = root->entries; + dx_set_block (entries, 1); + dx_set_count (entries, 1); + dx_set_limit (entries, dx_root_limit(dir, sizeof(root->info))); + + /* Initialize as for dx_probe */ + hinfo.hash_version = root->info.hash_version; + hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; + ext4fs_dirhash(name, namelen, &hinfo); + frame = frames; + frame->entries = entries; + frame->at = entries; + frame->bh = bh; + bh = bh2; + de = do_split(handle,dir, &bh, frame, &hinfo, &retval); + dx_release (frames); + if (!(de)) + return retval; + + return add_dirent_to_buf(handle, dentry, inode, de, bh); +} +#endif + +/* + * ext4_add_entry() + * + * adds a file entry to the specified directory, using the same + * semantics as ext4_find_entry(). It returns NULL if it failed. + * + * NOTE!! The inode part of 'de' is left at 0 - which means you + * may not sleep between calling this and putting something into + * the entry, as someone else might have used it while you slept. + */ +static int ext4_add_entry (handle_t *handle, struct dentry *dentry, + struct inode *inode) +{ + struct inode *dir = dentry->d_parent->d_inode; + unsigned long offset; + struct buffer_head * bh; + struct ext4_dir_entry_2 *de; + struct super_block * sb; + int retval; +#ifdef CONFIG_EXT4_INDEX + int dx_fallback=0; +#endif + unsigned blocksize; + u32 block, blocks; + + sb = dir->i_sb; + blocksize = sb->s_blocksize; + if (!dentry->d_name.len) + return -EINVAL; +#ifdef CONFIG_EXT4_INDEX + if (is_dx(dir)) { + retval = ext4_dx_add_entry(handle, dentry, inode); + if (!retval || (retval != ERR_BAD_DX_DIR)) + return retval; + EXT4_I(dir)->i_flags &= ~EXT4_INDEX_FL; + dx_fallback++; + ext4_mark_inode_dirty(handle, dir); + } +#endif + blocks = dir->i_size >> sb->s_blocksize_bits; + for (block = 0, offset = 0; block < blocks; block++) { + bh = ext4_bread(handle, dir, block, 0, &retval); + if(!bh) + return retval; + retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh); + if (retval != -ENOSPC) + return retval; + +#ifdef CONFIG_EXT4_INDEX + if (blocks == 1 && !dx_fallback && + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) + return make_indexed_dir(handle, dentry, inode, bh); +#endif + brelse(bh); + } + bh = ext4_append(handle, dir, &block, &retval); + if (!bh) + return retval; + de = (struct ext4_dir_entry_2 *) bh->b_data; + de->inode = 0; + de->rec_len = cpu_to_le16(blocksize); + return add_dirent_to_buf(handle, dentry, inode, de, bh); +} + +#ifdef CONFIG_EXT4_INDEX +/* + * Returns 0 for success, or a negative error value + */ +static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, + struct inode *inode) +{ + struct dx_frame frames[2], *frame; + struct dx_entry *entries, *at; + struct dx_hash_info hinfo; + struct buffer_head * bh; + struct inode *dir = dentry->d_parent->d_inode; + struct super_block * sb = dir->i_sb; + struct ext4_dir_entry_2 *de; + int err; + + frame = dx_probe(dentry, NULL, &hinfo, frames, &err); + if (!frame) + return err; + entries = frame->entries; + at = frame->at; + + if (!(bh = ext4_bread(handle,dir, dx_get_block(frame->at), 0, &err))) + goto cleanup; + + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, bh); + if (err) + goto journal_error; + + err = add_dirent_to_buf(handle, dentry, inode, NULL, bh); + if (err != -ENOSPC) { + bh = NULL; + goto cleanup; + } + + /* Block full, should compress but for now just split */ + dxtrace(printk("using %u of %u node entries\n", + dx_get_count(entries), dx_get_limit(entries))); + /* Need to split index? */ + if (dx_get_count(entries) == dx_get_limit(entries)) { + u32 newblock; + unsigned icount = dx_get_count(entries); + int levels = frame - frames; + struct dx_entry *entries2; + struct dx_node *node2; + struct buffer_head *bh2; + + if (levels && (dx_get_count(frames->entries) == + dx_get_limit(frames->entries))) { + ext4_warning(sb, __FUNCTION__, + "Directory index full!"); + err = -ENOSPC; + goto cleanup; + } + bh2 = ext4_append (handle, dir, &newblock, &err); + if (!(bh2)) + goto cleanup; + node2 = (struct dx_node *)(bh2->b_data); + entries2 = node2->entries; + node2->fake.rec_len = cpu_to_le16(sb->s_blocksize); + node2->fake.inode = 0; + BUFFER_TRACE(frame->bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, frame->bh); + if (err) + goto journal_error; + if (levels) { + unsigned icount1 = icount/2, icount2 = icount - icount1; + unsigned hash2 = dx_get_hash(entries + icount1); + dxtrace(printk("Split index %i/%i\n", icount1, icount2)); + + BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */ + err = ext4_journal_get_write_access(handle, + frames[0].bh); + if (err) + goto journal_error; + + memcpy ((char *) entries2, (char *) (entries + icount1), + icount2 * sizeof(struct dx_entry)); + dx_set_count (entries, icount1); + dx_set_count (entries2, icount2); + dx_set_limit (entries2, dx_node_limit(dir)); + + /* Which index block gets the new entry? */ + if (at - entries >= icount1) { + frame->at = at = at - entries - icount1 + entries2; + frame->entries = entries = entries2; + swap(frame->bh, bh2); + } + dx_insert_block (frames + 0, hash2, newblock); + dxtrace(dx_show_index ("node", frames[1].entries)); + dxtrace(dx_show_index ("node", + ((struct dx_node *) bh2->b_data)->entries)); + err = ext4_journal_dirty_metadata(handle, bh2); + if (err) + goto journal_error; + brelse (bh2); + } else { + dxtrace(printk("Creating second level index...\n")); + memcpy((char *) entries2, (char *) entries, + icount * sizeof(struct dx_entry)); + dx_set_limit(entries2, dx_node_limit(dir)); + + /* Set up root */ + dx_set_count(entries, 1); + dx_set_block(entries + 0, newblock); + ((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1; + + /* Add new access path frame */ + frame = frames + 1; + frame->at = at = at - entries + entries2; + frame->entries = entries = entries2; + frame->bh = bh2; + err = ext4_journal_get_write_access(handle, + frame->bh); + if (err) + goto journal_error; + } + ext4_journal_dirty_metadata(handle, frames[0].bh); + } + de = do_split(handle, dir, &bh, frame, &hinfo, &err); + if (!de) + goto cleanup; + err = add_dirent_to_buf(handle, dentry, inode, de, bh); + bh = NULL; + goto cleanup; + +journal_error: + ext4_std_error(dir->i_sb, err); +cleanup: + if (bh) + brelse(bh); + dx_release(frames); + return err; +} +#endif + +/* + * ext4_delete_entry deletes a directory entry by merging it with the + * previous entry + */ +static int ext4_delete_entry (handle_t *handle, + struct inode * dir, + struct ext4_dir_entry_2 * de_del, + struct buffer_head * bh) +{ + struct ext4_dir_entry_2 * de, * pde; + int i; + + i = 0; + pde = NULL; + de = (struct ext4_dir_entry_2 *) bh->b_data; + while (i < bh->b_size) { + if (!ext4_check_dir_entry("ext4_delete_entry", dir, de, bh, i)) + return -EIO; + if (de == de_del) { + BUFFER_TRACE(bh, "get_write_access"); + ext4_journal_get_write_access(handle, bh); + if (pde) + pde->rec_len = + cpu_to_le16(le16_to_cpu(pde->rec_len) + + le16_to_cpu(de->rec_len)); + else + de->inode = 0; + dir->i_version++; + BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata"); + ext4_journal_dirty_metadata(handle, bh); + return 0; + } + i += le16_to_cpu(de->rec_len); + pde = de; + de = (struct ext4_dir_entry_2 *) + ((char *) de + le16_to_cpu(de->rec_len)); + } + return -ENOENT; +} + +/* + * ext4_mark_inode_dirty is somewhat expensive, so unlike ext2 we + * do not perform it in these functions. We perform it at the call site, + * if it is needed. + */ +static inline void ext4_inc_count(handle_t *handle, struct inode *inode) +{ + inc_nlink(inode); +} + +static inline void ext4_dec_count(handle_t *handle, struct inode *inode) +{ + drop_nlink(inode); +} + +static int ext4_add_nondir(handle_t *handle, + struct dentry *dentry, struct inode *inode) +{ + int err = ext4_add_entry(handle, dentry, inode); + if (!err) { + ext4_mark_inode_dirty(handle, inode); + d_instantiate(dentry, inode); + return 0; + } + ext4_dec_count(handle, inode); + iput(inode); + return err; +} + +/* + * By the time this is called, we already have created + * the directory cache entry for the new file, but it + * is so far negative - it has no inode. + * + * If the create succeeds, we fill in the inode information + * with d_instantiate(). + */ +static int ext4_create (struct inode * dir, struct dentry * dentry, int mode, + struct nameidata *nd) +{ + handle_t *handle; + struct inode * inode; + int err, retries = 0; + +retry: + handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + + 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(dir)) + handle->h_sync = 1; + + inode = ext4_new_inode (handle, dir, mode); + err = PTR_ERR(inode); + if (!IS_ERR(inode)) { + inode->i_op = &ext4_file_inode_operations; + inode->i_fop = &ext4_file_operations; + ext4_set_aops(inode); + err = ext4_add_nondir(handle, dentry, inode); + } + ext4_journal_stop(handle); + if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) + goto retry; + return err; +} + +static int ext4_mknod (struct inode * dir, struct dentry *dentry, + int mode, dev_t rdev) +{ + handle_t *handle; + struct inode *inode; + int err, retries = 0; + + if (!new_valid_dev(rdev)) + return -EINVAL; + +retry: + handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + + 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(dir)) + handle->h_sync = 1; + + inode = ext4_new_inode (handle, dir, mode); + err = PTR_ERR(inode); + if (!IS_ERR(inode)) { + init_special_inode(inode, inode->i_mode, rdev); +#ifdef CONFIG_EXT4DEV_FS_XATTR + inode->i_op = &ext4_special_inode_operations; +#endif + err = ext4_add_nondir(handle, dentry, inode); + } + ext4_journal_stop(handle); + if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) + goto retry; + return err; +} + +static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode) +{ + handle_t *handle; + struct inode * inode; + struct buffer_head * dir_block; + struct ext4_dir_entry_2 * de; + int err, retries = 0; + + if (dir->i_nlink >= EXT4_LINK_MAX) + return -EMLINK; + +retry: + handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 + + 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(dir)) + handle->h_sync = 1; + + inode = ext4_new_inode (handle, dir, S_IFDIR | mode); + err = PTR_ERR(inode); + if (IS_ERR(inode)) + goto out_stop; + + inode->i_op = &ext4_dir_inode_operations; + inode->i_fop = &ext4_dir_operations; + inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize; + dir_block = ext4_bread (handle, inode, 0, 1, &err); + if (!dir_block) { + drop_nlink(inode); /* is this nlink == 0? */ + ext4_mark_inode_dirty(handle, inode); + iput (inode); + goto out_stop; + } + BUFFER_TRACE(dir_block, "get_write_access"); + ext4_journal_get_write_access(handle, dir_block); + de = (struct ext4_dir_entry_2 *) dir_block->b_data; + de->inode = cpu_to_le32(inode->i_ino); + de->name_len = 1; + de->rec_len = cpu_to_le16(EXT4_DIR_REC_LEN(de->name_len)); + strcpy (de->name, "."); + ext4_set_de_type(dir->i_sb, de, S_IFDIR); + de = (struct ext4_dir_entry_2 *) + ((char *) de + le16_to_cpu(de->rec_len)); + de->inode = cpu_to_le32(dir->i_ino); + de->rec_len = cpu_to_le16(inode->i_sb->s_blocksize-EXT4_DIR_REC_LEN(1)); + de->name_len = 2; + strcpy (de->name, ".."); + ext4_set_de_type(dir->i_sb, de, S_IFDIR); + inode->i_nlink = 2; + BUFFER_TRACE(dir_block, "call ext4_journal_dirty_metadata"); + ext4_journal_dirty_metadata(handle, dir_block); + brelse (dir_block); + ext4_mark_inode_dirty(handle, inode); + err = ext4_add_entry (handle, dentry, inode); + if (err) { + inode->i_nlink = 0; + ext4_mark_inode_dirty(handle, inode); + iput (inode); + goto out_stop; + } + inc_nlink(dir); + ext4_update_dx_flag(dir); + ext4_mark_inode_dirty(handle, dir); + d_instantiate(dentry, inode); +out_stop: + ext4_journal_stop(handle); + if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) + goto retry; + return err; +} + +/* + * routine to check that the specified directory is empty (for rmdir) + */ +static int empty_dir (struct inode * inode) +{ + unsigned long offset; + struct buffer_head * bh; + struct ext4_dir_entry_2 * de, * de1; + struct super_block * sb; + int err = 0; + + sb = inode->i_sb; + if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) || + !(bh = ext4_bread (NULL, inode, 0, 0, &err))) { + if (err) + ext4_error(inode->i_sb, __FUNCTION__, + "error %d reading directory #%lu offset 0", + err, inode->i_ino); + else + ext4_warning(inode->i_sb, __FUNCTION__, + "bad directory (dir #%lu) - no data block", + inode->i_ino); + return 1; + } + de = (struct ext4_dir_entry_2 *) bh->b_data; + de1 = (struct ext4_dir_entry_2 *) + ((char *) de + le16_to_cpu(de->rec_len)); + if (le32_to_cpu(de->inode) != inode->i_ino || + !le32_to_cpu(de1->inode) || + strcmp (".", de->name) || + strcmp ("..", de1->name)) { + ext4_warning (inode->i_sb, "empty_dir", + "bad directory (dir #%lu) - no `.' or `..'", + inode->i_ino); + brelse (bh); + return 1; + } + offset = le16_to_cpu(de->rec_len) + le16_to_cpu(de1->rec_len); + de = (struct ext4_dir_entry_2 *) + ((char *) de1 + le16_to_cpu(de1->rec_len)); + while (offset < inode->i_size ) { + if (!bh || + (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) { + err = 0; + brelse (bh); + bh = ext4_bread (NULL, inode, + offset >> EXT4_BLOCK_SIZE_BITS(sb), 0, &err); + if (!bh) { + if (err) + ext4_error(sb, __FUNCTION__, + "error %d reading directory" + " #%lu offset %lu", + err, inode->i_ino, offset); + offset += sb->s_blocksize; + continue; + } + de = (struct ext4_dir_entry_2 *) bh->b_data; + } + if (!ext4_check_dir_entry("empty_dir", inode, de, bh, offset)) { + de = (struct ext4_dir_entry_2 *)(bh->b_data + + sb->s_blocksize); + offset = (offset | (sb->s_blocksize - 1)) + 1; + continue; + } + if (le32_to_cpu(de->inode)) { + brelse (bh); + return 0; + } + offset += le16_to_cpu(de->rec_len); + de = (struct ext4_dir_entry_2 *) + ((char *) de + le16_to_cpu(de->rec_len)); + } + brelse (bh); + return 1; +} + +/* ext4_orphan_add() links an unlinked or truncated inode into a list of + * such inodes, starting at the superblock, in case we crash before the + * file is closed/deleted, or in case the inode truncate spans multiple + * transactions and the last transaction is not recovered after a crash. + * + * At filesystem recovery time, we walk this list deleting unlinked + * inodes and truncating linked inodes in ext4_orphan_cleanup(). + */ +int ext4_orphan_add(handle_t *handle, struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + struct ext4_iloc iloc; + int err = 0, rc; + + lock_super(sb); + if (!list_empty(&EXT4_I(inode)->i_orphan)) + goto out_unlock; + + /* Orphan handling is only valid for files with data blocks + * being truncated, or files being unlinked. */ + + /* @@@ FIXME: Observation from aviro: + * I think I can trigger J_ASSERT in ext4_orphan_add(). We block + * here (on lock_super()), so race with ext4_link() which might bump + * ->i_nlink. For, say it, character device. Not a regular file, + * not a directory, not a symlink and ->i_nlink > 0. + */ + J_ASSERT ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) || inode->i_nlink == 0); + + BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); + err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); + if (err) + goto out_unlock; + + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto out_unlock; + + /* Insert this inode at the head of the on-disk orphan list... */ + NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan); + EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); + err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh); + rc = ext4_mark_iloc_dirty(handle, inode, &iloc); + if (!err) + err = rc; + + /* Only add to the head of the in-memory list if all the + * previous operations succeeded. If the orphan_add is going to + * fail (possibly taking the journal offline), we can't risk + * leaving the inode on the orphan list: stray orphan-list + * entries can cause panics at unmount time. + * + * This is safe: on error we're going to ignore the orphan list + * anyway on the next recovery. */ + if (!err) + list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan); + + jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); + jbd_debug(4, "orphan inode %lu will point to %d\n", + inode->i_ino, NEXT_ORPHAN(inode)); +out_unlock: + unlock_super(sb); + ext4_std_error(inode->i_sb, err); + return err; +} + +/* + * ext4_orphan_del() removes an unlinked or truncated inode from the list + * of such inodes stored on disk, because it is finally being cleaned up. + */ +int ext4_orphan_del(handle_t *handle, struct inode *inode) +{ + struct list_head *prev; + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_sb_info *sbi; + unsigned long ino_next; + struct ext4_iloc iloc; + int err = 0; + + lock_super(inode->i_sb); + if (list_empty(&ei->i_orphan)) { + unlock_super(inode->i_sb); + return 0; + } + + ino_next = NEXT_ORPHAN(inode); + prev = ei->i_orphan.prev; + sbi = EXT4_SB(inode->i_sb); + + jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino); + + list_del_init(&ei->i_orphan); + + /* If we're on an error path, we may not have a valid + * transaction handle with which to update the orphan list on + * disk, but we still need to remove the inode from the linked + * list in memory. */ + if (!handle) + goto out; + + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto out_err; + + if (prev == &sbi->s_orphan) { + jbd_debug(4, "superblock will point to %lu\n", ino_next); + BUFFER_TRACE(sbi->s_sbh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) + goto out_brelse; + sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); + err = ext4_journal_dirty_metadata(handle, sbi->s_sbh); + } else { + struct ext4_iloc iloc2; + struct inode *i_prev = + &list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode; + + jbd_debug(4, "orphan inode %lu will point to %lu\n", + i_prev->i_ino, ino_next); + err = ext4_reserve_inode_write(handle, i_prev, &iloc2); + if (err) + goto out_brelse; + NEXT_ORPHAN(i_prev) = ino_next; + err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2); + } + if (err) + goto out_brelse; + NEXT_ORPHAN(inode) = 0; + err = ext4_mark_iloc_dirty(handle, inode, &iloc); + +out_err: + ext4_std_error(inode->i_sb, err); +out: + unlock_super(inode->i_sb); + return err; + +out_brelse: + brelse(iloc.bh); + goto out_err; +} + +static int ext4_rmdir (struct inode * dir, struct dentry *dentry) +{ + int retval; + struct inode * inode; + struct buffer_head * bh; + struct ext4_dir_entry_2 * de; + handle_t *handle; + + /* Initialize quotas before so that eventual writes go in + * separate transaction */ + DQUOT_INIT(dentry->d_inode); + handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + retval = -ENOENT; + bh = ext4_find_entry (dentry, &de); + if (!bh) + goto end_rmdir; + + if (IS_DIRSYNC(dir)) + handle->h_sync = 1; + + inode = dentry->d_inode; + + retval = -EIO; + if (le32_to_cpu(de->inode) != inode->i_ino) + goto end_rmdir; + + retval = -ENOTEMPTY; + if (!empty_dir (inode)) + goto end_rmdir; + + retval = ext4_delete_entry(handle, dir, de, bh); + if (retval) + goto end_rmdir; + if (inode->i_nlink != 2) + ext4_warning (inode->i_sb, "ext4_rmdir", + "empty directory has nlink!=2 (%d)", + inode->i_nlink); + inode->i_version++; + clear_nlink(inode); + /* There's no need to set i_disksize: the fact that i_nlink is + * zero will ensure that the right thing happens during any + * recovery. */ + inode->i_size = 0; + ext4_orphan_add(handle, inode); + inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; + ext4_mark_inode_dirty(handle, inode); + drop_nlink(dir); + ext4_update_dx_flag(dir); + ext4_mark_inode_dirty(handle, dir); + +end_rmdir: + ext4_journal_stop(handle); + brelse (bh); + return retval; +} + +static int ext4_unlink(struct inode * dir, struct dentry *dentry) +{ + int retval; + struct inode * inode; + struct buffer_head * bh; + struct ext4_dir_entry_2 * de; + handle_t *handle; + + /* Initialize quotas before so that eventual writes go + * in separate transaction */ + DQUOT_INIT(dentry->d_inode); + handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(dir)) + handle->h_sync = 1; + + retval = -ENOENT; + bh = ext4_find_entry (dentry, &de); + if (!bh) + goto end_unlink; + + inode = dentry->d_inode; + + retval = -EIO; + if (le32_to_cpu(de->inode) != inode->i_ino) + goto end_unlink; + + if (!inode->i_nlink) { + ext4_warning (inode->i_sb, "ext4_unlink", + "Deleting nonexistent file (%lu), %d", + inode->i_ino, inode->i_nlink); + inode->i_nlink = 1; + } + retval = ext4_delete_entry(handle, dir, de, bh); + if (retval) + goto end_unlink; + dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; + ext4_update_dx_flag(dir); + ext4_mark_inode_dirty(handle, dir); + drop_nlink(inode); + if (!inode->i_nlink) + ext4_orphan_add(handle, inode); + inode->i_ctime = dir->i_ctime; + ext4_mark_inode_dirty(handle, inode); + retval = 0; + +end_unlink: + ext4_journal_stop(handle); + brelse (bh); + return retval; +} + +static int ext4_symlink (struct inode * dir, + struct dentry *dentry, const char * symname) +{ + handle_t *handle; + struct inode * inode; + int l, err, retries = 0; + + l = strlen(symname)+1; + if (l > dir->i_sb->s_blocksize) + return -ENAMETOOLONG; + +retry: + handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 5 + + 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(dir)) + handle->h_sync = 1; + + inode = ext4_new_inode (handle, dir, S_IFLNK|S_IRWXUGO); + err = PTR_ERR(inode); + if (IS_ERR(inode)) + goto out_stop; + + if (l > sizeof (EXT4_I(inode)->i_data)) { + inode->i_op = &ext4_symlink_inode_operations; + ext4_set_aops(inode); + /* + * page_symlink() calls into ext4_prepare/commit_write. + * We have a transaction open. All is sweetness. It also sets + * i_size in generic_commit_write(). + */ + err = __page_symlink(inode, symname, l, + mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + if (err) { + ext4_dec_count(handle, inode); + ext4_mark_inode_dirty(handle, inode); + iput (inode); + goto out_stop; + } + } else { + inode->i_op = &ext4_fast_symlink_inode_operations; + memcpy((char*)&EXT4_I(inode)->i_data,symname,l); + inode->i_size = l-1; + } + EXT4_I(inode)->i_disksize = inode->i_size; + err = ext4_add_nondir(handle, dentry, inode); +out_stop: + ext4_journal_stop(handle); + if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) + goto retry; + return err; +} + +static int ext4_link (struct dentry * old_dentry, + struct inode * dir, struct dentry *dentry) +{ + handle_t *handle; + struct inode *inode = old_dentry->d_inode; + int err, retries = 0; + + if (inode->i_nlink >= EXT4_LINK_MAX) + return -EMLINK; + +retry: + handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(dir)) + handle->h_sync = 1; + + inode->i_ctime = CURRENT_TIME_SEC; + ext4_inc_count(handle, inode); + atomic_inc(&inode->i_count); + + err = ext4_add_nondir(handle, dentry, inode); + ext4_journal_stop(handle); + if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) + goto retry; + return err; +} + +#define PARENT_INO(buffer) \ + ((struct ext4_dir_entry_2 *) ((char *) buffer + \ + le16_to_cpu(((struct ext4_dir_entry_2 *) buffer)->rec_len)))->inode + +/* + * Anybody can rename anything with this: the permission checks are left to the + * higher-level routines. + */ +static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry, + struct inode * new_dir,struct dentry *new_dentry) +{ + handle_t *handle; + struct inode * old_inode, * new_inode; + struct buffer_head * old_bh, * new_bh, * dir_bh; + struct ext4_dir_entry_2 * old_de, * new_de; + int retval; + + old_bh = new_bh = dir_bh = NULL; + + /* Initialize quotas before so that eventual writes go + * in separate transaction */ + if (new_dentry->d_inode) + DQUOT_INIT(new_dentry->d_inode); + handle = ext4_journal_start(old_dir, 2 * + EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) + handle->h_sync = 1; + + old_bh = ext4_find_entry (old_dentry, &old_de); + /* + * Check for inode number is _not_ due to possible IO errors. + * We might rmdir the source, keep it as pwd of some process + * and merrily kill the link to whatever was created under the + * same name. Goodbye sticky bit ;-< + */ + old_inode = old_dentry->d_inode; + retval = -ENOENT; + if (!old_bh || le32_to_cpu(old_de->inode) != old_inode->i_ino) + goto end_rename; + + new_inode = new_dentry->d_inode; + new_bh = ext4_find_entry (new_dentry, &new_de); + if (new_bh) { + if (!new_inode) { + brelse (new_bh); + new_bh = NULL; + } + } + if (S_ISDIR(old_inode->i_mode)) { + if (new_inode) { + retval = -ENOTEMPTY; + if (!empty_dir (new_inode)) + goto end_rename; + } + retval = -EIO; + dir_bh = ext4_bread (handle, old_inode, 0, 0, &retval); + if (!dir_bh) + goto end_rename; + if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino) + goto end_rename; + retval = -EMLINK; + if (!new_inode && new_dir!=old_dir && + new_dir->i_nlink >= EXT4_LINK_MAX) + goto end_rename; + } + if (!new_bh) { + retval = ext4_add_entry (handle, new_dentry, old_inode); + if (retval) + goto end_rename; + } else { + BUFFER_TRACE(new_bh, "get write access"); + ext4_journal_get_write_access(handle, new_bh); + new_de->inode = cpu_to_le32(old_inode->i_ino); + if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb, + EXT4_FEATURE_INCOMPAT_FILETYPE)) + new_de->file_type = old_de->file_type; + new_dir->i_version++; + BUFFER_TRACE(new_bh, "call ext4_journal_dirty_metadata"); + ext4_journal_dirty_metadata(handle, new_bh); + brelse(new_bh); + new_bh = NULL; + } + + /* + * Like most other Unix systems, set the ctime for inodes on a + * rename. + */ + old_inode->i_ctime = CURRENT_TIME_SEC; + ext4_mark_inode_dirty(handle, old_inode); + + /* + * ok, that's it + */ + if (le32_to_cpu(old_de->inode) != old_inode->i_ino || + old_de->name_len != old_dentry->d_name.len || + strncmp(old_de->name, old_dentry->d_name.name, old_de->name_len) || + (retval = ext4_delete_entry(handle, old_dir, + old_de, old_bh)) == -ENOENT) { + /* old_de could have moved from under us during htree split, so + * make sure that we are deleting the right entry. We might + * also be pointing to a stale entry in the unused part of + * old_bh so just checking inum and the name isn't enough. */ + struct buffer_head *old_bh2; + struct ext4_dir_entry_2 *old_de2; + + old_bh2 = ext4_find_entry(old_dentry, &old_de2); + if (old_bh2) { + retval = ext4_delete_entry(handle, old_dir, + old_de2, old_bh2); + brelse(old_bh2); + } + } + if (retval) { + ext4_warning(old_dir->i_sb, "ext4_rename", + "Deleting old file (%lu), %d, error=%d", + old_dir->i_ino, old_dir->i_nlink, retval); + } + + if (new_inode) { + drop_nlink(new_inode); + new_inode->i_ctime = CURRENT_TIME_SEC; + } + old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; + ext4_update_dx_flag(old_dir); + if (dir_bh) { + BUFFER_TRACE(dir_bh, "get_write_access"); + ext4_journal_get_write_access(handle, dir_bh); + PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino); + BUFFER_TRACE(dir_bh, "call ext4_journal_dirty_metadata"); + ext4_journal_dirty_metadata(handle, dir_bh); + drop_nlink(old_dir); + if (new_inode) { + drop_nlink(new_inode); + } else { + inc_nlink(new_dir); + ext4_update_dx_flag(new_dir); + ext4_mark_inode_dirty(handle, new_dir); + } + } + ext4_mark_inode_dirty(handle, old_dir); + if (new_inode) { + ext4_mark_inode_dirty(handle, new_inode); + if (!new_inode->i_nlink) + ext4_orphan_add(handle, new_inode); + } + retval = 0; + +end_rename: + brelse (dir_bh); + brelse (old_bh); + brelse (new_bh); + ext4_journal_stop(handle); + return retval; +} + +/* + * directories can handle most operations... + */ +struct inode_operations ext4_dir_inode_operations = { + .create = ext4_create, + .lookup = ext4_lookup, + .link = ext4_link, + .unlink = ext4_unlink, + .symlink = ext4_symlink, + .mkdir = ext4_mkdir, + .rmdir = ext4_rmdir, + .mknod = ext4_mknod, + .rename = ext4_rename, + .setattr = ext4_setattr, +#ifdef CONFIG_EXT4DEV_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext4_listxattr, + .removexattr = generic_removexattr, +#endif + .permission = ext4_permission, +}; + +struct inode_operations ext4_special_inode_operations = { + .setattr = ext4_setattr, +#ifdef CONFIG_EXT4DEV_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext4_listxattr, + .removexattr = generic_removexattr, +#endif + .permission = ext4_permission, +}; diff --git a/fs/ext4/namei.h b/fs/ext4/namei.h new file mode 100644 index 00000000000..5e4dfff36a0 --- /dev/null +++ b/fs/ext4/namei.h @@ -0,0 +1,8 @@ +/* linux/fs/ext4/namei.h + * + * Copyright (C) 2005 Simtec Electronics + * Ben Dooks <ben@simtec.co.uk> + * +*/ + +extern struct dentry *ext4_get_parent(struct dentry *child); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c new file mode 100644 index 00000000000..1e9578052cd --- /dev/null +++ b/fs/ext4/resize.c @@ -0,0 +1,1045 @@ +/* + * linux/fs/ext4/resize.c + * + * Support for resizing an ext4 filesystem while it is mounted. + * + * Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com> + * + * This could probably be made into a module, because it is not often in use. + */ + + +#define EXT4FS_DEBUG + +#include <linux/sched.h> +#include <linux/smp_lock.h> +#include <linux/ext4_jbd2.h> + +#include <linux/errno.h> +#include <linux/slab.h> + + +#define outside(b, first, last) ((b) < (first) || (b) >= (last)) +#define inside(b, first, last) ((b) >= (first) && (b) < (last)) + +static int verify_group_input(struct super_block *sb, + struct ext4_new_group_data *input) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + ext4_fsblk_t start = ext4_blocks_count(es); + ext4_fsblk_t end = start + input->blocks_count; + unsigned group = input->group; + ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group; + unsigned overhead = ext4_bg_has_super(sb, group) ? + (1 + ext4_bg_num_gdb(sb, group) + + le16_to_cpu(es->s_reserved_gdt_blocks)) : 0; + ext4_fsblk_t metaend = start + overhead; + struct buffer_head *bh = NULL; + ext4_grpblk_t free_blocks_count, offset; + int err = -EINVAL; + + input->free_blocks_count = free_blocks_count = + input->blocks_count - 2 - overhead - sbi->s_itb_per_group; + + if (test_opt(sb, DEBUG)) + printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks " + "(%d free, %u reserved)\n", + ext4_bg_has_super(sb, input->group) ? "normal" : + "no-super", input->group, input->blocks_count, + free_blocks_count, input->reserved_blocks); + + ext4_get_group_no_and_offset(sb, start, NULL, &offset); + if (group != sbi->s_groups_count) + ext4_warning(sb, __FUNCTION__, + "Cannot add at group %u (only %lu groups)", + input->group, sbi->s_groups_count); + else if (offset != 0) + ext4_warning(sb, __FUNCTION__, "Last group not full"); + else if (input->reserved_blocks > input->blocks_count / 5) + ext4_warning(sb, __FUNCTION__, "Reserved blocks too high (%u)", + input->reserved_blocks); + else if (free_blocks_count < 0) + ext4_warning(sb, __FUNCTION__, "Bad blocks count %u", + input->blocks_count); + else if (!(bh = sb_bread(sb, end - 1))) + ext4_warning(sb, __FUNCTION__, + "Cannot read last block (%llu)", + end - 1); + else if (outside(input->block_bitmap, start, end)) + ext4_warning(sb, __FUNCTION__, + "Block bitmap not in group (block %llu)", + input->block_bitmap); + else if (outside(input->inode_bitmap, start, end)) + ext4_warning(sb, __FUNCTION__, + "Inode bitmap not in group (block %llu)", + input->inode_bitmap); + else if (outside(input->inode_table, start, end) || + outside(itend - 1, start, end)) + ext4_warning(sb, __FUNCTION__, + "Inode table not in group (blocks %llu-%llu)", + input->inode_table, itend - 1); + else if (input->inode_bitmap == input->block_bitmap) + ext4_warning(sb, __FUNCTION__, + "Block bitmap same as inode bitmap (%llu)", + input->block_bitmap); + else if (inside(input->block_bitmap, input->inode_table, itend)) + ext4_warning(sb, __FUNCTION__, + "Block bitmap (%llu) in inode table (%llu-%llu)", + input->block_bitmap, input->inode_table, itend-1); + else if (inside(input->inode_bitmap, input->inode_table, itend)) + ext4_warning(sb, __FUNCTION__, + "Inode bitmap (%llu) in inode table (%llu-%llu)", + input->inode_bitmap, input->inode_table, itend-1); + else if (inside(input->block_bitmap, start, metaend)) + ext4_warning(sb, __FUNCTION__, + "Block bitmap (%llu) in GDT table" + " (%llu-%llu)", + input->block_bitmap, start, metaend - 1); + else if (inside(input->inode_bitmap, start, metaend)) + ext4_warning(sb, __FUNCTION__, + "Inode bitmap (%llu) in GDT table" + " (%llu-%llu)", + input->inode_bitmap, start, metaend - 1); + else if (inside(input->inode_table, start, metaend) || + inside(itend - 1, start, metaend)) + ext4_warning(sb, __FUNCTION__, + "Inode table (%llu-%llu) overlaps" + "GDT table (%llu-%llu)", + input->inode_table, itend - 1, start, metaend - 1); + else + err = 0; + brelse(bh); + + return err; +} + +static struct buffer_head *bclean(handle_t *handle, struct super_block *sb, + ext4_fsblk_t blk) +{ + struct buffer_head *bh; + int err; + + bh = sb_getblk(sb, blk); + if (!bh) + return ERR_PTR(-EIO); + if ((err = ext4_journal_get_write_access(handle, bh))) { + brelse(bh); + bh = ERR_PTR(err); + } else { + lock_buffer(bh); + memset(bh->b_data, 0, sb->s_blocksize); + set_buffer_uptodate(bh); + unlock_buffer(bh); + } + + return bh; +} + +/* + * To avoid calling the atomic setbit hundreds or thousands of times, we only + * need to use it within a single byte (to ensure we get endianness right). + * We can use memset for the rest of the bitmap as there are no other users. + */ +static void mark_bitmap_end(int start_bit, int end_bit, char *bitmap) +{ + int i; + + if (start_bit >= end_bit) + return; + + ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit); + for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++) + ext4_set_bit(i, bitmap); + if (i < end_bit) + memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3); +} + +/* + * Set up the block and inode bitmaps, and the inode table for the new group. + * This doesn't need to be part of the main transaction, since we are only + * changing blocks outside the actual filesystem. We still do journaling to + * ensure the recovery is correct in case of a failure just after resize. + * If any part of this fails, we simply abort the resize. + */ +static int setup_new_group_blocks(struct super_block *sb, + struct ext4_new_group_data *input) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + ext4_fsblk_t start = ext4_group_first_block_no(sb, input->group); + int reserved_gdb = ext4_bg_has_super(sb, input->group) ? + le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0; + unsigned long gdblocks = ext4_bg_num_gdb(sb, input->group); + struct buffer_head *bh; + handle_t *handle; + ext4_fsblk_t block; + ext4_grpblk_t bit; + int i; + int err = 0, err2; + + handle = ext4_journal_start_sb(sb, reserved_gdb + gdblocks + + 2 + sbi->s_itb_per_group); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + lock_super(sb); + if (input->group != sbi->s_groups_count) { + err = -EBUSY; + goto exit_journal; + } + + if (IS_ERR(bh = bclean(handle, sb, input->block_bitmap))) { + err = PTR_ERR(bh); + goto exit_journal; + } + + if (ext4_bg_has_super(sb, input->group)) { + ext4_debug("mark backup superblock %#04lx (+0)\n", start); + ext4_set_bit(0, bh->b_data); + } + + /* Copy all of the GDT blocks into the backup in this group */ + for (i = 0, bit = 1, block = start + 1; + i < gdblocks; i++, block++, bit++) { + struct buffer_head *gdb; + + ext4_debug("update backup group %#04lx (+%d)\n", block, bit); + + gdb = sb_getblk(sb, block); + if (!gdb) { + err = -EIO; + goto exit_bh; + } + if ((err = ext4_journal_get_write_access(handle, gdb))) { + brelse(gdb); + goto exit_bh; + } + lock_buffer(bh); + memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, bh->b_size); + set_buffer_uptodate(gdb); + unlock_buffer(bh); + ext4_journal_dirty_metadata(handle, gdb); + ext4_set_bit(bit, bh->b_data); + brelse(gdb); + } + + /* Zero out all of the reserved backup group descriptor table blocks */ + for (i = 0, bit = gdblocks + 1, block = start + bit; + i < reserved_gdb; i++, block++, bit++) { + struct buffer_head *gdb; + + ext4_debug("clear reserved block %#04lx (+%d)\n", block, bit); + + if (IS_ERR(gdb = bclean(handle, sb, block))) { + err = PTR_ERR(bh); + goto exit_bh; + } + ext4_journal_dirty_metadata(handle, gdb); + ext4_set_bit(bit, bh->b_data); + brelse(gdb); + } + ext4_debug("mark block bitmap %#04x (+%ld)\n", input->block_bitmap, + input->block_bitmap - start); + ext4_set_bit(input->block_bitmap - start, bh->b_data); + ext4_debug("mark inode bitmap %#04x (+%ld)\n", input->inode_bitmap, + input->inode_bitmap - start); + ext4_set_bit(input->inode_bitmap - start, bh->b_data); + + /* Zero out all of the inode table blocks */ + for (i = 0, block = input->inode_table, bit = block - start; + i < sbi->s_itb_per_group; i++, bit++, block++) { + struct buffer_head *it; + + ext4_debug("clear inode block %#04lx (+%d)\n", block, bit); + if (IS_ERR(it = bclean(handle, sb, block))) { + err = PTR_ERR(it); + goto exit_bh; + } + ext4_journal_dirty_metadata(handle, it); + brelse(it); + ext4_set_bit(bit, bh->b_data); + } + mark_bitmap_end(input->blocks_count, EXT4_BLOCKS_PER_GROUP(sb), + bh->b_data); + ext4_journal_dirty_metadata(handle, bh); + brelse(bh); + + /* Mark unused entries in inode bitmap used */ + ext4_debug("clear inode bitmap %#04x (+%ld)\n", + input->inode_bitmap, input->inode_bitmap - start); + if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) { + err = PTR_ERR(bh); + goto exit_journal; + } + + mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb), + bh->b_data); + ext4_journal_dirty_metadata(handle, bh); +exit_bh: + brelse(bh); + +exit_journal: + unlock_super(sb); + if ((err2 = ext4_journal_stop(handle)) && !err) + err = err2; + + return err; +} + + +/* + * Iterate through the groups which hold BACKUP superblock/GDT copies in an + * ext4 filesystem. The counters should be initialized to 1, 5, and 7 before + * calling this for the first time. In a sparse filesystem it will be the + * sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ... + * For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ... + */ +static unsigned ext4_list_backups(struct super_block *sb, unsigned *three, + unsigned *five, unsigned *seven) +{ + unsigned *min = three; + int mult = 3; + unsigned ret; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) { + ret = *min; + *min += 1; + return ret; + } + + if (*five < *min) { + min = five; + mult = 5; + } + if (*seven < *min) { + min = seven; + mult = 7; + } + + ret = *min; + *min *= mult; + + return ret; +} + +/* + * Check that all of the backup GDT blocks are held in the primary GDT block. + * It is assumed that they are stored in group order. Returns the number of + * groups in current filesystem that have BACKUPS, or -ve error code. + */ +static int verify_reserved_gdb(struct super_block *sb, + struct buffer_head *primary) +{ + const ext4_fsblk_t blk = primary->b_blocknr; + const unsigned long end = EXT4_SB(sb)->s_groups_count; + unsigned three = 1; + unsigned five = 5; + unsigned seven = 7; + unsigned grp; + __le32 *p = (__le32 *)primary->b_data; + int gdbackups = 0; + + while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) { + if (le32_to_cpu(*p++) != + grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){ + ext4_warning(sb, __FUNCTION__, + "reserved GDT %llu" + " missing grp %d (%llu)", + blk, grp, + grp * + (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) + + blk); + return -EINVAL; + } + if (++gdbackups > EXT4_ADDR_PER_BLOCK(sb)) + return -EFBIG; + } + + return gdbackups; +} + +/* + * Called when we need to bring a reserved group descriptor table block into + * use from the resize inode. The primary copy of the new GDT block currently + * is an indirect block (under the double indirect block in the resize inode). + * The new backup GDT blocks will be stored as leaf blocks in this indirect + * block, in group order. Even though we know all the block numbers we need, + * we check to ensure that the resize inode has actually reserved these blocks. + * + * Don't need to update the block bitmaps because the blocks are still in use. + * + * We get all of the error cases out of the way, so that we are sure to not + * fail once we start modifying the data on disk, because JBD has no rollback. + */ +static int add_new_gdb(handle_t *handle, struct inode *inode, + struct ext4_new_group_data *input, + struct buffer_head **primary) +{ + struct super_block *sb = inode->i_sb; + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + unsigned long gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb); + ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num; + struct buffer_head **o_group_desc, **n_group_desc; + struct buffer_head *dind; + int gdbackups; + struct ext4_iloc iloc; + __le32 *data; + int err; + + if (test_opt(sb, DEBUG)) + printk(KERN_DEBUG + "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n", + gdb_num); + + /* + * If we are not using the primary superblock/GDT copy don't resize, + * because the user tools have no way of handling this. Probably a + * bad time to do it anyways. + */ + if (EXT4_SB(sb)->s_sbh->b_blocknr != + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { + ext4_warning(sb, __FUNCTION__, + "won't resize using backup superblock at %llu", + (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); + return -EPERM; + } + + *primary = sb_bread(sb, gdblock); + if (!*primary) + return -EIO; + + if ((gdbackups = verify_reserved_gdb(sb, *primary)) < 0) { + err = gdbackups; + goto exit_bh; + } + + data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK; + dind = sb_bread(sb, le32_to_cpu(*data)); + if (!dind) { + err = -EIO; + goto exit_bh; + } + + data = (__le32 *)dind->b_data; + if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) { + ext4_warning(sb, __FUNCTION__, + "new group %u GDT block %llu not reserved", + input->group, gdblock); + err = -EINVAL; + goto exit_dind; + } + + if ((err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh))) + goto exit_dind; + + if ((err = ext4_journal_get_write_access(handle, *primary))) + goto exit_sbh; + + if ((err = ext4_journal_get_write_access(handle, dind))) + goto exit_primary; + + /* ext4_reserve_inode_write() gets a reference on the iloc */ + if ((err = ext4_reserve_inode_write(handle, inode, &iloc))) + goto exit_dindj; + + n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *), + GFP_KERNEL); + if (!n_group_desc) { + err = -ENOMEM; + ext4_warning (sb, __FUNCTION__, + "not enough memory for %lu groups", gdb_num + 1); + goto exit_inode; + } + + /* + * Finally, we have all of the possible failures behind us... + * + * Remove new GDT block from inode double-indirect block and clear out + * the new GDT block for use (which also "frees" the backup GDT blocks + * from the reserved inode). We don't need to change the bitmaps for + * these blocks, because they are marked as in-use from being in the + * reserved inode, and will become GDT blocks (primary and backup). + */ + data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0; + ext4_journal_dirty_metadata(handle, dind); + brelse(dind); + inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9; + ext4_mark_iloc_dirty(handle, inode, &iloc); + memset((*primary)->b_data, 0, sb->s_blocksize); + ext4_journal_dirty_metadata(handle, *primary); + + o_group_desc = EXT4_SB(sb)->s_group_desc; + memcpy(n_group_desc, o_group_desc, + EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + n_group_desc[gdb_num] = *primary; + EXT4_SB(sb)->s_group_desc = n_group_desc; + EXT4_SB(sb)->s_gdb_count++; + kfree(o_group_desc); + + es->s_reserved_gdt_blocks = + cpu_to_le16(le16_to_cpu(es->s_reserved_gdt_blocks) - 1); + ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh); + + return 0; + +exit_inode: + //ext4_journal_release_buffer(handle, iloc.bh); + brelse(iloc.bh); +exit_dindj: + //ext4_journal_release_buffer(handle, dind); +exit_primary: + //ext4_journal_release_buffer(handle, *primary); +exit_sbh: + //ext4_journal_release_buffer(handle, *primary); +exit_dind: + brelse(dind); +exit_bh: + brelse(*primary); + + ext4_debug("leaving with error %d\n", err); + return err; +} + +/* + * Called when we are adding a new group which has a backup copy of each of + * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks. + * We need to add these reserved backup GDT blocks to the resize inode, so + * that they are kept for future resizing and not allocated to files. + * + * Each reserved backup GDT block will go into a different indirect block. + * The indirect blocks are actually the primary reserved GDT blocks, + * so we know in advance what their block numbers are. We only get the + * double-indirect block to verify it is pointing to the primary reserved + * GDT blocks so we don't overwrite a data block by accident. The reserved + * backup GDT blocks are stored in their reserved primary GDT block. + */ +static int reserve_backup_gdb(handle_t *handle, struct inode *inode, + struct ext4_new_group_data *input) +{ + struct super_block *sb = inode->i_sb; + int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks); + struct buffer_head **primary; + struct buffer_head *dind; + struct ext4_iloc iloc; + ext4_fsblk_t blk; + __le32 *data, *end; + int gdbackups = 0; + int res, i; + int err; + + primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_KERNEL); + if (!primary) + return -ENOMEM; + + data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK; + dind = sb_bread(sb, le32_to_cpu(*data)); + if (!dind) { + err = -EIO; + goto exit_free; + } + + blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count; + data = (__le32 *)dind->b_data + EXT4_SB(sb)->s_gdb_count; + end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb); + + /* Get each reserved primary GDT block and verify it holds backups */ + for (res = 0; res < reserved_gdb; res++, blk++) { + if (le32_to_cpu(*data) != blk) { + ext4_warning(sb, __FUNCTION__, + "reserved block %llu" + " not at offset %ld", + blk, + (long)(data - (__le32 *)dind->b_data)); + err = -EINVAL; + goto exit_bh; + } + primary[res] = sb_bread(sb, blk); + if (!primary[res]) { + err = -EIO; + goto exit_bh; + } + if ((gdbackups = verify_reserved_gdb(sb, primary[res])) < 0) { + brelse(primary[res]); + err = gdbackups; + goto exit_bh; + } + if (++data >= end) + data = (__le32 *)dind->b_data; + } + + for (i = 0; i < reserved_gdb; i++) { + if ((err = ext4_journal_get_write_access(handle, primary[i]))) { + /* + int j; + for (j = 0; j < i; j++) + ext4_journal_release_buffer(handle, primary[j]); + */ + goto exit_bh; + } + } + + if ((err = ext4_reserve_inode_write(handle, inode, &iloc))) + goto exit_bh; + + /* + * Finally we can add each of the reserved backup GDT blocks from + * the new group to its reserved primary GDT block. + */ + blk = input->group * EXT4_BLOCKS_PER_GROUP(sb); + for (i = 0; i < reserved_gdb; i++) { + int err2; + data = (__le32 *)primary[i]->b_data; + /* printk("reserving backup %lu[%u] = %lu\n", + primary[i]->b_blocknr, gdbackups, + blk + primary[i]->b_blocknr); */ + data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr); + err2 = ext4_journal_dirty_metadata(handle, primary[i]); + if (!err) + err = err2; + } + inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9; + ext4_mark_iloc_dirty(handle, inode, &iloc); + +exit_bh: + while (--res >= 0) + brelse(primary[res]); + brelse(dind); + +exit_free: + kfree(primary); + + return err; +} + +/* + * Update the backup copies of the ext4 metadata. These don't need to be part + * of the main resize transaction, because e2fsck will re-write them if there + * is a problem (basically only OOM will cause a problem). However, we + * _should_ update the backups if possible, in case the primary gets trashed + * for some reason and we need to run e2fsck from a backup superblock. The + * important part is that the new block and inode counts are in the backup + * superblocks, and the location of the new group metadata in the GDT backups. + * + * We do not need lock_super() for this, because these blocks are not + * otherwise touched by the filesystem code when it is mounted. We don't + * need to worry about last changing from sbi->s_groups_count, because the + * worst that can happen is that we do not copy the full number of backups + * at this time. The resize which changed s_groups_count will backup again. + */ +static void update_backups(struct super_block *sb, + int blk_off, char *data, int size) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + const unsigned long last = sbi->s_groups_count; + const int bpg = EXT4_BLOCKS_PER_GROUP(sb); + unsigned three = 1; + unsigned five = 5; + unsigned seven = 7; + unsigned group; + int rest = sb->s_blocksize - size; + handle_t *handle; + int err = 0, err2; + + handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA); + if (IS_ERR(handle)) { + group = 1; + err = PTR_ERR(handle); + goto exit_err; + } + + while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) { + struct buffer_head *bh; + + /* Out of journal space, and can't get more - abort - so sad */ + if (handle->h_buffer_credits == 0 && + ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) && + (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA))) + break; + + bh = sb_getblk(sb, group * bpg + blk_off); + if (!bh) { + err = -EIO; + break; + } + ext4_debug("update metadata backup %#04lx\n", + (unsigned long)bh->b_blocknr); + if ((err = ext4_journal_get_write_access(handle, bh))) + break; + lock_buffer(bh); + memcpy(bh->b_data, data, size); + if (rest) + memset(bh->b_data + size, 0, rest); + set_buffer_uptodate(bh); + unlock_buffer(bh); + ext4_journal_dirty_metadata(handle, bh); + brelse(bh); + } + if ((err2 = ext4_journal_stop(handle)) && !err) + err = err2; + + /* + * Ugh! Need to have e2fsck write the backup copies. It is too + * late to revert the resize, we shouldn't fail just because of + * the backup copies (they are only needed in case of corruption). + * + * However, if we got here we have a journal problem too, so we + * can't really start a transaction to mark the superblock. + * Chicken out and just set the flag on the hope it will be written + * to disk, and if not - we will simply wait until next fsck. + */ +exit_err: + if (err) { + ext4_warning(sb, __FUNCTION__, + "can't update backup for group %d (err %d), " + "forcing fsck on next reboot", group, err); + sbi->s_mount_state &= ~EXT4_VALID_FS; + sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS); + mark_buffer_dirty(sbi->s_sbh); + } +} + +/* Add group descriptor data to an existing or new group descriptor block. + * Ensure we handle all possible error conditions _before_ we start modifying + * the filesystem, because we cannot abort the transaction and not have it + * write the data to disk. + * + * If we are on a GDT block boundary, we need to get the reserved GDT block. + * Otherwise, we may need to add backup GDT blocks for a sparse group. + * + * We only need to hold the superblock lock while we are actually adding + * in the new group's counts to the superblock. Prior to that we have + * not really "added" the group at all. We re-check that we are still + * adding in the last group in case things have changed since verifying. + */ +int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + int reserved_gdb = ext4_bg_has_super(sb, input->group) ? + le16_to_cpu(es->s_reserved_gdt_blocks) : 0; + struct buffer_head *primary = NULL; + struct ext4_group_desc *gdp; + struct inode *inode = NULL; + handle_t *handle; + int gdb_off, gdb_num; + int err, err2; + + gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb); + gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb); + + if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) { + ext4_warning(sb, __FUNCTION__, + "Can't resize non-sparse filesystem further"); + return -EPERM; + } + + if (ext4_blocks_count(es) + input->blocks_count < + ext4_blocks_count(es)) { + ext4_warning(sb, __FUNCTION__, "blocks_count overflow\n"); + return -EINVAL; + } + + if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) < + le32_to_cpu(es->s_inodes_count)) { + ext4_warning(sb, __FUNCTION__, "inodes_count overflow\n"); + return -EINVAL; + } + + if (reserved_gdb || gdb_off == 0) { + if (!EXT4_HAS_COMPAT_FEATURE(sb, + EXT4_FEATURE_COMPAT_RESIZE_INODE)){ + ext4_warning(sb, __FUNCTION__, + "No reserved GDT blocks, can't resize"); + return -EPERM; + } + inode = iget(sb, EXT4_RESIZE_INO); + if (!inode || is_bad_inode(inode)) { + ext4_warning(sb, __FUNCTION__, + "Error opening resize inode"); + iput(inode); + return -ENOENT; + } + } + + if ((err = verify_group_input(sb, input))) + goto exit_put; + + if ((err = setup_new_group_blocks(sb, input))) + goto exit_put; + + /* + * We will always be modifying at least the superblock and a GDT + * block. If we are adding a group past the last current GDT block, + * we will also modify the inode and the dindirect block. If we + * are adding a group with superblock/GDT backups we will also + * modify each of the reserved GDT dindirect blocks. + */ + handle = ext4_journal_start_sb(sb, + ext4_bg_has_super(sb, input->group) ? + 3 + reserved_gdb : 4); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto exit_put; + } + + lock_super(sb); + if (input->group != sbi->s_groups_count) { + ext4_warning(sb, __FUNCTION__, + "multiple resizers run on filesystem!"); + err = -EBUSY; + goto exit_journal; + } + + if ((err = ext4_journal_get_write_access(handle, sbi->s_sbh))) + goto exit_journal; + + /* + * We will only either add reserved group blocks to a backup group + * or remove reserved blocks for the first group in a new group block. + * Doing both would be mean more complex code, and sane people don't + * use non-sparse filesystems anymore. This is already checked above. + */ + if (gdb_off) { + primary = sbi->s_group_desc[gdb_num]; + if ((err = ext4_journal_get_write_access(handle, primary))) + goto exit_journal; + + if (reserved_gdb && ext4_bg_num_gdb(sb, input->group) && + (err = reserve_backup_gdb(handle, inode, input))) + goto exit_journal; + } else if ((err = add_new_gdb(handle, inode, input, &primary))) + goto exit_journal; + + /* + * OK, now we've set up the new group. Time to make it active. + * + * Current kernels don't lock all allocations via lock_super(), + * so we have to be safe wrt. concurrent accesses the group + * data. So we need to be careful to set all of the relevant + * group descriptor data etc. *before* we enable the group. + * + * The key field here is sbi->s_groups_count: as long as + * that retains its old value, nobody is going to access the new + * group. + * + * So first we update all the descriptor metadata for the new + * group; then we update the total disk blocks count; then we + * update the groups count to enable the group; then finally we + * update the free space counts so that the system can start + * using the new disk blocks. + */ + + /* Update group descriptor block for new group */ + gdp = (struct ext4_group_desc *)primary->b_data + gdb_off; + + ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */ + ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */ + ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */ + gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count); + gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb)); + + /* + * Make the new blocks and inodes valid next. We do this before + * increasing the group count so that once the group is enabled, + * all of its blocks and inodes are already valid. + * + * We always allocate group-by-group, then block-by-block or + * inode-by-inode within a group, so enabling these + * blocks/inodes before the group is live won't actually let us + * allocate the new space yet. + */ + ext4_blocks_count_set(es, ext4_blocks_count(es) + + input->blocks_count); + es->s_inodes_count = cpu_to_le32(le32_to_cpu(es->s_inodes_count) + + EXT4_INODES_PER_GROUP(sb)); + + /* + * We need to protect s_groups_count against other CPUs seeing + * inconsistent state in the superblock. + * + * The precise rules we use are: + * + * * Writers of s_groups_count *must* hold lock_super + * AND + * * Writers must perform a smp_wmb() after updating all dependent + * data and before modifying the groups count + * + * * Readers must hold lock_super() over the access + * OR + * * Readers must perform an smp_rmb() after reading the groups count + * and before reading any dependent data. + * + * NB. These rules can be relaxed when checking the group count + * while freeing data, as we can only allocate from a block + * group after serialising against the group count, and we can + * only then free after serialising in turn against that + * allocation. + */ + smp_wmb(); + + /* Update the global fs size fields */ + sbi->s_groups_count++; + + ext4_journal_dirty_metadata(handle, primary); + + /* Update the reserved block counts only once the new group is + * active. */ + ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) + + input->reserved_blocks); + + /* Update the free space counts */ + percpu_counter_mod(&sbi->s_freeblocks_counter, + input->free_blocks_count); + percpu_counter_mod(&sbi->s_freeinodes_counter, + EXT4_INODES_PER_GROUP(sb)); + + ext4_journal_dirty_metadata(handle, sbi->s_sbh); + sb->s_dirt = 1; + +exit_journal: + unlock_super(sb); + if ((err2 = ext4_journal_stop(handle)) && !err) + err = err2; + if (!err) { + update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, + sizeof(struct ext4_super_block)); + update_backups(sb, primary->b_blocknr, primary->b_data, + primary->b_size); + } +exit_put: + iput(inode); + return err; +} /* ext4_group_add */ + +/* Extend the filesystem to the new number of blocks specified. This entry + * point is only used to extend the current filesystem to the end of the last + * existing group. It can be accessed via ioctl, or by "remount,resize=<size>" + * for emergencies (because it has no dependencies on reserved blocks). + * + * If we _really_ wanted, we could use default values to call ext4_group_add() + * allow the "remount" trick to work for arbitrary resizing, assuming enough + * GDT blocks are reserved to grow to the desired size. + */ +int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, + ext4_fsblk_t n_blocks_count) +{ + ext4_fsblk_t o_blocks_count; + unsigned long o_groups_count; + ext4_grpblk_t last; + ext4_grpblk_t add; + struct buffer_head * bh; + handle_t *handle; + int err; + unsigned long freed_blocks; + + /* We don't need to worry about locking wrt other resizers just + * yet: we're going to revalidate es->s_blocks_count after + * taking lock_super() below. */ + o_blocks_count = ext4_blocks_count(es); + o_groups_count = EXT4_SB(sb)->s_groups_count; + + if (test_opt(sb, DEBUG)) + printk(KERN_DEBUG "EXT4-fs: extending last group from %llu uto %llu blocks\n", + o_blocks_count, n_blocks_count); + + if (n_blocks_count == 0 || n_blocks_count == o_blocks_count) + return 0; + + if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { + printk(KERN_ERR "EXT4-fs: filesystem on %s:" + " too large to resize to %llu blocks safely\n", + sb->s_id, n_blocks_count); + if (sizeof(sector_t) < 8) + ext4_warning(sb, __FUNCTION__, + "CONFIG_LBD not enabled\n"); + return -EINVAL; + } + + if (n_blocks_count < o_blocks_count) { + ext4_warning(sb, __FUNCTION__, + "can't shrink FS - resize aborted"); + return -EBUSY; + } + + /* Handle the remaining blocks in the last group only. */ + ext4_get_group_no_and_offset(sb, o_blocks_count, NULL, &last); + + if (last == 0) { + ext4_warning(sb, __FUNCTION__, + "need to use ext2online to resize further"); + return -EPERM; + } + + add = EXT4_BLOCKS_PER_GROUP(sb) - last; + + if (o_blocks_count + add < o_blocks_count) { + ext4_warning(sb, __FUNCTION__, "blocks_count overflow"); + return -EINVAL; + } + + if (o_blocks_count + add > n_blocks_count) + add = n_blocks_count - o_blocks_count; + + if (o_blocks_count + add < n_blocks_count) + ext4_warning(sb, __FUNCTION__, + "will only finish group (%llu" + " blocks, %u new)", + o_blocks_count + add, add); + + /* See if the device is actually as big as what was requested */ + bh = sb_bread(sb, o_blocks_count + add -1); + if (!bh) { + ext4_warning(sb, __FUNCTION__, + "can't read last block, resize aborted"); + return -ENOSPC; + } + brelse(bh); + + /* We will update the superblock, one block bitmap, and + * one group descriptor via ext4_free_blocks(). + */ + handle = ext4_journal_start_sb(sb, 3); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + ext4_warning(sb, __FUNCTION__, "error %d on journal start",err); + goto exit_put; + } + + lock_super(sb); + if (o_blocks_count != ext4_blocks_count(es)) { + ext4_warning(sb, __FUNCTION__, + "multiple resizers run on filesystem!"); + unlock_super(sb); + err = -EBUSY; + goto exit_put; + } + + if ((err = ext4_journal_get_write_access(handle, + EXT4_SB(sb)->s_sbh))) { + ext4_warning(sb, __FUNCTION__, + "error %d on journal write access", err); + unlock_super(sb); + ext4_journal_stop(handle); + goto exit_put; + } + ext4_blocks_count_set(es, o_blocks_count + add); + ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh); + sb->s_dirt = 1; + unlock_super(sb); + ext4_debug("freeing blocks %lu through %llu\n", o_blocks_count, + o_blocks_count + add); + ext4_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks); + ext4_debug("freed blocks %llu through %llu\n", o_blocks_count, + o_blocks_count + add); + if ((err = ext4_journal_stop(handle))) + goto exit_put; + if (test_opt(sb, DEBUG)) + printk(KERN_DEBUG "EXT4-fs: extended group to %llu blocks\n", + ext4_blocks_count(es)); + update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es, + sizeof(struct ext4_super_block)); +exit_put: + return err; +} /* ext4_group_extend */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c new file mode 100644 index 00000000000..b4b022aa2bc --- /dev/null +++ b/fs/ext4/super.c @@ -0,0 +1,2829 @@ +/* + * linux/fs/ext4/super.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/inode.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + */ + +#include <linux/module.h> +#include <linux/string.h> +#include <linux/fs.h> +#include <linux/time.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/ext4_jbd2.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/blkdev.h> +#include <linux/parser.h> +#include <linux/smp_lock.h> +#include <linux/buffer_head.h> +#include <linux/vfs.h> +#include <linux/random.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/quotaops.h> +#include <linux/seq_file.h> + +#include <asm/uaccess.h> + +#include "xattr.h" +#include "acl.h" +#include "namei.h" + +static int ext4_load_journal(struct super_block *, struct ext4_super_block *, + unsigned long journal_devnum); +static int ext4_create_journal(struct super_block *, struct ext4_super_block *, + unsigned int); +static void ext4_commit_super (struct super_block * sb, + struct ext4_super_block * es, + int sync); +static void ext4_mark_recovery_complete(struct super_block * sb, + struct ext4_super_block * es); +static void ext4_clear_journal_err(struct super_block * sb, + struct ext4_super_block * es); +static int ext4_sync_fs(struct super_block *sb, int wait); +static const char *ext4_decode_error(struct super_block * sb, int errno, + char nbuf[16]); +static int ext4_remount (struct super_block * sb, int * flags, char * data); +static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf); +static void ext4_unlockfs(struct super_block *sb); +static void ext4_write_super (struct super_block * sb); +static void ext4_write_super_lockfs(struct super_block *sb); + + +ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, + struct ext4_group_desc *bg) +{ + return le32_to_cpu(bg->bg_block_bitmap) | + (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? + (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); +} + +ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, + struct ext4_group_desc *bg) +{ + return le32_to_cpu(bg->bg_inode_bitmap) | + (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); +} + +ext4_fsblk_t ext4_inode_table(struct super_block *sb, + struct ext4_group_desc *bg) +{ + return le32_to_cpu(bg->bg_inode_table) | + (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? + (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); +} + +void ext4_block_bitmap_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk) +{ + bg->bg_block_bitmap = cpu_to_le32((u32)blk); + if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) + bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32); +} + +void ext4_inode_bitmap_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk) +{ + bg->bg_inode_bitmap = cpu_to_le32((u32)blk); + if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) + bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32); +} + +void ext4_inode_table_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk) +{ + bg->bg_inode_table = cpu_to_le32((u32)blk); + if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) + bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); +} + +/* + * Wrappers for jbd2_journal_start/end. + * + * The only special thing we need to do here is to make sure that all + * journal_end calls result in the superblock being marked dirty, so + * that sync() will call the filesystem's write_super callback if + * appropriate. + */ +handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) +{ + journal_t *journal; + + if (sb->s_flags & MS_RDONLY) + return ERR_PTR(-EROFS); + + /* Special case here: if the journal has aborted behind our + * backs (eg. EIO in the commit thread), then we still need to + * take the FS itself readonly cleanly. */ + journal = EXT4_SB(sb)->s_journal; + if (is_journal_aborted(journal)) { + ext4_abort(sb, __FUNCTION__, + "Detected aborted journal"); + return ERR_PTR(-EROFS); + } + + return jbd2_journal_start(journal, nblocks); +} + +/* + * The only special thing we need to do here is to make sure that all + * jbd2_journal_stop calls result in the superblock being marked dirty, so + * that sync() will call the filesystem's write_super callback if + * appropriate. + */ +int __ext4_journal_stop(const char *where, handle_t *handle) +{ + struct super_block *sb; + int err; + int rc; + + sb = handle->h_transaction->t_journal->j_private; + err = handle->h_err; + rc = jbd2_journal_stop(handle); + + if (!err) + err = rc; + if (err) + __ext4_std_error(sb, where, err); + return err; +} + +void ext4_journal_abort_handle(const char *caller, const char *err_fn, + struct buffer_head *bh, handle_t *handle, int err) +{ + char nbuf[16]; + const char *errstr = ext4_decode_error(NULL, err, nbuf); + + if (bh) + BUFFER_TRACE(bh, "abort"); + + if (!handle->h_err) + handle->h_err = err; + + if (is_handle_aborted(handle)) + return; + + printk(KERN_ERR "%s: aborting transaction: %s in %s\n", + caller, errstr, err_fn); + + jbd2_journal_abort_handle(handle); +} + +/* Deal with the reporting of failure conditions on a filesystem such as + * inconsistencies detected or read IO failures. + * + * On ext2, we can store the error state of the filesystem in the + * superblock. That is not possible on ext4, because we may have other + * write ordering constraints on the superblock which prevent us from + * writing it out straight away; and given that the journal is about to + * be aborted, we can't rely on the current, or future, transactions to + * write out the superblock safely. + * + * We'll just use the jbd2_journal_abort() error code to record an error in + * the journal instead. On recovery, the journal will compain about + * that error until we've noted it down and cleared it. + */ + +static void ext4_handle_error(struct super_block *sb) +{ + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + + if (sb->s_flags & MS_RDONLY) + return; + + if (!test_opt (sb, ERRORS_CONT)) { + journal_t *journal = EXT4_SB(sb)->s_journal; + + EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT; + if (journal) + jbd2_journal_abort(journal, -EIO); + } + if (test_opt (sb, ERRORS_RO)) { + printk (KERN_CRIT "Remounting filesystem read-only\n"); + sb->s_flags |= MS_RDONLY; + } + ext4_commit_super(sb, es, 1); + if (test_opt(sb, ERRORS_PANIC)) + panic("EXT4-fs (device %s): panic forced after error\n", + sb->s_id); +} + +void ext4_error (struct super_block * sb, const char * function, + const char * fmt, ...) +{ + va_list args; + + va_start(args, fmt); + printk(KERN_CRIT "EXT4-fs error (device %s): %s: ",sb->s_id, function); + vprintk(fmt, args); + printk("\n"); + va_end(args); + + ext4_handle_error(sb); +} + +static const char *ext4_decode_error(struct super_block * sb, int errno, + char nbuf[16]) +{ + char *errstr = NULL; + + switch (errno) { + case -EIO: + errstr = "IO failure"; + break; + case -ENOMEM: + errstr = "Out of memory"; + break; + case -EROFS: + if (!sb || EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT) + errstr = "Journal has aborted"; + else + errstr = "Readonly filesystem"; + break; + default: + /* If the caller passed in an extra buffer for unknown + * errors, textualise them now. Else we just return + * NULL. */ + if (nbuf) { + /* Check for truncated error codes... */ + if (snprintf(nbuf, 16, "error %d", -errno) >= 0) + errstr = nbuf; + } + break; + } + + return errstr; +} + +/* __ext4_std_error decodes expected errors from journaling functions + * automatically and invokes the appropriate error response. */ + +void __ext4_std_error (struct super_block * sb, const char * function, + int errno) +{ + char nbuf[16]; + const char *errstr; + + /* Special case: if the error is EROFS, and we're not already + * inside a transaction, then there's really no point in logging + * an error. */ + if (errno == -EROFS && journal_current_handle() == NULL && + (sb->s_flags & MS_RDONLY)) + return; + + errstr = ext4_decode_error(sb, errno, nbuf); + printk (KERN_CRIT "EXT4-fs error (device %s) in %s: %s\n", + sb->s_id, function, errstr); + + ext4_handle_error(sb); +} + +/* + * ext4_abort is a much stronger failure handler than ext4_error. The + * abort function may be used to deal with unrecoverable failures such + * as journal IO errors or ENOMEM at a critical moment in log management. + * + * We unconditionally force the filesystem into an ABORT|READONLY state, + * unless the error response on the fs has been set to panic in which + * case we take the easy way out and panic immediately. + */ + +void ext4_abort (struct super_block * sb, const char * function, + const char * fmt, ...) +{ + va_list args; + + printk (KERN_CRIT "ext4_abort called.