litmus-rt.git - The LITMUS^RT kernel.

diff options

author	J. Bruce Fields <bfields@fieldses.org>	2011-01-18 15:45:09 -0500
committer	Al Viro <viro@zeniv.linux.org.uk>	2011-03-10 05:18:54 -0500
commit	d891eedbc3b1b0fade8a9ce60cc0eba1cccb59e5 (patch)
tree	55dd6aa9e17cd763efda6291d740bafd7f05d802 /scripts/checkversion.pl
parent	1ca551c6caae7b52178555cdedea6ca26444be46 (diff)

fs/dcache: allow d_obtain_alias() to return unhashed dentries

Without this patch, inodes are not promptly freed on last close of an unlinked file by an nfs client: client$ mount -tnfs4 server:/export/ /mnt/ client$ tail -f /mnt/FOO ... server$ df -i /export server$ rm /export/FOO (^C the tail -f) server$ df -i /export server$ echo 2 >/proc/sys/vm/drop_caches server$ df -i /export the df's will show that the inode is not freed on the filesystem until the last step, when it could have been freed after killing the client's tail -f. On-disk data won't be deallocated either, leading to possible spurious ENOSPC. This occurs because when the client does the close, it arrives in a compound with a putfh and a close, processed like: - putfh: look up the filehandle. The only alias found for the inode will be DCACHE_UNHASHED alias referenced by the filp this, so it creates a new DCACHE_DISCONECTED dentry and returns that instead. - close: closes the existing filp, which is destroyed immediately by dput() since it's DCACHE_UNHASHED. - end of the compound: release the reference to the current filehandle, and dput() the new DCACHE_DISCONECTED dentry, which gets put on the unused list instead of being destroyed immediately. Nick Piggin suggested fixing this by allowing d_obtain_alias to return the unhashed dentry that is referenced by the filp, instead of making it create a new dentry. Leave __d_find_alias() alone to avoid changing behavior of other callers. Also nfsd doesn't need all the checks of __d_find_alias(); any dentry, hashed or unhashed, disconnected or not, should work. Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Diffstat (limited to 'scripts/checkversion.pl')