\n"); + + va_start(args, fmt); + printk(KERN_CRIT "EXT4-fs error (device %s): %s: ",sb->s_id, function); + vprintk(fmt, args); + printk("\n"); + va_end(args); + + if (test_opt(sb, ERRORS_PANIC)) + panic("EXT4-fs panic from previous error\n"); + + if (sb->s_flags & MS_RDONLY) + return; + + printk(KERN_CRIT "Remounting filesystem read-only\n"); + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + sb->s_flags |= MS_RDONLY; + EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT; + jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); +} + +void ext4_warning (struct super_block * sb, const char * function, + const char * fmt, ...) +{ + va_list args; + + va_start(args, fmt); + printk(KERN_WARNING "EXT4-fs warning (device %s): %s: ", + sb->s_id, function); + vprintk(fmt, args); + printk("\n"); + va_end(args); +} + +void ext4_update_dynamic_rev(struct super_block *sb) +{ + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + + if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV) + return; + + ext4_warning(sb, __FUNCTION__, + "updating to rev %d because of new feature flag, " + "running e2fsck is recommended", + EXT4_DYNAMIC_REV); + + es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO); + es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE); + es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV); + /* leave es->s_feature_*compat flags alone */ + /* es->s_uuid will be set by e2fsck if empty */ + + /* + * The rest of the superblock fields should be zero, and if not it + * means they are likely already in use, so leave them alone. We + * can leave it up to e2fsck to clean up any inconsistencies there. + */ +} + +/* + * Open the external journal device + */ +static struct block_device *ext4_blkdev_get(dev_t dev) +{ + struct block_device *bdev; + char b[BDEVNAME_SIZE]; + + bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE); + if (IS_ERR(bdev)) + goto fail; + return bdev; + +fail: + printk(KERN_ERR "EXT4: failed to open journal device %s: %ld\n", + __bdevname(dev, b), PTR_ERR(bdev)); + return NULL; +} + +/* + * Release the journal device + */ +static int ext4_blkdev_put(struct block_device *bdev) +{ + bd_release(bdev); + return blkdev_put(bdev); +} + +static int ext4_blkdev_remove(struct ext4_sb_info *sbi) +{ + struct block_device *bdev; + int ret = -ENODEV; + + bdev = sbi->journal_bdev; + if (bdev) { + ret = ext4_blkdev_put(bdev); + sbi->journal_bdev = NULL; + } + return ret; +} + +static inline struct inode *orphan_list_entry(struct list_head *l) +{ + return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode; +} + +static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) +{ + struct list_head *l; + + printk(KERN_ERR "sb orphan head is %d\n", + le32_to_cpu(sbi->s_es->s_last_orphan)); + + printk(KERN_ERR "sb_info orphan list:\n"); + list_for_each(l, &sbi->s_orphan) { + struct inode *inode = orphan_list_entry(l); + printk(KERN_ERR " " + "inode %s:%lu at %p: mode %o, nlink %d, next %d\n", + inode->i_sb->s_id, inode->i_ino, inode, + inode->i_mode, inode->i_nlink, + NEXT_ORPHAN(inode)); + } +} + +static void ext4_put_super (struct super_block * sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + int i; + + ext4_ext_release(sb); + ext4_xattr_put_super(sb); + jbd2_journal_destroy(sbi->s_journal); + if (!(sb->s_flags & MS_RDONLY)) { + EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + es->s_state = cpu_to_le16(sbi->s_mount_state); + BUFFER_TRACE(sbi->s_sbh, "marking dirty"); + mark_buffer_dirty(sbi->s_sbh); + ext4_commit_super(sb, es, 1); + } + + for (i = 0; i < sbi->s_gdb_count; i++) + brelse(sbi->s_group_desc[i]); + kfree(sbi->s_group_desc); + percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeinodes_counter); + percpu_counter_destroy(&sbi->s_dirs_counter); + brelse(sbi->s_sbh); +#ifdef CONFIG_QUOTA + for (i = 0; i < MAXQUOTAS; i++) + kfree(sbi->s_qf_names[i]); +#endif + + /* Debugging code just in case the in-memory inode orphan list + * isn't empty. The on-disk one can be non-empty if we've + * detected an error and taken the fs readonly, but the + * in-memory list had better be clean by this point. */ + if (!list_empty(&sbi->s_orphan)) + dump_orphan_list(sb, sbi); + J_ASSERT(list_empty(&sbi->s_orphan)); + + invalidate_bdev(sb->s_bdev, 0); + if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) { + /* + * Invalidate the journal device's buffers. We don't want them + * floating about in memory - the physical journal device may + * hotswapped, and it breaks the `ro-after' testing code. + */ + sync_blockdev(sbi->journal_bdev); + invalidate_bdev(sbi->journal_bdev, 0); + ext4_blkdev_remove(sbi); + } + sb->s_fs_info = NULL; + kfree(sbi); + return; +} + +static kmem_cache_t *ext4_inode_cachep; + +/* + * Called inside transaction, so use GFP_NOFS + */ +static struct inode *ext4_alloc_inode(struct super_block *sb) +{ + struct ext4_inode_info *ei; + + ei = kmem_cache_alloc(ext4_inode_cachep, SLAB_NOFS); + if (!ei) + return NULL; +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + ei->i_acl = EXT4_ACL_NOT_CACHED; + ei->i_default_acl = EXT4_ACL_NOT_CACHED; +#endif + ei->i_block_alloc_info = NULL; + ei->vfs_inode.i_version = 1; + memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache)); + return &ei->vfs_inode; +} + +static void ext4_destroy_inode(struct inode *inode) +{ + kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); +} + +static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags) +{ + struct ext4_inode_info *ei = (struct ext4_inode_info *) foo; + + if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == + SLAB_CTOR_CONSTRUCTOR) { + INIT_LIST_HEAD(&ei->i_orphan); +#ifdef CONFIG_EXT4DEV_FS_XATTR + init_rwsem(&ei->xattr_sem); +#endif + mutex_init(&ei->truncate_mutex); + inode_init_once(&ei->vfs_inode); + } +} + +static int init_inodecache(void) +{ + ext4_inode_cachep = kmem_cache_create("ext4_inode_cache", + sizeof(struct ext4_inode_info), + 0, (SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD), + init_once, NULL); + if (ext4_inode_cachep == NULL) + return -ENOMEM; + return 0; +} + +static void destroy_inodecache(void) +{ + kmem_cache_destroy(ext4_inode_cachep); +} + +static void ext4_clear_inode(struct inode *inode) +{ + struct ext4_block_alloc_info *rsv = EXT4_I(inode)->i_block_alloc_info; +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + if (EXT4_I(inode)->i_acl && + EXT4_I(inode)->i_acl != EXT4_ACL_NOT_CACHED) { + posix_acl_release(EXT4_I(inode)->i_acl); + EXT4_I(inode)->i_acl = EXT4_ACL_NOT_CACHED; + } + if (EXT4_I(inode)->i_default_acl && + EXT4_I(inode)->i_default_acl != EXT4_ACL_NOT_CACHED) { + posix_acl_release(EXT4_I(inode)->i_default_acl); + EXT4_I(inode)->i_default_acl = EXT4_ACL_NOT_CACHED; + } +#endif + ext4_discard_reservation(inode); + EXT4_I(inode)->i_block_alloc_info = NULL; + if (unlikely(rsv)) + kfree(rsv); +} + +static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb) +{ +#if defined(CONFIG_QUOTA) + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (sbi->s_jquota_fmt) + seq_printf(seq, ",jqfmt=%s", + (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0"); + + if (sbi->s_qf_names[USRQUOTA]) + seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]); + + if (sbi->s_qf_names[GRPQUOTA]) + seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]); + + if (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA) + seq_puts(seq, ",usrquota"); + + if (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA) + seq_puts(seq, ",grpquota"); +#endif +} + +static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) +{ + struct super_block *sb = vfs->mnt_sb; + + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) + seq_puts(seq, ",data=journal"); + else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) + seq_puts(seq, ",data=ordered"); + else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) + seq_puts(seq, ",data=writeback"); + + ext4_show_quota_options(seq, sb); + + return 0; +} + + +static struct dentry *ext4_get_dentry(struct super_block *sb, void *vobjp) +{ + __u32 *objp = vobjp; + unsigned long ino = objp[0]; + __u32 generation = objp[1]; + struct inode *inode; + struct dentry *result; + + if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) + return ERR_PTR(-ESTALE); + if (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)) + return ERR_PTR(-ESTALE); + + /* iget isn't really right if the inode is currently unallocated!! + * + * ext4_read_inode will return a bad_inode if the inode had been + * deleted, so we should be safe. + * + * Currently we don't know the generation for parent directory, so + * a generation of 0 means "accept any" + */ + inode = iget(sb, ino); + if (inode == NULL) + return ERR_PTR(-ENOMEM); + if (is_bad_inode(inode) || + (generation && inode->i_generation != generation)) { + iput(inode); + return ERR_PTR(-ESTALE); + } + /* now to find a dentry. + * If possible, get a well-connected one + */ + result = d_alloc_anon(inode); + if (!result) { + iput(inode); + return ERR_PTR(-ENOMEM); + } + return result; +} + +#ifdef CONFIG_QUOTA +#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group") +#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA)) + +static int ext4_dquot_initialize(struct inode *inode, int type); +static int ext4_dquot_drop(struct inode *inode); +static int ext4_write_dquot(struct dquot *dquot); +static int ext4_acquire_dquot(struct dquot *dquot); +static int ext4_release_dquot(struct dquot *dquot); +static int ext4_mark_dquot_dirty(struct dquot *dquot); +static int ext4_write_info(struct super_block *sb, int type); +static int ext4_quota_on(struct super_block *sb, int type, int format_id, char *path); +static int ext4_quota_on_mount(struct super_block *sb, int type); +static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, + size_t len, loff_t off); +static ssize_t ext4_quota_write(struct super_block *sb, int type, + const char *data, size_t len, loff_t off); + +static struct dquot_operations ext4_quota_operations = { + .initialize = ext4_dquot_initialize, + .drop = ext4_dquot_drop, + .alloc_space = dquot_alloc_space, + .alloc_inode = dquot_alloc_inode, + .free_space = dquot_free_space, + .free_inode = dquot_free_inode, + .transfer = dquot_transfer, + .write_dquot = ext4_write_dquot, + .acquire_dquot = ext4_acquire_dquot, + .release_dquot = ext4_release_dquot, + .mark_dirty = ext4_mark_dquot_dirty, + .write_info = ext4_write_info +}; + +static struct quotactl_ops ext4_qctl_operations = { + .quota_on = ext4_quota_on, + .quota_off = vfs_quota_off, + .quota_sync = vfs_quota_sync, + .get_info = vfs_get_dqinfo, + .set_info = vfs_set_dqinfo, + .get_dqblk = vfs_get_dqblk, + .set_dqblk = vfs_set_dqblk +}; +#endif + +static struct super_operations ext4_sops = { + .alloc_inode = ext4_alloc_inode, + .destroy_inode = ext4_destroy_inode, + .read_inode = ext4_read_inode, + .write_inode = ext4_write_inode, + .dirty_inode = ext4_dirty_inode, + .delete_inode = ext4_delete_inode, + .put_super = ext4_put_super, + .write_super = ext4_write_super, + .sync_fs = ext4_sync_fs, + .write_super_lockfs = ext4_write_super_lockfs, + .unlockfs = ext4_unlockfs, + .statfs = ext4_statfs, + .remount_fs = ext4_remount, + .clear_inode = ext4_clear_inode, + .show_options = ext4_show_options, +#ifdef CONFIG_QUOTA + .quota_read = ext4_quota_read, + .quota_write = ext4_quota_write, +#endif +}; + +static struct export_operations ext4_export_ops = { + .get_parent = ext4_get_parent, + .get_dentry = ext4_get_dentry, +}; + +enum { + Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, + Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro, + Opt_nouid32, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov, + Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, + Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh, + Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev, + Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, + Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, + Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, + Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota, + Opt_grpquota, Opt_extents, +}; + +static match_table_t tokens = { + {Opt_bsd_df, "bsddf"}, + {Opt_minix_df, "minixdf"}, + {Opt_grpid, "grpid"}, + {Opt_grpid, "bsdgroups"}, + {Opt_nogrpid, "nogrpid"}, + {Opt_nogrpid, "sysvgroups"}, + {Opt_resgid, "resgid=%u"}, + {Opt_resuid, "resuid=%u"}, + {Opt_sb, "sb=%u"}, + {Opt_err_cont, "errors=continue"}, + {Opt_err_panic, "errors=panic"}, + {Opt_err_ro, "errors=remount-ro"}, + {Opt_nouid32, "nouid32"}, + {Opt_nocheck, "nocheck"}, + {Opt_nocheck, "check=none"}, + {Opt_debug, "debug"}, + {Opt_oldalloc, "oldalloc"}, + {Opt_orlov, "orlov"}, + {Opt_user_xattr, "user_xattr"}, + {Opt_nouser_xattr, "nouser_xattr"}, + {Opt_acl, "acl"}, + {Opt_noacl, "noacl"}, + {Opt_reservation, "reservation"}, + {Opt_noreservation, "noreservation"}, + {Opt_noload, "noload"}, + {Opt_nobh, "nobh"}, + {Opt_bh, "bh"}, + {Opt_commit, "commit=%u"}, + {Opt_journal_update, "journal=update"}, + {Opt_journal_inum, "journal=%u"}, + {Opt_journal_dev, "journal_dev=%u"}, + {Opt_abort, "abort"}, + {Opt_data_journal, "data=journal"}, + {Opt_data_ordered, "data=ordered"}, + {Opt_data_writeback, "data=writeback"}, + {Opt_offusrjquota, "usrjquota="}, + {Opt_usrjquota, "usrjquota=%s"}, + {Opt_offgrpjquota, "grpjquota="}, + {Opt_grpjquota, "grpjquota=%s"}, + {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, + {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, + {Opt_grpquota, "grpquota"}, + {Opt_noquota, "noquota"}, + {Opt_quota, "quota"}, + {Opt_usrquota, "usrquota"}, + {Opt_barrier, "barrier=%u"}, + {Opt_extents, "extents"}, + {Opt_err, NULL}, + {Opt_resize, "resize"}, +}; + +static ext4_fsblk_t get_sb_block(void **data) +{ + ext4_fsblk_t sb_block; + char *options = (char *) *data; + + if (!options || strncmp(options, "sb=", 3) != 0) + return 1; /* Default location */ + options += 3; + /*todo: use simple_strtoll with >32bit ext4 */ + sb_block = simple_strtoul(options, &options, 0); + if (*options && *options != ',') { + printk("EXT4-fs: Invalid sb specification: %s\n", + (char *) *data); + return 1; + } + if (*options == ',') + options++; + *data = (void *) options; + return sb_block; +} + +static int parse_options (char *options, struct super_block *sb, + unsigned int *inum, unsigned long *journal_devnum, + ext4_fsblk_t *n_blocks_count, int is_remount) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + char * p; + substring_t args[MAX_OPT_ARGS]; + int data_opt = 0; + int option; +#ifdef CONFIG_QUOTA + int qtype; + char *qname; +#endif + + if (!options) + return 1; + + while ((p = strsep (&options, ",")) != NULL) { + int token; + if (!*p) + continue; + + token = match_token(p, tokens, args); + switch (token) { + case Opt_bsd_df: + clear_opt (sbi->s_mount_opt, MINIX_DF); + break; + case Opt_minix_df: + set_opt (sbi->s_mount_opt, MINIX_DF); + break; + case Opt_grpid: + set_opt (sbi->s_mount_opt, GRPID); + break; + case Opt_nogrpid: + clear_opt (sbi->s_mount_opt, GRPID); + break; + case Opt_resuid: + if (match_int(&args[0], &option)) + return 0; + sbi->s_resuid = option; + break; + case Opt_resgid: + if (match_int(&args[0], &option)) + return 0; + sbi->s_resgid = option; + break; + case Opt_sb: + /* handled by get_sb_block() instead of here */ + /* *sb_block = match_int(&args[0]); */ + break; + case Opt_err_panic: + clear_opt (sbi->s_mount_opt, ERRORS_CONT); + clear_opt (sbi->s_mount_opt, ERRORS_RO); + set_opt (sbi->s_mount_opt, ERRORS_PANIC); + break; + case Opt_err_ro: + clear_opt (sbi->s_mount_opt, ERRORS_CONT); + clear_opt (sbi->s_mount_opt, ERRORS_PANIC); + set_opt (sbi->s_mount_opt, ERRORS_RO); + break; + case Opt_err_cont: + clear_opt (sbi->s_mount_opt, ERRORS_RO); + clear_opt (sbi->s_mount_opt, ERRORS_PANIC); + set_opt (sbi->s_mount_opt, ERRORS_CONT); + break; + case Opt_nouid32: + set_opt (sbi->s_mount_opt, NO_UID32); + break; + case Opt_nocheck: + clear_opt (sbi->s_mount_opt, CHECK); + break; + case Opt_debug: + set_opt (sbi->s_mount_opt, DEBUG); + break; + case Opt_oldalloc: + set_opt (sbi->s_mount_opt, OLDALLOC); + break; + case Opt_orlov: + clear_opt (sbi->s_mount_opt, OLDALLOC); + break; +#ifdef CONFIG_EXT4DEV_FS_XATTR + case Opt_user_xattr: + set_opt (sbi->s_mount_opt, XATTR_USER); + break; + case Opt_nouser_xattr: + clear_opt (sbi->s_mount_opt, XATTR_USER); + break; +#else + case Opt_user_xattr: + case Opt_nouser_xattr: + printk("EXT4 (no)user_xattr options not supported\n"); + break; +#endif +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + case Opt_acl: + set_opt(sbi->s_mount_opt, POSIX_ACL); + break; + case Opt_noacl: + clear_opt(sbi->s_mount_opt, POSIX_ACL); + break; +#else + case Opt_acl: + case Opt_noacl: + printk("EXT4 (no)acl options not supported\n"); + break; +#endif + case Opt_reservation: + set_opt(sbi->s_mount_opt, RESERVATION); + break; + case Opt_noreservation: + clear_opt(sbi->s_mount_opt, RESERVATION); + break; + case Opt_journal_update: + /* @@@ FIXME */ + /* Eventually we will want to be able to create + a journal file here. For now, only allow the + user to specify an existing inode to be the + journal file. */ + if (is_remount) { + printk(KERN_ERR "EXT4-fs: cannot specify " + "journal on remount\n"); + return 0; + } + set_opt (sbi->s_mount_opt, UPDATE_JOURNAL); + break; + case Opt_journal_inum: + if (is_remount) { + printk(KERN_ERR "EXT4-fs: cannot specify " + "journal on remount\n"); + return 0; + } + if (match_int(&args[0], &option)) + return 0; + *inum = option; + break; + case Opt_journal_dev: + if (is_remount) { + printk(KERN_ERR "EXT4-fs: cannot specify " + "journal on remount\n"); + return 0; + } + if (match_int(&args[0], &option)) + return 0; + *journal_devnum = option; + break; + case Opt_noload: + set_opt (sbi->s_mount_opt, NOLOAD); + break; + case Opt_commit: + if (match_int(&args[0], &option)) + return 0; + if (option < 0) + return 0; + if (option == 0) + option = JBD_DEFAULT_MAX_COMMIT_AGE; + sbi->s_commit_interval = HZ * option; + break; + case Opt_data_journal: + data_opt = EXT4_MOUNT_JOURNAL_DATA; + goto datacheck; + case Opt_data_ordered: + data_opt = EXT4_MOUNT_ORDERED_DATA; + goto datacheck; + case Opt_data_writeback: + data_opt = EXT4_MOUNT_WRITEBACK_DATA; + datacheck: + if (is_remount) { + if ((sbi->s_mount_opt & EXT4_MOUNT_DATA_FLAGS) + != data_opt) { + printk(KERN_ERR + "EXT4-fs: cannot change data " + "mode on remount\n"); + return 0; + } + } else { + sbi->s_mount_opt &= ~EXT4_MOUNT_DATA_FLAGS; + sbi->s_mount_opt |= data_opt; + } + break; +#ifdef CONFIG_QUOTA + case Opt_usrjquota: + qtype = USRQUOTA; + goto set_qf_name; + case Opt_grpjquota: + qtype = GRPQUOTA; +set_qf_name: + if (sb_any_quota_enabled(sb)) { + printk(KERN_ERR + "EXT4-fs: Cannot change journalled " + "quota options when quota turned on.\n"); + return 0; + } + qname = match_strdup(&args[0]); + if (!qname) { + printk(KERN_ERR + "EXT4-fs: not enough memory for " + "storing quotafile name.\n"); + return 0; + } + if (sbi->s_qf_names[qtype] && + strcmp(sbi->s_qf_names[qtype], qname)) { + printk(KERN_ERR + "EXT4-fs: %s quota file already " + "specified.\n", QTYPE2NAME(qtype)); + kfree(qname); + return 0; + } + sbi->s_qf_names[qtype] = qname; + if (strchr(sbi->s_qf_names[qtype], '/')) { + printk(KERN_ERR + "EXT4-fs: quotafile must be on " + "filesystem root.\n"); + kfree(sbi->s_qf_names[qtype]); + sbi->s_qf_names[qtype] = NULL; + return 0; + } + set_opt(sbi->s_mount_opt, QUOTA); + break; + case Opt_offusrjquota: + qtype = USRQUOTA; + goto clear_qf_name; + case Opt_offgrpjquota: + qtype = GRPQUOTA; +clear_qf_name: + if (sb_any_quota_enabled(sb)) { + printk(KERN_ERR "EXT4-fs: Cannot change " + "journalled quota options when " + "quota turned on.\n"); + return 0; + } + /* + * The space will be released later when all options + * are confirmed to be correct + */ + sbi->s_qf_names[qtype] = NULL; + break; + case Opt_jqfmt_vfsold: + sbi->s_jquota_fmt = QFMT_VFS_OLD; + break; + case Opt_jqfmt_vfsv0: + sbi->s_jquota_fmt = QFMT_VFS_V0; + break; + case Opt_quota: + case Opt_usrquota: + set_opt(sbi->s_mount_opt, QUOTA); + set_opt(sbi->s_mount_opt, USRQUOTA); + break; + case Opt_grpquota: + set_opt(sbi->s_mount_opt, QUOTA); + set_opt(sbi->s_mount_opt, GRPQUOTA); + break; + case Opt_noquota: + if (sb_any_quota_enabled(sb)) { + printk(KERN_ERR "EXT4-fs: Cannot change quota " + "options when quota turned on.\n"); + return 0; + } + clear_opt(sbi->s_mount_opt, QUOTA); + clear_opt(sbi->s_mount_opt, USRQUOTA); + clear_opt(sbi->s_mount_opt, GRPQUOTA); + break; +#else + case Opt_quota: + case Opt_usrquota: + case Opt_grpquota: + case Opt_usrjquota: + case Opt_grpjquota: + case Opt_offusrjquota: + case Opt_offgrpjquota: + case Opt_jqfmt_vfsold: + case Opt_jqfmt_vfsv0: + printk(KERN_ERR + "EXT4-fs: journalled quota options not " + "supported.\n"); + break; + case Opt_noquota: + break; +#endif + case Opt_abort: + set_opt(sbi->s_mount_opt, ABORT); + break; + case Opt_barrier: + if (match_int(&args[0], &option)) + return 0; + if (option) + set_opt(sbi->s_mount_opt, BARRIER); + else + clear_opt(sbi->s_mount_opt, BARRIER); + break; + case Opt_ignore: + break; + case Opt_resize: + if (!is_remount) { + printk("EXT4-fs: resize option only available " + "for remount\n"); + return 0; + } + if (match_int(&args[0], &option) != 0) + return 0; + *n_blocks_count = option; + break; + case Opt_nobh: + set_opt(sbi->s_mount_opt, NOBH); + break; + case Opt_bh: + clear_opt(sbi->s_mount_opt, NOBH); + break; + case Opt_extents: + set_opt (sbi->s_mount_opt, EXTENTS); + break; + default: + printk (KERN_ERR + "EXT4-fs: Unrecognized mount option \"%s\" " + "or missing value\n", p); + return 0; + } + } +#ifdef CONFIG_QUOTA + if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { + if ((sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA) && + sbi->s_qf_names[USRQUOTA]) + clear_opt(sbi->s_mount_opt, USRQUOTA); + + if ((sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA) && + sbi->s_qf_names[GRPQUOTA]) + clear_opt(sbi->s_mount_opt, GRPQUOTA); + + if ((sbi->s_qf_names[USRQUOTA] && + (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)) || + (sbi->s_qf_names[GRPQUOTA] && + (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA))) { + printk(KERN_ERR "EXT4-fs: old and new quota " + "format mixing.\n"); + return 0; + } + + if (!sbi->s_jquota_fmt) { + printk(KERN_ERR "EXT4-fs: journalled quota format " + "not specified.\n"); + return 0; + } + } else { + if (sbi->s_jquota_fmt) { + printk(KERN_ERR "EXT4-fs: journalled quota format " + "specified with no journalling " + "enabled.\n"); + return 0; + } + } +#endif + return 1; +} + +static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, + int read_only) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + int res = 0; + + if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { + printk (KERN_ERR "EXT4-fs warning: revision level too high, " + "forcing read-only mode\n"); + res = MS_RDONLY; + } + if (read_only) + return res; + if (!(sbi->s_mount_state & EXT4_VALID_FS)) + printk (KERN_WARNING "EXT4-fs warning: mounting unchecked fs, " + "running e2fsck is recommended\n"); + else if ((sbi->s_mount_state & EXT4_ERROR_FS)) + printk (KERN_WARNING + "EXT4-fs warning: mounting fs with errors, " + "running e2fsck is recommended\n"); + else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 && + le16_to_cpu(es->s_mnt_count) >= + (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) + printk (KERN_WARNING + "EXT4-fs warning: maximal mount count reached, " + "running e2fsck is recommended\n"); + else if (le32_to_cpu(es->s_checkinterval) && + (le32_to_cpu(es->s_lastcheck) + + le32_to_cpu(es->s_checkinterval) <= get_seconds())) + printk (KERN_WARNING + "EXT4-fs warning: checktime reached, " + "running e2fsck is recommended\n"); +#if 0 + /* @@@ We _will_ want to clear the valid bit if we find + * inconsistencies, to force a fsck at reboot. But for + * a plain journaled filesystem we can keep it set as + * valid forever! :) + */ + es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) & ~EXT4_VALID_FS); +#endif + if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) + es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); + es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1); + es->s_mtime = cpu_to_le32(get_seconds()); + ext4_update_dynamic_rev(sb); + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + + ext4_commit_super(sb, es, 1); + if (test_opt(sb, DEBUG)) + printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%lu, " + "bpg=%lu, ipg=%lu, mo=%04lx]\n", + sb->s_blocksize, + sbi->s_groups_count, + EXT4_BLOCKS_PER_GROUP(sb), + EXT4_INODES_PER_GROUP(sb), + sbi->s_mount_opt); + + printk(KERN_INFO "EXT4 FS on %s, ", sb->s_id); + if (EXT4_SB(sb)->s_journal->j_inode == NULL) { + char b[BDEVNAME_SIZE]; + + printk("external journal on %s\n", + bdevname(EXT4_SB(sb)->s_journal->j_dev, b)); + } else { + printk("internal journal\n"); + } + return res; +} + +/* Called at mount-time, super-block is locked */ +static int ext4_check_descriptors (struct super_block * sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); + ext4_fsblk_t last_block; + ext4_fsblk_t block_bitmap; + ext4_fsblk_t inode_bitmap; + ext4_fsblk_t inode_table; + struct ext4_group_desc * gdp = NULL; + int desc_block = 0; + int i; + + ext4_debug ("Checking group descriptors"); + + for (i = 0; i < sbi->s_groups_count; i++) + { + if (i == sbi->s_groups_count - 1) + last_block = ext4_blocks_count(sbi->s_es) - 1; + else + last_block = first_block + + (EXT4_BLOCKS_PER_GROUP(sb) - 1); + + if ((i % EXT4_DESC_PER_BLOCK(sb)) == 0) + gdp = (struct ext4_group_desc *) + sbi->s_group_desc[desc_block++]->b_data; + block_bitmap = ext4_block_bitmap(sb, gdp); + if (block_bitmap < first_block || block_bitmap > last_block) + { + ext4_error (sb, "ext4_check_descriptors", + "Block bitmap for group %d" + " not in group (block %llu)!", + i, block_bitmap); + return 0; + } + inode_bitmap = ext4_inode_bitmap(sb, gdp); + if (inode_bitmap < first_block || inode_bitmap > last_block) + { + ext4_error (sb, "ext4_check_descriptors", + "Inode bitmap for group %d" + " not in group (block %llu)!", + i, inode_bitmap); + return 0; + } + inode_table = ext4_inode_table(sb, gdp); + if (inode_table < first_block || + inode_table + sbi->s_itb_per_group > last_block) + { + ext4_error (sb, "ext4_check_descriptors", + "Inode table for group %d" + " not in group (block %llu)!", + i, inode_table); + return 0; + } + first_block += EXT4_BLOCKS_PER_GROUP(sb); + gdp = (struct ext4_group_desc *) + ((__u8 *)gdp + EXT4_DESC_SIZE(sb)); + } + + ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); + sbi->s_es->s_free_inodes_count=cpu_to_le32(ext4_count_free_inodes(sb)); + return 1; +} + + +/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at + * the superblock) which were deleted from all directories, but held open by + * a process at the time of a crash. We walk the list and try to delete these + * inodes at recovery time (only with a read-write filesystem). + * + * In order to keep the orphan inode chain consistent during traversal (in + * case of crash during recovery), we link each inode into the superblock + * orphan list_head and handle it the same way as an inode deletion during + * normal operation (which journals the operations for us). + * + * We only do an iget() and an iput() on each inode, which is very safe if we + * accidentally point at an in-use or already deleted inode. The worst that + * can happen in this case is that we get a "bit already cleared" message from + * ext4_free_inode(). The only reason we would point at a wrong inode is if + * e2fsck was run on this filesystem, and it must have already done the orphan + * inode cleanup for us, so we can safely abort without any further action. + */ +static void ext4_orphan_cleanup (struct super_block * sb, + struct ext4_super_block * es) +{ + unsigned int s_flags = sb->s_flags; + int nr_orphans = 0, nr_truncates = 0; +#ifdef CONFIG_QUOTA + int i; +#endif + if (!es->s_last_orphan) { + jbd_debug(4, "no orphan inodes to clean up\n"); + return; + } + + if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { + if (es->s_last_orphan) + jbd_debug(1, "Errors on filesystem, " + "clearing orphan list.\n"); + es->s_last_orphan = 0; + jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); + return; + } + + if (s_flags & MS_RDONLY) { + printk(KERN_INFO "EXT4-fs: %s: orphan cleanup on readonly fs\n", + sb->s_id); + sb->s_flags &= ~MS_RDONLY; + } +#ifdef CONFIG_QUOTA + /* Needed for iput() to work correctly and not trash data */ + sb->s_flags |= MS_ACTIVE; + /* Turn on quotas so that they are updated correctly */ + for (i = 0; i < MAXQUOTAS; i++) { + if (EXT4_SB(sb)->s_qf_names[i]) { + int ret = ext4_quota_on_mount(sb, i); + if (ret < 0) + printk(KERN_ERR + "EXT4-fs: Cannot turn on journalled " + "quota: error %d\n", ret); + } + } +#endif + + while (es->s_last_orphan) { + struct inode *inode; + + if (!(inode = + ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) { + es->s_last_orphan = 0; + break; + } + + list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan); + DQUOT_INIT(inode); + if (inode->i_nlink) { + printk(KERN_DEBUG + "%s: truncating inode %lu to %Ld bytes\n", + __FUNCTION__, inode->i_ino, inode->i_size); + jbd_debug(2, "truncating inode %lu to %Ld bytes\n", + inode->i_ino, inode->i_size); + ext4_truncate(inode); + nr_truncates++; + } else { + printk(KERN_DEBUG + "%s: deleting unreferenced inode %lu\n", + __FUNCTION__, inode->i_ino); + jbd_debug(2, "deleting unreferenced inode %lu\n", + inode->i_ino); + nr_orphans++; + } + iput(inode); /* The delete magic happens here! */ + } + +#define PLURAL(x) (x), ((x)==1) ? "" : "s" + + if (nr_orphans) + printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n", + sb->s_id, PLURAL(nr_orphans)); + if (nr_truncates) + printk(KERN_INFO "EXT4-fs: %s: %d truncate%s cleaned up\n", + sb->s_id, PLURAL(nr_truncates)); +#ifdef CONFIG_QUOTA + /* Turn quotas off */ + for (i = 0; i < MAXQUOTAS; i++) { + if (sb_dqopt(sb)->files[i]) + vfs_quota_off(sb, i); + } +#endif + sb->s_flags = s_flags; /* Restore MS_RDONLY status */ +} + +#define log2(n) ffz(~(n)) + +/* + * Maximal file size. There is a direct, and {,double-,triple-}indirect + * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks. + * We need to be 1 filesystem block less than the 2^32 sector limit. + */ +static loff_t ext4_max_size(int bits) +{ + loff_t res = EXT4_NDIR_BLOCKS; + /* This constant is calculated to be the largest file size for a + * dense, 4k-blocksize file such that the total number of + * sectors in the file, including data and all indirect blocks, + * does not exceed 2^32. */ + const loff_t upper_limit = 0x1ff7fffd000LL; + + res += 1LL << (bits-2); + res += 1LL << (2*(bits-2)); + res += 1LL << (3*(bits-2)); + res <<= bits; + if (res > upper_limit) + res = upper_limit; + return res; +} + +static ext4_fsblk_t descriptor_loc(struct super_block *sb, + ext4_fsblk_t logical_sb_block, int nr) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + unsigned long bg, first_meta_bg; + int has_super = 0; + + first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); + + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) || + nr < first_meta_bg) + return logical_sb_block + nr + 1; + bg = sbi->s_desc_per_block * nr; + if (ext4_bg_has_super(sb, bg)) + has_super = 1; + return (has_super + ext4_group_first_block_no(sb, bg)); +} + + +static int ext4_fill_super (struct super_block *sb, void *data, int silent) +{ + struct buffer_head * bh; + struct ext4_super_block *es = NULL; + struct ext4_sb_info *sbi; + ext4_fsblk_t block; + ext4_fsblk_t sb_block = get_sb_block(&data); + ext4_fsblk_t logical_sb_block; + unsigned long offset = 0; + unsigned int journal_inum = 0; + unsigned long journal_devnum = 0; + unsigned long def_mount_opts; + struct inode *root; + int blocksize; + int hblock; + int db_count; + int i; + int needs_recovery; + __le32 features; + __u64 blocks_count; + + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) + return -ENOMEM; + sb->s_fs_info = sbi; + sbi->s_mount_opt = 0; + sbi->s_resuid = EXT4_DEF_RESUID; + sbi->s_resgid = EXT4_DEF_RESGID; + + unlock_kernel(); + + blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); + if (!blocksize) { + printk(KERN_ERR "EXT4-fs: unable to set blocksize\n"); + goto out_fail; + } + + /* + * The ext4 superblock will not be buffer aligned for other than 1kB + * block sizes. We need to calculate the offset from buffer start. + */ + if (blocksize != EXT4_MIN_BLOCK_SIZE) { + logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE; + offset = do_div(logical_sb_block, blocksize); + } else { + logical_sb_block = sb_block; + } + + if (!(bh = sb_bread(sb, logical_sb_block))) { + printk (KERN_ERR "EXT4-fs: unable to read superblock\n"); + goto out_fail; + } + /* + * Note: s_es must be initialized as soon as possible because + * some ext4 macro-instructions depend on its value + */ + es = (struct ext4_super_block *) (((char *)bh->b_data) + offset); + sbi->s_es = es; + sb->s_magic = le16_to_cpu(es->s_magic); + if (sb->s_magic != EXT4_SUPER_MAGIC) + goto cantfind_ext4; + + /* Set defaults before we parse the mount options */ + def_mount_opts = le32_to_cpu(es->s_default_mount_opts); + if (def_mount_opts & EXT4_DEFM_DEBUG) + set_opt(sbi->s_mount_opt, DEBUG); + if (def_mount_opts & EXT4_DEFM_BSDGROUPS) + set_opt(sbi->s_mount_opt, GRPID); + if (def_mount_opts & EXT4_DEFM_UID16) + set_opt(sbi->s_mount_opt, NO_UID32); + if (def_mount_opts & EXT4_DEFM_XATTR_USER) + set_opt(sbi->s_mount_opt, XATTR_USER); + if (def_mount_opts & EXT4_DEFM_ACL) + set_opt(sbi->s_mount_opt, POSIX_ACL); + if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) + sbi->s_mount_opt |= EXT4_MOUNT_JOURNAL_DATA; + else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) + sbi->s_mount_opt |= EXT4_MOUNT_ORDERED_DATA; + else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK) + sbi->s_mount_opt |= EXT4_MOUNT_WRITEBACK_DATA; + + if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC) + set_opt(sbi->s_mount_opt, ERRORS_PANIC); + else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_RO) + set_opt(sbi->s_mount_opt, ERRORS_RO); + else + set_opt(sbi->s_mount_opt, ERRORS_CONT); + + sbi->s_resuid = le16_to_cpu(es->s_def_resuid); + sbi->s_resgid = le16_to_cpu(es->s_def_resgid); + + set_opt(sbi->s_mount_opt, RESERVATION); + + if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum, + NULL, 0)) + goto failed_mount; + + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0); + + if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV && + (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) || + EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) || + EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U))) + printk(KERN_WARNING + "EXT4-fs warning: feature flags set on rev 0 fs, " + "running e2fsck is recommended\n"); + /* + * Check feature flags regardless of the revision level, since we + * previously didn't change the revision level when setting the flags, + * so there is a chance incompat flags are set on a rev 0 filesystem. + */ + features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP); + if (features) { + printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of " + "unsupported optional features (%x).\n", + sb->s_id, le32_to_cpu(features)); + goto failed_mount; + } + features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP); + if (!(sb->s_flags & MS_RDONLY) && features) { + printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of " + "unsupported optional features (%x).\n", + sb->s_id, le32_to_cpu(features)); + goto failed_mount; + } + blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + + if (blocksize < EXT4_MIN_BLOCK_SIZE || + blocksize > EXT4_MAX_BLOCK_SIZE) { + printk(KERN_ERR + "EXT4-fs: Unsupported filesystem blocksize %d on %s.\n", + blocksize, sb->s_id); + goto failed_mount; + } + + hblock = bdev_hardsect_size(sb->s_bdev); + if (sb->s_blocksize != blocksize) { + /* + * Make sure the blocksize for the filesystem is larger + * than the hardware sectorsize for the machine. + */ + if (blocksize < hblock) { + printk(KERN_ERR "EXT4-fs: blocksize %d too small for " + "device blocksize %d.\n", blocksize, hblock); + goto failed_mount; + } + + brelse (bh); + sb_set_blocksize(sb, blocksize); + logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE; + offset = do_div(logical_sb_block, blocksize); + bh = sb_bread(sb, logical_sb_block); + if (!bh) { + printk(KERN_ERR + "EXT4-fs: Can't read superblock on 2nd try.\n"); + goto failed_mount; + } + es = (struct ext4_super_block *)(((char *)bh->b_data) + offset); + sbi->s_es = es; + if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { + printk (KERN_ERR + "EXT4-fs: Magic mismatch, very weird !\n"); + goto failed_mount; + } + } + + sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits); + + if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { + sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; + sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; + } else { + sbi->s_inode_size = le16_to_cpu(es->s_inode_size); + sbi->s_first_ino = le32_to_cpu(es->s_first_ino); + if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || + (sbi->s_inode_size & (sbi->s_inode_size - 1)) || + (sbi->s_inode_size > blocksize)) { + printk (KERN_ERR + "EXT4-fs: unsupported inode size: %d\n", + sbi->s_inode_size); + goto failed_mount; + } + } + sbi->s_frag_size = EXT4_MIN_FRAG_SIZE << + le32_to_cpu(es->s_log_frag_size); + if (blocksize != sbi->s_frag_size) { + printk(KERN_ERR + "EXT4-fs: fragsize %lu != blocksize %u (unsupported)\n", + sbi->s_frag_size, blocksize); + goto failed_mount; + } + sbi->s_desc_size = le16_to_cpu(es->s_desc_size); + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) { + if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || + sbi->s_desc_size > EXT4_MAX_DESC_SIZE || + sbi->s_desc_size & (sbi->s_desc_size - 1)) { + printk(KERN_ERR + "EXT4-fs: unsupported descriptor size %lu\n", + sbi->s_desc_size); + goto failed_mount; + } + } else + sbi->s_desc_size = EXT4_MIN_DESC_SIZE; + sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); + sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); + sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); + if (EXT4_INODE_SIZE(sb) == 0) + goto cantfind_ext4; + sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb); + if (sbi->s_inodes_per_block == 0) + goto cantfind_ext4; + sbi->s_itb_per_group = sbi->s_inodes_per_group / + sbi->s_inodes_per_block; + sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb); + sbi->s_sbh = bh; + sbi->s_mount_state = le16_to_cpu(es->s_state); + sbi->s_addr_per_block_bits = log2(EXT4_ADDR_PER_BLOCK(sb)); + sbi->s_desc_per_block_bits = log2(EXT4_DESC_PER_BLOCK(sb)); + for (i=0; i < 4; i++) + sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); + sbi->s_def_hash_version = es->s_def_hash_version; + + if (sbi->s_blocks_per_group > blocksize * 8) { + printk (KERN_ERR + "EXT4-fs: #blocks per group too big: %lu\n", + sbi->s_blocks_per_group); + goto failed_mount; + } + if (sbi->s_frags_per_group > blocksize * 8) { + printk (KERN_ERR + "EXT4-fs: #fragments per group too big: %lu\n", + sbi->s_frags_per_group); + goto failed_mount; + } + if (sbi->s_inodes_per_group > blocksize * 8) { + printk (KERN_ERR + "EXT4-fs: #inodes per group too big: %lu\n", + sbi->s_inodes_per_group); + goto failed_mount; + } + + if (ext4_blocks_count(es) > + (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { + printk(KERN_ERR "EXT4-fs: filesystem on %s:" + " too large to mount safely\n", sb->s_id); + if (sizeof(sector_t) < 8) + printk(KERN_WARNING "EXT4-fs: CONFIG_LBD not " + "enabled\n"); + goto failed_mount; + } + + if (EXT4_BLOCKS_PER_GROUP(sb) == 0) + goto cantfind_ext4; + blocks_count = (ext4_blocks_count(es) - + le32_to_cpu(es->s_first_data_block) + + EXT4_BLOCKS_PER_GROUP(sb) - 1); + do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); + sbi->s_groups_count = blocks_count; + db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / + EXT4_DESC_PER_BLOCK(sb); + sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *), + GFP_KERNEL); + if (sbi->s_group_desc == NULL) { + printk (KERN_ERR "EXT4-fs: not enough memory\n"); + goto failed_mount; + } + + bgl_lock_init(&sbi->s_blockgroup_lock); + + for (i = 0; i < db_count; i++) { + block = descriptor_loc(sb, logical_sb_block, i); + sbi->s_group_desc[i] = sb_bread(sb, block); + if (!sbi->s_group_desc[i]) { + printk (KERN_ERR "EXT4-fs: " + "can't read group descriptor %d\n", i); + db_count = i; + goto failed_mount2; + } + } + if (!ext4_check_descriptors (sb)) { + printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n"); + goto failed_mount2; + } + sbi->s_gdb_count = db_count; + get_random_bytes(&sbi->s_next_generation, sizeof(u32)); + spin_lock_init(&sbi->s_next_gen_lock); + + percpu_counter_init(&sbi->s_freeblocks_counter, + ext4_count_free_blocks(sb)); + percpu_counter_init(&sbi->s_freeinodes_counter, + ext4_count_free_inodes(sb)); + percpu_counter_init(&sbi->s_dirs_counter, + ext4_count_dirs(sb)); + + /* per fileystem reservation list head & lock */ + spin_lock_init(&sbi->s_rsv_window_lock); + sbi->s_rsv_window_root = RB_ROOT; + /* Add a single, static dummy reservation to the start of the + * reservation window list --- it gives us a placeholder for + * append-at-start-of-list which makes the allocation logic + * _much_ simpler. */ + sbi->s_rsv_window_head.rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED; + sbi->s_rsv_window_head.rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED; + sbi->s_rsv_window_head.rsv_alloc_hit = 0; + sbi->s_rsv_window_head.rsv_goal_size = 0; + ext4_rsv_window_add(sb, &sbi->s_rsv_window_head); + + /* + * set up enough so that it can read an inode + */ + sb->s_op = &ext4_sops; + sb->s_export_op = &ext4_export_ops; + sb->s_xattr = ext4_xattr_handlers; +#ifdef CONFIG_QUOTA + sb->s_qcop = &ext4_qctl_operations; + sb->dq_op = &ext4_quota_operations; +#endif + INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ + + sb->s_root = NULL; + + needs_recovery = (es->s_last_orphan != 0 || + EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_RECOVER)); + + /* + * The first inode we look at is the journal inode. Don't try + * root first: it may be modified in the journal! + */ + if (!test_opt(sb, NOLOAD) && + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) { + if (ext4_load_journal(sb, es, journal_devnum)) + goto failed_mount3; + } else if (journal_inum) { + if (ext4_create_journal(sb, es, journal_inum)) + goto failed_mount3; + } else { + if (!silent) + printk (KERN_ERR + "ext4: No journal on filesystem on %s\n", + sb->s_id); + goto failed_mount3; + } + + /* We have now updated the journal if required, so we can + * validate the data journaling mode. */ + switch (test_opt(sb, DATA_FLAGS)) { + case 0: + /* No mode set, assume a default based on the journal + * capabilities: ORDERED_DATA if the journal can + * cope, else JOURNAL_DATA + */ + if (jbd2_journal_check_available_features + (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) + set_opt(sbi->s_mount_opt, ORDERED_DATA); + else + set_opt(sbi->s_mount_opt, JOURNAL_DATA); + break; + + case EXT4_MOUNT_ORDERED_DATA: + case EXT4_MOUNT_WRITEBACK_DATA: + if (!jbd2_journal_check_available_features + (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { + printk(KERN_ERR "EXT4-fs: Journal does not support " + "requested data journaling mode\n"); + goto failed_mount4; + } + default: + break; + } + + if (test_opt(sb, NOBH)) { + if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) { + printk(KERN_WARNING "EXT4-fs: Ignoring nobh option - " + "its supported only with writeback mode\n"); + clear_opt(sbi->s_mount_opt, NOBH); + } + } + /* + * The jbd2_journal_load will have done any necessary log recovery, + * so we can safely mount the rest of the filesystem now. + */ + + root = iget(sb, EXT4_ROOT_INO); + sb->s_root = d_alloc_root(root); + if (!sb->s_root) { + printk(KERN_ERR "EXT4-fs: get root inode failed\n"); + iput(root); + goto failed_mount4; + } + if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { + dput(sb->s_root); + sb->s_root = NULL; + printk(KERN_ERR "EXT4-fs: corrupt root inode, run e2fsck\n"); + goto failed_mount4; + } + + ext4_setup_super (sb, es, sb->s_flags & MS_RDONLY); + /* + * akpm: core read_super() calls in here with the superblock locked. + * That deadlocks, because orphan cleanup needs to lock the superblock + * in numerous places. Here we just pop the lock - it's relatively + * harmless, because we are now ready to accept write_super() requests, + * and aviro says that's the only reason for hanging onto the + * superblock lock. + */ + EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; + ext4_orphan_cleanup(sb, es); + EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; + if (needs_recovery) + printk (KERN_INFO "EXT4-fs: recovery complete.\n"); + ext4_mark_recovery_complete(sb, es); + printk (KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n", + test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal": + test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered": + "writeback"); + + ext4_ext_init(sb); + + lock_kernel(); + return 0; + +cantfind_ext4: + if (!silent) + printk(KERN_ERR "VFS: Can't find ext4 filesystem on dev %s.\n", + sb->s_id); + goto failed_mount; + +failed_mount4: + jbd2_journal_destroy(sbi->s_journal); +failed_mount3: + percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeinodes_counter); + percpu_counter_destroy(&sbi->s_dirs_counter); +failed_mount2: + for (i = 0; i < db_count; i++) + brelse(sbi->s_group_desc[i]); + kfree(sbi->s_group_desc); +failed_mount: +#ifdef CONFIG_QUOTA + for (i = 0; i < MAXQUOTAS; i++) + kfree(sbi->s_qf_names[i]); +#endif + ext4_blkdev_remove(sbi); + brelse(bh); +out_fail: + sb->s_fs_info = NULL; + kfree(sbi); + lock_kernel(); + return -EINVAL; +} + +/* + * Setup any per-fs journal parameters now. We'll do this both on + * initial mount, once the journal has been initialised but before we've + * done any recovery; and again on any subsequent remount. + */ +static void ext4_init_journal_params(struct super_block *sb, journal_t *journal) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (sbi->s_commit_interval) + journal->j_commit_interval = sbi->s_commit_interval; + /* We could also set up an ext4-specific default for the commit + * interval here, but for now we'll just fall back to the jbd + * default. */ + + spin_lock(&journal->j_state_lock); + if (test_opt(sb, BARRIER)) + journal->j_flags |= JBD2_BARRIER; + else + journal->j_flags &= ~JBD2_BARRIER; + spin_unlock(&journal->j_state_lock); +} + +static journal_t *ext4_get_journal(struct super_block *sb, + unsigned int journal_inum) +{ + struct inode *journal_inode; + journal_t *journal; + + /* First, test for the existence of a valid inode on disk. Bad + * things happen if we iget() an unused inode, as the subsequent + * iput() will try to delete it. */ + + journal_inode = iget(sb, journal_inum); + if (!journal_inode) { + printk(KERN_ERR "EXT4-fs: no journal found.\n"); + return NULL; + } + if (!journal_inode->i_nlink) { + make_bad_inode(journal_inode); + iput(journal_inode); + printk(KERN_ERR "EXT4-fs: journal inode is deleted.\n"); + return NULL; + } + + jbd_debug(2, "Journal inode found at %p: %Ld bytes\n", + journal_inode, journal_inode->i_size); + if (is_bad_inode(journal_inode) || !S_ISREG(journal_inode->i_mode)) { + printk(KERN_ERR "EXT4-fs: invalid journal inode.\n"); + iput(journal_inode); + return NULL; + } + + journal = jbd2_journal_init_inode(journal_inode); + if (!journal) { + printk(KERN_ERR "EXT4-fs: Could not load journal inode\n"); + iput(journal_inode); + return NULL; + } + journal->j_private = sb; + ext4_init_journal_params(sb, journal); + return journal; +} + +static journal_t *ext4_get_dev_journal(struct super_block *sb, + dev_t j_dev) +{ + struct buffer_head * bh; + journal_t *journal; + ext4_fsblk_t start; + ext4_fsblk_t len; + int hblock, blocksize; + ext4_fsblk_t sb_block; + unsigned long offset; + struct ext4_super_block * es; + struct block_device *bdev; + + bdev = ext4_blkdev_get(j_dev); + if (bdev == NULL) + return NULL; + + if (bd_claim(bdev, sb)) { + printk(KERN_ERR + "EXT4: failed to claim external journal device.\n"); + blkdev_put(bdev); + return NULL; + } + + blocksize = sb->s_blocksize; + hblock = bdev_hardsect_size(bdev); + if (blocksize < hblock) { + printk(KERN_ERR + "EXT4-fs: blocksize too small for journal device.\n"); + goto out_bdev; + } + + sb_block = EXT4_MIN_BLOCK_SIZE / blocksize; + offset = EXT4_MIN_BLOCK_SIZE % blocksize; + set_blocksize(bdev, blocksize); + if (!(bh = __bread(bdev, sb_block, blocksize))) { + printk(KERN_ERR "EXT4-fs: couldn't read superblock of " + "external journal\n"); + goto out_bdev; + } + + es = (struct ext4_super_block *) (((char *)bh->b_data) + offset); + if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || + !(le32_to_cpu(es->s_feature_incompat) & + EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { + printk(KERN_ERR "EXT4-fs: external journal has " + "bad superblock\n"); + brelse(bh); + goto out_bdev; + } + + if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { + printk(KERN_ERR "EXT4-fs: journal UUID does not match\n"); + brelse(bh); + goto out_bdev; + } + + len = ext4_blocks_count(es); + start = sb_block + 1; + brelse(bh); /* we're done with the superblock */ + + journal = jbd2_journal_init_dev(bdev, sb->s_bdev, + start, len, blocksize); + if (!journal) { + printk(KERN_ERR "EXT4-fs: failed to create device journal\n"); + goto out_bdev; + } + journal->j_private = sb; + ll_rw_block(READ, 1, &journal->j_sb_buffer); + wait_on_buffer(journal->j_sb_buffer); + if (!buffer_uptodate(journal->j_sb_buffer)) { + printk(KERN_ERR "EXT4-fs: I/O error on journal device\n"); + goto out_journal; + } + if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { + printk(KERN_ERR "EXT4-fs: External journal has more than one " + "user (unsupported) - %d\n", + be32_to_cpu(journal->j_superblock->s_nr_users)); + goto out_journal; + } + EXT4_SB(sb)->journal_bdev = bdev; + ext4_init_journal_params(sb, journal); + return journal; +out_journal: + jbd2_journal_destroy(journal); +out_bdev: + ext4_blkdev_put(bdev); + return NULL; +} + +static int ext4_load_journal(struct super_block *sb, + struct ext4_super_block *es, + unsigned long journal_devnum) +{ + journal_t *journal; + unsigned int journal_inum = le32_to_cpu(es->s_journal_inum); + dev_t journal_dev; + int err = 0; + int really_read_only; + + if (journal_devnum && + journal_devnum != le32_to_cpu(es->s_journal_dev)) { + printk(KERN_INFO "EXT4-fs: external journal device major/minor " + "numbers have changed\n"); + journal_dev = new_decode_dev(journal_devnum); + } else + journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); + + really_read_only = bdev_read_only(sb->s_bdev); + + /* + * Are we loading a blank journal or performing recovery after a + * crash? For recovery, we need to check in advance whether we + * can get read-write access to the device. + */ + + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) { + if (sb->s_flags & MS_RDONLY) { + printk(KERN_INFO "EXT4-fs: INFO: recovery " + "required on readonly filesystem.\n"); + if (really_read_only) { + printk(KERN_ERR "EXT4-fs: write access " + "unavailable, cannot proceed.\n"); + return -EROFS; + } + printk (KERN_INFO "EXT4-fs: write access will " + "be enabled during recovery.\n"); + } + } + + if (journal_inum && journal_dev) { + printk(KERN_ERR "EXT4-fs: filesystem has both journal " + "and inode journals!\n"); + return -EINVAL; + } + + if (journal_inum) { + if (!(journal = ext4_get_journal(sb, journal_inum))) + return -EINVAL; + } else { + if (!(journal = ext4_get_dev_journal(sb, journal_dev))) + return -EINVAL; + } + + if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) { + err = jbd2_journal_update_format(journal); + if (err) { + printk(KERN_ERR "EXT4-fs: error updating journal.\n"); + jbd2_journal_destroy(journal); + return err; + } + } + + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) + err = jbd2_journal_wipe(journal, !really_read_only); + if (!err) + err = jbd2_journal_load(journal); + + if (err) { + printk(KERN_ERR "EXT4-fs: error loading journal.\n"); + jbd2_journal_destroy(journal); + return err; + } + + EXT4_SB(sb)->s_journal = journal; + ext4_clear_journal_err(sb, es); + + if (journal_devnum && + journal_devnum != le32_to_cpu(es->s_journal_dev)) { + es->s_journal_dev = cpu_to_le32(journal_devnum); + sb->s_dirt = 1; + + /* Make sure we flush the recovery flag to disk. */ + ext4_commit_super(sb, es, 1); + } + + return 0; +} + +static int ext4_create_journal(struct super_block * sb, + struct ext4_super_block * es, + unsigned int journal_inum) +{ + journal_t *journal; + + if (sb->s_flags & MS_RDONLY) { + printk(KERN_ERR "EXT4-fs: readonly filesystem when trying to " + "create journal.\n"); + return -EROFS; + } + + if (!(journal = ext4_get_journal(sb, journal_inum))) + return -EINVAL; + + printk(KERN_INFO "EXT4-fs: creating new journal on inode %u\n", + journal_inum); + + if (jbd2_journal_create(journal)) { + printk(KERN_ERR "EXT4-fs: error creating journal.\n"); + jbd2_journal_destroy(journal); + return -EIO; + } + + EXT4_SB(sb)->s_journal = journal; + + ext4_update_dynamic_rev(sb); + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL); + + es->s_journal_inum = cpu_to_le32(journal_inum); + sb->s_dirt = 1; + + /* Make sure we flush the recovery flag to disk. */ + ext4_commit_super(sb, es, 1); + + return 0; +} + +static void ext4_commit_super (struct super_block * sb, + struct ext4_super_block * es, + int sync) +{ + struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; + + if (!sbh) + return; + es->s_wtime = cpu_to_le32(get_seconds()); + ext4_free_blocks_count_set(es, ext4_count_free_blocks(sb)); + es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb)); + BUFFER_TRACE(sbh, "marking dirty"); + mark_buffer_dirty(sbh); + if (sync) + sync_dirty_buffer(sbh); +} + + +/* + * Have we just finished recovery? If so, and if we are mounting (or + * remounting) the filesystem readonly, then we will end up with a + * consistent fs on disk. Record that fact. + */ +static void ext4_mark_recovery_complete(struct super_block * sb, + struct ext4_super_block * es) +{ + journal_t *journal = EXT4_SB(sb)->s_journal; + + jbd2_journal_lock_updates(journal); + jbd2_journal_flush(journal); + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) && + sb->s_flags & MS_RDONLY) { + EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + sb->s_dirt = 0; + ext4_commit_super(sb, es, 1); + } + jbd2_journal_unlock_updates(journal); +} + +/* + * If we are mounting (or read-write remounting) a filesystem whose journal + * has recorded an error from a previous lifetime, move that error to the + * main filesystem now. + */ +static void ext4_clear_journal_err(struct super_block * sb, + struct ext4_super_block * es) +{ + journal_t *journal; + int j_errno; + const char *errstr; + + journal = EXT4_SB(sb)->s_journal; + + /* + * Now check for any error status which may have been recorded in the + * journal by a prior ext4_error() or ext4_abort() + */ + + j_errno = jbd2_journal_errno(journal); + if (j_errno) { + char nbuf[16]; + + errstr = ext4_decode_error(sb, j_errno, nbuf); + ext4_warning(sb, __FUNCTION__, "Filesystem error recorded " + "from previous mount: %s", errstr); + ext4_warning(sb, __FUNCTION__, "Marking fs in need of " + "filesystem check."); + + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + es->s_state |= cpu_to_le16(EXT4_ERROR_FS); + ext4_commit_super (sb, es, 1); + + jbd2_journal_clear_err(journal); + } +} + +/* + * Force the running and committing transactions to commit, + * and wait on the commit. + */ +int ext4_force_commit(struct super_block *sb) +{ + journal_t *journal; + int ret; + + if (sb->s_flags & MS_RDONLY) + return 0; + + journal = EXT4_SB(sb)->s_journal; + sb->s_dirt = 0; + ret = ext4_journal_force_commit(journal); + return ret; +} + +/* + * Ext4 always journals updates to the superblock itself, so we don't + * have to propagate any other updates to the superblock on disk at this + * point. Just start an async writeback to get the buffers on their way + * to the disk. + * + * This implicitly triggers the writebehind on sync(). + */ + +static void ext4_write_super (struct super_block * sb) +{ + if (mutex_trylock(&sb->s_lock) != 0) + BUG(); + sb->s_dirt = 0; +} + +static int ext4_sync_fs(struct super_block *sb, int wait) +{ + tid_t target; + + sb->s_dirt = 0; + if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) { + if (wait) + jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target); + } + return 0; +} + +/* + * LVM calls this function before a (read-only) snapshot is created. This + * gives us a chance to flush the journal completely and mark the fs clean. + */ +static void ext4_write_super_lockfs(struct super_block *sb) +{ + sb->s_dirt = 0; + + if (!(sb->s_flags & MS_RDONLY)) { + journal_t *journal = EXT4_SB(sb)->s_journal; + + /* Now we set up the journal barrier. */ + jbd2_journal_lock_updates(journal); + jbd2_journal_flush(journal); + + /* Journal blocked and flushed, clear needs_recovery flag. */ + EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); + } +} + +/* + * Called by LVM after the snapshot is done. We need to reset the RECOVER + * flag here, even though the filesystem is not technically dirty yet. + */ +static void ext4_unlockfs(struct super_block *sb) +{ + if (!(sb->s_flags & MS_RDONLY)) { + lock_super(sb); + /* Reser the needs_recovery flag before the fs is unlocked. */ + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); + ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1); + unlock_super(sb); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + } +} + +static int ext4_remount (struct super_block * sb, int * flags, char * data) +{ + struct ext4_super_block * es; + struct ext4_sb_info *sbi = EXT4_SB(sb); + ext4_fsblk_t n_blocks_count = 0; + unsigned long old_sb_flags; + struct ext4_mount_options old_opts; + int err; +#ifdef CONFIG_QUOTA + int i; +#endif + + /* Store the original options */ + old_sb_flags = sb->s_flags; + old_opts.s_mount_opt = sbi->s_mount_opt; + old_opts.s_resuid = sbi->s_resuid; + old_opts.s_resgid = sbi->s_resgid; + old_opts.s_commit_interval = sbi->s_commit_interval; +#ifdef CONFIG_QUOTA + old_opts.s_jquota_fmt = sbi->s_jquota_fmt; + for (i = 0; i < MAXQUOTAS; i++) + old_opts.s_qf_names[i] = sbi->s_qf_names[i]; +#endif + + /* + * Allow the "check" option to be passed as a remount option. + */ + if (!parse_options(data, sb, NULL, NULL, &n_blocks_count, 1)) { + err = -EINVAL; + goto restore_opts; + } + + if (sbi->s_mount_opt & EXT4_MOUNT_ABORT) + ext4_abort(sb, __FUNCTION__, "Abort forced by user"); + + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0); + + es = sbi->s_es; + + ext4_init_journal_params(sb, sbi->s_journal); + + if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) || + n_blocks_count > ext4_blocks_count(es)) { + if (sbi->s_mount_opt & EXT4_MOUNT_ABORT) { + err = -EROFS; + goto restore_opts; + } + + if (*flags & MS_RDONLY) { + /* + * First of all, the unconditional stuff we have to do + * to disable replay of the journal when we next remount + */ + sb->s_flags |= MS_RDONLY; + + /* + * OK, test if we are remounting a valid rw partition + * readonly, and if so set the rdonly flag and then + * mark the partition as valid again. + */ + if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) && + (sbi->s_mount_state & EXT4_VALID_FS)) + es->s_state = cpu_to_le16(sbi->s_mount_state); + + ext4_mark_recovery_complete(sb, es); + } else { + __le32 ret; + if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb, + ~EXT4_FEATURE_RO_COMPAT_SUPP))) { + printk(KERN_WARNING "EXT4-fs: %s: couldn't " + "remount RDWR because of unsupported " + "optional features (%x).\n", + sb->s_id, le32_to_cpu(ret)); + err = -EROFS; + goto restore_opts; + } + /* + * Mounting a RDONLY partition read-write, so reread + * and store the current valid flag. (It may have + * been changed by e2fsck since we originally mounted + * the partition.) + */ + ext4_clear_journal_err(sb, es); + sbi->s_mount_state = le16_to_cpu(es->s_state); + if ((err = ext4_group_extend(sb, es, n_blocks_count))) + goto restore_opts; + if (!ext4_setup_super (sb, es, 0)) + sb->s_flags &= ~MS_RDONLY; + } + } +#ifdef CONFIG_QUOTA + /* Release old quota file names */ + for (i = 0; i < MAXQUOTAS; i++) + if (old_opts.s_qf_names[i] && + old_opts.s_qf_names[i] != sbi->s_qf_names[i]) + kfree(old_opts.s_qf_names[i]); +#endif + return 0; +restore_opts: + sb->s_flags = old_sb_flags; + sbi->s_mount_opt = old_opts.s_mount_opt; + sbi->s_resuid = old_opts.s_resuid; + sbi->s_resgid = old_opts.s_resgid; + sbi->s_commit_interval = old_opts.s_commit_interval; +#ifdef CONFIG_QUOTA + sbi->s_jquota_fmt = old_opts.s_jquota_fmt; + for (i = 0; i < MAXQUOTAS; i++) { + if (sbi->s_qf_names[i] && + old_opts.s_qf_names[i] != sbi->s_qf_names[i]) + kfree(sbi->s_qf_names[i]); + sbi->s_qf_names[i] = old_opts.s_qf_names[i]; + } +#endif + return err; +} + +static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf) +{ + struct super_block *sb = dentry->d_sb; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + ext4_fsblk_t overhead; + int i; + + if (test_opt (sb, MINIX_DF)) + overhead = 0; + else { + unsigned long ngroups; + ngroups = EXT4_SB(sb)->s_groups_count; + smp_rmb(); + + /* + * Compute the overhead (FS structures) + */ + + /* + * All of the blocks before first_data_block are + * overhead + */ + overhead = le32_to_cpu(es->s_first_data_block); + + /* + * Add the overhead attributed to the superblock and + * block group descriptors. If the sparse superblocks + * feature is turned on, then not all groups have this. + */ + for (i = 0; i < ngroups; i++) { + overhead += ext4_bg_has_super(sb, i) + + ext4_bg_num_gdb(sb, i); + cond_resched(); + } + + /* + * Every block group has an inode bitmap, a block + * bitmap, and an inode table. + */ + overhead += (ngroups * (2 + EXT4_SB(sb)->s_itb_per_group)); + } + + buf->f_type = EXT4_SUPER_MAGIC; + buf->f_bsize = sb->s_blocksize; + buf->f_blocks = ext4_blocks_count(es) - overhead; + buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter); + buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); + if (buf->f_bfree < ext4_r_blocks_count(es)) + buf->f_bavail = 0; + buf->f_files = le32_to_cpu(es->s_inodes_count); + buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter); + buf->f_namelen = EXT4_NAME_LEN; + return 0; +} + +/* Helper function for writing quotas on sync - we need to start transaction before quota file + * is locked for write. Otherwise the are possible deadlocks: + * Process 1 Process 2 + * ext4_create() quota_sync() + * jbd2_journal_start() write_dquot() + * DQUOT_INIT() down(dqio_mutex) + * down(dqio_mutex) jbd2_journal_start() + * + */ + +#ifdef CONFIG_QUOTA + +static inline struct inode *dquot_to_inode(struct dquot *dquot) +{ + return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type]; +} + +static int ext4_dquot_initialize(struct inode *inode, int type) +{ + handle_t *handle; + int ret, err; + + /* We may create quota structure so we need to reserve enough blocks */ + handle = ext4_journal_start(inode, 2*EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ret = dquot_initialize(inode, type); + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; +} + +static int ext4_dquot_drop(struct inode *inode) +{ + handle_t *handle; + int ret, err; + + /* We may delete quota structure so we need to reserve enough blocks */ + handle = ext4_journal_start(inode, 2*EXT4_QUOTA_DEL_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ret = dquot_drop(inode); + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; +} + +static int ext4_write_dquot(struct dquot *dquot) +{ + int ret, err; + handle_t *handle; + struct inode *inode; + + inode = dquot_to_inode(dquot); + handle = ext4_journal_start(inode, + EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ret = dquot_commit(dquot); + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; +} + +static int ext4_acquire_dquot(struct dquot *dquot) +{ + int ret, err; + handle_t *handle; + + handle = ext4_journal_start(dquot_to_inode(dquot), + EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ret = dquot_acquire(dquot); + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; +} + +static int ext4_release_dquot(struct dquot *dquot) +{ + int ret, err; + handle_t *handle; + + handle = ext4_journal_start(dquot_to_inode(dquot), + EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ret = dquot_release(dquot); + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; +} + +static int ext4_mark_dquot_dirty(struct dquot *dquot) +{ + /* Are we journalling quotas? */ + if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] || + EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) { + dquot_mark_dquot_dirty(dquot); + return ext4_write_dquot(dquot); + } else { + return dquot_mark_dquot_dirty(dquot); + } +} + +static int ext4_write_info(struct super_block *sb, int type) +{ + int ret, err; + handle_t *handle; + + /* Data block + inode block */ + handle = ext4_journal_start(sb->s_root->d_inode, 2); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ret = dquot_commit_info(sb, type); + err = ext4_journal_stop(handle); + if (!ret) + ret = err; + return ret; +} + +/* + * Turn on quotas during mount time - we need to find + * the quota file and such... + */ +static int ext4_quota_on_mount(struct super_block *sb, int type) +{ + return vfs_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type], + EXT4_SB(sb)->s_jquota_fmt, type); +} + +/* + * Standard function to be called on quota_on + */ +static int ext4_quota_on(struct super_block *sb, int type, int format_id, + char *path) +{ + int err; + struct nameidata nd; + + if (!test_opt(sb, QUOTA)) + return -EINVAL; + /* Not journalling quota? */ + if (!EXT4_SB(sb)->s_qf_names[USRQUOTA] && + !EXT4_SB(sb)->s_qf_names[GRPQUOTA]) + return vfs_quota_on(sb, type, format_id, path); + err = path_lookup(path, LOOKUP_FOLLOW, &nd); + if (err) + return err; + /* Quotafile not on the same filesystem? */ + if (nd.mnt->mnt_sb != sb) { + path_release(&nd); + return -EXDEV; + } + /* Quotafile not of fs root? */ + if (nd.dentry->d_parent->d_inode != sb->s_root->d_inode) + printk(KERN_WARNING + "EXT4-fs: Quota file not on filesystem root. " + "Journalled quota will not work.\n"); + path_release(&nd); + return vfs_quota_on(sb, type, format_id, path); +} + +/* Read data from quotafile - avoid pagecache and such because we cannot afford + * acquiring the locks... As quota files are never truncated and quota code + * itself serializes the operations (and noone else should touch the files) + * we don't have to be afraid of races */ +static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, + size_t len, loff_t off) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + sector_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); + int err = 0; + int offset = off & (sb->s_blocksize - 1); + int tocopy; + size_t toread; + struct buffer_head *bh; + loff_t i_size = i_size_read(inode); + + if (off > i_size) + return 0; + if (off+len > i_size) + len = i_size-off; + toread = len; + while (toread > 0) { + tocopy = sb->s_blocksize - offset < toread ? + sb->s_blocksize - offset : toread; + bh = ext4_bread(NULL, inode, blk, 0, &err); + if (err) + return err; + if (!bh) /* A hole? */ + memset(data, 0, tocopy); + else + memcpy(data, bh->b_data+offset, tocopy); + brelse(bh); + offset = 0; + toread -= tocopy; + data += tocopy; + blk++; + } + return len; +} + +/* Write to quotafile (we know the transaction is already started and has + * enough credits) */ +static ssize_t ext4_quota_write(struct super_block *sb, int type, + const char *data, size_t len, loff_t off) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + sector_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); + int err = 0; + int offset = off & (sb->s_blocksize - 1); + int tocopy; + int journal_quota = EXT4_SB(sb)->s_qf_names[type] != NULL; + size_t towrite = len; + struct buffer_head *bh; + handle_t *handle = journal_current_handle(); + + mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); + while (towrite > 0) { + tocopy = sb->s_blocksize - offset < towrite ? + sb->s_blocksize - offset : towrite; + bh = ext4_bread(handle, inode, blk, 1, &err); + if (!bh) + goto out; + if (journal_quota) { + err = ext4_journal_get_write_access(handle, bh); + if (err) { + brelse(bh); + goto out; + } + } + lock_buffer(bh); + memcpy(bh->b_data+offset, data, tocopy); + flush_dcache_page(bh->b_page); + unlock_buffer(bh); + if (journal_quota) + err = ext4_journal_dirty_metadata(handle, bh); + else { + /* Always do at least ordered writes for quotas */ + err = ext4_journal_dirty_data(handle, bh); + mark_buffer_dirty(bh); + } + brelse(bh); + if (err) + goto out; + offset = 0; + towrite -= tocopy; + data += tocopy; + blk++; + } +out: + if (len == towrite) + return err; + if (inode->i_size < off+len-towrite) { + i_size_write(inode, off+len-towrite); + EXT4_I(inode)->i_disksize = inode->i_size; + } + inode->i_version++; + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + ext4_mark_inode_dirty(handle, inode); + mutex_unlock(&inode->i_mutex); + return len - towrite; +} + +#endif + +static int ext4_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, struct vfsmount *mnt) +{ + return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt); +} + +static struct file_system_type ext4dev_fs_type = { + .owner = THIS_MODULE, + .name = "ext4dev", + .get_sb = ext4_get_sb, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; + +static int __init init_ext4_fs(void) +{ + int err = init_ext4_xattr(); + if (err) + return err; + err = init_inodecache(); + if (err) + goto out1; + err = register_filesystem(&ext4dev_fs_type); + if (err) + goto out; + return 0; +out: + destroy_inodecache(); +out1: + exit_ext4_xattr(); + return err; +} + +static void __exit exit_ext4_fs(void) +{ + unregister_filesystem(&ext4dev_fs_type); + destroy_inodecache(); + exit_ext4_xattr(); +} + +MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); +MODULE_DESCRIPTION("Fourth Extended Filesystem with extents"); +MODULE_LICENSE("GPL"); +module_init(init_ext4_fs) +module_exit(exit_ext4_fs) diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c new file mode 100644 index 00000000000..fcf527286d7 --- /dev/null +++ b/fs/ext4/symlink.c @@ -0,0 +1,54 @@ +/* + * linux/fs/ext4/symlink.c + * + * Only fast symlinks left here - the rest is done by generic code. AV, 1999 + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/symlink.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * ext4 symlink handling code + */ + +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/namei.h> +#include "xattr.h" + +static void * ext4_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct ext4_inode_info *ei = EXT4_I(dentry->d_inode); + nd_set_link(nd, (char*)ei->i_data); + return NULL; +} + +struct inode_operations ext4_symlink_inode_operations = { + .readlink = generic_readlink, + .follow_link = page_follow_link_light, + .put_link = page_put_link, +#ifdef CONFIG_EXT4DEV_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext4_listxattr, + .removexattr = generic_removexattr, +#endif +}; + +struct inode_operations ext4_fast_symlink_inode_operations = { + .readlink = generic_readlink, + .follow_link = ext4_follow_link, +#ifdef CONFIG_EXT4DEV_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext4_listxattr, + .removexattr = generic_removexattr, +#endif +}; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c new file mode 100644 index 00000000000..63233cd946a --- /dev/null +++ b/fs/ext4/xattr.c @@ -0,0 +1,1317 @@ +/* + * linux/fs/ext4/xattr.c + * + * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> + * + * Fix by Harrison Xing <harrison@mountainviewdata.com>. + * Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>. + * Extended attributes for symlinks and special files added per + * suggestion of Luka Renko <luka.renko@hermes.si>. + * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>, + * Red Hat Inc. + * ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz + * and Andreas Gruenbacher <agruen@suse.de>. + */ + +/* + * Extended attributes are stored directly in inodes (on file systems with + * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl + * field contains the block number if an inode uses an additional block. All + * attributes must fit in the inode and one additional block. Blocks that + * contain the identical set of attributes may be shared among several inodes. + * Identical blocks are detected by keeping a cache of blocks that have + * recently been accessed. + * + * The attributes in inodes and on blocks have a different header; the entries + * are stored in the same format: + * + * +------------------+ + * | header | + * | entry 1 | | + * | entry 2 | | growing downwards + * | entry 3 | v + * | four null bytes | + * | . . . | + * | value 1 | ^ + * | value 3 | | growing upwards + * | value 2 | | + * +------------------+ + * + * The header is followed by multiple entry descriptors. In disk blocks, the + * entry descriptors are kept sorted. In inodes, they are unsorted. The + * attribute values are aligned to the end of the block in no specific order. + * + * Locking strategy + * ---------------- + * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem. + * EA blocks are only changed if they are exclusive to an inode, so + * holding xattr_sem also means that nothing but the EA block's reference + * count can change. Multiple writers to the same block are synchronized + * by the buffer lock. + */ + +#include <linux/init.h> +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/ext4_jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/mbcache.h> +#include <linux/quotaops.h> +#include <linux/rwsem.h> +#include "xattr.h" +#include "acl.h" + +#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data)) +#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr)) +#define BFIRST(bh) ENTRY(BHDR(bh)+1) +#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0) + +#define IHDR(inode, raw_inode) \ + ((struct ext4_xattr_ibody_header *) \ + ((void *)raw_inode + \ + EXT4_GOOD_OLD_INODE_SIZE + \ + EXT4_I(inode)->i_extra_isize)) +#define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1)) + +#ifdef EXT4_XATTR_DEBUG +# define ea_idebug(inode, f...) do { \ + printk(KERN_DEBUG "inode %s:%lu: ", \ + inode->i_sb->s_id, inode->i_ino); \ + printk(f); \ + printk("\n"); \ + } while (0) +# define ea_bdebug(bh, f...) do { \ + char b[BDEVNAME_SIZE]; \ + printk(KERN_DEBUG "block %s:%lu: ", \ + bdevname(bh->b_bdev, b), \ + (unsigned long) bh->b_blocknr); \ + printk(f); \ + printk("\n"); \ + } while (0) +#else +# define ea_idebug(f...) +# define ea_bdebug(f...) +#endif + +static void ext4_xattr_cache_insert(struct buffer_head *); +static struct buffer_head *ext4_xattr_cache_find(struct inode *, + struct ext4_xattr_header *, + struct mb_cache_entry **); +static void ext4_xattr_rehash(struct ext4_xattr_header *, + struct ext4_xattr_entry *); + +static struct mb_cache *ext4_xattr_cache; + +static struct xattr_handler *ext4_xattr_handler_map[] = { + [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler, +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &ext4_xattr_acl_access_handler, + [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext4_xattr_acl_default_handler, +#endif + [EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler, +#ifdef CONFIG_EXT4DEV_FS_SECURITY + [EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler, +#endif +}; + +struct xattr_handler *ext4_xattr_handlers[] = { + &ext4_xattr_user_handler, + &ext4_xattr_trusted_handler, +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + &ext4_xattr_acl_access_handler, + &ext4_xattr_acl_default_handler, +#endif +#ifdef CONFIG_EXT4DEV_FS_SECURITY + &ext4_xattr_security_handler, +#endif + NULL +}; + +static inline struct xattr_handler * +ext4_xattr_handler(int name_index) +{ + struct xattr_handler *handler = NULL; + + if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map)) + handler = ext4_xattr_handler_map[name_index]; + return handler; +} + +/* + * Inode operation listxattr() + * + * dentry->d_inode->i_mutex: don't care + */ +ssize_t +ext4_listxattr(struct dentry *dentry, char *buffer, size_t size) +{ + return ext4_xattr_list(dentry->d_inode, buffer, size); +} + +static int +ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end) +{ + while (!IS_LAST_ENTRY(entry)) { + struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry); + if ((void *)next >= end) + return -EIO; + entry = next; + } + return 0; +} + +static inline int +ext4_xattr_check_block(struct buffer_head *bh) +{ + int error; + + if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || + BHDR(bh)->h_blocks != cpu_to_le32(1)) + return -EIO; + error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size); + return error; +} + +static inline int +ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size) +{ + size_t value_size = le32_to_cpu(entry->e_value_size); + + if (entry->e_value_block != 0 || value_size > size || + le16_to_cpu(entry->e_value_offs) + value_size > size) + return -EIO; + return 0; +} + +static int +ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index, + const char *name, size_t size, int sorted) +{ + struct ext4_xattr_entry *entry; + size_t name_len; + int cmp = 1; + + if (name == NULL) + return -EINVAL; + name_len = strlen(name); + entry = *pentry; + for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { + cmp = name_index - entry->e_name_index; + if (!cmp) + cmp = name_len - entry->e_name_len; + if (!cmp) + cmp = memcmp(name, entry->e_name, name_len); + if (cmp <= 0 && (sorted || cmp == 0)) + break; + } + *pentry = entry; + if (!cmp && ext4_xattr_check_entry(entry, size)) + return -EIO; + return cmp ? -ENODATA : 0; +} + +static int +ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, + void *buffer, size_t buffer_size) +{ + struct buffer_head *bh = NULL; + struct ext4_xattr_entry *entry; + size_t size; + int error; + + ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", + name_index, name, buffer, (long)buffer_size); + + error = -ENODATA; + if (!EXT4_I(inode)->i_file_acl) + goto cleanup; + ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl); + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + if (!bh) + goto cleanup; + ea_bdebug(bh, "b_count=%d, refcount=%d", + atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); + if (ext4_xattr_check_block(bh)) { +bad_block: ext4_error(inode->i_sb, __FUNCTION__, + "inode %lu: bad block %llu", inode->i_ino, + EXT4_I(inode)->i_file_acl); + error = -EIO; + goto cleanup; + } + ext4_xattr_cache_insert(bh); + entry = BFIRST(bh); + error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1); + if (error == -EIO) + goto bad_block; + if (error) + goto cleanup; + size = le32_to_cpu(entry->e_value_size); + if (buffer) { + error = -ERANGE; + if (size > buffer_size) + goto cleanup; + memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs), + size); + } + error = size; + +cleanup: + brelse(bh); + return error; +} + +static int +ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, + void *buffer, size_t buffer_size) +{ + struct ext4_xattr_ibody_header *header; + struct ext4_xattr_entry *entry; + struct ext4_inode *raw_inode; + struct ext4_iloc iloc; + size_t size; + void *end; + int error; + + if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR)) + return -ENODATA; + error = ext4_get_inode_loc(inode, &iloc); + if (error) + return error; + raw_inode = ext4_raw_inode(&iloc); + header = IHDR(inode, raw_inode); + entry = IFIRST(header); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; + error = ext4_xattr_check_names(entry, end); + if (error) + goto cleanup; + error = ext4_xattr_find_entry(&entry, name_index, name, + end - (void *)entry, 0); + if (error) + goto cleanup; + size = le32_to_cpu(entry->e_value_size); + if (buffer) { + error = -ERANGE; + if (size > buffer_size) + goto cleanup; + memcpy(buffer, (void *)IFIRST(header) + + le16_to_cpu(entry->e_value_offs), size); + } + error = size; + +cleanup: + brelse(iloc.bh); + return error; +} + +/* + * ext4_xattr_get() + * + * Copy an extended attribute into the buffer + * provided, or compute the buffer size required. + * Buffer is NULL to compute the size of the buffer required. + * + * Returns a negative error number on failure, or the number of bytes + * used / required on success. + */ +int +ext4_xattr_get(struct inode *inode, int name_index, const char *name, + void *buffer, size_t buffer_size) +{ + int error; + + down_read(&EXT4_I(inode)->xattr_sem); + error = ext4_xattr_ibody_get(inode, name_index, name, buffer, + buffer_size); + if (error == -ENODATA) + error = ext4_xattr_block_get(inode, name_index, name, buffer, + buffer_size); + up_read(&EXT4_I(inode)->xattr_sem); + return error; +} + +static int +ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry, + char *buffer, size_t buffer_size) +{ + size_t rest = buffer_size; + + for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { + struct xattr_handler *handler = + ext4_xattr_handler(entry->e_name_index); + + if (handler) { + size_t size = handler->list(inode, buffer, rest, + entry->e_name, + entry->e_name_len); + if (buffer) { + if (size > rest) + return -ERANGE; + buffer += size; + } + rest -= size; + } + } + return buffer_size - rest; +} + +static int +ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size) +{ + struct buffer_head *bh = NULL; + int error; + + ea_idebug(inode, "buffer=%p, buffer_size=%ld", + buffer, (long)buffer_size); + + error = 0; + if (!EXT4_I(inode)->i_file_acl) + goto cleanup; + ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl); + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + error = -EIO; + if (!bh) + goto cleanup; + ea_bdebug(bh, "b_count=%d, refcount=%d", + atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); + if (ext4_xattr_check_block(bh)) { + ext4_error(inode->i_sb, __FUNCTION__, + "inode %lu: bad block %llu", inode->i_ino, + EXT4_I(inode)->i_file_acl); + error = -EIO; + goto cleanup; + } + ext4_xattr_cache_insert(bh); + error = ext4_xattr_list_entries(inode, BFIRST(bh), buffer, buffer_size); + +cleanup: + brelse(bh); + + return error; +} + +static int +ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size) +{ + struct ext4_xattr_ibody_header *header; + struct ext4_inode *raw_inode; + struct ext4_iloc iloc; + void *end; + int error; + + if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR)) + return 0; + error = ext4_get_inode_loc(inode, &iloc); + if (error) + return error; + raw_inode = ext4_raw_inode(&iloc); + header = IHDR(inode, raw_inode); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; + error = ext4_xattr_check_names(IFIRST(header), end); + if (error) + goto cleanup; + error = ext4_xattr_list_entries(inode, IFIRST(header), + buffer, buffer_size); + +cleanup: + brelse(iloc.bh); + return error; +} + +/* + * ext4_xattr_list() + * + * Copy a list of attribute names into the buffer + * provided, or compute the buffer size required. + * Buffer is NULL to compute the size of the buffer required. + * + * Returns a negative error number on failure, or the number of bytes + * used / required on success. + */ +int +ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size) +{ + int i_error, b_error; + + down_read(&EXT4_I(inode)->xattr_sem); + i_error = ext4_xattr_ibody_list(inode, buffer, buffer_size); + if (i_error < 0) { + b_error = 0; + } else { + if (buffer) { + buffer += i_error; + buffer_size -= i_error; + } + b_error = ext4_xattr_block_list(inode, buffer, buffer_size); + if (b_error < 0) + i_error = 0; + } + up_read(&EXT4_I(inode)->xattr_sem); + return i_error + b_error; +} + +/* + * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is + * not set, set it. + */ +static void ext4_xattr_update_super_block(handle_t *handle, + struct super_block *sb) +{ + if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR)) + return; + + lock_super(sb); + if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) { + EXT4_SB(sb)->s_es->s_feature_compat |= + cpu_to_le32(EXT4_FEATURE_COMPAT_EXT_ATTR); + sb->s_dirt = 1; + ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh); + } + unlock_super(sb); +} + +/* + * Release the xattr block BH: If the reference count is > 1, decrement + * it; otherwise free the block. + */ +static void +ext4_xattr_release_block(handle_t *handle, struct inode *inode, + struct buffer_head *bh) +{ + struct mb_cache_entry *ce = NULL; + + ce = mb_cache_entry_get(ext4_xattr_cache, bh->b_bdev, bh->b_blocknr); + if (BHDR(bh)->h_refcount == cpu_to_le32(1)) { + ea_bdebug(bh, "refcount now=0; freeing"); + if (ce) + mb_cache_entry_free(ce); + ext4_free_blocks(handle, inode, bh->b_blocknr, 1); + get_bh(bh); + ext4_forget(handle, 1, inode, bh, bh->b_blocknr); + } else { + if (ext4_journal_get_write_access(handle, bh) == 0) { + lock_buffer(bh); + BHDR(bh)->h_refcount = cpu_to_le32( + le32_to_cpu(BHDR(bh)->h_refcount) - 1); + ext4_journal_dirty_metadata(handle, bh); + if (IS_SYNC(inode)) + handle->h_sync = 1; + DQUOT_FREE_BLOCK(inode, 1); + unlock_buffer(bh); + ea_bdebug(bh, "refcount now=%d; releasing", + le32_to_cpu(BHDR(bh)->h_refcount)); + } + if (ce) + mb_cache_entry_release(ce); + } +} + +struct ext4_xattr_info { + int name_index; + const char *name; + const void *value; + size_t value_len; +}; + +struct ext4_xattr_search { + struct ext4_xattr_entry *first; + void *base; + void *end; + struct ext4_xattr_entry *here; + int not_found; +}; + +static int +ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) +{ + struct ext4_xattr_entry *last; + size_t free, min_offs = s->end - s->base, name_len = strlen(i->name); + + /* Compute min_offs and last. */ + last = s->first; + for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { + if (!last->e_value_block && last->e_value_size) { + size_t offs = le16_to_cpu(last->e_value_offs); + if (offs < min_offs) + min_offs = offs; + } + } + free = min_offs - ((void *)last - s->base) - sizeof(__u32); + if (!s->not_found) { + if (!s->here->e_value_block && s->here->e_value_size) { + size_t size = le32_to_cpu(s->here->e_value_size); + free += EXT4_XATTR_SIZE(size); + } + free += EXT4_XATTR_LEN(name_len); + } + if (i->value) { + if (free < EXT4_XATTR_SIZE(i->value_len) || + free < EXT4_XATTR_LEN(name_len) + + EXT4_XATTR_SIZE(i->value_len)) + return -ENOSPC; + } + + if (i->value && s->not_found) { + /* Insert the new name. */ + size_t size = EXT4_XATTR_LEN(name_len); + size_t rest = (void *)last - (void *)s->here + sizeof(__u32); + memmove((void *)s->here + size, s->here, rest); + memset(s->here, 0, size); + s->here->e_name_index = i->name_index; + s->here->e_name_len = name_len; + memcpy(s->here->e_name, i->name, name_len); + } else { + if (!s->here->e_value_block && s->here->e_value_size) { + void *first_val = s->base + min_offs; + size_t offs = le16_to_cpu(s->here->e_value_offs); + void *val = s->base + offs; + size_t size = EXT4_XATTR_SIZE( + le32_to_cpu(s->here->e_value_size)); + + if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) { + /* The old and the new value have the same + size. Just replace. */ + s->here->e_value_size = + cpu_to_le32(i->value_len); + memset(val + size - EXT4_XATTR_PAD, 0, + EXT4_XATTR_PAD); /* Clear pad bytes. */ + memcpy(val, i->value, i->value_len); + return 0; + } + + /* Remove the old value. */ + memmove(first_val + size, first_val, val - first_val); + memset(first_val, 0, size); + s->here->e_value_size = 0; + s->here->e_value_offs = 0; + min_offs += size; + + /* Adjust all value offsets. */ + last = s->first; + while (!IS_LAST_ENTRY(last)) { + size_t o = le16_to_cpu(last->e_value_offs); + if (!last->e_value_block && + last->e_value_size && o < offs) + last->e_value_offs = + cpu_to_le16(o + size); + last = EXT4_XATTR_NEXT(last); + } + } + if (!i->value) { + /* Remove the old name. */ + size_t size = EXT4_XATTR_LEN(name_len); + last = ENTRY((void *)last - size); + memmove(s->here, (void *)s->here + size, + (void *)last - (void *)s->here + sizeof(__u32)); + memset(last, 0, size); + } + } + + if (i->value) { + /* Insert the new value. */ + s->here->e_value_size = cpu_to_le32(i->value_len); + if (i->value_len) { + size_t size = EXT4_XATTR_SIZE(i->value_len); + void *val = s->base + min_offs - size; + s->here->e_value_offs = cpu_to_le16(min_offs - size); + memset(val + size - EXT4_XATTR_PAD, 0, + EXT4_XATTR_PAD); /* Clear the pad bytes. */ + memcpy(val, i->value, i->value_len); + } + } + return 0; +} + +struct ext4_xattr_block_find { + struct ext4_xattr_search s; + struct buffer_head *bh; +}; + +static int +ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i, + struct ext4_xattr_block_find *bs) +{ + struct super_block *sb = inode->i_sb; + int error; + + ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld", + i->name_index, i->name, i->value, (long)i->value_len); + + if (EXT4_I(inode)->i_file_acl) { + /* The inode already has an extended attribute block. */ + bs->bh = sb_bread(sb, EXT4_I(inode)->i_file_acl); + error = -EIO; + if (!bs->bh) + goto cleanup; + ea_bdebug(bs->bh, "b_count=%d, refcount=%d", + atomic_read(&(bs->bh->b_count)), + le32_to_cpu(BHDR(bs->bh)->h_refcount)); + if (ext4_xattr_check_block(bs->bh)) { + ext4_error(sb, __FUNCTION__, + "inode %lu: bad block %llu", inode->i_ino, + EXT4_I(inode)->i_file_acl); + error = -EIO; + goto cleanup; + } + /* Find the named attribute. */ + bs->s.base = BHDR(bs->bh); + bs->s.first = BFIRST(bs->bh); + bs->s.end = bs->bh->b_data + bs->bh->b_size; + bs->s.here = bs->s.first; + error = ext4_xattr_find_entry(&bs->s.here, i->name_index, + i->name, bs->bh->b_size, 1); + if (error && error != -ENODATA) + goto cleanup; + bs->s.not_found = error; + } + error = 0; + +cleanup: + return error; +} + +static int +ext4_xattr_block_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_block_find *bs) +{ + struct super_block *sb = inode->i_sb; + struct buffer_head *new_bh = NULL; + struct ext4_xattr_search *s = &bs->s; + struct mb_cache_entry *ce = NULL; + int error; + +#define header(x) ((struct ext4_xattr_header *)(x)) + + if (i->value && i->value_len > sb->s_blocksize) + return -ENOSPC; + if (s->base) { + ce = mb_cache_entry_get(ext4_xattr_cache, bs->bh->b_bdev, + bs->bh->b_blocknr); + if (header(s->base)->h_refcount == cpu_to_le32(1)) { + if (ce) { + mb_cache_entry_free(ce); + ce = NULL; + } + ea_bdebug(bs->bh, "modifying in-place"); + error = ext4_journal_get_write_access(handle, bs->bh); + if (error) + goto cleanup; + lock_buffer(bs->bh); + error = ext4_xattr_set_entry(i, s); + if (!error) { + if (!IS_LAST_ENTRY(s->first)) + ext4_xattr_rehash(header(s->base), + s->here); + ext4_xattr_cache_insert(bs->bh); + } + unlock_buffer(bs->bh); + if (error == -EIO) + goto bad_block; + if (!error) + error = ext4_journal_dirty_metadata(handle, + bs->bh); + if (error) + goto cleanup; + goto inserted; + } else { + int offset = (char *)s->here - bs->bh->b_data; + + if (ce) { + mb_cache_entry_release(ce); + ce = NULL; + } + ea_bdebug(bs->bh, "cloning"); + s->base = kmalloc(bs->bh->b_size, GFP_KERNEL); + error = -ENOMEM; + if (s->base == NULL) + goto cleanup; + memcpy(s->base, BHDR(bs->bh), bs->bh->b_size); + s->first = ENTRY(header(s->base)+1); + header(s->base)->h_refcount = cpu_to_le32(1); + s->here = ENTRY(s->base + offset); + s->end = s->base + bs->bh->b_size; + } + } else { + /* Allocate a buffer where we construct the new block. */ + s->base = kmalloc(sb->s_blocksize, GFP_KERNEL); + /* assert(header == s->base) */ + error = -ENOMEM; + if (s->base == NULL) + goto cleanup; + memset(s->base, 0, sb->s_blocksize); + header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); + header(s->base)->h_blocks = cpu_to_le32(1); + header(s->base)->h_refcount = cpu_to_le32(1); + s->first = ENTRY(header(s->base)+1); + s->here = ENTRY(header(s->base)+1); + s->end = s->base + sb->s_blocksize; + } + + error = ext4_xattr_set_entry(i, s); + if (error == -EIO) + goto bad_block; + if (error) + goto cleanup; + if (!IS_LAST_ENTRY(s->first)) + ext4_xattr_rehash(header(s->base), s->here); + +inserted: + if (!IS_LAST_ENTRY(s->first)) { + new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce); + if (new_bh) { + /* We found an identical block in the cache. */ + if (new_bh == bs->bh) + ea_bdebug(new_bh, "keeping"); + else { + /* The old block is released after updating + the inode. */ + error = -EDQUOT; + if (DQUOT_ALLOC_BLOCK(inode, 1)) + goto cleanup; + error = ext4_journal_get_write_access(handle, + new_bh); + if (error) + goto cleanup_dquot; + lock_buffer(new_bh); + BHDR(new_bh)->h_refcount = cpu_to_le32(1 + + le32_to_cpu(BHDR(new_bh)->h_refcount)); + ea_bdebug(new_bh, "reusing; refcount now=%d", + le32_to_cpu(BHDR(new_bh)->h_refcount)); + unlock_buffer(new_bh); + error = ext4_journal_dirty_metadata(handle, + new_bh); + if (error) + goto cleanup_dquot; + } + mb_cache_entry_release(ce); + ce = NULL; + } else if (bs->bh && s->base == bs->bh->b_data) { + /* We were modifying this block in-place. */ + ea_bdebug(bs->bh, "keeping this block"); + new_bh = bs->bh; + get_bh(new_bh); + } else { + /* We need to allocate a new block */ + ext4_fsblk_t goal = le32_to_cpu( + EXT4_SB(sb)->s_es->s_first_data_block) + + (ext4_fsblk_t)EXT4_I(inode)->i_block_group * + EXT4_BLOCKS_PER_GROUP(sb); + ext4_fsblk_t block = ext4_new_block(handle, inode, + goal, &error); + if (error) + goto cleanup; + ea_idebug(inode, "creating block %d", block); + + new_bh = sb_getblk(sb, block); + if (!new_bh) { +getblk_failed: + ext4_free_blocks(handle, inode, block, 1); + error = -EIO; + goto cleanup; + } + lock_buffer(new_bh); + error = ext4_journal_get_create_access(handle, new_bh); + if (error) { + unlock_buffer(new_bh); + goto getblk_failed; + } + memcpy(new_bh->b_data, s->base, new_bh->b_size); + set_buffer_uptodate(new_bh); + unlock_buffer(new_bh); + ext4_xattr_cache_insert(new_bh); + error = ext4_journal_dirty_metadata(handle, new_bh); + if (error) + goto cleanup; + } + } + + /* Update the inode. */ + EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; + + /* Drop the previous xattr block. */ + if (bs->bh && bs->bh != new_bh) + ext4_xattr_release_block(handle, inode, bs->bh); + error = 0; + +cleanup: + if (ce) + mb_cache_entry_release(ce); + brelse(new_bh); + if (!(bs->bh && s->base == bs->bh->b_data)) + kfree(s->base); + + return error; + +cleanup_dquot: + DQUOT_FREE_BLOCK(inode, 1); + goto cleanup; + +bad_block: + ext4_error(inode->i_sb, __FUNCTION__, + "inode %lu: bad block %llu", inode->i_ino, + EXT4_I(inode)->i_file_acl); + goto cleanup; + +#undef header +} + +struct ext4_xattr_ibody_find { + struct ext4_xattr_search s; + struct ext4_iloc iloc; +}; + +static int +ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is) +{ + struct ext4_xattr_ibody_header *header; + struct ext4_inode *raw_inode; + int error; + + if (EXT4_I(inode)->i_extra_isize == 0) + return 0; + raw_inode = ext4_raw_inode(&is->iloc); + header = IHDR(inode, raw_inode); + is->s.base = is->s.first = IFIRST(header); + is->s.here = is->s.first; + is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; + if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) { + error = ext4_xattr_check_names(IFIRST(header), is->s.end); + if (error) + return error; + /* Find the named attribute. */ + error = ext4_xattr_find_entry(&is->s.here, i->name_index, + i->name, is->s.end - + (void *)is->s.base, 0); + if (error && error != -ENODATA) + return error; + is->s.not_found = error; + } + return 0; +} + +static int +ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is) +{ + struct ext4_xattr_ibody_header *header; + struct ext4_xattr_search *s = &is->s; + int error; + + if (EXT4_I(inode)->i_extra_isize == 0) + return -ENOSPC; + error = ext4_xattr_set_entry(i, s); + if (error) + return error; + header = IHDR(inode, ext4_raw_inode(&is->iloc)); + if (!IS_LAST_ENTRY(s->first)) { + header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); + EXT4_I(inode)->i_state |= EXT4_STATE_XATTR; + } else { + header->h_magic = cpu_to_le32(0); + EXT4_I(inode)->i_state &= ~EXT4_STATE_XATTR; + } + return 0; +} + +/* + * ext4_xattr_set_handle() + * + * Create, replace or remove an extended attribute for this inode. Buffer + * is NULL to remove an existing extended attribute, and non-NULL to + * either replace an existing extended attribute, or create a new extended + * attribute. The flags XATTR_REPLACE and XATTR_CREATE + * specify that an extended attribute must exist and must not exist + * previous to the call, respectively. + * + * Returns 0, or a negative error number on failure. + */ +int +ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, + const char *name, const void *value, size_t value_len, + int flags) +{ + struct ext4_xattr_info i = { + .name_index = name_index, + .name = name, + .value = value, + .value_len = value_len, + + }; + struct ext4_xattr_ibody_find is = { + .s = { .not_found = -ENODATA, }, + }; + struct ext4_xattr_block_find bs = { + .s = { .not_found = -ENODATA, }, + }; + int error; + + if (!name) + return -EINVAL; + if (strlen(name) > 255) + return -ERANGE; + down_write(&EXT4_I(inode)->xattr_sem); + error = ext4_get_inode_loc(inode, &is.iloc); + if (error) + goto cleanup; + + if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) { + struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc); + memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); + EXT4_I(inode)->i_state &= ~EXT4_STATE_NEW; + } + + error = ext4_xattr_ibody_find(inode, &i, &is); + if (error) + goto cleanup; + if (is.s.not_found) + error = ext4_xattr_block_find(inode, &i, &bs); + if (error) + goto cleanup; + if (is.s.not_found && bs.s.not_found) { + error = -ENODATA; + if (flags & XATTR_REPLACE) + goto cleanup; + error = 0; + if (!value) + goto cleanup; + } else { + error = -EEXIST; + if (flags & XATTR_CREATE) + goto cleanup; + } + error = ext4_journal_get_write_access(handle, is.iloc.bh); + if (error) + goto cleanup; + if (!value) { + if (!is.s.not_found) + error = ext4_xattr_ibody_set(handle, inode, &i, &is); + else if (!bs.s.not_found) + error = ext4_xattr_block_set(handle, inode, &i, &bs); + } else { + error = ext4_xattr_ibody_set(handle, inode, &i, &is); + if (!error && !bs.s.not_found) { + i.value = NULL; + error = ext4_xattr_block_set(handle, inode, &i, &bs); + } else if (error == -ENOSPC) { + error = ext4_xattr_block_set(handle, inode, &i, &bs); + if (error) + goto cleanup; + if (!is.s.not_found) { + i.value = NULL; + error = ext4_xattr_ibody_set(handle, inode, &i, + &is); + } + } + } + if (!error) { + ext4_xattr_update_super_block(handle, inode->i_sb); + inode->i_ctime = CURRENT_TIME_SEC; + error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); + /* + * The bh is consumed by ext4_mark_iloc_dirty, even with + * error != 0. + */ + is.iloc.bh = NULL; + if (IS_SYNC(inode)) + handle->h_sync = 1; + } + +cleanup: + brelse(is.iloc.bh); + brelse(bs.bh); + up_write(&EXT4_I(inode)->xattr_sem); + return error; +} + +/* + * ext4_xattr_set() + * + * Like ext4_xattr_set_handle, but start from an inode. This extended + * attribute modification is a filesystem transaction by itself. + * + * Returns 0, or a negative error number on failure. + */ +int +ext4_xattr_set(struct inode *inode, int name_index, const char *name, + const void *value, size_t value_len, int flags) +{ + handle_t *handle; + int error, retries = 0; + +retry: + handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + } else { + int error2; + + error = ext4_xattr_set_handle(handle, inode, name_index, name, + value, value_len, flags); + error2 = ext4_journal_stop(handle); + if (error == -ENOSPC && + ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + if (error == 0) + error = error2; + } + + return error; +} + +/* + * ext4_xattr_delete_inode() + * + * Free extended attribute resources associated with this inode. This + * is called immediately before an inode is freed. We have exclusive + * access to the inode. + */ +void +ext4_xattr_delete_inode(handle_t *handle, struct inode *inode) +{ + struct buffer_head *bh = NULL; + + if (!EXT4_I(inode)->i_file_acl) + goto cleanup; + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + if (!bh) { + ext4_error(inode->i_sb, __FUNCTION__, + "inode %lu: block %llu read error", inode->i_ino, + EXT4_I(inode)->i_file_acl); + goto cleanup; + } + if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || + BHDR(bh)->h_blocks != cpu_to_le32(1)) { + ext4_error(inode->i_sb, __FUNCTION__, + "inode %lu: bad block %llu", inode->i_ino, + EXT4_I(inode)->i_file_acl); + goto cleanup; + } + ext4_xattr_release_block(handle, inode, bh); + EXT4_I(inode)->i_file_acl = 0; + +cleanup: + brelse(bh); +} + +/* + * ext4_xattr_put_super() + * + * This is called when a file system is unmounted. + */ +void +ext4_xattr_put_super(struct super_block *sb) +{ + mb_cache_shrink(sb->s_bdev); +} + +/* + * ext4_xattr_cache_insert() + * + * Create a new entry in the extended attribute cache, and insert + * it unless such an entry is already in the cache. + * + * Returns 0, or a negative error number on failure. + */ +static void +ext4_xattr_cache_insert(struct buffer_head *bh) +{ + __u32 hash = le32_to_cpu(BHDR(bh)->h_hash); + struct mb_cache_entry *ce; + int error; + + ce = mb_cache_entry_alloc(ext4_xattr_cache); + if (!ce) { + ea_bdebug(bh, "out of memory"); + return; + } + error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, &hash); + if (error) { + mb_cache_entry_free(ce); + if (error == -EBUSY) { + ea_bdebug(bh, "already in cache"); + error = 0; + } + } else { + ea_bdebug(bh, "inserting [%x]", (int)hash); + mb_cache_entry_release(ce); + } +} + +/* + * ext4_xattr_cmp() + * + * Compare two extended attribute blocks for equality. + * + * Returns 0 if the blocks are equal, 1 if they differ, and + * a negative error number on errors. + */ +static int +ext4_xattr_cmp(struct ext4_xattr_header *header1, + struct ext4_xattr_header *header2) +{ + struct ext4_xattr_entry *entry1, *entry2; + + entry1 = ENTRY(header1+1); + entry2 = ENTRY(header2+1); + while (!IS_LAST_ENTRY(entry1)) { + if (IS_LAST_ENTRY(entry2)) + return 1; + if (entry1->e_hash != entry2->e_hash || + entry1->e_name_index != entry2->e_name_index || + entry1->e_name_len != entry2->e_name_len || + entry1->e_value_size != entry2->e_value_size || + memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len)) + return 1; + if (entry1->e_value_block != 0 || entry2->e_value_block != 0) + return -EIO; + if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), + (char *)header2 + le16_to_cpu(entry2->e_value_offs), + le32_to_cpu(entry1->e_value_size))) + return 1; + + entry1 = EXT4_XATTR_NEXT(entry1); + entry2 = EXT4_XATTR_NEXT(entry2); + } + if (!IS_LAST_ENTRY(entry2)) + return 1; + return 0; +} + +/* + * ext4_xattr_cache_find() + * + * Find an identical extended attribute block. + * + * Returns a pointer to the block found, or NULL if such a block was + * not found or an error occurred. + */ +static struct buffer_head * +ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header, + struct mb_cache_entry **pce) +{ + __u32 hash = le32_to_cpu(header->h_hash); + struct mb_cache_entry *ce; + + if (!header->h_hash) + return NULL; /* never share */ + ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); +again: + ce = mb_cache_entry_find_first(ext4_xattr_cache, 0, + inode->i_sb->s_bdev, hash); + while (ce) { + struct buffer_head *bh; + + if (IS_ERR(ce)) { + if (PTR_ERR(ce) == -EAGAIN) + goto again; + break; + } + bh = sb_bread(inode->i_sb, ce->e_block); + if (!bh) { + ext4_error(inode->i_sb, __FUNCTION__, + "inode %lu: block %lu read error", + inode->i_ino, (unsigned long) ce->e_block); + } else if (le32_to_cpu(BHDR(bh)->h_refcount) >= + EXT4_XATTR_REFCOUNT_MAX) { + ea_idebug(inode, "block %lu refcount %d>=%d", + (unsigned long) ce->e_block, + le32_to_cpu(BHDR(bh)->h_refcount), + EXT4_XATTR_REFCOUNT_MAX); + } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) { + *pce = ce; + return bh; + } + brelse(bh); + ce = mb_cache_entry_find_next(ce, 0, inode->i_sb->s_bdev, hash); + } + return NULL; +} + +#define NAME_HASH_SHIFT 5 +#define VALUE_HASH_SHIFT 16 + +/* + * ext4_xattr_hash_entry() + * + * Compute the hash of an extended attribute. + */ +static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header, + struct ext4_xattr_entry *entry) +{ + __u32 hash = 0; + char *name = entry->e_name; + int n; + + for (n=0; n < entry->e_name_len; n++) { + hash = (hash << NAME_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ + *name++; + } + + if (entry->e_value_block == 0 && entry->e_value_size != 0) { + __le32 *value = (__le32 *)((char *)header + + le16_to_cpu(entry->e_value_offs)); + for (n = (le32_to_cpu(entry->e_value_size) + + EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) { + hash = (hash << VALUE_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ + le32_to_cpu(*value++); + } + } + entry->e_hash = cpu_to_le32(hash); +} + +#undef NAME_HASH_SHIFT +#undef VALUE_HASH_SHIFT + +#define BLOCK_HASH_SHIFT 16 + +/* + * ext4_xattr_rehash() + * + * Re-compute the extended attribute hash value after an entry has changed. + */ +static void ext4_xattr_rehash(struct ext4_xattr_header *header, + struct ext4_xattr_entry *entry) +{ + struct ext4_xattr_entry *here; + __u32 hash = 0; + + ext4_xattr_hash_entry(header, entry); + here = ENTRY(header+1); + while (!IS_LAST_ENTRY(here)) { + if (!here->e_hash) { + /* Block is not shared if an entry's hash value == 0 */ + hash = 0; + break; + } + hash = (hash << BLOCK_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^ + le32_to_cpu(here->e_hash); + here = EXT4_XATTR_NEXT(here); + } + header->h_hash = cpu_to_le32(hash); +} + +#undef BLOCK_HASH_SHIFT + +int __init +init_ext4_xattr(void) +{ + ext4_xattr_cache = mb_cache_create("ext4_xattr", NULL, + sizeof(struct mb_cache_entry) + + sizeof(((struct mb_cache_entry *) 0)->e_indexes[0]), 1, 6); + if (!ext4_xattr_cache) + return -ENOMEM; + return 0; +} + +void +exit_ext4_xattr(void) +{ + if (ext4_xattr_cache) + mb_cache_destroy(ext4_xattr_cache); + ext4_xattr_cache = NULL; +} diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h new file mode 100644 index 00000000000..79432b35398 --- /dev/null +++ b/fs/ext4/xattr.h @@ -0,0 +1,145 @@ +/* + File: fs/ext4/xattr.h + + On-disk format of extended attributes for the ext4 filesystem. + + (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> +*/ + +#include <linux/xattr.h> + +/* Magic value in attribute blocks */ +#define EXT4_XATTR_MAGIC 0xEA020000 + +/* Maximum number of references to one attribute block */ +#define EXT4_XATTR_REFCOUNT_MAX 1024 + +/* Name indexes */ +#define EXT4_XATTR_INDEX_USER 1 +#define EXT4_XATTR_INDEX_POSIX_ACL_ACCESS 2 +#define EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT 3 +#define EXT4_XATTR_INDEX_TRUSTED 4 +#define EXT4_XATTR_INDEX_LUSTRE 5 +#define EXT4_XATTR_INDEX_SECURITY 6 + +struct ext4_xattr_header { + __le32 h_magic; /* magic number for identification */ + __le32 h_refcount; /* reference count */ + __le32 h_blocks; /* number of disk blocks used */ + __le32 h_hash; /* hash value of all attributes */ + __u32 h_reserved[4]; /* zero right now */ +}; + +struct ext4_xattr_ibody_header { + __le32 h_magic; /* magic number for identification */ +}; + +struct ext4_xattr_entry { + __u8 e_name_len; /* length of name */ + __u8 e_name_index; /* attribute name index */ + __le16 e_value_offs; /* offset in disk block of value */ + __le32 e_value_block; /* disk block attribute is stored on (n/i) */ + __le32 e_value_size; /* size of attribute value */ + __le32 e_hash; /* hash value of name and value */ + char e_name[0]; /* attribute name */ +}; + +#define EXT4_XATTR_PAD_BITS 2 +#define EXT4_XATTR_PAD (1<<EXT4_XATTR_PAD_BITS) +#define EXT4_XATTR_ROUND (EXT4_XATTR_PAD-1) +#define EXT4_XATTR_LEN(name_len) \ + (((name_len) + EXT4_XATTR_ROUND + \ + sizeof(struct ext4_xattr_entry)) & ~EXT4_XATTR_ROUND) +#define EXT4_XATTR_NEXT(entry) \ + ( (struct ext4_xattr_entry *)( \ + (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)) ) +#define EXT4_XATTR_SIZE(size) \ + (((size) + EXT4_XATTR_ROUND) & ~EXT4_XATTR_ROUND) + +# ifdef CONFIG_EXT4DEV_FS_XATTR + +extern struct xattr_handler ext4_xattr_user_handler; +extern struct xattr_handler ext4_xattr_trusted_handler; +extern struct xattr_handler ext4_xattr_acl_access_handler; +extern struct xattr_handler ext4_xattr_acl_default_handler; +extern struct xattr_handler ext4_xattr_security_handler; + +extern ssize_t ext4_listxattr(struct dentry *, char *, size_t); + +extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t); +extern int ext4_xattr_list(struct inode *, char *, size_t); +extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_t, int); +extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int); + +extern void ext4_xattr_delete_inode(handle_t *, struct inode *); +extern void ext4_xattr_put_super(struct super_block *); + +extern int init_ext4_xattr(void); +extern void exit_ext4_xattr(void); + +extern struct xattr_handler *ext4_xattr_handlers[]; + +# else /* CONFIG_EXT4DEV_FS_XATTR */ + +static inline int +ext4_xattr_get(struct inode *inode, int name_index, const char *name, + void *buffer, size_t size, int flags) +{ + return -EOPNOTSUPP; +} + +static inline int +ext4_xattr_list(struct inode *inode, void *buffer, size_t size) +{ + return -EOPNOTSUPP; +} + +static inline int +ext4_xattr_set(struct inode *inode, int name_index, const char *name, + const void *value, size_t size, int flags) +{ + return -EOPNOTSUPP; +} + +static inline int +ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, + const char *name, const void *value, size_t size, int flags) +{ + return -EOPNOTSUPP; +} + +static inline void +ext4_xattr_delete_inode(handle_t *handle, struct inode *inode) +{ +} + +static inline void +ext4_xattr_put_super(struct super_block *sb) +{ +} + +static inline int +init_ext4_xattr(void) +{ + return 0; +} + +static inline void +exit_ext4_xattr(void) +{ +} + +#define ext4_xattr_handlers NULL + +# endif /* CONFIG_EXT4DEV_FS_XATTR */ + +#ifdef CONFIG_EXT4DEV_FS_SECURITY +extern int ext4_init_security(handle_t *handle, struct inode *inode, + struct inode *dir); +#else +static inline int ext4_init_security(handle_t *handle, struct inode *inode, + struct inode *dir) +{ + return 0; +} +#endif diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c new file mode 100644 index 00000000000..b6a6861951f --- /dev/null +++ b/fs/ext4/xattr_security.c @@ -0,0 +1,77 @@ +/* + * linux/fs/ext4/xattr_security.c + * Handler for storing security labels as extended attributes. + */ + +#include <linux/module.h> +#include <linux/string.h> +#include <linux/fs.h> +#include <linux/smp_lock.h> +#include <linux/ext4_jbd2.h> +#include <linux/ext4_fs.h> +#include <linux/security.h> +#include "xattr.h" + +static size_t +ext4_xattr_security_list(struct inode *inode, char *list, size_t list_size, + const char *name, size_t name_len) +{ + const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1; + const size_t total_len = prefix_len + name_len + 1; + + + if (list && total_len <= list_size) { + memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); + memcpy(list+prefix_len, name, name_len); + list[prefix_len + name_len] = '\0'; + } + return total_len; +} + +static int +ext4_xattr_security_get(struct inode *inode, const char *name, + void *buffer, size_t size) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY, name, + buffer, size); +} + +static int +ext4_xattr_security_set(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY, name, + value, size, flags); +} + +int +ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir) +{ + int err; + size_t len; + void *value; + char *name; + + err = security_inode_init_security(inode, dir, &name, &value, &len); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + err = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_SECURITY, + name, value, len, 0); + kfree(name); + kfree(value); + return err; +} + +struct xattr_handler ext4_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .list = ext4_xattr_security_list, + .get = ext4_xattr_security_get, + .set = ext4_xattr_security_set, +}; diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c new file mode 100644 index 00000000000..b76f2dbc82d --- /dev/null +++ b/fs/ext4/xattr_trusted.c @@ -0,0 +1,62 @@ +/* + * linux/fs/ext4/xattr_trusted.c + * Handler for trusted extended attributes. + * + * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org> + */ + +#include <linux/module.h> +#include <linux/string.h> +#include <linux/capability.h> +#include <linux/fs.h> +#include <linux/smp_lock.h> +#include <linux/ext4_jbd2.h> +#include <linux/ext4_fs.h> +#include "xattr.h" + +#define XATTR_TRUSTED_PREFIX "trusted." + +static size_t +ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size, + const char *name, size_t name_len) +{ + const size_t prefix_len = sizeof(XATTR_TRUSTED_PREFIX)-1; + const size_t total_len = prefix_len + name_len + 1; + + if (!capable(CAP_SYS_ADMIN)) + return 0; + + if (list && total_len <= list_size) { + memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); + memcpy(list+prefix_len, name, name_len); + list[prefix_len + name_len] = '\0'; + } + return total_len; +} + +static int +ext4_xattr_trusted_get(struct inode *inode, const char *name, + void *buffer, size_t size) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_TRUSTED, name, + buffer, size); +} + +static int +ext4_xattr_trusted_set(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return ext4_xattr_set(inode, EXT4_XATTR_INDEX_TRUSTED, name, + value, size, flags); +} + +struct xattr_handler ext4_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .list = ext4_xattr_trusted_list, + .get = ext4_xattr_trusted_get, + .set = ext4_xattr_trusted_set, +}; diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c new file mode 100644 index 00000000000..c53cded0761 --- /dev/null +++ b/fs/ext4/xattr_user.c @@ -0,0 +1,64 @@ +/* + * linux/fs/ext4/xattr_user.c + * Handler for extended user attributes. + * + * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org> + */ + +#include <linux/module.h> +#include <linux/string.h> +#include <linux/fs.h> +#include <linux/smp_lock.h> +#include <linux/ext4_jbd2.h> +#include <linux/ext4_fs.h> +#include "xattr.h" + +#define XATTR_USER_PREFIX "user." + +static size_t +ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size, + const char *name, size_t name_len) +{ + const size_t prefix_len = sizeof(XATTR_USER_PREFIX)-1; + const size_t total_len = prefix_len + name_len + 1; + + if (!test_opt(inode->i_sb, XATTR_USER)) + return 0; + + if (list && total_len <= list_size) { + memcpy(list, XATTR_USER_PREFIX, prefix_len); + memcpy(list+prefix_len, name, name_len); + list[prefix_len + name_len] = '\0'; + } + return total_len; +} + +static int +ext4_xattr_user_get(struct inode *inode, const char *name, + void *buffer, size_t size) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + if (!test_opt(inode->i_sb, XATTR_USER)) + return -EOPNOTSUPP; + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_USER, name, buffer, size); +} + +static int +ext4_xattr_user_set(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + if (!test_opt(inode->i_sb, XATTR_USER)) + return -EOPNOTSUPP; + return ext4_xattr_set(inode, EXT4_XATTR_INDEX_USER, name, + value, size, flags); +} + +struct xattr_handler ext4_xattr_user_handler = { + .prefix = XATTR_USER_PREFIX, + .list = ext4_xattr_user_list, + .get = ext4_xattr_user_get, + .set = ext4_xattr_user_set, +}; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 4613cb20217..78945b53b0f 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1472,7 +1472,7 @@ int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2) ret = writeback_inode(i1); if (!ret && i2) ret = writeback_inode(i2); - if (!ret && sb) { + if (!ret) { struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; ret = filemap_flush(mapping); } diff --git a/fs/gfs2/locking/dlm/mount.c b/fs/gfs2/locking/dlm/mount.c index 1f94dd35a94..cdd1694e889 100644 --- a/fs/gfs2/locking/dlm/mount.c +++ b/fs/gfs2/locking/dlm/mount.c @@ -45,7 +45,7 @@ static struct gdlm_ls *init_gdlm(lm_callback_t cb, struct gfs2_sbd *sdp, strncpy(buf, table_name, 256); buf[255] = '\0'; - p = strstr(buf, ":"); + p = strchr(buf, ':'); if (!p) { log_info("invalid table_name \"%s\"", table_name); kfree(ls); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 5e03b2f67b9..4ee3f006b86 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -293,7 +293,7 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff) if (h_vm_pgoff >= h_pgoff) v_offset = 0; - unmap_hugepage_range(vma, + __unmap_hugepage_range(vma, vma->vm_start + v_offset, vma->vm_end); } } diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index c518dd8fe60..b85c686b60d 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -725,6 +725,7 @@ journal_t * journal_init_dev(struct block_device *bdev, __FUNCTION__); kfree(journal); journal = NULL; + goto out; } journal->j_dev = bdev; journal->j_fs_dev = fs_dev; @@ -735,7 +736,7 @@ journal_t * journal_init_dev(struct block_device *bdev, J_ASSERT(bh != NULL); journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; - +out: return journal; } diff --git a/fs/jbd2/Makefile b/fs/jbd2/Makefile new file mode 100644 index 00000000000..802a3413872 --- /dev/null +++ b/fs/jbd2/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the linux journaling routines. +# + +obj-$(CONFIG_JBD2) += jbd2.o + +jbd2-objs := transaction.o commit.o recovery.o checkpoint.o revoke.o journal.o diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c new file mode 100644 index 00000000000..68039fa9a56 --- /dev/null +++ b/fs/jbd2/checkpoint.c @@ -0,0 +1,697 @@ +/* + * linux/fs/checkpoint.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 + * + * Copyright 1999 Red Hat Software --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Checkpoint routines for the generic filesystem journaling code. + * Part of the ext2fs journaling system. + * + * Checkpointing is the process of ensuring that a section of the log is + * committed fully to disk, so that that portion of the log can be + * reused. + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> + +/* + * Unlink a buffer from a transaction checkpoint list. + * + * Called with j_list_lock held. + */ +static inline void __buffer_unlink_first(struct journal_head *jh) +{ + transaction_t *transaction = jh->b_cp_transaction; + + jh->b_cpnext->b_cpprev = jh->b_cpprev; + jh->b_cpprev->b_cpnext = jh->b_cpnext; + if (transaction->t_checkpoint_list == jh) { + transaction->t_checkpoint_list = jh->b_cpnext; + if (transaction->t_checkpoint_list == jh) + transaction->t_checkpoint_list = NULL; + } +} + +/* + * Unlink a buffer from a transaction checkpoint(io) list. + * + * Called with j_list_lock held. + */ +static inline void __buffer_unlink(struct journal_head *jh) +{ + transaction_t *transaction = jh->b_cp_transaction; + + __buffer_unlink_first(jh); + if (transaction->t_checkpoint_io_list == jh) { + transaction->t_checkpoint_io_list = jh->b_cpnext; + if (transaction->t_checkpoint_io_list == jh) + transaction->t_checkpoint_io_list = NULL; + } +} + +/* + * Move a buffer from the checkpoint list to the checkpoint io list + * + * Called with j_list_lock held + */ +static inline void __buffer_relink_io(struct journal_head *jh) +{ + transaction_t *transaction = jh->b_cp_transaction; + + __buffer_unlink_first(jh); + + if (!transaction->t_checkpoint_io_list) { + jh->b_cpnext = jh->b_cpprev = jh; + } else { + jh->b_cpnext = transaction->t_checkpoint_io_list; + jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev; + jh->b_cpprev->b_cpnext = jh; + jh->b_cpnext->b_cpprev = jh; + } + transaction->t_checkpoint_io_list = jh; +} + +/* + * Try to release a checkpointed buffer from its transaction. + * Returns 1 if we released it and 2 if we also released the + * whole transaction. + * + * Requires j_list_lock + * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it + */ +static int __try_to_free_cp_buf(struct journal_head *jh) +{ + int ret = 0; + struct buffer_head *bh = jh2bh(jh); + + if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) { + JBUFFER_TRACE(jh, "remove from checkpoint list"); + ret = __jbd2_journal_remove_checkpoint(jh) + 1; + jbd_unlock_bh_state(bh); + jbd2_journal_remove_journal_head(bh); + BUFFER_TRACE(bh, "release"); + __brelse(bh); + } else { + jbd_unlock_bh_state(bh); + } + return ret; +} + +/* + * __jbd2_log_wait_for_space: wait until there is space in the journal. + * + * Called under j-state_lock *only*. It will be unlocked if we have to wait + * for a checkpoint to free up some space in the log. + */ +void __jbd2_log_wait_for_space(journal_t *journal) +{ + int nblocks; + assert_spin_locked(&journal->j_state_lock); + + nblocks = jbd_space_needed(journal); + while (__jbd2_log_space_left(journal) < nblocks) { + if (journal->j_flags & JBD2_ABORT) + return; + spin_unlock(&journal->j_state_lock); + mutex_lock(&journal->j_checkpoint_mutex); + + /* + * Test again, another process may have checkpointed while we + * were waiting for the checkpoint lock + */ + spin_lock(&journal->j_state_lock); + nblocks = jbd_space_needed(journal); + if (__jbd2_log_space_left(journal) < nblocks) { + spin_unlock(&journal->j_state_lock); + jbd2_log_do_checkpoint(journal); + spin_lock(&journal->j_state_lock); + } + mutex_unlock(&journal->j_checkpoint_mutex); + } +} + +/* + * We were unable to perform jbd_trylock_bh_state() inside j_list_lock. + * The caller must restart a list walk. Wait for someone else to run + * jbd_unlock_bh_state(). + */ +static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh) + __releases(journal->j_list_lock) +{ + get_bh(bh); + spin_unlock(&journal->j_list_lock); + jbd_lock_bh_state(bh); + jbd_unlock_bh_state(bh); + put_bh(bh); +} + +/* + * Clean up transaction's list of buffers submitted for io. + * We wait for any pending IO to complete and remove any clean + * buffers. Note that we take the buffers in the opposite ordering + * from the one in which they were submitted for IO. + * + * Called with j_list_lock held. + */ +static void __wait_cp_io(journal_t *journal, transaction_t *transaction) +{ + struct journal_head *jh; + struct buffer_head *bh; + tid_t this_tid; + int released = 0; + + this_tid = transaction->t_tid; +restart: + /* Did somebody clean up the transaction in the meanwhile? */ + if (journal->j_checkpoint_transactions != transaction || + transaction->t_tid != this_tid) + return; + while (!released && transaction->t_checkpoint_io_list) { + jh = transaction->t_checkpoint_io_list; + bh = jh2bh(jh); + if (!jbd_trylock_bh_state(bh)) { + jbd_sync_bh(journal, bh); + spin_lock(&journal->j_list_lock); + goto restart; + } + if (buffer_locked(bh)) { + atomic_inc(&bh->b_count); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + wait_on_buffer(bh); + /* the journal_head may have gone by now */ + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + spin_lock(&journal->j_list_lock); + goto restart; + } + /* + * Now in whatever state the buffer currently is, we know that + * it has been written out and so we can drop it from the list + */ + released = __jbd2_journal_remove_checkpoint(jh); + jbd_unlock_bh_state(bh); + jbd2_journal_remove_journal_head(bh); + __brelse(bh); + } +} + +#define NR_BATCH 64 + +static void +__flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count) +{ + int i; + + ll_rw_block(SWRITE, *batch_count, bhs); + for (i = 0; i < *batch_count; i++) { + struct buffer_head *bh = bhs[i]; + clear_buffer_jwrite(bh); + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + } + *batch_count = 0; +} + +/* + * Try to flush one buffer from the checkpoint list to disk. + * + * Return 1 if something happened which requires us to abort the current + * scan of the checkpoint list. + * + * Called with j_list_lock held and drops it if 1 is returned + * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it + */ +static int __process_buffer(journal_t *journal, struct journal_head *jh, + struct buffer_head **bhs, int *batch_count) +{ + struct buffer_head *bh = jh2bh(jh); + int ret = 0; + + if (buffer_locked(bh)) { + atomic_inc(&bh->b_count); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + wait_on_buffer(bh); + /* the journal_head may have gone by now */ + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + ret = 1; + } else if (jh->b_transaction != NULL) { + transaction_t *t = jh->b_transaction; + tid_t tid = t->t_tid; + + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + jbd2_log_start_commit(journal, tid); + jbd2_log_wait_commit(journal, tid); + ret = 1; + } else if (!buffer_dirty(bh)) { + J_ASSERT_JH(jh, !buffer_jbddirty(bh)); + BUFFER_TRACE(bh, "remove from checkpoint"); + __jbd2_journal_remove_checkpoint(jh); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + jbd2_journal_remove_journal_head(bh); + __brelse(bh); + ret = 1; + } else { + /* + * Important: we are about to write the buffer, and + * possibly block, while still holding the journal lock. + * We cannot afford to let the transaction logic start + * messing around with this buffer before we write it to + * disk, as that would break recoverability. + */ + BUFFER_TRACE(bh, "queue"); + get_bh(bh); + J_ASSERT_BH(bh, !buffer_jwrite(bh)); + set_buffer_jwrite(bh); + bhs[*batch_count] = bh; + __buffer_relink_io(jh); + jbd_unlock_bh_state(bh); + (*batch_count)++; + if (*batch_count == NR_BATCH) { + spin_unlock(&journal->j_list_lock); + __flush_batch(journal, bhs, batch_count); + ret = 1; + } + } + return ret; +} + +/* + * Perform an actual checkpoint. We take the first transaction on the + * list of transactions to be checkpointed and send all its buffers + * to disk. We submit larger chunks of data at once. + * + * The journal should be locked before calling this function. + */ +int jbd2_log_do_checkpoint(journal_t *journal) +{ + transaction_t *transaction; + tid_t this_tid; + int result; + + jbd_debug(1, "Start checkpoint\n"); + + /* + * First thing: if there are any transactions in the log which + * don't need checkpointing, just eliminate them from the + * journal straight away. + */ + result = jbd2_cleanup_journal_tail(journal); + jbd_debug(1, "cleanup_journal_tail returned %d\n", result); + if (result <= 0) + return result; + + /* + * OK, we need to start writing disk blocks. Take one transaction + * and write it. + */ + spin_lock(&journal->j_list_lock); + if (!journal->j_checkpoint_transactions) + goto out; + transaction = journal->j_checkpoint_transactions; + this_tid = transaction->t_tid; +restart: + /* + * If someone cleaned up this transaction while we slept, we're + * done (maybe it's a new transaction, but it fell at the same + * address). + */ + if (journal->j_checkpoint_transactions == transaction && + transaction->t_tid == this_tid) { + int batch_count = 0; + struct buffer_head *bhs[NR_BATCH]; + struct journal_head *jh; + int retry = 0; + + while (!retry && transaction->t_checkpoint_list) { + struct buffer_head *bh; + + jh = transaction->t_checkpoint_list; + bh = jh2bh(jh); + if (!jbd_trylock_bh_state(bh)) { + jbd_sync_bh(journal, bh); + retry = 1; + break; + } + retry = __process_buffer(journal, jh, bhs,&batch_count); + if (!retry && lock_need_resched(&journal->j_list_lock)){ + spin_unlock(&journal->j_list_lock); + retry = 1; + break; + } + } + + if (batch_count) { + if (!retry) { + spin_unlock(&journal->j_list_lock); + retry = 1; + } + __flush_batch(journal, bhs, &batch_count); + } + + if (retry) { + spin_lock(&journal->j_list_lock); + goto restart; + } + /* + * Now we have cleaned up the first transaction's checkpoint + * list. Let's clean up the second one + */ + __wait_cp_io(journal, transaction); + } +out: + spin_unlock(&journal->j_list_lock); + result = jbd2_cleanup_journal_tail(journal); + if (result < 0) + return result; + return 0; +} + +/* + * Check the list of checkpoint transactions for the journal to see if + * we have already got rid of any since the last update of the log tail + * in the journal superblock. If so, we can instantly roll the + * superblock forward to remove those transactions from the log. + * + * Return <0 on error, 0 on success, 1 if there was nothing to clean up. + * + * Called with the journal lock held. + * + * This is the only part of the journaling code which really needs to be + * aware of transaction aborts. Checkpointing involves writing to the + * main filesystem area rather than to the journal, so it can proceed + * even in abort state, but we must not update the journal superblock if + * we have an abort error outstanding. + */ + +int jbd2_cleanup_journal_tail(journal_t *journal) +{ + transaction_t * transaction; + tid_t first_tid; + unsigned long blocknr, freed; + + /* OK, work out the oldest transaction remaining in the log, and + * the log block it starts at. + * + * If the log is now empty, we need to work out which is the + * next transaction ID we will write, and where it will + * start. */ + + spin_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + transaction = journal->j_checkpoint_transactions; + if (transaction) { + first_tid = transaction->t_tid; + blocknr = transaction->t_log_start; + } else if ((transaction = journal->j_committing_transaction) != NULL) { + first_tid = transaction->t_tid; + blocknr = transaction->t_log_start; + } else if ((transaction = journal->j_running_transaction) != NULL) { + first_tid = transaction->t_tid; + blocknr = journal->j_head; + } else { + first_tid = journal->j_transaction_sequence; + blocknr = journal->j_head; + } + spin_unlock(&journal->j_list_lock); + J_ASSERT(blocknr != 0); + + /* If the oldest pinned transaction is at the tail of the log + already then there's not much we can do right now. */ + if (journal->j_tail_sequence == first_tid) { + spin_unlock(&journal->j_state_lock); + return 1; + } + + /* OK, update the superblock to recover the freed space. + * Physical blocks come first: have we wrapped beyond the end of + * the log? */ + freed = blocknr - journal->j_tail; + if (blocknr < journal->j_tail) + freed = freed + journal->j_last - journal->j_first; + + jbd_debug(1, + "Cleaning journal tail from %d to %d (offset %lu), " + "freeing %lu\n", + journal->j_tail_sequence, first_tid, blocknr, freed); + + journal->j_free += freed; + journal->j_tail_sequence = first_tid; + journal->j_tail = blocknr; + spin_unlock(&journal->j_state_lock); + if (!(journal->j_flags & JBD2_ABORT)) + jbd2_journal_update_superblock(journal, 1); + return 0; +} + + +/* Checkpoint list management */ + +/* + * journal_clean_one_cp_list + * + * Find all the written-back checkpoint buffers in the given list and release them. + * + * Called with the journal locked. + * Called with j_list_lock held. + * Returns number of bufers reaped (for debug) + */ + +static int journal_clean_one_cp_list(struct journal_head *jh, int *released) +{ + struct journal_head *last_jh; + struct journal_head *next_jh = jh; + int ret, freed = 0; + + *released = 0; + if (!jh) + return 0; + + last_jh = jh->b_cpprev; + do { + jh = next_jh; + next_jh = jh->b_cpnext; + /* Use trylock because of the ranking */ + if (jbd_trylock_bh_state(jh2bh(jh))) { + ret = __try_to_free_cp_buf(jh); + if (ret) { + freed++; + if (ret == 2) { + *released = 1; + return freed; + } + } + } + /* + * This function only frees up some memory + * if possible so we dont have an obligation + * to finish processing. Bail out if preemption + * requested: + */ + if (need_resched()) + return freed; + } while (jh != last_jh); + + return freed; +} + +/* + * journal_clean_checkpoint_list + * + * Find all the written-back checkpoint buffers in the journal and release them. + * + * Called with the journal locked. + * Called with j_list_lock held. + * Returns number of buffers reaped (for debug) + */ + +int __jbd2_journal_clean_checkpoint_list(journal_t *journal) +{ + transaction_t *transaction, *last_transaction, *next_transaction; + int ret = 0; + int released; + + transaction = journal->j_checkpoint_transactions; + if (!transaction) + goto out; + + last_transaction = transaction->t_cpprev; + next_transaction = transaction; + do { + transaction = next_transaction; + next_transaction = transaction->t_cpnext; + ret += journal_clean_one_cp_list(transaction-> + t_checkpoint_list, &released); + /* + * This function only frees up some memory if possible so we + * dont have an obligation to finish processing. Bail out if + * preemption requested: + */ + if (need_resched()) + goto out; + if (released) + continue; + /* + * It is essential that we are as careful as in the case of + * t_checkpoint_list with removing the buffer from the list as + * we can possibly see not yet submitted buffers on io_list + */ + ret += journal_clean_one_cp_list(transaction-> + t_checkpoint_io_list, &released); + if (need_resched()) + goto out; + } while (transaction != last_transaction); +out: + return ret; +} + +/* + * journal_remove_checkpoint: called after a buffer has been committed + * to disk (either by being write-back flushed to disk, or being + * committed to the log). + * + * We cannot safely clean a transaction out of the log until all of the + * buffer updates committed in that transaction have safely been stored + * elsewhere on disk. To achieve this, all of the buffers in a + * transaction need to be maintained on the transaction's checkpoint + * lists until they have been rewritten, at which point this function is + * called to remove the buffer from the existing transaction's + * checkpoint lists. + * + * The function returns 1 if it frees the transaction, 0 otherwise. + * + * This function is called with the journal locked. + * This function is called with j_list_lock held. + * This function is called with jbd_lock_bh_state(jh2bh(jh)) + */ + +int __jbd2_journal_remove_checkpoint(struct journal_head *jh) +{ + transaction_t *transaction; + journal_t *journal; + int ret = 0; + + JBUFFER_TRACE(jh, "entry"); + + if ((transaction = jh->b_cp_transaction) == NULL) { + JBUFFER_TRACE(jh, "not on transaction"); + goto out; + } + journal = transaction->t_journal; + + __buffer_unlink(jh); + jh->b_cp_transaction = NULL; + + if (transaction->t_checkpoint_list != NULL || + transaction->t_checkpoint_io_list != NULL) + goto out; + JBUFFER_TRACE(jh, "transaction has no more buffers"); + + /* + * There is one special case to worry about: if we have just pulled the + * buffer off a committing transaction's forget list, then even if the + * checkpoint list is empty, the transaction obviously cannot be + * dropped! + * + * The locking here around j_committing_transaction is a bit sleazy. + * See the comment at the end of jbd2_journal_commit_transaction(). + */ + if (transaction == journal->j_committing_transaction) { + JBUFFER_TRACE(jh, "belongs to committing transaction"); + goto out; + } + + /* OK, that was the last buffer for the transaction: we can now + safely remove this transaction from the log */ + + __jbd2_journal_drop_transaction(journal, transaction); + + /* Just in case anybody was waiting for more transactions to be + checkpointed... */ + wake_up(&journal->j_wait_logspace); + ret = 1; +out: + JBUFFER_TRACE(jh, "exit"); + return ret; +} + +/* + * journal_insert_checkpoint: put a committed buffer onto a checkpoint + * list so that we know when it is safe to clean the transaction out of + * the log. + * + * Called with the journal locked. + * Called with j_list_lock held. + */ +void __jbd2_journal_insert_checkpoint(struct journal_head *jh, + transaction_t *transaction) +{ + JBUFFER_TRACE(jh, "entry"); + J_ASSERT_JH(jh, buffer_dirty(jh2bh(jh)) || buffer_jbddirty(jh2bh(jh))); + J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); + + jh->b_cp_transaction = transaction; + + if (!transaction->t_checkpoint_list) { + jh->b_cpnext = jh->b_cpprev = jh; + } else { + jh->b_cpnext = transaction->t_checkpoint_list; + jh->b_cpprev = transaction->t_checkpoint_list->b_cpprev; + jh->b_cpprev->b_cpnext = jh; + jh->b_cpnext->b_cpprev = jh; + } + transaction->t_checkpoint_list = jh; +} + +/* + * We've finished with this transaction structure: adios... + * + * The transaction must have no links except for the checkpoint by this + * point. + * + * Called with the journal locked. + * Called with j_list_lock held. + */ + +void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transaction) +{ + assert_spin_locked(&journal->j_list_lock); + if (transaction->t_cpnext) { + transaction->t_cpnext->t_cpprev = transaction->t_cpprev; + transaction->t_cpprev->t_cpnext = transaction->t_cpnext; + if (journal->j_checkpoint_transactions == transaction) + journal->j_checkpoint_transactions = + transaction->t_cpnext; + if (journal->j_checkpoint_transactions == transaction) + journal->j_checkpoint_transactions = NULL; + } + + J_ASSERT(transaction->t_state == T_FINISHED); + J_ASSERT(transaction->t_buffers == NULL); + J_ASSERT(transaction->t_sync_datalist == NULL); + J_ASSERT(transaction->t_forget == NULL); + J_ASSERT(transaction->t_iobuf_list == NULL); + J_ASSERT(transaction->t_shadow_list == NULL); + J_ASSERT(transaction->t_log_list == NULL); + J_ASSERT(transaction->t_checkpoint_list == NULL); + J_ASSERT(transaction->t_checkpoint_io_list == NULL); + J_ASSERT(transaction->t_updates == 0); + J_ASSERT(journal->j_committing_transaction != transaction); + J_ASSERT(journal->j_running_transaction != transaction); + + jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid); + kfree(transaction); +} diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c new file mode 100644 index 00000000000..70b2ae1ef28 --- /dev/null +++ b/fs/jbd2/commit.c @@ -0,0 +1,920 @@ +/* + * linux/fs/jbd2/commit.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 + * + * Copyright 1998 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Journal commit routines for the generic filesystem journaling code; + * part of the ext2fs journaling system. + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/smp_lock.h> + +/* + * Default IO end handler for temporary BJ_IO buffer_heads. + */ +static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate) +{ + BUFFER_TRACE(bh, ""); + if (uptodate) + set_buffer_uptodate(bh); + else + clear_buffer_uptodate(bh); + unlock_buffer(bh); +} + +/* + * When an ext3-ordered file is truncated, it is possible that many pages are + * not sucessfully freed, because they are attached to a committing transaction. + * After the transaction commits, these pages are left on the LRU, with no + * ->mapping, and with attached buffers. These pages are trivially reclaimable + * by the VM, but their apparent absence upsets the VM accounting, and it makes + * the numbers in /proc/meminfo look odd. + * + * So here, we have a buffer which has just come off the forget list. Look to + * see if we can strip all buffers from the backing page. + * + * Called under lock_journal(), and possibly under journal_datalist_lock. The + * caller provided us with a ref against the buffer, and we drop that here. + */ +static void release_buffer_page(struct buffer_head *bh) +{ + struct page *page; + + if (buffer_dirty(bh)) + goto nope; + if (atomic_read(&bh->b_count) != 1) + goto nope; + page = bh->b_page; + if (!page) + goto nope; + if (page->mapping) + goto nope; + + /* OK, it's a truncated page */ + if (TestSetPageLocked(page)) + goto nope; + + page_cache_get(page); + __brelse(bh); + try_to_free_buffers(page); + unlock_page(page); + page_cache_release(page); + return; + +nope: + __brelse(bh); +} + +/* + * Try to acquire jbd_lock_bh_state() against the buffer, when j_list_lock is + * held. For ranking reasons we must trylock. If we lose, schedule away and + * return 0. j_list_lock is dropped in this case. + */ +static int inverted_lock(journal_t *journal, struct buffer_head *bh) +{ + if (!jbd_trylock_bh_state(bh)) { + spin_unlock(&journal->j_list_lock); + schedule(); + return 0; + } + return 1; +} + +/* Done it all: now write the commit record. We should have + * cleaned up our previous buffers by now, so if we are in abort + * mode we can now just skip the rest of the journal write + * entirely. + * + * Returns 1 if the journal needs to be aborted or 0 on success + */ +static int journal_write_commit_record(journal_t *journal, + transaction_t *commit_transaction) +{ + struct journal_head *descriptor; + struct buffer_head *bh; + int i, ret; + int barrier_done = 0; + + if (is_journal_aborted(journal)) + return 0; + + descriptor = jbd2_journal_get_descriptor_buffer(journal); + if (!descriptor) + return 1; + + bh = jh2bh(descriptor); + + /* AKPM: buglet - add `i' to tmp! */ + for (i = 0; i < bh->b_size; i += 512) { + journal_header_t *tmp = (journal_header_t*)bh->b_data; + tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); + tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK); + tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid); + } + + JBUFFER_TRACE(descriptor, "write commit block"); + set_buffer_dirty(bh); + if (journal->j_flags & JBD2_BARRIER) { + set_buffer_ordered(bh); + barrier_done = 1; + } + ret = sync_dirty_buffer(bh); + /* is it possible for another commit to fail at roughly + * the same time as this one? If so, we don't want to + * trust the barrier flag in the super, but instead want + * to remember if we sent a barrier request + */ + if (ret == -EOPNOTSUPP && barrier_done) { + char b[BDEVNAME_SIZE]; + + printk(KERN_WARNING + "JBD: barrier-based sync failed on %s - " + "disabling barriers\n", + bdevname(journal->j_dev, b)); + spin_lock(&journal->j_state_lock); + journal->j_flags &= ~JBD2_BARRIER; + spin_unlock(&journal->j_state_lock); + + /* And try again, without the barrier */ + clear_buffer_ordered(bh); + set_buffer_uptodate(bh); + set_buffer_dirty(bh); + ret = sync_dirty_buffer(bh); + } + put_bh(bh); /* One for getblk() */ + jbd2_journal_put_journal_head(descriptor); + + return (ret == -EIO); +} + +static void journal_do_submit_data(struct buffer_head **wbuf, int bufs) +{ + int i; + + for (i = 0; i < bufs; i++) { + wbuf[i]->b_end_io = end_buffer_write_sync; + /* We use-up our safety reference in submit_bh() */ + submit_bh(WRITE, wbuf[i]); + } +} + +/* + * Submit all the data buffers to disk + */ +static void journal_submit_data_buffers(journal_t *journal, + transaction_t *commit_transaction) +{ + struct journal_head *jh; + struct buffer_head *bh; + int locked; + int bufs = 0; + struct buffer_head **wbuf = journal->j_wbuf; + + /* + * Whenever we unlock the journal and sleep, things can get added + * onto ->t_sync_datalist, so we have to keep looping back to + * write_out_data until we *know* that the list is empty. + * + * Cleanup any flushed data buffers from the data list. Even in + * abort mode, we want to flush this out as soon as possible. + */ +write_out_data: + cond_resched(); + spin_lock(&journal->j_list_lock); + + while (commit_transaction->t_sync_datalist) { + jh = commit_transaction->t_sync_datalist; + bh = jh2bh(jh); + locked = 0; + + /* Get reference just to make sure buffer does not disappear + * when we are forced to drop various locks */ + get_bh(bh); + /* If the buffer is dirty, we need to submit IO and hence + * we need the buffer lock. We try to lock the buffer without + * blocking. If we fail, we need to drop j_list_lock and do + * blocking lock_buffer(). + */ + if (buffer_dirty(bh)) { + if (test_set_buffer_locked(bh)) { + BUFFER_TRACE(bh, "needs blocking lock"); + spin_unlock(&journal->j_list_lock); + /* Write out all data to prevent deadlocks */ + journal_do_submit_data(wbuf, bufs); + bufs = 0; + lock_buffer(bh); + spin_lock(&journal->j_list_lock); + } + locked = 1; + } + /* We have to get bh_state lock. Again out of order, sigh. */ + if (!inverted_lock(journal, bh)) { + jbd_lock_bh_state(bh); + spin_lock(&journal->j_list_lock); + } + /* Someone already cleaned up the buffer? */ + if (!buffer_jbd(bh) + || jh->b_transaction != commit_transaction + || jh->b_jlist != BJ_SyncData) { + jbd_unlock_bh_state(bh); + if (locked) + unlock_buffer(bh); + BUFFER_TRACE(bh, "already cleaned up"); + put_bh(bh); + continue; + } + if (locked && test_clear_buffer_dirty(bh)) { + BUFFER_TRACE(bh, "needs writeout, adding to array"); + wbuf[bufs++] = bh; + __jbd2_journal_file_buffer(jh, commit_transaction, + BJ_Locked); + jbd_unlock_bh_state(bh); + if (bufs == journal->j_wbufsize) { + spin_unlock(&journal->j_list_lock); + journal_do_submit_data(wbuf, bufs); + bufs = 0; + goto write_out_data; + } + } + else { + BUFFER_TRACE(bh, "writeout complete: unfile"); + __jbd2_journal_unfile_buffer(jh); + jbd_unlock_bh_state(bh); + if (locked) + unlock_buffer(bh); + jbd2_journal_remove_journal_head(bh); + /* Once for our safety reference, once for + * jbd2_journal_remove_journal_head() */ + put_bh(bh); + put_bh(bh); + } + + if (lock_need_resched(&journal->j_list_lock)) { + spin_unlock(&journal->j_list_lock); + goto write_out_data; + } + } + spin_unlock(&journal->j_list_lock); + journal_do_submit_data(wbuf, bufs); +} + +static inline void write_tag_block(int tag_bytes, journal_block_tag_t *tag, + unsigned long long block) +{ + tag->t_blocknr = cpu_to_be32(block & (u32)~0); + if (tag_bytes > JBD_TAG_SIZE32) + tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); +} + +/* + * jbd2_journal_commit_transaction + * + * The primary function for committing a transaction to the log. This + * function is called by the journal thread to begin a complete commit. + */ +void jbd2_journal_commit_transaction(journal_t *journal) +{ + transaction_t *commit_transaction; + struct journal_head *jh, *new_jh, *descriptor; + struct buffer_head **wbuf = journal->j_wbuf; + int bufs; + int flags; + int err; + unsigned long long blocknr; + char *tagp = NULL; + journal_header_t *header; + journal_block_tag_t *tag = NULL; + int space_left = 0; + int first_tag = 0; + int tag_flag; + int i; + int tag_bytes = journal_tag_bytes(journal); + + /* + * First job: lock down the current transaction and wait for + * all outstanding updates to complete. + */ + +#ifdef COMMIT_STATS + spin_lock(&journal->j_list_lock); + summarise_journal_usage(journal); + spin_unlock(&journal->j_list_lock); +#endif + + /* Do we need to erase the effects of a prior jbd2_journal_flush? */ + if (journal->j_flags & JBD2_FLUSHED) { + jbd_debug(3, "super block updated\n"); + jbd2_journal_update_superblock(journal, 1); + } else { + jbd_debug(3, "superblock not updated\n"); + } + + J_ASSERT(journal->j_running_transaction != NULL); + J_ASSERT(journal->j_committing_transaction == NULL); + + commit_transaction = journal->j_running_transaction; + J_ASSERT(commit_transaction->t_state == T_RUNNING); + + jbd_debug(1, "JBD: starting commit of transaction %d\n", + commit_transaction->t_tid); + + spin_lock(&journal->j_state_lock); + commit_transaction->t_state = T_LOCKED; + + spin_lock(&commit_transaction->t_handle_lock); + while (commit_transaction->t_updates) { + DEFINE_WAIT(wait); + + prepare_to_wait(&journal->j_wait_updates, &wait, + TASK_UNINTERRUPTIBLE); + if (commit_transaction->t_updates) { + spin_unlock(&commit_transaction->t_handle_lock); + spin_unlock(&journal->j_state_lock); + schedule(); + spin_lock(&journal->j_state_lock); + spin_lock(&commit_transaction->t_handle_lock); + } + finish_wait(&journal->j_wait_updates, &wait); + } + spin_unlock(&commit_transaction->t_handle_lock); + + J_ASSERT (commit_transaction->t_outstanding_credits <= + journal->j_max_transaction_buffers); + + /* + * First thing we are allowed to do is to discard any remaining + * BJ_Reserved buffers. Note, it is _not_ permissible to assume + * that there are no such buffers: if a large filesystem + * operation like a truncate needs to split itself over multiple + * transactions, then it may try to do a jbd2_journal_restart() while + * there are still BJ_Reserved buffers outstanding. These must + * be released cleanly from the current transaction. + * + * In this case, the filesystem must still reserve write access + * again before modifying the buffer in the new transaction, but + * we do not require it to remember exactly which old buffers it + * has reserved. This is consistent with the existing behaviour + * that multiple jbd2_journal_get_write_access() calls to the same + * buffer are perfectly permissable. + */ + while (commit_transaction->t_reserved_list) { + jh = commit_transaction->t_reserved_list; + JBUFFER_TRACE(jh, "reserved, unused: refile"); + /* + * A jbd2_journal_get_undo_access()+jbd2_journal_release_buffer() may + * leave undo-committed data. + */ + if (jh->b_committed_data) { + struct buffer_head *bh = jh2bh(jh); + + jbd_lock_bh_state(bh); + jbd2_slab_free(jh->b_committed_data, bh->b_size); + jh->b_committed_data = NULL; + jbd_unlock_bh_state(bh); + } + jbd2_journal_refile_buffer(journal, jh); + } + + /* + * Now try to drop any written-back buffers from the journal's + * checkpoint lists. We do this *before* commit because it potentially + * frees some memory + */ + spin_lock(&journal->j_list_lock); + __jbd2_journal_clean_checkpoint_list(journal); + spin_unlock(&journal->j_list_lock); + + jbd_debug (3, "JBD: commit phase 1\n"); + + /* + * Switch to a new revoke table. + */ + jbd2_journal_switch_revoke_table(journal); + + commit_transaction->t_state = T_FLUSH; + journal->j_committing_transaction = commit_transaction; + journal->j_running_transaction = NULL; + commit_transaction->t_log_start = journal->j_head; + wake_up(&journal->j_wait_transaction_locked); + spin_unlock(&journal->j_state_lock); + + jbd_debug (3, "JBD: commit phase 2\n"); + + /* + * First, drop modified flag: all accesses to the buffers + * will be tracked for a new trasaction only -bzzz + */ + spin_lock(&journal->j_list_lock); + if (commit_transaction->t_buffers) { + new_jh = jh = commit_transaction->t_buffers->b_tnext; + do { + J_ASSERT_JH(new_jh, new_jh->b_modified == 1 || + new_jh->b_modified == 0); + new_jh->b_modified = 0; + new_jh = new_jh->b_tnext; + } while (new_jh != jh); + } + spin_unlock(&journal->j_list_lock); + + /* + * Now start flushing things to disk, in the order they appear + * on the transaction lists. Data blocks go first. + */ + err = 0; + journal_submit_data_buffers(journal, commit_transaction); + + /* + * Wait for all previously submitted IO to complete. + */ + spin_lock(&journal->j_list_lock); + while (commit_transaction->t_locked_list) { + struct buffer_head *bh; + + jh = commit_transaction->t_locked_list->b_tprev; + bh = jh2bh(jh); + get_bh(bh); + if (buffer_locked(bh)) { + spin_unlock(&journal->j_list_lock); + wait_on_buffer(bh); + if (unlikely(!buffer_uptodate(bh))) + err = -EIO; + spin_lock(&journal->j_list_lock); + } + if (!inverted_lock(journal, bh)) { + put_bh(bh); + spin_lock(&journal->j_list_lock); + continue; + } + if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) { + __jbd2_journal_unfile_buffer(jh); + jbd_unlock_bh_state(bh); + jbd2_journal_remove_journal_head(bh); + put_bh(bh); + } else { + jbd_unlock_bh_state(bh); + } + put_bh(bh); + cond_resched_lock(&journal->j_list_lock); + } + spin_unlock(&journal->j_list_lock); + + if (err) + __jbd2_journal_abort_hard(journal); + + jbd2_journal_write_revoke_records(journal, commit_transaction); + + jbd_debug(3, "JBD: commit phase 2\n"); + + /* + * If we found any dirty or locked buffers, then we should have + * looped back up to the write_out_data label. If there weren't + * any then journal_clean_data_list should have wiped the list + * clean by now, so check that it is in fact empty. + */ + J_ASSERT (commit_transaction->t_sync_datalist == NULL); + + jbd_debug (3, "JBD: commit phase 3\n"); + + /* + * Way to go: we have now written out all of the data for a + * transaction! Now comes the tricky part: we need to write out + * metadata. Loop over the transaction's entire buffer list: + */ + commit_transaction->t_state = T_COMMIT; + + descriptor = NULL; + bufs = 0; + while (commit_transaction->t_buffers) { + + /* Find the next buffer to be journaled... */ + + jh = commit_transaction->t_buffers; + + /* If we're in abort mode, we just un-journal the buffer and + release it for background writing. */ + + if (is_journal_aborted(journal)) { + JBUFFER_TRACE(jh, "journal is aborting: refile"); + jbd2_journal_refile_buffer(journal, jh); + /* If that was the last one, we need to clean up + * any descriptor buffers which may have been + * already allocated, even if we are now + * aborting. */ + if (!commit_transaction->t_buffers) + goto start_journal_io; + continue; + } + + /* Make sure we have a descriptor block in which to + record the metadata buffer. */ + + if (!descriptor) { + struct buffer_head *bh; + + J_ASSERT (bufs == 0); + + jbd_debug(4, "JBD: get descriptor\n"); + + descriptor = jbd2_journal_get_descriptor_buffer(journal); + if (!descriptor) { + __jbd2_journal_abort_hard(journal); + continue; + } + + bh = jh2bh(descriptor); + jbd_debug(4, "JBD: got buffer %llu (%p)\n", + (unsigned long long)bh->b_blocknr, bh->b_data); + header = (journal_header_t *)&bh->b_data[0]; + header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); + header->h_blocktype = cpu_to_be32(JBD2_DESCRIPTOR_BLOCK); + header->h_sequence = cpu_to_be32(commit_transaction->t_tid); + + tagp = &bh->b_data[sizeof(journal_header_t)]; + space_left = bh->b_size - sizeof(journal_header_t); + first_tag = 1; + set_buffer_jwrite(bh); + set_buffer_dirty(bh); + wbuf[bufs++] = bh; + + /* Record it so that we can wait for IO + completion later */ + BUFFER_TRACE(bh, "ph3: file as descriptor"); + jbd2_journal_file_buffer(descriptor, commit_transaction, + BJ_LogCtl); + } + + /* Where is the buffer to be written? */ + + err = jbd2_journal_next_log_block(journal, &blocknr); + /* If the block mapping failed, just abandon the buffer + and repeat this loop: we'll fall into the + refile-on-abort condition above. */ + if (err) { + __jbd2_journal_abort_hard(journal); + continue; + } + + /* + * start_this_handle() uses t_outstanding_credits to determine + * the free space in the log, but this counter is changed + * by jbd2_journal_next_log_block() also. + */ + commit_transaction->t_outstanding_credits--; + + /* Bump b_count to prevent truncate from stumbling over + the shadowed buffer! @@@ This can go if we ever get + rid of the BJ_IO/BJ_Shadow pairing of buffers. */ + atomic_inc(&jh2bh(jh)->b_count); + + /* Make a temporary IO buffer with which to write it out + (this will requeue both the metadata buffer and the + temporary IO buffer). new_bh goes on BJ_IO*/ + + set_bit(BH_JWrite, &jh2bh(jh)->b_state); + /* + * akpm: jbd2_journal_write_metadata_buffer() sets + * new_bh->b_transaction to commit_transaction. + * We need to clean this up before we release new_bh + * (which is of type BJ_IO) + */ + JBUFFER_TRACE(jh, "ph3: write metadata"); + flags = jbd2_journal_write_metadata_buffer(commit_transaction, + jh, &new_jh, blocknr); + set_bit(BH_JWrite, &jh2bh(new_jh)->b_state); + wbuf[bufs++] = jh2bh(new_jh); + + /* Record the new block's tag in the current descriptor + buffer */ + + tag_flag = 0; + if (flags & 1) + tag_flag |= JBD2_FLAG_ESCAPE; + if (!first_tag) + tag_flag |= JBD2_FLAG_SAME_UUID; + + tag = (journal_block_tag_t *) tagp; + write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr); + tag->t_flags = cpu_to_be32(tag_flag); + tagp += tag_bytes; + space_left -= tag_bytes; + + if (first_tag) { + memcpy (tagp, journal->j_uuid, 16); + tagp += 16; + space_left -= 16; + first_tag = 0; + } + + /* If there's no more to do, or if the descriptor is full, + let the IO rip! */ + + if (bufs == journal->j_wbufsize || + commit_transaction->t_buffers == NULL || + space_left < tag_bytes + 16) { + + jbd_debug(4, "JBD: Submit %d IOs\n", bufs); + + /* Write an end-of-descriptor marker before + submitting the IOs. "tag" still points to + the last tag we set up. */ + + tag->t_flags |= cpu_to_be32(JBD2_FLAG_LAST_TAG); + +start_journal_io: + for (i = 0; i < bufs; i++) { + struct buffer_head *bh = wbuf[i]; + lock_buffer(bh); + clear_buffer_dirty(bh); + set_buffer_uptodate(bh); + bh->b_end_io = journal_end_buffer_io_sync; + submit_bh(WRITE, bh); + } + cond_resched(); + + /* Force a new descriptor to be generated next + time round the loop. */ + descriptor = NULL; + bufs = 0; + } + } + + /* Lo and behold: we have just managed to send a transaction to + the log. Before we can commit it, wait for the IO so far to + complete. Control buffers being written are on the + transaction's t_log_list queue, and metadata buffers are on + the t_iobuf_list queue. + + Wait for the buffers in reverse order. That way we are + less likely to be woken up until all IOs have completed, and + so we incur less scheduling load. + */ + + jbd_debug(3, "JBD: commit phase 4\n"); + + /* + * akpm: these are BJ_IO, and j_list_lock is not needed. + * See __journal_try_to_free_buffer. + */ +wait_for_iobuf: + while (commit_transaction->t_iobuf_list != NULL) { + struct buffer_head *bh; + + jh = commit_transaction->t_iobuf_list->b_tprev; + bh = jh2bh(jh); + if (buffer_locked(bh)) { + wait_on_buffer(bh); + goto wait_for_iobuf; + } + if (cond_resched()) + goto wait_for_iobuf; + + if (unlikely(!buffer_uptodate(bh))) + err = -EIO; + + clear_buffer_jwrite(bh); + + JBUFFER_TRACE(jh, "ph4: unfile after journal write"); + jbd2_journal_unfile_buffer(journal, jh); + + /* + * ->t_iobuf_list should contain only dummy buffer_heads + * which were created by jbd2_journal_write_metadata_buffer(). + */ + BUFFER_TRACE(bh, "dumping temporary bh"); + jbd2_journal_put_journal_head(jh); + __brelse(bh); + J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0); + free_buffer_head(bh); + + /* We also have to unlock and free the corresponding + shadowed buffer */ + jh = commit_transaction->t_shadow_list->b_tprev; + bh = jh2bh(jh); + clear_bit(BH_JWrite, &bh->b_state); + J_ASSERT_BH(bh, buffer_jbddirty(bh)); + + /* The metadata is now released for reuse, but we need + to remember it against this transaction so that when + we finally commit, we can do any checkpointing + required. */ + JBUFFER_TRACE(jh, "file as BJ_Forget"); + jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget); + /* Wake up any transactions which were waiting for this + IO to complete */ + wake_up_bit(&bh->b_state, BH_Unshadow); + JBUFFER_TRACE(jh, "brelse shadowed buffer"); + __brelse(bh); + } + + J_ASSERT (commit_transaction->t_shadow_list == NULL); + + jbd_debug(3, "JBD: commit phase 5\n"); + + /* Here we wait for the revoke record and descriptor record buffers */ + wait_for_ctlbuf: + while (commit_transaction->t_log_list != NULL) { + struct buffer_head *bh; + + jh = commit_transaction->t_log_list->b_tprev; + bh = jh2bh(jh); + if (buffer_locked(bh)) { + wait_on_buffer(bh); + goto wait_for_ctlbuf; + } + if (cond_resched()) + goto wait_for_ctlbuf; + + if (unlikely(!buffer_uptodate(bh))) + err = -EIO; + + BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile"); + clear_buffer_jwrite(bh); + jbd2_journal_unfile_buffer(journal, jh); + jbd2_journal_put_journal_head(jh); + __brelse(bh); /* One for getblk */ + /* AKPM: bforget here */ + } + + jbd_debug(3, "JBD: commit phase 6\n"); + + if (journal_write_commit_record(journal, commit_transaction)) + err = -EIO; + + if (err) + __jbd2_journal_abort_hard(journal); + + /* End of a transaction! Finally, we can do checkpoint + processing: any buffers committed as a result of this + transaction can be removed from any checkpoint list it was on + before. */ + + jbd_debug(3, "JBD: commit phase 7\n"); + + J_ASSERT(commit_transaction->t_sync_datalist == NULL); + J_ASSERT(commit_transaction->t_buffers == NULL); + J_ASSERT(commit_transaction->t_checkpoint_list == NULL); + J_ASSERT(commit_transaction->t_iobuf_list == NULL); + J_ASSERT(commit_transaction->t_shadow_list == NULL); + J_ASSERT(commit_transaction->t_log_list == NULL); + +restart_loop: + /* + * As there are other places (journal_unmap_buffer()) adding buffers + * to this list we have to be careful and hold the j_list_lock. + */ + spin_lock(&journal->j_list_lock); + while (commit_transaction->t_forget) { + transaction_t *cp_transaction; + struct buffer_head *bh; + + jh = commit_transaction->t_forget; + spin_unlock(&journal->j_list_lock); + bh = jh2bh(jh); + jbd_lock_bh_state(bh); + J_ASSERT_JH(jh, jh->b_transaction == commit_transaction || + jh->b_transaction == journal->j_running_transaction); + + /* + * If there is undo-protected committed data against + * this buffer, then we can remove it now. If it is a + * buffer needing such protection, the old frozen_data + * field now points to a committed version of the + * buffer, so rotate that field to the new committed + * data. + * + * Otherwise, we can just throw away the frozen data now. + */ + if (jh->b_committed_data) { + jbd2_slab_free(jh->b_committed_data, bh->b_size); + jh->b_committed_data = NULL; + if (jh->b_frozen_data) { + jh->b_committed_data = jh->b_frozen_data; + jh->b_frozen_data = NULL; + } + } else if (jh->b_frozen_data) { + jbd2_slab_free(jh->b_frozen_data, bh->b_size); + jh->b_frozen_data = NULL; + } + + spin_lock(&journal->j_list_lock); + cp_transaction = jh->b_cp_transaction; + if (cp_transaction) { + JBUFFER_TRACE(jh, "remove from old cp transaction"); + __jbd2_journal_remove_checkpoint(jh); + } + + /* Only re-checkpoint the buffer_head if it is marked + * dirty. If the buffer was added to the BJ_Forget list + * by jbd2_journal_forget, it may no longer be dirty and + * there's no point in keeping a checkpoint record for + * it. */ + + /* A buffer which has been freed while still being + * journaled by a previous transaction may end up still + * being dirty here, but we want to avoid writing back + * that buffer in the future now that the last use has + * been committed. That's not only a performance gain, + * it also stops aliasing problems if the buffer is left + * behind for writeback and gets reallocated for another + * use in a different page. */ + if (buffer_freed(bh)) { + clear_buffer_freed(bh); + clear_buffer_jbddirty(bh); + } + + if (buffer_jbddirty(bh)) { + JBUFFER_TRACE(jh, "add to new checkpointing trans"); + __jbd2_journal_insert_checkpoint(jh, commit_transaction); + JBUFFER_TRACE(jh, "refile for checkpoint writeback"); + __jbd2_journal_refile_buffer(jh); + jbd_unlock_bh_state(bh); + } else { + J_ASSERT_BH(bh, !buffer_dirty(bh)); + /* The buffer on BJ_Forget list and not jbddirty means + * it has been freed by this transaction and hence it + * could not have been reallocated until this + * transaction has committed. *BUT* it could be + * reallocated once we have written all the data to + * disk and before we process the buffer on BJ_Forget + * list. */ + JBUFFER_TRACE(jh, "refile or unfile freed buffer"); + __jbd2_journal_refile_buffer(jh); + if (!jh->b_transaction) { + jbd_unlock_bh_state(bh); + /* needs a brelse */ + jbd2_journal_remove_journal_head(bh); + release_buffer_page(bh); + } else + jbd_unlock_bh_state(bh); + } + cond_resched_lock(&journal->j_list_lock); + } + spin_unlock(&journal->j_list_lock); + /* + * This is a bit sleazy. We borrow j_list_lock to protect + * journal->j_committing_transaction in __jbd2_journal_remove_checkpoint. + * Really, __jbd2_journal_remove_checkpoint should be using j_state_lock but + * it's a bit hassle to hold that across __jbd2_journal_remove_checkpoint + */ + spin_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + /* + * Now recheck if some buffers did not get attached to the transaction + * while the lock was dropped... + */ + if (commit_transaction->t_forget) { + spin_unlock(&journal->j_list_lock); + spin_unlock(&journal->j_state_lock); + goto restart_loop; + } + + /* Done with this transaction! */ + + jbd_debug(3, "JBD: commit phase 8\n"); + + J_ASSERT(commit_transaction->t_state == T_COMMIT); + + commit_transaction->t_state = T_FINISHED; + J_ASSERT(commit_transaction == journal->j_committing_transaction); + journal->j_commit_sequence = commit_transaction->t_tid; + journal->j_committing_transaction = NULL; + spin_unlock(&journal->j_state_lock); + + if (commit_transaction->t_checkpoint_list == NULL) { + __jbd2_journal_drop_transaction(journal, commit_transaction); + } else { + if (journal->j_checkpoint_transactions == NULL) { + journal->j_checkpoint_transactions = commit_transaction; + commit_transaction->t_cpnext = commit_transaction; + commit_transaction->t_cpprev = commit_transaction; + } else { + commit_transaction->t_cpnext = + journal->j_checkpoint_transactions; + commit_transaction->t_cpprev = + commit_transaction->t_cpnext->t_cpprev; + commit_transaction->t_cpnext->t_cpprev = + commit_transaction; + commit_transaction->t_cpprev->t_cpnext = + commit_transaction; + } + } + spin_unlock(&journal->j_list_lock); + + jbd_debug(1, "JBD: commit %d complete, head %d\n", + journal->j_commit_sequence, journal->j_tail_sequence); + + wake_up(&journal->j_wait_done_commit); +} diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c new file mode 100644 index 00000000000..10db92ced01 --- /dev/null +++ b/fs/jbd2/journal.c @@ -0,0 +1,2083 @@ +/* + * linux/fs/jbd2/journal.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 + * + * Copyright 1998 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Generic filesystem journal-writing code; part of the ext2fs + * journaling system. + * + * This file manages journals: areas of disk reserved for logging + * transactional updates. This includes the kernel journaling thread + * which is responsible for scheduling updates to the log. + * + * We do not actually manage the physical storage of the journal in this + * file: that is left to a per-journal policy function, which allows us + * to store the journal within a filesystem-specified area for ext2 + * journaling (ext2 can use a reserved inode for storing the log). + */ + +#include <linux/module.h> +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/smp_lock.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/suspend.h> +#include <linux/pagemap.h> +#include <linux/kthread.h> +#include <linux/poison.h> +#include <linux/proc_fs.h> + +#include <asm/uaccess.h> +#include <asm/page.h> + +EXPORT_SYMBOL(jbd2_journal_start); +EXPORT_SYMBOL(jbd2_journal_restart); +EXPORT_SYMBOL(jbd2_journal_extend); +EXPORT_SYMBOL(jbd2_journal_stop); +EXPORT_SYMBOL(jbd2_journal_lock_updates); +EXPORT_SYMBOL(jbd2_journal_unlock_updates); +EXPORT_SYMBOL(jbd2_journal_get_write_access); +EXPORT_SYMBOL(jbd2_journal_get_create_access); +EXPORT_SYMBOL(jbd2_journal_get_undo_access); +EXPORT_SYMBOL(jbd2_journal_dirty_data); +EXPORT_SYMBOL(jbd2_journal_dirty_metadata); +EXPORT_SYMBOL(jbd2_journal_release_buffer); +EXPORT_SYMBOL(jbd2_journal_forget); +#if 0 +EXPORT_SYMBOL(journal_sync_buffer); +#endif +EXPORT_SYMBOL(jbd2_journal_flush); +EXPORT_SYMBOL(jbd2_journal_revoke); + +EXPORT_SYMBOL(jbd2_journal_init_dev); +EXPORT_SYMBOL(jbd2_journal_init_inode); +EXPORT_SYMBOL(jbd2_journal_update_format); +EXPORT_SYMBOL(jbd2_journal_check_used_features); +EXPORT_SYMBOL(jbd2_journal_check_available_features); +EXPORT_SYMBOL(jbd2_journal_set_features); +EXPORT_SYMBOL(jbd2_journal_create); +EXPORT_SYMBOL(jbd2_journal_load); +EXPORT_SYMBOL(jbd2_journal_destroy); +EXPORT_SYMBOL(jbd2_journal_update_superblock); +EXPORT_SYMBOL(jbd2_journal_abort); +EXPORT_SYMBOL(jbd2_journal_errno); +EXPORT_SYMBOL(jbd2_journal_ack_err); +EXPORT_SYMBOL(jbd2_journal_clear_err); +EXPORT_SYMBOL(jbd2_log_wait_commit); +EXPORT_SYMBOL(jbd2_journal_start_commit); +EXPORT_SYMBOL(jbd2_journal_force_commit_nested); +EXPORT_SYMBOL(jbd2_journal_wipe); +EXPORT_SYMBOL(jbd2_journal_blocks_per_page); +EXPORT_SYMBOL(jbd2_journal_invalidatepage); +EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); +EXPORT_SYMBOL(jbd2_journal_force_commit); + +static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); +static void __journal_abort_soft (journal_t *journal, int errno); +static int jbd2_journal_create_jbd_slab(size_t slab_size); + +/* + * Helper function used to manage commit timeouts + */ + +static void commit_timeout(unsigned long __data) +{ + struct task_struct * p = (struct task_struct *) __data; + + wake_up_process(p); +} + +/* + * kjournald2: The main thread function used to manage a logging device + * journal. + * + * This kernel thread is responsible for two things: + * + * 1) COMMIT: Every so often we need to commit the current state of the + * filesystem to disk. The journal thread is responsible for writing + * all of the metadata buffers to disk. + * + * 2) CHECKPOINT: We cannot reuse a used section of the log file until all + * of the data in that part of the log has been rewritten elsewhere on + * the disk. Flushing these old buffers to reclaim space in the log is + * known as checkpointing, and this thread is responsible for that job. + */ + +static int kjournald2(void *arg) +{ + journal_t *journal = arg; + transaction_t *transaction; + + /* + * Set up an interval timer which can be used to trigger a commit wakeup + * after the commit interval expires + */ + setup_timer(&journal->j_commit_timer, commit_timeout, + (unsigned long)current); + + /* Record that the journal thread is running */ + journal->j_task = current; + wake_up(&journal->j_wait_done_commit); + + printk(KERN_INFO "kjournald2 starting. Commit interval %ld seconds\n", + journal->j_commit_interval / HZ); + + /* + * And now, wait forever for commit wakeup events. + */ + spin_lock(&journal->j_state_lock); + +loop: + if (journal->j_flags & JBD2_UNMOUNT) + goto end_loop; + + jbd_debug(1, "commit_sequence=%d, commit_request=%d\n", + journal->j_commit_sequence, journal->j_commit_request); + + if (journal->j_commit_sequence != journal->j_commit_request) { + jbd_debug(1, "OK, requests differ\n"); + spin_unlock(&journal->j_state_lock); + del_timer_sync(&journal->j_commit_timer); + jbd2_journal_commit_transaction(journal); + spin_lock(&journal->j_state_lock); + goto loop; + } + + wake_up(&journal->j_wait_done_commit); + if (freezing(current)) { + /* + * The simpler the better. Flushing journal isn't a + * good idea, because that depends on threads that may + * be already stopped. + */ + jbd_debug(1, "Now suspending kjournald2\n"); + spin_unlock(&journal->j_state_lock); + refrigerator(); + spin_lock(&journal->j_state_lock); + } else { + /* + * We assume on resume that commits are already there, + * so we don't sleep + */ + DEFINE_WAIT(wait); + int should_sleep = 1; + + prepare_to_wait(&journal->j_wait_commit, &wait, + TASK_INTERRUPTIBLE); + if (journal->j_commit_sequence != journal->j_commit_request) + should_sleep = 0; + transaction = journal->j_running_transaction; + if (transaction && time_after_eq(jiffies, + transaction->t_expires)) + should_sleep = 0; + if (journal->j_flags & JBD2_UNMOUNT) + should_sleep = 0; + if (should_sleep) { + spin_unlock(&journal->j_state_lock); + schedule(); + spin_lock(&journal->j_state_lock); + } + finish_wait(&journal->j_wait_commit, &wait); + } + + jbd_debug(1, "kjournald2 wakes\n"); + + /* + * Were we woken up by a commit wakeup event? + */ + transaction = journal->j_running_transaction; + if (transaction && time_after_eq(jiffies, transaction->t_expires)) { + journal->j_commit_request = transaction->t_tid; + jbd_debug(1, "woke because of timeout\n"); + } + goto loop; + +end_loop: + spin_unlock(&journal->j_state_lock); + del_timer_sync(&journal->j_commit_timer); + journal->j_task = NULL; + wake_up(&journal->j_wait_done_commit); + jbd_debug(1, "Journal thread exiting.\n"); + return 0; +} + +static void jbd2_journal_start_thread(journal_t *journal) +{ + kthread_run(kjournald2, journal, "kjournald2"); + wait_event(journal->j_wait_done_commit, journal->j_task != 0); +} + +static void journal_kill_thread(journal_t *journal) +{ + spin_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_UNMOUNT; + + while (journal->j_task) { + wake_up(&journal->j_wait_commit); + spin_unlock(&journal->j_state_lock); + wait_event(journal->j_wait_done_commit, journal->j_task == 0); + spin_lock(&journal->j_state_lock); + } + spin_unlock(&journal->j_state_lock); +} + +/* + * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal. + * + * Writes a metadata buffer to a given disk block. The actual IO is not + * performed but a new buffer_head is constructed which labels the data + * to be written with the correct destination disk block. + * + * Any magic-number escaping which needs to be done will cause a + * copy-out here. If the buffer happens to start with the + * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the + * magic number is only written to the log for descripter blocks. In + * this case, we copy the data and replace the first word with 0, and we + * return a result code which indicates that this buffer needs to be + * marked as an escaped buffer in the corresponding log descriptor + * block. The missing word can then be restored when the block is read + * during recovery. + * + * If the source buffer has already been modified by a new transaction + * since we took the last commit snapshot, we use the frozen copy of + * that data for IO. If we end up using the existing buffer_head's data + * for the write, then we *have* to lock the buffer to prevent anyone + * else from using and possibly modifying it while the IO is in + * progress. + * + * The function returns a pointer to the buffer_heads to be used for IO. + * + * We assume that the journal has already been locked in this function. + * + * Return value: + * <0: Error + * >=0: Finished OK + * + * On success: + * Bit 0 set == escape performed on the data + * Bit 1 set == buffer copy-out performed (kfree the data after IO) + */ + +int jbd2_journal_write_metadata_buffer(transaction_t *transaction, + struct journal_head *jh_in, + struct journal_head **jh_out, + unsigned long long blocknr) +{ + int need_copy_out = 0; + int done_copy_out = 0; + int do_escape = 0; + char *mapped_data; + struct buffer_head *new_bh; + struct journal_head *new_jh; + struct page *new_page; + unsigned int new_offset; + struct buffer_head *bh_in = jh2bh(jh_in); + + /* + * The buffer really shouldn't be locked: only the current committing + * transaction is allowed to write it, so nobody else is allowed + * to do any IO. + * + * akpm: except if we're journalling data, and write() output is + * also part of a shared mapping, and another thread has + * decided to launch a writepage() against this buffer. + */ + J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in)); + + new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL); + + /* + * If a new transaction has already done a buffer copy-out, then + * we use that version of the data for the commit. + */ + jbd_lock_bh_state(bh_in); +repeat: + if (jh_in->b_frozen_data) { + done_copy_out = 1; + new_page = virt_to_page(jh_in->b_frozen_data); + new_offset = offset_in_page(jh_in->b_frozen_data); + } else { + new_page = jh2bh(jh_in)->b_page; + new_offset = offset_in_page(jh2bh(jh_in)->b_data); + } + + mapped_data = kmap_atomic(new_page, KM_USER0); + /* + * Check for escaping + */ + if (*((__be32 *)(mapped_data + new_offset)) == + cpu_to_be32(JBD2_MAGIC_NUMBER)) { + need_copy_out = 1; + do_escape = 1; + } + kunmap_atomic(mapped_data, KM_USER0); + + /* + * Do we need to do a data copy? + */ + if (need_copy_out && !done_copy_out) { + char *tmp; + + jbd_unlock_bh_state(bh_in); + tmp = jbd2_slab_alloc(bh_in->b_size, GFP_NOFS); + jbd_lock_bh_state(bh_in); + if (jh_in->b_frozen_data) { + jbd2_slab_free(tmp, bh_in->b_size); + goto repeat; + } + + jh_in->b_frozen_data = tmp; + mapped_data = kmap_atomic(new_page, KM_USER0); + memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size); + kunmap_atomic(mapped_data, KM_USER0); + + new_page = virt_to_page(tmp); + new_offset = offset_in_page(tmp); + done_copy_out = 1; + } + + /* + * Did we need to do an escaping? Now we've done all the + * copying, we can finally do so. + */ + if (do_escape) { + mapped_data = kmap_atomic(new_page, KM_USER0); + *((unsigned int *)(mapped_data + new_offset)) = 0; + kunmap_atomic(mapped_data, KM_USER0); + } + + /* keep subsequent assertions sane */ + new_bh->b_state = 0; + init_buffer(new_bh, NULL, NULL); + atomic_set(&new_bh->b_count, 1); + jbd_unlock_bh_state(bh_in); + + new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */ + + set_bh_page(new_bh, new_page, new_offset); + new_jh->b_transaction = NULL; + new_bh->b_size = jh2bh(jh_in)->b_size; + new_bh->b_bdev = transaction->t_journal->j_dev; + new_bh->b_blocknr = blocknr; + set_buffer_mapped(new_bh); + set_buffer_dirty(new_bh); + + *jh_out = new_jh; + + /* + * The to-be-written buffer needs to get moved to the io queue, + * and the original buffer whose contents we are shadowing or + * copying is moved to the transaction's shadow queue. + */ + JBUFFER_TRACE(jh_in, "file as BJ_Shadow"); + jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow); + JBUFFER_TRACE(new_jh, "file as BJ_IO"); + jbd2_journal_file_buffer(new_jh, transaction, BJ_IO); + + return do_escape | (done_copy_out << 1); +} + +/* + * Allocation code for the journal file. Manage the space left in the + * journal, so that we can begin checkpointing when appropriate. + */ + +/* + * __jbd2_log_space_left: Return the number of free blocks left in the journal. + * + * Called with the journal already locked. + * + * Called under j_state_lock + */ + +int __jbd2_log_space_left(journal_t *journal) +{ + int left = journal->j_free; + + assert_spin_locked(&journal->j_state_lock); + + /* + * Be pessimistic here about the number of those free blocks which + * might be required for log descriptor control blocks. + */ + +#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */ + + left -= MIN_LOG_RESERVED_BLOCKS; + + if (left <= 0) + return 0; + left -= (left >> 3); + return left; +} + +/* + * Called under j_state_lock. Returns true if a transaction was started. + */ +int __jbd2_log_start_commit(journal_t *journal, tid_t target) +{ + /* + * Are we already doing a recent enough commit? + */ + if (!tid_geq(journal->j_commit_request, target)) { + /* + * We want a new commit: OK, mark the request and wakup the + * commit thread. We do _not_ do the commit ourselves. + */ + + journal->j_commit_request = target; + jbd_debug(1, "JBD: requesting commit %d/%d\n", + journal->j_commit_request, + journal->j_commit_sequence); + wake_up(&journal->j_wait_commit); + return 1; + } + return 0; +} + +int jbd2_log_start_commit(journal_t *journal, tid_t tid) +{ + int ret; + + spin_lock(&journal->j_state_lock); + ret = __jbd2_log_start_commit(journal, tid); + spin_unlock(&journal->j_state_lock); + return ret; +} + +/* + * Force and wait upon a commit if the calling process is not within + * transaction. This is used for forcing out undo-protected data which contains + * bitmaps, when the fs is running out of space. + * + * We can only force the running transaction if we don't have an active handle; + * otherwise, we will deadlock. + * + * Returns true if a transaction was started. + */ +int jbd2_journal_force_commit_nested(journal_t *journal) +{ + transaction_t *transaction = NULL; + tid_t tid; + + spin_lock(&journal->j_state_lock); + if (journal->j_running_transaction && !current->journal_info) { + transaction = journal->j_running_transaction; + __jbd2_log_start_commit(journal, transaction->t_tid); + } else if (journal->j_committing_transaction) + transaction = journal->j_committing_transaction; + + if (!transaction) { + spin_unlock(&journal->j_state_lock); + return 0; /* Nothing to retry */ + } + + tid = transaction->t_tid; + spin_unlock(&journal->j_state_lock); + jbd2_log_wait_commit(journal, tid); + return 1; +} + +/* + * Start a commit of the current running transaction (if any). Returns true + * if a transaction was started, and fills its tid in at *ptid + */ +int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) +{ + int ret = 0; + + spin_lock(&journal->j_state_lock); + if (journal->j_running_transaction) { + tid_t tid = journal->j_running_transaction->t_tid; + + ret = __jbd2_log_start_commit(journal, tid); + if (ret && ptid) + *ptid = tid; + } else if (journal->j_committing_transaction && ptid) { + /* + * If ext3_write_super() recently started a commit, then we + * have to wait for completion of that transaction + */ + *ptid = journal->j_committing_transaction->t_tid; + ret = 1; + } + spin_unlock(&journal->j_state_lock); + return ret; +} + +/* + * Wait for a specified commit to complete. + * The caller may not hold the journal lock. + */ +int jbd2_log_wait_commit(journal_t *journal, tid_t tid) +{ + int err = 0; + +#ifdef CONFIG_JBD_DEBUG + spin_lock(&journal->j_state_lock); + if (!tid_geq(journal->j_commit_request, tid)) { + printk(KERN_EMERG + "%s: error: j_commit_request=%d, tid=%d\n", + __FUNCTION__, journal->j_commit_request, tid); + } + spin_unlock(&journal->j_state_lock); +#endif + spin_lock(&journal->j_state_lock); + while (tid_gt(tid, journal->j_commit_sequence)) { + jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n", + tid, journal->j_commit_sequence); + wake_up(&journal->j_wait_commit); + spin_unlock(&journal->j_state_lock); + wait_event(journal->j_wait_done_commit, + !tid_gt(tid, journal->j_commit_sequence)); + spin_lock(&journal->j_state_lock); + } + spin_unlock(&journal->j_state_lock); + + if (unlikely(is_journal_aborted(journal))) { + printk(KERN_EMERG "journal commit I/O error\n"); + err = -EIO; + } + return err; +} + +/* + * Log buffer allocation routines: + */ + +int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp) +{ + unsigned long blocknr; + + spin_lock(&journal->j_state_lock); + J_ASSERT(journal->j_free > 1); + + blocknr = journal->j_head; + journal->j_head++; + journal->j_free--; + if (journal->j_head == journal->j_last) + journal->j_head = journal->j_first; + spin_unlock(&journal->j_state_lock); + return jbd2_journal_bmap(journal, blocknr, retp); +} + +/* + * Conversion of logical to physical block numbers for the journal + * + * On external journals the journal blocks are identity-mapped, so + * this is a no-op. If needed, we can use j_blk_offset - everything is + * ready. + */ +int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, + unsigned long long *retp) +{ + int err = 0; + unsigned long long ret; + + if (journal->j_inode) { + ret = bmap(journal->j_inode, blocknr); + if (ret) + *retp = ret; + else { + char b[BDEVNAME_SIZE]; + + printk(KERN_ALERT "%s: journal block not found " + "at offset %lu on %s\n", + __FUNCTION__, + blocknr, + bdevname(journal->j_dev, b)); + err = -EIO; + __journal_abort_soft(journal, err); + } + } else { + *retp = blocknr; /* +journal->j_blk_offset */ + } + return err; +} + +/* + * We play buffer_head aliasing tricks to write data/metadata blocks to + * the journal without copying their contents, but for journal + * descriptor blocks we do need to generate bona fide buffers. + * + * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying + * the buffer's contents they really should run flush_dcache_page(bh->b_page). + * But we don't bother doing that, so there will be coherency problems with + * mmaps of blockdevs which hold live JBD-controlled filesystems. + */ +struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal) +{ + struct buffer_head *bh; + unsigned long long blocknr; + int err; + + err = jbd2_journal_next_log_block(journal, &blocknr); + + if (err) + return NULL; + + bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + lock_buffer(bh); + memset(bh->b_data, 0, journal->j_blocksize); + set_buffer_uptodate(bh); + unlock_buffer(bh); + BUFFER_TRACE(bh, "return this buffer"); + return jbd2_journal_add_journal_head(bh); +} + +/* + * Management for journal control blocks: functions to create and + * destroy journal_t structures, and to initialise and read existing + * journal blocks from disk. */ + +/* First: create and setup a journal_t object in memory. We initialise + * very few fields yet: that has to wait until we have created the + * journal structures from from scratch, or loaded them from disk. */ + +static journal_t * journal_init_common (void) +{ + journal_t *journal; + int err; + + journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL); + if (!journal) + goto fail; + memset(journal, 0, sizeof(*journal)); + + init_waitqueue_head(&journal->j_wait_transaction_locked); + init_waitqueue_head(&journal->j_wait_logspace); + init_waitqueue_head(&journal->j_wait_done_commit); + init_waitqueue_head(&journal->j_wait_checkpoint); + init_waitqueue_head(&journal->j_wait_commit); + init_waitqueue_head(&journal->j_wait_updates); + mutex_init(&journal->j_barrier); + mutex_init(&journal->j_checkpoint_mutex); + spin_lock_init(&journal->j_revoke_lock); + spin_lock_init(&journal->j_list_lock); + spin_lock_init(&journal->j_state_lock); + + journal->j_commit_interval = (HZ * JBD_DEFAULT_MAX_COMMIT_AGE); + + /* The journal is marked for error until we succeed with recovery! */ + journal->j_flags = JBD2_ABORT; + + /* Set up a default-sized revoke table for the new mount. */ + err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH); + if (err) { + kfree(journal); + goto fail; + } + return journal; +fail: + return NULL; +} + +/* jbd2_journal_init_dev and jbd2_journal_init_inode: + * + * Create a journal structure assigned some fixed set of disk blocks to + * the journal. We don't actually touch those disk blocks yet, but we + * need to set up all of the mapping information to tell the journaling + * system where the journal blocks are. + * + */ + +/** + * journal_t * jbd2_journal_init_dev() - creates an initialises a journal structure + * @bdev: Block device on which to create the journal + * @fs_dev: Device which hold journalled filesystem for this journal. + * @start: Block nr Start of journal. + * @len: Length of the journal in blocks. + * @blocksize: blocksize of journalling device + * @returns: a newly created journal_t * + * + * jbd2_journal_init_dev creates a journal which maps a fixed contiguous + * range of blocks on an arbitrary block device. + * + */ +journal_t * jbd2_journal_init_dev(struct block_device *bdev, + struct block_device *fs_dev, + unsigned long long start, int len, int blocksize) +{ + journal_t *journal = journal_init_common(); + struct buffer_head *bh; + int n; + + if (!journal) + return NULL; + + /* journal descriptor can store up to n blocks -bzzz */ + journal->j_blocksize = blocksize; + n = journal->j_blocksize / sizeof(journal_block_tag_t); + journal->j_wbufsize = n; + journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL); + if (!journal->j_wbuf) { + printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n", + __FUNCTION__); + kfree(journal); + journal = NULL; + } + journal->j_dev = bdev; + journal->j_fs_dev = fs_dev; + journal->j_blk_offset = start; + journal->j_maxlen = len; + + bh = __getblk(journal->j_dev, start, journal->j_blocksize); + J_ASSERT(bh != NULL); + journal->j_sb_buffer = bh; + journal->j_superblock = (journal_superblock_t *)bh->b_data; + + return journal; +} + +/** + * journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode. + * @inode: An inode to create the journal in + * + * jbd2_journal_init_inode creates a journal which maps an on-disk inode as + * the journal. The inode must exist already, must support bmap() and + * must have all data blocks preallocated. + */ +journal_t * jbd2_journal_init_inode (struct inode *inode) +{ + struct buffer_head *bh; + journal_t *journal = journal_init_common(); + int err; + int n; + unsigned long long blocknr; + + if (!journal) + return NULL; + + journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev; + journal->j_inode = inode; + jbd_debug(1, + "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n", + journal, inode->i_sb->s_id, inode->i_ino, + (long long) inode->i_size, + inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); + + journal->j_maxlen = inode->i_size >> inode->i_sb->s_blocksize_bits; + journal->j_blocksize = inode->i_sb->s_blocksize; + + /* journal descriptor can store up to n blocks -bzzz */ + n = journal->j_blocksize / sizeof(journal_block_tag_t); + journal->j_wbufsize = n; + journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL); + if (!journal->j_wbuf) { + printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n", + __FUNCTION__); + kfree(journal); + return NULL; + } + + err = jbd2_journal_bmap(journal, 0, &blocknr); + /* If that failed, give up */ + if (err) { + printk(KERN_ERR "%s: Cannnot locate journal superblock\n", + __FUNCTION__); + kfree(journal); + return NULL; + } + + bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + J_ASSERT(bh != NULL); + journal->j_sb_buffer = bh; + journal->j_superblock = (journal_superblock_t *)bh->b_data; + + return journal; +} + +/* + * If the journal init or create aborts, we need to mark the journal + * superblock as being NULL to prevent the journal destroy from writing + * back a bogus superblock. + */ +static void journal_fail_superblock (journal_t *journal) +{ + struct buffer_head *bh = journal->j_sb_buffer; + brelse(bh); + journal->j_sb_buffer = NULL; +} + +/* + * Given a journal_t structure, initialise the various fields for + * startup of a new journaling session. We use this both when creating + * a journal, and after recovering an old journal to reset it for + * subsequent use. + */ + +static int journal_reset(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + unsigned long long first, last; + + first = be32_to_cpu(sb->s_first); + last = be32_to_cpu(sb->s_maxlen); + + journal->j_first = first; + journal->j_last = last; + + journal->j_head = first; + journal->j_tail = first; + journal->j_free = last - first; + + journal->j_tail_sequence = journal->j_transaction_sequence; + journal->j_commit_sequence = journal->j_transaction_sequence - 1; + journal->j_commit_request = journal->j_commit_sequence; + + journal->j_max_transaction_buffers = journal->j_maxlen / 4; + + /* Add the dynamic fields and write it to disk. */ + jbd2_journal_update_superblock(journal, 1); + jbd2_journal_start_thread(journal); + return 0; +} + +/** + * int jbd2_journal_create() - Initialise the new journal file + * @journal: Journal to create. This structure must have been initialised + * + * Given a journal_t structure which tells us which disk blocks we can + * use, create a new journal superblock and initialise all of the + * journal fields from scratch. + **/ +int jbd2_journal_create(journal_t *journal) +{ + unsigned long long blocknr; + struct buffer_head *bh; + journal_superblock_t *sb; + int i, err; + + if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) { + printk (KERN_ERR "Journal length (%d blocks) too short.\n", + journal->j_maxlen); + journal_fail_superblock(journal); + return -EINVAL; + } + + if (journal->j_inode == NULL) { + /* + * We don't know what block to start at! + */ + printk(KERN_EMERG + "%s: creation of journal on external device!\n", + __FUNCTION__); + BUG(); + } + + /* Zero out the entire journal on disk. We cannot afford to + have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */ + jbd_debug(1, "JBD: Zeroing out journal blocks...\n"); + for (i = 0; i < journal->j_maxlen; i++) { + err = jbd2_journal_bmap(journal, i, &blocknr); + if (err) + return err; + bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + lock_buffer(bh); + memset (bh->b_data, 0, journal->j_blocksize); + BUFFER_TRACE(bh, "marking dirty"); + mark_buffer_dirty(bh); + BUFFER_TRACE(bh, "marking uptodate"); + set_buffer_uptodate(bh); + unlock_buffer(bh); + __brelse(bh); + } + + sync_blockdev(journal->j_dev); + jbd_debug(1, "JBD: journal cleared.\n"); + + /* OK, fill in the initial static fields in the new superblock */ + sb = journal->j_superblock; + + sb->s_header.h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); + sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2); + + sb->s_blocksize = cpu_to_be32(journal->j_blocksize); + sb->s_maxlen = cpu_to_be32(journal->j_maxlen); + sb->s_first = cpu_to_be32(1); + + journal->j_transaction_sequence = 1; + + journal->j_flags &= ~JBD2_ABORT; + journal->j_format_version = 2; + + return journal_reset(journal); +} + +/** + * void jbd2_journal_update_superblock() - Update journal sb on disk. + * @journal: The journal to update. + * @wait: Set to '0' if you don't want to wait for IO completion. + * + * Update a journal's dynamic superblock fields and write it to disk, + * optionally waiting for the IO to complete. + */ +void jbd2_journal_update_superblock(journal_t *journal, int wait) +{ + journal_superblock_t *sb = journal->j_superblock; + struct buffer_head *bh = journal->j_sb_buffer; + + /* + * As a special case, if the on-disk copy is already marked as needing + * no recovery (s_start == 0) and there are no outstanding transactions + * in the filesystem, then we can safely defer the superblock update + * until the next commit by setting JBD2_FLUSHED. This avoids + * attempting a write to a potential-readonly device. + */ + if (sb->s_start == 0 && journal->j_tail_sequence == + journal->j_transaction_sequence) { + jbd_debug(1,"JBD: Skipping superblock update on recovered sb " + "(start %ld, seq %d, errno %d)\n", + journal->j_tail, journal->j_tail_sequence, + journal->j_errno); + goto out; + } + + spin_lock(&journal->j_state_lock); + jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n", + journal->j_tail, journal->j_tail_sequence, journal->j_errno); + + sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); + sb->s_start = cpu_to_be32(journal->j_tail); + sb->s_errno = cpu_to_be32(journal->j_errno); + spin_unlock(&journal->j_state_lock); + + BUFFER_TRACE(bh, "marking dirty"); + mark_buffer_dirty(bh); + if (wait) + sync_dirty_buffer(bh); + else + ll_rw_block(SWRITE, 1, &bh); + +out: + /* If we have just flushed the log (by marking s_start==0), then + * any future commit will have to be careful to update the + * superblock again to re-record the true start of the log. */ + + spin_lock(&journal->j_state_lock); + if (sb->s_start) + journal->j_flags &= ~JBD2_FLUSHED; + else + journal->j_flags |= JBD2_FLUSHED; + spin_unlock(&journal->j_state_lock); +} + +/* + * Read the superblock for a given journal, performing initial + * validation of the format. + */ + +static int journal_get_superblock(journal_t *journal) +{ + struct buffer_head *bh; + journal_superblock_t *sb; + int err = -EIO; + + bh = journal->j_sb_buffer; + + J_ASSERT(bh != NULL); + if (!buffer_uptodate(bh)) { + ll_rw_block(READ, 1, &bh); + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) { + printk (KERN_ERR + "JBD: IO error reading journal superblock\n"); + goto out; + } + } + + sb = journal->j_superblock; + + err = -EINVAL; + + if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) || + sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) { + printk(KERN_WARNING "JBD: no valid journal superblock found\n"); + goto out; + } + + switch(be32_to_cpu(sb->s_header.h_blocktype)) { + case JBD2_SUPERBLOCK_V1: + journal->j_format_version = 1; + break; + case JBD2_SUPERBLOCK_V2: + journal->j_format_version = 2; + break; + default: + printk(KERN_WARNING "JBD: unrecognised superblock format ID\n"); + goto out; + } + + if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen) + journal->j_maxlen = be32_to_cpu(sb->s_maxlen); + else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) { + printk (KERN_WARNING "JBD: journal file too short\n"); + goto out; + } + + return 0; + +out: + journal_fail_superblock(journal); + return err; +} + +/* + * Load the on-disk journal superblock and read the key fields into the + * journal_t. + */ + +static int load_superblock(journal_t *journal) +{ + int err; + journal_superblock_t *sb; + + err = journal_get_superblock(journal); + if (err) + return err; + + sb = journal->j_superblock; + + journal->j_tail_sequence = be32_to_cpu(sb->s_sequence); + journal->j_tail = be32_to_cpu(sb->s_start); + journal->j_first = be32_to_cpu(sb->s_first); + journal->j_last = be32_to_cpu(sb->s_maxlen); + journal->j_errno = be32_to_cpu(sb->s_errno); + + return 0; +} + + +/** + * int jbd2_journal_load() - Read journal from disk. + * @journal: Journal to act on. + * + * Given a journal_t structure which tells us which disk blocks contain + * a journal, read the journal from disk to initialise the in-memory + * structures. + */ +int jbd2_journal_load(journal_t *journal) +{ + int err; + journal_superblock_t *sb; + + err = load_superblock(journal); + if (err) + return err; + + sb = journal->j_superblock; + /* If this is a V2 superblock, then we have to check the + * features flags on it. */ + + if (journal->j_format_version >= 2) { + if ((sb->s_feature_ro_compat & + ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || + (sb->s_feature_incompat & + ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { + printk (KERN_WARNING + "JBD: Unrecognised features on journal\n"); + return -EINVAL; + } + } + + /* + * Create a slab for this blocksize + */ + err = jbd2_journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize)); + if (err) + return err; + + /* Let the recovery code check whether it needs to recover any + * data from the journal. */ + if (jbd2_journal_recover(journal)) + goto recovery_error; + + /* OK, we've finished with the dynamic journal bits: + * reinitialise the dynamic contents of the superblock in memory + * and reset them on disk. */ + if (journal_reset(journal)) + goto recovery_error; + + journal->j_flags &= ~JBD2_ABORT; + journal->j_flags |= JBD2_LOADED; + return 0; + +recovery_error: + printk (KERN_WARNING "JBD: recovery failed\n"); + return -EIO; +} + +/** + * void jbd2_journal_destroy() - Release a journal_t structure. + * @journal: Journal to act on. + * + * Release a journal_t structure once it is no longer in use by the + * journaled object. + */ +void jbd2_journal_destroy(journal_t *journal) +{ + /* Wait for the commit thread to wake up and die. */ + journal_kill_thread(journal); + + /* Force a final log commit */ + if (journal->j_running_transaction) + jbd2_journal_commit_transaction(journal); + + /* Force any old transactions to disk */ + + /* Totally anal locking here... */ + spin_lock(&journal->j_list_lock); + while (journal->j_checkpoint_transactions != NULL) { + spin_unlock(&journal->j_list_lock); + jbd2_log_do_checkpoint(journal); + spin_lock(&journal->j_list_lock); + } + + J_ASSERT(journal->j_running_transaction == NULL); + J_ASSERT(journal->j_committing_transaction == NULL); + J_ASSERT(journal->j_checkpoint_transactions == NULL); + spin_unlock(&journal->j_list_lock); + + /* We can now mark the journal as empty. */ + journal->j_tail = 0; + journal->j_tail_sequence = ++journal->j_transaction_sequence; + if (journal->j_sb_buffer) { + jbd2_journal_update_superblock(journal, 1); + brelse(journal->j_sb_buffer); + } + + if (journal->j_inode) + iput(journal->j_inode); + if (journal->j_revoke) + jbd2_journal_destroy_revoke(journal); + kfree(journal->j_wbuf); + kfree(journal); +} + + +/** + *int jbd2_journal_check_used_features () - Check if features specified are used. + * @journal: Journal to check. + * @compat: bitmask of compatible features + * @ro: bitmask of features that force read-only mount + * @incompat: bitmask of incompatible features + * + * Check whether the journal uses all of a given set of + * features. Return true (non-zero) if it does. + **/ + +int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, + unsigned long ro, unsigned long incompat) +{ + journal_superblock_t *sb; + + if (!compat && !ro && !incompat) + return 1; + if (journal->j_format_version == 1) + return 0; + + sb = journal->j_superblock; + + if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) && + ((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) && + ((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat)) + return 1; + + return 0; +} + +/** + * int jbd2_journal_check_available_features() - Check feature set in journalling layer + * @journal: Journal to check. + * @compat: bitmask of compatible features + * @ro: bitmask of features that force read-only mount + * @incompat: bitmask of incompatible features + * + * Check whether the journaling code supports the use of + * all of a given set of features on this journal. Return true + * (non-zero) if it can. */ + +int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat, + unsigned long ro, unsigned long incompat) +{ + journal_superblock_t *sb; + + if (!compat && !ro && !incompat) + return 1; + + sb = journal->j_superblock; + + /* We can support any known requested features iff the + * superblock is in version 2. Otherwise we fail to support any + * extended sb features. */ + + if (journal->j_format_version != 2) + return 0; + + if ((compat & JBD2_KNOWN_COMPAT_FEATURES) == compat && + (ro & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro && + (incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat) + return 1; + + return 0; +} + +/** + * int jbd2_journal_set_features () - Mark a given journal feature in the superblock + * @journal: Journal to act on. + * @compat: bitmask of compatible features + * @ro: bitmask of features that force read-only mount + * @incompat: bitmask of incompatible features + * + * Mark a given journal feature as present on the + * superblock. Returns true if the requested features could be set. + * + */ + +int jbd2_journal_set_features (journal_t *journal, unsigned long compat, + unsigned long ro, unsigned long incompat) +{ + journal_superblock_t *sb; + + if (jbd2_journal_check_used_features(journal, compat, ro, incompat)) + return 1; + + if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) + return 0; + + jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", + compat, ro, incompat); + + sb = journal->j_superblock; + + sb->s_feature_compat |= cpu_to_be32(compat); + sb->s_feature_ro_compat |= cpu_to_be32(ro); + sb->s_feature_incompat |= cpu_to_be32(incompat); + + return 1; +} + + +/** + * int jbd2_journal_update_format () - Update on-disk journal structure. + * @journal: Journal to act on. + * + * Given an initialised but unloaded journal struct, poke about in the + * on-disk structure to update it to the most recent supported version. + */ +int jbd2_journal_update_format (journal_t *journal) +{ + journal_superblock_t *sb; + int err; + + err = journal_get_superblock(journal); + if (err) + return err; + + sb = journal->j_superblock; + + switch (be32_to_cpu(sb->s_header.h_blocktype)) { + case JBD2_SUPERBLOCK_V2: + return 0; + case JBD2_SUPERBLOCK_V1: + return journal_convert_superblock_v1(journal, sb); + default: + break; + } + return -EINVAL; +} + +static int journal_convert_superblock_v1(journal_t *journal, + journal_superblock_t *sb) +{ + int offset, blocksize; + struct buffer_head *bh; + + printk(KERN_WARNING + "JBD: Converting superblock from version 1 to 2.\n"); + + /* Pre-initialise new fields to zero */ + offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb); + blocksize = be32_to_cpu(sb->s_blocksize); + memset(&sb->s_feature_compat, 0, blocksize-offset); + + sb->s_nr_users = cpu_to_be32(1); + sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2); + journal->j_format_version = 2; + + bh = journal->j_sb_buffer; + BUFFER_TRACE(bh, "marking dirty"); + mark_buffer_dirty(bh); + sync_dirty_buffer(bh); + return 0; +} + + +/** + * int jbd2_journal_flush () - Flush journal + * @journal: Journal to act on. + * + * Flush all data for a given journal to disk and empty the journal. + * Filesystems can use this when remounting readonly to ensure that + * recovery does not need to happen on remount. + */ + +int jbd2_journal_flush(journal_t *journal) +{ + int err = 0; + transaction_t *transaction = NULL; + unsigned long old_tail; + + spin_lock(&journal->j_state_lock); + + /* Force everything buffered to the log... */ + if (journal->j_running_transaction) { + transaction = journal->j_running_transaction; + __jbd2_log_start_commit(journal, transaction->t_tid); + } else if (journal->j_committing_transaction) + transaction = journal->j_committing_transaction; + + /* Wait for the log commit to complete... */ + if (transaction) { + tid_t tid = transaction->t_tid; + + spin_unlock(&journal->j_state_lock); + jbd2_log_wait_commit(journal, tid); + } else { + spin_unlock(&journal->j_state_lock); + } + + /* ...and flush everything in the log out to disk. */ + spin_lock(&journal->j_list_lock); + while (!err && journal->j_checkpoint_transactions != NULL) { + spin_unlock(&journal->j_list_lock); + err = jbd2_log_do_checkpoint(journal); + spin_lock(&journal->j_list_lock); + } + spin_unlock(&journal->j_list_lock); + jbd2_cleanup_journal_tail(journal); + + /* Finally, mark the journal as really needing no recovery. + * This sets s_start==0 in the underlying superblock, which is + * the magic code for a fully-recovered superblock. Any future + * commits of data to the journal will restore the current + * s_start value. */ + spin_lock(&journal->j_state_lock); + old_tail = journal->j_tail; + journal->j_tail = 0; + spin_unlock(&journal->j_state_lock); + jbd2_journal_update_superblock(journal, 1); + spin_lock(&journal->j_state_lock); + journal->j_tail = old_tail; + + J_ASSERT(!journal->j_running_transaction); + J_ASSERT(!journal->j_committing_transaction); + J_ASSERT(!journal->j_checkpoint_transactions); + J_ASSERT(journal->j_head == journal->j_tail); + J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence); + spin_unlock(&journal->j_state_lock); + return err; +} + +/** + * int jbd2_journal_wipe() - Wipe journal contents + * @journal: Journal to act on. + * @write: flag (see below) + * + * Wipe out all of the contents of a journal, safely. This will produce + * a warning if the journal contains any valid recovery information. + * Must be called between journal_init_*() and jbd2_journal_load(). + * + * If 'write' is non-zero, then we wipe out the journal on disk; otherwise + * we merely suppress recovery. + */ + +int jbd2_journal_wipe(journal_t *journal, int write) +{ + journal_superblock_t *sb; + int err = 0; + + J_ASSERT (!(journal->j_flags & JBD2_LOADED)); + + err = load_superblock(journal); + if (err) + return err; + + sb = journal->j_superblock; + + if (!journal->j_tail) + goto no_recovery; + + printk (KERN_WARNING "JBD: %s recovery information on journal\n", + write ? "Clearing" : "Ignoring"); + + err = jbd2_journal_skip_recovery(journal); + if (write) + jbd2_journal_update_superblock(journal, 1); + + no_recovery: + return err; +} + +/* + * journal_dev_name: format a character string to describe on what + * device this journal is present. + */ + +static const char *journal_dev_name(journal_t *journal, char *buffer) +{ + struct block_device *bdev; + + if (journal->j_inode) + bdev = journal->j_inode->i_sb->s_bdev; + else + bdev = journal->j_dev; + + return bdevname(bdev, buffer); +} + +/* + * Journal abort has very specific semantics, which we describe + * for journal abort. + * + * Two internal function, which provide abort to te jbd layer + * itself are here. + */ + +/* + * Quick version for internal journal use (doesn't lock the journal). + * Aborts hard --- we mark the abort as occurred, but do _nothing_ else, + * and don't attempt to make any other journal updates. + */ +void __jbd2_journal_abort_hard(journal_t *journal) +{ + transaction_t *transaction; + char b[BDEVNAME_SIZE]; + + if (journal->j_flags & JBD2_ABORT) + return; + + printk(KERN_ERR "Aborting journal on device %s.\n", + journal_dev_name(journal, b)); + + spin_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_ABORT; + transaction = journal->j_running_transaction; + if (transaction) + __jbd2_log_start_commit(journal, transaction->t_tid); + spin_unlock(&journal->j_state_lock); +} + +/* Soft abort: record the abort error status in the journal superblock, + * but don't do any other IO. */ +static void __journal_abort_soft (journal_t *journal, int errno) +{ + if (journal->j_flags & JBD2_ABORT) + return; + + if (!journal->j_errno) + journal->j_errno = errno; + + __jbd2_journal_abort_hard(journal); + + if (errno) + jbd2_journal_update_superblock(journal, 1); +} + +/** + * void jbd2_journal_abort () - Shutdown the journal immediately. + * @journal: the journal to shutdown. + * @errno: an error number to record in the journal indicating + * the reason for the shutdown. + * + * Perform a complete, immediate shutdown of the ENTIRE + * journal (not of a single transaction). This operation cannot be + * undone without closing and reopening the journal. + * + * The jbd2_journal_abort function is intended to support higher level error + * recovery mechanisms such as the ext2/ext3 remount-readonly error + * mode. + * + * Journal abort has very specific semantics. Any existing dirty, + * unjournaled buffers in the main filesystem will still be written to + * disk by bdflush, but the journaling mechanism will be suspended + * immediately and no further transaction commits will be honoured. + * + * Any dirty, journaled buffers will be written back to disk without + * hitting the journal. Atomicity cannot be guaranteed on an aborted + * filesystem, but we _do_ attempt to leave as much data as possible + * behind for fsck to use for cleanup. + * + * Any attempt to get a new transaction handle on a journal which is in + * ABORT state will just result in an -EROFS error return. A + * jbd2_journal_stop on an existing handle will return -EIO if we have + * entered abort state during the update. + * + * Recursive transactions are not disturbed by journal abort until the + * final jbd2_journal_stop, which will receive the -EIO error. + * + * Finally, the jbd2_journal_abort call allows the caller to supply an errno + * which will be recorded (if possible) in the journal superblock. This + * allows a client to record failure conditions in the middle of a + * transaction without having to complete the transaction to record the + * failure to disk. ext3_error, for example, now uses this + * functionality. + * + * Errors which originate from within the journaling layer will NOT + * supply an errno; a null errno implies that absolutely no further + * writes are done to the journal (unless there are any already in + * progress). + * + */ + +void jbd2_journal_abort(journal_t *journal, int errno) +{ + __journal_abort_soft(journal, errno); +} + +/** + * int jbd2_journal_errno () - returns the journal's error state. + * @journal: journal to examine. + * + * This is the errno numbet set with jbd2_journal_abort(), the last + * time the journal was mounted - if the journal was stopped + * without calling abort this will be 0. + * + * If the journal has been aborted on this mount time -EROFS will + * be returned. + */ +int jbd2_journal_errno(journal_t *journal) +{ + int err; + + spin_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) + err = -EROFS; + else + err = journal->j_errno; + spin_unlock(&journal->j_state_lock); + return err; +} + +/** + * int jbd2_journal_clear_err () - clears the journal's error state + * @journal: journal to act on. + * + * An error must be cleared or Acked to take a FS out of readonly + * mode. + */ +int jbd2_journal_clear_err(journal_t *journal) +{ + int err = 0; + + spin_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) + err = -EROFS; + else + journal->j_errno = 0; + spin_unlock(&journal->j_state_lock); + return err; +} + +/** + * void jbd2_journal_ack_err() - Ack journal err. + * @journal: journal to act on. + * + * An error must be cleared or Acked to take a FS out of readonly + * mode. + */ +void jbd2_journal_ack_err(journal_t *journal) +{ + spin_lock(&journal->j_state_lock); + if (journal->j_errno) + journal->j_flags |= JBD2_ACK_ERR; + spin_unlock(&journal->j_state_lock); +} + +int jbd2_journal_blocks_per_page(struct inode *inode) +{ + return 1 << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); +} + +/* + * helper functions to deal with 32 or 64bit block numbers. + */ +size_t journal_tag_bytes(journal_t *journal) +{ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) + return JBD_TAG_SIZE64; + else + return JBD_TAG_SIZE32; +} + +/* + * Simple support for retrying memory allocations. Introduced to help to + * debug different VM deadlock avoidance strategies. + */ +void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry) +{ + return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0)); +} + +/* + * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed + * and allocate frozen and commit buffers from these slabs. + * + * Reason for doing this is to avoid, SLAB_DEBUG - since it could + * cause bh to cross page boundary. + */ + +#define JBD_MAX_SLABS 5 +#define JBD_SLAB_INDEX(size) (size >> 11) + +static kmem_cache_t *jbd_slab[JBD_MAX_SLABS]; +static const char *jbd_slab_names[JBD_MAX_SLABS] = { + "jbd2_1k", "jbd2_2k", "jbd2_4k", NULL, "jbd2_8k" +}; + +static void jbd2_journal_destroy_jbd_slabs(void) +{ + int i; + + for (i = 0; i < JBD_MAX_SLABS; i++) { + if (jbd_slab[i]) + kmem_cache_destroy(jbd_slab[i]); + jbd_slab[i] = NULL; + } +} + +static int jbd2_journal_create_jbd_slab(size_t slab_size) +{ + int i = JBD_SLAB_INDEX(slab_size); + + BUG_ON(i >= JBD_MAX_SLABS); + + /* + * Check if we already have a slab created for this size + */ + if (jbd_slab[i]) + return 0; + + /* + * Create a slab and force alignment to be same as slabsize - + * this will make sure that allocations won't cross the page + * boundary. + */ + jbd_slab[i] = kmem_cache_create(jbd_slab_names[i], + slab_size, slab_size, 0, NULL, NULL); + if (!jbd_slab[i]) { + printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n"); + return -ENOMEM; + } + return 0; +} + +void * jbd2_slab_alloc(size_t size, gfp_t flags) +{ + int idx; + + idx = JBD_SLAB_INDEX(size); + BUG_ON(jbd_slab[idx] == NULL); + return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL); +} + +void jbd2_slab_free(void *ptr, size_t size) +{ + int idx; + + idx = JBD_SLAB_INDEX(size); + BUG_ON(jbd_slab[idx] == NULL); + kmem_cache_free(jbd_slab[idx], ptr); +} + +/* + * Journal_head storage management + */ +static kmem_cache_t *jbd2_journal_head_cache; +#ifdef CONFIG_JBD_DEBUG +static atomic_t nr_journal_heads = ATOMIC_INIT(0); +#endif + +static int journal_init_jbd2_journal_head_cache(void) +{ + int retval; + + J_ASSERT(jbd2_journal_head_cache == 0); + jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head", + sizeof(struct journal_head), + 0, /* offset */ + 0, /* flags */ + NULL, /* ctor */ + NULL); /* dtor */ + retval = 0; + if (jbd2_journal_head_cache == 0) { + retval = -ENOMEM; + printk(KERN_EMERG "JBD: no memory for journal_head cache\n"); + } + return retval; +} + +static void jbd2_journal_destroy_jbd2_journal_head_cache(void) +{ + J_ASSERT(jbd2_journal_head_cache != NULL); + kmem_cache_destroy(jbd2_journal_head_cache); + jbd2_journal_head_cache = NULL; +} + +/* + * journal_head splicing and dicing + */ +static struct journal_head *journal_alloc_journal_head(void) +{ + struct journal_head *ret; + static unsigned long last_warning; + +#ifdef CONFIG_JBD_DEBUG + atomic_inc(&nr_journal_heads); +#endif + ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS); + if (ret == 0) { + jbd_debug(1, "out of memory for journal_head\n"); + if (time_after(jiffies, last_warning + 5*HZ)) { + printk(KERN_NOTICE "ENOMEM in %s, retrying.\n", + __FUNCTION__); + last_warning = jiffies; + } + while (ret == 0) { + yield(); + ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS); + } + } + return ret; +} + +static void journal_free_journal_head(struct journal_head *jh) +{ +#ifdef CONFIG_JBD_DEBUG + atomic_dec(&nr_journal_heads); + memset(jh, JBD_POISON_FREE, sizeof(*jh)); +#endif + kmem_cache_free(jbd2_journal_head_cache, jh); +} + +/* + * A journal_head is attached to a buffer_head whenever JBD has an + * interest in the buffer. + * + * Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit + * is set. This bit is tested in core kernel code where we need to take + * JBD-specific actions. Testing the zeroness of ->b_private is not reliable + * there. + * + * When a buffer has its BH_JBD bit set, its ->b_count is elevated by one. + * + * When a buffer has its BH_JBD bit set it is immune from being released by + * core kernel code, mainly via ->b_count. + * + * A journal_head may be detached from its buffer_head when the journal_head's + * b_transaction, b_cp_transaction and b_next_transaction pointers are NULL. + * Various places in JBD call jbd2_journal_remove_journal_head() to indicate that the + * journal_head can be dropped if needed. + * + * Various places in the kernel want to attach a journal_head to a buffer_head + * _before_ attaching the journal_head to a transaction. To protect the + * journal_head in this situation, jbd2_journal_add_journal_head elevates the + * journal_head's b_jcount refcount by one. The caller must call + * jbd2_journal_put_journal_head() to undo this. + * + * So the typical usage would be: + * + * (Attach a journal_head if needed. Increments b_jcount) + * struct journal_head *jh = jbd2_journal_add_journal_head(bh); + * ... + * jh->b_transaction = xxx; + * jbd2_journal_put_journal_head(jh); + * + * Now, the journal_head's b_jcount is zero, but it is safe from being released + * because it has a non-zero b_transaction. + */ + +/* + * Give a buffer_head a journal_head. + * + * Doesn't need the journal lock. + * May sleep. + */ +struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) +{ + struct journal_head *jh; + struct journal_head *new_jh = NULL; + +repeat: + if (!buffer_jbd(bh)) { + new_jh = journal_alloc_journal_head(); + memset(new_jh, 0, sizeof(*new_jh)); + } + + jbd_lock_bh_journal_head(bh); + if (buffer_jbd(bh)) { + jh = bh2jh(bh); + } else { + J_ASSERT_BH(bh, + (atomic_read(&bh->b_count) > 0) || + (bh->b_page && bh->b_page->mapping)); + + if (!new_jh) { + jbd_unlock_bh_journal_head(bh); + goto repeat; + } + + jh = new_jh; + new_jh = NULL; /* We consumed it */ + set_buffer_jbd(bh); + bh->b_private = jh; + jh->b_bh = bh; + get_bh(bh); + BUFFER_TRACE(bh, "added journal_head"); + } + jh->b_jcount++; + jbd_unlock_bh_journal_head(bh); + if (new_jh) + journal_free_journal_head(new_jh); + return bh->b_private; +} + +/* + * Grab a ref against this buffer_head's journal_head. If it ended up not + * having a journal_head, return NULL + */ +struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh) +{ + struct journal_head *jh = NULL; + + jbd_lock_bh_journal_head(bh); + if (buffer_jbd(bh)) { + jh = bh2jh(bh); + jh->b_jcount++; + } + jbd_unlock_bh_journal_head(bh); + return jh; +} + +static void __journal_remove_journal_head(struct buffer_head *bh) +{ + struct journal_head *jh = bh2jh(bh); + + J_ASSERT_JH(jh, jh->b_jcount >= 0); + + get_bh(bh); + if (jh->b_jcount == 0) { + if (jh->b_transaction == NULL && + jh->b_next_transaction == NULL && + jh->b_cp_transaction == NULL) { + J_ASSERT_JH(jh, jh->b_jlist == BJ_None); + J_ASSERT_BH(bh, buffer_jbd(bh)); + J_ASSERT_BH(bh, jh2bh(jh) == bh); + BUFFER_TRACE(bh, "remove journal_head"); + if (jh->b_frozen_data) { + printk(KERN_WARNING "%s: freeing " + "b_frozen_data\n", + __FUNCTION__); + jbd2_slab_free(jh->b_frozen_data, bh->b_size); + } + if (jh->b_committed_data) { + printk(KERN_WARNING "%s: freeing " + "b_committed_data\n", + __FUNCTION__); + jbd2_slab_free(jh->b_committed_data, bh->b_size); + } + bh->b_private = NULL; + jh->b_bh = NULL; /* debug, really */ + clear_buffer_jbd(bh); + __brelse(bh); + journal_free_journal_head(jh); + } else { + BUFFER_TRACE(bh, "journal_head was locked"); + } + } +} + +/* + * jbd2_journal_remove_journal_head(): if the buffer isn't attached to a transaction + * and has a zero b_jcount then remove and release its journal_head. If we did + * see that the buffer is not used by any transaction we also "logically" + * decrement ->b_count. + * + * We in fact take an additional increment on ->b_count as a convenience, + * because the caller usually wants to do additional things with the bh + * after calling here. + * The caller of jbd2_journal_remove_journal_head() *must* run __brelse(bh) at some + * time. Once the caller has run __brelse(), the buffer is eligible for + * reaping by try_to_free_buffers(). + */ +void jbd2_journal_remove_journal_head(struct buffer_head *bh) +{ + jbd_lock_bh_journal_head(bh); + __journal_remove_journal_head(bh); + jbd_unlock_bh_journal_head(bh); +} + +/* + * Drop a reference on the passed journal_head. If it fell to zero then try to + * release the journal_head from the buffer_head. + */ +void jbd2_journal_put_journal_head(struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + jbd_lock_bh_journal_head(bh); + J_ASSERT_JH(jh, jh->b_jcount > 0); + --jh->b_jcount; + if (!jh->b_jcount && !jh->b_transaction) { + __journal_remove_journal_head(bh); + __brelse(bh); + } + jbd_unlock_bh_journal_head(bh); +} + +/* + * /proc tunables + */ +#if defined(CONFIG_JBD_DEBUG) +int jbd2_journal_enable_debug; +EXPORT_SYMBOL(jbd2_journal_enable_debug); +#endif + +#if defined(CONFIG_JBD_DEBUG) && defined(CONFIG_PROC_FS) + +static struct proc_dir_entry *proc_jbd_debug; + +static int read_jbd_debug(char *page, char **start, off_t off, + int count, int *eof, void *data) +{ + int ret; + + ret = sprintf(page + off, "%d\n", jbd2_journal_enable_debug); + *eof = 1; + return ret; +} + +static int write_jbd_debug(struct file *file, const char __user *buffer, + unsigned long count, void *data) +{ + char buf[32]; + + if (count > ARRAY_SIZE(buf) - 1) + count = ARRAY_SIZE(buf) - 1; + if (copy_from_user(buf, buffer, count)) + return -EFAULT; + buf[ARRAY_SIZE(buf) - 1] = '\0'; + jbd2_journal_enable_debug = simple_strtoul(buf, NULL, 10); + return count; +} + +#define JBD_PROC_NAME "sys/fs/jbd2-debug" + +static void __init create_jbd_proc_entry(void) +{ + proc_jbd_debug = create_proc_entry(JBD_PROC_NAME, 0644, NULL); + if (proc_jbd_debug) { + /* Why is this so hard? */ + proc_jbd_debug->read_proc = read_jbd_debug; + proc_jbd_debug->write_proc = write_jbd_debug; + } +} + +static void __exit jbd2_remove_jbd_proc_entry(void) +{ + if (proc_jbd_debug) + remove_proc_entry(JBD_PROC_NAME, NULL); +} + +#else + +#define create_jbd_proc_entry() do {} while (0) +#define jbd2_remove_jbd_proc_entry() do {} while (0) + +#endif + +kmem_cache_t *jbd2_handle_cache; + +static int __init journal_init_handle_cache(void) +{ + jbd2_handle_cache = kmem_cache_create("jbd2_journal_handle", + sizeof(handle_t), + 0, /* offset */ + 0, /* flags */ + NULL, /* ctor */ + NULL); /* dtor */ + if (jbd2_handle_cache == NULL) { + printk(KERN_EMERG "JBD: failed to create handle cache\n"); + return -ENOMEM; + } + return 0; +} + +static void jbd2_journal_destroy_handle_cache(void) +{ + if (jbd2_handle_cache) + kmem_cache_destroy(jbd2_handle_cache); +} + +/* + * Module startup and shutdown + */ + +static int __init journal_init_caches(void) +{ + int ret; + + ret = jbd2_journal_init_revoke_caches(); + if (ret == 0) + ret = journal_init_jbd2_journal_head_cache(); + if (ret == 0) + ret = journal_init_handle_cache(); + return ret; +} + +static void jbd2_journal_destroy_caches(void) +{ + jbd2_journal_destroy_revoke_caches(); + jbd2_journal_destroy_jbd2_journal_head_cache(); + jbd2_journal_destroy_handle_cache(); + jbd2_journal_destroy_jbd_slabs(); +} + +static int __init journal_init(void) +{ + int ret; + + BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024); + + ret = journal_init_caches(); + if (ret != 0) + jbd2_journal_destroy_caches(); + create_jbd_proc_entry(); + return ret; +} + +static void __exit journal_exit(void) +{ +#ifdef CONFIG_JBD_DEBUG + int n = atomic_read(&nr_journal_heads); + if (n) + printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n); +#endif + jbd2_remove_jbd_proc_entry(); + jbd2_journal_destroy_caches(); +} + +MODULE_LICENSE("GPL"); +module_init(journal_init); +module_exit(journal_exit); + diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c new file mode 100644 index 00000000000..9f10acafaf7 --- /dev/null +++ b/fs/jbd2/recovery.c @@ -0,0 +1,609 @@ +/* + * linux/fs/recovery.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 + * + * Copyright 1999-2000 Red Hat Software --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Journal recovery routines for the generic filesystem journaling code; + * part of the ext2fs journaling system. + */ + +#ifndef __KERNEL__ +#include "jfs_user.h" +#else +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#endif + +/* + * Maintain information about the progress of the recovery job, so that + * the different passes can carry information between them. + */ +struct recovery_info +{ + tid_t start_transaction; + tid_t end_transaction; + + int nr_replays; + int nr_revokes; + int nr_revoke_hits; +}; + +enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; +static int do_one_pass(journal_t *journal, + struct recovery_info *info, enum passtype pass); +static int scan_revoke_records(journal_t *, struct buffer_head *, + tid_t, struct recovery_info *); + +#ifdef __KERNEL__ + +/* Release readahead buffers after use */ +static void journal_brelse_array(struct buffer_head *b[], int n) +{ + while (--n >= 0) + brelse (b[n]); +} + + +/* + * When reading from the journal, we are going through the block device + * layer directly and so there is no readahead being done for us. We + * need to implement any readahead ourselves if we want it to happen at + * all. Recovery is basically one long sequential read, so make sure we + * do the IO in reasonably large chunks. + * + * This is not so critical that we need to be enormously clever about + * the readahead size, though. 128K is a purely arbitrary, good-enough + * fixed value. + */ + +#define MAXBUF 8 +static int do_readahead(journal_t *journal, unsigned int start) +{ + int err; + unsigned int max, nbufs, next; + unsigned long long blocknr; + struct buffer_head *bh; + + struct buffer_head * bufs[MAXBUF]; + + /* Do up to 128K of readahead */ + max = start + (128 * 1024 / journal->j_blocksize); + if (max > journal->j_maxlen) + max = journal->j_maxlen; + + /* Do the readahead itself. We'll submit MAXBUF buffer_heads at + * a time to the block device IO layer. */ + + nbufs = 0; + + for (next = start; next < max; next++) { + err = jbd2_journal_bmap(journal, next, &blocknr); + + if (err) { + printk (KERN_ERR "JBD: bad block at offset %u\n", + next); + goto failed; + } + + bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + if (!bh) { + err = -ENOMEM; + goto failed; + } + + if (!buffer_uptodate(bh) && !buffer_locked(bh)) { + bufs[nbufs++] = bh; + if (nbufs == MAXBUF) { + ll_rw_block(READ, nbufs, bufs); + journal_brelse_array(bufs, nbufs); + nbufs = 0; + } + } else + brelse(bh); + } + + if (nbufs) + ll_rw_block(READ, nbufs, bufs); + err = 0; + +failed: + if (nbufs) + journal_brelse_array(bufs, nbufs); + return err; +} + +#endif /* __KERNEL__ */ + + +/* + * Read a block from the journal + */ + +static int jread(struct buffer_head **bhp, journal_t *journal, + unsigned int offset) +{ + int err; + unsigned long long blocknr; + struct buffer_head *bh; + + *bhp = NULL; + + if (offset >= journal->j_maxlen) { + printk(KERN_ERR "JBD: corrupted journal superblock\n"); + return -EIO; + } + + err = jbd2_journal_bmap(journal, offset, &blocknr); + + if (err) { + printk (KERN_ERR "JBD: bad block at offset %u\n", + offset); + return err; + } + + bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + if (!bh) + return -ENOMEM; + + if (!buffer_uptodate(bh)) { + /* If this is a brand new buffer, start readahead. + Otherwise, we assume we are already reading it. */ + if (!buffer_req(bh)) + do_readahead(journal, offset); + wait_on_buffer(bh); + } + + if (!buffer_uptodate(bh)) { + printk (KERN_ERR "JBD: Failed to read block at offset %u\n", + offset); + brelse(bh); + return -EIO; + } + + *bhp = bh; + return 0; +} + + +/* + * Count the number of in-use tags in a journal descriptor block. + */ + +static int count_tags(journal_t *journal, struct buffer_head *bh) +{ + char * tagp; + journal_block_tag_t * tag; + int nr = 0, size = journal->j_blocksize; + int tag_bytes = journal_tag_bytes(journal); + + tagp = &bh->b_data[sizeof(journal_header_t)]; + + while ((tagp - bh->b_data + tag_bytes) <= size) { + tag = (journal_block_tag_t *) tagp; + + nr++; + tagp += tag_bytes; + if (!(tag->t_flags & cpu_to_be32(JBD2_FLAG_SAME_UUID))) + tagp += 16; + + if (tag->t_flags & cpu_to_be32(JBD2_FLAG_LAST_TAG)) + break; + } + + return nr; +} + + +/* Make sure we wrap around the log correctly! */ +#define wrap(journal, var) \ +do { \ + if (var >= (journal)->j_last) \ + var -= ((journal)->j_last - (journal)->j_first); \ +} while (0) + +/** + * jbd2_journal_recover - recovers a on-disk journal + * @journal: the journal to recover + * + * The primary function for recovering the log contents when mounting a + * journaled device. + * + * Recovery is done in three passes. In the first pass, we look for the + * end of the log. In the second, we assemble the list of revoke + * blocks. In the third and final pass, we replay any un-revoked blocks + * in the log. + */ +int jbd2_journal_recover(journal_t *journal) +{ + int err; + journal_superblock_t * sb; + + struct recovery_info info; + + memset(&info, 0, sizeof(info)); + sb = journal->j_superblock; + + /* + * The journal superblock's s_start field (the current log head) + * is always zero if, and only if, the journal was cleanly + * unmounted. + */ + + if (!sb->s_start) { + jbd_debug(1, "No recovery required, last transaction %d\n", + be32_to_cpu(sb->s_sequence)); + journal->j_transaction_sequence = be32_to_cpu(sb->s_sequence) + 1; + return 0; + } + + err = do_one_pass(journal, &info, PASS_SCAN); + if (!err) + err = do_one_pass(journal, &info, PASS_REVOKE); + if (!err) + err = do_one_pass(journal, &info, PASS_REPLAY); + + jbd_debug(0, "JBD: recovery, exit status %d, " + "recovered transactions %u to %u\n", + err, info.start_transaction, info.end_transaction); + jbd_debug(0, "JBD: Replayed %d and revoked %d/%d blocks\n", + info.nr_replays, info.nr_revoke_hits, info.nr_revokes); + + /* Restart the log at the next transaction ID, thus invalidating + * any existing commit records in the log. */ + journal->j_transaction_sequence = ++info.end_transaction; + + jbd2_journal_clear_revoke(journal); + sync_blockdev(journal->j_fs_dev); + return err; +} + +/** + * jbd2_journal_skip_recovery - Start journal and wipe exiting records + * @journal: journal to startup + * + * Locate any valid recovery information from the journal and set up the + * journal structures in memory to ignore it (presumably because the + * caller has evidence that it is out of date). + * This function does'nt appear to be exorted.. + * + * We perform one pass over the journal to allow us to tell the user how + * much recovery information is being erased, and to let us initialise + * the journal transaction sequence numbers to the next unused ID. + */ +int jbd2_journal_skip_recovery(journal_t *journal) +{ + int err; + journal_superblock_t * sb; + + struct recovery_info info; + + memset (&info, 0, sizeof(info)); + sb = journal->j_superblock; + + err = do_one_pass(journal, &info, PASS_SCAN); + + if (err) { + printk(KERN_ERR "JBD: error %d scanning journal\n", err); + ++journal->j_transaction_sequence; + } else { +#ifdef CONFIG_JBD_DEBUG + int dropped = info.end_transaction - be32_to_cpu(sb->s_sequence); +#endif + jbd_debug(0, + "JBD: ignoring %d transaction%s from the journal.\n", + dropped, (dropped == 1) ? "" : "s"); + journal->j_transaction_sequence = ++info.end_transaction; + } + + journal->j_tail = 0; + return err; +} + +static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag) +{ + unsigned long long block = be32_to_cpu(tag->t_blocknr); + if (tag_bytes > JBD_TAG_SIZE32) + block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32; + return block; +} + +static int do_one_pass(journal_t *journal, + struct recovery_info *info, enum passtype pass) +{ + unsigned int first_commit_ID, next_commit_ID; + unsigned long next_log_block; + int err, success = 0; + journal_superblock_t * sb; + journal_header_t * tmp; + struct buffer_head * bh; + unsigned int sequence; + int blocktype; + int tag_bytes = journal_tag_bytes(journal); + + /* Precompute the maximum metadata descriptors in a descriptor block */ + int MAX_BLOCKS_PER_DESC; + MAX_BLOCKS_PER_DESC = ((journal->j_blocksize-sizeof(journal_header_t)) + / tag_bytes); + + /* + * First thing is to establish what we expect to find in the log + * (in terms of transaction IDs), and where (in terms of log + * block offsets): query the superblock. + */ + + sb = journal->j_superblock; + next_commit_ID = be32_to_cpu(sb->s_sequence); + next_log_block = be32_to_cpu(sb->s_start); + + first_commit_ID = next_commit_ID; + if (pass == PASS_SCAN) + info->start_transaction = first_commit_ID; + + jbd_debug(1, "Starting recovery pass %d\n", pass); + + /* + * Now we walk through the log, transaction by transaction, + * making sure that each transaction has a commit block in the + * expected place. Each complete transaction gets replayed back + * into the main filesystem. + */ + + while (1) { + int flags; + char * tagp; + journal_block_tag_t * tag; + struct buffer_head * obh; + struct buffer_head * nbh; + + cond_resched(); /* We're under lock_kernel() */ + + /* If we already know where to stop the log traversal, + * check right now that we haven't gone past the end of + * the log. */ + + if (pass != PASS_SCAN) + if (tid_geq(next_commit_ID, info->end_transaction)) + break; + + jbd_debug(2, "Scanning for sequence ID %u at %lu/%lu\n", + next_commit_ID, next_log_block, journal->j_last); + + /* Skip over each chunk of the transaction looking + * either the next descriptor block or the final commit + * record. */ + + jbd_debug(3, "JBD: checking block %ld\n", next_log_block); + err = jread(&bh, journal, next_log_block); + if (err) + goto failed; + + next_log_block++; + wrap(journal, next_log_block); + + /* What kind of buffer is it? + * + * If it is a descriptor block, check that it has the + * expected sequence number. Otherwise, we're all done + * here. */ + + tmp = (journal_header_t *)bh->b_data; + + if (tmp->h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER)) { + brelse(bh); + break; + } + + blocktype = be32_to_cpu(tmp->h_blocktype); + sequence = be32_to_cpu(tmp->h_sequence); + jbd_debug(3, "Found magic %d, sequence %d\n", + blocktype, sequence); + + if (sequence != next_commit_ID) { + brelse(bh); + break; + } + + /* OK, we have a valid descriptor block which matches + * all of the sequence number checks. What are we going + * to do with it? That depends on the pass... */ + + switch(blocktype) { + case JBD2_DESCRIPTOR_BLOCK: + /* If it is a valid descriptor block, replay it + * in pass REPLAY; otherwise, just skip over the + * blocks it describes. */ + if (pass != PASS_REPLAY) { + next_log_block += count_tags(journal, bh); + wrap(journal, next_log_block); + brelse(bh); + continue; + } + + /* A descriptor block: we can now write all of + * the data blocks. Yay, useful work is finally + * getting done here! */ + + tagp = &bh->b_data[sizeof(journal_header_t)]; + while ((tagp - bh->b_data + tag_bytes) + <= journal->j_blocksize) { + unsigned long io_block; + + tag = (journal_block_tag_t *) tagp; + flags = be32_to_cpu(tag->t_flags); + + io_block = next_log_block++; + wrap(journal, next_log_block); + err = jread(&obh, journal, io_block); + if (err) { + /* Recover what we can, but + * report failure at the end. */ + success = err; + printk (KERN_ERR + "JBD: IO error %d recovering " + "block %ld in log\n", + err, io_block); + } else { + unsigned long long blocknr; + + J_ASSERT(obh != NULL); + blocknr = read_tag_block(tag_bytes, + tag); + + /* If the block has been + * revoked, then we're all done + * here. */ + if (jbd2_journal_test_revoke + (journal, blocknr, + next_commit_ID)) { + brelse(obh); + ++info->nr_revoke_hits; + goto skip_write; + } + + /* Find a buffer for the new + * data being restored */ + nbh = __getblk(journal->j_fs_dev, + blocknr, + journal->j_blocksize); + if (nbh == NULL) { + printk(KERN_ERR + "JBD: Out of memory " + "during recovery.\n"); + err = -ENOMEM; + brelse(bh); + brelse(obh); + goto failed; + } + + lock_buffer(nbh); + memcpy(nbh->b_data, obh->b_data, + journal->j_blocksize); + if (flags & JBD2_FLAG_ESCAPE) { + *((__be32 *)bh->b_data) = + cpu_to_be32(JBD2_MAGIC_NUMBER); + } + + BUFFER_TRACE(nbh, "marking dirty"); + set_buffer_uptodate(nbh); + mark_buffer_dirty(nbh); + BUFFER_TRACE(nbh, "marking uptodate"); + ++info->nr_replays; + /* ll_rw_block(WRITE, 1, &nbh); */ + unlock_buffer(nbh); + brelse(obh); + brelse(nbh); + } + + skip_write: + tagp += tag_bytes; + if (!(flags & JBD2_FLAG_SAME_UUID)) + tagp += 16; + + if (flags & JBD2_FLAG_LAST_TAG) + break; + } + + brelse(bh); + continue; + + case JBD2_COMMIT_BLOCK: + /* Found an expected commit block: not much to + * do other than move on to the next sequence + * number. */ + brelse(bh); + next_commit_ID++; + continue; + + case JBD2_REVOKE_BLOCK: + /* If we aren't in the REVOKE pass, then we can + * just skip over this block. */ + if (pass != PASS_REVOKE) { + brelse(bh); + continue; + } + + err = scan_revoke_records(journal, bh, + next_commit_ID, info); + brelse(bh); + if (err) + goto failed; + continue; + + default: + jbd_debug(3, "Unrecognised magic %d, end of scan.\n", + blocktype); + brelse(bh); + goto done; + } + } + + done: + /* + * We broke out of the log scan loop: either we came to the + * known end of the log or we found an unexpected block in the + * log. If the latter happened, then we know that the "current" + * transaction marks the end of the valid log. + */ + + if (pass == PASS_SCAN) + info->end_transaction = next_commit_ID; + else { + /* It's really bad news if different passes end up at + * different places (but possible due to IO errors). */ + if (info->end_transaction != next_commit_ID) { + printk (KERN_ERR "JBD: recovery pass %d ended at " + "transaction %u, expected %u\n", + pass, next_commit_ID, info->end_transaction); + if (!success) + success = -EIO; + } + } + + return success; + + failed: + return err; +} + + +/* Scan a revoke record, marking all blocks mentioned as revoked. */ + +static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, + tid_t sequence, struct recovery_info *info) +{ + jbd2_journal_revoke_header_t *header; + int offset, max; + int record_len = 4; + + header = (jbd2_journal_revoke_header_t *) bh->b_data; + offset = sizeof(jbd2_journal_revoke_header_t); + max = be32_to_cpu(header->r_count); + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) + record_len = 8; + + while (offset + record_len <= max) { + unsigned long long blocknr; + int err; + + if (record_len == 4) + blocknr = be32_to_cpu(* ((__be32 *) (bh->b_data+offset))); + else + blocknr = be64_to_cpu(* ((__be64 *) (bh->b_data+offset))); + offset += record_len; + err = jbd2_journal_set_revoke(journal, blocknr, sequence); + if (err) + return err; + ++info->nr_revokes; + } + return 0; +} diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c new file mode 100644 index 00000000000..380d19917f3 --- /dev/null +++ b/fs/jbd2/revoke.c @@ -0,0 +1,712 @@ +/* + * linux/fs/revoke.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 2000 + * + * Copyright 2000 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Journal revoke routines for the generic filesystem journaling code; + * part of the ext2fs journaling system. + * + * Revoke is the mechanism used to prevent old log records for deleted + * metadata from being replayed on top of newer data using the same + * blocks. The revoke mechanism is used in two separate places: + * + * + Commit: during commit we write the entire list of the current + * transaction's revoked blocks to the journal + * + * + Recovery: during recovery we record the transaction ID of all + * revoked blocks. If there are multiple revoke records in the log + * for a single block, only the last one counts, and if there is a log + * entry for a block beyond the last revoke, then that log entry still + * gets replayed. + * + * We can get interactions between revokes and new log data within a + * single transaction: + * + * Block is revoked and then journaled: + * The desired end result is the journaling of the new block, so we + * cancel the revoke before the transaction commits. + * + * Block is journaled and then revoked: + * The revoke must take precedence over the write of the block, so we + * need either to cancel the journal entry or to write the revoke + * later in the log than the log block. In this case, we choose the + * latter: journaling a block cancels any revoke record for that block + * in the current transaction, so any revoke for that block in the + * transaction must have happened after the block was journaled and so + * the revoke must take precedence. + * + * Block is revoked and then written as data: + * The data write is allowed to succeed, but the revoke is _not_ + * cancelled. We still need to prevent old log records from + * overwriting the new data. We don't even need to clear the revoke + * bit here. + * + * Revoke information on buffers is a tri-state value: + * + * RevokeValid clear: no cached revoke status, need to look it up + * RevokeValid set, Revoked clear: + * buffer has not been revoked, and cancel_revoke + * need do nothing. + * RevokeValid set, Revoked set: + * buffer has been revoked. + */ + +#ifndef __KERNEL__ +#include "jfs_user.h" +#else +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/smp_lock.h> +#include <linux/init.h> +#endif + +static kmem_cache_t *jbd2_revoke_record_cache; +static kmem_cache_t *jbd2_revoke_table_cache; + +/* Each revoke record represents one single revoked block. During + journal replay, this involves recording the transaction ID of the + last transaction to revoke this block. */ + +struct jbd2_revoke_record_s +{ + struct list_head hash; + tid_t sequence; /* Used for recovery only */ + unsigned long long blocknr; +}; + + +/* The revoke table is just a simple hash table of revoke records. */ +struct jbd2_revoke_table_s +{ + /* It is conceivable that we might want a larger hash table + * for recovery. Must be a power of two. */ + int hash_size; + int hash_shift; + struct list_head *hash_table; +}; + + +#ifdef __KERNEL__ +static void write_one_revoke_record(journal_t *, transaction_t *, + struct journal_head **, int *, + struct jbd2_revoke_record_s *); +static void flush_descriptor(journal_t *, struct journal_head *, int); +#endif + +/* Utility functions to maintain the revoke table */ + +/* Borrowed from buffer.c: this is a tried and tested block hash function */ +static inline int hash(journal_t *journal, unsigned long long block) +{ + struct jbd2_revoke_table_s *table = journal->j_revoke; + int hash_shift = table->hash_shift; + int hash = (int)block ^ (int)((block >> 31) >> 1); + + return ((hash << (hash_shift - 6)) ^ + (hash >> 13) ^ + (hash << (hash_shift - 12))) & (table->hash_size - 1); +} + +static int insert_revoke_hash(journal_t *journal, unsigned long long blocknr, + tid_t seq) +{ + struct list_head *hash_list; + struct jbd2_revoke_record_s *record; + +repeat: + record = kmem_cache_alloc(jbd2_revoke_record_cache, GFP_NOFS); + if (!record) + goto oom; + + record->sequence = seq; + record->blocknr = blocknr; + hash_list = &journal->j_revoke->hash_table[hash(journal, blocknr)]; + spin_lock(&journal->j_revoke_lock); + list_add(&record->hash, hash_list); + spin_unlock(&journal->j_revoke_lock); + return 0; + +oom: + if (!journal_oom_retry) + return -ENOMEM; + jbd_debug(1, "ENOMEM in %s, retrying\n", __FUNCTION__); + yield(); + goto repeat; +} + +/* Find a revoke record in the journal's hash table. */ + +static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal, + unsigned long long blocknr) +{ + struct list_head *hash_list; + struct jbd2_revoke_record_s *record; + + hash_list = &journal->j_revoke->hash_table[hash(journal, blocknr)]; + + spin_lock(&journal->j_revoke_lock); + record = (struct jbd2_revoke_record_s *) hash_list->next; + while (&(record->hash) != hash_list) { + if (record->blocknr == blocknr) { + spin_unlock(&journal->j_revoke_lock); + return record; + } + record = (struct jbd2_revoke_record_s *) record->hash.next; + } + spin_unlock(&journal->j_revoke_lock); + return NULL; +} + +int __init jbd2_journal_init_revoke_caches(void) +{ + jbd2_revoke_record_cache = kmem_cache_create("jbd2_revoke_record", + sizeof(struct jbd2_revoke_record_s), + 0, SLAB_HWCACHE_ALIGN, NULL, NULL); + if (jbd2_revoke_record_cache == 0) + return -ENOMEM; + + jbd2_revoke_table_cache = kmem_cache_create("jbd2_revoke_table", + sizeof(struct jbd2_revoke_table_s), + 0, 0, NULL, NULL); + if (jbd2_revoke_table_cache == 0) { + kmem_cache_destroy(jbd2_revoke_record_cache); + jbd2_revoke_record_cache = NULL; + return -ENOMEM; + } + return 0; +} + +void jbd2_journal_destroy_revoke_caches(void) +{ + kmem_cache_destroy(jbd2_revoke_record_cache); + jbd2_revoke_record_cache = NULL; + kmem_cache_destroy(jbd2_revoke_table_cache); + jbd2_revoke_table_cache = NULL; +} + +/* Initialise the revoke table for a given journal to a given size. */ + +int jbd2_journal_init_revoke(journal_t *journal, int hash_size) +{ + int shift, tmp; + + J_ASSERT (journal->j_revoke_table[0] == NULL); + + shift = 0; + tmp = hash_size; + while((tmp >>= 1UL) != 0UL) + shift++; + + journal->j_revoke_table[0] = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL); + if (!journal->j_revoke_table[0]) + return -ENOMEM; + journal->j_revoke = journal->j_revoke_table[0]; + + /* Check that the hash_size is a power of two */ + J_ASSERT ((hash_size & (hash_size-1)) == 0); + + journal->j_revoke->hash_size = hash_size; + + journal->j_revoke->hash_shift = shift; + + journal->j_revoke->hash_table = + kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL); + if (!journal->j_revoke->hash_table) { + kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]); + journal->j_revoke = NULL; + return -ENOMEM; + } + + for (tmp = 0; tmp < hash_size; tmp++) + INIT_LIST_HEAD(&journal->j_revoke->hash_table[tmp]); + + journal->j_revoke_table[1] = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL); + if (!journal->j_revoke_table[1]) { + kfree(journal->j_revoke_table[0]->hash_table); + kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]); + return -ENOMEM; + } + + journal->j_revoke = journal->j_revoke_table[1]; + + /* Check that the hash_size is a power of two */ + J_ASSERT ((hash_size & (hash_size-1)) == 0); + + journal->j_revoke->hash_size = hash_size; + + journal->j_revoke->hash_shift = shift; + + journal->j_revoke->hash_table = + kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL); + if (!journal->j_revoke->hash_table) { + kfree(journal->j_revoke_table[0]->hash_table); + kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]); + kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[1]); + journal->j_revoke = NULL; + return -ENOMEM; + } + + for (tmp = 0; tmp < hash_size; tmp++) + INIT_LIST_HEAD(&journal->j_revoke->hash_table[tmp]); + + spin_lock_init(&journal->j_revoke_lock); + + return 0; +} + +/* Destoy a journal's revoke table. The table must already be empty! */ + +void jbd2_journal_destroy_revoke(journal_t *journal) +{ + struct jbd2_revoke_table_s *table; + struct list_head *hash_list; + int i; + + table = journal->j_revoke_table[0]; + if (!table) + return; + + for (i=0; i<table->hash_size; i++) { + hash_list = &table->hash_table[i]; + J_ASSERT (list_empty(hash_list)); + } + + kfree(table->hash_table); + kmem_cache_free(jbd2_revoke_table_cache, table); + journal->j_revoke = NULL; + + table = journal->j_revoke_table[1]; + if (!table) + return; + + for (i=0; i<table->hash_size; i++) { + hash_list = &table->hash_table[i]; + J_ASSERT (list_empty(hash_list)); + } + + kfree(table->hash_table); + kmem_cache_free(jbd2_revoke_table_cache, table); + journal->j_revoke = NULL; +} + + +#ifdef __KERNEL__ + +/* + * jbd2_journal_revoke: revoke a given buffer_head from the journal. This + * prevents the block from being replayed during recovery if we take a + * crash after this current transaction commits. Any subsequent + * metadata writes of the buffer in this transaction cancel the + * revoke. + * + * Note that this call may block --- it is up to the caller to make + * sure that there are no further calls to journal_write_metadata + * before the revoke is complete. In ext3, this implies calling the + * revoke before clearing the block bitmap when we are deleting + * metadata. + * + * Revoke performs a jbd2_journal_forget on any buffer_head passed in as a + * parameter, but does _not_ forget the buffer_head if the bh was only + * found implicitly. + * + * bh_in may not be a journalled buffer - it may have come off + * the hash tables without an attached journal_head. + * + * If bh_in is non-zero, jbd2_journal_revoke() will decrement its b_count + * by one. + */ + +int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr, + struct buffer_head *bh_in) +{ + struct buffer_head *bh = NULL; + journal_t *journal; + struct block_device *bdev; + int err; + + might_sleep(); + if (bh_in) + BUFFER_TRACE(bh_in, "enter"); + + journal = handle->h_transaction->t_journal; + if (!jbd2_journal_set_features(journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)){ + J_ASSERT (!"Cannot set revoke feature!"); + return -EINVAL; + } + + bdev = journal->j_fs_dev; + bh = bh_in; + + if (!bh) { + bh = __find_get_block(bdev, blocknr, journal->j_blocksize); + if (bh) + BUFFER_TRACE(bh, "found on hash"); + } +#ifdef JBD_EXPENSIVE_CHECKING + else { + struct buffer_head *bh2; + + /* If there is a different buffer_head lying around in + * memory anywhere... */ + bh2 = __find_get_block(bdev, blocknr, journal->j_blocksize); + if (bh2) { + /* ... and it has RevokeValid status... */ + if (bh2 != bh && buffer_revokevalid(bh2)) + /* ...then it better be revoked too, + * since it's illegal to create a revoke + * record against a buffer_head which is + * not marked revoked --- that would + * risk missing a subsequent revoke + * cancel. */ + J_ASSERT_BH(bh2, buffer_revoked(bh2)); + put_bh(bh2); + } + } +#endif + + /* We really ought not ever to revoke twice in a row without + first having the revoke cancelled: it's illegal to free a + block twice without allocating it in between! */ + if (bh) { + if (!J_EXPECT_BH(bh, !buffer_revoked(bh), + "inconsistent data on disk")) { + if (!bh_in) + brelse(bh); + return -EIO; + } + set_buffer_revoked(bh); + set_buffer_revokevalid(bh); + if (bh_in) { + BUFFER_TRACE(bh_in, "call jbd2_journal_forget"); + jbd2_journal_forget(handle, bh_in); + } else { + BUFFER_TRACE(bh, "call brelse"); + __brelse(bh); + } + } + + jbd_debug(2, "insert revoke for block %llu, bh_in=%p\n",blocknr, bh_in); + err = insert_revoke_hash(journal, blocknr, + handle->h_transaction->t_tid); + BUFFER_TRACE(bh_in, "exit"); + return err; +} + +/* + * Cancel an outstanding revoke. For use only internally by the + * journaling code (called from jbd2_journal_get_write_access). + * + * We trust buffer_revoked() on the buffer if the buffer is already + * being journaled: if there is no revoke pending on the buffer, then we + * don't do anything here. + * + * This would break if it were possible for a buffer to be revoked and + * discarded, and then reallocated within the same transaction. In such + * a case we would have lost the revoked bit, but when we arrived here + * the second time we would still have a pending revoke to cancel. So, + * do not trust the Revoked bit on buffers unless RevokeValid is also + * set. + * + * The caller must have the journal locked. + */ +int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh) +{ + struct jbd2_revoke_record_s *record; + journal_t *journal = handle->h_transaction->t_journal; + int need_cancel; + int did_revoke = 0; /* akpm: debug */ + struct buffer_head *bh = jh2bh(jh); + + jbd_debug(4, "journal_head %p, cancelling revoke\n", jh); + + /* Is the existing Revoke bit valid? If so, we trust it, and + * only perform the full cancel if the revoke bit is set. If + * not, we can't trust the revoke bit, and we need to do the + * full search for a revoke record. */ + if (test_set_buffer_revokevalid(bh)) { + need_cancel = test_clear_buffer_revoked(bh); + } else { + need_cancel = 1; + clear_buffer_revoked(bh); + } + + if (need_cancel) { + record = find_revoke_record(journal, bh->b_blocknr); + if (record) { + jbd_debug(4, "cancelled existing revoke on " + "blocknr %llu\n", (unsigned long long)bh->b_blocknr); + spin_lock(&journal->j_revoke_lock); + list_del(&record->hash); + spin_unlock(&journal->j_revoke_lock); + kmem_cache_free(jbd2_revoke_record_cache, record); + did_revoke = 1; + } + } + +#ifdef JBD_EXPENSIVE_CHECKING + /* There better not be one left behind by now! */ + record = find_revoke_record(journal, bh->b_blocknr); + J_ASSERT_JH(jh, record == NULL); +#endif + + /* Finally, have we just cleared revoke on an unhashed + * buffer_head? If so, we'd better make sure we clear the + * revoked status on any hashed alias too, otherwise the revoke + * state machine will get very upset later on. */ + if (need_cancel) { + struct buffer_head *bh2; + bh2 = __find_get_block(bh->b_bdev, bh->b_blocknr, bh->b_size); + if (bh2) { + if (bh2 != bh) + clear_buffer_revoked(bh2); + __brelse(bh2); + } + } + return did_revoke; +} + +/* journal_switch_revoke table select j_revoke for next transaction + * we do not want to suspend any processing until all revokes are + * written -bzzz + */ +void jbd2_journal_switch_revoke_table(journal_t *journal) +{ + int i; + + if (journal->j_revoke == journal->j_revoke_table[0]) + journal->j_revoke = journal->j_revoke_table[1]; + else + journal->j_revoke = journal->j_revoke_table[0]; + + for (i = 0; i < journal->j_revoke->hash_size; i++) + INIT_LIST_HEAD(&journal->j_revoke->hash_table[i]); +} + +/* + * Write revoke records to the journal for all entries in the current + * revoke hash, deleting the entries as we go. + * + * Called with the journal lock held. + */ + +void jbd2_journal_write_revoke_records(journal_t *journal, + transaction_t *transaction) +{ + struct journal_head *descriptor; + struct jbd2_revoke_record_s *record; + struct jbd2_revoke_table_s *revoke; + struct list_head *hash_list; + int i, offset, count; + + descriptor = NULL; + offset = 0; + count = 0; + + /* select revoke table for committing transaction */ + revoke = journal->j_revoke == journal->j_revoke_table[0] ? + journal->j_revoke_table[1] : journal->j_revoke_table[0]; + + for (i = 0; i < revoke->hash_size; i++) { + hash_list = &revoke->hash_table[i]; + + while (!list_empty(hash_list)) { + record = (struct jbd2_revoke_record_s *) + hash_list->next; + write_one_revoke_record(journal, transaction, + &descriptor, &offset, + record); + count++; + list_del(&record->hash); + kmem_cache_free(jbd2_revoke_record_cache, record); + } + } + if (descriptor) + flush_descriptor(journal, descriptor, offset); + jbd_debug(1, "Wrote %d revoke records\n", count); +} + +/* + * Write out one revoke record. We need to create a new descriptor + * block if the old one is full or if we have not already created one. + */ + +static void write_one_revoke_record(journal_t *journal, + transaction_t *transaction, + struct journal_head **descriptorp, + int *offsetp, + struct jbd2_revoke_record_s *record) +{ + struct journal_head *descriptor; + int offset; + journal_header_t *header; + + /* If we are already aborting, this all becomes a noop. We + still need to go round the loop in + jbd2_journal_write_revoke_records in order to free all of the + revoke records: only the IO to the journal is omitted. */ + if (is_journal_aborted(journal)) + return; + + descriptor = *descriptorp; + offset = *offsetp; + + /* Make sure we have a descriptor with space left for the record */ + if (descriptor) { + if (offset == journal->j_blocksize) { + flush_descriptor(journal, descriptor, offset); + descriptor = NULL; + } + } + + if (!descriptor) { + descriptor = jbd2_journal_get_descriptor_buffer(journal); + if (!descriptor) + return; + header = (journal_header_t *) &jh2bh(descriptor)->b_data[0]; + header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); + header->h_blocktype = cpu_to_be32(JBD2_REVOKE_BLOCK); + header->h_sequence = cpu_to_be32(transaction->t_tid); + + /* Record it so that we can wait for IO completion later */ + JBUFFER_TRACE(descriptor, "file as BJ_LogCtl"); + jbd2_journal_file_buffer(descriptor, transaction, BJ_LogCtl); + + offset = sizeof(jbd2_journal_revoke_header_t); + *descriptorp = descriptor; + } + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) { + * ((__be64 *)(&jh2bh(descriptor)->b_data[offset])) = + cpu_to_be64(record->blocknr); + offset += 8; + + } else { + * ((__be32 *)(&jh2bh(descriptor)->b_data[offset])) = + cpu_to_be32(record->blocknr); + offset += 4; + } + + *offsetp = offset; +} + +/* + * Flush a revoke descriptor out to the journal. If we are aborting, + * this is a noop; otherwise we are generating a buffer which needs to + * be waited for during commit, so it has to go onto the appropriate + * journal buffer list. + */ + +static void flush_descriptor(journal_t *journal, + struct journal_head *descriptor, + int offset) +{ + jbd2_journal_revoke_header_t *header; + struct buffer_head *bh = jh2bh(descriptor); + + if (is_journal_aborted(journal)) { + put_bh(bh); + return; + } + + header = (jbd2_journal_revoke_header_t *) jh2bh(descriptor)->b_data; + header->r_count = cpu_to_be32(offset); + set_buffer_jwrite(bh); + BUFFER_TRACE(bh, "write"); + set_buffer_dirty(bh); + ll_rw_block(SWRITE, 1, &bh); +} +#endif + +/* + * Revoke support for recovery. + * + * Recovery needs to be able to: + * + * record all revoke records, including the tid of the latest instance + * of each revoke in the journal + * + * check whether a given block in a given transaction should be replayed + * (ie. has not been revoked by a revoke record in that or a subsequent + * transaction) + * + * empty the revoke table after recovery. + */ + +/* + * First, setting revoke records. We create a new revoke record for + * every block ever revoked in the log as we scan it for recovery, and + * we update the existing records if we find multiple revokes for a + * single block. + */ + +int jbd2_journal_set_revoke(journal_t *journal, + unsigned long long blocknr, + tid_t sequence) +{ + struct jbd2_revoke_record_s *record; + + record = find_revoke_record(journal, blocknr); + if (record) { + /* If we have multiple occurrences, only record the + * latest sequence number in the hashed record */ + if (tid_gt(sequence, record->sequence)) + record->sequence = sequence; + return 0; + } + return insert_revoke_hash(journal, blocknr, sequence); +} + +/* + * Test revoke records. For a given block referenced in the log, has + * that block been revoked? A revoke record with a given transaction + * sequence number revokes all blocks in that transaction and earlier + * ones, but later transactions still need replayed. + */ + +int jbd2_journal_test_revoke(journal_t *journal, + unsigned long long blocknr, + tid_t sequence) +{ + struct jbd2_revoke_record_s *record; + + record = find_revoke_record(journal, blocknr); + if (!record) + return 0; + if (tid_gt(sequence, record->sequence)) + return 0; + return 1; +} + +/* + * Finally, once recovery is over, we need to clear the revoke table so + * that it can be reused by the running filesystem. + */ + +void jbd2_journal_clear_revoke(journal_t *journal) +{ + int i; + struct list_head *hash_list; + struct jbd2_revoke_record_s *record; + struct jbd2_revoke_table_s *revoke; + + revoke = journal->j_revoke; + + for (i = 0; i < revoke->hash_size; i++) { + hash_list = &revoke->hash_table[i]; + while (!list_empty(hash_list)) { + record = (struct jbd2_revoke_record_s*) hash_list->next; + list_del(&record->hash); + kmem_cache_free(jbd2_revoke_record_cache, record); + } + } +} diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c new file mode 100644 index 00000000000..149957bef90 --- /dev/null +++ b/fs/jbd2/transaction.c @@ -0,0 +1,2080 @@ +/* + * linux/fs/transaction.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 + * + * Copyright 1998 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Generic filesystem transaction handling code; part of the ext2fs + * journaling system. + * + * This file manages transactions (compound commits managed by the + * journaling code) and handles (individual atomic operations by the + * filesystem). + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <linux/smp_lock.h> +#include <linux/mm.h> +#include <linux/highmem.h> + +/* + * jbd2_get_transaction: obtain a new transaction_t object. + * + * Simply allocate and initialise a new transaction. Create it in + * RUNNING state and add it to the current journal (which should not + * have an existing running transaction: we only make a new transaction + * once we have started to commit the old one). + * + * Preconditions: + * The journal MUST be locked. We don't perform atomic mallocs on the + * new transaction and we can't block without protecting against other + * processes trying to touch the journal while it is in transition. + * + * Called under j_state_lock + */ + +static transaction_t * +jbd2_get_transaction(journal_t *journal, transaction_t *transaction) +{ + transaction->t_journal = journal; + transaction->t_state = T_RUNNING; + transaction->t_tid = journal->j_transaction_sequence++; + transaction->t_expires = jiffies + journal->j_commit_interval; + spin_lock_init(&transaction->t_handle_lock); + + /* Set up the commit timer for the new transaction. */ + journal->j_commit_timer.expires = transaction->t_expires; + add_timer(&journal->j_commit_timer); + + J_ASSERT(journal->j_running_transaction == NULL); + journal->j_running_transaction = transaction; + + return transaction; +} + +/* + * Handle management. + * + * A handle_t is an object which represents a single atomic update to a + * filesystem, and which tracks all of the modifications which form part + * of that one update. + */ + +/* + * start_this_handle: Given a handle, deal with any locking or stalling + * needed to make sure that there is enough journal space for the handle + * to begin. Attach the handle to a transaction and set up the + * transaction's buffer credits. + */ + +static int start_this_handle(journal_t *journal, handle_t *handle) +{ + transaction_t *transaction; + int needed; + int nblocks = handle->h_buffer_credits; + transaction_t *new_transaction = NULL; + int ret = 0; + + if (nblocks > journal->j_max_transaction_buffers) { + printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n", + current->comm, nblocks, + journal->j_max_transaction_buffers); + ret = -ENOSPC; + goto out; + } + +alloc_transaction: + if (!journal->j_running_transaction) { + new_transaction = jbd_kmalloc(sizeof(*new_transaction), + GFP_NOFS); + if (!new_transaction) { + ret = -ENOMEM; + goto out; + } + memset(new_transaction, 0, sizeof(*new_transaction)); + } + + jbd_debug(3, "New handle %p going live.\n", handle); + +repeat: + + /* + * We need to hold j_state_lock until t_updates has been incremented, + * for proper journal barrier handling + */ + spin_lock(&journal->j_state_lock); +repeat_locked: + if (is_journal_aborted(journal) || + (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) { + spin_unlock(&journal->j_state_lock); + ret = -EROFS; + goto out; + } + + /* Wait on the journal's transaction barrier if necessary */ + if (journal->j_barrier_count) { + spin_unlock(&journal->j_state_lock); + wait_event(journal->j_wait_transaction_locked, + journal->j_barrier_count == 0); + goto repeat; + } + + if (!journal->j_running_transaction) { + if (!new_transaction) { + spin_unlock(&journal->j_state_lock); + goto alloc_transaction; + } + jbd2_get_transaction(journal, new_transaction); + new_transaction = NULL; + } + + transaction = journal->j_running_transaction; + + /* + * If the current transaction is locked down for commit, wait for the + * lock to be released. + */ + if (transaction->t_state == T_LOCKED) { + DEFINE_WAIT(wait); + + prepare_to_wait(&journal->j_wait_transaction_locked, + &wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&journal->j_state_lock); + schedule(); + finish_wait(&journal->j_wait_transaction_locked, &wait); + goto repeat; + } + + /* + * If there is not enough space left in the log to write all potential + * buffers requested by this operation, we need to stall pending a log + * checkpoint to free some more log space. + */ + spin_lock(&transaction->t_handle_lock); + needed = transaction->t_outstanding_credits + nblocks; + + if (needed > journal->j_max_transaction_buffers) { + /* + * If the current transaction is already too large, then start + * to commit it: we can then go back and attach this handle to + * a new transaction. + */ + DEFINE_WAIT(wait); + + jbd_debug(2, "Handle %p starting new commit...\n", handle); + spin_unlock(&transaction->t_handle_lock); + prepare_to_wait(&journal->j_wait_transaction_locked, &wait, + TASK_UNINTERRUPTIBLE); + __jbd2_log_start_commit(journal, transaction->t_tid); + spin_unlock(&journal->j_state_lock); + schedule(); + finish_wait(&journal->j_wait_transaction_locked, &wait); + goto repeat; + } + + /* + * The commit code assumes that it can get enough log space + * without forcing a checkpoint. This is *critical* for + * correctness: a checkpoint of a buffer which is also + * associated with a committing transaction creates a deadlock, + * so commit simply cannot force through checkpoints. + * + * We must therefore ensure the necessary space in the journal + * *before* starting to dirty potentially checkpointed buffers + * in the new transaction. + * + * The worst part is, any transaction currently committing can + * reduce the free space arbitrarily. Be careful to account for + * those buffers when checkpointing. + */ + + /* + * @@@ AKPM: This seems rather over-defensive. We're giving commit + * a _lot_ of headroom: 1/4 of the journal plus the size of + * the committing transaction. Really, we only need to give it + * committing_transaction->t_outstanding_credits plus "enough" for + * the log control blocks. + * Also, this test is inconsitent with the matching one in + * jbd2_journal_extend(). + */ + if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) { + jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle); + spin_unlock(&transaction->t_handle_lock); + __jbd2_log_wait_for_space(journal); + goto repeat_locked; + } + + /* OK, account for the buffers that this operation expects to + * use and add the handle to the running transaction. */ + + handle->h_transaction = transaction; + transaction->t_outstanding_credits += nblocks; + transaction->t_updates++; + transaction->t_handle_count++; + jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n", + handle, nblocks, transaction->t_outstanding_credits, + __jbd2_log_space_left(journal)); + spin_unlock(&transaction->t_handle_lock); + spin_unlock(&journal->j_state_lock); +out: + if (unlikely(new_transaction)) /* It's usually NULL */ + kfree(new_transaction); + return ret; +} + +/* Allocate a new handle. This should probably be in a slab... */ +static handle_t *new_handle(int nblocks) +{ + handle_t *handle = jbd_alloc_handle(GFP_NOFS); + if (!handle) + return NULL; + memset(handle, 0, sizeof(*handle)); + handle->h_buffer_credits = nblocks; + handle->h_ref = 1; + + return handle; +} + +/** + * handle_t *jbd2_journal_start() - Obtain a new handle. + * @journal: Journal to start transaction on. + * @nblocks: number of block buffer we might modify + * + * We make sure that the transaction can guarantee at least nblocks of + * modified buffers in the log. We block until the log can guarantee + * that much space. + * + * This function is visible to journal users (like ext3fs), so is not + * called with the journal already locked. + * + * Return a pointer to a newly allocated handle, or NULL on failure + */ +handle_t *jbd2_journal_start(journal_t *journal, int nblocks) +{ + handle_t *handle = journal_current_handle(); + int err; + + if (!journal) + return ERR_PTR(-EROFS); + + if (handle) { + J_ASSERT(handle->h_transaction->t_journal == journal); + handle->h_ref++; + return handle; + } + + handle = new_handle(nblocks); + if (!handle) + return ERR_PTR(-ENOMEM); + + current->journal_info = handle; + + err = start_this_handle(journal, handle); + if (err < 0) { + jbd_free_handle(handle); + current->journal_info = NULL; + handle = ERR_PTR(err); + } + return handle; +} + +/** + * int jbd2_journal_extend() - extend buffer credits. + * @handle: handle to 'extend' + * @nblocks: nr blocks to try to extend by. + * + * Some transactions, such as large extends and truncates, can be done + * atomically all at once or in several stages. The operation requests + * a credit for a number of buffer modications in advance, but can + * extend its credit if it needs more. + * + * jbd2_journal_extend tries to give the running handle more buffer credits. + * It does not guarantee that allocation - this is a best-effort only. + * The calling process MUST be able to deal cleanly with a failure to + * extend here. + * + * Return 0 on success, non-zero on failure. + * + * return code < 0 implies an error + * return code > 0 implies normal transaction-full status. + */ +int jbd2_journal_extend(handle_t *handle, int nblocks) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal = transaction->t_journal; + int result; + int wanted; + + result = -EIO; + if (is_handle_aborted(handle)) + goto out; + + result = 1; + + spin_lock(&journal->j_state_lock); + + /* Don't extend a locked-down transaction! */ + if (handle->h_transaction->t_state != T_RUNNING) { + jbd_debug(3, "denied handle %p %d blocks: " + "transaction not running\n", handle, nblocks); + goto error_out; + } + + spin_lock(&transaction->t_handle_lock); + wanted = transaction->t_outstanding_credits + nblocks; + + if (wanted > journal->j_max_transaction_buffers) { + jbd_debug(3, "denied handle %p %d blocks: " + "transaction too large\n", handle, nblocks); + goto unlock; + } + + if (wanted > __jbd2_log_space_left(journal)) { + jbd_debug(3, "denied handle %p %d blocks: " + "insufficient log space\n", handle, nblocks); + goto unlock; + } + + handle->h_buffer_credits += nblocks; + transaction->t_outstanding_credits += nblocks; + result = 0; + + jbd_debug(3, "extended handle %p by %d\n", handle, nblocks); +unlock: + spin_unlock(&transaction->t_handle_lock); +error_out: + spin_unlock(&journal->j_state_lock); +out: + return result; +} + + +/** + * int jbd2_journal_restart() - restart a handle . + * @handle: handle to restart + * @nblocks: nr credits requested + * + * Restart a handle for a multi-transaction filesystem + * operation. + * + * If the jbd2_journal_extend() call above fails to grant new buffer credits + * to a running handle, a call to jbd2_journal_restart will commit the + * handle's transaction so far and reattach the handle to a new + * transaction capabable of guaranteeing the requested number of + * credits. + */ + +int jbd2_journal_restart(handle_t *handle, int nblocks) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal = transaction->t_journal; + int ret; + + /* If we've had an abort of any type, don't even think about + * actually doing the restart! */ + if (is_handle_aborted(handle)) + return 0; + + /* + * First unlink the handle from its current transaction, and start the + * commit on that. + */ + J_ASSERT(transaction->t_updates > 0); + J_ASSERT(journal_current_handle() == handle); + + spin_lock(&journal->j_state_lock); + spin_lock(&transaction->t_handle_lock); + transaction->t_outstanding_credits -= handle->h_buffer_credits; + transaction->t_updates--; + + if (!transaction->t_updates) + wake_up(&journal->j_wait_updates); + spin_unlock(&transaction->t_handle_lock); + + jbd_debug(2, "restarting handle %p\n", handle); + __jbd2_log_start_commit(journal, transaction->t_tid); + spin_unlock(&journal->j_state_lock); + + handle->h_buffer_credits = nblocks; + ret = start_this_handle(journal, handle); + return ret; +} + + +/** + * void jbd2_journal_lock_updates () - establish a transaction barrier. + * @journal: Journal to establish a barrier on. + * + * This locks out any further updates from being started, and blocks + * until all existing updates have completed, returning only once the + * journal is in a quiescent state with no updates running. + * + * The journal lock should not be held on entry. + */ +void jbd2_journal_lock_updates(journal_t *journal) +{ + DEFINE_WAIT(wait); + + spin_lock(&journal->j_state_lock); + ++journal->j_barrier_count; + + /* Wait until there are no running updates */ + while (1) { + transaction_t *transaction = journal->j_running_transaction; + + if (!transaction) + break; + + spin_lock(&transaction->t_handle_lock); + if (!transaction->t_updates) { + spin_unlock(&transaction->t_handle_lock); + break; + } + prepare_to_wait(&journal->j_wait_updates, &wait, + TASK_UNINTERRUPTIBLE); + spin_unlock(&transaction->t_handle_lock); + spin_unlock(&journal->j_state_lock); + schedule(); + finish_wait(&journal->j_wait_updates, &wait); + spin_lock(&journal->j_state_lock); + } + spin_unlock(&journal->j_state_lock); + + /* + * We have now established a barrier against other normal updates, but + * we also need to barrier against other jbd2_journal_lock_updates() calls + * to make sure that we serialise special journal-locked operations + * too. + */ + mutex_lock(&journal->j_barrier); +} + +/** + * void jbd2_journal_unlock_updates (journal_t* journal) - release barrier + * @journal: Journal to release the barrier on. + * + * Release a transaction barrier obtained with jbd2_journal_lock_updates(). + * + * Should be called without the journal lock held. + */ +void jbd2_journal_unlock_updates (journal_t *journal) +{ + J_ASSERT(journal->j_barrier_count != 0); + + mutex_unlock(&journal->j_barrier); + spin_lock(&journal->j_state_lock); + --journal->j_barrier_count; + spin_unlock(&journal->j_state_lock); + wake_up(&journal->j_wait_transaction_locked); +} + +/* + * Report any unexpected dirty buffers which turn up. Normally those + * indicate an error, but they can occur if the user is running (say) + * tune2fs to modify the live filesystem, so we need the option of + * continuing as gracefully as possible. # + * + * The caller should already hold the journal lock and + * j_list_lock spinlock: most callers will need those anyway + * in order to probe the buffer's journaling state safely. + */ +static void jbd_unexpected_dirty_buffer(struct journal_head *jh) +{ + int jlist; + + /* If this buffer is one which might reasonably be dirty + * --- ie. data, or not part of this journal --- then + * we're OK to leave it alone, but otherwise we need to + * move the dirty bit to the journal's own internal + * JBDDirty bit. */ + jlist = jh->b_jlist; + + if (jlist == BJ_Metadata || jlist == BJ_Reserved || + jlist == BJ_Shadow || jlist == BJ_Forget) { + struct buffer_head *bh = jh2bh(jh); + + if (test_clear_buffer_dirty(bh)) + set_buffer_jbddirty(bh); + } +} + +/* + * If the buffer is already part of the current transaction, then there + * is nothing we need to do. If it is already part of a prior + * transaction which we are still committing to disk, then we need to + * make sure that we do not overwrite the old copy: we do copy-out to + * preserve the copy going to disk. We also account the buffer against + * the handle's metadata buffer credits (unless the buffer is already + * part of the transaction, that is). + * + */ +static int +do_get_write_access(handle_t *handle, struct journal_head *jh, + int force_copy) +{ + struct buffer_head *bh; + transaction_t *transaction; + journal_t *journal; + int error; + char *frozen_buffer = NULL; + int need_copy = 0; + + if (is_handle_aborted(handle)) + return -EROFS; + + transaction = handle->h_transaction; + journal = transaction->t_journal; + + jbd_debug(5, "buffer_head %p, force_copy %d\n", jh, force_copy); + + JBUFFER_TRACE(jh, "entry"); +repeat: + bh = jh2bh(jh); + + /* @@@ Need to check for errors here at some point. */ + + lock_buffer(bh); + jbd_lock_bh_state(bh); + + /* We now hold the buffer lock so it is safe to query the buffer + * state. Is the buffer dirty? + * + * If so, there are two possibilities. The buffer may be + * non-journaled, and undergoing a quite legitimate writeback. + * Otherwise, it is journaled, and we don't expect dirty buffers + * in that state (the buffers should be marked JBD_Dirty + * instead.) So either the IO is being done under our own + * control and this is a bug, or it's a third party IO such as + * dump(8) (which may leave the buffer scheduled for read --- + * ie. locked but not dirty) or tune2fs (which may actually have + * the buffer dirtied, ugh.) */ + + if (buffer_dirty(bh)) { + /* + * First question: is this buffer already part of the current + * transaction or the existing committing transaction? + */ + if (jh->b_transaction) { + J_ASSERT_JH(jh, + jh->b_transaction == transaction || + jh->b_transaction == + journal->j_committing_transaction); + if (jh->b_next_transaction) + J_ASSERT_JH(jh, jh->b_next_transaction == + transaction); + } + /* + * In any case we need to clean the dirty flag and we must + * do it under the buffer lock to be sure we don't race + * with running write-out. + */ + JBUFFER_TRACE(jh, "Unexpected dirty buffer"); + jbd_unexpected_dirty_buffer(jh); + } + + unlock_buffer(bh); + + error = -EROFS; + if (is_handle_aborted(handle)) { + jbd_unlock_bh_state(bh); + goto out; + } + error = 0; + + /* + * The buffer is already part of this transaction if b_transaction or + * b_next_transaction points to it + */ + if (jh->b_transaction == transaction || + jh->b_next_transaction == transaction) + goto done; + + /* + * If there is already a copy-out version of this buffer, then we don't + * need to make another one + */ + if (jh->b_frozen_data) { + JBUFFER_TRACE(jh, "has frozen data"); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + jh->b_next_transaction = transaction; + goto done; + } + + /* Is there data here we need to preserve? */ + + if (jh->b_transaction && jh->b_transaction != transaction) { + JBUFFER_TRACE(jh, "owned by older transaction"); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + J_ASSERT_JH(jh, jh->b_transaction == + journal->j_committing_transaction); + + /* There is one case we have to be very careful about. + * If the committing transaction is currently writing + * this buffer out to disk and has NOT made a copy-out, + * then we cannot modify the buffer contents at all + * right now. The essence of copy-out is that it is the + * extra copy, not the primary copy, which gets + * journaled. If the primary copy is already going to + * disk then we cannot do copy-out here. */ + + if (jh->b_jlist == BJ_Shadow) { + DEFINE_WAIT_BIT(wait, &bh->b_state, BH_Unshadow); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&bh->b_state, BH_Unshadow); + + JBUFFER_TRACE(jh, "on shadow: sleep"); + jbd_unlock_bh_state(bh); + /* commit wakes up all shadow buffers after IO */ + for ( ; ; ) { + prepare_to_wait(wqh, &wait.wait, + TASK_UNINTERRUPTIBLE); + if (jh->b_jlist != BJ_Shadow) + break; + schedule(); + } + finish_wait(wqh, &wait.wait); + goto repeat; + } + + /* Only do the copy if the currently-owning transaction + * still needs it. If it is on the Forget list, the + * committing transaction is past that stage. The + * buffer had better remain locked during the kmalloc, + * but that should be true --- we hold the journal lock + * still and the buffer is already on the BUF_JOURNAL + * list so won't be flushed. + * + * Subtle point, though: if this is a get_undo_access, + * then we will be relying on the frozen_data to contain + * the new value of the committed_data record after the + * transaction, so we HAVE to force the frozen_data copy + * in that case. */ + + if (jh->b_jlist != BJ_Forget || force_copy) { + JBUFFER_TRACE(jh, "generate frozen data"); + if (!frozen_buffer) { + JBUFFER_TRACE(jh, "allocate memory for buffer"); + jbd_unlock_bh_state(bh); + frozen_buffer = + jbd2_slab_alloc(jh2bh(jh)->b_size, + GFP_NOFS); + if (!frozen_buffer) { + printk(KERN_EMERG + "%s: OOM for frozen_buffer\n", + __FUNCTION__); + JBUFFER_TRACE(jh, "oom!"); + error = -ENOMEM; + jbd_lock_bh_state(bh); + goto done; + } + goto repeat; + } + jh->b_frozen_data = frozen_buffer; + frozen_buffer = NULL; + need_copy = 1; + } + jh->b_next_transaction = transaction; + } + + + /* + * Finally, if the buffer is not journaled right now, we need to make + * sure it doesn't get written to disk before the caller actually + * commits the new data + */ + if (!jh->b_transaction) { + JBUFFER_TRACE(jh, "no transaction"); + J_ASSERT_JH(jh, !jh->b_next_transaction); + jh->b_transaction = transaction; + JBUFFER_TRACE(jh, "file as BJ_Reserved"); + spin_lock(&journal->j_list_lock); + __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); + spin_unlock(&journal->j_list_lock); + } + +done: + if (need_copy) { + struct page *page; + int offset; + char *source; + + J_EXPECT_JH(jh, buffer_uptodate(jh2bh(jh)), + "Possible IO failure.\n"); + page = jh2bh(jh)->b_page; + offset = ((unsigned long) jh2bh(jh)->b_data) & ~PAGE_MASK; + source = kmap_atomic(page, KM_USER0); + memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size); + kunmap_atomic(source, KM_USER0); + } + jbd_unlock_bh_state(bh); + + /* + * If we are about to journal a buffer, then any revoke pending on it is + * no longer valid + */ + jbd2_journal_cancel_revoke(handle, jh); + +out: + if (unlikely(frozen_buffer)) /* It's usually NULL */ + jbd2_slab_free(frozen_buffer, bh->b_size); + + JBUFFER_TRACE(jh, "exit"); + return error; +} + +/** + * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update. + * @handle: transaction to add buffer modifications to + * @bh: bh to be used for metadata writes + * @credits: variable that will receive credits for the buffer + * + * Returns an error code or 0 on success. + * + * In full data journalling mode the buffer may be of type BJ_AsyncData, + * because we're write()ing a buffer which is also part of a shared mapping. + */ + +int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) +{ + struct journal_head *jh = jbd2_journal_add_journal_head(bh); + int rc; + + /* We do not want to get caught playing with fields which the + * log thread also manipulates. Make sure that the buffer + * completes any outstanding IO before proceeding. */ + rc = do_get_write_access(handle, jh, 0); + jbd2_journal_put_journal_head(jh); + return rc; +} + + +/* + * When the user wants to journal a newly created buffer_head + * (ie. getblk() returned a new buffer and we are going to populate it + * manually rather than reading off disk), then we need to keep the + * buffer_head locked until it has been completely filled with new + * data. In this case, we should be able to make the assertion that + * the bh is not already part of an existing transaction. + * + * The buffer should already be locked by the caller by this point. + * There is no lock ranking violation: it was a newly created, + * unlocked buffer beforehand. */ + +/** + * int jbd2_journal_get_create_access () - notify intent to use newly created bh + * @handle: transaction to new buffer to + * @bh: new buffer. + * + * Call this if you create a new bh. + */ +int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal = transaction->t_journal; + struct journal_head *jh = jbd2_journal_add_journal_head(bh); + int err; + + jbd_debug(5, "journal_head %p\n", jh); + err = -EROFS; + if (is_handle_aborted(handle)) + goto out; + err = 0; + + JBUFFER_TRACE(jh, "entry"); + /* + * The buffer may already belong to this transaction due to pre-zeroing + * in the filesystem's new_block code. It may also be on the previous, + * committing transaction's lists, but it HAS to be in Forget state in + * that case: the transaction must have deleted the buffer for it to be + * reused here. + */ + jbd_lock_bh_state(bh); + spin_lock(&journal->j_list_lock); + J_ASSERT_JH(jh, (jh->b_transaction == transaction || + jh->b_transaction == NULL || + (jh->b_transaction == journal->j_committing_transaction && + jh->b_jlist == BJ_Forget))); + + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + J_ASSERT_JH(jh, buffer_locked(jh2bh(jh))); + + if (jh->b_transaction == NULL) { + jh->b_transaction = transaction; + JBUFFER_TRACE(jh, "file as BJ_Reserved"); + __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); + } else if (jh->b_transaction == journal->j_committing_transaction) { + JBUFFER_TRACE(jh, "set next transaction"); + jh->b_next_transaction = transaction; + } + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + + /* + * akpm: I added this. ext3_alloc_branch can pick up new indirect + * blocks which contain freed but then revoked metadata. We need + * to cancel the revoke in case we end up freeing it yet again + * and the reallocating as data - this would cause a second revoke, + * which hits an assertion error. + */ + JBUFFER_TRACE(jh, "cancelling revoke"); + jbd2_journal_cancel_revoke(handle, jh); + jbd2_journal_put_journal_head(jh); +out: + return err; +} + +/** + * int jbd2_journal_get_undo_access() - Notify intent to modify metadata with + * non-rewindable consequences + * @handle: transaction + * @bh: buffer to undo + * @credits: store the number of taken credits here (if not NULL) + * + * Sometimes there is a need to distinguish between metadata which has + * been committed to disk and that which has not. The ext3fs code uses + * this for freeing and allocating space, we have to make sure that we + * do not reuse freed space until the deallocation has been committed, + * since if we overwrote that space we would make the delete + * un-rewindable in case of a crash. + * + * To deal with that, jbd2_journal_get_undo_access requests write access to a + * buffer for parts of non-rewindable operations such as delete + * operations on the bitmaps. The journaling code must keep a copy of + * the buffer's contents prior to the undo_access call until such time + * as we know that the buffer has definitely been committed to disk. + * + * We never need to know which transaction the committed data is part + * of, buffers touched here are guaranteed to be dirtied later and so + * will be committed to a new transaction in due course, at which point + * we can discard the old committed data pointer. + * + * Returns error number or 0 on success. + */ +int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) +{ + int err; + struct journal_head *jh = jbd2_journal_add_journal_head(bh); + char *committed_data = NULL; + + JBUFFER_TRACE(jh, "entry"); + + /* + * Do this first --- it can drop the journal lock, so we want to + * make sure that obtaining the committed_data is done + * atomically wrt. completion of any outstanding commits. + */ + err = do_get_write_access(handle, jh, 1); + if (err) + goto out; + +repeat: + if (!jh->b_committed_data) { + committed_data = jbd2_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS); + if (!committed_data) { + printk(KERN_EMERG "%s: No memory for committed data\n", + __FUNCTION__); + err = -ENOMEM; + goto out; + } + } + + jbd_lock_bh_state(bh); + if (!jh->b_committed_data) { + /* Copy out the current buffer contents into the + * preserved, committed copy. */ + JBUFFER_TRACE(jh, "generate b_committed data"); + if (!committed_data) { + jbd_unlock_bh_state(bh); + goto repeat; + } + + jh->b_committed_data = committed_data; + committed_data = NULL; + memcpy(jh->b_committed_data, bh->b_data, bh->b_size); + } + jbd_unlock_bh_state(bh); +out: + jbd2_journal_put_journal_head(jh); + if (unlikely(committed_data)) + jbd2_slab_free(committed_data, bh->b_size); + return err; +} + +/** + * int jbd2_journal_dirty_data() - mark a buffer as containing dirty data which + * needs to be flushed before we can commit the + * current transaction. + * @handle: transaction + * @bh: bufferhead to mark + * + * The buffer is placed on the transaction's data list and is marked as + * belonging to the transaction. + * + * Returns error number or 0 on success. + * + * jbd2_journal_dirty_data() can be called via page_launder->ext3_writepage + * by kswapd. + */ +int jbd2_journal_dirty_data(handle_t *handle, struct buffer_head *bh) +{ + journal_t *journal = handle->h_transaction->t_journal; + int need_brelse = 0; + struct journal_head *jh; + + if (is_handle_aborted(handle)) + return 0; + + jh = jbd2_journal_add_journal_head(bh); + JBUFFER_TRACE(jh, "entry"); + + /* + * The buffer could *already* be dirty. Writeout can start + * at any time. + */ + jbd_debug(4, "jh: %p, tid:%d\n", jh, handle->h_transaction->t_tid); + + /* + * What if the buffer is already part of a running transaction? + * + * There are two cases: + * 1) It is part of the current running transaction. Refile it, + * just in case we have allocated it as metadata, deallocated + * it, then reallocated it as data. + * 2) It is part of the previous, still-committing transaction. + * If all we want to do is to guarantee that the buffer will be + * written to disk before this new transaction commits, then + * being sure that the *previous* transaction has this same + * property is sufficient for us! Just leave it on its old + * transaction. + * + * In case (2), the buffer must not already exist as metadata + * --- that would violate write ordering (a transaction is free + * to write its data at any point, even before the previous + * committing transaction has committed). The caller must + * never, ever allow this to happen: there's nothing we can do + * about it in this layer. + */ + jbd_lock_bh_state(bh); + spin_lock(&journal->j_list_lock); + if (jh->b_transaction) { + JBUFFER_TRACE(jh, "has transaction"); + if (jh->b_transaction != handle->h_transaction) { + JBUFFER_TRACE(jh, "belongs to older transaction"); + J_ASSERT_JH(jh, jh->b_transaction == + journal->j_committing_transaction); + + /* @@@ IS THIS TRUE ? */ + /* + * Not any more. Scenario: someone does a write() + * in data=journal mode. The buffer's transaction has + * moved into commit. Then someone does another + * write() to the file. We do the frozen data copyout + * and set b_next_transaction to point to j_running_t. + * And while we're in that state, someone does a + * writepage() in an attempt to pageout the same area + * of the file via a shared mapping. At present that + * calls jbd2_journal_dirty_data(), and we get right here. + * It may be too late to journal the data. Simply + * falling through to the next test will suffice: the + * data will be dirty and wil be checkpointed. The + * ordering comments in the next comment block still + * apply. + */ + //J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + + /* + * If we're journalling data, and this buffer was + * subject to a write(), it could be metadata, forget + * or shadow against the committing transaction. Now, + * someone has dirtied the same darn page via a mapping + * and it is being writepage()'d. + * We *could* just steal the page from commit, with some + * fancy locking there. Instead, we just skip it - + * don't tie the page's buffers to the new transaction + * at all. + * Implication: if we crash before the writepage() data + * is written into the filesystem, recovery will replay + * the write() data. + */ + if (jh->b_jlist != BJ_None && + jh->b_jlist != BJ_SyncData && + jh->b_jlist != BJ_Locked) { + JBUFFER_TRACE(jh, "Not stealing"); + goto no_journal; + } + + /* + * This buffer may be undergoing writeout in commit. We + * can't return from here and let the caller dirty it + * again because that can cause the write-out loop in + * commit to never terminate. + */ + if (buffer_dirty(bh)) { + get_bh(bh); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + need_brelse = 1; + sync_dirty_buffer(bh); + jbd_lock_bh_state(bh); + spin_lock(&journal->j_list_lock); + /* The buffer may become locked again at any + time if it is redirtied */ + } + + /* journal_clean_data_list() may have got there first */ + if (jh->b_transaction != NULL) { + JBUFFER_TRACE(jh, "unfile from commit"); + __jbd2_journal_temp_unlink_buffer(jh); + /* It still points to the committing + * transaction; move it to this one so + * that the refile assert checks are + * happy. */ + jh->b_transaction = handle->h_transaction; + } + /* The buffer will be refiled below */ + + } + /* + * Special case --- the buffer might actually have been + * allocated and then immediately deallocated in the previous, + * committing transaction, so might still be left on that + * transaction's metadata lists. + */ + if (jh->b_jlist != BJ_SyncData && jh->b_jlist != BJ_Locked) { + JBUFFER_TRACE(jh, "not on correct data list: unfile"); + J_ASSERT_JH(jh, jh->b_jlist != BJ_Shadow); + __jbd2_journal_temp_unlink_buffer(jh); + jh->b_transaction = handle->h_transaction; + JBUFFER_TRACE(jh, "file as data"); + __jbd2_journal_file_buffer(jh, handle->h_transaction, + BJ_SyncData); + } + } else { + JBUFFER_TRACE(jh, "not on a transaction"); + __jbd2_journal_file_buffer(jh, handle->h_transaction, BJ_SyncData); + } +no_journal: + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + if (need_brelse) { + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + } + JBUFFER_TRACE(jh, "exit"); + jbd2_journal_put_journal_head(jh); + return 0; +} + +/** + * int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata + * @handle: transaction to add buffer to. + * @bh: buffer to mark + * + * mark dirty metadata which needs to be journaled as part of the current + * transaction. + * + * The buffer is placed on the transaction's metadata list and is marked + * as belonging to the transaction. + * + * Returns error number or 0 on success. + * + * Special care needs to be taken if the buffer already belongs to the + * current committing transaction (in which case we should have frozen + * data present for that commit). In that case, we don't relink the + * buffer: that only gets done when the old transaction finally + * completes its commit. + */ +int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal = transaction->t_journal; + struct journal_head *jh = bh2jh(bh); + + jbd_debug(5, "journal_head %p\n", jh); + JBUFFER_TRACE(jh, "entry"); + if (is_handle_aborted(handle)) + goto out; + + jbd_lock_bh_state(bh); + + if (jh->b_modified == 0) { + /* + * This buffer's got modified and becoming part + * of the transaction. This needs to be done + * once a transaction -bzzz + */ + jh->b_modified = 1; + J_ASSERT_JH(jh, handle->h_buffer_credits > 0); + handle->h_buffer_credits--; + } + + /* + * fastpath, to avoid expensive locking. If this buffer is already + * on the running transaction's metadata list there is nothing to do. + * Nobody can take it off again because there is a handle open. + * I _think_ we're OK here with SMP barriers - a mistaken decision will + * result in this test being false, so we go in and take the locks. + */ + if (jh->b_transaction == transaction && jh->b_jlist == BJ_Metadata) { + JBUFFER_TRACE(jh, "fastpath"); + J_ASSERT_JH(jh, jh->b_transaction == + journal->j_running_transaction); + goto out_unlock_bh; + } + + set_buffer_jbddirty(bh); + + /* + * Metadata already on the current transaction list doesn't + * need to be filed. Metadata on another transaction's list must + * be committing, and will be refiled once the commit completes: + * leave it alone for now. + */ + if (jh->b_transaction != transaction) { + JBUFFER_TRACE(jh, "already on other transaction"); + J_ASSERT_JH(jh, jh->b_transaction == + journal->j_committing_transaction); + J_ASSERT_JH(jh, jh->b_next_transaction == transaction); + /* And this case is illegal: we can't reuse another + * transaction's data buffer, ever. */ + goto out_unlock_bh; + } + + /* That test should have eliminated the following case: */ + J_ASSERT_JH(jh, jh->b_frozen_data == 0); + + JBUFFER_TRACE(jh, "file as BJ_Metadata"); + spin_lock(&journal->j_list_lock); + __jbd2_journal_file_buffer(jh, handle->h_transaction, BJ_Metadata); + spin_unlock(&journal->j_list_lock); +out_unlock_bh: + jbd_unlock_bh_state(bh); +out: + JBUFFER_TRACE(jh, "exit"); + return 0; +} + +/* + * jbd2_journal_release_buffer: undo a get_write_access without any buffer + * updates, if the update decided in the end that it didn't need access. + * + */ +void +jbd2_journal_release_buffer(handle_t *handle, struct buffer_head *bh) +{ + BUFFER_TRACE(bh, "entry"); +} + +/** + * void jbd2_journal_forget() - bforget() for potentially-journaled buffers. + * @handle: transaction handle + * @bh: bh to 'forget' + * + * We can only do the bforget if there are no commits pending against the + * buffer. If the buffer is dirty in the current running transaction we + * can safely unlink it. + * + * bh may not be a journalled buffer at all - it may be a non-JBD + * buffer which came off the hashtable. Check for this. + * + * Decrements bh->b_count by one. + * + * Allow this call even if the handle has aborted --- it may be part of + * the caller's cleanup after an abort. + */ +int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal = transaction->t_journal; + struct journal_head *jh; + int drop_reserve = 0; + int err = 0; + + BUFFER_TRACE(bh, "entry"); + + jbd_lock_bh_state(bh); + spin_lock(&journal->j_list_lock); + + if (!buffer_jbd(bh)) + goto not_jbd; + jh = bh2jh(bh); + + /* Critical error: attempting to delete a bitmap buffer, maybe? + * Don't do any jbd operations, and return an error. */ + if (!J_EXPECT_JH(jh, !jh->b_committed_data, + "inconsistent data on disk")) { + err = -EIO; + goto not_jbd; + } + + /* + * The buffer's going from the transaction, we must drop + * all references -bzzz + */ + jh->b_modified = 0; + + if (jh->b_transaction == handle->h_transaction) { + J_ASSERT_JH(jh, !jh->b_frozen_data); + + /* If we are forgetting a buffer which is already part + * of this transaction, then we can just drop it from + * the transaction immediately. */ + clear_buffer_dirty(bh); + clear_buffer_jbddirty(bh); + + JBUFFER_TRACE(jh, "belongs to current transaction: unfile"); + + drop_reserve = 1; + + /* + * We are no longer going to journal this buffer. + * However, the commit of this transaction is still + * important to the buffer: the delete that we are now + * processing might obsolete an old log entry, so by + * committing, we can satisfy the buffer's checkpoint. + * + * So, if we have a checkpoint on the buffer, we should + * now refile the buffer on our BJ_Forget list so that + * we know to remove the checkpoint after we commit. + */ + + if (jh->b_cp_transaction) { + __jbd2_journal_temp_unlink_buffer(jh); + __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); + } else { + __jbd2_journal_unfile_buffer(jh); + jbd2_journal_remove_journal_head(bh); + __brelse(bh); + if (!buffer_jbd(bh)) { + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + __bforget(bh); + goto drop; + } + } + } else if (jh->b_transaction) { + J_ASSERT_JH(jh, (jh->b_transaction == + journal->j_committing_transaction)); + /* However, if the buffer is still owned by a prior + * (committing) transaction, we can't drop it yet... */ + JBUFFER_TRACE(jh, "belongs to older transaction"); + /* ... but we CAN drop it from the new transaction if we + * have also modified it since the original commit. */ + + if (jh->b_next_transaction) { + J_ASSERT(jh->b_next_transaction == transaction); + jh->b_next_transaction = NULL; + drop_reserve = 1; + } + } + +not_jbd: + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + __brelse(bh); +drop: + if (drop_reserve) { + /* no need to reserve log space for this block -bzzz */ + handle->h_buffer_credits++; + } + return err; +} + +/** + * int jbd2_journal_stop() - complete a transaction + * @handle: tranaction to complete. + * + * All done for a particular handle. + * + * There is not much action needed here. We just return any remaining + * buffer credits to the transaction and remove the handle. The only + * complication is that we need to start a commit operation if the + * filesystem is marked for synchronous update. + * + * jbd2_journal_stop itself will not usually return an error, but it may + * do so in unusual circumstances. In particular, expect it to + * return -EIO if a jbd2_journal_abort has been executed since the + * transaction began. + */ +int jbd2_journal_stop(handle_t *handle) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal = transaction->t_journal; + int old_handle_count, err; + pid_t pid; + + J_ASSERT(transaction->t_updates > 0); + J_ASSERT(journal_current_handle() == handle); + + if (is_handle_aborted(handle)) + err = -EIO; + else + err = 0; + + if (--handle->h_ref > 0) { + jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, + handle->h_ref); + return err; + } + + jbd_debug(4, "Handle %p going down\n", handle); + + /* + * Implement synchronous transaction batching. If the handle + * was synchronous, don't force a commit immediately. Let's + * yield and let another thread piggyback onto this transaction. + * Keep doing that while new threads continue to arrive. + * It doesn't cost much - we're about to run a commit and sleep + * on IO anyway. Speeds up many-threaded, many-dir operations + * by 30x or more... + * + * But don't do this if this process was the most recent one to + * perform a synchronous write. We do this to detect the case where a + * single process is doing a stream of sync writes. No point in waiting + * for joiners in that case. + */ + pid = current->pid; + if (handle->h_sync && journal->j_last_sync_writer != pid) { + journal->j_last_sync_writer = pid; + do { + old_handle_count = transaction->t_handle_count; + schedule_timeout_uninterruptible(1); + } while (old_handle_count != transaction->t_handle_count); + } + + current->journal_info = NULL; + spin_lock(&journal->j_state_lock); + spin_lock(&transaction->t_handle_lock); + transaction->t_outstanding_credits -= handle->h_buffer_credits; + transaction->t_updates--; + if (!transaction->t_updates) { + wake_up(&journal->j_wait_updates); + if (journal->j_barrier_count) + wake_up(&journal->j_wait_transaction_locked); + } + + /* + * If the handle is marked SYNC, we need to set another commit + * going! We also want to force a commit if the current + * transaction is occupying too much of the log, or if the + * transaction is too old now. + */ + if (handle->h_sync || + transaction->t_outstanding_credits > + journal->j_max_transaction_buffers || + time_after_eq(jiffies, transaction->t_expires)) { + /* Do this even for aborted journals: an abort still + * completes the commit thread, it just doesn't write + * anything to disk. */ + tid_t tid = transaction->t_tid; + + spin_unlock(&transaction->t_handle_lock); + jbd_debug(2, "transaction too old, requesting commit for " + "handle %p\n", handle); + /* This is non-blocking */ + __jbd2_log_start_commit(journal, transaction->t_tid); + spin_unlock(&journal->j_state_lock); + + /* + * Special case: JBD2_SYNC synchronous updates require us + * to wait for the commit to complete. + */ + if (handle->h_sync && !(current->flags & PF_MEMALLOC)) + err = jbd2_log_wait_commit(journal, tid); + } else { + spin_unlock(&transaction->t_handle_lock); + spin_unlock(&journal->j_state_lock); + } + + jbd_free_handle(handle); + return err; +} + +/**int jbd2_journal_force_commit() - force any uncommitted transactions + * @journal: journal to force + * + * For synchronous operations: force any uncommitted transactions + * to disk. May seem kludgy, but it reuses all the handle batching + * code in a very simple manner. + */ +int jbd2_journal_force_commit(journal_t *journal) +{ + handle_t *handle; + int ret; + + handle = jbd2_journal_start(journal, 1); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + } else { + handle->h_sync = 1; + ret = jbd2_journal_stop(handle); + } + return ret; +} + +/* + * + * List management code snippets: various functions for manipulating the + * transaction buffer lists. + * + */ + +/* + * Append a buffer to a transaction list, given the transaction's list head + * pointer. + * + * j_list_lock is held. + * + * jbd_lock_bh_state(jh2bh(jh)) is held. + */ + +static inline void +__blist_add_buffer(struct journal_head **list, struct journal_head *jh) +{ + if (!*list) { + jh->b_tnext = jh->b_tprev = jh; + *list = jh; + } else { + /* Insert at the tail of the list to preserve order */ + struct journal_head *first = *list, *last = first->b_tprev; + jh->b_tprev = last; + jh->b_tnext = first; + last->b_tnext = first->b_tprev = jh; + } +} + +/* + * Remove a buffer from a transaction list, given the transaction's list + * head pointer. + * + * Called with j_list_lock held, and the journal may not be locked. + * + * jbd_lock_bh_state(jh2bh(jh)) is held. + */ + +static inline void +__blist_del_buffer(struct journal_head **list, struct journal_head *jh) +{ + if (*list == jh) { + *list = jh->b_tnext; + if (*list == jh) + *list = NULL; + } + jh->b_tprev->b_tnext = jh->b_tnext; + jh->b_tnext->b_tprev = jh->b_tprev; +} + +/* + * Remove a buffer from the appropriate transaction list. + * + * Note that this function can *change* the value of + * bh->b_transaction->t_sync_datalist, t_buffers, t_forget, + * t_iobuf_list, t_shadow_list, t_log_list or t_reserved_list. If the caller + * is holding onto a copy of one of thee pointers, it could go bad. + * Generally the caller needs to re-read the pointer from the transaction_t. + * + * Called under j_list_lock. The journal may not be locked. + */ +void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) +{ + struct journal_head **list = NULL; + transaction_t *transaction; + struct buffer_head *bh = jh2bh(jh); + + J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh)); + transaction = jh->b_transaction; + if (transaction) + assert_spin_locked(&transaction->t_journal->j_list_lock); + + J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); + if (jh->b_jlist != BJ_None) + J_ASSERT_JH(jh, transaction != 0); + + switch (jh->b_jlist) { + case BJ_None: + return; + case BJ_SyncData: + list = &transaction->t_sync_datalist; + break; + case BJ_Metadata: + transaction->t_nr_buffers--; + J_ASSERT_JH(jh, transaction->t_nr_buffers >= 0); + list = &transaction->t_buffers; + break; + case BJ_Forget: + list = &transaction->t_forget; + break; + case BJ_IO: + list = &transaction->t_iobuf_list; + break; + case BJ_Shadow: + list = &transaction->t_shadow_list; + break; + case BJ_LogCtl: + list = &transaction->t_log_list; + break; + case BJ_Reserved: + list = &transaction->t_reserved_list; + break; + case BJ_Locked: + list = &transaction->t_locked_list; + break; + } + + __blist_del_buffer(list, jh); + jh->b_jlist = BJ_None; + if (test_clear_buffer_jbddirty(bh)) + mark_buffer_dirty(bh); /* Expose it to the VM */ +} + +void __jbd2_journal_unfile_buffer(struct journal_head *jh) +{ + __jbd2_journal_temp_unlink_buffer(jh); + jh->b_transaction = NULL; +} + +void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) +{ + jbd_lock_bh_state(jh2bh(jh)); + spin_lock(&journal->j_list_lock); + __jbd2_journal_unfile_buffer(jh); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(jh2bh(jh)); +} + +/* + * Called from jbd2_journal_try_to_free_buffers(). + * + * Called under jbd_lock_bh_state(bh) + */ +static void +__journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) +{ + struct journal_head *jh; + + jh = bh2jh(bh); + + if (buffer_locked(bh) || buffer_dirty(bh)) + goto out; + + if (jh->b_next_transaction != 0) + goto out; + + spin_lock(&journal->j_list_lock); + if (jh->b_transaction != 0 && jh->b_cp_transaction == 0) { + if (jh->b_jlist == BJ_SyncData || jh->b_jlist == BJ_Locked) { + /* A written-back ordered data buffer */ + JBUFFER_TRACE(jh, "release data"); + __jbd2_journal_unfile_buffer(jh); + jbd2_journal_remove_journal_head(bh); + __brelse(bh); + } + } else if (jh->b_cp_transaction != 0 && jh->b_transaction == 0) { + /* written-back checkpointed metadata buffer */ + if (jh->b_jlist == BJ_None) { + JBUFFER_TRACE(jh, "remove from checkpoint list"); + __jbd2_journal_remove_checkpoint(jh); + jbd2_journal_remove_journal_head(bh); + __brelse(bh); + } + } + spin_unlock(&journal->j_list_lock); +out: + return; +} + + +/** + * int jbd2_journal_try_to_free_buffers() - try to free page buffers. + * @journal: journal for operation + * @page: to try and free + * @unused_gfp_mask: unused + * + * + * For all the buffers on this page, + * if they are fully written out ordered data, move them onto BUF_CLEAN + * so try_to_free_buffers() can reap them. + * + * This function returns non-zero if we wish try_to_free_buffers() + * to be called. We do this if the page is releasable by try_to_free_buffers(). + * We also do it if the page has locked or dirty buffers and the caller wants + * us to perform sync or async writeout. + * + * This complicates JBD locking somewhat. We aren't protected by the + * BKL here. We wish to remove the buffer from its committing or + * running transaction's ->t_datalist via __jbd2_journal_unfile_buffer. + * + * This may *change* the value of transaction_t->t_datalist, so anyone + * who looks at t_datalist needs to lock against this function. + * + * Even worse, someone may be doing a jbd2_journal_dirty_data on this + * buffer. So we need to lock against that. jbd2_journal_dirty_data() + * will come out of the lock with the buffer dirty, which makes it + * ineligible for release here. + * + * Who else is affected by this? hmm... Really the only contender + * is do_get_write_access() - it could be looking at the buffer while + * journal_try_to_free_buffer() is changing its state. But that + * cannot happen because we never reallocate freed data as metadata + * while the data is part of a transaction. Yes? + */ +int jbd2_journal_try_to_free_buffers(journal_t *journal, + struct page *page, gfp_t unused_gfp_mask) +{ + struct buffer_head *head; + struct buffer_head *bh; + int ret = 0; + + J_ASSERT(PageLocked(page)); + + head = page_buffers(page); + bh = head; + do { + struct journal_head *jh; + + /* + * We take our own ref against the journal_head here to avoid + * having to add tons of locking around each instance of + * jbd2_journal_remove_journal_head() and jbd2_journal_put_journal_head(). + */ + jh = jbd2_journal_grab_journal_head(bh); + if (!jh) + continue; + + jbd_lock_bh_state(bh); + __journal_try_to_free_buffer(journal, bh); + jbd2_journal_put_journal_head(jh); + jbd_unlock_bh_state(bh); + if (buffer_jbd(bh)) + goto busy; + } while ((bh = bh->b_this_page) != head); + ret = try_to_free_buffers(page); +busy: + return ret; +} + +/* + * This buffer is no longer needed. If it is on an older transaction's + * checkpoint list we need to record it on this transaction's forget list + * to pin this buffer (and hence its checkpointing transaction) down until + * this transaction commits. If the buffer isn't on a checkpoint list, we + * release it. + * Returns non-zero if JBD no longer has an interest in the buffer. + * + * Called under j_list_lock. + * + * Called under jbd_lock_bh_state(bh). + */ +static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) +{ + int may_free = 1; + struct buffer_head *bh = jh2bh(jh); + + __jbd2_journal_unfile_buffer(jh); + + if (jh->b_cp_transaction) { + JBUFFER_TRACE(jh, "on running+cp transaction"); + __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); + clear_buffer_jbddirty(bh); + may_free = 0; + } else { + JBUFFER_TRACE(jh, "on running transaction"); + jbd2_journal_remove_journal_head(bh); + __brelse(bh); + } + return may_free; +} + +/* + * jbd2_journal_invalidatepage + * + * This code is tricky. It has a number of cases to deal with. + * + * There are two invariants which this code relies on: + * + * i_size must be updated on disk before we start calling invalidatepage on the + * data. + * + * This is done in ext3 by defining an ext3_setattr method which + * updates i_size before truncate gets going. By maintaining this + * invariant, we can be sure that it is safe to throw away any buffers + * attached to the current transaction: once the transaction commits, + * we know that the data will not be needed. + * + * Note however that we can *not* throw away data belonging to the + * previous, committing transaction! + * + * Any disk blocks which *are* part of the previous, committing + * transaction (and which therefore cannot be discarded immediately) are + * not going to be reused in the new running transaction + * + * The bitmap committed_data images guarantee this: any block which is + * allocated in one transaction and removed in the next will be marked + * as in-use in the committed_data bitmap, so cannot be reused until + * the next transaction to delete the block commits. This means that + * leaving committing buffers dirty is quite safe: the disk blocks + * cannot be reallocated to a different file and so buffer aliasing is + * not possible. + * + * + * The above applies mainly to ordered data mode. In writeback mode we + * don't make guarantees about the order in which data hits disk --- in + * particular we don't guarantee that new dirty data is flushed before + * transaction commit --- so it is always safe just to discard data + * immediately in that mode. --sct + */ + +/* + * The journal_unmap_buffer helper function returns zero if the buffer + * concerned remains pinned as an anonymous buffer belonging to an older + * transaction. + * + * We're outside-transaction here. Either or both of j_running_transaction + * and j_committing_transaction may be NULL. + */ +static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) +{ + transaction_t *transaction; + struct journal_head *jh; + int may_free = 1; + int ret; + + BUFFER_TRACE(bh, "entry"); + + /* + * It is safe to proceed here without the j_list_lock because the + * buffers cannot be stolen by try_to_free_buffers as long as we are + * holding the page lock. --sct + */ + + if (!buffer_jbd(bh)) + goto zap_buffer_unlocked; + + spin_lock(&journal->j_state_lock); + jbd_lock_bh_state(bh); + spin_lock(&journal->j_list_lock); + + jh = jbd2_journal_grab_journal_head(bh); + if (!jh) + goto zap_buffer_no_jh; + + transaction = jh->b_transaction; + if (transaction == NULL) { + /* First case: not on any transaction. If it + * has no checkpoint link, then we can zap it: + * it's a writeback-mode buffer so we don't care + * if it hits disk safely. */ + if (!jh->b_cp_transaction) { + JBUFFER_TRACE(jh, "not on any transaction: zap"); + goto zap_buffer; + } + + if (!buffer_dirty(bh)) { + /* bdflush has written it. We can drop it now */ + goto zap_buffer; + } + + /* OK, it must be in the journal but still not + * written fully to disk: it's metadata or + * journaled data... */ + + if (journal->j_running_transaction) { + /* ... and once the current transaction has + * committed, the buffer won't be needed any + * longer. */ + JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget"); + ret = __dispose_buffer(jh, + journal->j_running_transaction); + jbd2_journal_put_journal_head(jh); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + spin_unlock(&journal->j_state_lock); + return ret; + } else { + /* There is no currently-running transaction. So the + * orphan record which we wrote for this file must have + * passed into commit. We must attach this buffer to + * the committing transaction, if it exists. */ + if (journal->j_committing_transaction) { + JBUFFER_TRACE(jh, "give to committing trans"); + ret = __dispose_buffer(jh, + journal->j_committing_transaction); + jbd2_journal_put_journal_head(jh); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + spin_unlock(&journal->j_state_lock); + return ret; + } else { + /* The orphan record's transaction has + * committed. We can cleanse this buffer */ + clear_buffer_jbddirty(bh); + goto zap_buffer; + } + } + } else if (transaction == journal->j_committing_transaction) { + if (jh->b_jlist == BJ_Locked) { + /* + * The buffer is on the committing transaction's locked + * list. We have the buffer locked, so I/O has + * completed. So we can nail the buffer now. + */ + may_free = __dispose_buffer(jh, transaction); + goto zap_buffer; + } + /* + * If it is committing, we simply cannot touch it. We + * can remove it's next_transaction pointer from the + * running transaction if that is set, but nothing + * else. */ + JBUFFER_TRACE(jh, "on committing transaction"); + set_buffer_freed(bh); + if (jh->b_next_transaction) { + J_ASSERT(jh->b_next_transaction == + journal->j_running_transaction); + jh->b_next_transaction = NULL; + } + jbd2_journal_put_journal_head(jh); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + spin_unlock(&journal->j_state_lock); + return 0; + } else { + /* Good, the buffer belongs to the running transaction. + * We are writing our own transaction's data, not any + * previous one's, so it is safe to throw it away + * (remember that we expect the filesystem to have set + * i_size already for this truncate so recovery will not + * expose the disk blocks we are discarding here.) */ + J_ASSERT_JH(jh, transaction == journal->j_running_transaction); + may_free = __dispose_buffer(jh, transaction); + } + +zap_buffer: + jbd2_journal_put_journal_head(jh); +zap_buffer_no_jh: + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + spin_unlock(&journal->j_state_lock); +zap_buffer_unlocked: + clear_buffer_dirty(bh); + J_ASSERT_BH(bh, !buffer_jbddirty(bh)); + clear_buffer_mapped(bh); + clear_buffer_req(bh); + clear_buffer_new(bh); + bh->b_bdev = NULL; + return may_free; +} + +/** + * void jbd2_journal_invalidatepage() + * @journal: journal to use for flush... + * @page: page to flush + * @offset: length of page to invalidate. + * + * Reap page buffers containing data after offset in page. + * + */ +void jbd2_journal_invalidatepage(journal_t *journal, + struct page *page, + unsigned long offset) +{ + struct buffer_head *head, *bh, *next; + unsigned int curr_off = 0; + int may_free = 1; + + if (!PageLocked(page)) + BUG(); + if (!page_has_buffers(page)) + return; + + /* We will potentially be playing with lists other than just the + * data lists (especially for journaled data mode), so be + * cautious in our locking. */ + + head = bh = page_buffers(page); + do { + unsigned int next_off = curr_off + bh->b_size; + next = bh->b_this_page; + + if (offset <= curr_off) { + /* This block is wholly outside the truncation point */ + lock_buffer(bh); + may_free &= journal_unmap_buffer(journal, bh); + unlock_buffer(bh); + } + curr_off = next_off; + bh = next; + + } while (bh != head); + + if (!offset) { + if (may_free && try_to_free_buffers(page)) + J_ASSERT(!page_has_buffers(page)); + } +} + +/* + * File a buffer on the given transaction list. + */ +void __jbd2_journal_file_buffer(struct journal_head *jh, + transaction_t *transaction, int jlist) +{ + struct journal_head **list = NULL; + int was_dirty = 0; + struct buffer_head *bh = jh2bh(jh); + + J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh)); + assert_spin_locked(&transaction->t_journal->j_list_lock); + + J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); + J_ASSERT_JH(jh, jh->b_transaction == transaction || + jh->b_transaction == 0); + + if (jh->b_transaction && jh->b_jlist == jlist) + return; + + /* The following list of buffer states needs to be consistent + * with __jbd_unexpected_dirty_buffer()'s handling of dirty + * state. */ + + if (jlist == BJ_Metadata || jlist == BJ_Reserved || + jlist == BJ_Shadow || jlist == BJ_Forget) { + if (test_clear_buffer_dirty(bh) || + test_clear_buffer_jbddirty(bh)) + was_dirty = 1; + } + + if (jh->b_transaction) + __jbd2_journal_temp_unlink_buffer(jh); + jh->b_transaction = transaction; + + switch (jlist) { + case BJ_None: + J_ASSERT_JH(jh, !jh->b_committed_data); + J_ASSERT_JH(jh, !jh->b_frozen_data); + return; + case BJ_SyncData: + list = &transaction->t_sync_datalist; + break; + case BJ_Metadata: + transaction->t_nr_buffers++; + list = &transaction->t_buffers; + break; + case BJ_Forget: + list = &transaction->t_forget; + break; + case BJ_IO: + list = &transaction->t_iobuf_list; + break; + case BJ_Shadow: + list = &transaction->t_shadow_list; + break; + case BJ_LogCtl: + list = &transaction->t_log_list; + break; + case BJ_Reserved: + list = &transaction->t_reserved_list; + break; + case BJ_Locked: + list = &transaction->t_locked_list; + break; + } + + __blist_add_buffer(list, jh); + jh->b_jlist = jlist; + + if (was_dirty) + set_buffer_jbddirty(bh); +} + +void jbd2_journal_file_buffer(struct journal_head *jh, + transaction_t *transaction, int jlist) +{ + jbd_lock_bh_state(jh2bh(jh)); + spin_lock(&transaction->t_journal->j_list_lock); + __jbd2_journal_file_buffer(jh, transaction, jlist); + spin_unlock(&transaction->t_journal->j_list_lock); + jbd_unlock_bh_state(jh2bh(jh)); +} + +/* + * Remove a buffer from its current buffer list in preparation for + * dropping it from its current transaction entirely. If the buffer has + * already started to be used by a subsequent transaction, refile the + * buffer on that transaction's metadata list. + * + * Called under journal->j_list_lock + * + * Called under jbd_lock_bh_state(jh2bh(jh)) + */ +void __jbd2_journal_refile_buffer(struct journal_head *jh) +{ + int was_dirty; + struct buffer_head *bh = jh2bh(jh); + + J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh)); + if (jh->b_transaction) + assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock); + + /* If the buffer is now unused, just drop it. */ + if (jh->b_next_transaction == NULL) { + __jbd2_journal_unfile_buffer(jh); + return; + } + + /* + * It has been modified by a later transaction: add it to the new + * transaction's metadata list. + */ + + was_dirty = test_clear_buffer_jbddirty(bh); + __jbd2_journal_temp_unlink_buffer(jh); + jh->b_transaction = jh->b_next_transaction; + jh->b_next_transaction = NULL; + __jbd2_journal_file_buffer(jh, jh->b_transaction, + was_dirty ? BJ_Metadata : BJ_Reserved); + J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING); + + if (was_dirty) + set_buffer_jbddirty(bh); +} + +/* + * For the unlocked version of this call, also make sure that any + * hanging journal_head is cleaned up if necessary. + * + * __jbd2_journal_refile_buffer is usually called as part of a single locked + * operation on a buffer_head, in which the caller is probably going to + * be hooking the journal_head onto other lists. In that case it is up + * to the caller to remove the journal_head if necessary. For the + * unlocked jbd2_journal_refile_buffer call, the caller isn't going to be + * doing anything else to the buffer so we need to do the cleanup + * ourselves to avoid a jh leak. + * + * *** The journal_head may be freed by this call! *** + */ +void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + jbd_lock_bh_state(bh); + spin_lock(&journal->j_list_lock); + + __jbd2_journal_refile_buffer(jh); + jbd_unlock_bh_state(bh); + jbd2_journal_remove_journal_head(bh); + + spin_unlock(&journal->j_list_lock); + __brelse(bh); +} diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 6de374513c0..bc4b8106a49 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -334,10 +334,10 @@ static int __init init_jffs2_fs(void) which means just 'no padding', without the alignment thing. But GCC doesn't have that -- we have to just hope the structs are the right sizes, instead. */ - BUG_ON(sizeof(struct jffs2_unknown_node) != 12); - BUG_ON(sizeof(struct jffs2_raw_dirent) != 40); - BUG_ON(sizeof(struct jffs2_raw_inode) != 68); - BUG_ON(sizeof(struct jffs2_raw_summary) != 32); + BUILD_BUG_ON(sizeof(struct jffs2_unknown_node) != 12); + BUILD_BUG_ON(sizeof(struct jffs2_raw_dirent) != 40); + BUILD_BUG_ON(sizeof(struct jffs2_raw_inode) != 68); + BUILD_BUG_ON(sizeof(struct jffs2_raw_summary) != 32); printk(KERN_INFO "JFFS2 version 2.2." #ifdef CONFIG_JFFS2_FS_WRITEBUFFER diff --git a/fs/minix/inode.c b/fs/minix/inode.c index c11a4b9fb86..1e36bae4d0e 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -149,12 +149,8 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) return -ENOMEM; s->s_fs_info = sbi; - /* N.B. These should be compile-time tests. - Unfortunately that is impossible. */ - if (32 != sizeof (struct minix_inode)) - panic("bad V1 i-node size"); - if (64 != sizeof(struct minix2_inode)) - panic("bad V2 i-node size"); + BUILD_BUG_ON(32 != sizeof (struct minix_inode)); + BUILD_BUG_ON(64 != sizeof(struct minix2_inode)); if (!sb_set_blocksize(s, BLOCK_SIZE)) goto out_bad_hblock; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 4c29cd7cc8e..76b46ebbb10 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -339,7 +339,7 @@ static unsigned long long ocfs2_max_file_offset(unsigned int blockshift) #if BITS_PER_LONG == 32 # if defined(CONFIG_LBD) - BUG_ON(sizeof(sector_t) != 8); + BUILD_BUG_ON(sizeof(sector_t) != 8); pagefactor = PAGE_CACHE_SIZE; bitshift = BITS_PER_LONG; # else diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index c89aa233819..9041802df83 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -430,20 +430,29 @@ int remove_save_link(struct inode *inode, int truncate) return journal_end(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT); } -static void reiserfs_put_super(struct super_block *s) +static void reiserfs_kill_sb(struct super_block *s) { - struct reiserfs_transaction_handle th; - th.t_trans_id = 0; + if (REISERFS_SB(s)) { + if (REISERFS_SB(s)->xattr_root) { + d_invalidate(REISERFS_SB(s)->xattr_root); + dput(REISERFS_SB(s)->xattr_root); + REISERFS_SB(s)->xattr_root = NULL; + } - if (REISERFS_SB(s)->xattr_root) { - d_invalidate(REISERFS_SB(s)->xattr_root); - dput(REISERFS_SB(s)->xattr_root); + if (REISERFS_SB(s)->priv_root) { + d_invalidate(REISERFS_SB(s)->priv_root); + dput(REISERFS_SB(s)->priv_root); + REISERFS_SB(s)->priv_root = NULL; + } } - if (REISERFS_SB(s)->priv_root) { - d_invalidate(REISERFS_SB(s)->priv_root); - dput(REISERFS_SB(s)->priv_root); - } + kill_block_super(s); +} + +static void reiserfs_put_super(struct super_block *s) +{ + struct reiserfs_transaction_handle th; + th.t_trans_id = 0; /* change file system state to current state if it was mounted with read-write permissions */ if (!(s->s_flags & MS_RDONLY)) { @@ -2156,7 +2165,7 @@ struct file_system_type reiserfs_fs_type = { .owner = THIS_MODULE, .name = "reiserfs", .get_sb = get_super_block, - .kill_sb = kill_block_super, + .kill_sb = reiserfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/super.c b/fs/super.c index aec99ddbe53..47e554c12e7 100644 --- a/fs/super.c +++ b/fs/super.c @@ -260,17 +260,17 @@ int fsync_super(struct super_block *sb) * that need destruction out of superblock, call generic_shutdown_super() * and release aforementioned objects. Note: dentries and inodes _are_ * taken care of and do not need specific handling. + * + * Upon calling this function, the filesystem may no longer alter or + * rearrange the set of dentries belonging to this super_block, nor may it + * change the attachments of dentries to inodes. */ void generic_shutdown_super(struct super_block *sb) { - struct dentry *root = sb->s_root; struct super_operations *sop = sb->s_op; - if (root) { - sb->s_root = NULL; - shrink_dcache_parent(root); - shrink_dcache_sb(sb); - dput(root); + if (sb->s_root) { + shrink_dcache_for_umount(sb); fsync_super(sb); lock_super(sb); sb->s_flags &= ~MS_ACTIVE; diff --git a/fs/sysv/super.c b/fs/sysv/super.c index 350cba5d680..dc9e7dc07fb 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -358,16 +358,11 @@ static int sysv_fill_super(struct super_block *sb, void *data, int silent) unsigned long blocknr; int size = 0, i; - if (1024 != sizeof (struct xenix_super_block)) - panic("Xenix FS: bad superblock size"); - if (512 != sizeof (struct sysv4_super_block)) - panic("SystemV FS: bad superblock size"); - if (512 != sizeof (struct sysv2_super_block)) - panic("SystemV FS: bad superblock size"); - if (500 != sizeof (struct coh_super_block)) - panic("Coherent FS: bad superblock size"); - if (64 != sizeof (struct sysv_inode)) - panic("sysv fs: bad inode size"); + BUILD_BUG_ON(1024 != sizeof (struct xenix_super_block)); + BUILD_BUG_ON(512 != sizeof (struct sysv4_super_block)); + BUILD_BUG_ON(512 != sizeof (struct sysv2_super_block)); + BUILD_BUG_ON(500 != sizeof (struct coh_super_block)); + BUILD_BUG_ON(64 != sizeof (struct sysv_inode)); sbi = kzalloc(sizeof(struct sysv_sb_info), GFP_KERNEL); if (!sbi) diff --git a/include/asm-alpha/io.h b/include/asm-alpha/io.h index f5ae98c25d1..5d15af24573 100644 --- a/include/asm-alpha/io.h +++ b/include/asm-alpha/io.h @@ -533,19 +533,6 @@ extern void outsl (unsigned long port, const void *src, unsigned long count); #define eth_io_copy_and_sum(skb,src,len,unused) \ memcpy_fromio((skb)->data,src,len) -static inline int -check_signature(const volatile void __iomem *io_addr, - const unsigned char *signature, int length) -{ - do { - if (readb(io_addr) != *signature) - return 0; - io_addr++; - signature++; - } while (--length); - return 1; -} - /* * The Alpha Jensen hardware for some rather strange reason puts * the RTC clock at 0x170 instead of 0x70. Probably due to some diff --git a/include/asm-arm/arch-versatile/hardware.h b/include/asm-arm/arch-versatile/hardware.h index 41c1bee342a..edc06598d18 100644 --- a/include/asm-arm/arch-versatile/hardware.h +++ b/include/asm-arm/arch-versatile/hardware.h @@ -28,8 +28,8 @@ /* * PCI space virtual addresses */ -#define VERSATILE_PCI_VIRT_BASE 0xe8000000 -#define VERSATILE_PCI_CFG_VIRT_BASE 0xe9000000 +#define VERSATILE_PCI_VIRT_BASE (void __iomem *)0xe8000000ul +#define VERSATILE_PCI_CFG_VIRT_BASE (void __iomem *)0xe9000000ul #if 0 #define VERSATILE_PCI_VIRT_MEM_BASE0 0xf4000000 diff --git a/include/asm-arm/io.h b/include/asm-arm/io.h index 34aaaac4f61..ae999fd5dc6 100644 --- a/include/asm-arm/io.h +++ b/include/asm-arm/io.h @@ -193,23 +193,6 @@ extern void _memset_io(volatile void __iomem *, int, size_t); #define eth_io_copy_and_sum(s,c,l,b) \ eth_copy_and_sum((s),__mem_pci(c),(l),(b)) -static inline int -check_signature(void __iomem *io_addr, const unsigned char *signature, - int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - #elif !defined(readb) #define readb(c) (__readwrite_bug("readb"),0) diff --git a/include/asm-arm/uaccess.h b/include/asm-arm/uaccess.h index 87aba57a66c..09ad0cab901 100644 --- a/include/asm-arm/uaccess.h +++ b/include/asm-arm/uaccess.h @@ -110,7 +110,7 @@ extern int __get_user_4(void *); #define get_user(x,p) \ ({ \ const register typeof(*(p)) __user *__p asm("r0") = (p);\ - register unsigned int __r2 asm("r2"); \ + register unsigned long __r2 asm("r2"); \ register int __e asm("r0"); \ switch (sizeof(*(__p))) { \ case 1: \ diff --git a/include/asm-avr32/irq_regs.h b/include/asm-avr32/irq_regs.h new file mode 100644 index 00000000000..3dd9c0b7027 --- /dev/null +++ b/include/asm-avr32/irq_regs.h @@ -0,0 +1 @@ +#include <asm-generic/irq_regs.h> diff --git a/include/asm-frv/io.h b/include/asm-frv/io.h index 7765f552889..20e44fe00ab 100644 --- a/include/asm-frv/io.h +++ b/include/asm-frv/io.h @@ -385,27 +385,6 @@ static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) */ #define xlate_dev_kmem_ptr(p) p -/* - * Check BIOS signature - */ -static inline int check_signature(volatile void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - - retval = 1; -out: - return retval; -} - #endif /* __KERNEL__ */ #endif /* _ASM_IO_H */ diff --git a/include/asm-generic/bitops/sched.h b/include/asm-generic/bitops/sched.h index 5ef93a4d009..815bb014806 100644 --- a/include/asm-generic/bitops/sched.h +++ b/include/asm-generic/bitops/sched.h @@ -15,7 +15,7 @@ static inline int sched_find_first_bit(const unsigned long *b) #if BITS_PER_LONG == 64 if (unlikely(b[0])) return __ffs(b[0]); - if (unlikely(b[1])) + if (likely(b[1])) return __ffs(b[1]) + 64; return __ffs(b[2]) + 128; #elif BITS_PER_LONG == 32 diff --git a/include/asm-i386/io.h b/include/asm-i386/io.h index b3724fe93ff..68df0dc3ab8 100644 --- a/include/asm-i386/io.h +++ b/include/asm-i386/io.h @@ -224,33 +224,6 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int #define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void __force *)(b),(c),(d)) -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ - -static inline int check_signature(volatile void __iomem * io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* * Cache management * diff --git a/include/asm-i386/uaccess.h b/include/asm-i386/uaccess.h index 54d905ebc63..eef5133b9ce 100644 --- a/include/asm-i386/uaccess.h +++ b/include/asm-i386/uaccess.h @@ -404,20 +404,6 @@ unsigned long __must_check __copy_from_user_ll_nocache_nozero(void *to, * anything, so this is accurate. */ -/** - * __copy_to_user: - Copy a block of data into user space, with less checking. - * @to: Destination address, in user space. - * @from: Source address, in kernel space. - * @n: Number of bytes to copy. - * - * Context: User context only. This function may sleep. - * - * Copy data from kernel space to user space. Caller must check - * the specified block with access_ok() before calling this function. - * - * Returns number of bytes that could not be copied. - * On success, this will be zero. - */ static __always_inline unsigned long __must_check __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { @@ -439,35 +425,27 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) return __copy_to_user_ll(to, from, n); } -static __always_inline unsigned long __must_check -__copy_to_user(void __user *to, const void *from, unsigned long n) -{ - might_sleep(); - return __copy_to_user_inatomic(to, from, n); -} - /** - * __copy_from_user: - Copy a block of data from user space, with less checking. - * @to: Destination address, in kernel space. - * @from: Source address, in user space. + * __copy_to_user: - Copy a block of data into user space, with less checking. + * @to: Destination address, in user space. + * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. This function may sleep. * - * Copy data from user space to kernel space. Caller must check + * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * * Returns number of bytes that could not be copied. * On success, this will be zero. - * - * If some data could not be copied, this function will pad the copied - * data to the requested size using zero bytes. - * - * An alternate version - __copy_from_user_inatomic() - may be called from - * atomic context and will fail rather than sleep. In this case the - * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h - * for explanation of why this is needed. */ +static __always_inline unsigned long __must_check +__copy_to_user(void __user *to, const void *from, unsigned long n) +{ + might_sleep(); + return __copy_to_user_inatomic(to, from, n); +} + static __always_inline unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { @@ -493,6 +471,29 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) } return __copy_from_user_ll_nozero(to, from, n); } + +/** + * __copy_from_user: - Copy a block of data from user space, with less checking. + * @to: Destination address, in kernel space. + * @from: Source address, in user space. + * @n: Number of bytes to copy. + * + * Context: User context only. This function may sleep. + * + * Copy data from user space to kernel space. Caller must check + * the specified block with access_ok() before calling this function. + * + * Returns number of bytes that could not be copied. + * On success, this will be zero. + * + * If some data could not be copied, this function will pad the copied + * data to the requested size using zero bytes. + * + * An alternate version - __copy_from_user_inatomic() - may be called from + * atomic context and will fail rather than sleep. In this case the + * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h + * for explanation of why this is needed. + */ static __always_inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h index 3ca7ab963d7..beeeaf6b054 100644 --- a/include/asm-i386/unistd.h +++ b/include/asm-i386/unistd.h @@ -324,10 +324,11 @@ #define __NR_vmsplice 316 #define __NR_move_pages 317 #define __NR_getcpu 318 +#define __NR_epoll_pwait 319 #ifdef __KERNEL__ -#define NR_syscalls 319 +#define NR_syscalls 320 #include <linux/err.h> /* diff --git a/include/asm-m32r/io.h b/include/asm-m32r/io.h index 70ad1c949c2..d06933bd631 100644 --- a/include/asm-m32r/io.h +++ b/include/asm-m32r/io.h @@ -166,38 +166,6 @@ static inline void _writel(unsigned long l, unsigned long addr) #define flush_write_buffers() do { } while (0) /* M32R_FIXME */ -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the ISA mmio address io_addr. - * Returns 1 on a match. - * - * This function is deprecated. New drivers should use ioremap and - * check_signature. - */ - -static inline int check_signature(void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; -#if 0 -printk("check_signature\n"); - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: -#endif - return retval; -} - static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count) { diff --git a/include/asm-m68k/uaccess.h b/include/asm-m68k/uaccess.h index 88b1f47400e..e4c9f080ff2 100644 --- a/include/asm-m68k/uaccess.h +++ b/include/asm-m68k/uaccess.h @@ -76,7 +76,7 @@ asm volatile ("\n" \ break; \ case 8: \ { \ - const void *__pu_ptr = (ptr); \ + const void __user *__pu_ptr = (ptr); \ asm volatile ("\n" \ "1: moves.l %2,(%1)+\n" \ "2: moves.l %R2,(%1)\n" \ @@ -125,7 +125,7 @@ asm volatile ("\n" \ " .previous" \ : "+d" (res), "=&" #reg (__gu_val) \ : "m" (*(ptr)), "i" (err)); \ - (x) = (typeof(*(ptr)))(long)__gu_val; \ + (x) = (typeof(*(ptr)))(unsigned long)__gu_val; \ }) #define __get_user(x, ptr) \ @@ -221,16 +221,16 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: - __get_user_asm(res, *(u8 *)to, (u8 *)from, u8, b, d, 1); + __get_user_asm(res, *(u8 *)to, (u8 __user *)from, u8, b, d, 1); break; case 2: - __get_user_asm(res, *(u16 *)to, (u16 *)from, u16, w, d, 2); + __get_user_asm(res, *(u16 *)to, (u16 __user *)from, u16, w, d, 2); break; case 3: __constant_copy_from_user_asm(res, to, from, tmp, 3, w, b,); break; case 4: - __get_user_asm(res, *(u32 *)to, (u32 *)from, u32, l, r, 4); + __get_user_asm(res, *(u32 *)to, (u32 __user *)from, u32, l, r, 4); break; case 5: __constant_copy_from_user_asm(res, to, from, tmp, 5, l, b,); @@ -302,16 +302,16 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n) switch (n) { case 1: - __put_user_asm(res, *(u8 *)from, (u8 *)to, b, d, 1); + __put_user_asm(res, *(u8 *)from, (u8 __user *)to, b, d, 1); break; case 2: - __put_user_asm(res, *(u16 *)from, (u16 *)to, w, d, 2); + __put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, d, 2); break; case 3: __constant_copy_to_user_asm(res, to, from, tmp, 3, w, b,); break; case 4: - __put_user_asm(res, *(u32 *)from, (u32 *)to, l, r, 4); + __put_user_asm(res, *(u32 *)from, (u32 __user *)to, l, r, 4); break; case 5: __constant_copy_to_user_asm(res, to, from, tmp, 5, l, b,); diff --git a/include/asm-mips/io.h b/include/asm-mips/io.h index df624e1ee6e..c2d124badbe 100644 --- a/include/asm-mips/io.h +++ b/include/asm-mips/io.h @@ -562,32 +562,6 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *); #define eth_io_copy_and_sum(skb,src,len,unused) memcpy_fromio((skb)->data,(src),(len)) /* - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ -static inline int check_signature(char __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - -/* * The caches on some architectures aren't dma-coherent and have need to * handle this in software. There are three types of operations that * can be applied to dma buffers. diff --git a/include/asm-powerpc/io.h b/include/asm-powerpc/io.h index cbbd8c648df..3baff8b0fd5 100644 --- a/include/asm-powerpc/io.h +++ b/include/asm-powerpc/io.h @@ -404,32 +404,6 @@ static inline void __out_be64(volatile unsigned long __iomem *addr, unsigned lon #include <asm/eeh.h> -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ -static inline int check_signature(const volatile void __iomem * io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* Nothing to do */ #define dma_cache_inv(_start,_size) do { } while (0) diff --git a/include/asm-ppc/io.h b/include/asm-ppc/io.h index 3d9a9e6f332..a4c411b753e 100644 --- a/include/asm-ppc/io.h +++ b/include/asm-ppc/io.h @@ -439,22 +439,6 @@ extern inline void * phys_to_virt(unsigned long address) #define iobarrier_r() eieio() #define iobarrier_w() eieio() -static inline int check_signature(volatile void __iomem * io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* * Here comes the ppc implementation of the IOMAP * interfaces. diff --git a/include/asm-sh/io.h b/include/asm-sh/io.h index ed12d38e8c0..a0e55b09e4f 100644 --- a/include/asm-sh/io.h +++ b/include/asm-sh/io.h @@ -304,22 +304,6 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags) #define iounmap(addr) \ __iounmap((addr)) -static inline int check_signature(char __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* * The caches on some architectures aren't dma-coherent and have need to * handle this in software. There are three types of operations that diff --git a/include/asm-sh64/io.h b/include/asm-sh64/io.h index 252fedbb662..14d8e7b4bf4 100644 --- a/include/asm-sh64/io.h +++ b/include/asm-sh64/io.h @@ -178,22 +178,6 @@ extern void iounmap(void *addr); unsigned long onchip_remap(unsigned long addr, unsigned long size, const char* name); extern void onchip_unmap(unsigned long vaddr); -static __inline__ int check_signature(volatile void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* * The caches on some architectures aren't dma-coherent and have need to * handle this in software. There are three types of operations that diff --git a/include/asm-sparc64/io.h b/include/asm-sparc64/io.h index 0056770e83a..30b912d8e8b 100644 --- a/include/asm-sparc64/io.h +++ b/include/asm-sparc64/io.h @@ -440,21 +440,6 @@ _memcpy_toio(volatile void __iomem *dst, const void *src, __kernel_size_t n) #define memcpy_toio(d,s,sz) _memcpy_toio(d,s,sz) -static inline int check_signature(void __iomem *io_addr, - const unsigned char *signature, - int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature++) - goto out; - io_addr++; - } while (--length); - retval = 1; -out: - return retval; -} - #define mmiowb() #ifdef __KERNEL__ diff --git a/include/asm-x86_64/io.h b/include/asm-x86_64/io.h index 70e91fe7634..6ee9fadaaac 100644 --- a/include/asm-x86_64/io.h +++ b/include/asm-x86_64/io.h @@ -254,33 +254,6 @@ void memset_io(volatile void __iomem *a, int b, size_t c); #define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void *)(b),(c),(d)) -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ - -static inline int check_signature(void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - /* Nothing to do */ #define dma_cache_inv(_start,_size) do { } while (0) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcc5de7cc48..64b4641904f 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -46,7 +46,8 @@ * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_scnprintf(buf, len, src, nbits) Print bitmap src to buf - * bitmap_parse(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf + * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf + * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf * bitmap_scnlistprintf(buf, len, src, nbits) Print bitmap src as list to buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from list * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region @@ -106,7 +107,9 @@ extern int __bitmap_weight(const unsigned long *bitmap, int bits); extern int bitmap_scnprintf(char *buf, unsigned int len, const unsigned long *src, int nbits); -extern int bitmap_parse(const char __user *ubuf, unsigned int ulen, +extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, + unsigned long *dst, int nbits); +extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern int bitmap_scnlistprintf(char *buf, unsigned int len, const unsigned long *src, int nbits); @@ -270,6 +273,12 @@ static inline void bitmap_shift_left(unsigned long *dst, __bitmap_shift_left(dst, src, n, nbits); } +static inline int bitmap_parse(const char *buf, unsigned int buflen, + unsigned long *maskp, int nmaskbits) +{ + return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits); +} + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/carta_random32.h b/include/linux/carta_random32.h new file mode 100644 index 00000000000..f6f3bd9f20b --- /dev/null +++ b/include/linux/carta_random32.h @@ -0,0 +1,29 @@ +/* + * Fast, simple, yet decent quality random number generator based on + * a paper by David G. Carta ("Two Fast Implementations of the + * `Minimal Standard' Random Number Generator," Communications of the + * ACM, January, 1990). + * + * Copyright (c) 2002-2006 Hewlett-Packard Development Company, L.P. + * Contributed by Stephane Eranian <eranian@hpl.hp.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + * 02111-1307 USA + */ +#ifndef _LINUX_CARTA_RANDOM32_H_ +#define _LINUX_CARTA_RANDOM32_H_ + +u64 carta_random32(u64 seed); + +#endif /* _LINUX_CARTA_RANDOM32_H_ */ diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h index 4e1663d7691..cfdb4f6a89d 100644 --- a/include/linux/compat_ioctl.h +++ b/include/linux/compat_ioctl.h @@ -61,17 +61,23 @@ COMPATIBLE_IOCTL(FIGETBSZ) * Some need translations, these do not. */ COMPATIBLE_IOCTL(HDIO_GET_IDENTITY) -COMPATIBLE_IOCTL(HDIO_SET_DMA) -COMPATIBLE_IOCTL(HDIO_SET_UNMASKINTR) -COMPATIBLE_IOCTL(HDIO_SET_NOWERR) -COMPATIBLE_IOCTL(HDIO_SET_32BIT) -COMPATIBLE_IOCTL(HDIO_SET_MULTCOUNT) -COMPATIBLE_IOCTL(HDIO_DRIVE_CMD) COMPATIBLE_IOCTL(HDIO_DRIVE_TASK) -COMPATIBLE_IOCTL(HDIO_SET_PIO_MODE) -COMPATIBLE_IOCTL(HDIO_SET_NICE) -COMPATIBLE_IOCTL(HDIO_SET_KEEPSETTINGS) +COMPATIBLE_IOCTL(HDIO_DRIVE_CMD) +ULONG_IOCTL(HDIO_SET_MULTCOUNT) +ULONG_IOCTL(HDIO_SET_UNMASKINTR) +ULONG_IOCTL(HDIO_SET_KEEPSETTINGS) +ULONG_IOCTL(HDIO_SET_32BIT) +ULONG_IOCTL(HDIO_SET_NOWERR) +ULONG_IOCTL(HDIO_SET_DMA) +ULONG_IOCTL(HDIO_SET_PIO_MODE) +ULONG_IOCTL(HDIO_SET_NICE) +ULONG_IOCTL(HDIO_SET_WCACHE) +ULONG_IOCTL(HDIO_SET_ACOUSTIC) +ULONG_IOCTL(HDIO_SET_BUSSTATE) +ULONG_IOCTL(HDIO_SET_ADDRESS) COMPATIBLE_IOCTL(HDIO_SCAN_HWIF) +/* 0x330 is reserved -- it used to be HDIO_GETGEO_BIG */ +COMPATIBLE_IOCTL(0x330) /* 0x02 -- Floppy ioctls */ COMPATIBLE_IOCTL(FDMSGON) COMPATIBLE_IOCTL(FDMSGOFF) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b268a3c0c37..d0e8c8b0e34 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -8,8 +8,8 @@ * See detailed comments in the file linux/bitmap.h describing the * data type on which these cpumasks are based. * - * For details of cpumask_scnprintf() and cpumask_parse(), - * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c. + * For details of cpumask_scnprintf() and cpumask_parse_user(), + * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. * For details of cpulist_scnprintf() and cpulist_parse(), see * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. * For details of cpu_remap(), see bitmap_bitremap in lib/bitmap.c @@ -49,7 +49,7 @@ * unsigned long *cpus_addr(mask) Array of unsigned long's in mask * * int cpumask_scnprintf(buf, len, mask) Format cpumask for printing - * int cpumask_parse(ubuf, ulen, mask) Parse ascii string as cpumask + * int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask * int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing * int cpulist_parse(buf, map) Parse ascii string as cpulist * int cpu_remap(oldbit, old, new) newbit = map(old, new)(oldbit) @@ -273,12 +273,12 @@ static inline int __cpumask_scnprintf(char *buf, int len, return bitmap_scnprintf(buf, len, srcp->bits, nbits); } -#define cpumask_parse(ubuf, ulen, dst) \ - __cpumask_parse((ubuf), (ulen), &(dst), NR_CPUS) -static inline int __cpumask_parse(const char __user *buf, int len, +#define cpumask_parse_user(ubuf, ulen, dst) \ + __cpumask_parse_user((ubuf), (ulen), &(dst), NR_CPUS) +static inline int __cpumask_parse_user(const char __user *buf, int len, cpumask_t *dstp, int nbits) { - return bitmap_parse(buf, len, dstp->bits, nbits); + return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define cpulist_scnprintf(buf, len, src) \ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 44605be5940..63f64a9a5bf 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -230,6 +230,7 @@ extern struct dentry * d_alloc_anon(struct inode *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); +extern void shrink_dcache_for_umount(struct super_block *); extern int d_invalidate(struct dentry *); /* only used at mount-time */ diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h new file mode 100644 index 00000000000..498503ee613 --- /dev/null +++ b/include/linux/ext4_fs.h @@ -0,0 +1,994 @@ +/* + * linux/include/linux/ext4_fs.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT4_FS_H +#define _LINUX_EXT4_FS_H + +#include <linux/types.h> +#include <linux/blkdev.h> +#include <linux/magic.h> + +/* + * The second extended filesystem constants/structures + */ + +/* + * Define EXT4FS_DEBUG to produce debug messages + */ +#undef EXT4FS_DEBUG + +/* + * Define EXT4_RESERVATION to reserve data blocks for expanding files + */ +#define EXT4_DEFAULT_RESERVE_BLOCKS 8 +/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ +#define EXT4_MAX_RESERVE_BLOCKS 1027 +#define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0 +/* + * Always enable hashed directories + */ +#define CONFIG_EXT4_INDEX + +/* + * Debug code + */ +#ifdef EXT4FS_DEBUG +#define ext4_debug(f, a...) \ + do { \ + printk (KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \ + __FILE__, __LINE__, __FUNCTION__); \ + printk (KERN_DEBUG f, ## a); \ + } while (0) +#else +#define ext4_debug(f, a...) do {} while (0) +#endif + +/* + * Special inodes numbers + */ +#define EXT4_BAD_INO 1 /* Bad blocks inode */ +#define EXT4_ROOT_INO 2 /* Root inode */ +#define EXT4_BOOT_LOADER_INO 5 /* Boot loader inode */ +#define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */ +#define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */ +#define EXT4_JOURNAL_INO 8 /* Journal inode */ + +/* First non-reserved inode for old ext4 filesystems */ +#define EXT4_GOOD_OLD_FIRST_INO 11 + +/* + * Maximal count of links to a file + */ +#define EXT4_LINK_MAX 32000 + +/* + * Macro-instructions used to manage several block sizes + */ +#define EXT4_MIN_BLOCK_SIZE 1024 +#define EXT4_MAX_BLOCK_SIZE 4096 +#define EXT4_MIN_BLOCK_LOG_SIZE 10 +#ifdef __KERNEL__ +# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) +#else +# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size) +#endif +#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof (__u32)) +#ifdef __KERNEL__ +# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) +#else +# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10) +#endif +#ifdef __KERNEL__ +#define EXT4_ADDR_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_addr_per_block_bits) +#define EXT4_INODE_SIZE(s) (EXT4_SB(s)->s_inode_size) +#define EXT4_FIRST_INO(s) (EXT4_SB(s)->s_first_ino) +#else +#define EXT4_INODE_SIZE(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ + EXT4_GOOD_OLD_INODE_SIZE : \ + (s)->s_inode_size) +#define EXT4_FIRST_INO(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \ + EXT4_GOOD_OLD_FIRST_INO : \ + (s)->s_first_ino) +#endif + +/* + * Macro-instructions used to manage fragments + */ +#define EXT4_MIN_FRAG_SIZE 1024 +#define EXT4_MAX_FRAG_SIZE 4096 +#define EXT4_MIN_FRAG_LOG_SIZE 10 +#ifdef __KERNEL__ +# define EXT4_FRAG_SIZE(s) (EXT4_SB(s)->s_frag_size) +# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_SB(s)->s_frags_per_block) +#else +# define EXT4_FRAG_SIZE(s) (EXT4_MIN_FRAG_SIZE << (s)->s_log_frag_size) +# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_FRAG_SIZE(s)) +#endif + +/* + * Structure of a blocks group descriptor + */ +struct ext4_group_desc +{ + __le32 bg_block_bitmap; /* Blocks bitmap block */ + __le32 bg_inode_bitmap; /* Inodes bitmap block */ + __le32 bg_inode_table; /* Inodes table block */ + __le16 bg_free_blocks_count; /* Free blocks count */ + __le16 bg_free_inodes_count; /* Free inodes count */ + __le16 bg_used_dirs_count; /* Directories count */ + __u16 bg_flags; + __u32 bg_reserved[3]; + __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ + __le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */ + __le32 bg_inode_table_hi; /* Inodes table block MSB */ +}; + +#ifdef __KERNEL__ +#include <linux/ext4_fs_i.h> +#include <linux/ext4_fs_sb.h> +#endif +/* + * Macro-instructions used to manage group descriptors + */ +#define EXT4_MIN_DESC_SIZE 32 +#define EXT4_MIN_DESC_SIZE_64BIT 64 +#define EXT4_MAX_DESC_SIZE EXT4_MIN_BLOCK_SIZE +#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size) +#ifdef __KERNEL__ +# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group) +# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block) +# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group) +# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits) +#else +# define EXT4_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group) +# define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s)) +# define EXT4_INODES_PER_GROUP(s) ((s)->s_inodes_per_group) +#endif + +/* + * Constants relative to the data blocks + */ +#define EXT4_NDIR_BLOCKS 12 +#define EXT4_IND_BLOCK EXT4_NDIR_BLOCKS +#define EXT4_DIND_BLOCK (EXT4_IND_BLOCK + 1) +#define EXT4_TIND_BLOCK (EXT4_DIND_BLOCK + 1) +#define EXT4_N_BLOCKS (EXT4_TIND_BLOCK + 1) + +/* + * Inode flags + */ +#define EXT4_SECRM_FL 0x00000001 /* Secure deletion */ +#define EXT4_UNRM_FL 0x00000002 /* Undelete */ +#define EXT4_COMPR_FL 0x00000004 /* Compress file */ +#define EXT4_SYNC_FL 0x00000008 /* Synchronous updates */ +#define EXT4_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define EXT4_APPEND_FL 0x00000020 /* writes to file may only append */ +#define EXT4_NODUMP_FL 0x00000040 /* do not dump file */ +#define EXT4_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define EXT4_DIRTY_FL 0x00000100 +#define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */ +#define EXT4_ECOMPR_FL 0x00000800 /* Compression error */ +/* End compression flags --- maybe not all used */ +#define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */ +#define EXT4_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ +#define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ +#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ + +#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */ +#define EXT4_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ + +/* + * Inode dynamic state flags + */ +#define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */ +#define EXT4_STATE_NEW 0x00000002 /* inode is newly created */ +#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */ + +/* Used to pass group descriptor data when online resize is done */ +struct ext4_new_group_input { + __u32 group; /* Group number for this data */ + __u64 block_bitmap; /* Absolute block number of block bitmap */ + __u64 inode_bitmap; /* Absolute block number of inode bitmap */ + __u64 inode_table; /* Absolute block number of inode table start */ + __u32 blocks_count; /* Total number of blocks in this group */ + __u16 reserved_blocks; /* Number of reserved blocks in this group */ + __u16 unused; +}; + +/* The struct ext4_new_group_input in kernel space, with free_blocks_count */ +struct ext4_new_group_data { + __u32 group; + __u64 block_bitmap; + __u64 inode_bitmap; + __u64 inode_table; + __u32 blocks_count; + __u16 reserved_blocks; + __u16 unused; + __u32 free_blocks_count; +}; + + +/* + * ioctl commands + */ +#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS +#define EXT4_IOC_GETVERSION _IOR('f', 3, long) +#define EXT4_IOC_SETVERSION _IOW('f', 4, long) +#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) +#define EXT4_IOC_GROUP_ADD _IOW('f', 8,struct ext4_new_group_input) +#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION +#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION +#ifdef CONFIG_JBD_DEBUG +#define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) +#endif +#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long) +#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long) + +/* + * ioctl commands in 32 bit emulation + */ +#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define EXT4_IOC32_GETVERSION _IOR('f', 3, int) +#define EXT4_IOC32_SETVERSION _IOW('f', 4, int) +#define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) +#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int) +#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) +#ifdef CONFIG_JBD_DEBUG +#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) +#endif +#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION +#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION + + +/* + * Mount options + */ +struct ext4_mount_options { + unsigned long s_mount_opt; + uid_t s_resuid; + gid_t s_resgid; + unsigned long s_commit_interval; +#ifdef CONFIG_QUOTA + int s_jquota_fmt; + char *s_qf_names[MAXQUOTAS]; +#endif +}; + +/* + * Structure of an inode on the disk + */ +struct ext4_inode { + __le16 i_mode; /* File mode */ + __le16 i_uid; /* Low 16 bits of Owner Uid */ + __le32 i_size; /* Size in bytes */ + __le32 i_atime; /* Access time */ + __le32 i_ctime; /* Creation time */ + __le32 i_mtime; /* Modification time */ + __le32 i_dtime; /* Deletion Time */ + __le16 i_gid; /* Low 16 bits of Group Id */ + __le16 i_links_count; /* Links count */ + __le32 i_blocks; /* Blocks count */ + __le32 i_flags; /* File flags */ + union { + struct { + __u32 l_i_reserved1; + } linux1; + struct { + __u32 h_i_translator; + } hurd1; + struct { + __u32 m_i_reserved1; + } masix1; + } osd1; /* OS dependent 1 */ + __le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */ + __le32 i_generation; /* File version (for NFS) */ + __le32 i_file_acl; /* File ACL */ + __le32 i_dir_acl; /* Directory ACL */ + __le32 i_faddr; /* Fragment address */ + union { + struct { + __u8 l_i_frag; /* Fragment number */ + __u8 l_i_fsize; /* Fragment size */ + __le16 l_i_file_acl_high; + __le16 l_i_uid_high; /* these 2 fields */ + __le16 l_i_gid_high; /* were reserved2[0] */ + __u32 l_i_reserved2; + } linux2; + struct { + __u8 h_i_frag; /* Fragment number */ + __u8 h_i_fsize; /* Fragment size */ + __u16 h_i_mode_high; + __u16 h_i_uid_high; + __u16 h_i_gid_high; + __u32 h_i_author; + } hurd2; + struct { + __u8 m_i_frag; /* Fragment number */ + __u8 m_i_fsize; /* Fragment size */ + __le16 m_i_file_acl_high; + __u32 m_i_reserved2[2]; + } masix2; + } osd2; /* OS dependent 2 */ + __le16 i_extra_isize; + __le16 i_pad1; +}; + +#define i_size_high i_dir_acl + +#if defined(__KERNEL__) || defined(__linux__) +#define i_reserved1 osd1.linux1.l_i_reserved1 +#define i_frag osd2.linux2.l_i_frag +#define i_fsize osd2.linux2.l_i_fsize +#define i_file_acl_high osd2.linux2.l_i_file_acl_high +#define i_uid_low i_uid +#define i_gid_low i_gid +#define i_uid_high osd2.linux2.l_i_uid_high +#define i_gid_high osd2.linux2.l_i_gid_high +#define i_reserved2 osd2.linux2.l_i_reserved2 + +#elif defined(__GNU__) + +#define i_translator osd1.hurd1.h_i_translator +#define i_frag osd2.hurd2.h_i_frag; +#define i_fsize osd2.hurd2.h_i_fsize; +#define i_uid_high osd2.hurd2.h_i_uid_high +#define i_gid_high osd2.hurd2.h_i_gid_high +#define i_author osd2.hurd2.h_i_author + +#elif defined(__masix__) + +#define i_reserved1 osd1.masix1.m_i_reserved1 +#define i_frag osd2.masix2.m_i_frag +#define i_fsize osd2.masix2.m_i_fsize +#define i_file_acl_high osd2.masix2.m_i_file_acl_high +#define i_reserved2 osd2.masix2.m_i_reserved2 + +#endif /* defined(__KERNEL__) || defined(__linux__) */ + +/* + * File system states + */ +#define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */ +#define EXT4_ERROR_FS 0x0002 /* Errors detected */ +#define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */ + +/* + * Mount flags + */ +#define EXT4_MOUNT_CHECK 0x00001 /* Do mount-time checks */ +#define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */ +#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ +#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ +#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ +#define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ +#define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ +#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ +#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ +#define EXT4_MOUNT_ABORT 0x00200 /* Fatal error detected */ +#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ +#define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ +#define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ +#define EXT4_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ +#define EXT4_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ +#define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ +#define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ +#define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ +#define EXT4_MOUNT_RESERVATION 0x10000 /* Preallocation */ +#define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */ +#define EXT4_MOUNT_NOBH 0x40000 /* No bufferheads */ +#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ +#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ +#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ +#define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */ + +/* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */ +#ifndef _LINUX_EXT2_FS_H +#define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt +#define set_opt(o, opt) o |= EXT4_MOUNT_##opt +#define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \ + EXT4_MOUNT_##opt) +#else +#define EXT2_MOUNT_NOLOAD EXT4_MOUNT_NOLOAD +#define EXT2_MOUNT_ABORT EXT4_MOUNT_ABORT +#define EXT2_MOUNT_DATA_FLAGS EXT4_MOUNT_DATA_FLAGS +#endif + +#define ext4_set_bit ext2_set_bit +#define ext4_set_bit_atomic ext2_set_bit_atomic +#define ext4_clear_bit ext2_clear_bit +#define ext4_clear_bit_atomic ext2_clear_bit_atomic +#define ext4_test_bit ext2_test_bit +#define ext4_find_first_zero_bit ext2_find_first_zero_bit +#define ext4_find_next_zero_bit ext2_find_next_zero_bit + +/* + * Maximal mount counts between two filesystem checks + */ +#define EXT4_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ +#define EXT4_DFL_CHECKINTERVAL 0 /* Don't use interval check */ + +/* + * Behaviour when detecting errors + */ +#define EXT4_ERRORS_CONTINUE 1 /* Continue execution */ +#define EXT4_ERRORS_RO 2 /* Remount fs read-only */ +#define EXT4_ERRORS_PANIC 3 /* Panic */ +#define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE + +/* + * Structure of the super block + */ +struct ext4_super_block { +/*00*/ __le32 s_inodes_count; /* Inodes count */ + __le32 s_blocks_count; /* Blocks count */ + __le32 s_r_blocks_count; /* Reserved blocks count */ + __le32 s_free_blocks_count; /* Free blocks count */ +/*10*/ __le32 s_free_inodes_count; /* Free inodes count */ + __le32 s_first_data_block; /* First Data Block */ + __le32 s_log_block_size; /* Block size */ + __le32 s_log_frag_size; /* Fragment size */ +/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */ + __le32 s_frags_per_group; /* # Fragments per group */ + __le32 s_inodes_per_group; /* # Inodes per group */ + __le32 s_mtime; /* Mount time */ +/*30*/ __le32 s_wtime; /* Write time */ + __le16 s_mnt_count; /* Mount count */ + __le16 s_max_mnt_count; /* Maximal mount count */ + __le16 s_magic; /* Magic signature */ + __le16 s_state; /* File system state */ + __le16 s_errors; /* Behaviour when detecting errors */ + __le16 s_minor_rev_level; /* minor revision level */ +/*40*/ __le32 s_lastcheck; /* time of last check */ + __le32 s_checkinterval; /* max. time between checks */ + __le32 s_creator_os; /* OS */ + __le32 s_rev_level; /* Revision level */ +/*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */ + __le16 s_def_resgid; /* Default gid for reserved blocks */ + /* + * These fields are for EXT4_DYNAMIC_REV superblocks only. + * + * Note: the difference between the compatible feature set and + * the incompatible feature set is that if there is a bit set + * in the incompatible feature set that the kernel doesn't + * know about, it should refuse to mount the filesystem. + * + * e2fsck's requirements are more strict; if it doesn't know + * about a feature in either the compatible or incompatible + * feature set, it must abort and not try to meddle with + * things it doesn't understand... + */ + __le32 s_first_ino; /* First non-reserved inode */ + __le16 s_inode_size; /* size of inode structure */ + __le16 s_block_group_nr; /* block group # of this superblock */ + __le32 s_feature_compat; /* compatible feature set */ +/*60*/ __le32 s_feature_incompat; /* incompatible feature set */ + __le32 s_feature_ro_compat; /* readonly-compatible feature set */ +/*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ +/*78*/ char s_volume_name[16]; /* volume name */ +/*88*/ char s_last_mounted[64]; /* directory where last mounted */ +/*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ + /* + * Performance hints. Directory preallocation should only + * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on. + */ + __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/ + __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */ + __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */ + /* + * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set. + */ +/*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */ +/*E0*/ __le32 s_journal_inum; /* inode number of journal file */ + __le32 s_journal_dev; /* device number of journal file */ + __le32 s_last_orphan; /* start of list of inodes to delete */ + __le32 s_hash_seed[4]; /* HTREE hash seed */ + __u8 s_def_hash_version; /* Default hash version to use */ + __u8 s_reserved_char_pad; + __le16 s_desc_size; /* size of group descriptor */ +/*100*/ __le32 s_default_mount_opts; + __le32 s_first_meta_bg; /* First metablock block group */ + __le32 s_mkfs_time; /* When the filesystem was created */ + __le32 s_jnl_blocks[17]; /* Backup of the journal inode */ + /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */ +/*150*/ __le32 s_blocks_count_hi; /* Blocks count */ + __le32 s_r_blocks_count_hi; /* Reserved blocks count */ + __le32 s_free_blocks_count_hi; /* Free blocks count */ + __u32 s_reserved[169]; /* Padding to the end of the block */ +}; + +#ifdef __KERNEL__ +static inline struct ext4_sb_info * EXT4_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} +static inline struct ext4_inode_info *EXT4_I(struct inode *inode) +{ + return container_of(inode, struct ext4_inode_info, vfs_inode); +} + +static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) +{ + return ino == EXT4_ROOT_INO || + ino == EXT4_JOURNAL_INO || + ino == EXT4_RESIZE_INO || + (ino >= EXT4_FIRST_INO(sb) && + ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); +} +#else +/* Assume that user mode programs are passing in an ext4fs superblock, not + * a kernel struct super_block. This will allow us to call the feature-test + * macros from user land. */ +#define EXT4_SB(sb) (sb) +#endif + +#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime + +/* + * Codes for operating systems + */ +#define EXT4_OS_LINUX 0 +#define EXT4_OS_HURD 1 +#define EXT4_OS_MASIX 2 +#define EXT4_OS_FREEBSD 3 +#define EXT4_OS_LITES 4 + +/* + * Revision levels + */ +#define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */ +#define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ + +#define EXT4_CURRENT_REV EXT4_GOOD_OLD_REV +#define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV + +#define EXT4_GOOD_OLD_INODE_SIZE 128 + +/* + * Feature set definitions + */ + +#define EXT4_HAS_COMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) ) +#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) ) +#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \ + ( EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) ) +#define EXT4_SET_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask) +#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask) +#define EXT4_SET_INCOMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask) +#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask) +#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask) +#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask) \ + EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask) + +#define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001 +#define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002 +#define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004 +#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008 +#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 +#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 + +#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 +#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 +#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 + +#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 +#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 +#define EXT4_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ +#define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ +#define EXT4_FEATURE_INCOMPAT_META_BG 0x0010 +#define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */ +#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080 + +#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR +#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \ + EXT4_FEATURE_INCOMPAT_RECOVER| \ + EXT4_FEATURE_INCOMPAT_META_BG| \ + EXT4_FEATURE_INCOMPAT_EXTENTS| \ + EXT4_FEATURE_INCOMPAT_64BIT) +#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ + EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ + EXT4_FEATURE_RO_COMPAT_BTREE_DIR) + +/* + * Default values for user and/or group using reserved blocks + */ +#define EXT4_DEF_RESUID 0 +#define EXT4_DEF_RESGID 0 + +/* + * Default mount options + */ +#define EXT4_DEFM_DEBUG 0x0001 +#define EXT4_DEFM_BSDGROUPS 0x0002 +#define EXT4_DEFM_XATTR_USER 0x0004 +#define EXT4_DEFM_ACL 0x0008 +#define EXT4_DEFM_UID16 0x0010 +#define EXT4_DEFM_JMODE 0x0060 +#define EXT4_DEFM_JMODE_DATA 0x0020 +#define EXT4_DEFM_JMODE_ORDERED 0x0040 +#define EXT4_DEFM_JMODE_WBACK 0x0060 + +/* + * Structure of a directory entry + */ +#define EXT4_NAME_LEN 255 + +struct ext4_dir_entry { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __le16 name_len; /* Name length */ + char name[EXT4_NAME_LEN]; /* File name */ +}; + +/* + * The new version of the directory entry. Since EXT4 structures are + * stored in intel byte order, and the name_len field could never be + * bigger than 255 chars, it's safe to reclaim the extra byte for the + * file_type field. + */ +struct ext4_dir_entry_2 { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __u8 name_len; /* Name length */ + __u8 file_type; + char name[EXT4_NAME_LEN]; /* File name */ +}; + +/* + * Ext4 directory file types. Only the low 3 bits are used. The + * other bits are reserved for now. + */ +#define EXT4_FT_UNKNOWN 0 +#define EXT4_FT_REG_FILE 1 +#define EXT4_FT_DIR 2 +#define EXT4_FT_CHRDEV 3 +#define EXT4_FT_BLKDEV 4 +#define EXT4_FT_FIFO 5 +#define EXT4_FT_SOCK 6 +#define EXT4_FT_SYMLINK 7 + +#define EXT4_FT_MAX 8 + +/* + * EXT4_DIR_PAD defines the directory entries boundaries + * + * NOTE: It must be a multiple of 4 + */ +#define EXT4_DIR_PAD 4 +#define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) +#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ + ~EXT4_DIR_ROUND) +/* + * Hash Tree Directory indexing + * (c) Daniel Phillips, 2001 + */ + +#ifdef CONFIG_EXT4_INDEX + #define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \ + EXT4_FEATURE_COMPAT_DIR_INDEX) && \ + (EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) +#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX) +#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) +#else + #define is_dx(dir) 0 +#define EXT4_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT4_LINK_MAX) +#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2) +#endif + +/* Legal values for the dx_root hash_version field: */ + +#define DX_HASH_LEGACY 0 +#define DX_HASH_HALF_MD4 1 +#define DX_HASH_TEA 2 + +#ifdef __KERNEL__ + +/* hash info structure used by the directory hash */ +struct dx_hash_info +{ + u32 hash; + u32 minor_hash; + int hash_version; + u32 *seed; +}; + +#define EXT4_HTREE_EOF 0x7fffffff + +/* + * Control parameters used by ext4_htree_next_block + */ +#define HASH_NB_ALWAYS 1 + + +/* + * Describe an inode's exact location on disk and in memory + */ +struct ext4_iloc +{ + struct buffer_head *bh; + unsigned long offset; + unsigned long block_group; +}; + +static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc) +{ + return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset); +} + +/* + * This structure is stuffed into the struct file's private_data field + * for directories. It is where we put information so that we can do + * readdir operations in hash tree order. + */ +struct dir_private_info { + struct rb_root root; + struct rb_node *curr_node; + struct fname *extra_fname; + loff_t last_pos; + __u32 curr_hash; + __u32 curr_minor_hash; + __u32 next_hash; +}; + +/* calculate the first block number of the group */ +static inline ext4_fsblk_t +ext4_group_first_block_no(struct super_block *sb, unsigned long group_no) +{ + return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); +} + +/* + * Special error return code only used by dx_probe() and its callers. + */ +#define ERR_BAD_DX_DIR -75000 + +void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, + unsigned long *blockgrpp, ext4_grpblk_t *offsetp); + +/* + * Function prototypes + */ + +/* + * Ok, these declarations are also in <linux/kernel.h> but none of the + * ext4 source programs needs to include it so they are duplicated here. + */ +# define NORET_TYPE /**/ +# define ATTRIB_NORET __attribute__((noreturn)) +# define NORET_AND noreturn, + +/* balloc.c */ +extern unsigned int ext4_block_group(struct super_block *sb, + ext4_fsblk_t blocknr); +extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb, + ext4_fsblk_t blocknr); +extern int ext4_bg_has_super(struct super_block *sb, int group); +extern unsigned long ext4_bg_num_gdb(struct super_block *sb, int group); +extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, int *errp); +extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode, + ext4_fsblk_t goal, unsigned long *count, int *errp); +extern void ext4_free_blocks (handle_t *handle, struct inode *inode, + ext4_fsblk_t block, unsigned long count); +extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb, + ext4_fsblk_t block, unsigned long count, + unsigned long *pdquot_freed_blocks); +extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *); +extern void ext4_check_blocks_bitmap (struct super_block *); +extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, + unsigned int block_group, + struct buffer_head ** bh); +extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); +extern void ext4_init_block_alloc_info(struct inode *); +extern void ext4_rsv_window_add(struct super_block *sb, struct ext4_reserve_window_node *rsv); + +/* dir.c */ +extern int ext4_check_dir_entry(const char *, struct inode *, + struct ext4_dir_entry_2 *, + struct buffer_head *, unsigned long); +extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, + __u32 minor_hash, + struct ext4_dir_entry_2 *dirent); +extern void ext4_htree_free_dir_info(struct dir_private_info *p); + +/* fsync.c */ +extern int ext4_sync_file (struct file *, struct dentry *, int); + +/* hash.c */ +extern int ext4fs_dirhash(const char *name, int len, struct + dx_hash_info *hinfo); + +/* ialloc.c */ +extern struct inode * ext4_new_inode (handle_t *, struct inode *, int); +extern void ext4_free_inode (handle_t *, struct inode *); +extern struct inode * ext4_orphan_get (struct super_block *, unsigned long); +extern unsigned long ext4_count_free_inodes (struct super_block *); +extern unsigned long ext4_count_dirs (struct super_block *); +extern void ext4_check_inodes_bitmap (struct super_block *); +extern unsigned long ext4_count_free (struct buffer_head *, unsigned); + + +/* inode.c */ +int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t blocknr); +struct buffer_head * ext4_getblk (handle_t *, struct inode *, long, int, int *); +struct buffer_head * ext4_bread (handle_t *, struct inode *, int, int, int *); +int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, + sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result, + int create, int extend_disksize); + +extern void ext4_read_inode (struct inode *); +extern int ext4_write_inode (struct inode *, int); +extern int ext4_setattr (struct dentry *, struct iattr *); +extern void ext4_delete_inode (struct inode *); +extern int ext4_sync_inode (handle_t *, struct inode *); +extern void ext4_discard_reservation (struct inode *); +extern void ext4_dirty_inode(struct inode *); +extern int ext4_change_inode_journal_flag(struct inode *, int); +extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *); +extern void ext4_truncate (struct inode *); +extern void ext4_set_inode_flags(struct inode *); +extern void ext4_set_aops(struct inode *inode); +extern int ext4_writepage_trans_blocks(struct inode *); +extern int ext4_block_truncate_page(handle_t *handle, struct page *page, + struct address_space *mapping, loff_t from); + +/* ioctl.c */ +extern int ext4_ioctl (struct inode *, struct file *, unsigned int, + unsigned long); +extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long); + +/* namei.c */ +extern int ext4_orphan_add(handle_t *, struct inode *); +extern int ext4_orphan_del(handle_t *, struct inode *); +extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, + __u32 start_minor_hash, __u32 *next_hash); + +/* resize.c */ +extern int ext4_group_add(struct super_block *sb, + struct ext4_new_group_data *input); +extern int ext4_group_extend(struct super_block *sb, + struct ext4_super_block *es, + ext4_fsblk_t n_blocks_count); + +/* super.c */ +extern void ext4_error (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void __ext4_std_error (struct super_block *, const char *, int); +extern void ext4_abort (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void ext4_warning (struct super_block *, const char *, const char *, ...) + __attribute__ ((format (printf, 3, 4))); +extern void ext4_update_dynamic_rev (struct super_block *sb); +extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, + struct ext4_group_desc *bg); +extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, + struct ext4_group_desc *bg); +extern ext4_fsblk_t ext4_inode_table(struct super_block *sb, + struct ext4_group_desc *bg); +extern void ext4_block_bitmap_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern void ext4_inode_bitmap_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); +extern void ext4_inode_table_set(struct super_block *sb, + struct ext4_group_desc *bg, ext4_fsblk_t blk); + +static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | + le32_to_cpu(es->s_blocks_count); +} + +static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) | + le32_to_cpu(es->s_r_blocks_count); +} + +static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es) +{ + return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) | + le32_to_cpu(es->s_free_blocks_count); +} + +static inline void ext4_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_blocks_count = cpu_to_le32((u32)blk); + es->s_blocks_count_hi = cpu_to_le32(blk >> 32); +} + +static inline void ext4_free_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_free_blocks_count = cpu_to_le32((u32)blk); + es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32); +} + +static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, + ext4_fsblk_t blk) +{ + es->s_r_blocks_count = cpu_to_le32((u32)blk); + es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); +} + + + +#define ext4_std_error(sb, errno) \ +do { \ + if ((errno)) \ + __ext4_std_error((sb), __FUNCTION__, (errno)); \ +} while (0) + +/* + * Inodes and files operations + */ + +/* dir.c */ +extern const struct file_operations ext4_dir_operations; + +/* file.c */ +extern struct inode_operations ext4_file_inode_operations; +extern const struct file_operations ext4_file_operations; + +/* namei.c */ +extern struct inode_operations ext4_dir_inode_operations; +extern struct inode_operations ext4_special_inode_operations; + +/* symlink.c */ +extern struct inode_operations ext4_symlink_inode_operations; +extern struct inode_operations ext4_fast_symlink_inode_operations; + +/* extents.c */ +extern int ext4_ext_tree_init(handle_t *handle, struct inode *); +extern int ext4_ext_writepage_trans_blocks(struct inode *, int); +extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, + ext4_fsblk_t iblock, + unsigned long max_blocks, struct buffer_head *bh_result, + int create, int extend_disksize); +extern void ext4_ext_truncate(struct inode *, struct page *); +extern void ext4_ext_init(struct super_block *); +extern void ext4_ext_release(struct super_block *); +static inline int +ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, + unsigned long max_blocks, struct buffer_head *bh, + int create, int extend_disksize) +{ + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) + return ext4_ext_get_blocks(handle, inode, block, max_blocks, + bh, create, extend_disksize); + return ext4_get_blocks_handle(handle, inode, block, max_blocks, bh, + create, extend_disksize); +} + + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_EXT4_FS_H */ diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h new file mode 100644 index 00000000000..a41cc24568c --- /dev/null +++ b/include/linux/ext4_fs_extents.h @@ -0,0 +1,198 @@ +/* + * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com + * Written by Alex Tomas <alex@clusterfs.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public Licens + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111- + */ + +#ifndef _LINUX_EXT4_EXTENTS +#define _LINUX_EXT4_EXTENTS + +#include <linux/ext4_fs.h> + +/* + * With AGRESSIVE_TEST defined, the capacity of index/leaf blocks + * becomes very small, so index split, in-depth growing and + * other hard changes happen much more often. + * This is for debug purposes only. + */ +#define AGRESSIVE_TEST_ + +/* + * With EXTENTS_STATS defined, the number of blocks and extents + * are collected in the truncate path. They'll be shown at + * umount time. + */ +#define EXTENTS_STATS__ + +/* + * If CHECK_BINSEARCH is defined, then the results of the binary search + * will also be checked by linear search. + */ +#define CHECK_BINSEARCH__ + +/* + * If EXT_DEBUG is defined you can use the 'extdebug' mount option + * to get lots of info about what's going on. + */ +#define EXT_DEBUG__ +#ifdef EXT_DEBUG +#define ext_debug(a...) printk(a) +#else +#define ext_debug(a...) +#endif + +/* + * If EXT_STATS is defined then stats numbers are collected. + * These number will be displayed at umount time. + */ +#define EXT_STATS_ + + +/* + * ext4_inode has i_block array (60 bytes total). + * The first 12 bytes store ext4_extent_header; + * the remainder stores an array of ext4_extent. + */ + +/* + * This is the extent on-disk structure. + * It's used at the bottom of the tree. + */ +struct ext4_extent { + __le32 ee_block; /* first logical block extent covers */ + __le16 ee_len; /* number of blocks covered by extent */ + __le16 ee_start_hi; /* high 16 bits of physical block */ + __le32 ee_start; /* low 32 bits of physical block */ +}; + +/* + * This is index on-disk structure. + * It's used at all the levels except the bottom. + */ +struct ext4_extent_idx { + __le32 ei_block; /* index covers logical blocks from 'block' */ + __le32 ei_leaf; /* pointer to the physical block of the next * + * level. leaf or next index could be there */ + __le16 ei_leaf_hi; /* high 16 bits of physical block */ + __u16 ei_unused; +}; + +/* + * Each block (leaves and indexes), even inode-stored has header. + */ +struct ext4_extent_header { + __le16 eh_magic; /* probably will support different formats */ + __le16 eh_entries; /* number of valid entries */ + __le16 eh_max; /* capacity of store in entries */ + __le16 eh_depth; /* has tree real underlying blocks? */ + __le32 eh_generation; /* generation of the tree */ +}; + +#define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) + +/* + * Array of ext4_ext_path contains path to some extent. + * Creation/lookup routines use it for traversal/splitting/etc. + * Truncate uses it to simulate recursive walking. + */ +struct ext4_ext_path { + ext4_fsblk_t p_block; + __u16 p_depth; + struct ext4_extent *p_ext; + struct ext4_extent_idx *p_idx; + struct ext4_extent_header *p_hdr; + struct buffer_head *p_bh; +}; + +/* + * structure for external API + */ + +#define EXT4_EXT_CACHE_NO 0 +#define EXT4_EXT_CACHE_GAP 1 +#define EXT4_EXT_CACHE_EXTENT 2 + +/* + * to be called by ext4_ext_walk_space() + * negative retcode - error + * positive retcode - signal for ext4_ext_walk_space(), see below + * callback must return valid extent (passed or newly created) + */ +typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, + struct ext4_ext_cache *, + void *); + +#define EXT_CONTINUE 0 +#define EXT_BREAK 1 +#define EXT_REPEAT 2 + + +#define EXT_MAX_BLOCK 0xffffffff + +#define EXT_MAX_LEN ((1UL << 15) - 1) + + +#define EXT_FIRST_EXTENT(__hdr__) \ + ((struct ext4_extent *) (((char *) (__hdr__)) + \ + sizeof(struct ext4_extent_header))) +#define EXT_FIRST_INDEX(__hdr__) \ + ((struct ext4_extent_idx *) (((char *) (__hdr__)) + \ + sizeof(struct ext4_extent_header))) +#define EXT_HAS_FREE_INDEX(__path__) \ + (le16_to_cpu((__path__)->p_hdr->eh_entries) \ + < le16_to_cpu((__path__)->p_hdr->eh_max)) +#define EXT_LAST_EXTENT(__hdr__) \ + (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) +#define EXT_LAST_INDEX(__hdr__) \ + (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) +#define EXT_MAX_EXTENT(__hdr__) \ + (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) +#define EXT_MAX_INDEX(__hdr__) \ + (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1) + +static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode) +{ + return (struct ext4_extent_header *) EXT4_I(inode)->i_data; +} + +static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh) +{ + return (struct ext4_extent_header *) bh->b_data; +} + +static inline unsigned short ext_depth(struct inode *inode) +{ + return le16_to_cpu(ext_inode_hdr(inode)->eh_depth); +} + +static inline void ext4_ext_tree_changed(struct inode *inode) +{ + EXT4_I(inode)->i_ext_generation++; +} + +static inline void +ext4_ext_invalidate_cache(struct inode *inode) +{ + EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO; +} + +extern int ext4_extent_tree_init(handle_t *, struct inode *); +extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *); +extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *); +extern int ext4_ext_walk_space(struct inode *, unsigned long, unsigned long, ext_prepare_callback, void *); +extern struct ext4_ext_path * ext4_ext_find_extent(struct inode *, int, struct ext4_ext_path *); + +#endif /* _LINUX_EXT4_EXTENTS */ + diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h new file mode 100644 index 00000000000..bb42379cb7f --- /dev/null +++ b/include/linux/ext4_fs_i.h @@ -0,0 +1,158 @@ +/* + * linux/include/linux/ext4_fs_i.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs_i.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT4_FS_I +#define _LINUX_EXT4_FS_I + +#include <linux/rwsem.h> +#include <linux/rbtree.h> +#include <linux/seqlock.h> +#include <linux/mutex.h> + +/* data type for block offset of block group */ +typedef int ext4_grpblk_t; + +/* data type for filesystem-wide blocks number */ +typedef unsigned long long ext4_fsblk_t; + +struct ext4_reserve_window { + ext4_fsblk_t _rsv_start; /* First byte reserved */ + ext4_fsblk_t _rsv_end; /* Last byte reserved or 0 */ +}; + +struct ext4_reserve_window_node { + struct rb_node rsv_node; + __u32 rsv_goal_size; + __u32 rsv_alloc_hit; + struct ext4_reserve_window rsv_window; +}; + +struct ext4_block_alloc_info { + /* information about reservation window */ + struct ext4_reserve_window_node rsv_window_node; + /* + * was i_next_alloc_block in ext4_inode_info + * is the logical (file-relative) number of the + * most-recently-allocated block in this file. + * We use this for detecting linearly ascending allocation requests. + */ + __u32 last_alloc_logical_block; + /* + * Was i_next_alloc_goal in ext4_inode_info + * is the *physical* companion to i_next_alloc_block. + * it the the physical block number of the block which was most-recentl + * allocated to this file. This give us the goal (target) for the next + * allocation when we detect linearly ascending requests. + */ + ext4_fsblk_t last_alloc_physical_block; +}; + +#define rsv_start rsv_window._rsv_start +#define rsv_end rsv_window._rsv_end + +/* + * storage for cached extent + */ +struct ext4_ext_cache { + ext4_fsblk_t ec_start; + __u32 ec_block; + __u32 ec_len; /* must be 32bit to return holes */ + __u32 ec_type; +}; + +/* + * third extended file system inode data in memory + */ +struct ext4_inode_info { + __le32 i_data[15]; /* unconverted */ + __u32 i_flags; +#ifdef EXT4_FRAGMENTS + __u32 i_faddr; + __u8 i_frag_no; + __u8 i_frag_size; +#endif + ext4_fsblk_t i_file_acl; + __u32 i_dir_acl; + __u32 i_dtime; + + /* + * i_block_group is the number of the block group which contains + * this file's inode. Constant across the lifetime of the inode, + * it is ued for making block allocation decisions - we try to + * place a file's data blocks near its inode block, and new inodes + * near to their parent directory's inode. + */ + __u32 i_block_group; + __u32 i_state; /* Dynamic state flags for ext4 */ + + /* block reservation info */ + struct ext4_block_alloc_info *i_block_alloc_info; + + __u32 i_dir_start_lookup; +#ifdef CONFIG_EXT4DEV_FS_XATTR + /* + * Extended attributes can be read independently of the main file + * data. Taking i_mutex even when reading would cause contention + * between readers of EAs and writers of regular file data, so + * instead we synchronize on xattr_sem when reading or changing + * EAs. + */ + struct rw_semaphore xattr_sem; +#endif +#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL + struct posix_acl *i_acl; + struct posix_acl *i_default_acl; +#endif + + struct list_head i_orphan; /* unlinked but open inodes */ + + /* + * i_disksize keeps track of what the inode size is ON DISK, not + * in memory. During truncate, i_size is set to the new size by + * the VFS prior to calling ext4_truncate(), but the filesystem won't + * set i_disksize to 0 until the truncate is actually under way. + * + * The intent is that i_disksize always represents the blocks which + * are used by this file. This allows recovery to restart truncate + * on orphans if we crash during truncate. We actually write i_disksize + * into the on-disk inode when writing inodes out, instead of i_size. + * + * The only time when i_disksize and i_size may be different is when + * a truncate is in progress. The only things which change i_disksize + * are ext4_get_block (growth) and ext4_truncate (shrinkth). + */ + loff_t i_disksize; + + /* on-disk additional length */ + __u16 i_extra_isize; + + /* + * truncate_mutex is for serialising ext4_truncate() against + * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's + * data tree are chopped off during truncate. We can't do that in + * ext4 because whenever we perform intermediate commits during + * truncate, the inode and all the metadata blocks *must* be in a + * consistent state which allows truncation of the orphans to restart + * during recovery. Hence we must fix the get_block-vs-truncate race + * by other means, so we have truncate_mutex. + */ + struct mutex truncate_mutex; + struct inode vfs_inode; + + unsigned long i_ext_generation; + struct ext4_ext_cache i_cached_extent; +}; + +#endif /* _LINUX_EXT4_FS_I */ diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h new file mode 100644 index 00000000000..691a713139c --- /dev/null +++ b/include/linux/ext4_fs_sb.h @@ -0,0 +1,94 @@ +/* + * linux/include/linux/ext4_fs_sb.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs_sb.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_EXT4_FS_SB +#define _LINUX_EXT4_FS_SB + +#ifdef __KERNEL__ +#include <linux/timer.h> +#include <linux/wait.h> +#include <linux/blockgroup_lock.h> +#include <linux/percpu_counter.h> +#endif +#include <linux/rbtree.h> + +/* + * third extended-fs super-block data in memory + */ +struct ext4_sb_info { + unsigned long s_frag_size; /* Size of a fragment in bytes */ + unsigned long s_desc_size; /* Size of a group descriptor in bytes */ + unsigned long s_frags_per_block;/* Number of fragments per block */ + unsigned long s_inodes_per_block;/* Number of inodes per block */ + unsigned long s_frags_per_group;/* Number of fragments in a group */ + unsigned long s_blocks_per_group;/* Number of blocks in a group */ + unsigned long s_inodes_per_group;/* Number of inodes in a group */ + unsigned long s_itb_per_group; /* Number of inode table blocks per group */ + unsigned long s_gdb_count; /* Number of group descriptor blocks */ + unsigned long s_desc_per_block; /* Number of group descriptors per block */ + unsigned long s_groups_count; /* Number of groups in the fs */ + struct buffer_head * s_sbh; /* Buffer containing the super block */ + struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */ + struct buffer_head ** s_group_desc; + unsigned long s_mount_opt; + uid_t s_resuid; + gid_t s_resgid; + unsigned short s_mount_state; + unsigned short s_pad; + int s_addr_per_block_bits; + int s_desc_per_block_bits; + int s_inode_size; + int s_first_ino; + spinlock_t s_next_gen_lock; + u32 s_next_generation; + u32 s_hash_seed[4]; + int s_def_hash_version; + struct percpu_counter s_freeblocks_counter; + struct percpu_counter s_freeinodes_counter; + struct percpu_counter s_dirs_counter; + struct blockgroup_lock s_blockgroup_lock; + + /* root of the per fs reservation window tree */ + spinlock_t s_rsv_window_lock; + struct rb_root s_rsv_window_root; + struct ext4_reserve_window_node s_rsv_window_head; + + /* Journaling */ + struct inode * s_journal_inode; + struct journal_s * s_journal; + struct list_head s_orphan; + unsigned long s_commit_interval; + struct block_device *journal_bdev; +#ifdef CONFIG_JBD_DEBUG + struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */ + wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */ +#endif +#ifdef CONFIG_QUOTA + char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ + int s_jquota_fmt; /* Format of quota to use */ +#endif + +#ifdef EXTENTS_STATS + /* ext4 extents stats */ + unsigned long s_ext_min; + unsigned long s_ext_max; + unsigned long s_depth_max; + spinlock_t s_ext_stats_lock; + unsigned long s_ext_blocks; + unsigned long s_ext_extents; +#endif +}; + +#endif /* _LINUX_EXT4_FS_SB */ diff --git a/include/linux/ext4_jbd2.h b/include/linux/ext4_jbd2.h new file mode 100644 index 00000000000..72dd631912e --- /dev/null +++ b/include/linux/ext4_jbd2.h @@ -0,0 +1,273 @@ +/* + * linux/include/linux/ext4_jbd2.h + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 + * + * Copyright 1998--1999 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Ext4-specific journaling extensions. + */ + +#ifndef _LINUX_EXT4_JBD_H +#define _LINUX_EXT4_JBD_H + +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/ext4_fs.h> + +#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) + +/* Define the number of blocks we need to account to a transaction to + * modify one block of data. + * + * We may have to touch one inode, one bitmap buffer, up to three + * indirection blocks, the group and superblock summaries, and the data + * block to complete the transaction. + * + * For extents-enabled fs we may have to allocate and modify up to + * 5 levels of tree + root which are stored in the inode. */ + +#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ + (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \ + || test_opt(sb, EXTENTS) ? 