0 files changed, 0 insertions, 0 deletions

/* * linux/init/main.c * * Copyright (C) 1991, 1992 Linus Torvalds * * GK 2/5/95 - Changed to support mounting root fs via NFS * Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb '96 * Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May '96 * Simplified starting of init: Michael A. Griffith <grif@acm.org> */ #define DEBUG /* Enable initcall_debug */ #include <linux/types.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/stackprotector.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/delay.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/initrd.h> #include <linux/bootmem.h> #include <linux/acpi.h> #include <linux/tty.h> #include <linux/percpu.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/kernel_stat.h> #include <linux/start_kernel.h> #include <linux/security.h> #include <linux/smp.h> #include <linux/profile.h> #include <linux/rcupdate.h> #include <linux/moduleparam.h> #include <linux/kallsyms.h> #include <linux/writeback.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/cgroup.h> #include <linux/efi.h> #include <linux/tick.h> #include <linux/interrupt.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> #include <linux/unistd.h> #include <linux/rmap.h> #include <linux/mempolicy.h> #include <linux/key.h> #include <linux/buffer_head.h> #include <linux/page_ext.h> #include <linux/debug_locks.h> #include <linux/debugobjects.h> #include <linux/lockdep.h> #include <linux/kmemleak.h> #include <linux/pid_namespace.h> #include <linux/device.h> #include <linux/kthread.h> #include <linux/sched.h> #include <linux/signal.h> #include <linux/idr.h> #include <linux/kgdb.h> #include <linux/ftrace.h> #include <linux/async.h> #include <linux/kmemcheck.h> #include <linux/sfi.h> #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/perf_event.h> #include <linux/file.h> #include <linux/ptrace.h> #include <linux/blkdev.h> #include <linux/elevator.h> #include <linux/sched_clock.h> #include <linux/context_tracking.h> #include <linux/random.h> #include <linux/list.h> #include <linux/integrity.h> #include <linux/proc_ns.h> #include <linux/io.h> #include <asm/io.h> #include <asm/bugs.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/cacheflush.h> static int kernel_init(void *); extern void init_IRQ(void); extern void fork_init(void); extern void radix_tree_init(void); #ifndef CONFIG_DEBUG_RODATA static inline void mark_rodata_ro(void) { } #endif /* * Debug helper: via this flag we know that we are in 'early bootup code' * where only the boot processor is running with IRQ disabled. This means * two things - IRQ must not be enabled before the flag is cleared and some * operations which are not allowed with IRQ disabled are allowed while the * flag is set. */ bool early_boot_irqs_disabled __read_mostly; enum system_states system_state __read_mostly; EXPORT_SYMBOL(system_state); /* * Boot command-line arguments */ #define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT #define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT extern void time_init(void); /* Default late time init is NULL. archs can override this later. */ void (*__initdata late_time_init)(void); /* Untouched command line saved by arch-specific code. */ char __initdata boot_command_line[COMMAND_LINE_SIZE]; /* Untouched saved command line (eg. for /proc) */ char *saved_command_line; /* Command line for parameter parsing */ static char *static_command_line; /* Command line for per-initcall parameter parsing */ static char *initcall_command_line; static char *execute_command; static char *ramdisk_execute_command; /* * Used to generate warnings if static_key manipulation functions are used * before jump_label_init is called. */ bool static_key_initialized __read_mostly; EXPORT_SYMBOL_GPL(static_key_initialized); /* * If set, this is an indication to the drivers that reset the underlying * device before going ahead with the initialization otherwise driver might * rely on the BIOS and skip the reset operation. * * This is useful if kernel is booting in an unreliable environment. * For ex. kdump situation where previous kernel has crashed, BIOS has been * skipped and devices will be in unknown state. */ unsigned int reset_devices; EXPORT_SYMBOL(reset_devices); static int __init set_reset_devices(char *str) { reset_devices = 1; return 1; } __setup("reset_devices", set_reset_devices); static const char *argv_init[MAX_INIT_ARGS+2] = { "init", NULL, }; const char *envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, }; static const char *panic_later, *panic_param; extern const struct obs_kernel_param __setup_start[], __setup_end[]; static int __init obsolete_checksetup(char *line) { const struct obs_kernel_param *p; int had_early_param = 0; p = __setup_start; do { int n = strlen(p->str); if (parameqn(line, p->str, n)) { if (p->early) { /* Already done in parse_early_param? * (Needs exact match on param part). * Keep iterating, as we can have early * params and __setups of same names 8( */ if (line[n] == '\0' || line[n] == '=') had_early_param = 1; } else if (!p->setup_func) { pr_warn("Parameter %s is obsolete, ignored\n", p->str); return 1; } else if (p->setup_func(line + n)) return 1; } p++; } while (p < __setup_end); return had_early_param; } /* * This should be approx 2 Bo*oMips to start (note initial shift), and will * still work even if initially too large, it will just take slightly longer */ unsigned long loops_per_jiffy = (1<<12); EXPORT_SYMBOL(loops_per_jiffy); static int __init debug_kernel(char *str) { console_loglevel = CONSOLE_LOGLEVEL_DEBUG; return 0; } static int __init quiet_kernel(char *str) { console_loglevel = CONSOLE_LOGLEVEL_QUIET; return 0; } early_param("debug", debug_kernel); early_param("quiet", quiet_kernel); static int __init loglevel(char *str) { int newlevel; /* * Only update loglevel value when a correct setting was passed, * to prevent blind crashes (when loglevel being set to 0) that * are quite hard to debug */ if (get_option(&str, &newlevel)) { console_loglevel = newlevel; return 0; } return -EINVAL; } early_param("loglevel", loglevel); /* Change NUL term back to "=", to make "param" the whole string. */ static int __init repair_env_string(char *param, char *val, const char *unused, void *arg) { if (val) { /* param=val or param="val"? */ if (val == param+strlen(param)+1) val[-1] = '='; else if (val == param+strlen(param)+2) { val[-2] = '='; memmove(val-1, val, strlen(val)+1); val--; } else BUG(); } return 0; } /* Anything after -- gets handed straight to init. */ static int __init set_init_arg(char *param, char *val, const char *unused, void *arg) { unsigned int i; if (panic_later) return 0; repair_env_string(param, val, unused, NULL); for (i = 0; argv_init[i]; i++) { if (i == MAX_INIT_ARGS) { panic_later = "init"; panic_param = param; return 0; } } argv_init[i] = param; return 0; } /* * Unknown boot options get handed to init, unless they look like * unused parameters (modprobe will find them in /proc/cmdline). */ static int __init unknown_bootoption(char *param, char *val, const char *unused, void *arg) { repair_env_string(param, val, unused, NULL); /* Handle obsolete-style parameters */ if (obsolete_checksetup(param)) return 0; /* Unused module parameter. */ if (strchr(param, '.') && (!val || strchr(param, '.') < val)) return 0; if (panic_later) return 0; if (val) { /* Environment option */ unsigned int i; for (i = 0; envp_init[i]; i++) { if (i == MAX_INIT_ENVS) { panic_later = "env"; panic_param = param; } if (!strncmp(param, envp_init[i], val - param)) break; } envp_init[i] = param; } else { /* Command line option */ unsigned int i; for (i = 0; argv_init[i]; i++) { if (i == MAX_INIT_ARGS) { panic_later = "init"; panic_param = param; } } argv_init[i] = param; } return 0; } static int __init init_setup(char *str) { unsigned int i; execute_command = str; /* * In case LILO is going to boot us with default command line, * it prepends "auto" before the whole cmdline which makes * the shell think it should execute a script with such name. * So we ignore all arguments entered _before_ init=... [MJ] */ for (i = 1; i < MAX_INIT_ARGS; i++) argv_init[i] = NULL; return 1; } __setup("init=", init_setup); static int __init rdinit_setup(char *str) { unsigned int i; ramdisk_execute_command = str; /* See "auto" comment in init_setup */ for (i = 1; i < MAX_INIT_ARGS; i++) argv_init[i] = NULL; return 1; } __setup("rdinit=", rdinit_setup); #ifndef CONFIG_SMP static const unsigned int setup_max_cpus = NR_CPUS; static inline void setup_nr_cpu_ids(void) { } static inline void smp_prepare_cpus(unsigned int maxcpus) { } #endif /* * We need to store the untouched command line for future reference. * We also need to store the touched command line since the parameter * parsing is performed in place, and we should allow a component to * store reference of name/value for future reference. */ static void __init setup_command_line(char *command_line) { saved_command_line = memblock_virt_alloc(strlen(boot_command_line) + 1, 0); initcall_command_line = memblock_virt_alloc(strlen(boot_command_line) + 1, 0); static_command_line = memblock_virt_alloc(strlen(command_line) + 1, 0); strcpy(saved_command_line, boot_command_line); strcpy(static_command_line, command_line); } /* * We need to finalize in a non-__init function or else race conditions * between the root thread and the init thread may cause start_kernel to * be reaped by free_initmem before the root thread has proceeded to * cpu_idle. * * gcc-3.4 accidentally inlines this function, so use noinline. */ static __initdata DECLARE_COMPLETION(kthreadd_done); static noinline void __init_refok rest_init(void) { int pid; rcu_scheduler_starting(); smpboot_thread_init(); /* * We need to spawn init first so that it obtains pid 1, however * the init task will end up wanting to create kthreads, which, if * we schedule it before we