27U : 8U) + +/* Extended attribute operations touch at most two data buffers, + * two bitmap buffers, and two group summaries, in addition to the inode + * and the superblock, which are already accounted for. */ + +#define EXT4_XATTR_TRANS_BLOCKS 6U + +/* Define the minimum size for a transaction which modifies data. This + * needs to take into account the fact that we may end up modifying two + * quota files too (one for the group, one for the user quota). The + * superblock only gets updated once, of course, so don't bother + * counting that again for the quota updates. */ + +#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ + EXT4_XATTR_TRANS_BLOCKS - 2 + \ + 2*EXT4_QUOTA_TRANS_BLOCKS(sb)) + +/* Delete operations potentially hit one directory's namespace plus an + * entire inode, plus arbitrary amounts of bitmap/indirection data. Be + * generous. We can grow the delete transaction later if necessary. */ + +#define EXT4_DELETE_TRANS_BLOCKS(sb) (2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64) + +/* Define an arbitrary limit for the amount of data we will anticipate + * writing to any given transaction. For unbounded transactions such as + * write(2) and truncate(2) we can write more than this, but we always + * start off at the maximum transaction size and grow the transaction + * optimistically as we go. */ + +#define EXT4_MAX_TRANS_DATA 64U + +/* We break up a large truncate or write transaction once the handle's + * buffer credits gets this low, we need either to extend the + * transaction or to start a new one. Reserve enough space here for + * inode, bitmap, superblock, group and indirection updates for at least + * one block, plus two quota updates. Quota allocations are not + * needed. */ + +#define EXT4_RESERVE_TRANS_BLOCKS 12U + +#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8 + +#ifdef CONFIG_QUOTA +/* Amount of blocks needed for quota update - we know that the structure was + * allocated so we need to update only inode+data */ +#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) +/* Amount of blocks needed for quota insert/delete - we do some block writes + * but inode, sb and group updates are done only once */ +#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ + (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0) +#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ + (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0) +#else +#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 +#define EXT4_QUOTA_INIT_BLOCKS(sb) 0 +#define EXT4_QUOTA_DEL_BLOCKS(sb) 0 +#endif + +int +ext4_mark_iloc_dirty(handle_t *handle, + struct inode *inode, + struct ext4_iloc *iloc); + +/* + * On success, We end up with an outstanding reference count against + * iloc->bh. This _must_ be cleaned up later. + */ + +int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, + struct ext4_iloc *iloc); + +int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode); + +/* + * Wrapper functions with which ext4 calls into JBD. The intent here is + * to allow these to be turned into appropriate stubs so ext4 can control + * ext2 filesystems, so ext2+ext4 systems only nee one fs. This work hasn't + * been done yet. + */ + +void ext4_journal_abort_handle(const char *caller, const char *err_fn, + struct buffer_head *bh, handle_t *handle, int err); + +static inline int +__ext4_journal_get_undo_access(const char *where, handle_t *handle, + struct buffer_head *bh) +{ + int err = jbd2_journal_get_undo_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_get_write_access(const char *where, handle_t *handle, + struct buffer_head *bh) +{ + int err = jbd2_journal_get_write_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline void +ext4_journal_release_buffer(handle_t *handle, struct buffer_head *bh) +{ + jbd2_journal_release_buffer(handle, bh); +} + +static inline int +__ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh) +{ + int err = jbd2_journal_forget(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_revoke(const char *where, handle_t *handle, + ext4_fsblk_t blocknr, struct buffer_head *bh) +{ + int err = jbd2_journal_revoke(handle, blocknr, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_get_create_access(const char *where, + handle_t *handle, struct buffer_head *bh) +{ + int err = jbd2_journal_get_create_access(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + +static inline int +__ext4_journal_dirty_metadata(const char *where, + handle_t *handle, struct buffer_head *bh) +{ + int err = jbd2_journal_dirty_metadata(handle, bh); + if (err) + ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err); + return err; +} + + +#define ext4_journal_get_undo_access(handle, bh) \ + __ext4_journal_get_undo_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_get_write_access(handle, bh) \ + __ext4_journal_get_write_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_revoke(handle, blocknr, bh) \ + __ext4_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh)) +#define ext4_journal_get_create_access(handle, bh) \ + __ext4_journal_get_create_access(__FUNCTION__, (handle), (bh)) +#define ext4_journal_dirty_metadata(handle, bh) \ + __ext4_journal_dirty_metadata(__FUNCTION__, (handle), (bh)) +#define ext4_journal_forget(handle, bh) \ + __ext4_journal_forget(__FUNCTION__, (handle), (bh)) + +int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh); + +handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); +int __ext4_journal_stop(const char *where, handle_t *handle); + +static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks) +{ + return ext4_journal_start_sb(inode->i_sb, nblocks); +} + +#define ext4_journal_stop(handle) \ + __ext4_journal_stop(__FUNCTION__, (handle)) + +static inline handle_t *ext4_journal_current_handle(void) +{ + return journal_current_handle(); +} + +static inline int ext4_journal_extend(handle_t *handle, int nblocks) +{ + return jbd2_journal_extend(handle, nblocks); +} + +static inline int ext4_journal_restart(handle_t *handle, int nblocks) +{ + return jbd2_journal_restart(handle, nblocks); +} + +static inline int ext4_journal_blocks_per_page(struct inode *inode) +{ + return jbd2_journal_blocks_per_page(inode); +} + +static inline int ext4_journal_force_commit(journal_t *journal) +{ + return jbd2_journal_force_commit(journal); +} + +/* super.c */ +int ext4_force_commit(struct super_block *sb); + +static inline int ext4_should_journal_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 1; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) + return 1; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 1; + return 0; +} + +static inline int ext4_should_order_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) + return 1; + return 0; +} + +static inline int ext4_should_writeback_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) + return 1; + return 0; +} + +#endif /* _LINUX_EXT4_JBD_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c25a38d8f60..5081d27bfa2 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -17,6 +17,7 @@ int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user * int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); +void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); int hugetlb_prefault(struct address_space *, struct vm_area_struct *); int hugetlb_report_meminfo(char *); int hugetlb_report_node_meminfo(int, char *); diff --git a/include/linux/io.h b/include/linux/io.h index 2ad96c3f0e4..81877ea3930 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -28,4 +28,31 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count); int ioremap_page_range(unsigned long addr, unsigned long end, unsigned long phys_addr, pgprot_t prot); +/** + * check_signature - find BIOS signatures + * @io_addr: mmio address to check + * @signature: signature block + * @length: length of signature + * + * Perform a signature comparison with the mmio address io_addr. This + * address should have been obtained by ioremap. + * Returns 1 on a match. + */ + +static inline int check_signature(const volatile void __iomem *io_addr, + const unsigned char *signature, int length) +{ + int retval = 0; + do { + if (readb(io_addr) != *signature) + goto out; + io_addr++; + signature++; + length--; + } while (length); + retval = 1; +out: + return retval; +} + #endif /* _LINUX_IO_H */ diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h new file mode 100644 index 00000000000..ddb12879578 --- /dev/null +++ b/include/linux/jbd2.h @@ -0,0 +1,1107 @@ +/* + * linux/include/linux/jbd2.h + * + * Written by Stephen C. Tweedie <sct@redhat.com> + * + * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * Definitions for transaction data structures for the buffer cache + * filesystem journaling support. + */ + +#ifndef _LINUX_JBD_H +#define _LINUX_JBD_H + +/* Allow this file to be included directly into e2fsprogs */ +#ifndef __KERNEL__ +#include "jfs_compat.h" +#define JBD2_DEBUG +#define jfs_debug jbd_debug +#else + +#include <linux/types.h> +#include <linux/buffer_head.h> +#include <linux/journal-head.h> +#include <linux/stddef.h> +#include <linux/bit_spinlock.h> +#include <linux/mutex.h> +#include <linux/timer.h> + +#include <asm/semaphore.h> +#endif + +#define journal_oom_retry 1 + +/* + * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds + * certain classes of error which can occur due to failed IOs. Under + * normal use we want ext3 to continue after such errors, because + * hardware _can_ fail, but for debugging purposes when running tests on + * known-good hardware we may want to trap these errors. + */ +#undef JBD_PARANOID_IOFAIL + +/* + * The default maximum commit age, in seconds. + */ +#define JBD_DEFAULT_MAX_COMMIT_AGE 5 + +#ifdef CONFIG_JBD_DEBUG +/* + * Define JBD_EXPENSIVE_CHECKING to enable more expensive internal + * consistency checks. By default we don't do this unless + * CONFIG_JBD_DEBUG is on. + */ +#define JBD_EXPENSIVE_CHECKING +extern int jbd2_journal_enable_debug; + +#define jbd_debug(n, f, a...) \ + do { \ + if ((n) <= jbd2_journal_enable_debug) { \ + printk (KERN_DEBUG "(%s, %d): %s: ", \ + __FILE__, __LINE__, __FUNCTION__); \ + printk (f, ## a); \ + } \ + } while (0) +#else +#define jbd_debug(f, a...) /**/ +#endif + +extern void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry); +extern void * jbd2_slab_alloc(size_t size, gfp_t flags); +extern void jbd2_slab_free(void *ptr, size_t size); + +#define jbd_kmalloc(size, flags) \ + __jbd2_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry) +#define jbd_rep_kmalloc(size, flags) \ + __jbd2_kmalloc(__FUNCTION__, (size), (flags), 1) + +#define JBD2_MIN_JOURNAL_BLOCKS 1024 + +#ifdef __KERNEL__ + +/** + * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. + * + * All filesystem modifications made by the process go + * through this handle. Recursive operations (such as quota operations) + * are gathered into a single update. + * + * The buffer credits field is used to account for journaled buffers + * being modified by the running process. To ensure that there is + * enough log space for all outstanding operations, we need to limit the + * number of outstanding buffers possible at any time. When the + * operation completes, any buffer credits not used are credited back to + * the transaction, so that at all times we know how many buffers the + * outstanding updates on a transaction might possibly touch. + * + * This is an opaque datatype. + **/ +typedef struct handle_s handle_t; /* Atomic operation type */ + + +/** + * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. + * + * journal_t is linked to from the fs superblock structure. + * + * We use the journal_t to keep track of all outstanding transaction + * activity on the filesystem, and to manage the state of the log + * writing process. + * + * This is an opaque datatype. + **/ +typedef struct journal_s journal_t; /* Journal control structure */ +#endif + +/* + * Internal structures used by the logging mechanism: + */ + +#define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ + +/* + * On-disk structures + */ + +/* + * Descriptor block types: + */ + +#define JBD2_DESCRIPTOR_BLOCK 1 +#define JBD2_COMMIT_BLOCK 2 +#define JBD2_SUPERBLOCK_V1 3 +#define JBD2_SUPERBLOCK_V2 4 +#define JBD2_REVOKE_BLOCK 5 + +/* + * Standard header for all descriptor blocks: + */ +typedef struct journal_header_s +{ + __be32 h_magic; + __be32 h_blocktype; + __be32 h_sequence; +} journal_header_t; + + +/* + * The block tag: used to describe a single buffer in the journal. + * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this + * raw struct shouldn't be used for pointer math or sizeof() - use + * journal_tag_bytes(journal) instead to compute this. + */ +typedef struct journal_block_tag_s +{ + __be32 t_blocknr; /* The on-disk block number */ + __be32 t_flags; /* See below */ + __be32 t_blocknr_high; /* most-significant high 32bits. */ +} journal_block_tag_t; + +#define JBD_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) +#define JBD_TAG_SIZE64 (sizeof(journal_block_tag_t)) + +/* + * The revoke descriptor: used on disk to describe a series of blocks to + * be revoked from the log + */ +typedef struct jbd2_journal_revoke_header_s +{ + journal_header_t r_header; + __be32 r_count; /* Count of bytes used in the block */ +} jbd2_journal_revoke_header_t; + + +/* Definitions for the journal tag flags word: */ +#define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ +#define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ +#define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ +#define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ + + +/* + * The journal superblock. All fields are in big-endian byte order. + */ +typedef struct journal_superblock_s +{ +/* 0x0000 */ + journal_header_t s_header; + +/* 0x000C */ + /* Static information describing the journal */ + __be32 s_blocksize; /* journal device blocksize */ + __be32 s_maxlen; /* total blocks in journal file */ + __be32 s_first; /* first block of log information */ + +/* 0x0018 */ + /* Dynamic information describing the current state of the log */ + __be32 s_sequence; /* first commit ID expected in log */ + __be32 s_start; /* blocknr of start of log */ + +/* 0x0020 */ + /* Error value, as set by jbd2_journal_abort(). */ + __be32 s_errno; + +/* 0x0024 */ + /* Remaining fields are only valid in a version-2 superblock */ + __be32 s_feature_compat; /* compatible feature set */ + __be32 s_feature_incompat; /* incompatible feature set */ + __be32 s_feature_ro_compat; /* readonly-compatible feature set */ +/* 0x0030 */ + __u8 s_uuid[16]; /* 128-bit uuid for journal */ + +/* 0x0040 */ + __be32 s_nr_users; /* Nr of filesystems sharing log */ + + __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ + +/* 0x0048 */ + __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ + __be32 s_max_trans_data; /* Limit of data blocks per trans. */ + +/* 0x0050 */ + __u32 s_padding[44]; + +/* 0x0100 */ + __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ +/* 0x0400 */ +} journal_superblock_t; + +#define JBD2_HAS_COMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) +#define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) +#define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \ + ((j)->j_format_version >= 2 && \ + ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) + +#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 +#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 + +/* Features known to this kernel version: */ +#define JBD2_KNOWN_COMPAT_FEATURES 0 +#define JBD2_KNOWN_ROCOMPAT_FEATURES 0 +#define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ + JBD2_FEATURE_INCOMPAT_64BIT) + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/sched.h> + +#define JBD_ASSERTIONS +#ifdef JBD_ASSERTIONS +#define J_ASSERT(assert) \ +do { \ + if (!(assert)) { \ + printk (KERN_EMERG \ + "Assertion failure in %s() at %s:%d: \"%s\"\n", \ + __FUNCTION__, __FILE__, __LINE__, # assert); \ + BUG(); \ + } \ +} while (0) + +#if defined(CONFIG_BUFFER_DEBUG) +void buffer_assertion_failure(struct buffer_head *bh); +#define J_ASSERT_BH(bh, expr) \ + do { \ + if (!(expr)) \ + buffer_assertion_failure(bh); \ + J_ASSERT(expr); \ + } while (0) +#define J_ASSERT_JH(jh, expr) J_ASSERT_BH(jh2bh(jh), expr) +#else +#define J_ASSERT_BH(bh, expr) J_ASSERT(expr) +#define J_ASSERT_JH(jh, expr) J_ASSERT(expr) +#endif + +#else +#define J_ASSERT(assert) do { } while (0) +#endif /* JBD_ASSERTIONS */ + +#if defined(JBD_PARANOID_IOFAIL) +#define J_EXPECT(expr, why...) J_ASSERT(expr) +#define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) +#define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) +#else +#define __journal_expect(expr, why...) \ + ({ \ + int val = (expr); \ + if (!val) { \ + printk(KERN_ERR \ + "EXT3-fs unexpected failure: %s;\n",# expr); \ + printk(KERN_ERR why "\n"); \ + } \ + val; \ + }) +#define J_EXPECT(expr, why...) __journal_expect(expr, ## why) +#define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) +#define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) +#endif + +enum jbd_state_bits { + BH_JBD /* Has an attached ext3 journal_head */ + = BH_PrivateStart, + BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ + BH_Freed, /* Has been freed (truncated) */ + BH_Revoked, /* Has been revoked from the log */ + BH_RevokeValid, /* Revoked flag is valid */ + BH_JBDDirty, /* Is dirty but journaled */ + BH_State, /* Pins most journal_head state */ + BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ + BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */ +}; + +BUFFER_FNS(JBD, jbd) +BUFFER_FNS(JWrite, jwrite) +BUFFER_FNS(JBDDirty, jbddirty) +TAS_BUFFER_FNS(JBDDirty, jbddirty) +BUFFER_FNS(Revoked, revoked) +TAS_BUFFER_FNS(Revoked, revoked) +BUFFER_FNS(RevokeValid, revokevalid) +TAS_BUFFER_FNS(RevokeValid, revokevalid) +BUFFER_FNS(Freed, freed) + +static inline struct buffer_head *jh2bh(struct journal_head *jh) +{ + return jh->b_bh; +} + +static inline struct journal_head *bh2jh(struct buffer_head *bh) +{ + return bh->b_private; +} + +static inline void jbd_lock_bh_state(struct buffer_head *bh) +{ + bit_spin_lock(BH_State, &bh->b_state); +} + +static inline int jbd_trylock_bh_state(struct buffer_head *bh) +{ + return bit_spin_trylock(BH_State, &bh->b_state); +} + +static inline int jbd_is_locked_bh_state(struct buffer_head *bh) +{ + return bit_spin_is_locked(BH_State, &bh->b_state); +} + +static inline void jbd_unlock_bh_state(struct buffer_head *bh) +{ + bit_spin_unlock(BH_State, &bh->b_state); +} + +static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) +{ + bit_spin_lock(BH_JournalHead, &bh->b_state); +} + +static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) +{ + bit_spin_unlock(BH_JournalHead, &bh->b_state); +} + +struct jbd2_revoke_table_s; + +/** + * struct handle_s - The handle_s type is the concrete type associated with + * handle_t. + * @h_transaction: Which compound transaction is this update a part of? + * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. + * @h_ref: Reference count on this handle + * @h_err: Field for caller's use to track errors through large fs operations + * @h_sync: flag for sync-on-close + * @h_jdata: flag to force data journaling + * @h_aborted: flag indicating fatal error on handle + **/ + +/* Docbook can't yet cope with the bit fields, but will leave the documentation + * in so it can be fixed later. + */ + +struct handle_s +{ + /* Which compound transaction is this update a part of? */ + transaction_t *h_transaction; + + /* Number of remaining buffers we are allowed to dirty: */ + int h_buffer_credits; + + /* Reference count on this handle */ + int h_ref; + + /* Field for caller's use to track errors through large fs */ + /* operations */ + int h_err; + + /* Flags [no locking] */ + unsigned int h_sync: 1; /* sync-on-close */ + unsigned int h_jdata: 1; /* force data journaling */ + unsigned int h_aborted: 1; /* fatal error on handle */ +}; + + +/* The transaction_t type is the guts of the journaling mechanism. It + * tracks a compound transaction through its various states: + * + * RUNNING: accepting new updates + * LOCKED: Updates still running but we don't accept new ones + * RUNDOWN: Updates are tidying up but have finished requesting + * new buffers to modify (state not used for now) + * FLUSH: All updates complete, but we are still writing to disk + * COMMIT: All data on disk, writing commit record + * FINISHED: We still have to keep the transaction for checkpointing. + * + * The transaction keeps track of all of the buffers modified by a + * running transaction, and all of the buffers committed but not yet + * flushed to home for finished transactions. + */ + +/* + * Lock ranking: + * + * j_list_lock + * ->jbd_lock_bh_journal_head() (This is "innermost") + * + * j_state_lock + * ->jbd_lock_bh_state() + * + * jbd_lock_bh_state() + * ->j_list_lock + * + * j_state_lock + * ->t_handle_lock + * + * j_state_lock + * ->j_list_lock (journal_unmap_buffer) + * + */ + +struct transaction_s +{ + /* Pointer to the journal for this transaction. [no locking] */ + journal_t *t_journal; + + /* Sequence number for this transaction [no locking] */ + tid_t t_tid; + + /* + * Transaction's current state + * [no locking - only kjournald2 alters this] + * FIXME: needs barriers + * KLUDGE: [use j_state_lock] + */ + enum { + T_RUNNING, + T_LOCKED, + T_RUNDOWN, + T_FLUSH, + T_COMMIT, + T_FINISHED + } t_state; + + /* + * Where in the log does this transaction's commit start? [no locking] + */ + unsigned long t_log_start; + + /* Number of buffers on the t_buffers list [j_list_lock] */ + int t_nr_buffers; + + /* + * Doubly-linked circular list of all buffers reserved but not yet + * modified by this transaction [j_list_lock] + */ + struct journal_head *t_reserved_list; + + /* + * Doubly-linked circular list of all buffers under writeout during + * commit [j_list_lock] + */ + struct journal_head *t_locked_list; + + /* + * Doubly-linked circular list of all metadata buffers owned by this + * transaction [j_list_lock] + */ + struct journal_head *t_buffers; + + /* + * Doubly-linked circular list of all data buffers still to be + * flushed before this transaction can be committed [j_list_lock] + */ + struct journal_head *t_sync_datalist; + + /* + * Doubly-linked circular list of all forget buffers (superseded + * buffers which we can un-checkpoint once this transaction commits) + * [j_list_lock] + */ + struct journal_head *t_forget; + + /* + * Doubly-linked circular list of all buffers still to be flushed before + * this transaction can be checkpointed. [j_list_lock] + */ + struct journal_head *t_checkpoint_list; + + /* + * Doubly-linked circular list of all buffers submitted for IO while + * checkpointing. [j_list_lock] + */ + struct journal_head *t_checkpoint_io_list; + + /* + * Doubly-linked circular list of temporary buffers currently undergoing + * IO in the log [j_list_lock] + */ + struct journal_head *t_iobuf_list; + + /* + * Doubly-linked circular list of metadata buffers being shadowed by log + * IO. The IO buffers on the iobuf list and the shadow buffers on this + * list match each other one for one at all times. [j_list_lock] + */ + struct journal_head *t_shadow_list; + + /* + * Doubly-linked circular list of control buffers being written to the + * log. [j_list_lock] + */ + struct journal_head *t_log_list; + + /* + * Protects info related to handles + */ + spinlock_t t_handle_lock; + + /* + * Number of outstanding updates running on this transaction + * [t_handle_lock] + */ + int t_updates; + + /* + * Number of buffers reserved for use by all handles in this transaction + * handle but not yet modified. [t_handle_lock] + */ + int t_outstanding_credits; + + /* + * Forward and backward links for the circular list of all transactions + * awaiting checkpoint. [j_list_lock] + */ + transaction_t *t_cpnext, *t_cpprev; + + /* + * When will the transaction expire (become due for commit), in jiffies? + * [no locking] + */ + unsigned long t_expires; + + /* + * How many handles used this transaction? [t_handle_lock] + */ + int t_handle_count; + +}; + +/** + * struct journal_s - The journal_s type is the concrete type associated with + * journal_t. + * @j_flags: General journaling state flags + * @j_errno: Is there an outstanding uncleared error on the journal (from a + * prior abort)? + * @j_sb_buffer: First part of superblock buffer + * @j_superblock: Second part of superblock buffer + * @j_format_version: Version of the superblock format + * @j_state_lock: Protect the various scalars in the journal + * @j_barrier_count: Number of processes waiting to create a barrier lock + * @j_barrier: The barrier lock itself + * @j_running_transaction: The current running transaction.. + * @j_committing_transaction: the transaction we are pushing to disk + * @j_checkpoint_transactions: a linked circular list of all transactions + * waiting for checkpointing + * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction + * to start committing, or for a barrier lock to be released + * @j_wait_logspace: Wait queue for waiting for checkpointing to complete + * @j_wait_done_commit: Wait queue for waiting for commit to complete + * @j_wait_checkpoint: Wait queue to trigger checkpointing + * @j_wait_commit: Wait queue to trigger commit + * @j_wait_updates: Wait queue to wait for updates to complete + * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints + * @j_head: Journal head - identifies the first unused block in the journal + * @j_tail: Journal tail - identifies the oldest still-used block in the + * journal. + * @j_free: Journal free - how many free blocks are there in the journal? + * @j_first: The block number of the first usable block + * @j_last: The block number one beyond the last usable block + * @j_dev: Device where we store the journal + * @j_blocksize: blocksize for the location where we store the journal. + * @j_blk_offset: starting block offset for into the device where we store the + * journal + * @j_fs_dev: Device which holds the client fs. For internal journal this will + * be equal to j_dev + * @j_maxlen: Total maximum capacity of the journal region on disk. + * @j_list_lock: Protects the buffer lists and internal buffer state. + * @j_inode: Optional inode where we store the journal. If present, all journal + * block numbers are mapped into this inode via bmap(). + * @j_tail_sequence: Sequence number of the oldest transaction in the log + * @j_transaction_sequence: Sequence number of the next transaction to grant + * @j_commit_sequence: Sequence number of the most recently committed + * transaction + * @j_commit_request: Sequence number of the most recent transaction wanting + * commit + * @j_uuid: Uuid of client object. + * @j_task: Pointer to the current commit thread for this journal + * @j_max_transaction_buffers: Maximum number of metadata buffers to allow in a + * single compound commit transaction + * @j_commit_interval: What is the maximum transaction lifetime before we begin + * a commit? + * @j_commit_timer: The timer used to wakeup the commit thread + * @j_revoke_lock: Protect the revoke table + * @j_revoke: The revoke table - maintains the list of revoked blocks in the + * current transaction. + * @j_revoke_table: alternate revoke tables for j_revoke + * @j_wbuf: array of buffer_heads for jbd2_journal_commit_transaction + * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the + * number that will fit in j_blocksize + * @j_last_sync_writer: most recent pid which did a synchronous write + * @j_private: An opaque pointer to fs-private information. + */ + +struct journal_s +{ + /* General journaling state flags [j_state_lock] */ + unsigned long j_flags; + + /* + * Is there an outstanding uncleared error on the journal (from a prior + * abort)? [j_state_lock] + */ + int j_errno; + + /* The superblock buffer */ + struct buffer_head *j_sb_buffer; + journal_superblock_t *j_superblock; + + /* Version of the superblock format */ + int j_format_version; + + /* + * Protect the various scalars in the journal + */ + spinlock_t j_state_lock; + + /* + * Number of processes waiting to create a barrier lock [j_state_lock] + */ + int j_barrier_count; + + /* The barrier lock itself */ + struct mutex j_barrier; + + /* + * Transactions: The current running transaction... + * [j_state_lock] [caller holding open handle] + */ + transaction_t *j_running_transaction; + + /* + * the transaction we are pushing to disk + * [j_state_lock] [caller holding open handle] + */ + transaction_t *j_committing_transaction; + + /* + * ... and a linked circular list of all transactions waiting for + * checkpointing. [j_list_lock] + */ + transaction_t *j_checkpoint_transactions; + + /* + * Wait queue for waiting for a locked transaction to start committing, + * or for a barrier lock to be released + */ + wait_queue_head_t j_wait_transaction_locked; + + /* Wait queue for waiting for checkpointing to complete */ + wait_queue_head_t j_wait_logspace; + + /* Wait queue for waiting for commit to complete */ + wait_queue_head_t j_wait_done_commit; + + /* Wait queue to trigger checkpointing */ + wait_queue_head_t j_wait_checkpoint; + + /* Wait queue to trigger commit */ + wait_queue_head_t j_wait_commit; + + /* Wait queue to wait for updates to complete */ + wait_queue_head_t j_wait_updates; + + /* Semaphore for locking against concurrent checkpoints */ + struct mutex j_checkpoint_mutex; + + /* + * Journal head: identifies the first unused block in the journal. + * [j_state_lock] + */ + unsigned long j_head; + + /* + * Journal tail: identifies the oldest still-used block in the journal. + * [j_state_lock] + */ + unsigned long j_tail; + + /* + * Journal free: how many free blocks are there in the journal? + * [j_state_lock] + */ + unsigned long j_free; + + /* + * Journal start and end: the block numbers of the first usable block + * and one beyond the last usable block in the journal. [j_state_lock] + */ + unsigned long j_first; + unsigned long j_last; + + /* + * Device, blocksize and starting block offset for the location where we + * store the journal. + */ + struct block_device *j_dev; + int j_blocksize; + unsigned long long j_blk_offset; + + /* + * Device which holds the client fs. For internal journal this will be + * equal to j_dev. + */ + struct block_device *j_fs_dev; + + /* Total maximum capacity of the journal region on disk. */ + unsigned int j_maxlen; + + /* + * Protects the buffer lists and internal buffer state. + */ + spinlock_t j_list_lock; + + /* Optional inode where we store the journal. If present, all */ + /* journal block numbers are mapped into this inode via */ + /* bmap(). */ + struct inode *j_inode; + + /* + * Sequence number of the oldest transaction in the log [j_state_lock] + */ + tid_t j_tail_sequence; + + /* + * Sequence number of the next transaction to grant [j_state_lock] + */ + tid_t j_transaction_sequence; + + /* + * Sequence number of the most recently committed transaction + * [j_state_lock]. + */ + tid_t j_commit_sequence; + + /* + * Sequence number of the most recent transaction wanting commit + * [j_state_lock] + */ + tid_t j_commit_request; + + /* + * Journal uuid: identifies the object (filesystem, LVM volume etc) + * backed by this journal. This will eventually be replaced by an array + * of uuids, allowing us to index multiple devices within a single + * journal and to perform atomic updates across them. + */ + __u8 j_uuid[16]; + + /* Pointer to the current commit thread for this journal */ + struct task_struct *j_task; + + /* + * Maximum number of metadata buffers to allow in a single compound + * commit transaction + */ + int j_max_transaction_buffers; + + /* + * What is the maximum transaction lifetime before we begin a commit? + */ + unsigned long j_commit_interval; + + /* The timer used to wakeup the commit thread: */ + struct timer_list j_commit_timer; + + /* + * The revoke table: maintains the list of revoked blocks in the + * current transaction. [j_revoke_lock] + */ + spinlock_t j_revoke_lock; + struct jbd2_revoke_table_s *j_revoke; + struct jbd2_revoke_table_s *j_revoke_table[2]; + + /* + * array of bhs for jbd2_journal_commit_transaction + */ + struct buffer_head **j_wbuf; + int j_wbufsize; + + pid_t j_last_sync_writer; + + /* + * An opaque pointer to fs-private information. ext3 puts its + * superblock pointer here + */ + void *j_private; +}; + +/* + * Journal flag definitions + */ +#define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ +#define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ +#define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ +#define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ +#define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ +#define JBD2_BARRIER 0x020 /* Use IDE barriers */ + +/* + * Function declarations for the journaling transaction and buffer + * management + */ + +/* Filing buffers */ +extern void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); +extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); +extern void __jbd2_journal_unfile_buffer(struct journal_head *); +extern void __jbd2_journal_refile_buffer(struct journal_head *); +extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); +extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); +extern void __journal_free_buffer(struct journal_head *bh); +extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); +extern void __journal_clean_data_list(transaction_t *transaction); + +/* Log buffer allocation */ +extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *); +int jbd2_journal_next_log_block(journal_t *, unsigned long long *); + +/* Commit management */ +extern void jbd2_journal_commit_transaction(journal_t *); + +/* Checkpoint list management */ +int __jbd2_journal_clean_checkpoint_list(journal_t *journal); +int __jbd2_journal_remove_checkpoint(struct journal_head *); +void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); + +/* Buffer IO */ +extern int +jbd2_journal_write_metadata_buffer(transaction_t *transaction, + struct journal_head *jh_in, + struct journal_head **jh_out, + unsigned long long blocknr); + +/* Transaction locking */ +extern void __wait_on_journal (journal_t *); + +/* + * Journal locking. + * + * We need to lock the journal during transaction state changes so that nobody + * ever tries to take a handle on the running transaction while we are in the + * middle of moving it to the commit phase. j_state_lock does this. + * + * Note that the locking is completely interrupt unsafe. We never touch + * journal structures from interrupts. + */ + +static inline handle_t *journal_current_handle(void) +{ + return current->journal_info; +} + +/* The journaling code user interface: + * + * Create and destroy handles + * Register buffer modifications against the current transaction. + */ + +extern handle_t *jbd2_journal_start(journal_t *, int nblocks); +extern int jbd2_journal_restart (handle_t *, int nblocks); +extern int jbd2_journal_extend (handle_t *, int nblocks); +extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); +extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); +extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); +extern int jbd2_journal_dirty_data (handle_t *, struct buffer_head *); +extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); +extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *); +extern int jbd2_journal_forget (handle_t *, struct buffer_head *); +extern void journal_sync_buffer (struct buffer_head *); +extern void jbd2_journal_invalidatepage(journal_t *, + struct page *, unsigned long); +extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int jbd2_journal_stop(handle_t *); +extern int jbd2_journal_flush (journal_t *); +extern void jbd2_journal_lock_updates (journal_t *); +extern void jbd2_journal_unlock_updates (journal_t *); + +extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, + struct block_device *fs_dev, + unsigned long long start, int len, int bsize); +extern journal_t * jbd2_journal_init_inode (struct inode *); +extern int jbd2_journal_update_format (journal_t *); +extern int jbd2_journal_check_used_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_check_available_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_set_features + (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_create (journal_t *); +extern int jbd2_journal_load (journal_t *journal); +extern void jbd2_journal_destroy (journal_t *); +extern int jbd2_journal_recover (journal_t *journal); +extern int jbd2_journal_wipe (journal_t *, int); +extern int jbd2_journal_skip_recovery (journal_t *); +extern void jbd2_journal_update_superblock (journal_t *, int); +extern void __jbd2_journal_abort_hard (journal_t *); +extern void jbd2_journal_abort (journal_t *, int); +extern int jbd2_journal_errno (journal_t *); +extern void jbd2_journal_ack_err (journal_t *); +extern int jbd2_journal_clear_err (journal_t *); +extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); +extern int jbd2_journal_force_commit(journal_t *); + +/* + * journal_head management + */ +struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); +struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); +void jbd2_journal_remove_journal_head(struct buffer_head *bh); +void jbd2_journal_put_journal_head(struct journal_head *jh); + +/* + * handle management + */ +extern kmem_cache_t *jbd2_handle_cache; + +static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) +{ + return kmem_cache_alloc(jbd2_handle_cache, gfp_flags); +} + +static inline void jbd_free_handle(handle_t *handle) +{ + kmem_cache_free(jbd2_handle_cache, handle); +} + +/* Primary revoke support */ +#define JOURNAL_REVOKE_DEFAULT_HASH 256 +extern int jbd2_journal_init_revoke(journal_t *, int); +extern void jbd2_journal_destroy_revoke_caches(void); +extern int jbd2_journal_init_revoke_caches(void); + +extern void jbd2_journal_destroy_revoke(journal_t *); +extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); +extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); +extern void jbd2_journal_write_revoke_records(journal_t *, transaction_t *); + +/* Recovery revoke support */ +extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); +extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); +extern void jbd2_journal_clear_revoke(journal_t *); +extern void jbd2_journal_switch_revoke_table(journal_t *journal); + +/* + * The log thread user interface: + * + * Request space in the current transaction, and force transaction commit + * transitions on demand. + */ + +int __jbd2_log_space_left(journal_t *); /* Called with journal locked */ +int jbd2_log_start_commit(journal_t *journal, tid_t tid); +int __jbd2_log_start_commit(journal_t *journal, tid_t tid); +int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); +int jbd2_journal_force_commit_nested(journal_t *journal); +int jbd2_log_wait_commit(journal_t *journal, tid_t tid); +int jbd2_log_do_checkpoint(journal_t *journal); + +void __jbd2_log_wait_for_space(journal_t *journal); +extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); +extern int jbd2_cleanup_journal_tail(journal_t *); + +/* Debugging code only: */ + +#define jbd_ENOSYS() \ +do { \ + printk (KERN_ERR "JBD unimplemented function %s\n", __FUNCTION__); \ + current->state = TASK_UNINTERRUPTIBLE; \ + schedule(); \ +} while (1) + +/* + * is_journal_abort + * + * Simple test wrapper function to test the JBD2_ABORT state flag. This + * bit, when set, indicates that we have had a fatal error somewhere, + * either inside the journaling layer or indicated to us by the client + * (eg. ext3), and that we and should not commit any further + * transactions. + */ + +static inline int is_journal_aborted(journal_t *journal) +{ + return journal->j_flags & JBD2_ABORT; +} + +static inline int is_handle_aborted(handle_t *handle) +{ + if (handle->h_aborted) + return 1; + return is_journal_aborted(handle->h_transaction->t_journal); +} + +static inline void jbd2_journal_abort_handle(handle_t *handle) +{ + handle->h_aborted = 1; +} + +#endif /* __KERNEL__ */ + +/* Comparison functions for transaction IDs: perform comparisons using + * modulo arithmetic so that they work over sequence number wraps. */ + +static inline int tid_gt(tid_t x, tid_t y) +{ + int difference = (x - y); + return (difference > 0); +} + +static inline int tid_geq(tid_t x, tid_t y) +{ + int difference = (x - y); + return (difference >= 0); +} + +extern int jbd2_journal_blocks_per_page(struct inode *inode); +extern size_t journal_tag_bytes(journal_t *journal); + +/* + * Return the minimum number of blocks which must be free in the journal + * before a new transaction may be started. Must be called under j_state_lock. + */ +static inline int jbd_space_needed(journal_t *journal) +{ + int nblocks = journal->j_max_transaction_buffers; + if (journal->j_committing_transaction) + nblocks += journal->j_committing_transaction-> + t_outstanding_credits; + return nblocks; +} + +/* + * Definitions which augment the buffer_head layer + */ + +/* journaling buffer types */ +#define BJ_None 0 /* Not journaled */ +#define BJ_SyncData 1 /* Normal data: flush before commit */ +#define BJ_Metadata 2 /* Normal journaled metadata */ +#define BJ_Forget 3 /* Buffer superseded by this transaction */ +#define BJ_IO 4 /* Buffer is for temporary IO use */ +#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */ +#define BJ_LogCtl 6 /* Buffer contains log descriptors */ +#define BJ_Reserved 7 /* Buffer is reserved for access by journal */ +#define BJ_Locked 8 /* Locked for I/O during commit */ +#define BJ_Types 9 + +extern int jbd_blocks_per_page(struct inode *inode); + +#ifdef __KERNEL__ + +#define buffer_trace_init(bh) do {} while (0) +#define print_buffer_fields(bh) do {} while (0) +#define print_buffer_trace(bh) do {} while (0) +#define BUFFER_TRACE(bh, info) do {} while (0) +#define BUFFER_TRACE2(bh, bh2, info) do {} while (0) +#define JBUFFER_TRACE(jh, info) do {} while (0) + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_JBD_H */ diff --git a/include/linux/magic.h b/include/linux/magic.h index 22036dd2ba3..156c40fc664 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -8,6 +8,7 @@ #define EFS_SUPER_MAGIC 0x414A53 #define EXT2_SUPER_MAGIC 0xEF53 #define EXT3_SUPER_MAGIC 0xEF53 +#define EXT4_SUPER_MAGIC 0xEF53 #define HPFS_SUPER_MAGIC 0xf995e849 #define ISOFS_SUPER_MAGIC 0x9660 #define JFFS2_SUPER_MAGIC 0x72b6 diff --git a/include/linux/mm.h b/include/linux/mm.h index 26146623be2..5a6068ff555 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1103,12 +1103,7 @@ static inline void vm_stat_account(struct mm_struct *mm, #ifndef CONFIG_DEBUG_PAGEALLOC static inline void -kernel_map_pages(struct page *page, int numpages, int enable) -{ - if (!PageHighMem(page) && !enable) - debug_check_no_locks_freed(page_address(page), - numpages * PAGE_SIZE); -} +kernel_map_pages(struct page *page, int numpages, int enable) {} #endif extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk); diff --git a/include/linux/module.h b/include/linux/module.h index 4b2d8091a41..d1d00ce8f4e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -317,9 +317,6 @@ struct module /* Am I unsafe to unload? */ int unsafe; - /* Am I GPL-compatible */ - int license_gplok; - unsigned int taints; /* same bits as kernel:tainted */ #ifdef CONFIG_MODULE_UNLOAD diff --git a/include/linux/nbd.h b/include/linux/nbd.h index e712e7d47cc..d6b6dc09ad9 100644 --- a/include/linux/nbd.h +++ b/include/linux/nbd.h @@ -15,6 +15,8 @@ #ifndef LINUX_NBD_H #define LINUX_NBD_H +#include <linux/types.h> + #define NBD_SET_SOCK _IO( 0xab, 0 ) #define NBD_SET_BLKSIZE _IO( 0xab, 1 ) #define NBD_SET_SIZE _IO( 0xab, 2 ) diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 5dce5c21822..b1063e9cdb1 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -8,8 +8,8 @@ * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * - * For details of nodemask_scnprintf() and nodemask_parse(), - * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c. + * For details of nodemask_scnprintf() and nodemask_parse_user(), + * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. * For details of nodelist_scnprintf() and nodelist_parse(), see * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. * For details of node_remap(), see bitmap_bitremap in lib/bitmap.c. @@ -51,7 +51,7 @@ * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_scnprintf(buf, len, mask) Format nodemask for printing - * int nodemask_parse(ubuf, ulen, mask) Parse ascii string as nodemask + * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_scnprintf(buf, len, mask) Format nodemask as list for printing * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) @@ -288,12 +288,12 @@ static inline int __nodemask_scnprintf(char *buf, int len, return bitmap_scnprintf(buf, len, srcp->bits, nbits); } -#define nodemask_parse(ubuf, ulen, dst) \ - __nodemask_parse((ubuf), (ulen), &(dst), MAX_NUMNODES) -static inline int __nodemask_parse(const char __user *buf, int len, +#define nodemask_parse_user(ubuf, ulen, dst) \ + __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) +static inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { - return bitmap_parse(buf, len, dstp->bits, nbits); + return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_scnprintf(buf, len, src) \ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b0ace3fd7eb..1912c6cbef5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -431,6 +431,10 @@ asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, int timeout); +asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout, + const sigset_t __user *sigmask, + size_t sigsetsize); asmlinkage long sys_gethostname(char __user *name, int len); asmlinkage long sys_sethostname(char __user *name, int len); asmlinkage long sys_setdomainname(char __user *name, int len); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 607c7809ad0..9a352667007 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -57,7 +57,7 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer, if (!irq_desc[irq].chip->set_affinity || no_irq_affinity) return -EIO; - err = cpumask_parse(buffer, count, new_value); + err = cpumask_parse_user(buffer, count, new_value); if (err) return err; diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 4c055346100..805a322a565 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -1114,8 +1114,6 @@ static int count_matching_names(struct lock_class *new_class) return count + 1; } -extern void __error_too_big_MAX_LOCKDEP_SUBCLASSES(void); - /* * Register a lock's class in the hash-table, if the class is not present * yet. Otherwise we look it up. We cache the result in the lock object @@ -1153,8 +1151,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) * (or spin_lock_init()) call - which acts as the key. For static * locks we use the lock object itself as the key. */ - if (sizeof(struct lock_class_key) > sizeof(struct lock_class)) - __error_too_big_MAX_LOCKDEP_SUBCLASSES(); + BUILD_BUG_ON(sizeof(struct lock_class_key) > sizeof(struct lock_class)); key = lock->key->subkeys + subclass; diff --git a/kernel/module.c b/kernel/module.c index 7f60e782de1..67009bd56c5 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -87,6 +87,12 @@ static inline int strong_try_module_get(struct module *mod) return try_module_get(mod); } +static inline void add_taint_module(struct module *mod, unsigned flag) +{ + add_taint(flag); + mod->taints |= flag; +} + /* A thread that wants to hold a reference to a module only while it * is running can call ths to safely exit. * nfsd and lockd use this. @@ -847,12 +853,10 @@ static int check_version(Elf_Shdr *sechdrs, return 0; } /* Not in module's version table. OK, but that taints the kernel. */ - if (!(tainted & TAINT_FORCED_MODULE)) { + if (!(tainted & TAINT_FORCED_MODULE)) printk("%s: no version for \"%s\" found: kernel tainted.\n", mod->name, symname); - add_taint(TAINT_FORCED_MODULE); - mod->taints |= TAINT_FORCED_MODULE; - } + add_taint_module(mod, TAINT_FORCED_MODULE); return 1; } @@ -910,7 +914,8 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs, unsigned long ret; const unsigned long *crc; - ret = __find_symbol(name, &owner, &crc, mod->license_gplok); + ret = __find_symbol(name, &owner, &crc, + !(mod->taints & TAINT_PROPRIETARY_MODULE)); if (ret) { /* use_module can fail due to OOM, or module unloading */ if (!check_version(sechdrs, versindex, name, mod, crc) || @@ -1335,12 +1340,11 @@ static void set_license(struct module *mod, const char *license) if (!license) license = "unspecified"; - mod->license_gplok = license_is_gpl_compatible(license); - if (!mod->license_gplok && !(tainted & TAINT_PROPRIETARY_MODULE)) { - printk(KERN_WARNING "%s: module license '%s' taints kernel.\n", - mod->name, license); - add_taint(TAINT_PROPRIETARY_MODULE); - mod->taints |= TAINT_PROPRIETARY_MODULE; + if (!license_is_gpl_compatible(license)) { + if (!(tainted & TAINT_PROPRIETARY_MODULE)) + printk(KERN_WARNING "%s: module license '%s' taints" + "kernel.\n", mod->name, license); + add_taint_module(mod, TAINT_PROPRIETARY_MODULE); } } @@ -1619,8 +1623,7 @@ static struct module *load_module(void __user *umod, modmagic = get_modinfo(sechdrs, infoindex, "vermagic"); /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { - add_taint(TAINT_FORCED_MODULE); - mod->taints |= TAINT_FORCED_MODULE; + add_taint_module(mod, TAINT_FORCED_MODULE); printk(KERN_WARNING "%s: no version magic, tainting kernel.\n", mod->name); } else if (!same_magic(modmagic, vermagic)) { @@ -1714,14 +1717,10 @@ static struct module *load_module(void __user *umod, /* Set up license info based on the info section */ set_license(mod, get_modinfo(sechdrs, infoindex, "license")); - if (strcmp(mod->name, "ndiswrapper") == 0) { - add_taint(TAINT_PROPRIETARY_MODULE); - mod->taints |= TAINT_PROPRIETARY_MODULE; - } - if (strcmp(mod->name, "driverloader") == 0) { - add_taint(TAINT_PROPRIETARY_MODULE); - mod->taints |= TAINT_PROPRIETARY_MODULE; - } + if (strcmp(mod->name, "ndiswrapper") == 0) + add_taint_module(mod, TAINT_PROPRIETARY_MODULE); + if (strcmp(mod->name, "driverloader") == 0) + add_taint_module(mod, TAINT_PROPRIETARY_MODULE); /* Set up MODINFO_ATTR fields */ setup_modinfo(mod, sechdrs, infoindex); @@ -1766,8 +1765,7 @@ static struct module *load_module(void __user *umod, (mod->num_unused_gpl_syms && !unusedgplcrcindex)) { printk(KERN_WARNING "%s: No versions for exported symbols." " Tainting kernel.\n", mod->name); - add_taint(TAINT_FORCED_MODULE); - mod->taints |= TAINT_FORCED_MODULE; + add_taint_module(mod, TAINT_FORCED_MODULE); } #endif @@ -2132,9 +2130,33 @@ static void m_stop(struct seq_file *m, void *p) mutex_unlock(&module_mutex); } +static char *taint_flags(unsigned int taints, char *buf) +{ + int bx = 0; + + if (taints) { + buf[bx++] = '('; + if (taints & TAINT_PROPRIETARY_MODULE) + buf[bx++] = 'P'; + if (taints & TAINT_FORCED_MODULE) + buf[bx++] = 'F'; + /* + * TAINT_FORCED_RMMOD: could be added. + * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't + * apply to modules. + */ + buf[bx++] = ')'; + } + buf[bx] = '\0'; + + return buf; +} + static int m_show(struct seq_file *m, void *p) { struct module *mod = list_entry(p, struct module, list); + char buf[8]; + seq_printf(m, "%s %lu", mod->name, mod->init_size + mod->core_size); print_unload_info(m, mod); @@ -2147,6 +2169,10 @@ static int m_show(struct seq_file *m, void *p) /* Used by oprofile and other similar tools. */ seq_printf(m, " 0x%p", mod->module_core); + /* Taints info */ + if (mod->taints) + seq_printf(m, " %s", taint_flags(mod->taints, buf)); + seq_printf(m, "\n"); return 0; } @@ -2235,28 +2261,6 @@ struct module *module_text_address(unsigned long addr) return mod; } -static char *taint_flags(unsigned int taints, char *buf) -{ - *buf = '\0'; - if (taints) { - int bx; - - buf[0] = '('; - bx = 1; - if (taints & TAINT_PROPRIETARY_MODULE) - buf[bx++] = 'P'; - if (taints & TAINT_FORCED_MODULE) - buf[bx++] = 'F'; - /* - * TAINT_FORCED_RMMOD: could be added. - * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't - * apply to modules. - */ - buf[bx] = ')'; - } - return buf; -} - /* Don't grab lock, we're oopsing. */ void print_modules(void) { diff --git a/kernel/power/disk.c b/kernel/power/disk.c index d7223494279..d3a158a6031 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -18,6 +18,7 @@ #include <linux/fs.h> #include <linux/mount.h> #include <linux/pm.h> +#include <linux/console.h> #include <linux/cpu.h> #include "power.h" @@ -119,8 +120,10 @@ int pm_suspend_disk(void) if (error) return error; + suspend_console(); error = device_suspend(PMSG_FREEZE); if (error) { + resume_console(); printk("Some devices failed to suspend\n"); unprepare_processes(); return error; @@ -133,6 +136,7 @@ int pm_suspend_disk(void) if (in_suspend) { device_resume(); + resume_console(); pr_debug("PM: writing image.\n"); error = swsusp_write(); if (!error) @@ -148,6 +152,7 @@ int pm_suspend_disk(void) swsusp_free(); Done: device_resume(); + resume_console(); unprepare_processes(); return error; } @@ -212,7 +217,9 @@ static int software_resume(void) pr_debug("PM: Preparing devices for restore.\n"); + suspend_console(); if ((error = device_suspend(PMSG_PRETHAW))) { + resume_console(); printk("Some devices failed to suspend\n"); swsusp_free(); goto Thaw; @@ -224,6 +231,7 @@ static int software_resume(void) swsusp_resume(); pr_debug("PM: Restore failed, recovering.n"); device_resume(); + resume_console(); Thaw: unprepare_processes(); Done: diff --git a/kernel/power/user.c b/kernel/power/user.c index 93b5dd283de..d991d3b0e5a 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -19,6 +19,7 @@ #include <linux/swapops.h> #include <linux/pm.h> #include <linux/fs.h> +#include <linux/console.h> #include <linux/cpu.h> #include <asm/uaccess.h> @@ -173,12 +174,14 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, /* Free memory before shutting down devices. */ error = swsusp_shrink_memory(); if (!error) { + suspend_console(); error = device_suspend(PMSG_FREEZE); if (!error) { in_suspend = 1; error = swsusp_suspend(); device_resume(); } + resume_console(); } up(&pm_sem); if (!error) @@ -196,11 +199,13 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, snapshot_free_unused_memory(&data->handle); down(&pm_sem); pm_prepare_console(); + suspend_console(); error = device_suspend(PMSG_PRETHAW); if (!error) { error = swsusp_resume(); device_resume(); } + resume_console(); pm_restore_console(); up(&pm_sem); break; @@ -289,6 +294,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, } /* Put devices to sleep */ + suspend_console(); error = device_suspend(PMSG_SUSPEND); if (error) { printk(KERN_ERR "Failed to suspend some devices.\n"); @@ -299,7 +305,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, /* Wake up devices */ device_resume(); } - + resume_console(); if (pm_ops->finish) pm_ops->finish(PM_SUSPEND_MEM); diff --git a/kernel/printk.c b/kernel/printk.c index 771f5e861bc..f7d427ef503 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -820,15 +820,8 @@ void release_console_sem(void) console_locked = 0; up(&console_sem); spin_unlock_irqrestore(&logbuf_lock, flags); - if (wake_klogd && !oops_in_progress && waitqueue_active(&log_wait)) { - /* - * If we printk from within the lock dependency code, - * from within the scheduler code, then do not lock - * up due to self-recursion: - */ - if (!lockdep_internal()) - wake_up_interruptible(&log_wait); - } + if (wake_klogd && !oops_in_progress && waitqueue_active(&log_wait)) + wake_up_interruptible(&log_wait); } EXPORT_SYMBOL(release_console_sem); diff --git a/kernel/profile.c b/kernel/profile.c index 857300a2afe..f940b462eec 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -399,7 +399,7 @@ static int prof_cpu_mask_write_proc (struct file *file, const char __user *buffe unsigned long full_count = count, err; cpumask_t new_value; - err = cpumask_parse(buffer, count, new_value); + err = cpumask_parse_user(buffer, count, new_value); if (err) return err; diff --git a/kernel/sched.c b/kernel/sched.c index 53608a59d6e..094b5687eef 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1822,14 +1822,14 @@ context_switch(struct rq *rq, struct task_struct *prev, struct mm_struct *mm = next->mm; struct mm_struct *oldmm = prev->active_mm; - if (unlikely(!mm)) { + if (!mm) { next->active_mm = oldmm; atomic_inc(&oldmm->mm_count); enter_lazy_tlb(oldmm, next); } else switch_mm(oldmm, mm, next); - if (unlikely(!prev->mm)) { + if (!prev->mm) { prev->active_mm = NULL; WARN_ON(rq->prev_mm); rq->prev_mm = oldmm; @@ -3491,7 +3491,7 @@ asmlinkage void __sched preempt_schedule(void) * If there is a non-zero preempt_count or interrupts are disabled, * we do not want to preempt the current task. Just return.. */ - if (unlikely(ti->preempt_count || irqs_disabled())) + if (likely(ti->preempt_count || irqs_disabled())) return; need_resched: diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cfc737bffe6..3df9bfc7ff7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -28,6 +28,7 @@ #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> +#include <linux/mempolicy.h> /* * The per-CPU workqueue (if single thread, we always use the first @@ -245,6 +246,12 @@ static int worker_thread(void *__cwq) sigprocmask(SIG_BLOCK, &blocked, NULL); flush_signals(current); + /* + * We inherited MPOL_INTERLEAVE from the booting kernel. + * Set MPOL_DEFAULT to insure node local allocations. + */ + numa_default_policy(); + /* SIG_IGN makes children autoreap: see do_notify_parent(). */ sa.sa.sa_handler = SIG_IGN; sa.sa.sa_flags = 0; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 756a908c441..8fd2dbf7eb5 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -71,7 +71,7 @@ config LOG_BUF_SHIFT config DETECT_SOFTLOCKUP bool "Detect Soft Lockups" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !S390 default y help Say Y here to enable the kernel to detect "soft lockups", @@ -371,6 +371,19 @@ config FORCED_INLINING become the default in the future, until then this option is there to test gcc for this. +config HEADERS_CHECK + bool "Run 'make headers_check' when building vmlinux" + help + This option will extract the user-visible kernel headers whenever + building the kernel, and will run basic sanity checks on them to + ensure that exported files do not attempt to include files which + were not exported, etc. + + If you're making modifications to header files which are + relevant for userspace, say 'Y', and check the headers + exported to $(INSTALL_HDR_PATH) (usually 'usr/include' in + your build tree), to make sure they're suitable. + config RCU_TORTURE_TEST tristate "torture tests for RCU" depends on DEBUG_KERNEL diff --git a/lib/Makefile b/lib/Makefile index 8e6662bb9c3..59070dbfbeb 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -5,7 +5,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ bust_spinlocks.o rbtree.o radix-tree.o dump_stack.o \ idr.o div64.o int_sqrt.o bitmap.o extable.o prio_tree.o \ - sha1.o irq_regs.o + sha1.o irq_regs.o carta_random32.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o diff --git a/lib/bitmap.c b/lib/bitmap.c index d71e38c54ea..037fa9aa2ed 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -316,10 +316,11 @@ int bitmap_scnprintf(char *buf, unsigned int buflen, EXPORT_SYMBOL(bitmap_scnprintf); /** - * bitmap_parse - convert an ASCII hex string into a bitmap. - * @ubuf: pointer to buffer in user space containing string. - * @ubuflen: buffer size in bytes. If string is smaller than this + * __bitmap_parse - convert an ASCII hex string into a bitmap. + * @buf: pointer to buffer containing string. + * @buflen: buffer size in bytes. If string is smaller than this * then it must be terminated with a \0. + * @is_user: location of buffer, 0 indicates kernel space * @maskp: pointer to bitmap array that will contain result. * @nmaskbits: size of bitmap, in bits. * @@ -330,11 +331,13 @@ EXPORT_SYMBOL(bitmap_scnprintf); * characters and for grouping errors such as "1,,5", ",44", "," and "". * Leading and trailing whitespace accepted, but not embedded whitespace. */ -int bitmap_parse(const char __user *ubuf, unsigned int ubuflen, - unsigned long *maskp, int nmaskbits) +int __bitmap_parse(const char *buf, unsigned int buflen, + int is_user, unsigned long *maskp, + int nmaskbits) { int c, old_c, totaldigits, ndigits, nchunks, nbits; u32 chunk; + const char __user *ubuf = buf; bitmap_zero(maskp, nmaskbits); @@ -343,11 +346,15 @@ int bitmap_parse(const char __user *ubuf, unsigned int ubuflen, chunk = ndigits = 0; /* Get the next chunk of the bitmap */ - while (ubuflen) { + while (buflen) { old_c = c; - if (get_user(c, ubuf++)) - return -EFAULT; - ubuflen--; + if (is_user) { + if (__get_user(c, ubuf++)) + return -EFAULT; + } + else + c = *buf++; + buflen--; if (isspace(c)) continue; @@ -388,11 +395,36 @@ int bitmap_parse(const char __user *ubuf, unsigned int ubuflen, nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ; if (nbits > nmaskbits) return -EOVERFLOW; - } while (ubuflen && c == ','); + } while (buflen && c == ','); return 0; } -EXPORT_SYMBOL(bitmap_parse); +EXPORT_SYMBOL(__bitmap_parse); + +/** + * bitmap_parse_user() + * + * @ubuf: pointer to user buffer containing string. + * @ulen: buffer size in bytes. If string is smaller than this + * then it must be terminated with a \0. + * @maskp: pointer to bitmap array that will contain result. + * @nmaskbits: size of bitmap, in bits. + * + * Wrapper for __bitmap_parse(), providing it with user buffer. + * + * We cannot have this as an inline function in bitmap.h because it needs + * linux/uaccess.h to get the access_ok() declaration and this causes + * cyclic dependencies. + */ +int bitmap_parse_user(const char __user *ubuf, + unsigned int ulen, unsigned long *maskp, + int nmaskbits) +{ + if (!access_ok(VERIFY_READ, ubuf, ulen)) + return -EFAULT; + return __bitmap_parse((const char *)ubuf, ulen, 1, maskp, nmaskbits); +} +EXPORT_SYMBOL(bitmap_parse_user); /* * bscnl_emit(buf, buflen, rbot, rtop, bp) diff --git a/lib/carta_random32.c b/lib/carta_random32.c new file mode 100644 index 00000000000..ca82df70eee --- /dev/null +++ b/lib/carta_random32.c @@ -0,0 +1,41 @@ +/* + * Copyright (c) 2002-2006 Hewlett-Packard Development Company, L.P. + * Contributed by David Mosberger-Tang <davidm@hpl.hp.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + * 02111-1307 USA + */ +#include <linux/types.h> +#include <linux/module.h> + +/* + * Fast, simple, yet decent quality random number generator based on + * a paper by David G. Carta ("Two Fast Implementations of the + * `Minimal Standard' Random Number Generator," Communications of the + * ACM, January, 1990). + */ +u64 carta_random32 (u64 seed) +{ +# define A 16807 +# define M ((u32) 1 << 31) + u64 s, prod = A * seed, p, q; + + p = (prod >> 31) & (M - 1); + q = (prod >> 0) & (M - 1); + s = p + q; + if (s >= M) + s -= M - 1; + return s; +} +EXPORT_SYMBOL_GPL(carta_random32); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1d709ff528e..2dbec90dc3b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -356,8 +356,8 @@ nomem: return -ENOMEM; } -void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) +void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -398,6 +398,24 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } } +void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + /* + * It is undesirable to test vma->vm_file as it should be non-null + * for valid hugetlb area. However, vm_file will be NULL in the error + * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails, + * do_mmap_pgoff() nullifies vma->vm_file before calling this function + * to clean up. Since no pte has actually been setup, it is safe to + * do nothing in this case. + */ + if (vma->vm_file) { + spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); + __unmap_hugepage_range(vma, start, end); + spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); + } +} + static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t pte) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 25788b1b7fc..617fb31086e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -727,7 +727,7 @@ int do_migrate_pages(struct mm_struct *mm, return -ENOSYS; } -static struct page *new_vma_page(struct page *page, unsigned long private) +static struct page *new_vma_page(struct page *page, unsigned long private, int **x) { return NULL; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a8c003e7b3d..40db96a655d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -495,17 +495,16 @@ static void __free_pages_ok(struct page *page, unsigned int order) int i; int reserved = 0; - arch_free_page(page, order); - if (!PageHighMem(page)) - debug_check_no_locks_freed(page_address(page), - PAGE_SIZE<<order); - for (i = 0 ; i < (1 << order) ; ++i) reserved += free_pages_check(page + i); if (reserved) return; + if (!PageHighMem(page)) + debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order); + arch_free_page(page, order); kernel_map_pages(page, 1 << order, 0); + local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, order); @@ -781,13 +780,14 @@ static void fastcall free_hot_cold_page(struct page *page, int cold) struct per_cpu_pages *pcp; unsigned long flags; - arch_free_page(page, 0); - if (PageAnon(page)) page->mapping = NULL; if (free_pages_check(page)) return; + if (!PageHighMem(page)) + debug_check_no_locks_freed(page_address(page), PAGE_SIZE); + arch_free_page(page, 0); kernel_map_pages(page, 1, 0); pcp = &zone_pcp(zone, get_cpu())->pcp[cold]; @@ -2294,19 +2294,6 @@ unsigned long __init zone_absent_pages_in_node(int nid, return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); } -/* Return the zone index a PFN is in */ -int memmap_zone_idx(struct page *lmem_map) -{ - int i; - unsigned long phys_addr = virt_to_phys(lmem_map); - unsigned long pfn = phys_addr >> PAGE_SHIFT; - - for (i = 0; i < MAX_NR_ZONES; i++) - if (pfn < arch_zone_highest_possible_pfn[i]) - break; - - return i; -} #else static inline unsigned long zone_spanned_pages_in_node(int nid, unsigned long zone_type, @@ -2325,10 +2312,6 @@ static inline unsigned long zone_absent_pages_in_node(int nid, return zholes_size[zone_type]; } -static inline int memmap_zone_idx(struct page *lmem_map) -{ - return MAX_NR_ZONES; -} #endif static void __init calculate_node_totalpages(struct pglist_data *pgdat, diff --git a/mm/rmap.c b/mm/rmap.c index e2155d791d9..a9136d8b757 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -576,15 +576,14 @@ void page_add_file_rmap(struct page *page) void page_remove_rmap(struct page *page) { if (atomic_add_negative(-1, &page->_mapcount)) { -#ifdef CONFIG_DEBUG_VM if (unlikely(page_mapcount(page) < 0)) { printk (KERN_EMERG "Eeek! page_mapcount(page) went negative! (%d)\n", page_mapcount(page)); printk (KERN_EMERG " page->flags = %lx\n", page->flags); printk (KERN_EMERG " page->count = %x\n", page_count(page)); printk (KERN_EMERG " page->mapping = %p\n", page->mapping); + BUG(); } -#endif - BUG_ON(page_mapcount(page) < 0); + /* * It would be tidy to reset the PageAnon mapping here, * but that might overwrite a racing page_add_anon_rmap diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c index c946bf46871..f5664c5b9eb 100644 --- a/mm/shmem_acl.c +++ b/mm/shmem_acl.c @@ -35,7 +35,7 @@ shmem_get_acl(struct inode *inode, int type) } /** - * shmem_get_acl - generic_acl_operations->setacl() operation + * shmem_set_acl - generic_acl_operations->setacl() operation */ static void shmem_set_acl(struct inode *inode, int type, struct posix_acl *acl) diff --git a/mm/truncate.c b/mm/truncate.c index f4edbc179d1..11ca480701d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -302,7 +302,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return 0; - if (PagePrivate(page) && !try_to_release_page(page, 0)) + if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; write_lock_irq(&mapping->tree_lock); @@ -396,6 +396,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pagevec_release(&pvec); cond_resched(); } + WARN_ON_ONCE(ret); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); diff --git a/scripts/kconfig/lxdialog/dialog.h b/scripts/kconfig/lxdialog/dialog.h index 8dea47f9d3e..fd695e1070f 100644 --- a/scripts/kconfig/lxdialog/dialog.h +++ b/scripts/kconfig/lxdialog/dialog.h @@ -24,6 +24,7 @@ #include <ctype.h> #include <stdlib.h> #include <string.h> +#include <stdbool.h> #ifdef __sun__ #define CURS_MACROS diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 00d1ad19b2c..187f5de4612 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1262,7 +1262,9 @@ sub output_intro_text(%) { } ## -# generic output function for typedefs +# generic output function for all types (function, struct/union, typedef, enum); +# calls the generated, variable output_ function name based on +# functype and output_mode sub output_declaration { no strict 'refs'; my $name = shift; @@ -1278,8 +1280,7 @@ sub output_declaration { } ## -# generic output function - calls the right one based -# on current output mode. +# generic output function - calls the right one based on current output mode. sub output_intro { no strict 'refs'; my $func = "output_intro_".$output_mode; @@ -1518,6 +1519,9 @@ sub dump_function($$) { $prototype =~ s/^asmlinkage +//; $prototype =~ s/^inline +//; $prototype =~ s/^__inline__ +//; + $prototype =~ s/^__inline +//; + $prototype =~ s/^__always_inline +//; + $prototype =~ s/^noinline +//; $prototype =~ s/__devinit +//; $prototype =~ s/^#define +//; #ak added $prototype =~ s/__attribute__ \(\([a-z,]*\)\)//; @@ -1778,8 +1782,9 @@ sub process_file($) { $in_doc_sect = 1; $contents = $newcontents; if ($contents ne "") { - if (substr($contents, 0, 1) eq " ") { - $contents = substr($contents, 1); + while ((substr($contents, 0, 1) eq " ") || + substr($contents, 0, 1) eq "\t") { + $contents = substr($contents, 1); } $contents .= "\n"; } |