create kthreadd, will OOPS. */ kernel_thread(kernel_init, NULL, CLONE_FS); numa_default_policy(); pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES); rcu_read_lock(); kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns); rcu_read_unlock(); complete(&kthreadd_done); /* * The boot idle thread must execute schedule() * at least once to get things moving: */ init_idle_bootup_task(current); schedule_preempt_disabled(); /* Call into cpu_idle with preempt disabled */ cpu_startup_entry(CPUHP_ONLINE); } /* Check for early params. */ static int __init do_early_param(char *param, char *val, const char *unused, void *arg) { const struct obs_kernel_param *p; for (p = __setup_start; p < __setup_end; p++) { if ((p->early && parameq(param, p->str)) || (strcmp(param, "console") == 0 && strcmp(p->str, "earlycon") == 0) ) { if (p->setup_func(val) != 0) pr_warn("Malformed early option '%s'\n", param); } } /* We accept everything at this stage. */ return 0; } void __init parse_early_options(char *cmdline) { parse_args("early options", cmdline, NULL, 0, 0, 0, NULL, do_early_param); } /* Arch code calls this early on, or if not, just before other parsing. */ void __init parse_early_param(void) { static int done __initdata; static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata; if (done) return; /* All fall through to do_early_param. */ strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE); parse_early_options(tmp_cmdline); done = 1; } /* * Activate the first processor. */ static void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); } void __init __weak smp_setup_processor_id(void) { } # if THREAD_SIZE >= PAGE_SIZE void __init __weak thread_info_cache_init(void) { } #endif /* * Set up kernel memory allocators */ static void __init mm_init(void) { /* * page_ext requires contiguous pages, * bigger than MAX_ORDER unless SPARSEMEM. */ page_ext_init_flatmem(); mem_init(); kmem_cache_init(); percpu_init_late(); pgtable_init(); vmalloc_init(); ioremap_huge_init(); } asmlinkage __visible void __init start_kernel(void) { char *command_line; char *after_dashes; /* * Need to run as early as possible, to initialize the * lockdep hash: */ lockdep_init(); set_task_stack_end_magic(&init_task); smp_setup_processor_id(); debug_objects_early_init(); /* * Set up the the initial canary ASAP: */ boot_init_stack_canary(); cgroup_init_early(); local_irq_disable(); early_boot_irqs_disabled = true; /* * Interrupts are still disabled. Do necessary setups, then * enable them */ boot_cpu_init(); page_address_init(); pr_notice("%s", linux_banner); setup_arch(&command_line); mm_init_cpumask(&init_mm); setup_command_line(command_line); setup_nr_cpu_ids(); setup_per_cpu_areas(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ build_all_zonelists(NULL, NULL); page_alloc_init(); pr_notice("Kernel command line: %s\n", boot_command_line); parse_early_param(); after_dashes = parse_args("Booting kernel", static_command_line, __start___param, __stop___param - __start___param, -1, -1, NULL, &unknown_bootoption); if (!IS_ERR_OR_NULL(after_dashes)) parse_args("Setting init args", after_dashes, NULL, 0, -1, -1, NULL, set_init_arg); jump_label_init(); /* * These use large bootmem allocations and must precede * kmem_cache_init() */ setup_log_buf(0); pidhash_init(); vfs_caches_init_early(); sort_main_extable(); trap_init(); mm_init(); /* * Set up the scheduler prior starting any interrupts (such as the * timer interrupt). Full topology setup happens at smp_init() * time - but meanwhile we still have a functioning scheduler. */ sched_init(); /* * Disable preemption - early bootup scheduling is extremely * fragile until we cpu_idle() for the first time. */ preempt_disable(); if (WARN(!irqs_disabled(), "Interrupts were enabled *very* early, fixing it\n")) local_irq_disable(); idr_init_cache(); rcu_init(); /* trace_printk() and trace points may be used after this */ trace_init(); context_tracking_init(); radix_tree_init(); /* init some links before init_ISA_irqs() */ early_irq_init(); init_IRQ(); tick_init(); rcu_init_nohz(); init_timers(); hrtimers_init(); softirq_init(); timekeeping_init(); time_init(); sched_clock_postinit(); perf_event_init(); profile_init(); call_function_init(); WARN(!irqs_disabled(), "Interrupts were enabled early\n"); early_boot_irqs_disabled = false; local_irq_enable(); kmem_cache_init_late(); /* * HACK ALERT! This is early. We're enabling the console before * we've done PCI setups etc, and console_init() must be aware of * this. But we do want output early, in case something goes wrong. */ console_init(); if (panic_later) panic("Too many boot %s vars at `%s'", panic_later, panic_param); lockdep_info(); /* * Need to run this when irqs are enabled, because it wants * to self-test [hard/soft]-irqs on/off lock inversion bugs * too: */ locking_selftest(); #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start && !initrd_below_start_ok &&


context:
space:
mode: