diff options
214 files changed, 2820 insertions, 1690 deletions
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index 2a4cdda..8cb4d78 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -129,9 +129,9 @@ On all - write a character to /proc/sysrq-trigger. e.g.: * Okay, so what can I use them for? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Well, un'R'aw is very handy when your X server or a svgalib program crashes. +Well, unraw(r) is very handy when your X server or a svgalib program crashes. -sa'K' (Secure Access Key) is useful when you want to be sure there is no +sak(k) (Secure Access Key) is useful when you want to be sure there is no trojan program running at console which could grab your password when you would try to login. It will kill all programs on given console, thus letting you make sure that the login prompt you see is actually @@ -143,20 +143,20 @@ IMPORTANT: such. :IMPORTANT useful when you want to exit a program that will not let you switch consoles. (For example, X or a svgalib program.) -re'B'oot is good when you're unable to shut down. But you should also 'S'ync -and 'U'mount first. +reboot(b) is good when you're unable to shut down. But you should also +sync(s) and umount(u) first. -'C'rash can be used to manually trigger a crashdump when the system is hung. +crash(c) can be used to manually trigger a crashdump when the system is hung. Note that this just triggers a crash if there is no dump mechanism available. -'S'ync is great when your system is locked up, it allows you to sync your +sync(s) is great when your system is locked up, it allows you to sync your disks and will certainly lessen the chance of data loss and fscking. Note that the sync hasn't taken place until you see the "OK" and "Done" appear on the screen. (If the kernel is really in strife, you may not ever get the OK or Done message...) -'U'mount is basically useful in the same ways as 'S'ync. I generally 'S'ync, -'U'mount, then re'B'oot when my system locks. It's saved me many a fsck. +umount(u) is basically useful in the same ways as sync(s). I generally sync(s), +umount(u), then reboot(b) when my system locks. It's saved me many a fsck. Again, the unmount (remount read-only) hasn't taken place until you see the "OK" and "Done" message appear on the screen. @@ -165,11 +165,11 @@ kernel messages you do not want to see. Selecting '0' will prevent all but the most urgent kernel messages from reaching your console. (They will still be logged if syslogd/klogd are alive, though.) -t'E'rm and k'I'll are useful if you have some sort of runaway process you +term(e) and kill(i) are useful if you have some sort of runaway process you are unable to kill any other way, especially if it's spawning other processes. -"'J'ust thaw it" is useful if your system becomes unresponsive due to a frozen +"just thaw it(j)" is useful if your system becomes unresponsive due to a frozen (probably root) filesystem via the FIFREEZE ioctl. * Sometimes SysRq seems to get 'stuck' after using it, what can I do? diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index a3fd8a2..ab80a80 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -175,6 +175,7 @@ machine_power_off(void) void show_regs(struct pt_regs *regs) { + show_regs_print_info(KERN_DEFAULT); dik_show_regs(regs, NULL); } diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 4037461..affccb9 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -169,13 +169,6 @@ void show_stack(struct task_struct *task, unsigned long *sp) dik_show_trace(sp); } -void dump_stack(void) -{ - show_stack(NULL, NULL); -} - -EXPORT_SYMBOL(dump_stack); - void die_if_kernel(char * str, struct pt_regs *regs, long err, unsigned long *r9_15) { diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index a63ff84..ca0207b 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -220,13 +220,6 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) show_stacktrace(tsk, NULL); } -/* Expected by Rest of kernel code */ -void dump_stack(void) -{ - show_stacktrace(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); - /* Another API expected by schedular, shows up in "ps" as Wait Channel * Ofcourse just returning schedule( ) would be pointless so unwind until * the function is not in schedular code diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 7c10873..0aec0198 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -71,7 +71,7 @@ void print_task_path_n_nm(struct task_struct *tsk, char *buf) } done: - pr_info("%s, TGID %u\n", path_nm, tsk->tgid); + pr_info("Path: %s\n", path_nm); } EXPORT_SYMBOL(print_task_path_n_nm); @@ -163,6 +163,7 @@ void show_regs(struct pt_regs *regs) return; print_task_path_n_nm(tsk, buf); + show_regs_print_info(KERN_INFO); if (current->thread.cause_code) show_ecr_verbose(regs); diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c index 9b6de8c..8ff0ecd 100644 --- a/arch/arm/kernel/etm.c +++ b/arch/arm/kernel/etm.c @@ -254,7 +254,7 @@ static void sysrq_etm_dump(int key) static struct sysrq_key_op sysrq_etm_op = { .handler = sysrq_etm_dump, - .help_msg = "ETM buffer dump", + .help_msg = "etm-buffer-dump(v)", .action_msg = "etm", }; diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index c9a5e2c..ae58d3b 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -225,11 +225,8 @@ void __show_regs(struct pt_regs *regs) unsigned long flags; char buf[64]; - printk("CPU: %d %s (%s %.*s)\n", - raw_smp_processor_id(), print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); + show_regs_print_info(KERN_DEFAULT); + print_symbol("PC is at %s\n", instruction_pointer(regs)); print_symbol("LR is at %s\n", regs->ARM_lr); printk("pc : [<%08lx>] lr : [<%08lx>] psr: %08lx\n" @@ -284,7 +281,6 @@ void __show_regs(struct pt_regs *regs) void show_regs(struct pt_regs * regs) { printk("\n"); - printk("Pid: %d, comm: %20s\n", task_pid_nr(current), current->comm); __show_regs(regs); dump_stack(); } diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 1c08911..18b32e8 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -204,13 +204,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) } #endif -void dump_stack(void) -{ - dump_backtrace(NULL, NULL); -} - -EXPORT_SYMBOL(dump_stack); - void show_stack(struct task_struct *tsk, unsigned long *sp) { dump_backtrace(NULL, tsk); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 6f3822f..f491972 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -145,11 +145,7 @@ void __show_regs(struct pt_regs *regs) { int i; - printk("CPU: %d %s (%s %.*s)\n", - raw_smp_processor_id(), print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); + show_regs_print_info(KERN_DEFAULT); print_symbol("PC is at %s\n", instruction_pointer(regs)); print_symbol("LR is at %s\n", regs->regs[30]); printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n", @@ -166,7 +162,6 @@ void __show_regs(struct pt_regs *regs) void show_regs(struct pt_regs * regs) { printk("\n"); - printk("Pid: %d, comm: %20s\n", task_pid_nr(current), current->comm); __show_regs(regs); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index b3c5f62..61d7dd2 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -167,13 +167,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) } } -void dump_stack(void) -{ - dump_backtrace(NULL, NULL); -} - -EXPORT_SYMBOL(dump_stack); - void show_stack(struct task_struct *tsk, unsigned long *sp) { dump_backtrace(NULL, tsk); diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index 073c3c2..e7b6149 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -204,14 +204,6 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) show_stack_log_lvl(tsk, (unsigned long)stack, NULL, ""); } -void dump_stack(void) -{ - unsigned long stack; - - show_trace_log_lvl(current, &stack, NULL, ""); -} -EXPORT_SYMBOL(dump_stack); - static const char *cpu_modes[] = { "Application", "Supervisor", "Interrupt level 0", "Interrupt level 1", "Interrupt level 2", "Interrupt level 3", "Exception", "NMI" @@ -223,6 +215,8 @@ void show_regs_log_lvl(struct pt_regs *regs, const char *log_lvl) unsigned long lr = regs->lr; unsigned long mode = (regs->sr & MODE_MASK) >> MODE_SHIFT; + show_regs_print_info(log_lvl); + if (!user_mode(regs)) { sp = (unsigned long)regs + FRAME_SIZE_FULL; @@ -260,9 +254,6 @@ void show_regs_log_lvl(struct pt_regs *regs, const char *log_lvl) regs->sr & SR_I0M ? '0' : '.', regs->sr & SR_GM ? 'G' : 'g'); printk("%sCPU Mode: %s\n", log_lvl, cpu_modes[mode]); - printk("%sProcess: %s [%d] (task: %p thread: %p)\n", - log_lvl, current->comm, current->pid, current, - task_thread_info(current)); } void show_regs(struct pt_regs *regs) diff --git a/arch/blackfin/kernel/dumpstack.c b/arch/blackfin/kernel/dumpstack.c index 5cfbaa2..95ba6d9 100644 --- a/arch/blackfin/kernel/dumpstack.c +++ b/arch/blackfin/kernel/dumpstack.c @@ -168,6 +168,7 @@ void dump_stack(void) #endif trace_buffer_save(tflags); dump_bfin_trace_buffer(); + dump_stack_print_info(KERN_DEFAULT); show_stack(current, &stack); trace_buffer_restore(tflags); } diff --git a/arch/blackfin/kernel/trace.c b/arch/blackfin/kernel/trace.c index f7f7a18..c36efa0 100644 --- a/arch/blackfin/kernel/trace.c +++ b/arch/blackfin/kernel/trace.c @@ -853,6 +853,8 @@ void show_regs(struct pt_regs *fp) unsigned char in_atomic = (bfin_read_IPEND() & 0x10) || in_atomic(); pr_notice("\n"); + show_regs_print_info(KERN_NOTICE); + if (CPUID != bfin_cpuid()) pr_notice("Compiled for cpu family 0x%04x (Rev %d), " "but running on:0x%04x (Rev %d)\n", diff --git a/arch/c6x/kernel/traps.c b/arch/c6x/kernel/traps.c index 1be74e5..dcc2c2f 100644 --- a/arch/c6x/kernel/traps.c +++ b/arch/c6x/kernel/traps.c @@ -31,6 +31,7 @@ void __init trap_init(void) void show_regs(struct pt_regs *regs) { pr_err("\n"); + show_regs_print_info(KERN_ERR); pr_err("PC: %08lx SP: %08lx\n", regs->pc, regs->sp); pr_err("Status: %08lx ORIG_A4: %08lx\n", regs->csr, regs->orig_a4); pr_err("A0: %08lx B0: %08lx\n", regs->a0, regs->b0); @@ -67,15 +68,6 @@ void show_regs(struct pt_regs *regs) pr_err("A31: %08lx B31: %08lx\n", regs->a31, regs->b31); } -void dump_stack(void) -{ - unsigned long stack; - - show_stack(current, &stack); -} -EXPORT_SYMBOL(dump_stack); - - void die(char *str, struct pt_regs *fp, int nr) { console_verbose(); diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index 2ba23c1..753e9a0 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -176,6 +176,9 @@ unsigned long get_wchan(struct task_struct *p) void show_regs(struct pt_regs * regs) { unsigned long usp = rdusp(); + + show_regs_print_info(KERN_DEFAULT); + printk("IRP: %08lx SRP: %08lx DCCR: %08lx USP: %08lx MOF: %08lx\n", regs->irp, regs->srp, regs->dccr, usp, regs->mof ); printk(" r0: %08lx r1: %08lx r2: %08lx r3: %08lx\n", diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index 57451fa..cebd32e 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -164,6 +164,9 @@ get_wchan(struct task_struct *p) void show_regs(struct pt_regs * regs) { unsigned long usp = rdusp(); + + show_regs_print_info(KERN_DEFAULT); + printk("ERP: %08lx SRP: %08lx CCS: %08lx USP: %08lx MOF: %08lx\n", regs->erp, regs->srp, regs->ccs, usp, regs->mof); diff --git a/arch/cris/kernel/traps.c b/arch/cris/kernel/traps.c index a11ad32..0ffda73 100644 --- a/arch/cris/kernel/traps.c +++ b/arch/cris/kernel/traps.c @@ -147,13 +147,6 @@ show_stack(void) #endif void -dump_stack(void) -{ - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); - -void set_nmi_handler(void (*handler)(struct pt_regs *)) { nmi_handler = handler; diff --git a/arch/frv/kernel/traps.c b/arch/frv/kernel/traps.c index 5cfd142..4bff48c 100644 --- a/arch/frv/kernel/traps.c +++ b/arch/frv/kernel/traps.c @@ -466,17 +466,6 @@ asmlinkage void compound_exception(unsigned long esfr1, BUG(); } /* end compound_exception() */ -/*****************************************************************************/ -/* - * The architecture-independent backtrace generator - */ -void dump_stack(void) -{ - show_stack(NULL, NULL); -} - -EXPORT_SYMBOL(dump_stack); - void show_stack(struct task_struct *task, unsigned long *sp) { } @@ -508,6 +497,7 @@ void show_regs(struct pt_regs *regs) int loop; printk("\n"); + show_regs_print_info(KERN_DEFAULT); printk("Frame: @%08lx [%s]\n", (unsigned long) regs, @@ -522,8 +512,6 @@ void show_regs(struct pt_regs *regs) else printk(" | "); } - - printk("Process %s (pid: %d)\n", current->comm, current->pid); } void die_if_kernel(const char *str, ...) diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index a17d2cd..1a744ab 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -83,6 +83,8 @@ void machine_power_off(void) void show_regs(struct pt_regs * regs) { + show_regs_print_info(KERN_DEFAULT); + printk("\nPC: %08lx Status: %02x", regs->pc, regs->ccr); printk("\nORIG_ER0: %08lx ER0: %08lx ER1: %08lx", diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c index 7833aa3..cfe494d 100644 --- a/arch/h8300/kernel/traps.c +++ b/arch/h8300/kernel/traps.c @@ -164,10 +164,3 @@ void show_trace_task(struct task_struct *tsk) { show_stack(tsk,(unsigned long *)tsk->thread.esp0); } - -void dump_stack(void) -{ - show_stack(NULL,NULL); -} - -EXPORT_SYMBOL(dump_stack); diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index be5e2dd..cc2171b 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -191,14 +191,6 @@ void show_stack(struct task_struct *task, unsigned long *fp) do_show_stack(task, fp, 0); } -void dump_stack(void) -{ - unsigned long *fp; - asm("%0 = r30" : "=r" (fp)); - show_stack(current, fp); -} -EXPORT_SYMBOL(dump_stack); - int die(const char *str, struct pt_regs *regs, long err) { static struct { diff --git a/arch/hexagon/kernel/vm_events.c b/arch/hexagon/kernel/vm_events.c index 9b5a4a2..f337281 100644 --- a/arch/hexagon/kernel/vm_events.c +++ b/arch/hexagon/kernel/vm_events.c @@ -33,6 +33,8 @@ */ void show_regs(struct pt_regs *regs) { + show_regs_print_info(KERN_EMERG); + printk(KERN_EMERG "restart_r0: \t0x%08lx syscall_nr: %ld\n", regs->restart_r0, regs->syscall_nr); printk(KERN_EMERG "preds: \t\t0x%08lx\n", regs->preds); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index a26fc64..55d4ba4 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -96,21 +96,13 @@ show_stack (struct task_struct *task, unsigned long *sp) } void -dump_stack (void) -{ - show_stack(NULL, NULL); -} - -EXPORT_SYMBOL(dump_stack); - -void show_regs (struct pt_regs *regs) { unsigned long ip = regs->cr_iip + ia64_psr(regs)->ri; print_modules(); - printk("\nPid: %d, CPU %d, comm: %20s\n", task_pid_nr(current), - smp_processor_id(), current->comm); + printk("\n"); + show_regs_print_info(KERN_DEFAULT); printk("psr : %016lx ifs : %016lx ip : [<%016lx>] %s (%s)\n", regs->cr_ipsr, regs->cr_ifs, ip, print_tainted(), init_utsname()->release); diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 2029cc0..13bfdd2 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1063,6 +1063,7 @@ check_bugs (void) static int __init run_dmi_scan(void) { dmi_scan_machine(); + dmi_set_dump_stack_arch_desc(); return 0; } core_initcall(run_dmi_scan); diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index e2d0490..e69221d 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -73,6 +73,8 @@ void machine_power_off(void) void show_regs(struct pt_regs * regs) { printk("\n"); + show_regs_print_info(KERN_DEFAULT); + printk("BPC[%08lx]:PSW[%08lx]:LR [%08lx]:FP [%08lx]\n", \ regs->bpc, regs->psw, regs->lr, regs->fp); printk("BBPC[%08lx]:BBPSW[%08lx]:SPU[%08lx]:SPI[%08lx]\n", \ diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c index 9fe3467..a7a424f 100644 --- a/arch/m32r/kernel/traps.c +++ b/arch/m32r/kernel/traps.c @@ -167,15 +167,6 @@ void show_stack(struct task_struct *task, unsigned long *sp) show_trace(task, sp); } -void dump_stack(void) -{ - unsigned long stack; - - show_trace(current, &stack); -} - -EXPORT_SYMBOL(dump_stack); - static void show_registers(struct pt_regs *regs) { int i = 0; diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index f32ab22..88fcd8c 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -992,18 +992,6 @@ void show_stack(struct task_struct *task, unsigned long *stack) } /* - * The architecture-independent backtrace generator - */ -void dump_stack(void) -{ - unsigned long stack; - - show_trace(&stack); -} - -EXPORT_SYMBOL(dump_stack); - -/* * The vector number returned in the frame pointer may also contain * the "fs" (Fault Status) bits on ColdFire. These are in the bottom * 2 bits, and upper 2 bits. So we need to mask out the real vector diff --git a/arch/metag/kernel/process.c b/arch/metag/kernel/process.c index dc59235..483dff9 100644 --- a/arch/metag/kernel/process.c +++ b/arch/metag/kernel/process.c @@ -129,6 +129,8 @@ void show_regs(struct pt_regs *regs) "D1.7 " }; + show_regs_print_info(KERN_INFO); + pr_info(" pt_regs @ %p\n", regs); pr_info(" SaveMask = 0x%04hx\n", regs->ctx.SaveMask); pr_info(" Flags = 0x%04hx (%c%c%c%c)\n", regs->ctx.Flags, diff --git a/arch/metag/kernel/traps.c b/arch/metag/kernel/traps.c index 8961f24..2ceeaae 100644 --- a/arch/metag/kernel/traps.c +++ b/arch/metag/kernel/traps.c @@ -987,9 +987,3 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) show_trace(tsk, sp, NULL); } - -void dump_stack(void) -{ - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 7cce2e9..a558938 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -20,6 +20,8 @@ void show_regs(struct pt_regs *regs) { + show_regs_print_info(KERN_INFO); + pr_info(" Registers dump: mode=%X\r\n", regs->pt_mode); pr_info(" r1=%08lX, r2=%08lX, r3=%08lX, r4=%08lX\n", regs->r1, regs->r2, regs->r3, regs->r4); diff --git a/arch/microblaze/kernel/traps.c b/arch/microblaze/kernel/traps.c index 30e6b50..cb61953 100644 --- a/arch/microblaze/kernel/traps.c +++ b/arch/microblaze/kernel/traps.c @@ -75,9 +75,3 @@ void show_stack(struct task_struct *task, unsigned long *sp) debug_show_held_locks(task); } - -void dump_stack(void) -{ - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index c3abb881..2522551 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -206,19 +206,6 @@ void show_stack(struct task_struct *task, unsigned long *sp) show_stacktrace(task, ®s); } -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - struct pt_regs regs; - - prepare_frametrace(®s); - show_backtrace(current, ®s); -} - -EXPORT_SYMBOL(dump_stack); - static void show_code(unsigned int __user *pc) { long i; @@ -244,7 +231,7 @@ static void __show_regs(const struct pt_regs *regs) unsigned int cause = regs->cp0_cause; int i; - printk("Cpu %d\n", smp_processor_id()); + show_regs_print_info(KERN_DEFAULT); /* * Saved main processor registers diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 2da39fb..3707da5 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -97,6 +97,7 @@ void machine_power_off(void) void show_regs(struct pt_regs *regs) { + show_regs_print_info(KERN_DEFAULT); } /* diff --git a/arch/mn10300/kernel/traps.c b/arch/mn10300/kernel/traps.c index b900e5a..a7a987c 100644 --- a/arch/mn10300/kernel/traps.c +++ b/arch/mn10300/kernel/traps.c @@ -294,17 +294,6 @@ void show_stack(struct task_struct *task, unsigned long *sp) } /* - * the architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - unsigned long stack; - - show_stack(current, &stack); -} -EXPORT_SYMBOL(dump_stack); - -/* * dump the register file in the specified exception frame */ void show_registers_only(struct pt_regs *regs) diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 00c233b..386af25 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -90,6 +90,7 @@ void show_regs(struct pt_regs *regs) { extern void show_registers(struct pt_regs *regs); + show_regs_print_info(KERN_DEFAULT); /* __PHX__ cleanup this mess */ show_registers(regs); } diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 5cce396..3d3f606 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -105,17 +105,6 @@ void show_trace_task(struct task_struct *tsk) */ } -/* - * The architecture-independent backtrace generator - */ -void dump_stack(void) -{ - unsigned long stack; - - show_stack(current, &stack); -} -EXPORT_SYMBOL(dump_stack); - void show_registers(struct pt_regs *regs) { int i; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 0339181..433e75a 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -1,5 +1,6 @@ config PARISC def_bool y + select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select HAVE_IDE select HAVE_OPROFILE select HAVE_FUNCTION_TRACER if 64BIT diff --git a/arch/parisc/Kconfig.debug b/arch/parisc/Kconfig.debug index 7305ac8..bc989e5 100644 --- a/arch/parisc/Kconfig.debug +++ b/arch/parisc/Kconfig.debug @@ -12,18 +12,4 @@ config DEBUG_RODATA portion of the kernel code won't be covered by a TLB anymore. If in doubt, say "N". -config DEBUG_STRICT_USER_COPY_CHECKS - bool "Strict copy size checks" - depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING - ---help--- - Enabling this option turns a certain set of sanity checks for user - copy operations into compile time failures. - - The copy_from_user() etc checks are there to help test if there - are sufficient security checks on the length argument of - the copy operation, by having gcc prove that the argument is - within bounds. - - If unsure, or if you run an older (pre 4.4) gcc, say N. - endmenu diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index aeb8f8f..f702bff 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -126,6 +126,8 @@ void show_regs(struct pt_regs *regs) user = user_mode(regs); level = user ? KERN_DEBUG : KERN_CRIT; + show_regs_print_info(level); + print_gr(level, regs); for (i = 0; i < 8; i += 4) @@ -158,14 +160,6 @@ void show_regs(struct pt_regs *regs) } } - -void dump_stack(void) -{ - show_stack(NULL, NULL); -} - -EXPORT_SYMBOL(dump_stack); - static void do_show_stack(struct unwind_frame_info *info) { int i = 1; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 16e77a8..13a8d9d 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -831,6 +831,8 @@ void show_regs(struct pt_regs * regs) { int i, trap; + show_regs_print_info(KERN_DEFAULT); + printk("NIP: "REG" LR: "REG" CTR: "REG"\n", regs->nip, regs->link, regs->ctr); printk("REGS: %p TRAP: %04lx %s (%s)\n", @@ -850,12 +852,6 @@ void show_regs(struct pt_regs * regs) #else printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr); #endif - printk("TASK = %p[%d] '%s' THREAD: %p", - current, task_pid_nr(current), current->comm, task_thread_info(current)); - -#ifdef CONFIG_SMP - printk(" CPU: %d", raw_smp_processor_id()); -#endif /* CONFIG_SMP */ for (i = 0; i < 32; i++) { if ((i % REGS_PER_LINE) == 0) @@ -1362,12 +1358,6 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) } while (count++ < kstack_depth_to_print); } -void dump_stack(void) -{ - show_stack(current, NULL); -} -EXPORT_SYMBOL(dump_stack); - #ifdef CONFIG_PPC64 /* Called with hard IRQs off */ void __ppc64_runlatch_on(void) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 13f85de..3e34cd2 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2947,7 +2947,7 @@ static void sysrq_handle_xmon(int key) static struct sysrq_key_op sysrq_xmon_op = { .handler = sysrq_handle_xmon, - .help_msg = "Xmon", + .help_msg = "xmon(x)", .action_msg = "Entering xmon", }; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bda6ba6..ce640af 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -91,6 +91,7 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_BH select ARCH_INLINE_WRITE_UNLOCK_IRQ select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_SAVE_PAGE_KEYS if HIBERNATION select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug index fc32a2d..c56878e 100644 --- a/arch/s390/Kconfig.debug +++ b/arch/s390/Kconfig.debug @@ -17,20 +17,6 @@ config STRICT_DEVMEM If you are unsure, say Y. -config DEBUG_STRICT_USER_COPY_CHECKS - def_bool n - prompt "Strict user copy size checks" - ---help--- - Enabling this option turns a certain set of sanity checks for user - copy operations into compile time warnings. - - The copy_from_user() etc checks are there to help test if there - are sufficient security checks on the length argument of - the copy operation, by having gcc prove that the argument is - within bounds. - - If unsure, or if you run an older (pre 4.4) gcc, say N. - config S390_PTDUMP bool "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 03dce39..2982974 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -129,23 +129,6 @@ static void show_last_breaking_event(struct pt_regs *regs) #endif } -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); - static inline int mask_bits(struct pt_regs *regs, unsigned long bits) { return (regs->psw.mask & bits) / ((~bits + 1) & bits); @@ -183,14 +166,7 @@ void show_registers(struct pt_regs *regs) void show_regs(struct pt_regs *regs) { - printk("CPU: %d %s %s %.*s\n", - task_thread_info(current)->cpu, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk("Process %s (pid: %d, task: %p, ksp: %p)\n", - current->comm, current->pid, current, - (void *) current->thread.ksp); + show_regs_print_info(KERN_DEFAULT); show_registers(regs); /* Show stack backtrace if pt_regs is from kernel mode */ if (!user_mode(regs)) diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 6ab0d0b..20b0e97 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -3,7 +3,6 @@ # lib-y += delay.o string.o uaccess_std.o uaccess_pt.o -obj-y += usercopy.o obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o obj-$(CONFIG_64BIT) += mem64.o lib-$(CONFIG_64BIT) += uaccess_mvcos.o diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c index 0e46fb1..1517a7d 100644 --- a/arch/score/kernel/traps.c +++ b/arch/score/kernel/traps.c @@ -117,6 +117,8 @@ static void show_code(unsigned int *pc) */ void show_regs(struct pt_regs *regs) { + show_regs_print_info(KERN_DEFAULT); + printk("r0 : %08lx %08lx %08lx %08lx %08lx %08lx %08lx %08lx\n", regs->regs[0], regs->regs[1], regs->regs[2], regs->regs[3], regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); @@ -149,16 +151,6 @@ static void show_registers(struct pt_regs *regs) printk(KERN_NOTICE "\n"); } -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - show_stack(current_thread_info()->task, - (long *) get_irq_regs()->regs[0]); -} -EXPORT_SYMBOL(dump_stack); - void __die(const char *str, struct pt_regs *regs, const char *file, const char *func, unsigned long line) { diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c index 7617dc4..b959f55 100644 --- a/arch/sh/kernel/dumpstack.c +++ b/arch/sh/kernel/dumpstack.c @@ -158,9 +158,3 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) (unsigned long)task_stack_page(tsk)); show_trace(tsk, sp, NULL); } - -void dump_stack(void) -{ - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 73eb66f..ebd3933 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -32,11 +32,7 @@ void show_regs(struct pt_regs * regs) { printk("\n"); - printk("Pid : %d, Comm: \t\t%s\n", task_pid_nr(current), current->comm); - printk("CPU : %d \t\t%s (%s %.*s)\n\n", - smp_processor_id(), print_tainted(), init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); + show_regs_print_info(KERN_DEFAULT); print_symbol("PC is at %s\n", instruction_pointer(regs)); print_symbol("PR is at %s\n", regs->pr); diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index e611c85..174d124b 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -40,6 +40,7 @@ void show_regs(struct pt_regs *regs) unsigned long long ah, al, bh, bl, ch, cl; printk("\n"); + show_regs_print_info(KERN_DEFAULT); ah = (regs->pc) >> 32; al = (regs->pc) & 0xffffffff; diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index c852410..fdd819d 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -112,6 +112,8 @@ void show_regs(struct pt_regs *r) { struct reg_window32 *rw = (struct reg_window32 *) r->u_regs[14]; + show_regs_print_info(KERN_DEFAULT); + printk("PSR: %08lx PC: %08lx NPC: %08lx Y: %08lx %s\n", r->psr, r->pc, r->npc, r->y, print_tainted()); printk("PC: <%pS>\n", (void *) r->pc); @@ -142,11 +144,13 @@ void show_stack(struct task_struct *tsk, unsigned long *_ksp) struct reg_window32 *rw; int count = 0; - if (tsk != NULL) - task_base = (unsigned long) task_stack_page(tsk); - else - task_base = (unsigned long) current_thread_info(); + if (!tsk) + tsk = current; + + if (tsk == current && !_ksp) + __asm__ __volatile__("mov %%fp, %0" : "=r" (_ksp)); + task_base = (unsigned long) task_stack_page(tsk); fp = (unsigned long) _ksp; do { /* Bogus frame pointer? */ @@ -162,17 +166,6 @@ void show_stack(struct task_struct *tsk, unsigned long *_ksp) printk("\n"); } -void dump_stack(void) -{ - unsigned long *ksp; - - __asm__ __volatile__("mov %%fp, %0" - : "=r" (ksp)); - show_stack(current, ksp); -} - -EXPORT_SYMBOL(dump_stack); - /* * Note: sparc64 has a pretty intricated thread_saved_pc, check it out. */ diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 9fbf0d1..baebab2 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -163,6 +163,8 @@ static void show_regwindow(struct pt_regs *regs) void show_regs(struct pt_regs *regs) { + show_regs_print_info(KERN_DEFAULT); + printk("TSTATE: %016lx TPC: %016lx TNPC: %016lx Y: %08x %s\n", regs->tstate, regs->tpc, regs->tnpc, regs->y, print_tainted()); printk("TPC: <%pS>\n", (void *) regs->tpc); @@ -292,7 +294,7 @@ static void sysrq_handle_globreg(int key) static struct sysrq_key_op sparc_globalreg_op = { .handler = sysrq_handle_globreg, - .help_msg = "global-regs(Y)", + .help_msg = "global-regs(y)", .action_msg = "Show Global CPU Regs", }; @@ -362,7 +364,7 @@ static void sysrq_handle_globpmu(int key) static struct sysrq_key_op sparc_globalpmu_op = { .handler = sysrq_handle_globpmu, - .help_msg = "global-pmu(X)", + .help_msg = "global-pmu(x)", .action_msg = "Show Global PMU Regs", }; diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 8d38ca9..b3f833a 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2350,13 +2350,6 @@ void show_stack(struct task_struct *tsk, unsigned long *_ksp) } while (++count < 16); } -void dump_stack(void) -{ - show_stack(current, NULL); -} - -EXPORT_SYMBOL(dump_stack); - static inline struct reg_window *kernel_stack_up(struct reg_window *rw) { unsigned long fp = rw->ins[6]; diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index 8410065f2..dbe119b 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -45,4 +45,3 @@ obj-y += iomap.o obj-$(CONFIG_SPARC32) += atomic32.o ucmpdi2.o obj-y += ksyms.o obj-$(CONFIG_SPARC64) += PeeCeeI.o -obj-y += usercopy.o diff --git a/arch/sparc/lib/usercopy.c b/arch/sparc/lib/usercopy.c deleted file mode 100644 index 5c4284c..0000000 --- a/arch/sparc/lib/usercopy.c +++ /dev/null @@ -1,9 +0,0 @@ -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/bug.h> - -void copy_from_user_overflow(void) -{ - WARN(1, "Buffer overflow detected!\n"); -} -EXPORT_SYMBOL(copy_from_user_overflow); diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 25877ae..0f712f4e 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -19,6 +19,7 @@ config TILE select HAVE_SYSCALL_WRAPPERS if TILEGX select VIRT_TO_BUS select SYS_HYPERVISOR + select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_CLOCKEVENTS select MODULES_USE_ELF_RELA @@ -114,13 +115,6 @@ config STRICT_DEVMEM config SMP def_bool y -# Allow checking for compile-time determined overflow errors in -# copy_from_user(). There are still unprovable places in the -# generic code as of 2.6.34, so this option is not really compatible -# with -Werror, which is more useful in general. -config DEBUG_COPY_FROM_USER - def_bool n - config HVC_TILE depends on TTY select HVC_DRIVER diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index 9ab078a..8a082bc 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -395,7 +395,12 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return n; } -#ifdef CONFIG_DEBUG_COPY_FROM_USER +#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS +/* + * There are still unprovable places in the generic code as of 2.6.34, so this + * option is not really compatible with -Werror, which is more useful in + * general. + */ extern void copy_from_user_overflow(void) __compiletime_warning("copy_from_user() size is not provably correct"); diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 80b2a18..8ac3044 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -573,8 +573,7 @@ void show_regs(struct pt_regs *regs) int i; pr_err("\n"); - pr_err(" Pid: %d, comm: %20s, CPU: %d\n", - tsk->pid, tsk->comm, smp_processor_id()); + show_regs_print_info(KERN_ERR); #ifdef __tilegx__ for (i = 0; i < 51; i += 3) pr_err(" r%-2d: "REGFMT" r%-2d: "REGFMT" r%-2d: "REGFMT"\n", diff --git a/arch/tile/lib/uaccess.c b/arch/tile/lib/uaccess.c index f8d398c..030abe3 100644 --- a/arch/tile/lib/uaccess.c +++ b/arch/tile/lib/uaccess.c @@ -22,11 +22,3 @@ int __range_ok(unsigned long addr, unsigned long size) is_arch_mappable_range(addr, size)); } EXPORT_SYMBOL(__range_ok); - -#ifdef CONFIG_DEBUG_COPY_FROM_USER -void copy_from_user_overflow(void) -{ - WARN(1, "Buffer overflow detected!\n"); -} -EXPORT_SYMBOL(copy_from_user_overflow); -#endif diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c index e562ff8..7d101a2 100644 --- a/arch/um/kernel/sysrq.c +++ b/arch/um/kernel/sysrq.c @@ -35,18 +35,6 @@ void show_trace(struct task_struct *task, unsigned long * stack) } #endif -/* - * stack dumps generator - this is used by arch-independent code. - * And this is identical to i386 currently. - */ -void dump_stack(void) -{ - unsigned long stack; - - show_trace(current, &stack); -} -EXPORT_SYMBOL(dump_stack); - /*Stolen from arch/i386/kernel/traps.c */ static const int kstack_depth_to_print = 24; diff --git a/arch/um/sys-ppc/sysrq.c b/arch/um/sys-ppc/sysrq.c index f889449..1ff1ad7 100644 --- a/arch/um/sys-ppc/sysrq.c +++ b/arch/um/sys-ppc/sysrq.c @@ -11,6 +11,8 @@ void show_regs(struct pt_regs_subarch *regs) { printk("\n"); + show_regs_print_info(KERN_DEFAULT); + printk("show_regs(): insert regs here.\n"); #if 0 printk("\n"); diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c index 7fab86d..c944769 100644 --- a/arch/unicore32/kernel/process.c +++ b/arch/unicore32/kernel/process.c @@ -144,11 +144,7 @@ void __show_regs(struct pt_regs *regs) unsigned long flags; char buf[64]; - printk(KERN_DEFAULT "CPU: %d %s (%s %.*s)\n", - raw_smp_processor_id(), print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); + show_regs_print_info(KERN_DEFAULT); print_symbol("PC is at %s\n", instruction_pointer(regs)); print_symbol("LR is at %s\n", regs->UCreg_lr); printk(KERN_DEFAULT "pc : [<%08lx>] lr : [<%08lx>] psr: %08lx\n" diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c index 0870b68..c54e324 100644 --- a/arch/unicore32/kernel/traps.c +++ b/arch/unicore32/kernel/traps.c @@ -170,12 +170,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) c_backtrace(fp, mode); } -void dump_stack(void) -{ - dump_backtrace(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); - void show_stack(struct task_struct *tsk, unsigned long *sp) { dump_backtrace(NULL, tsk); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 05b057d..5db2117 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -20,6 +20,7 @@ config X86_64 ### Arch settings config X86 def_bool y + select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select HAVE_AOUT if X86_32 select HAVE_UNSTABLE_SCHED_CLOCK select ARCH_SUPPORTS_NUMA_BALANCING diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 16f7383..c198b7e 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -292,20 +292,6 @@ config OPTIMIZE_INLINING If unsure, say N. -config DEBUG_STRICT_USER_COPY_CHECKS - bool "Strict copy size checks" - depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING - ---help--- - Enabling this option turns a certain set of sanity checks for user - copy operations into compile time failures. - - The copy_from_user() etc checks are there to help test if there - are sufficient security checks on the length argument of - the copy operation, by having gcc prove that the argument is - within bounds. - - If unsure, or if you run an older (pre 4.4) gcc, say N. - config DEBUG_NMI_SELFTEST bool "NMI Selftest" depends on DEBUG_KERNEL && X86_LOCAL_APIC diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 03abf9b..81e94d9 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -162,7 +162,6 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, fs = get_fs(); set_fs(KERNEL_DS); has_dumped = 1; - current->flags |= PF_DUMPCORE; strncpy(dump.u_comm, current->comm, sizeof(current->comm)); dump.u_ar0 = offsetof(struct user32, regs); dump.signal = signr; diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 11e1152..2f03ff0 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -37,7 +37,4 @@ do { \ #include <asm-generic/bug.h> - -extern void show_regs_common(void); - #endif /* _ASM_X86_BUG_H */ diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index c8797d5..deb6421 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -176,26 +176,20 @@ void show_trace(struct task_struct *task, struct pt_regs *regs, void show_stack(struct task_struct *task, unsigned long *sp) { - show_stack_log_lvl(task, NULL, sp, 0, ""); -} - -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - unsigned long bp; + unsigned long bp = 0; unsigned long stack; - bp = stack_frame(current, NULL); - printk("Pid: %d, comm: %.20s %s %s %.*s\n", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - show_trace(NULL, NULL, &stack, bp); + /* + * Stack frames below this one aren't interesting. Don't show them + * if we're printing for %current. + */ + if (!sp && (!task || task == current)) { + sp = &stack; + bp = stack_frame(current, NULL); + } + + show_stack_log_lvl(task, NULL, sp, bp, ""); } -EXPORT_SYMBOL(dump_stack); static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; static int die_owner = -1; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 1038a41..f2a1770 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -86,11 +86,9 @@ void show_regs(struct pt_regs *regs) { int i; + show_regs_print_info(KERN_EMERG); __show_regs(regs, !user_mode_vm(regs)); - pr_emerg("Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", - TASK_COMM_LEN, current->comm, task_pid_nr(current), - current_thread_info(), current, task_thread_info(current)); /* * When in-kernel, we also print out the stack and code at the * time of the fault.. diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index b653675..addb207 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -249,14 +249,10 @@ void show_regs(struct pt_regs *regs) { int i; unsigned long sp; - const int cpu = smp_processor_id(); - struct task_struct *cur = current; sp = regs->sp; - printk("CPU %d ", cpu); + show_regs_print_info(KERN_DEFAULT); __show_regs(regs, 1); - printk(KERN_DEFAULT "Process %s (pid: %d, threadinfo %p, task %p)\n", - cur->comm, cur->pid, task_thread_info(cur), cur); /* * When in-kernel, we also print out the stack and code at the diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 14fcf55..607af0d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -121,30 +121,6 @@ void exit_thread(void) drop_fpu(me); } -void show_regs_common(void) -{ - const char *vendor, *product, *board; - - vendor = dmi_get_system_info(DMI_SYS_VENDOR); - if (!vendor) - vendor = ""; - product = dmi_get_system_info(DMI_PRODUCT_NAME); - if (!product) - product = ""; - - /* Board Name is optional */ - board = dmi_get_system_info(DMI_BOARD_NAME); - - printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s %s%s%s\n", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version, - vendor, product, - board ? "/" : "", - board ? board : ""); -} - void flush_thread(void) { struct task_struct *tsk = current; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index b5a8905..7305f7d 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -84,8 +84,6 @@ void __show_regs(struct pt_regs *regs, int all) savesegment(gs, gs); } - show_regs_common(); - printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n", (u16)regs->cs, regs->ip, regs->flags, smp_processor_id()); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0f49677..355ae06 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -62,7 +62,6 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int fsindex, gsindex; unsigned int ds, cs, es; - show_regs_common(); printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); printk_address(regs->ip, 1); printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4689855..56f7fcf 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -996,6 +996,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); dmi_scan_machine(); + dmi_set_dump_stack_arch_desc(); /* * VMware detection requires dmi to be available, so this diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index f0312d7..3eb18ac 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -689,9 +689,3 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return n; } EXPORT_SYMBOL(_copy_from_user); - -void copy_from_user_overflow(void) -{ - WARN(1, "Buffer overflow detected!\n"); -} -EXPORT_SYMBOL(copy_from_user_overflow); diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 923db5c..458186d 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -383,6 +383,8 @@ void show_regs(struct pt_regs * regs) { int i, wmask; + show_regs_print_info(KERN_DEFAULT); + wmask = regs->wmask & ~1; for (i = 0; i < 16; i++) { @@ -481,14 +483,6 @@ void show_stack(struct task_struct *task, unsigned long *sp) show_trace(task, stack); } -void dump_stack(void) -{ - show_stack(current, NULL); -} - -EXPORT_SYMBOL(dump_stack); - - void show_code(unsigned int *pc) { long i; diff --git a/drivers/Kconfig b/drivers/Kconfig index 78a956e..8d96238 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -120,6 +120,8 @@ source "drivers/vfio/Kconfig" source "drivers/vlynq/Kconfig" +source "drivers/virt/Kconfig" + source "drivers/virtio/Kconfig" source "drivers/hv/Kconfig" @@ -144,8 +146,6 @@ source "drivers/remoteproc/Kconfig" source "drivers/rpmsg/Kconfig" -source "drivers/virt/Kconfig" - source "drivers/devfreq/Kconfig" source "drivers/extcon/Kconfig" diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c index 42e67ad..ab41be6 100644 --- a/drivers/block/aoe/aoechr.c +++ b/drivers/block/aoe/aoechr.c @@ -139,13 +139,12 @@ bail: spin_unlock_irqrestore(&emsgs_lock, flags); return; } - mp = kmalloc(n, GFP_ATOMIC); + mp = kmemdup(msg, n, GFP_ATOMIC); if (mp == NULL) { printk(KERN_ERR "aoe: allocation failure, len=%ld\n", n); goto bail; } - memcpy(mp, msg, n); em->msg = mp; em->flags |= EMFL_VALID; em->len = n; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 7fecc78..037288e 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -856,6 +856,8 @@ static int __init nbd_init(void) disk->queue->limits.discard_granularity = 512; disk->queue->limits.max_discard_sectors = UINT_MAX; disk->queue->limits.discard_zeroes_data = 0; + blk_queue_max_hw_sectors(disk->queue, 65536); + disk->queue->limits.max_sectors = 256; } if (register_blkdev(NBD_MAJOR, "nbd")) { diff --git a/drivers/char/random.c b/drivers/char/random.c index 32a6c57..cd9a621 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1485,6 +1485,7 @@ unsigned int get_random_int(void) return ret; } +EXPORT_SYMBOL(get_random_int); /* * randomize_range() returns a start address such that diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 4cd392d..b95159b 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -22,6 +22,9 @@ static u16 __initdata dmi_ver; */ static int dmi_initialized; +/* DMI system identification string used during boot */ +static char dmi_ids_string[128] __initdata; + static const char * __init dmi_string_nosave(const struct dmi_header *dm, u8 s) { const u8 *bp = ((u8 *) dm) + dm->length; @@ -376,99 +379,103 @@ static void __init dmi_decode(const struct dmi_header *dm, void *dummy) } } -static void __init print_filtered(const char *info) +static int __init print_filtered(char *buf, size_t len, const char *info) { + int c = 0; const char *p; if (!info) - return; + return c; for (p = info; *p; p++) if (isprint(*p)) - printk(KERN_CONT "%c", *p); + c += scnprintf(buf + c, len - c, "%c", *p); else - printk(KERN_CONT "\\x%02x", *p & 0xff); + c += scnprintf(buf + c, len - c, "\\x%02x", *p & 0xff); + return c; } -static void __init dmi_dump_ids(void) +static void __init dmi_format_ids(char *buf, size_t len) { + int c = 0; const char *board; /* Board Name is optional */ - printk(KERN_DEBUG "DMI: "); - print_filtered(dmi_get_system_info(DMI_SYS_VENDOR)); - printk(KERN_CONT " "); - print_filtered(dmi_get_system_info(DMI_PRODUCT_NAME)); + c += print_filtered(buf + c, len - c, + dmi_get_system_info(DMI_SYS_VENDOR)); + c += scnprintf(buf + c, len - c, " "); + c += print_filtered(buf + c, len - c, + dmi_get_system_info(DMI_PRODUCT_NAME)); + board = dmi_get_system_info(DMI_BOARD_NAME); if (board) { - printk(KERN_CONT "/"); - print_filtered(board); + c += scnprintf(buf + c, len - c, "/"); + c += print_filtered(buf + c, len - c, board); } - printk(KERN_CONT ", BIOS "); - print_filtered(dmi_get_system_info(DMI_BIOS_VERSION)); - printk(KERN_CONT " "); - print_filtered(dmi_get_system_info(DMI_BIOS_DATE)); - printk(KERN_CONT "\n"); + c += scnprintf(buf + c, len - c, ", BIOS "); + c += print_filtered(buf + c, len - c, + dmi_get_system_info(DMI_BIOS_VERSION)); + c += scnprintf(buf + c, len - c, " "); + c += print_filtered(buf + c, len - c, + dmi_get_system_info(DMI_BIOS_DATE)); } -static int __init dmi_present(const char __iomem *p) +static int __init dmi_present(const u8 *buf) { - u8 buf[15]; + int smbios_ver; + + if (memcmp(buf, "_SM_", 4) == 0 && + buf[5] < 32 && dmi_checksum(buf, buf[5])) { + smbios_ver = (buf[6] << 8) + buf[7]; + + /* Some BIOS report weird SMBIOS version, fix that up */ + switch (smbios_ver) { + case 0x021F: + case 0x0221: + pr_debug("SMBIOS version fixup(2.%d->2.%d)\n", + smbios_ver & 0xFF, 3); + smbios_ver = 0x0203; + break; + case 0x0233: + pr_debug("SMBIOS version fixup(2.%d->2.%d)\n", 51, 6); + smbios_ver = 0x0206; + break; + } + } else { + smbios_ver = 0; + } - memcpy_fromio(buf, p, 15); - if (dmi_checksum(buf, 15)) { + buf += 16; + + if (memcmp(buf, "_DMI_", 5) == 0 && dmi_checksum(buf, 15)) { dmi_num = (buf[13] << 8) | buf[12]; dmi_len = (buf[7] << 8) | buf[6]; dmi_base = (buf[11] << 24) | (buf[10] << 16) | (buf[9] << 8) | buf[8]; if (dmi_walk_early(dmi_decode) == 0) { - if (dmi_ver) + if (smbios_ver) { + dmi_ver = smbios_ver; pr_info("SMBIOS %d.%d present.\n", dmi_ver >> 8, dmi_ver & 0xFF); - else { + } else { dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F); pr_info("Legacy DMI %d.%d present.\n", dmi_ver >> 8, dmi_ver & 0xFF); } - dmi_dump_ids(); + dmi_format_ids(dmi_ids_string, sizeof(dmi_ids_string)); + printk(KERN_DEBUG "DMI: %s\n", dmi_ids_string); return 0; } } - dmi_ver = 0; - return 1; -} - -static int __init smbios_present(const char __iomem *p) -{ - u8 buf[32]; - memcpy_fromio(buf, p, 32); - if ((buf[5] < 32) && dmi_checksum(buf, buf[5])) { - dmi_ver = (buf[6] << 8) + buf[7]; - - /* Some BIOS report weird SMBIOS version, fix that up */ - switch (dmi_ver) { - case 0x021F: - case 0x0221: - pr_debug("SMBIOS version fixup(2.%d->2.%d)\n", - dmi_ver & 0xFF, 3); - dmi_ver = 0x0203; - break; - case 0x0233: - pr_debug("SMBIOS version fixup(2.%d->2.%d)\n", 51, 6); - dmi_ver = 0x0206; - break; - } - return memcmp(p + 16, "_DMI_", 5) || dmi_present(p + 16); - } return 1; } void __init dmi_scan_machine(void) { char __iomem *p, *q; - int rc; + char buf[32]; if (efi_enabled(EFI_CONFIG_TABLES)) { if (efi.smbios == EFI_INVALID_TABLE_ADDR) @@ -481,10 +488,10 @@ void __init dmi_scan_machine(void) p = dmi_ioremap(efi.smbios, 32); if (p == NULL) goto error; - - rc = smbios_present(p); + memcpy_fromio(buf, p, 32); dmi_iounmap(p, 32); - if (!rc) { + + if (!dmi_present(buf)) { dmi_available = 1; goto out; } @@ -499,18 +506,15 @@ void __init dmi_scan_machine(void) if (p == NULL) goto error; + memset(buf, 0, 16); for (q = p; q < p + 0x10000; q += 16) { - if (memcmp(q, "_SM_", 4) == 0 && q - p <= 0xFFE0) - rc = smbios_present(q); - else if (memcmp(q, "_DMI_", 5) == 0) - rc = dmi_present(q); - else - continue; - if (!rc) { + memcpy_fromio(buf + 16, q, 16); + if (!dmi_present(buf)) { dmi_available = 1; dmi_iounmap(p, 0x10000); goto out; } + memcpy(buf, buf + 16, 16); } dmi_iounmap(p, 0x10000); } @@ -521,6 +525,19 @@ void __init dmi_scan_machine(void) } /** + * dmi_set_dump_stack_arch_desc - set arch description for dump_stack() + * + * Invoke dump_stack_set_arch_desc() with DMI system information so that + * DMI identifiers are printed out on task dumps. Arch boot code should + * call this function after dmi_scan_machine() if it wants to print out DMI + * identifiers on task dumps. + */ +void __init dmi_set_dump_stack_arch_desc(void) +{ + dump_stack_set_arch_desc("%s", dmi_ids_string); +} + +/** * dmi_matches - check if dmi_system_id structure matches system DMI data * @dmi: pointer to the dmi_system_id structure to check */ diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c index a7c5b31..9718661 100644 --- a/drivers/memstick/host/r592.c +++ b/drivers/memstick/host/r592.c @@ -847,7 +847,7 @@ static void r592_remove(struct pci_dev *pdev) dev->dummy_dma_page_physical_address); } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int r592_suspend(struct device *core_dev) { struct pci_dev *pdev = to_pci_dev(core_dev); @@ -870,10 +870,10 @@ static int r592_resume(struct device *core_dev) r592_update_card_detect(dev); return 0; } - -SIMPLE_DEV_PM_OPS(r592_pm_ops, r592_suspend, r592_resume); #endif +static SIMPLE_DEV_PM_OPS(r592_pm_ops, r592_suspend, r592_resume); + MODULE_DEVICE_TABLE(pci, r592_pci_id_tbl); static struct pci_driver r852_pci_driver = { @@ -881,9 +881,7 @@ static struct pci_driver r852_pci_driver = { .id_table = r592_pci_id_tbl, .probe = r592_probe, .remove = r592_remove, -#ifdef CONFIG_PM .driver.pm = &r592_pm_ops, -#endif }; static __init int r592_module_init(void) diff --git a/drivers/message/i2o/i2o_config.c b/drivers/message/i2o/i2o_config.c index 5451bef..a60c188 100644 --- a/drivers/message/i2o/i2o_config.c +++ b/drivers/message/i2o/i2o_config.c @@ -687,6 +687,11 @@ static int i2o_cfg_passthru32(struct file *file, unsigned cmnd, } size = size >> 16; size *= 4; + if (size > sizeof(rmsg)) { + rcode = -EINVAL; + goto sg_list_cleanup; + } + /* Copy in the user's I2O command */ if (copy_from_user(rmsg, user_msg, size)) { rcode = -EFAULT; @@ -922,6 +927,11 @@ static int i2o_cfg_passthru(unsigned long arg) } size = size >> 16; size *= 4; + if (size > sizeof(rmsg)) { + rcode = -EFAULT; + goto sg_list_cleanup; + } + /* Copy in the user's I2O command */ if (copy_from_user(rmsg, user_msg, size)) { rcode = -EFAULT; diff --git a/drivers/net/ethernet/ibm/emac/debug.c b/drivers/net/ethernet/ibm/emac/debug.c index b16b482..a559f32 100644 --- a/drivers/net/ethernet/ibm/emac/debug.c +++ b/drivers/net/ethernet/ibm/emac/debug.c @@ -245,7 +245,7 @@ static void emac_sysrq_handler(int key) static struct sysrq_key_op emac_sysrq_op = { .handler = emac_sysrq_handler, - .help_msg = "emaC", + .help_msg = "emac(c)", .action_msg = "Show EMAC(s) status", }; diff --git a/drivers/pps/Kconfig b/drivers/pps/Kconfig index 982d16b..7512e98 100644 --- a/drivers/pps/Kconfig +++ b/drivers/pps/Kconfig @@ -20,10 +20,10 @@ config PPS To compile this driver as a module, choose M here: the module will be called pps_core.ko. +if PPS config PPS_DEBUG bool "PPS debugging messages" - depends on PPS help Say Y here if you want the PPS support to produce a bunch of debug messages to the system log. Select this if you are having a @@ -31,13 +31,15 @@ config PPS_DEBUG config NTP_PPS bool "PPS kernel consumer support" - depends on PPS && !NO_HZ + depends on !NO_HZ help This option adds support for direct in-kernel time synchronization using an external PPS signal. It doesn't work on tickless systems at the moment. +endif + source drivers/pps/clients/Kconfig source drivers/pps/generators/Kconfig diff --git a/drivers/pps/kc.c b/drivers/pps/kc.c index 079e930..e219db1 100644 --- a/drivers/pps/kc.c +++ b/drivers/pps/kc.c @@ -34,10 +34,10 @@ */ /* state variables to bind kernel consumer */ -DEFINE_SPINLOCK(pps_kc_hardpps_lock); +static DEFINE_SPINLOCK(pps_kc_hardpps_lock); /* PPS API (RFC 2783): current source and mode for kernel consumer */ -struct pps_device *pps_kc_hardpps_dev; /* unique pointer to device */ -int pps_kc_hardpps_mode; /* mode bits for kernel consumer */ +static struct pps_device *pps_kc_hardpps_dev; /* unique pointer to device */ +static int pps_kc_hardpps_mode; /* mode bits for kernel consumer */ /* pps_kc_bind - control PPS kernel consumer binding * @pps: the PPS source diff --git a/drivers/staging/speakup/kobjects.c b/drivers/staging/speakup/kobjects.c index d6d9264..943b6c1 100644 --- a/drivers/staging/speakup/kobjects.c +++ b/drivers/staging/speakup/kobjects.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/kobject.h> #include <linux/string.h> +#include <linux/string_helpers.h> #include <linux/sysfs.h> #include <linux/ctype.h> @@ -417,7 +418,7 @@ static ssize_t synth_direct_store(struct kobject *kobj, bytes = min_t(size_t, len, 250); strncpy(tmp, ptr, bytes); tmp[bytes] = '\0'; - spk_xlate(tmp); + string_unescape_any_inplace(tmp); synth_printf("%s", tmp); ptr += bytes; len -= bytes; @@ -605,7 +606,8 @@ ssize_t spk_var_store(struct kobject *kobj, struct kobj_attribute *attr, if (param->data == NULL) return 0; ret = 0; - cp = spk_xlate((char *) buf); + cp = (char *)buf; + string_unescape_any_inplace(cp); spk_lock(flags); switch (param->var_type) { diff --git a/drivers/staging/speakup/speakup.h b/drivers/staging/speakup/speakup.h index c387a02..0126f71 100644 --- a/drivers/staging/speakup/speakup.h +++ b/drivers/staging/speakup/speakup.h @@ -54,7 +54,6 @@ void spk_get_index_count(int *linecount, int *sentcount); extern int spk_set_key_info(const u_char *key_info, u_char *k_buffer); extern char *spk_strlwr(char *s); extern char *spk_s2uchar(char *start, char *dest); -extern char *spk_xlate(char *s); extern int speakup_kobj_init(void); extern void speakup_kobj_exit(void); extern int spk_chartab_get_value(char *keyword); diff --git a/drivers/staging/speakup/varhandlers.c b/drivers/staging/speakup/varhandlers.c index 0099cb1..7f6288f 100644 --- a/drivers/staging/speakup/varhandlers.c +++ b/drivers/staging/speakup/varhandlers.c @@ -328,49 +328,3 @@ char *spk_s2uchar(char *start, char *dest) *dest = (u_char)val; return start; } - -char *spk_xlate(char *s) -{ - static const char finds[] = "nrtvafe"; - static const char subs[] = "\n\r\t\013\001\014\033"; - static const char hx[] = "0123456789abcdefABCDEF"; - char *p = s, *p1, *p2, c; - int num; - while ((p = strchr(p, '\\'))) { - p1 = p+1; - p2 = strchr(finds, *p1); - if (p2) { - *p++ = subs[p2-finds]; - p1++; - } else if (*p1 >= '0' && *p1 <= '7') { - num = (*p1++)&7; - while (num < 32 && *p1 >= '0' && *p1 <= '7') { - num <<= 3; - num += (*p1++)&7; - } - *p++ = num; - } else if (*p1 == 'x' && - strchr(hx, p1[1]) && strchr(hx, p1[2])) { - p1++; - c = *p1++; - if (c > '9') - c = (c - '7') & 0x0f; - else - c -= '0'; - num = c << 4; - c = *p1++; - if (c > '9') - c = (c-'7')&0x0f; - else - c -= '0'; - num += c; - *p++ = num; - } else - *p++ = *p1++; - p2 = p; - while (*p1) - *p2++ = *p1++; - *p2 = '\0'; - } - return s; -} diff --git a/drivers/staging/zcache/Kconfig b/drivers/staging/zcache/Kconfig index 05e87a1..2d7b2da 100644 --- a/drivers/staging/zcache/Kconfig +++ b/drivers/staging/zcache/Kconfig @@ -1,5 +1,5 @@ config ZCACHE - bool "Dynamic compression of swap pages and clean pagecache pages" + tristate "Dynamic compression of swap pages and clean pagecache pages" depends on CRYPTO=y && SWAP=y && CLEANCACHE && FRONTSWAP select CRYPTO_LZO default n @@ -19,8 +19,8 @@ config ZCACHE_DEBUG how zcache is doing. You probably want to set this to 'N'. config RAMSTER - bool "Cross-machine RAM capacity sharing, aka peer-to-peer tmem" - depends on CONFIGFS_FS=y && SYSFS=y && !HIGHMEM && ZCACHE=y + tristate "Cross-machine RAM capacity sharing, aka peer-to-peer tmem" + depends on CONFIGFS_FS=y && SYSFS=y && !HIGHMEM && ZCACHE depends on NET # must ensure struct page is 8-byte aligned select HAVE_ALIGNED_STRUCT_PAGE if !64BIT diff --git a/drivers/staging/zcache/ramster.h b/drivers/staging/zcache/ramster.h index 1b71aea..e1f91d5 100644 --- a/drivers/staging/zcache/ramster.h +++ b/drivers/staging/zcache/ramster.h @@ -11,10 +11,14 @@ #ifndef _ZCACHE_RAMSTER_H_ #define _ZCACHE_RAMSTER_H_ +#ifdef CONFIG_RAMSTER_MODULE +#define CONFIG_RAMSTER +#endif + #ifdef CONFIG_RAMSTER #include "ramster/ramster.h" #else -static inline void ramster_init(bool x, bool y, bool z) +static inline void ramster_init(bool x, bool y, bool z, bool w) { } diff --git a/drivers/staging/zcache/ramster/debug.c b/drivers/staging/zcache/ramster/debug.c index bf34133..327e4f0 100644 --- a/drivers/staging/zcache/ramster/debug.c +++ b/drivers/staging/zcache/ramster/debug.c @@ -43,7 +43,7 @@ static struct debug_entry { }; #undef ATTR -int __init ramster_debugfs_init(void) +int ramster_debugfs_init(void) { int i; struct dentry *root = debugfs_create_dir("ramster", NULL); diff --git a/drivers/staging/zcache/ramster/nodemanager.c b/drivers/staging/zcache/ramster/nodemanager.c index c0f4815..2cfe933 100644 --- a/drivers/staging/zcache/ramster/nodemanager.c +++ b/drivers/staging/zcache/ramster/nodemanager.c @@ -949,7 +949,7 @@ static void __exit exit_r2nm(void) r2hb_exit(); } -static int __init init_r2nm(void) +int r2nm_init(void) { int ret = -1; @@ -986,10 +986,11 @@ out_r2hb: out: return ret; } +EXPORT_SYMBOL_GPL(r2nm_init); MODULE_AUTHOR("Oracle"); MODULE_LICENSE("GPL"); -/* module_init(init_r2nm) */ -late_initcall(init_r2nm); -/* module_exit(exit_r2nm) */ +#ifndef CONFIG_RAMSTER_MODULE +late_initcall(r2nm_init); +#endif diff --git a/drivers/staging/zcache/ramster/ramster.c b/drivers/staging/zcache/ramster/ramster.c index 8781627..b18b887 100644 --- a/drivers/staging/zcache/ramster/ramster.c +++ b/drivers/staging/zcache/ramster/ramster.c @@ -121,6 +121,7 @@ int ramster_do_preload_flnode(struct tmem_pool *pool) kmem_cache_free(ramster_flnode_cache, flnode); return ret; } +EXPORT_SYMBOL_GPL(ramster_do_preload_flnode); /* * Called by the message handler after a (still compressed) page has been @@ -388,6 +389,7 @@ void *ramster_pampd_free(void *pampd, struct tmem_pool *pool, } return local_pampd; } +EXPORT_SYMBOL_GPL(ramster_pampd_free); void ramster_count_foreign_pages(bool eph, int count) { @@ -408,6 +410,7 @@ void ramster_count_foreign_pages(bool eph, int count) } } } +EXPORT_SYMBOL_GPL(ramster_count_foreign_pages); /* * For now, just push over a few pages every few seconds to @@ -593,7 +596,7 @@ requeue: ramster_remotify_queue_delayed_work(HZ); } -void __init ramster_remotify_init(void) +void ramster_remotify_init(void) { unsigned long n = 60UL; ramster_remotify_workqueue = @@ -768,8 +771,10 @@ static bool frontswap_selfshrinking __read_mostly; static void selfshrink_process(struct work_struct *work); static DECLARE_DELAYED_WORK(selfshrink_worker, selfshrink_process); +#ifndef CONFIG_RAMSTER_MODULE /* Enable/disable with kernel boot option. */ -static bool use_frontswap_selfshrink __initdata = true; +static bool use_frontswap_selfshrink = true; +#endif /* * The default values for the following parameters were deemed reasonable @@ -824,6 +829,7 @@ static void frontswap_selfshrink(void) frontswap_shrink(tgt_frontswap_pages); } +#ifndef CONFIG_RAMSTER_MODULE static int __init ramster_nofrontswap_selfshrink_setup(char *s) { use_frontswap_selfshrink = false; @@ -831,6 +837,7 @@ static int __init ramster_nofrontswap_selfshrink_setup(char *s) } __setup("noselfshrink", ramster_nofrontswap_selfshrink_setup); +#endif static void selfshrink_process(struct work_struct *work) { @@ -849,6 +856,7 @@ void ramster_cpu_up(int cpu) per_cpu(ramster_remoteputmem1, cpu) = p1; per_cpu(ramster_remoteputmem2, cpu) = p2; } +EXPORT_SYMBOL_GPL(ramster_cpu_up); void ramster_cpu_down(int cpu) { @@ -864,6 +872,7 @@ void ramster_cpu_down(int cpu) kp->flnode = NULL; } } +EXPORT_SYMBOL_GPL(ramster_cpu_down); void ramster_register_pamops(struct tmem_pamops *pamops) { @@ -874,9 +883,11 @@ void ramster_register_pamops(struct tmem_pamops *pamops) pamops->repatriate = ramster_pampd_repatriate; pamops->repatriate_preload = ramster_pampd_repatriate_preload; } +EXPORT_SYMBOL_GPL(ramster_register_pamops); -void __init ramster_init(bool cleancache, bool frontswap, - bool frontswap_exclusive_gets) +void ramster_init(bool cleancache, bool frontswap, + bool frontswap_exclusive_gets, + bool frontswap_selfshrink) { int ret = 0; @@ -891,10 +902,17 @@ void __init ramster_init(bool cleancache, bool frontswap, if (ret) pr_err("ramster: can't create sysfs for ramster\n"); (void)r2net_register_handlers(); +#ifdef CONFIG_RAMSTER_MODULE + ret = r2nm_init(); + if (ret) + pr_err("ramster: can't init r2net\n"); + frontswap_selfshrinking = frontswap_selfshrink; +#else + frontswap_selfshrinking = use_frontswap_selfshrink; +#endif INIT_LIST_HEAD(&ramster_rem_op_list); ramster_flnode_cache = kmem_cache_create("ramster_flnode", sizeof(struct flushlist_node), 0, 0, NULL); - frontswap_selfshrinking = use_frontswap_selfshrink; if (frontswap_selfshrinking) { pr_info("ramster: Initializing frontswap selfshrink driver.\n"); schedule_delayed_work(&selfshrink_worker, @@ -902,3 +920,4 @@ void __init ramster_init(bool cleancache, bool frontswap, } ramster_remotify_init(); } +EXPORT_SYMBOL_GPL(ramster_init); diff --git a/drivers/staging/zcache/ramster/ramster.h b/drivers/staging/zcache/ramster/ramster.h index 12ae56f..6d41a7a 100644 --- a/drivers/staging/zcache/ramster/ramster.h +++ b/drivers/staging/zcache/ramster/ramster.h @@ -147,7 +147,7 @@ extern int r2net_register_handlers(void); extern int r2net_remote_target_node_set(int); extern int ramster_remotify_pageframe(bool); -extern void ramster_init(bool, bool, bool); +extern void ramster_init(bool, bool, bool, bool); extern void ramster_register_pamops(struct tmem_pamops *); extern int ramster_localify(int, struct tmem_oid *oidp, uint32_t, char *, unsigned int, void *); diff --git a/drivers/staging/zcache/ramster/ramster_nodemanager.h b/drivers/staging/zcache/ramster/ramster_nodemanager.h index 49f879d..dbaae34 100644 --- a/drivers/staging/zcache/ramster/ramster_nodemanager.h +++ b/drivers/staging/zcache/ramster/ramster_nodemanager.h @@ -36,4 +36,6 @@ /* host name, group name, cluster name all 64 bytes */ #define R2NM_MAX_NAME_LEN 64 /* __NEW_UTS_LEN */ +extern int r2nm_init(void); + #endif /* _RAMSTER_NODEMANAGER_H */ diff --git a/drivers/staging/zcache/tmem.c b/drivers/staging/zcache/tmem.c index a2b7e03..d7e51e4 100644 --- a/drivers/staging/zcache/tmem.c +++ b/drivers/staging/zcache/tmem.c @@ -35,7 +35,8 @@ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/atomic.h> -#ifdef CONFIG_RAMSTER +#include <linux/export.h> +#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE) #include <linux/delay.h> #endif @@ -641,6 +642,7 @@ void *tmem_localify_get_pampd(struct tmem_pool *pool, struct tmem_oid *oidp, /* note, hashbucket remains locked */ return pampd; } +EXPORT_SYMBOL_GPL(tmem_localify_get_pampd); void tmem_localify_finish(struct tmem_obj *obj, uint32_t index, void *pampd, void *saved_hb, bool delete) @@ -658,6 +660,7 @@ void tmem_localify_finish(struct tmem_obj *obj, uint32_t index, } spin_unlock(&hb->lock); } +EXPORT_SYMBOL_GPL(tmem_localify_finish); /* * For ramster only. Helper function to support asynchronous tmem_get. @@ -719,6 +722,7 @@ out: spin_unlock(&hb->lock); return ret; } +EXPORT_SYMBOL_GPL(tmem_replace); #endif /* diff --git a/drivers/staging/zcache/tmem.h b/drivers/staging/zcache/tmem.h index adbe5a8..d128ce2 100644 --- a/drivers/staging/zcache/tmem.h +++ b/drivers/staging/zcache/tmem.h @@ -126,7 +126,7 @@ static inline unsigned tmem_oid_hash(struct tmem_oid *oidp) TMEM_HASH_BUCKET_BITS); } -#ifdef CONFIG_RAMSTER +#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE) struct tmem_xhandle { uint8_t client_id; uint8_t xh_data_cksum; @@ -171,7 +171,7 @@ struct tmem_obj { unsigned int objnode_tree_height; unsigned long objnode_count; long pampd_count; -#ifdef CONFIG_RAMSTER +#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE) /* * for current design of ramster, all pages belonging to * an object reside on the same remotenode and extra is @@ -215,7 +215,7 @@ struct tmem_pamops { uint32_t); void (*free)(void *, struct tmem_pool *, struct tmem_oid *, uint32_t, bool); -#ifdef CONFIG_RAMSTER +#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE) void (*new_obj)(struct tmem_obj *); void (*free_obj)(struct tmem_pool *, struct tmem_obj *, bool); void *(*repatriate_preload)(void *, struct tmem_pool *, @@ -247,7 +247,7 @@ extern int tmem_flush_page(struct tmem_pool *, struct tmem_oid *, extern int tmem_flush_object(struct tmem_pool *, struct tmem_oid *); extern int tmem_destroy_pool(struct tmem_pool *); extern void tmem_new_pool(struct tmem_pool *, uint32_t); -#ifdef CONFIG_RAMSTER +#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE) extern int tmem_replace(struct tmem_pool *, struct tmem_oid *, uint32_t index, void *); extern void *tmem_localify_get_pampd(struct tmem_pool *, struct tmem_oid *, diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index e23d814..522cb8e 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -37,8 +37,10 @@ #include "debug.h" #ifdef CONFIG_RAMSTER static bool ramster_enabled __read_mostly; +static int disable_frontswap_selfshrink; #else #define ramster_enabled false +#define disable_frontswap_selfshrink 0 #endif #ifndef __PG_WAS_ACTIVE @@ -81,8 +83,12 @@ static char *namestr __read_mostly = "zcache"; (__GFP_FS | __GFP_NORETRY | __GFP_NOWARN | __GFP_NOMEMALLOC) /* crypto API for zcache */ +#ifdef CONFIG_ZCACHE_MODULE +static char *zcache_comp_name = "lzo"; +#else #define ZCACHE_COMP_NAME_SZ CRYPTO_MAX_ALG_NAME static char zcache_comp_name[ZCACHE_COMP_NAME_SZ] __read_mostly; +#endif static struct crypto_comp * __percpu *zcache_comp_pcpu_tfms __read_mostly; enum comp_op { @@ -1576,9 +1582,9 @@ static struct cleancache_ops zcache_cleancache_ops = { .init_fs = zcache_cleancache_init_fs }; -struct cleancache_ops zcache_cleancache_register_ops(void) +struct cleancache_ops *zcache_cleancache_register_ops(void) { - struct cleancache_ops old_ops = + struct cleancache_ops *old_ops = cleancache_register_ops(&zcache_cleancache_ops); return old_ops; @@ -1707,9 +1713,9 @@ static struct frontswap_ops zcache_frontswap_ops = { .init = zcache_frontswap_init }; -struct frontswap_ops zcache_frontswap_register_ops(void) +struct frontswap_ops *zcache_frontswap_register_ops(void) { - struct frontswap_ops old_ops = + struct frontswap_ops *old_ops = frontswap_register_ops(&zcache_frontswap_ops); return old_ops; @@ -1721,6 +1727,7 @@ struct frontswap_ops zcache_frontswap_register_ops(void) * OR NOTHING HAPPENS! */ +#ifndef CONFIG_ZCACHE_MODULE static int __init enable_zcache(char *s) { zcache_enabled = true; @@ -1787,18 +1794,27 @@ static int __init enable_zcache_compressor(char *s) return 1; } __setup("zcache=", enable_zcache_compressor); +#endif -static int __init zcache_comp_init(void) +static int zcache_comp_init(void) { int ret = 0; /* check crypto algorithm */ +#ifdef CONFIG_ZCACHE_MODULE + ret = crypto_has_comp(zcache_comp_name, 0, 0); + if (!ret) { + ret = -1; + goto out; + } +#else if (*zcache_comp_name != '\0') { ret = crypto_has_comp(zcache_comp_name, 0, 0); if (!ret) pr_info("zcache: %s not supported\n", zcache_comp_name); + goto out; } if (!ret) strcpy(zcache_comp_name, "lzo"); @@ -1807,6 +1823,7 @@ static int __init zcache_comp_init(void) ret = 1; goto out; } +#endif pr_info("zcache: using %s compressor\n", zcache_comp_name); /* alloc percpu transforms */ @@ -1818,10 +1835,13 @@ out: return ret; } -static int __init zcache_init(void) +static int zcache_init(void) { int ret = 0; +#ifdef CONFIG_ZCACHE_MODULE + zcache_enabled = 1; +#endif if (ramster_enabled) { namestr = "ramster"; ramster_register_pamops(&zcache_pamops); @@ -1860,7 +1880,7 @@ static int __init zcache_init(void) } zbud_init(); if (zcache_enabled && !disable_cleancache) { - struct cleancache_ops old_ops; + struct cleancache_ops *old_ops; register_shrinker(&zcache_shrinker); old_ops = zcache_cleancache_register_ops(); @@ -1870,11 +1890,11 @@ static int __init zcache_init(void) pr_info("%s: cleancache: ignorenonactive = %d\n", namestr, !disable_cleancache_ignore_nonactive); #endif - if (old_ops.init_fs != NULL) + if (old_ops != NULL) pr_warn("%s: cleancache_ops overridden\n", namestr); } if (zcache_enabled && !disable_frontswap) { - struct frontswap_ops old_ops; + struct frontswap_ops *old_ops; old_ops = zcache_frontswap_register_ops(); if (frontswap_has_exclusive_gets) @@ -1886,14 +1906,36 @@ static int __init zcache_init(void) namestr, frontswap_has_exclusive_gets, !disable_frontswap_ignore_nonactive); #endif - if (old_ops.init != NULL) + if (IS_ERR(old_ops) || old_ops) { + if (IS_ERR(old_ops)) + return PTR_RET(old_ops); pr_warn("%s: frontswap_ops overridden\n", namestr); + } } if (ramster_enabled) ramster_init(!disable_cleancache, !disable_frontswap, - frontswap_has_exclusive_gets); + frontswap_has_exclusive_gets, + !disable_frontswap_selfshrink); out: return ret; } +#ifdef CONFIG_ZCACHE_MODULE +#ifdef CONFIG_RAMSTER +module_param(ramster_enabled, int, S_IRUGO); +module_param(disable_frontswap_selfshrink, int, S_IRUGO); +#endif +module_param(disable_cleancache, int, S_IRUGO); +module_param(disable_frontswap, int, S_IRUGO); +#ifdef FRONTSWAP_HAS_EXCLUSIVE_GETS +module_param(frontswap_has_exclusive_gets, bool, S_IRUGO); +#endif +module_param(disable_frontswap_ignore_nonactive, int, S_IRUGO); +module_param(zcache_comp_name, charp, S_IRUGO); +module_init(zcache_init); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Dan Magenheimer <dan.magenheimer@oracle.com>"); +MODULE_DESCRIPTION("In-kernel compression of cleancache/frontswap pages"); +#else late_initcall(zcache_init); +#endif diff --git a/drivers/staging/zcache/zcache.h b/drivers/staging/zcache/zcache.h index 81722b3..8491200 100644 --- a/drivers/staging/zcache/zcache.h +++ b/drivers/staging/zcache/zcache.h @@ -39,7 +39,7 @@ extern int zcache_flush_page(int, int, struct tmem_oid *, uint32_t); extern int zcache_flush_object(int, int, struct tmem_oid *); extern void zcache_decompress_to_page(char *, unsigned int, struct page *); -#ifdef CONFIG_RAMSTER +#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE) extern void *zcache_pampd_create(char *, unsigned int, bool, int, struct tmem_handle *); int zcache_autocreate_pool(unsigned int cli_id, unsigned int pool_id, bool eph); diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c index 4797228..8623577 100644 --- a/drivers/usb/storage/realtek_cr.c +++ b/drivers/usb/storage/realtek_cr.c @@ -933,14 +933,11 @@ static int realtek_cr_autosuspend_setup(struct us_data *us) static void realtek_cr_destructor(void *extra) { - struct rts51x_chip *chip = (struct rts51x_chip *)extra; - struct us_data *us; + struct rts51x_chip *chip = extra; if (!chip) return; - us = chip->us; - #ifdef CONFIG_REALTEK_AUTOPM if (ss_en) { del_timer(&chip->rts51x_suspend_timer); diff --git a/drivers/w1/slaves/w1_bq27000.c b/drivers/w1/slaves/w1_bq27000.c index 773dca5..afbefed 100644 --- a/drivers/w1/slaves/w1_bq27000.c +++ b/drivers/w1/slaves/w1_bq27000.c @@ -57,6 +57,8 @@ static int w1_bq27000_add_slave(struct w1_slave *sl) ret = platform_device_add_data(pdev, &bq27000_battery_info, sizeof(bq27000_battery_info)); + if (ret) + goto pdev_add_failed; pdev->dev.parent = &sl->dev; ret = platform_device_add(pdev); @@ -68,7 +70,7 @@ static int w1_bq27000_add_slave(struct w1_slave *sl) goto success; pdev_add_failed: - platform_device_unregister(pdev); + platform_device_put(pdev); success: return ret; } diff --git a/drivers/w1/slaves/w1_ds2760.c b/drivers/w1/slaves/w1_ds2760.c index aa7bd5f..e86a69d 100644 --- a/drivers/w1/slaves/w1_ds2760.c +++ b/drivers/w1/slaves/w1_ds2760.c @@ -148,8 +148,9 @@ static int w1_ds2760_add_slave(struct w1_slave *sl) goto success; bin_attr_failed: + platform_device_del(pdev); pdev_add_failed: - platform_device_unregister(pdev); + platform_device_put(pdev); pdev_alloc_failed: ida_simple_remove(&bat_ida, id); noid: diff --git a/drivers/w1/slaves/w1_ds2780.c b/drivers/w1/slaves/w1_ds2780.c index 7b09307..98ed9c4 100644 --- a/drivers/w1/slaves/w1_ds2780.c +++ b/drivers/w1/slaves/w1_ds2780.c @@ -141,8 +141,9 @@ static int w1_ds2780_add_slave(struct w1_slave *sl) return 0; bin_attr_failed: + platform_device_del(pdev); pdev_add_failed: - platform_device_unregister(pdev); + platform_device_put(pdev); pdev_alloc_failed: ida_simple_remove(&bat_ida, id); noid: diff --git a/drivers/w1/slaves/w1_ds2781.c b/drivers/w1/slaves/w1_ds2781.c index 877daf7..5140d7b 100644 --- a/drivers/w1/slaves/w1_ds2781.c +++ b/drivers/w1/slaves/w1_ds2781.c @@ -139,8 +139,9 @@ static int w1_ds2781_add_slave(struct w1_slave *sl) return 0; bin_attr_failed: + platform_device_del(pdev); pdev_add_failed: - platform_device_unregister(pdev); + platform_device_put(pdev); pdev_alloc_failed: ida_simple_remove(&bat_ida, id); noid: diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 67af155..dd4d9cb 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -145,9 +145,9 @@ config SWIOTLB_XEN select SWIOTLB config XEN_TMEM - bool + tristate depends on !ARM - default y if (CLEANCACHE || FRONTSWAP) + default m if (CLEANCACHE || FRONTSWAP) help Shim to interface in-kernel Transcendent Memory hooks (e.g. cleancache and frontswap) to Xen tmem hypercalls. diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c index 3ee836d..e3600be 100644 --- a/drivers/xen/tmem.c +++ b/drivers/xen/tmem.c @@ -5,6 +5,7 @@ * Author: Dan Magenheimer */ +#include <linux/module.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> @@ -128,6 +129,7 @@ static int xen_tmem_flush_object(u32 pool_id, struct tmem_oid oid) return xen_tmem_op(TMEM_FLUSH_OBJECT, pool_id, oid, 0, 0, 0, 0, 0); } +#ifndef CONFIG_XEN_TMEM_MODULE bool __read_mostly tmem_enabled = false; static int __init enable_tmem(char *s) @@ -136,6 +138,7 @@ static int __init enable_tmem(char *s) return 1; } __setup("tmem", enable_tmem); +#endif #ifdef CONFIG_CLEANCACHE static int xen_tmem_destroy_pool(u32 pool_id) @@ -227,16 +230,21 @@ static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize) return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize); } -static bool __initdata use_cleancache = true; - +static bool disable_cleancache __read_mostly; +static bool disable_selfballooning __read_mostly; +#ifdef CONFIG_XEN_TMEM_MODULE +module_param(disable_cleancache, bool, S_IRUGO); +module_param(disable_selfballooning, bool, S_IRUGO); +#else static int __init no_cleancache(char *s) { - use_cleancache = false; + disable_cleancache = true; return 1; } __setup("nocleancache", no_cleancache); +#endif -static struct cleancache_ops __initdata tmem_cleancache_ops = { +static struct cleancache_ops tmem_cleancache_ops = { .put_page = tmem_cleancache_put_page, .get_page = tmem_cleancache_get_page, .invalidate_page = tmem_cleancache_flush_page, @@ -353,54 +361,71 @@ static void tmem_frontswap_init(unsigned ignored) xen_tmem_new_pool(private, TMEM_POOL_PERSIST, PAGE_SIZE); } -static bool __initdata use_frontswap = true; - +static bool disable_frontswap __read_mostly; +static bool disable_frontswap_selfshrinking __read_mostly; +#ifdef CONFIG_XEN_TMEM_MODULE +module_param(disable_frontswap, bool, S_IRUGO); +module_param(disable_frontswap_selfshrinking, bool, S_IRUGO); +#else static int __init no_frontswap(char *s) { - use_frontswap = false; + disable_frontswap = true; return 1; } __setup("nofrontswap", no_frontswap); +#endif -static struct frontswap_ops __initdata tmem_frontswap_ops = { +static struct frontswap_ops tmem_frontswap_ops = { .store = tmem_frontswap_store, .load = tmem_frontswap_load, .invalidate_page = tmem_frontswap_flush_page, .invalidate_area = tmem_frontswap_flush_area, .init = tmem_frontswap_init }; +#else /* CONFIG_FRONTSWAP */ +#define disable_frontswap_selfshrinking 1 #endif -static int __init xen_tmem_init(void) +static int xen_tmem_init(void) { if (!xen_domain()) return 0; #ifdef CONFIG_FRONTSWAP - if (tmem_enabled && use_frontswap) { + if (tmem_enabled && !disable_frontswap) { char *s = ""; - struct frontswap_ops old_ops = + struct frontswap_ops *old_ops = frontswap_register_ops(&tmem_frontswap_ops); tmem_frontswap_poolid = -1; - if (old_ops.init != NULL) + if (IS_ERR(old_ops) || old_ops) { + if (IS_ERR(old_ops)) + return PTR_ERR(old_ops); s = " (WARNING: frontswap_ops overridden)"; + } printk(KERN_INFO "frontswap enabled, RAM provided by " "Xen Transcendent Memory%s\n", s); } #endif #ifdef CONFIG_CLEANCACHE BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid)); - if (tmem_enabled && use_cleancache) { + if (tmem_enabled && !disable_cleancache) { char *s = ""; - struct cleancache_ops old_ops = + struct cleancache_ops *old_ops = cleancache_register_ops(&tmem_cleancache_ops); - if (old_ops.init_fs != NULL) + if (old_ops) s = " (WARNING: cleancache_ops overridden)"; printk(KERN_INFO "cleancache enabled, RAM provided by " "Xen Transcendent Memory%s\n", s); } #endif +#ifdef CONFIG_XEN_SELFBALLOONING + xen_selfballoon_init(!disable_selfballooning, + !disable_frontswap_selfshrinking); +#endif return 0; } module_init(xen_tmem_init) +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Dan Magenheimer <dan.magenheimer@oracle.com>"); +MODULE_DESCRIPTION("Shim to Xen transcendent memory"); diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c index 2552d3e..f2ef569 100644 --- a/drivers/xen/xen-selfballoon.c +++ b/drivers/xen/xen-selfballoon.c @@ -121,7 +121,7 @@ static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process); static bool frontswap_selfshrinking __read_mostly; /* Enable/disable with kernel boot option. */ -static bool use_frontswap_selfshrink __initdata = true; +static bool use_frontswap_selfshrink = true; /* * The default values for the following parameters were deemed reasonable @@ -185,7 +185,7 @@ static int __init xen_nofrontswap_selfshrink_setup(char *s) __setup("noselfshrink", xen_nofrontswap_selfshrink_setup); /* Disable with kernel boot option. */ -static bool use_selfballooning __initdata = true; +static bool use_selfballooning = true; static int __init xen_noselfballooning_setup(char *s) { @@ -196,7 +196,7 @@ static int __init xen_noselfballooning_setup(char *s) __setup("noselfballooning", xen_noselfballooning_setup); #else /* !CONFIG_FRONTSWAP */ /* Enable with kernel boot option. */ -static bool use_selfballooning __initdata = false; +static bool use_selfballooning; static int __init xen_selfballooning_setup(char *s) { @@ -537,7 +537,7 @@ int register_xen_selfballooning(struct device *dev) } EXPORT_SYMBOL(register_xen_selfballooning); -static int __init xen_selfballoon_init(void) +int xen_selfballoon_init(bool use_selfballooning, bool use_frontswap_selfshrink) { bool enable = false; @@ -571,7 +571,4 @@ static int __init xen_selfballoon_init(void) return 0; } - -subsys_initcall(xen_selfballoon_init); - -MODULE_LICENSE("GPL"); +EXPORT_SYMBOL(xen_selfballoon_init); diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 0efd152..370b24c 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -65,6 +65,20 @@ config CORE_DUMP_DEFAULT_ELF_HEADERS This config option changes the default setting of coredump_filter seen at boot time. If unsure, say Y. +config BINFMT_SCRIPT + tristate "Kernel support for scripts starting with #!" + default y + help + Say Y here if you want to execute interpreted scripts starting with + #! followed by the path to an interpreter. + + You can build this support as a module; however, until that module + gets loaded, you cannot run scripts. Thus, if you want to load this + module from an initramfs, the portion of the initramfs before loading + this module must consist of compiled binaries only. + + Most systems will not boot if you say M or N here. If unsure, say Y. + config BINFMT_FLAT bool "Kernel support for flat binaries" depends on !MMU && (!FRV || BROKEN) diff --git a/fs/Makefile b/fs/Makefile index 3b2c767..5e67e57 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -34,10 +34,7 @@ obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o - -# binfmt_script is always there -obj-y += binfmt_script.o - +obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o obj-$(CONFIG_COMPAT_BINFMT_ELF) += compat_binfmt_elf.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += binfmt_elf_fdpic.o diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index bbc8f88..02fe378 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -62,7 +62,6 @@ static int aout_core_dump(struct coredump_params *cprm) fs = get_fs(); set_fs(KERNEL_DS); has_dumped = 1; - current->flags |= PF_DUMPCORE; strncpy(dump.u_comm, current->comm, sizeof(dump.u_comm)); dump.u_ar0 = offsetof(struct user, regs); dump.signal = cprm->siginfo->si_signo; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 86af964..34a9771 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -803,7 +803,8 @@ static int load_elf_binary(struct linux_binprm *bprm) * follow the loader, and is not movable. */ #ifdef CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE /* Memory randomization might have been switched off - * in runtime via sysctl. + * in runtime via sysctl or explicit setting of + * personality flags. * If that is the case, retain the original non-zero * load_bias value in order to establish proper * non-randomized mappings. @@ -2091,8 +2092,7 @@ static int elf_core_dump(struct coredump_params *cprm) goto cleanup; has_dumped = 1; - current->flags |= PF_DUMPCORE; - + fs = get_fs(); set_fs(KERNEL_DS); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 9c13e02..c1cc06a 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1687,8 +1687,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) fill_elf_fdpic_header(elf, e_phnum); has_dumped = 1; - current->flags |= PF_DUMPCORE; - /* * Set up the notes in similar form to SVR4 core dumps made * with info from their /proc. diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 751df5e..1c740e1 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -23,6 +23,7 @@ #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/ctype.h> +#include <linux/string_helpers.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/namei.h> @@ -234,24 +235,6 @@ static char *scanarg(char *s, char del) return s; } -static int unquote(char *from) -{ - char c = 0, *s = from, *p = from; - - while ((c = *s++) != '\0') { - if (c == '\\' && *s == 'x') { - s++; - c = toupper(*s++); - *p = (c - (isdigit(c) ? '0' : 'A' - 10)) << 4; - c = toupper(*s++); - *p++ |= c - (isdigit(c) ? '0' : 'A' - 10); - continue; - } - *p++ = c; - } - return p - from; -} - static char * check_special_flags (char * sfs, Node * e) { char * p = sfs; @@ -354,8 +337,9 @@ static Node *create_entry(const char __user *buffer, size_t count) p[-1] = '\0'; if (!e->mask[0]) e->mask = NULL; - e->size = unquote(e->magic); - if (e->mask && unquote(e->mask) != e->size) + e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX); + if (e->mask && + string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size) goto Einval; if (e->size + e->offset > BINPRM_BUF_SIZE) goto Einval; diff --git a/fs/block_dev.c b/fs/block_dev.c index aae187a..ce08de7 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -617,11 +617,9 @@ void bd_forget(struct inode *inode) struct block_device *bdev = NULL; spin_lock(&bdev_lock); - if (inode->i_bdev) { - if (!sb_is_blkdev_sb(inode->i_sb)) - bdev = inode->i_bdev; - __bd_forget(inode); - } + if (!sb_is_blkdev_sb(inode->i_sb)) + bdev = inode->i_bdev; + __bd_forget(inode); spin_unlock(&bdev_lock); if (bdev) diff --git a/fs/coredump.c b/fs/coredump.c index c647965..ec306cc 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -263,7 +263,6 @@ static int zap_process(struct task_struct *start, int exit_code) struct task_struct *t; int nr = 0; - start->signal->flags = SIGNAL_GROUP_EXIT; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; @@ -280,8 +279,8 @@ static int zap_process(struct task_struct *start, int exit_code) return nr; } -static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, - struct core_state *core_state, int exit_code) +static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, + struct core_state *core_state, int exit_code) { struct task_struct *g, *p; unsigned long flags; @@ -291,11 +290,16 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (!signal_group_exit(tsk->signal)) { mm->core_state = core_state; nr = zap_process(tsk, exit_code); + tsk->signal->group_exit_task = tsk; + /* ignore all signals except SIGKILL, see prepare_signal() */ + tsk->signal->flags = SIGNAL_GROUP_COREDUMP; + clear_tsk_thread_flag(tsk, TIF_SIGPENDING); } spin_unlock_irq(&tsk->sighand->siglock); if (unlikely(nr < 0)) return nr; + tsk->flags = PF_DUMPCORE; if (atomic_read(&mm->mm_users) == nr + 1) goto done; /* @@ -340,6 +344,7 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (unlikely(p->mm == mm)) { lock_task_sighand(p, &flags); nr += zap_process(p, exit_code); + p->signal->flags = SIGNAL_GROUP_EXIT; unlock_task_sighand(p, &flags); } break; @@ -386,11 +391,18 @@ static int coredump_wait(int exit_code, struct core_state *core_state) return core_waiters; } -static void coredump_finish(struct mm_struct *mm) +static void coredump_finish(struct mm_struct *mm, bool core_dumped) { struct core_thread *curr, *next; struct task_struct *task; + spin_lock_irq(¤t->sighand->siglock); + if (core_dumped && !__fatal_signal_pending(current)) + current->signal->group_exit_code |= 0x80; + current->signal->group_exit_task = NULL; + current->signal->flags = SIGNAL_GROUP_EXIT; + spin_unlock_irq(¤t->sighand->siglock); + next = mm->core_state->dumper.next; while ((curr = next) != NULL) { next = curr->next; @@ -407,6 +419,17 @@ static void coredump_finish(struct mm_struct *mm) mm->core_state = NULL; } +static bool dump_interrupted(void) +{ + /* + * SIGKILL or freezing() interrupt the coredumping. Perhaps we + * can do try_to_freeze() and check __fatal_signal_pending(), + * but then we need to teach dump_write() to restart and clear + * TIF_SIGPENDING. + */ + return signal_pending(current); +} + static void wait_for_dump_helpers(struct file *file) { struct pipe_inode_info *pipe; @@ -416,17 +439,20 @@ static void wait_for_dump_helpers(struct file *file) pipe_lock(pipe); pipe->readers++; pipe->writers--; + wake_up_interruptible_sync(&pipe->wait); + kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); + pipe_unlock(pipe); - while ((pipe->readers > 1) && (!signal_pending(current))) { - wake_up_interruptible_sync(&pipe->wait); - kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); - pipe_wait(pipe); - } + /* + * We actually want wait_event_freezable() but then we need + * to clear TIF_SIGPENDING and improve dump_interrupted(). + */ + wait_event_interruptible(pipe->wait, pipe->readers == 1); + pipe_lock(pipe); pipe->readers--; pipe->writers++; pipe_unlock(pipe); - } /* @@ -471,6 +497,7 @@ void do_coredump(siginfo_t *siginfo) int ispipe; struct files_struct *displaced; bool need_nonrelative = false; + bool core_dumped = false; static atomic_t core_dump_count = ATOMIC_INIT(0); struct coredump_params cprm = { .siginfo = siginfo, @@ -514,17 +541,12 @@ void do_coredump(siginfo_t *siginfo) old_cred = override_creds(cred); - /* - * Clear any false indication of pending signals that might - * be seen by the filesystem code called to write the core file. - */ - clear_thread_flag(TIF_SIGPENDING); - ispipe = format_corename(&cn, &cprm); - if (ispipe) { + if (ispipe) { int dump_count; char **helper_argv; + struct subprocess_info *sub_info; if (ispipe < 0) { printk(KERN_WARNING "format_corename failed\n"); @@ -571,15 +593,20 @@ void do_coredump(siginfo_t *siginfo) goto fail_dropcount; } - retval = call_usermodehelper_fns(helper_argv[0], helper_argv, - NULL, UMH_WAIT_EXEC, umh_pipe_setup, - NULL, &cprm); + retval = -ENOMEM; + sub_info = call_usermodehelper_setup(helper_argv[0], + helper_argv, NULL, GFP_KERNEL, + umh_pipe_setup, NULL, &cprm); + if (sub_info) + retval = call_usermodehelper_exec(sub_info, + UMH_WAIT_EXEC); + argv_free(helper_argv); if (retval) { - printk(KERN_INFO "Core dump to %s pipe failed\n", + printk(KERN_INFO "Core dump to %s pipe failed\n", cn.corename); goto close_fail; - } + } } else { struct inode *inode; @@ -629,9 +656,7 @@ void do_coredump(siginfo_t *siginfo) goto close_fail; if (displaced) put_files_struct(displaced); - retval = binfmt->core_dump(&cprm); - if (retval) - current->signal->group_exit_code |= 0x80; + core_dumped = !dump_interrupted() && binfmt->core_dump(&cprm); if (ispipe && core_pipe_limit) wait_for_dump_helpers(cprm.file); @@ -644,7 +669,7 @@ fail_dropcount: fail_unlock: kfree(cn.corename); fail_corename: - coredump_finish(mm); + coredump_finish(mm, core_dumped); revert_creds(old_cred); fail_creds: put_cred(cred); @@ -659,7 +684,9 @@ fail: */ int dump_write(struct file *file, const void *addr, int nr) { - return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr; + return !dump_interrupted() && + access_ok(VERIFY_READ, addr, nr) && + file->f_op->write(file, addr, nr, &file->f_pos) == nr; } EXPORT_SYMBOL(dump_write); @@ -668,7 +695,8 @@ int dump_seek(struct file *file, loff_t off) int ret = 1; if (file->f_op->llseek && file->f_op->llseek != no_llseek) { - if (file->f_op->llseek(file, off, SEEK_CUR) < 0) + if (dump_interrupted() || + file->f_op->llseek(file, off, SEEK_CUR) < 0) return 0; } else { char *buf = (char *)get_zeroed_page(GFP_KERNEL); diff --git a/fs/dcache.c b/fs/dcache.c index e8bc342..e689268 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1230,8 +1230,10 @@ void shrink_dcache_parent(struct dentry * parent) LIST_HEAD(dispose); int found; - while ((found = select_parent(parent, &dispose)) != 0) + while ((found = select_parent(parent, &dispose)) != 0) { shrink_dentry_list(&dispose); + cond_resched(); + } } EXPORT_SYMBOL(shrink_dcache_parent); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9fec183..277cc38 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -104,7 +104,7 @@ struct epoll_filefd { struct file *file; int fd; -}; +} __packed; /* * Structure used to track possible nested calls, for too deep recursions @@ -128,6 +128,8 @@ struct nested_calls { /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. + * Avoid increasing the size of this struct, there can be many thousands + * of these on a server and we do not want this to take another cache line. */ struct epitem { /* RB tree node used to link this structure to the eventpoll RB tree */ @@ -158,7 +160,7 @@ struct epitem { struct list_head fllink; /* wakeup_source used when EPOLLWAKEUP is set */ - struct wakeup_source *ws; + struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; @@ -536,6 +538,38 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) } } +/* call only when ep->mtx is held */ +static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) +{ + return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); +} + +/* call only when ep->mtx is held */ +static inline void ep_pm_stay_awake(struct epitem *epi) +{ + struct wakeup_source *ws = ep_wakeup_source(epi); + + if (ws) + __pm_stay_awake(ws); +} + +static inline bool ep_has_wakeup_source(struct epitem *epi) +{ + return rcu_access_pointer(epi->ws) ? true : false; +} + +/* call when ep->mtx cannot be held (ep_poll_callback) */ +static inline void ep_pm_stay_awake_rcu(struct epitem *epi) +{ + struct wakeup_source *ws; + + rcu_read_lock(); + ws = rcu_dereference(epi->ws); + if (ws) + __pm_stay_awake(ws); + rcu_read_unlock(); +} + /** * ep_scan_ready_list - Scans the ready list in a way that makes possible for * the scan code, to call f_op->poll(). Also allows for @@ -599,7 +633,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, */ if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); } } /* @@ -668,7 +702,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) list_del_init(&epi->rdllink); spin_unlock_irqrestore(&ep->lock, flags); - wakeup_source_unregister(epi->ws); + wakeup_source_unregister(ep_wakeup_source(epi)); /* At this point it is safe to free the eventpoll item */ kmem_cache_free(epi_cache, epi); @@ -711,11 +745,15 @@ static void ep_free(struct eventpoll *ep) * point we are sure no poll callbacks will be lingering around, and also by * holding "epmutex" we can be sure that no file cleanup code will hit * us during this operation. So we can avoid the lock on "ep->lock". + * We do not need to lock ep->mtx, either, we only do it to prevent + * a lockdep warning. */ + mutex_lock(&ep->mtx); while ((rbp = rb_first(&ep->rbr)) != NULL) { epi = rb_entry(rbp, struct epitem, rbn); ep_remove(ep, epi); } + mutex_unlock(&ep->mtx); mutex_unlock(&epmutex); mutex_destroy(&ep->mtx); @@ -734,6 +772,13 @@ static int ep_eventpoll_release(struct inode *inode, struct file *file) return 0; } +static inline unsigned int ep_item_poll(struct epitem *epi, poll_table *pt) +{ + pt->_key = epi->event.events; + + return epi->ffd.file->f_op->poll(epi->ffd.file, pt) & epi->event.events; +} + static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, void *priv) { @@ -741,10 +786,9 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, poll_table pt; init_poll_funcptr(&pt, NULL); + list_for_each_entry_safe(epi, tmp, head, rdllink) { - pt._key = epi->event.events; - if (epi->ffd.file->f_op->poll(epi->ffd.file, &pt) & - epi->event.events) + if (ep_item_poll(epi, &pt)) return POLLIN | POLLRDNORM; else { /* @@ -752,7 +796,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ - __pm_relax(epi->ws); + __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } @@ -984,7 +1028,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k /* If this file is already in the ready list we exit soon */ if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake_rcu(epi); } /* @@ -1146,6 +1190,7 @@ static int reverse_path_check(void) static int ep_create_wakeup_source(struct epitem *epi) { const char *name; + struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register("eventpoll"); @@ -1154,17 +1199,29 @@ static int ep_create_wakeup_source(struct epitem *epi) } name = epi->ffd.file->f_path.dentry->d_name.name; - epi->ws = wakeup_source_register(name); - if (!epi->ws) + ws = wakeup_source_register(name); + + if (!ws) return -ENOMEM; + rcu_assign_pointer(epi->ws, ws); return 0; } -static void ep_destroy_wakeup_source(struct epitem *epi) +/* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ +static noinline void ep_destroy_wakeup_source(struct epitem *epi) { - wakeup_source_unregister(epi->ws); - epi->ws = NULL; + struct wakeup_source *ws = ep_wakeup_source(epi); + + RCU_INIT_POINTER(epi->ws, NULL); + + /* + * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is + * used internally by wakeup_source_remove, too (called by + * wakeup_source_unregister), so we cannot use call_rcu + */ + synchronize_rcu(); + wakeup_source_unregister(ws); } /* @@ -1199,13 +1256,12 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, if (error) goto error_create_wakeup_source; } else { - epi->ws = NULL; + RCU_INIT_POINTER(epi->ws, NULL); } /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); - epq.pt._key = event->events; /* * Attach the item to the poll hooks and get current event bits. @@ -1214,7 +1270,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, * this operation completes, the poll callback can start hitting * the new item. */ - revents = tfile->f_op->poll(tfile, &epq.pt); + revents = ep_item_poll(epi, &epq.pt); /* * We have to check if something went wrong during the poll wait queue @@ -1247,7 +1303,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, /* If the file is already "ready" we drop it inside the ready list */ if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) @@ -1288,7 +1344,7 @@ error_unregister: list_del_init(&epi->rdllink); spin_unlock_irqrestore(&ep->lock, flags); - wakeup_source_unregister(epi->ws); + wakeup_source_unregister(ep_wakeup_source(epi)); error_create_wakeup_source: kmem_cache_free(epi_cache, epi); @@ -1314,12 +1370,11 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ - pt._key = event->events; epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { - if (!epi->ws) + if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); - } else if (epi->ws) { + } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } @@ -1347,7 +1402,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. */ - revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt); + revents = ep_item_poll(epi, &pt); /* * If the item is "hot" and it is not registered inside the ready @@ -1357,7 +1412,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even spin_lock_irq(&ep->lock); if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) @@ -1383,6 +1438,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, unsigned int revents; struct epitem *epi; struct epoll_event __user *uevent; + struct wakeup_source *ws; poll_table pt; init_poll_funcptr(&pt, NULL); @@ -1405,14 +1461,16 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, * instead, but then epi->ws would temporarily be out of sync * with ep_is_linked(). */ - if (epi->ws && epi->ws->active) - __pm_stay_awake(ep->ws); - __pm_relax(epi->ws); + ws = ep_wakeup_source(epi); + if (ws) { + if (ws->active) + __pm_stay_awake(ep->ws); + __pm_relax(ws); + } + list_del_init(&epi->rdllink); - pt._key = epi->event.events; - revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt) & - epi->event.events; + revents = ep_item_poll(epi, &pt); /* * If the event mask intersect the caller-requested one, @@ -1424,7 +1482,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, if (__put_user(revents, &uevent->events) || __put_user(epi->event.data, &uevent->data)) { list_add(&epi->rdllink, head); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); return eventcnt ? eventcnt : -EFAULT; } eventcnt++; @@ -1444,7 +1502,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); - __pm_stay_awake(epi->ws); + ep_pm_stay_awake(epi); } } } @@ -1964,6 +2022,12 @@ static int __init eventpoll_init(void) /* Initialize the structure used to perform file's f_op->poll() calls */ ep_nested_calls_init(&poll_readywalk_ncalls); + /* + * We can have many thousands of epitems, so prevent this from + * using an extra cache line on 64-bit (and smaller) CPUs + */ + BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); + /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); @@ -898,11 +898,13 @@ static int de_thread(struct task_struct *tsk) sig->notify_count = -1; /* for exit_notify() */ for (;;) { + threadgroup_change_begin(tsk); write_lock_irq(&tasklist_lock); if (likely(leader->exit_state)) break; __set_current_state(TASK_KILLABLE); write_unlock_irq(&tasklist_lock); + threadgroup_change_end(tsk); schedule(); if (unlikely(__fatal_signal_pending(tsk))) goto killed; @@ -960,6 +962,7 @@ static int de_thread(struct task_struct *tsk) if (unlikely(leader->ptrace)) __wake_up_parent(leader, leader->parent); write_unlock_irq(&tasklist_lock); + threadgroup_change_end(tsk); release_task(leader); } @@ -1027,17 +1030,7 @@ EXPORT_SYMBOL_GPL(get_task_comm); void set_task_comm(struct task_struct *tsk, char *buf) { task_lock(tsk); - trace_task_rename(tsk, buf); - - /* - * Threads may access current->comm without holding - * the task lock, so write the string carefully. - * Readers without a lock may see incomplete new - * names but are safe from non-terminating string reads. - */ - memset(tsk->comm, 0, TASK_COMM_LEN); - wmb(); strlcpy(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); perf_event_comm(tsk); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 21f46fb..798d445 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1028,6 +1028,7 @@ int bdi_writeback_thread(void *data) struct backing_dev_info *bdi = wb->bdi; long pages_written; + set_worker_desc("flush-%s", dev_name(bdi->dev)); current->flags |= PF_SWAPWRITE; set_freezable(); wb->last_active = jiffies; diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index 571abe9..de69d8a 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -22,7 +22,8 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) return -ENOMEM; fd->search_key = ptr; fd->key = ptr + tree->max_key_len + 2; - dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); + hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", + tree->cnid, __builtin_return_address(0)); mutex_lock(&tree->tree_lock); return 0; } @@ -31,7 +32,8 @@ void hfs_find_exit(struct hfs_find_data *fd) { hfs_bnode_put(fd->bnode); kfree(fd->search_key); - dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0)); + hfs_dbg(BNODE_REFS, "find_exit: %d (%p)\n", + fd->tree->cnid, __builtin_return_address(0)); mutex_unlock(&fd->tree->tree_lock); fd->tree = NULL; } @@ -135,8 +137,8 @@ int hfs_brec_find(struct hfs_find_data *fd) return res; invalid: - printk(KERN_ERR "hfs: inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", - height, bnode->height, bnode->type, nidx, parent); + pr_err("inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", + height, bnode->height, bnode->type, nidx, parent); res = -EIO; release: hfs_bnode_put(bnode); diff --git a/fs/hfs/bitmap.c b/fs/hfs/bitmap.c index c6e9736..28307bc 100644 --- a/fs/hfs/bitmap.c +++ b/fs/hfs/bitmap.c @@ -158,7 +158,7 @@ u32 hfs_vbm_search_free(struct super_block *sb, u32 goal, u32 *num_bits) } } - dprint(DBG_BITMAP, "alloc_bits: %u,%u\n", pos, *num_bits); + hfs_dbg(BITMAP, "alloc_bits: %u,%u\n", pos, *num_bits); HFS_SB(sb)->free_ablocks -= *num_bits; hfs_bitmap_dirty(sb); out: @@ -200,7 +200,7 @@ int hfs_clear_vbm_bits(struct super_block *sb, u16 start, u16 count) if (!count) return 0; - dprint(DBG_BITMAP, "clear_bits: %u,%u\n", start, count); + hfs_dbg(BITMAP, "clear_bits: %u,%u\n", start, count); /* are all of the bits in range? */ if ((start + count) > HFS_SB(sb)->fs_ablocks) return -2; diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index cdb41a1..f3b1a15 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -100,7 +100,7 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst, struct hfs_btree *tree; struct page *src_page, *dst_page; - dprint(DBG_BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); + hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); if (!len) return; tree = src_node->tree; @@ -120,7 +120,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) struct page *page; void *ptr; - dprint(DBG_BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); + hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); if (!len) return; src += node->page_offset; @@ -138,16 +138,16 @@ void hfs_bnode_dump(struct hfs_bnode *node) __be32 cnid; int i, off, key_off; - dprint(DBG_BNODE_MOD, "bnode: %d\n", node->this); + hfs_dbg(BNODE_MOD, "bnode: %d\n", node->this); hfs_bnode_read(node, &desc, 0, sizeof(desc)); - dprint(DBG_BNODE_MOD, "%d, %d, %d, %d, %d\n", + hfs_dbg(BNODE_MOD, "%d, %d, %d, %d, %d\n", be32_to_cpu(desc.next), be32_to_cpu(desc.prev), desc.type, desc.height, be16_to_cpu(desc.num_recs)); off = node->tree->node_size - 2; for (i = be16_to_cpu(desc.num_recs); i >= 0; off -= 2, i--) { key_off = hfs_bnode_read_u16(node, off); - dprint(DBG_BNODE_MOD, " %d", key_off); + hfs_dbg_cont(BNODE_MOD, " %d", key_off); if (i && node->type == HFS_NODE_INDEX) { int tmp; @@ -155,17 +155,18 @@ void hfs_bnode_dump(struct hfs_bnode *node) tmp = (hfs_bnode_read_u8(node, key_off) | 1) + 1; else tmp = node->tree->max_key_len + 1; - dprint(DBG_BNODE_MOD, " (%d,%d", tmp, hfs_bnode_read_u8(node, key_off)); + hfs_dbg_cont(BNODE_MOD, " (%d,%d", + tmp, hfs_bnode_read_u8(node, key_off)); hfs_bnode_read(node, &cnid, key_off + tmp, 4); - dprint(DBG_BNODE_MOD, ",%d)", be32_to_cpu(cnid)); + hfs_dbg_cont(BNODE_MOD, ",%d)", be32_to_cpu(cnid)); } else if (i && node->type == HFS_NODE_LEAF) { int tmp; tmp = hfs_bnode_read_u8(node, key_off); - dprint(DBG_BNODE_MOD, " (%d)", tmp); + hfs_dbg_cont(BNODE_MOD, " (%d)", tmp); } } - dprint(DBG_BNODE_MOD, "\n"); + hfs_dbg_cont(BNODE_MOD, "\n"); } void hfs_bnode_unlink(struct hfs_bnode *node) @@ -220,7 +221,7 @@ struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid) struct hfs_bnode *node; if (cnid >= tree->node_count) { - printk(KERN_ERR "hfs: request for non-existent node %d in B*Tree\n", cnid); + pr_err("request for non-existent node %d in B*Tree\n", cnid); return NULL; } @@ -243,7 +244,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) loff_t off; if (cnid >= tree->node_count) { - printk(KERN_ERR "hfs: request for non-existent node %d in B*Tree\n", cnid); + pr_err("request for non-existent node %d in B*Tree\n", cnid); return NULL; } @@ -257,8 +258,8 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) node->this = cnid; set_bit(HFS_BNODE_NEW, &node->flags); atomic_set(&node->refcnt, 1); - dprint(DBG_BNODE_REFS, "new_node(%d:%d): 1\n", - node->tree->cnid, node->this); + hfs_dbg(BNODE_REFS, "new_node(%d:%d): 1\n", + node->tree->cnid, node->this); init_waitqueue_head(&node->lock_wq); spin_lock(&tree->hash_lock); node2 = hfs_bnode_findhash(tree, cnid); @@ -301,7 +302,7 @@ void hfs_bnode_unhash(struct hfs_bnode *node) { struct hfs_bnode **p; - dprint(DBG_BNODE_REFS, "remove_node(%d:%d): %d\n", + hfs_dbg(BNODE_REFS, "remove_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); for (p = &node->tree->node_hash[hfs_bnode_hash(node->this)]; *p && *p != node; p = &(*p)->next_hash) @@ -443,8 +444,9 @@ void hfs_bnode_get(struct hfs_bnode *node) { if (node) { atomic_inc(&node->refcnt); - dprint(DBG_BNODE_REFS, "get_node(%d:%d): %d\n", - node->tree->cnid, node->this, atomic_read(&node->refcnt)); + hfs_dbg(BNODE_REFS, "get_node(%d:%d): %d\n", + node->tree->cnid, node->this, + atomic_read(&node->refcnt)); } } @@ -455,8 +457,9 @@ void hfs_bnode_put(struct hfs_bnode *node) struct hfs_btree *tree = node->tree; int i; - dprint(DBG_BNODE_REFS, "put_node(%d:%d): %d\n", - node->tree->cnid, node->this, atomic_read(&node->refcnt)); + hfs_dbg(BNODE_REFS, "put_node(%d:%d): %d\n", + node->tree->cnid, node->this, + atomic_read(&node->refcnt)); BUG_ON(!atomic_read(&node->refcnt)); if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock)) return; diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 92fb358..9f4ee7f 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -47,15 +47,13 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) if (node->tree->attributes & HFS_TREE_BIGKEYS) { retval = hfs_bnode_read_u16(node, recoff) + 2; if (retval > node->tree->max_key_len + 2) { - printk(KERN_ERR "hfs: keylen %d too large\n", - retval); + pr_err("keylen %d too large\n", retval); retval = 0; } } else { retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1; if (retval > node->tree->max_key_len + 1) { - printk(KERN_ERR "hfs: keylen %d too large\n", - retval); + pr_err("keylen %d too large\n", retval); retval = 0; } } @@ -94,7 +92,8 @@ again: end_rec_off = tree->node_size - (node->num_recs + 1) * 2; end_off = hfs_bnode_read_u16(node, end_rec_off); end_rec_off -= 2; - dprint(DBG_BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", rec, size, end_off, end_rec_off); + hfs_dbg(BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", + rec, size, end_off, end_rec_off); if (size > end_rec_off - end_off) { if (new_node) panic("not enough room!\n"); @@ -190,7 +189,8 @@ again: mark_inode_dirty(tree->inode); } hfs_bnode_dump(node); - dprint(DBG_BNODE_MOD, "remove_rec: %d, %d\n", fd->record, fd->keylength + fd->entrylength); + hfs_dbg(BNODE_MOD, "remove_rec: %d, %d\n", + fd->record, fd->keylength + fd->entrylength); if (!--node->num_recs) { hfs_bnode_unlink(node); if (!node->parent) @@ -240,7 +240,7 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd) if (IS_ERR(new_node)) return new_node; hfs_bnode_get(node); - dprint(DBG_BNODE_MOD, "split_nodes: %d - %d - %d\n", + hfs_dbg(BNODE_MOD, "split_nodes: %d - %d - %d\n", node->this, new_node->this, node->next); new_node->next = node->next; new_node->prev = node->this; @@ -374,7 +374,8 @@ again: newkeylen = (hfs_bnode_read_u8(node, 14) | 1) + 1; else fd->keylength = newkeylen = tree->max_key_len + 1; - dprint(DBG_BNODE_MOD, "update_rec: %d, %d, %d\n", rec, fd->keylength, newkeylen); + hfs_dbg(BNODE_MOD, "update_rec: %d, %d, %d\n", + rec, fd->keylength, newkeylen); rec_off = tree->node_size - (rec + 2) * 2; end_rec_off = tree->node_size - (parent->num_recs + 1) * 2; @@ -385,7 +386,7 @@ again: end_off = hfs_bnode_read_u16(parent, end_rec_off); if (end_rec_off - end_off < diff) { - printk(KERN_DEBUG "hfs: splitting index node...\n"); + printk(KERN_DEBUG "splitting index node...\n"); fd->bnode = parent; new_node = hfs_bnode_split(fd); if (IS_ERR(new_node)) diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 1cbdeea..1ab19e6 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -48,7 +48,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke mdb->drXTFlSize, be32_to_cpu(mdb->drXTClpSiz)); if (HFS_I(tree->inode)->alloc_blocks > HFS_I(tree->inode)->first_blocks) { - printk(KERN_ERR "hfs: invalid btree extent records\n"); + pr_err("invalid btree extent records\n"); unlock_new_inode(tree->inode); goto free_inode; } @@ -60,8 +60,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke mdb->drCTFlSize, be32_to_cpu(mdb->drCTClpSiz)); if (!HFS_I(tree->inode)->first_blocks) { - printk(KERN_ERR "hfs: invalid btree extent records " - "(0 size).\n"); + pr_err("invalid btree extent records (0 size)\n"); unlock_new_inode(tree->inode); goto free_inode; } @@ -100,15 +99,15 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke switch (id) { case HFS_EXT_CNID: if (tree->max_key_len != HFS_MAX_EXT_KEYLEN) { - printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", - tree->max_key_len); + pr_err("invalid extent max_key_len %d\n", + tree->max_key_len); goto fail_page; } break; case HFS_CAT_CNID: if (tree->max_key_len != HFS_MAX_CAT_KEYLEN) { - printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", - tree->max_key_len); + pr_err("invalid catalog max_key_len %d\n", + tree->max_key_len); goto fail_page; } break; @@ -146,8 +145,9 @@ void hfs_btree_close(struct hfs_btree *tree) while ((node = tree->node_hash[i])) { tree->node_hash[i] = node->next_hash; if (atomic_read(&node->refcnt)) - printk(KERN_ERR "hfs: node %d:%d still has %d user(s)!\n", - node->tree->cnid, node->this, atomic_read(&node->refcnt)); + pr_err("node %d:%d still has %d user(s)!\n", + node->tree->cnid, node->this, + atomic_read(&node->refcnt)); hfs_bnode_free(node); tree->node_hash_cnt--; } @@ -290,7 +290,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) kunmap(*pagep); nidx = node->next; if (!nidx) { - printk(KERN_DEBUG "hfs: create new bmap node...\n"); + printk(KERN_DEBUG "create new bmap node...\n"); next_node = hfs_bmap_new_bmap(node, idx); } else next_node = hfs_bnode_find(tree, nidx); @@ -316,7 +316,7 @@ void hfs_bmap_free(struct hfs_bnode *node) u32 nidx; u8 *data, byte, m; - dprint(DBG_BNODE_MOD, "btree_free_node: %u\n", node->this); + hfs_dbg(BNODE_MOD, "btree_free_node: %u\n", node->this); tree = node->tree; nidx = node->this; node = hfs_bnode_find(tree, 0); @@ -331,7 +331,8 @@ void hfs_bmap_free(struct hfs_bnode *node) hfs_bnode_put(node); if (!i) { /* panic */; - printk(KERN_CRIT "hfs: unable to free bnode %u. bmap not found!\n", node->this); + pr_crit("unable to free bnode %u. bmap not found!\n", + node->this); return; } node = hfs_bnode_find(tree, i); @@ -339,7 +340,8 @@ void hfs_bmap_free(struct hfs_bnode *node) return; if (node->type != HFS_NODE_MAP) { /* panic */; - printk(KERN_CRIT "hfs: invalid bmap found! (%u,%d)\n", node->this, node->type); + pr_crit("invalid bmap found! (%u,%d)\n", + node->this, node->type); hfs_bnode_put(node); return; } @@ -352,7 +354,8 @@ void hfs_bmap_free(struct hfs_bnode *node) m = 1 << (~nidx & 7); byte = data[off]; if (!(byte & m)) { - printk(KERN_CRIT "hfs: trying to free free bnode %u(%d)\n", node->this, node->type); + pr_crit("trying to free free bnode %u(%d)\n", + node->this, node->type); kunmap(page); hfs_bnode_put(node); return; diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c index 424b033..ff0316b 100644 --- a/fs/hfs/catalog.c +++ b/fs/hfs/catalog.c @@ -87,12 +87,15 @@ int hfs_cat_create(u32 cnid, struct inode *dir, struct qstr *str, struct inode * int entry_size; int err; - dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink); + hfs_dbg(CAT_MOD, "create_cat: %s,%u(%d)\n", + str->name, cnid, inode->i_nlink); if (dir->i_size >= HFS_MAX_VALENCE) return -ENOSPC; sb = dir->i_sb; - hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + err = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + if (err) + return err; hfs_cat_build_key(sb, fd.search_key, cnid, NULL); entry_size = hfs_cat_build_thread(sb, &entry, S_ISDIR(inode->i_mode) ? @@ -184,14 +187,14 @@ int hfs_cat_find_brec(struct super_block *sb, u32 cnid, type = rec.type; if (type != HFS_CDR_THD && type != HFS_CDR_FTH) { - printk(KERN_ERR "hfs: found bad thread record in catalog\n"); + pr_err("found bad thread record in catalog\n"); return -EIO; } fd->search_key->cat.ParID = rec.thread.ParID; len = fd->search_key->cat.CName.len = rec.thread.CName.len; if (len > HFS_NAMELEN) { - printk(KERN_ERR "hfs: bad catalog namelength\n"); + pr_err("bad catalog namelength\n"); return -EIO; } memcpy(fd->search_key->cat.CName.name, rec.thread.CName.name, len); @@ -212,9 +215,11 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str) struct list_head *pos; int res, type; - dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid); + hfs_dbg(CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid); sb = dir->i_sb; - hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + res = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + if (res) + return res; hfs_cat_build_key(sb, fd.search_key, dir->i_ino, str); res = hfs_brec_find(&fd); @@ -278,10 +283,13 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, struct qstr *src_name, int entry_size, type; int err; - dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name, + hfs_dbg(CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", + cnid, src_dir->i_ino, src_name->name, dst_dir->i_ino, dst_name->name); sb = src_dir->i_sb; - hfs_find_init(HFS_SB(sb)->cat_tree, &src_fd); + err = hfs_find_init(HFS_SB(sb)->cat_tree, &src_fd); + if (err) + return err; dst_fd = src_fd; /* find the old dir entry and read the data */ diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 5f7f1ab..17c22a8 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -25,7 +25,9 @@ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry, struct inode *inode = NULL; int res; - hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); + res = hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); + if (res) + return ERR_PTR(res); hfs_cat_build_key(dir->i_sb, fd.search_key, dir->i_ino, &dentry->d_name); res = hfs_brec_read(&fd, &rec, sizeof(rec)); if (res) { @@ -63,7 +65,9 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) if (filp->f_pos >= inode->i_size) return 0; - hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + err = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + if (err) + return err; hfs_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); err = hfs_brec_find(&fd); if (err) @@ -84,12 +88,12 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); if (entry.type != HFS_CDR_THD) { - printk(KERN_ERR "hfs: bad catalog folder thread\n"); + pr_err("bad catalog folder thread\n"); err = -EIO; goto out; } //if (fd.entrylength < HFS_MIN_THREAD_SZ) { - // printk(KERN_ERR "hfs: truncated catalog thread\n"); + // pr_err("truncated catalog thread\n"); // err = -EIO; // goto out; //} @@ -108,7 +112,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) for (;;) { if (be32_to_cpu(fd.key->cat.ParID) != inode->i_ino) { - printk(KERN_ERR "hfs: walked past end of dir\n"); + pr_err("walked past end of dir\n"); err = -EIO; goto out; } @@ -123,7 +127,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) len = hfs_mac2asc(sb, strbuf, &fd.key->cat.CName); if (type == HFS_CDR_DIR) { if (fd.entrylength < sizeof(struct hfs_cat_dir)) { - printk(KERN_ERR "hfs: small dir entry\n"); + pr_err("small dir entry\n"); err = -EIO; goto out; } @@ -132,7 +136,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) break; } else if (type == HFS_CDR_FIL) { if (fd.entrylength < sizeof(struct hfs_cat_file)) { - printk(KERN_ERR "hfs: small file entry\n"); + pr_err("small file entry\n"); err = -EIO; goto out; } @@ -140,7 +144,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) be32_to_cpu(entry.file.FlNum), DT_REG)) break; } else { - printk(KERN_ERR "hfs: bad catalog entry type %d\n", type); + pr_err("bad catalog entry type %d\n", type); err = -EIO; goto out; } diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index a67955a..e33a0d3 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -107,7 +107,7 @@ static u16 hfs_ext_lastblock(struct hfs_extent *ext) return be16_to_cpu(ext->block) + be16_to_cpu(ext->count); } -static void __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) +static int __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) { int res; @@ -116,26 +116,31 @@ static void __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd res = hfs_brec_find(fd); if (HFS_I(inode)->flags & HFS_FLG_EXT_NEW) { if (res != -ENOENT) - return; + return res; hfs_brec_insert(fd, HFS_I(inode)->cached_extents, sizeof(hfs_extent_rec)); HFS_I(inode)->flags &= ~(HFS_FLG_EXT_DIRTY|HFS_FLG_EXT_NEW); } else { if (res) - return; + return res; hfs_bnode_write(fd->bnode, HFS_I(inode)->cached_extents, fd->entryoffset, fd->entrylength); HFS_I(inode)->flags &= ~HFS_FLG_EXT_DIRTY; } + return 0; } -void hfs_ext_write_extent(struct inode *inode) +int hfs_ext_write_extent(struct inode *inode) { struct hfs_find_data fd; + int res = 0; if (HFS_I(inode)->flags & HFS_FLG_EXT_DIRTY) { - hfs_find_init(HFS_SB(inode->i_sb)->ext_tree, &fd); - __hfs_ext_write_extent(inode, &fd); + res = hfs_find_init(HFS_SB(inode->i_sb)->ext_tree, &fd); + if (res) + return res; + res = __hfs_ext_write_extent(inode, &fd); hfs_find_exit(&fd); } + return res; } static inline int __hfs_ext_read_extent(struct hfs_find_data *fd, struct hfs_extent *extent, @@ -161,8 +166,11 @@ static inline int __hfs_ext_cache_extent(struct hfs_find_data *fd, struct inode { int res; - if (HFS_I(inode)->flags & HFS_FLG_EXT_DIRTY) - __hfs_ext_write_extent(inode, fd); + if (HFS_I(inode)->flags & HFS_FLG_EXT_DIRTY) { + res = __hfs_ext_write_extent(inode, fd); + if (res) + return res; + } res = __hfs_ext_read_extent(fd, HFS_I(inode)->cached_extents, inode->i_ino, block, HFS_IS_RSRC(inode) ? HFS_FK_RSRC : HFS_FK_DATA); @@ -185,9 +193,11 @@ static int hfs_ext_read_extent(struct inode *inode, u16 block) block < HFS_I(inode)->cached_start + HFS_I(inode)->cached_blocks) return 0; - hfs_find_init(HFS_SB(inode->i_sb)->ext_tree, &fd); - res = __hfs_ext_cache_extent(&fd, inode, block); - hfs_find_exit(&fd); + res = hfs_find_init(HFS_SB(inode->i_sb)->ext_tree, &fd); + if (!res) { + res = __hfs_ext_cache_extent(&fd, inode, block); + hfs_find_exit(&fd); + } return res; } @@ -195,11 +205,12 @@ static void hfs_dump_extent(struct hfs_extent *extent) { int i; - dprint(DBG_EXTENT, " "); + hfs_dbg(EXTENT, " "); for (i = 0; i < 3; i++) - dprint(DBG_EXTENT, " %u:%u", be16_to_cpu(extent[i].block), - be16_to_cpu(extent[i].count)); - dprint(DBG_EXTENT, "\n"); + hfs_dbg_cont(EXTENT, " %u:%u", + be16_to_cpu(extent[i].block), + be16_to_cpu(extent[i].count)); + hfs_dbg_cont(EXTENT, "\n"); } static int hfs_add_extent(struct hfs_extent *extent, u16 offset, @@ -298,7 +309,9 @@ int hfs_free_fork(struct super_block *sb, struct hfs_cat_file *file, int type) if (total_blocks == blocks) return 0; - hfs_find_init(HFS_SB(sb)->ext_tree, &fd); + res = hfs_find_init(HFS_SB(sb)->ext_tree, &fd); + if (res) + return res; do { res = __hfs_ext_read_extent(&fd, extent, cnid, total_blocks, type); if (res) @@ -392,10 +405,10 @@ int hfs_extend_file(struct inode *inode) goto out; } - dprint(DBG_EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); + hfs_dbg(EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); if (HFS_I(inode)->alloc_blocks == HFS_I(inode)->first_blocks) { if (!HFS_I(inode)->first_blocks) { - dprint(DBG_EXTENT, "first extents\n"); + hfs_dbg(EXTENT, "first extents\n"); /* no extents yet */ HFS_I(inode)->first_extents[0].block = cpu_to_be16(start); HFS_I(inode)->first_extents[0].count = cpu_to_be16(len); @@ -437,8 +450,10 @@ out: return res; insert_extent: - dprint(DBG_EXTENT, "insert new extent\n"); - hfs_ext_write_extent(inode); + hfs_dbg(EXTENT, "insert new extent\n"); + res = hfs_ext_write_extent(inode); + if (res) + goto out; memset(HFS_I(inode)->cached_extents, 0, sizeof(hfs_extent_rec)); HFS_I(inode)->cached_extents[0].block = cpu_to_be16(start); @@ -460,13 +475,13 @@ void hfs_file_truncate(struct inode *inode) u32 size; int res; - dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n", inode->i_ino, - (long long)HFS_I(inode)->phys_size, inode->i_size); + hfs_dbg(INODE, "truncate: %lu, %Lu -> %Lu\n", + inode->i_ino, (long long)HFS_I(inode)->phys_size, + inode->i_size); if (inode->i_size > HFS_I(inode)->phys_size) { struct address_space *mapping = inode->i_mapping; void *fsdata; struct page *page; - int res; /* XXX: Can use generic_cont_expand? */ size = inode->i_size - 1; @@ -488,7 +503,12 @@ void hfs_file_truncate(struct inode *inode) goto out; mutex_lock(&HFS_I(inode)->extents_lock); - hfs_find_init(HFS_SB(sb)->ext_tree, &fd); + res = hfs_find_init(HFS_SB(sb)->ext_tree, &fd); + if (res) { + mutex_unlock(&HFS_I(inode)->extents_lock); + /* XXX: We lack error handling of hfs_file_truncate() */ + return; + } while (1) { if (alloc_cnt == HFS_I(inode)->first_blocks) { hfs_free_extents(sb, HFS_I(inode)->first_extents, diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 693df9f..a73b118 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -9,6 +9,12 @@ #ifndef _LINUX_HFS_FS_H #define _LINUX_HFS_FS_H +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/slab.h> #include <linux/types.h> #include <linux/mutex.h> @@ -34,8 +40,18 @@ //#define DBG_MASK (DBG_CAT_MOD|DBG_BNODE_REFS|DBG_INODE|DBG_EXTENT) #define DBG_MASK (0) -#define dprint(flg, fmt, args...) \ - if (flg & DBG_MASK) printk(fmt , ## args) +#define hfs_dbg(flg, fmt, ...) \ +do { \ + if (DBG_##flg & DBG_MASK) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ +} while (0) + +#define hfs_dbg_cont(flg, fmt, ...) \ +do { \ + if (DBG_##flg & DBG_MASK) \ + pr_cont(fmt, ##__VA_ARGS__); \ +} while (0) + /* * struct hfs_inode_info @@ -174,7 +190,7 @@ extern const struct inode_operations hfs_dir_inode_operations; /* extent.c */ extern int hfs_ext_keycmp(const btree_key *, const btree_key *); extern int hfs_free_fork(struct super_block *, struct hfs_cat_file *, int); -extern void hfs_ext_write_extent(struct inode *); +extern int hfs_ext_write_extent(struct inode *); extern int hfs_extend_file(struct inode *); extern void hfs_file_truncate(struct inode *); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 3031dfd..716e1aa 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -237,7 +237,7 @@ void hfs_delete_inode(struct inode *inode) { struct super_block *sb = inode->i_sb; - dprint(DBG_INODE, "delete_inode: %lu\n", inode->i_ino); + hfs_dbg(INODE, "delete_inode: %lu\n", inode->i_ino); if (S_ISDIR(inode->i_mode)) { HFS_SB(sb)->folder_count--; if (HFS_I(inode)->cat_key.ParID == cpu_to_be32(HFS_ROOT_CNID)) @@ -416,9 +416,12 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) struct inode *main_inode = inode; struct hfs_find_data fd; hfs_cat_rec rec; + int res; - dprint(DBG_INODE, "hfs_write_inode: %lu\n", inode->i_ino); - hfs_ext_write_extent(inode); + hfs_dbg(INODE, "hfs_write_inode: %lu\n", inode->i_ino); + res = hfs_ext_write_extent(inode); + if (res) + return res; if (inode->i_ino < HFS_FIRSTUSER_CNID) { switch (inode->i_ino) { @@ -515,7 +518,11 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, if (!inode) return ERR_PTR(-ENOMEM); - hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); + res = hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); + if (res) { + iput(inode); + return ERR_PTR(res); + } fd.search_key->cat = HFS_I(dir)->cat_key; res = hfs_brec_read(&fd, &rec, sizeof(rec)); if (!res) { diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index b7ec224..aa3f0d6 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -48,7 +48,7 @@ static int hfs_get_last_session(struct super_block *sb, *start = (sector_t)te.cdte_addr.lba << 2; return 0; } - printk(KERN_ERR "hfs: invalid session number or type of track\n"); + pr_err("invalid session number or type of track\n"); return -EINVAL; } ms_info.addr_format = CDROM_LBA; @@ -101,7 +101,7 @@ int hfs_mdb_get(struct super_block *sb) HFS_SB(sb)->alloc_blksz = size = be32_to_cpu(mdb->drAlBlkSiz); if (!size || (size & (HFS_SECTOR_SIZE - 1))) { - printk(KERN_ERR "hfs: bad allocation block size %d\n", size); + pr_err("bad allocation block size %d\n", size); goto out_bh; } @@ -118,7 +118,7 @@ int hfs_mdb_get(struct super_block *sb) size >>= 1; brelse(bh); if (!sb_set_blocksize(sb, size)) { - printk(KERN_ERR "hfs: unable to set blocksize to %u\n", size); + pr_err("unable to set blocksize to %u\n", size); goto out; } @@ -162,8 +162,8 @@ int hfs_mdb_get(struct super_block *sb) } if (!HFS_SB(sb)->alt_mdb) { - printk(KERN_WARNING "hfs: unable to locate alternate MDB\n"); - printk(KERN_WARNING "hfs: continuing without an alternate MDB\n"); + pr_warn("unable to locate alternate MDB\n"); + pr_warn("continuing without an alternate MDB\n"); } HFS_SB(sb)->bitmap = (__be32 *)__get_free_pages(GFP_KERNEL, PAGE_SIZE < 8192 ? 1 : 0); @@ -178,7 +178,7 @@ int hfs_mdb_get(struct super_block *sb) while (size) { bh = sb_bread(sb, off >> sb->s_blocksize_bits); if (!bh) { - printk(KERN_ERR "hfs: unable to read volume bitmap\n"); + pr_err("unable to read volume bitmap\n"); goto out; } off2 = off & (sb->s_blocksize - 1); @@ -192,23 +192,22 @@ int hfs_mdb_get(struct super_block *sb) HFS_SB(sb)->ext_tree = hfs_btree_open(sb, HFS_EXT_CNID, hfs_ext_keycmp); if (!HFS_SB(sb)->ext_tree) { - printk(KERN_ERR "hfs: unable to open extent tree\n"); + pr_err("unable to open extent tree\n"); goto out; } HFS_SB(sb)->cat_tree = hfs_btree_open(sb, HFS_CAT_CNID, hfs_cat_keycmp); if (!HFS_SB(sb)->cat_tree) { - printk(KERN_ERR "hfs: unable to open catalog tree\n"); + pr_err("unable to open catalog tree\n"); goto out; } attrib = mdb->drAtrb; if (!(attrib & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { - printk(KERN_WARNING "hfs: filesystem was not cleanly unmounted, " - "running fsck.hfs is recommended. mounting read-only.\n"); + pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } if ((attrib & cpu_to_be16(HFS_SB_ATTRIB_SLOCK))) { - printk(KERN_WARNING "hfs: filesystem is marked locked, mounting read-only.\n"); + pr_warn("filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } if (!(sb->s_flags & MS_RDONLY)) { @@ -312,7 +311,7 @@ void hfs_mdb_commit(struct super_block *sb) while (size) { bh = sb_bread(sb, block); if (!bh) { - printk(KERN_ERR "hfs: unable to read volume bitmap\n"); + pr_err("unable to read volume bitmap\n"); break; } len = min((int)sb->s_blocksize - off, size); diff --git a/fs/hfs/super.c b/fs/hfs/super.c index bbaaa8a..2d2039e 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -117,12 +117,11 @@ static int hfs_remount(struct super_block *sb, int *flags, char *data) return 0; if (!(*flags & MS_RDONLY)) { if (!(HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { - printk(KERN_WARNING "hfs: filesystem was not cleanly unmounted, " - "running fsck.hfs is recommended. leaving read-only.\n"); + pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } else if (HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_SLOCK)) { - printk(KERN_WARNING "hfs: filesystem is marked locked, leaving read-only.\n"); + pr_warn("filesystem is marked locked, leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } @@ -253,29 +252,29 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) switch (token) { case opt_uid: if (match_int(&args[0], &tmp)) { - printk(KERN_ERR "hfs: uid requires an argument\n"); + pr_err("uid requires an argument\n"); return 0; } hsb->s_uid = make_kuid(current_user_ns(), (uid_t)tmp); if (!uid_valid(hsb->s_uid)) { - printk(KERN_ERR "hfs: invalid uid %d\n", tmp); + pr_err("invalid uid %d\n", tmp); return 0; } break; case opt_gid: if (match_int(&args[0], &tmp)) { - printk(KERN_ERR "hfs: gid requires an argument\n"); + pr_err("gid requires an argument\n"); return 0; } hsb->s_gid = make_kgid(current_user_ns(), (gid_t)tmp); if (!gid_valid(hsb->s_gid)) { - printk(KERN_ERR "hfs: invalid gid %d\n", tmp); + pr_err("invalid gid %d\n", tmp); return 0; } break; case opt_umask: if (match_octal(&args[0], &tmp)) { - printk(KERN_ERR "hfs: umask requires a value\n"); + pr_err("umask requires a value\n"); return 0; } hsb->s_file_umask = (umode_t)tmp; @@ -283,39 +282,39 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) break; case opt_file_umask: if (match_octal(&args[0], &tmp)) { - printk(KERN_ERR "hfs: file_umask requires a value\n"); + pr_err("file_umask requires a value\n"); return 0; } hsb->s_file_umask = (umode_t)tmp; break; case opt_dir_umask: if (match_octal(&args[0], &tmp)) { - printk(KERN_ERR "hfs: dir_umask requires a value\n"); + pr_err("dir_umask requires a value\n"); return 0; } hsb->s_dir_umask = (umode_t)tmp; break; case opt_part: if (match_int(&args[0], &hsb->part)) { - printk(KERN_ERR "hfs: part requires an argument\n"); + pr_err("part requires an argument\n"); return 0; } break; case opt_session: if (match_int(&args[0], &hsb->session)) { - printk(KERN_ERR "hfs: session requires an argument\n"); + pr_err("session requires an argument\n"); return 0; } break; case opt_type: if (match_fourchar(&args[0], &hsb->s_type)) { - printk(KERN_ERR "hfs: type requires a 4 character value\n"); + pr_err("type requires a 4 character value\n"); return 0; } break; case opt_creator: if (match_fourchar(&args[0], &hsb->s_creator)) { - printk(KERN_ERR "hfs: creator requires a 4 character value\n"); + pr_err("creator requires a 4 character value\n"); return 0; } break; @@ -324,14 +323,14 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) break; case opt_codepage: if (hsb->nls_disk) { - printk(KERN_ERR "hfs: unable to change codepage\n"); + pr_err("unable to change codepage\n"); return 0; } p = match_strdup(&args[0]); if (p) hsb->nls_disk = load_nls(p); if (!hsb->nls_disk) { - printk(KERN_ERR "hfs: unable to load codepage \"%s\"\n", p); + pr_err("unable to load codepage \"%s\"\n", p); kfree(p); return 0; } @@ -339,14 +338,14 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) break; case opt_iocharset: if (hsb->nls_io) { - printk(KERN_ERR "hfs: unable to change iocharset\n"); + pr_err("unable to change iocharset\n"); return 0; } p = match_strdup(&args[0]); if (p) hsb->nls_io = load_nls(p); if (!hsb->nls_io) { - printk(KERN_ERR "hfs: unable to load iocharset \"%s\"\n", p); + pr_err("unable to load iocharset \"%s\"\n", p); kfree(p); return 0; } @@ -360,7 +359,7 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) if (hsb->nls_disk && !hsb->nls_io) { hsb->nls_io = load_nls_default(); if (!hsb->nls_io) { - printk(KERN_ERR "hfs: unable to load default iocharset\n"); + pr_err("unable to load default iocharset\n"); return 0; } } @@ -400,7 +399,7 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) res = -EINVAL; if (!parse_options((char *)data, sbi)) { - printk(KERN_ERR "hfs: unable to parse mount options.\n"); + pr_err("unable to parse mount options\n"); goto bail; } @@ -411,14 +410,16 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) res = hfs_mdb_get(sb); if (res) { if (!silent) - printk(KERN_WARNING "hfs: can't find a HFS filesystem on dev %s.\n", + pr_warn("can't find a HFS filesystem on dev %s\n", hfs_mdb_name(sb)); res = -EINVAL; goto bail; } /* try to get the root inode */ - hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + res = hfs_find_init(HFS_SB(sb)->cat_tree, &fd); + if (res) + goto bail_no_root; res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd); if (!res) { if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { @@ -447,7 +448,7 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) return 0; bail_no_root: - printk(KERN_ERR "hfs: get root inode failed.\n"); + pr_err("get root inode failed\n"); bail: hfs_mdb_put(sb); return res; diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c index 8d691f1..0f47890 100644 --- a/fs/hfsplus/attributes.c +++ b/fs/hfsplus/attributes.c @@ -56,7 +56,7 @@ int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key, if (name) { len = strlen(name); if (len > HFSPLUS_ATTR_MAX_STRLEN) { - printk(KERN_ERR "hfs: invalid xattr name's length\n"); + pr_err("invalid xattr name's length\n"); return -EINVAL; } hfsplus_asc2uni(sb, @@ -166,10 +166,10 @@ int hfsplus_find_attr(struct super_block *sb, u32 cnid, { int err = 0; - dprint(DBG_ATTR_MOD, "find_attr: %s,%d\n", name ? name : NULL, cnid); + hfs_dbg(ATTR_MOD, "find_attr: %s,%d\n", name ? name : NULL, cnid); if (!HFSPLUS_SB(sb)->attr_tree) { - printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + pr_err("attributes file doesn't exist\n"); return -EINVAL; } @@ -228,11 +228,11 @@ int hfsplus_create_attr(struct inode *inode, int entry_size; int err; - dprint(DBG_ATTR_MOD, "create_attr: %s,%ld\n", + hfs_dbg(ATTR_MOD, "create_attr: %s,%ld\n", name ? name : NULL, inode->i_ino); if (!HFSPLUS_SB(sb)->attr_tree) { - printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + pr_err("attributes file doesn't exist\n"); return -EINVAL; } @@ -307,10 +307,10 @@ static int __hfsplus_delete_attr(struct inode *inode, u32 cnid, break; case HFSPLUS_ATTR_FORK_DATA: case HFSPLUS_ATTR_EXTENTS: - printk(KERN_ERR "hfs: only inline data xattr are supported\n"); + pr_err("only inline data xattr are supported\n"); return -EOPNOTSUPP; default: - printk(KERN_ERR "hfs: invalid extended attribute record\n"); + pr_err("invalid extended attribute record\n"); return -ENOENT; } @@ -328,11 +328,11 @@ int hfsplus_delete_attr(struct inode *inode, const char *name) struct super_block *sb = inode->i_sb; struct hfs_find_data fd; - dprint(DBG_ATTR_MOD, "delete_attr: %s,%ld\n", + hfs_dbg(ATTR_MOD, "delete_attr: %s,%ld\n", name ? name : NULL, inode->i_ino); if (!HFSPLUS_SB(sb)->attr_tree) { - printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + pr_err("attributes file doesn't exist\n"); return -EINVAL; } @@ -346,7 +346,7 @@ int hfsplus_delete_attr(struct inode *inode, const char *name) if (err) goto out; } else { - printk(KERN_ERR "hfs: invalid extended attribute name\n"); + pr_err("invalid extended attribute name\n"); err = -EINVAL; goto out; } @@ -369,10 +369,10 @@ int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid) int err = 0; struct hfs_find_data fd; - dprint(DBG_ATTR_MOD, "delete_all_attrs: %d\n", cnid); + hfs_dbg(ATTR_MOD, "delete_all_attrs: %d\n", cnid); if (!HFSPLUS_SB(dir->i_sb)->attr_tree) { - printk(KERN_ERR "hfs: attributes file doesn't exist\n"); + pr_err("attributes file doesn't exist\n"); return -EINVAL; } @@ -384,7 +384,7 @@ int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid) err = hfsplus_find_attr(dir->i_sb, cnid, NULL, &fd); if (err) { if (err != -ENOENT) - printk(KERN_ERR "hfs: xattr search failed.\n"); + pr_err("xattr search failed\n"); goto end_delete_all; } diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c index d73c98d..c1422d9 100644 --- a/fs/hfsplus/bfind.c +++ b/fs/hfsplus/bfind.c @@ -22,7 +22,7 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) return -ENOMEM; fd->search_key = ptr; fd->key = ptr + tree->max_key_len + 2; - dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", + hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0)); switch (tree->cnid) { case HFSPLUS_CAT_CNID: @@ -44,7 +44,7 @@ void hfs_find_exit(struct hfs_find_data *fd) { hfs_bnode_put(fd->bnode); kfree(fd->search_key); - dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", + hfs_dbg(BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0)); mutex_unlock(&fd->tree->tree_lock); fd->tree = NULL; @@ -56,7 +56,8 @@ int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode, int *end, int *cur_rec) { - __be32 cur_cnid, search_cnid; + __be32 cur_cnid; + __be32 search_cnid; if (bnode->tree->cnid == HFSPLUS_EXT_CNID) { cur_cnid = fd->key->ext.cnid; @@ -67,8 +68,11 @@ int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode, } else if (bnode->tree->cnid == HFSPLUS_ATTR_CNID) { cur_cnid = fd->key->attr.cnid; search_cnid = fd->search_key->attr.cnid; - } else + } else { + cur_cnid = 0; /* used-uninitialized warning */ + search_cnid = 0; BUG(); + } if (cur_cnid == search_cnid) { (*end) = (*cur_rec); @@ -204,7 +208,7 @@ int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare) return res; invalid: - printk(KERN_ERR "hfs: inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", + pr_err("inconsistency in B*Tree (%d,%d,%d,%u,%u)\n", height, bnode->height, bnode->type, nidx, parent); res = -EIO; release: diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c index 6feefc0..d2954451 100644 --- a/fs/hfsplus/bitmap.c +++ b/fs/hfsplus/bitmap.c @@ -30,7 +30,7 @@ int hfsplus_block_allocate(struct super_block *sb, u32 size, if (!len) return size; - dprint(DBG_BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len); + hfs_dbg(BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len); mutex_lock(&sbi->alloc_mutex); mapping = sbi->alloc_file->i_mapping; page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL); @@ -89,14 +89,14 @@ int hfsplus_block_allocate(struct super_block *sb, u32 size, else end = pptr + ((size + 31) & (PAGE_CACHE_BITS - 1)) / 32; } - dprint(DBG_BITMAP, "bitmap full\n"); + hfs_dbg(BITMAP, "bitmap full\n"); start = size; goto out; found: start = offset + (curr - pptr) * 32 + i; if (start >= size) { - dprint(DBG_BITMAP, "bitmap full\n"); + hfs_dbg(BITMAP, "bitmap full\n"); goto out; } /* do any partial u32 at the start */ @@ -154,7 +154,7 @@ done: *max = offset + (curr - pptr) * 32 + i - start; sbi->free_blocks -= *max; hfsplus_mark_mdb_dirty(sb); - dprint(DBG_BITMAP, "-> %u,%u\n", start, *max); + hfs_dbg(BITMAP, "-> %u,%u\n", start, *max); out: mutex_unlock(&sbi->alloc_mutex); return start; @@ -173,7 +173,7 @@ int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count) if (!count) return 0; - dprint(DBG_BITMAP, "block_free: %u,%u\n", offset, count); + hfs_dbg(BITMAP, "block_free: %u,%u\n", offset, count); /* are all of the bits in range? */ if ((offset + count) > sbi->total_blocks) return -ENOENT; @@ -238,8 +238,7 @@ out: return 0; kaboom: - printk(KERN_CRIT "hfsplus: unable to mark blocks free: error %ld\n", - PTR_ERR(page)); + pr_crit("unable to mark blocks free: error %ld\n", PTR_ERR(page)); mutex_unlock(&sbi->alloc_mutex); return -EIO; diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index f31ac6f..11c8602 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -130,7 +130,7 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst, struct page **src_page, **dst_page; int l; - dprint(DBG_BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); + hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); if (!len) return; tree = src_node->tree; @@ -188,7 +188,7 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) struct page **src_page, **dst_page; int l; - dprint(DBG_BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); + hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); if (!len) return; src += node->page_offset; @@ -302,16 +302,16 @@ void hfs_bnode_dump(struct hfs_bnode *node) __be32 cnid; int i, off, key_off; - dprint(DBG_BNODE_MOD, "bnode: %d\n", node->this); + hfs_dbg(BNODE_MOD, "bnode: %d\n", node->this); hfs_bnode_read(node, &desc, 0, sizeof(desc)); - dprint(DBG_BNODE_MOD, "%d, %d, %d, %d, %d\n", + hfs_dbg(BNODE_MOD, "%d, %d, %d, %d, %d\n", be32_to_cpu(desc.next), be32_to_cpu(desc.prev), desc.type, desc.height, be16_to_cpu(desc.num_recs)); off = node->tree->node_size - 2; for (i = be16_to_cpu(desc.num_recs); i >= 0; off -= 2, i--) { key_off = hfs_bnode_read_u16(node, off); - dprint(DBG_BNODE_MOD, " %d", key_off); + hfs_dbg(BNODE_MOD, " %d", key_off); if (i && node->type == HFS_NODE_INDEX) { int tmp; @@ -320,17 +320,17 @@ void hfs_bnode_dump(struct hfs_bnode *node) tmp = hfs_bnode_read_u16(node, key_off) + 2; else tmp = node->tree->max_key_len + 2; - dprint(DBG_BNODE_MOD, " (%d", tmp); + hfs_dbg_cont(BNODE_MOD, " (%d", tmp); hfs_bnode_read(node, &cnid, key_off + tmp, 4); - dprint(DBG_BNODE_MOD, ",%d)", be32_to_cpu(cnid)); + hfs_dbg_cont(BNODE_MOD, ",%d)", be32_to_cpu(cnid)); } else if (i && node->type == HFS_NODE_LEAF) { int tmp; tmp = hfs_bnode_read_u16(node, key_off); - dprint(DBG_BNODE_MOD, " (%d)", tmp); + hfs_dbg_cont(BNODE_MOD, " (%d)", tmp); } } - dprint(DBG_BNODE_MOD, "\n"); + hfs_dbg_cont(BNODE_MOD, "\n"); } void hfs_bnode_unlink(struct hfs_bnode *node) @@ -366,7 +366,7 @@ void hfs_bnode_unlink(struct hfs_bnode *node) /* move down? */ if (!node->prev && !node->next) - dprint(DBG_BNODE_MOD, "hfs_btree_del_level\n"); + hfs_dbg(BNODE_MOD, "hfs_btree_del_level\n"); if (!node->parent) { tree->root = 0; tree->depth = 0; @@ -386,7 +386,7 @@ struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid) struct hfs_bnode *node; if (cnid >= tree->node_count) { - printk(KERN_ERR "hfs: request for non-existent node " + pr_err("request for non-existent node " "%d in B*Tree\n", cnid); return NULL; @@ -409,7 +409,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) loff_t off; if (cnid >= tree->node_count) { - printk(KERN_ERR "hfs: request for non-existent node " + pr_err("request for non-existent node " "%d in B*Tree\n", cnid); return NULL; @@ -425,8 +425,8 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) node->this = cnid; set_bit(HFS_BNODE_NEW, &node->flags); atomic_set(&node->refcnt, 1); - dprint(DBG_BNODE_REFS, "new_node(%d:%d): 1\n", - node->tree->cnid, node->this); + hfs_dbg(BNODE_REFS, "new_node(%d:%d): 1\n", + node->tree->cnid, node->this); init_waitqueue_head(&node->lock_wq); spin_lock(&tree->hash_lock); node2 = hfs_bnode_findhash(tree, cnid); @@ -470,7 +470,7 @@ void hfs_bnode_unhash(struct hfs_bnode *node) { struct hfs_bnode **p; - dprint(DBG_BNODE_REFS, "remove_node(%d:%d): %d\n", + hfs_dbg(BNODE_REFS, "remove_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); for (p = &node->tree->node_hash[hfs_bnode_hash(node->this)]; *p && *p != node; p = &(*p)->next_hash) @@ -588,7 +588,7 @@ struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num) node = hfs_bnode_findhash(tree, num); spin_unlock(&tree->hash_lock); if (node) { - printk(KERN_CRIT "new node %u already hashed?\n", num); + pr_crit("new node %u already hashed?\n", num); WARN_ON(1); return node; } @@ -620,7 +620,7 @@ void hfs_bnode_get(struct hfs_bnode *node) { if (node) { atomic_inc(&node->refcnt); - dprint(DBG_BNODE_REFS, "get_node(%d:%d): %d\n", + hfs_dbg(BNODE_REFS, "get_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); } @@ -633,7 +633,7 @@ void hfs_bnode_put(struct hfs_bnode *node) struct hfs_btree *tree = node->tree; int i; - dprint(DBG_BNODE_REFS, "put_node(%d:%d): %d\n", + hfs_dbg(BNODE_REFS, "put_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); BUG_ON(!atomic_read(&node->refcnt)); diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 298d4e4..6e560d5 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -45,13 +45,13 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) if (!recoff) return 0; if (recoff > node->tree->node_size - 2) { - printk(KERN_ERR "hfs: recoff %d too large\n", recoff); + pr_err("recoff %d too large\n", recoff); return 0; } retval = hfs_bnode_read_u16(node, recoff) + 2; if (retval > node->tree->max_key_len + 2) { - printk(KERN_ERR "hfs: keylen %d too large\n", + pr_err("keylen %d too large\n", retval); retval = 0; } @@ -90,7 +90,7 @@ again: end_rec_off = tree->node_size - (node->num_recs + 1) * 2; end_off = hfs_bnode_read_u16(node, end_rec_off); end_rec_off -= 2; - dprint(DBG_BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", + hfs_dbg(BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", rec, size, end_off, end_rec_off); if (size > end_rec_off - end_off) { if (new_node) @@ -191,7 +191,7 @@ again: mark_inode_dirty(tree->inode); } hfs_bnode_dump(node); - dprint(DBG_BNODE_MOD, "remove_rec: %d, %d\n", + hfs_dbg(BNODE_MOD, "remove_rec: %d, %d\n", fd->record, fd->keylength + fd->entrylength); if (!--node->num_recs) { hfs_bnode_unlink(node); @@ -244,7 +244,7 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd) if (IS_ERR(new_node)) return new_node; hfs_bnode_get(node); - dprint(DBG_BNODE_MOD, "split_nodes: %d - %d - %d\n", + hfs_dbg(BNODE_MOD, "split_nodes: %d - %d - %d\n", node->this, new_node->this, node->next); new_node->next = node->next; new_node->prev = node->this; @@ -379,7 +379,7 @@ again: newkeylen = hfs_bnode_read_u16(node, 14) + 2; else fd->keylength = newkeylen = tree->max_key_len + 2; - dprint(DBG_BNODE_MOD, "update_rec: %d, %d, %d\n", + hfs_dbg(BNODE_MOD, "update_rec: %d, %d, %d\n", rec, fd->keylength, newkeylen); rec_off = tree->node_size - (rec + 2) * 2; @@ -391,7 +391,7 @@ again: end_off = hfs_bnode_read_u16(parent, end_rec_off); if (end_rec_off - end_off < diff) { - dprint(DBG_BNODE_MOD, "hfs: splitting index node.\n"); + hfs_dbg(BNODE_MOD, "splitting index node\n"); fd->bnode = parent; new_node = hfs_bnode_split(fd); if (IS_ERR(new_node)) diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index efb689c..0c6540c 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -40,8 +40,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) tree->inode = inode; if (!HFSPLUS_I(tree->inode)->first_blocks) { - printk(KERN_ERR - "hfs: invalid btree extent records (0 size).\n"); + pr_err("invalid btree extent records (0 size)\n"); goto free_inode; } @@ -68,12 +67,12 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) switch (id) { case HFSPLUS_EXT_CNID: if (tree->max_key_len != HFSPLUS_EXT_KEYLEN - sizeof(u16)) { - printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", + pr_err("invalid extent max_key_len %d\n", tree->max_key_len); goto fail_page; } if (tree->attributes & HFS_TREE_VARIDXKEYS) { - printk(KERN_ERR "hfs: invalid extent btree flag\n"); + pr_err("invalid extent btree flag\n"); goto fail_page; } @@ -81,12 +80,12 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) break; case HFSPLUS_CAT_CNID: if (tree->max_key_len != HFSPLUS_CAT_KEYLEN - sizeof(u16)) { - printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", + pr_err("invalid catalog max_key_len %d\n", tree->max_key_len); goto fail_page; } if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) { - printk(KERN_ERR "hfs: invalid catalog btree flag\n"); + pr_err("invalid catalog btree flag\n"); goto fail_page; } @@ -100,19 +99,19 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) break; case HFSPLUS_ATTR_CNID: if (tree->max_key_len != HFSPLUS_ATTR_KEYLEN - sizeof(u16)) { - printk(KERN_ERR "hfs: invalid attributes max_key_len %d\n", + pr_err("invalid attributes max_key_len %d\n", tree->max_key_len); goto fail_page; } tree->keycmp = hfsplus_attr_bin_cmp_key; break; default: - printk(KERN_ERR "hfs: unknown B*Tree requested\n"); + pr_err("unknown B*Tree requested\n"); goto fail_page; } if (!(tree->attributes & HFS_TREE_BIGKEYS)) { - printk(KERN_ERR "hfs: invalid btree flag\n"); + pr_err("invalid btree flag\n"); goto fail_page; } @@ -155,7 +154,7 @@ void hfs_btree_close(struct hfs_btree *tree) while ((node = tree->node_hash[i])) { tree->node_hash[i] = node->next_hash; if (atomic_read(&node->refcnt)) - printk(KERN_CRIT "hfs: node %d:%d " + pr_crit("node %d:%d " "still has %d user(s)!\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); @@ -303,7 +302,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) kunmap(*pagep); nidx = node->next; if (!nidx) { - dprint(DBG_BNODE_MOD, "hfs: create new bmap node.\n"); + hfs_dbg(BNODE_MOD, "create new bmap node\n"); next_node = hfs_bmap_new_bmap(node, idx); } else next_node = hfs_bnode_find(tree, nidx); @@ -329,7 +328,7 @@ void hfs_bmap_free(struct hfs_bnode *node) u32 nidx; u8 *data, byte, m; - dprint(DBG_BNODE_MOD, "btree_free_node: %u\n", node->this); + hfs_dbg(BNODE_MOD, "btree_free_node: %u\n", node->this); BUG_ON(!node->this); tree = node->tree; nidx = node->this; @@ -345,7 +344,7 @@ void hfs_bmap_free(struct hfs_bnode *node) hfs_bnode_put(node); if (!i) { /* panic */; - printk(KERN_CRIT "hfs: unable to free bnode %u. " + pr_crit("unable to free bnode %u. " "bmap not found!\n", node->this); return; @@ -355,7 +354,7 @@ void hfs_bmap_free(struct hfs_bnode *node) return; if (node->type != HFS_NODE_MAP) { /* panic */; - printk(KERN_CRIT "hfs: invalid bmap found! " + pr_crit("invalid bmap found! " "(%u,%d)\n", node->this, node->type); hfs_bnode_put(node); @@ -370,7 +369,7 @@ void hfs_bmap_free(struct hfs_bnode *node) m = 1 << (~nidx & 7); byte = data[off]; if (!(byte & m)) { - printk(KERN_CRIT "hfs: trying to free free bnode " + pr_crit("trying to free free bnode " "%u(%d)\n", node->this, node->type); kunmap(page); diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 840d71e..968ce41 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -188,12 +188,12 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid, type = be16_to_cpu(tmp.type); if (type != HFSPLUS_FOLDER_THREAD && type != HFSPLUS_FILE_THREAD) { - printk(KERN_ERR "hfs: found bad thread record in catalog\n"); + pr_err("found bad thread record in catalog\n"); return -EIO; } if (be16_to_cpu(tmp.thread.nodeName.length) > 255) { - printk(KERN_ERR "hfs: catalog name length corrupted\n"); + pr_err("catalog name length corrupted\n"); return -EIO; } @@ -212,7 +212,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, int entry_size; int err; - dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", + hfs_dbg(CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); if (err) @@ -271,8 +271,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) int err, off; u16 type; - dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", - str ? str->name : NULL, cnid); + hfs_dbg(CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); if (err) return err; @@ -361,7 +360,7 @@ int hfsplus_rename_cat(u32 cnid, int entry_size, type; int err; - dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", + hfs_dbg(CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name, dst_dir->i_ino, dst_name->name); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd); diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 031c24e..a37ac93 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -103,7 +103,7 @@ again: } else if (!dentry->d_fsdata) dentry->d_fsdata = (void *)(unsigned long)cnid; } else { - printk(KERN_ERR "hfs: invalid catalog entry type in lookup\n"); + pr_err("invalid catalog entry type in lookup\n"); err = -EIO; goto fail; } @@ -159,12 +159,12 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); if (be16_to_cpu(entry.type) != HFSPLUS_FOLDER_THREAD) { - printk(KERN_ERR "hfs: bad catalog folder thread\n"); + pr_err("bad catalog folder thread\n"); err = -EIO; goto out; } if (fd.entrylength < HFSPLUS_MIN_THREAD_SZ) { - printk(KERN_ERR "hfs: truncated catalog thread\n"); + pr_err("truncated catalog thread\n"); err = -EIO; goto out; } @@ -183,7 +183,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) for (;;) { if (be32_to_cpu(fd.key->cat.parent) != inode->i_ino) { - printk(KERN_ERR "hfs: walked past end of dir\n"); + pr_err("walked past end of dir\n"); err = -EIO; goto out; } @@ -203,7 +203,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) if (type == HFSPLUS_FOLDER) { if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) { - printk(KERN_ERR "hfs: small dir entry\n"); + pr_err("small dir entry\n"); err = -EIO; goto out; } @@ -216,7 +216,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) break; } else if (type == HFSPLUS_FILE) { if (fd.entrylength < sizeof(struct hfsplus_cat_file)) { - printk(KERN_ERR "hfs: small file entry\n"); + pr_err("small file entry\n"); err = -EIO; goto out; } @@ -224,7 +224,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) be32_to_cpu(entry.file.id), DT_REG)) break; } else { - printk(KERN_ERR "hfs: bad catalog entry type\n"); + pr_err("bad catalog entry type\n"); err = -EIO; goto out; } diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index fe0a762..fbb212f 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -83,7 +83,7 @@ static u32 hfsplus_ext_lastblock(struct hfsplus_extent *ext) return be32_to_cpu(ext->start_block) + be32_to_cpu(ext->block_count); } -static void __hfsplus_ext_write_extent(struct inode *inode, +static int __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) { struct hfsplus_inode_info *hip = HFSPLUS_I(inode); @@ -98,13 +98,13 @@ static void __hfsplus_ext_write_extent(struct inode *inode, res = hfs_brec_find(fd, hfs_find_rec_by_key); if (hip->extent_state & HFSPLUS_EXT_NEW) { if (res != -ENOENT) - return; + return res; hfs_brec_insert(fd, hip->cached_extents, sizeof(hfsplus_extent_rec)); hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); } else { if (res) - return; + return res; hfs_bnode_write(fd->bnode, hip->cached_extents, fd->entryoffset, fd->entrylength); hip->extent_state &= ~HFSPLUS_EXT_DIRTY; @@ -117,11 +117,13 @@ static void __hfsplus_ext_write_extent(struct inode *inode, * to explicily mark the inode dirty, too. */ set_bit(HFSPLUS_I_EXT_DIRTY, &hip->flags); + + return 0; } static int hfsplus_ext_write_extent_locked(struct inode *inode) { - int res; + int res = 0; if (HFSPLUS_I(inode)->extent_state & HFSPLUS_EXT_DIRTY) { struct hfs_find_data fd; @@ -129,10 +131,10 @@ static int hfsplus_ext_write_extent_locked(struct inode *inode) res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); if (res) return res; - __hfsplus_ext_write_extent(inode, &fd); + res = __hfsplus_ext_write_extent(inode, &fd); hfs_find_exit(&fd); } - return 0; + return res; } int hfsplus_ext_write_extent(struct inode *inode) @@ -175,8 +177,11 @@ static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, WARN_ON(!mutex_is_locked(&hip->extents_lock)); - if (hip->extent_state & HFSPLUS_EXT_DIRTY) - __hfsplus_ext_write_extent(inode, fd); + if (hip->extent_state & HFSPLUS_EXT_DIRTY) { + res = __hfsplus_ext_write_extent(inode, fd); + if (res) + return res; + } res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino, block, HFSPLUS_IS_RSRC(inode) ? @@ -265,7 +270,7 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock, mutex_unlock(&hip->extents_lock); done: - dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n", + hfs_dbg(EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock); mask = (1 << sbi->fs_shift) - 1; @@ -288,11 +293,12 @@ static void hfsplus_dump_extent(struct hfsplus_extent *extent) { int i; - dprint(DBG_EXTENT, " "); + hfs_dbg(EXTENT, " "); for (i = 0; i < 8; i++) - dprint(DBG_EXTENT, " %u:%u", be32_to_cpu(extent[i].start_block), - be32_to_cpu(extent[i].block_count)); - dprint(DBG_EXTENT, "\n"); + hfs_dbg_cont(EXTENT, " %u:%u", + be32_to_cpu(extent[i].start_block), + be32_to_cpu(extent[i].block_count)); + hfs_dbg_cont(EXTENT, "\n"); } static int hfsplus_add_extent(struct hfsplus_extent *extent, u32 offset, @@ -348,8 +354,8 @@ found: if (count <= block_nr) { err = hfsplus_block_free(sb, start, count); if (err) { - printk(KERN_ERR "hfs: can't free extent\n"); - dprint(DBG_EXTENT, " start: %u count: %u\n", + pr_err("can't free extent\n"); + hfs_dbg(EXTENT, " start: %u count: %u\n", start, count); } extent->block_count = 0; @@ -359,8 +365,8 @@ found: count -= block_nr; err = hfsplus_block_free(sb, start + count, block_nr); if (err) { - printk(KERN_ERR "hfs: can't free extent\n"); - dprint(DBG_EXTENT, " start: %u count: %u\n", + pr_err("can't free extent\n"); + hfs_dbg(EXTENT, " start: %u count: %u\n", start, count); } extent->block_count = cpu_to_be32(count); @@ -432,7 +438,7 @@ int hfsplus_file_extend(struct inode *inode) if (sbi->alloc_file->i_size * 8 < sbi->total_blocks - sbi->free_blocks + 8) { /* extend alloc file */ - printk(KERN_ERR "hfs: extend alloc file! " + pr_err("extend alloc file! " "(%llu,%u,%u)\n", sbi->alloc_file->i_size * 8, sbi->total_blocks, sbi->free_blocks); @@ -459,11 +465,11 @@ int hfsplus_file_extend(struct inode *inode) } } - dprint(DBG_EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); + hfs_dbg(EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len); if (hip->alloc_blocks <= hip->first_blocks) { if (!hip->first_blocks) { - dprint(DBG_EXTENT, "first extents\n"); + hfs_dbg(EXTENT, "first extents\n"); /* no extents yet */ hip->first_extents[0].start_block = cpu_to_be32(start); hip->first_extents[0].block_count = cpu_to_be32(len); @@ -500,7 +506,7 @@ out: return res; insert_extent: - dprint(DBG_EXTENT, "insert new extent\n"); + hfs_dbg(EXTENT, "insert new extent\n"); res = hfsplus_ext_write_extent_locked(inode); if (res) goto out; @@ -525,9 +531,8 @@ void hfsplus_file_truncate(struct inode *inode) u32 alloc_cnt, blk_cnt, start; int res; - dprint(DBG_INODE, "truncate: %lu, %llu -> %llu\n", - inode->i_ino, (long long)hip->phys_size, - inode->i_size); + hfs_dbg(INODE, "truncate: %lu, %llu -> %llu\n", + inode->i_ino, (long long)hip->phys_size, inode->i_size); if (inode->i_size > hip->phys_size) { struct address_space *mapping = inode->i_mapping; diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 05b11f3..60b0a33 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -10,6 +10,12 @@ #ifndef _LINUX_HFSPLUS_FS_H #define _LINUX_HFSPLUS_FS_H +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/fs.h> #include <linux/mutex.h> #include <linux/buffer_head.h> @@ -32,9 +38,17 @@ #endif #define DBG_MASK (0) -#define dprint(flg, fmt, args...) \ - if (flg & DBG_MASK) \ - printk(fmt , ## args) +#define hfs_dbg(flg, fmt, ...) \ +do { \ + if (DBG_##flg & DBG_MASK) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ +} while (0) + +#define hfs_dbg_cont(flg, fmt, ...) \ +do { \ + if (DBG_##flg & DBG_MASK) \ + pr_cont(fmt, ##__VA_ARGS__); \ +} while (0) /* Runtime config options */ #define HFSPLUS_DEF_CR_TYPE 0x3F3F3F3F /* '????' */ diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 160ccc9..7faaa96 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -357,7 +357,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, if (!error) error = error2; } else { - printk(KERN_ERR "hfs: sync non-existent attributes tree\n"); + pr_err("sync non-existent attributes tree\n"); } } @@ -573,7 +573,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) inode->i_ctime = hfsp_mt2ut(file->attribute_mod_date); HFSPLUS_I(inode)->create_date = file->create_date; } else { - printk(KERN_ERR "hfs: bad catalog entry used to create inode\n"); + pr_err("bad catalog entry used to create inode\n"); res = -EIO; } return res; diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index ed257c6..968eab5 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -113,67 +113,67 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) switch (token) { case opt_creator: if (match_fourchar(&args[0], &sbi->creator)) { - printk(KERN_ERR "hfs: creator requires a 4 character value\n"); + pr_err("creator requires a 4 character value\n"); return 0; } break; case opt_type: if (match_fourchar(&args[0], &sbi->type)) { - printk(KERN_ERR "hfs: type requires a 4 character value\n"); + pr_err("type requires a 4 character value\n"); return 0; } break; case opt_umask: if (match_octal(&args[0], &tmp)) { - printk(KERN_ERR "hfs: umask requires a value\n"); + pr_err("umask requires a value\n"); return 0; } sbi->umask = (umode_t)tmp; break; case opt_uid: if (match_int(&args[0], &tmp)) { - printk(KERN_ERR "hfs: uid requires an argument\n"); + pr_err("uid requires an argument\n"); return 0; } sbi->uid = make_kuid(current_user_ns(), (uid_t)tmp); if (!uid_valid(sbi->uid)) { - printk(KERN_ERR "hfs: invalid uid specified\n"); + pr_err("invalid uid specified\n"); return 0; } break; case opt_gid: if (match_int(&args[0], &tmp)) { - printk(KERN_ERR "hfs: gid requires an argument\n"); + pr_err("gid requires an argument\n"); return 0; } sbi->gid = make_kgid(current_user_ns(), (gid_t)tmp); if (!gid_valid(sbi->gid)) { - printk(KERN_ERR "hfs: invalid gid specified\n"); + pr_err("invalid gid specified\n"); return 0; } break; case opt_part: if (match_int(&args[0], &sbi->part)) { - printk(KERN_ERR "hfs: part requires an argument\n"); + pr_err("part requires an argument\n"); return 0; } break; case opt_session: if (match_int(&args[0], &sbi->session)) { - printk(KERN_ERR "hfs: session requires an argument\n"); + pr_err("session requires an argument\n"); return 0; } break; case opt_nls: if (sbi->nls) { - printk(KERN_ERR "hfs: unable to change nls mapping\n"); + pr_err("unable to change nls mapping\n"); return 0; } p = match_strdup(&args[0]); if (p) sbi->nls = load_nls(p); if (!sbi->nls) { - printk(KERN_ERR "hfs: unable to load " + pr_err("unable to load " "nls mapping \"%s\"\n", p); kfree(p); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 7b87284..4c4d142 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -132,7 +132,7 @@ static int hfsplus_system_write_inode(struct inode *inode) if (tree) { int err = hfs_btree_write(tree); if (err) { - printk(KERN_ERR "hfs: b-tree write err: %d, ino %lu\n", + pr_err("b-tree write err: %d, ino %lu\n", err, inode->i_ino); return err; } @@ -145,7 +145,7 @@ static int hfsplus_write_inode(struct inode *inode, { int err; - dprint(DBG_INODE, "hfsplus_write_inode: %lu\n", inode->i_ino); + hfs_dbg(INODE, "hfsplus_write_inode: %lu\n", inode->i_ino); err = hfsplus_ext_write_extent(inode); if (err) @@ -160,7 +160,7 @@ static int hfsplus_write_inode(struct inode *inode, static void hfsplus_evict_inode(struct inode *inode) { - dprint(DBG_INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino); + hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino); truncate_inode_pages(&inode->i_data, 0); clear_inode(inode); if (HFSPLUS_IS_RSRC(inode)) { @@ -179,7 +179,7 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait) if (!wait) return 0; - dprint(DBG_SUPER, "hfsplus_sync_fs\n"); + hfs_dbg(SUPER, "hfsplus_sync_fs\n"); /* * Explicitly write out the special metadata inodes. @@ -251,7 +251,7 @@ static void delayed_sync_fs(struct work_struct *work) err = hfsplus_sync_fs(sbi->alloc_file->i_sb, 1); if (err) - printk(KERN_ERR "hfs: delayed sync fs err %d\n", err); + pr_err("delayed sync fs err %d\n", err); } void hfsplus_mark_mdb_dirty(struct super_block *sb) @@ -275,7 +275,7 @@ static void hfsplus_put_super(struct super_block *sb) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); - dprint(DBG_SUPER, "hfsplus_put_super\n"); + hfs_dbg(SUPER, "hfsplus_put_super\n"); cancel_delayed_work_sync(&sbi->sync_work); @@ -333,25 +333,19 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data) return -EINVAL; if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) { - printk(KERN_WARNING "hfs: filesystem was " - "not cleanly unmounted, " - "running fsck.hfsplus is recommended. " - "leaving read-only.\n"); + pr_warn("filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } else if (force) { /* nothing */ } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) { - printk(KERN_WARNING "hfs: filesystem is marked locked, " - "leaving read-only.\n"); + pr_warn("filesystem is marked locked, leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) { - printk(KERN_WARNING "hfs: filesystem is " - "marked journaled, " - "leaving read-only.\n"); + pr_warn("filesystem is marked journaled, leaving read-only.\n"); sb->s_flags |= MS_RDONLY; *flags |= MS_RDONLY; } @@ -397,7 +391,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) err = -EINVAL; if (!hfsplus_parse_options(data, sbi)) { - printk(KERN_ERR "hfs: unable to parse mount options\n"); + pr_err("unable to parse mount options\n"); goto out_unload_nls; } @@ -405,14 +399,14 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) nls = sbi->nls; sbi->nls = load_nls("utf8"); if (!sbi->nls) { - printk(KERN_ERR "hfs: unable to load nls for utf8\n"); + pr_err("unable to load nls for utf8\n"); goto out_unload_nls; } /* Grab the volume header */ if (hfsplus_read_wrapper(sb)) { if (!silent) - printk(KERN_WARNING "hfs: unable to find HFS+ superblock\n"); + pr_warn("unable to find HFS+ superblock\n"); goto out_unload_nls; } vhdr = sbi->s_vhdr; @@ -421,7 +415,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sb->s_magic = HFSPLUS_VOLHEAD_SIG; if (be16_to_cpu(vhdr->version) < HFSPLUS_MIN_VERSION || be16_to_cpu(vhdr->version) > HFSPLUS_CURRENT_VERSION) { - printk(KERN_ERR "hfs: wrong filesystem version\n"); + pr_err("wrong filesystem version\n"); goto out_free_vhdr; } sbi->total_blocks = be32_to_cpu(vhdr->total_blocks); @@ -445,7 +439,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if ((last_fs_block > (sector_t)(~0ULL) >> (sbi->alloc_blksz_shift - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { - printk(KERN_ERR "hfs: filesystem size too large.\n"); + pr_err("filesystem size too large\n"); goto out_free_vhdr; } @@ -454,22 +448,16 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sb->s_maxbytes = MAX_LFS_FILESIZE; if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) { - printk(KERN_WARNING "hfs: Filesystem was " - "not cleanly unmounted, " - "running fsck.hfsplus is recommended. " - "mounting read-only.\n"); + pr_warn("Filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) { /* nothing */ } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) { - printk(KERN_WARNING "hfs: Filesystem is marked locked, mounting read-only.\n"); + pr_warn("Filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) && !(sb->s_flags & MS_RDONLY)) { - printk(KERN_WARNING "hfs: write access to " - "a journaled filesystem is not supported, " - "use the force option at your own risk, " - "mounting read-only.\n"); + pr_warn("write access to a journaled filesystem is not supported, use the force option at your own risk, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } @@ -478,18 +466,18 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) /* Load metadata objects (B*Trees) */ sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID); if (!sbi->ext_tree) { - printk(KERN_ERR "hfs: failed to load extents file\n"); + pr_err("failed to load extents file\n"); goto out_free_vhdr; } sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID); if (!sbi->cat_tree) { - printk(KERN_ERR "hfs: failed to load catalog file\n"); + pr_err("failed to load catalog file\n"); goto out_close_ext_tree; } if (vhdr->attr_file.total_blocks != 0) { sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID); if (!sbi->attr_tree) { - printk(KERN_ERR "hfs: failed to load attributes file\n"); + pr_err("failed to load attributes file\n"); goto out_close_cat_tree; } } @@ -497,7 +485,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID); if (IS_ERR(inode)) { - printk(KERN_ERR "hfs: failed to load allocation file\n"); + pr_err("failed to load allocation file\n"); err = PTR_ERR(inode); goto out_close_attr_tree; } @@ -506,7 +494,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) /* Load the root directory */ root = hfsplus_iget(sb, HFSPLUS_ROOT_CNID); if (IS_ERR(root)) { - printk(KERN_ERR "hfs: failed to load root directory\n"); + pr_err("failed to load root directory\n"); err = PTR_ERR(root); goto out_put_alloc_file; } diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 90effcc..b51a607 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -156,7 +156,7 @@ static int hfsplus_get_last_session(struct super_block *sb, *start = (sector_t)te.cdte_addr.lba << 2; return 0; } - printk(KERN_ERR "hfs: invalid session number or type of track\n"); + pr_err("invalid session number or type of track\n"); return -EINVAL; } ms_info.addr_format = CDROM_LBA; @@ -234,8 +234,7 @@ reread: error = -EINVAL; if (sbi->s_backup_vhdr->signature != sbi->s_vhdr->signature) { - printk(KERN_WARNING - "hfs: invalid secondary volume header\n"); + pr_warn("invalid secondary volume header\n"); goto out_free_backup_vhdr; } @@ -259,8 +258,7 @@ reread: blocksize >>= 1; if (sb_set_blocksize(sb, blocksize) != blocksize) { - printk(KERN_ERR "hfs: unable to set blocksize to %u!\n", - blocksize); + pr_err("unable to set blocksize to %u!\n", blocksize); goto out_free_backup_vhdr; } diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index e8a4b08..f6634615 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -107,19 +107,19 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd); if (err) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return err; } err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd); if (err) { - printk(KERN_ERR "hfs: catalog searching failed\n"); + pr_err("catalog searching failed\n"); goto end_setxattr; } if (!strcmp_xattr_finder_info(name)) { if (flags & XATTR_CREATE) { - printk(KERN_ERR "hfs: xattr exists yet\n"); + pr_err("xattr exists yet\n"); err = -EOPNOTSUPP; goto end_setxattr; } @@ -165,7 +165,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, if (hfsplus_attr_exists(inode, name)) { if (flags & XATTR_CREATE) { - printk(KERN_ERR "hfs: xattr exists yet\n"); + pr_err("xattr exists yet\n"); err = -EOPNOTSUPP; goto end_setxattr; } @@ -177,7 +177,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, goto end_setxattr; } else { if (flags & XATTR_REPLACE) { - printk(KERN_ERR "hfs: cannot replace xattr\n"); + pr_err("cannot replace xattr\n"); err = -EOPNOTSUPP; goto end_setxattr; } @@ -210,7 +210,7 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, cat_entry_flags); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); } else { - printk(KERN_ERR "hfs: invalid catalog entry type\n"); + pr_err("invalid catalog entry type\n"); err = -EIO; goto end_setxattr; } @@ -269,7 +269,7 @@ static ssize_t hfsplus_getxattr_finder_info(struct dentry *dentry, if (size >= record_len) { res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); if (res) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return res; } res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); @@ -340,13 +340,13 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, entry = hfsplus_alloc_attr_entry(); if (!entry) { - printk(KERN_ERR "hfs: can't allocate xattr entry\n"); + pr_err("can't allocate xattr entry\n"); return -ENOMEM; } res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd); if (res) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); goto failed_getxattr_init; } @@ -355,7 +355,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, if (res == -ENOENT) res = -ENODATA; else - printk(KERN_ERR "hfs: xattr searching failed\n"); + pr_err("xattr searching failed\n"); goto out; } @@ -368,17 +368,17 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, offsetof(struct hfsplus_attr_inline_data, length)); if (record_length > HFSPLUS_MAX_INLINE_DATA_SIZE) { - printk(KERN_ERR "hfs: invalid xattr record size\n"); + pr_err("invalid xattr record size\n"); res = -EIO; goto out; } } else if (record_type == HFSPLUS_ATTR_FORK_DATA || record_type == HFSPLUS_ATTR_EXTENTS) { - printk(KERN_ERR "hfs: only inline data xattr are supported\n"); + pr_err("only inline data xattr are supported\n"); res = -EOPNOTSUPP; goto out; } else { - printk(KERN_ERR "hfs: invalid xattr record\n"); + pr_err("invalid xattr record\n"); res = -EIO; goto out; } @@ -427,7 +427,7 @@ static ssize_t hfsplus_listxattr_finder_info(struct dentry *dentry, res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); if (res) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return res; } @@ -506,7 +506,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd); if (err) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return err; } @@ -525,8 +525,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) for (;;) { key_len = hfs_bnode_read_u16(fd.bnode, fd.keyoffset); if (key_len == 0 || key_len > fd.tree->max_key_len) { - printk(KERN_ERR "hfs: invalid xattr key length: %d\n", - key_len); + pr_err("invalid xattr key length: %d\n", key_len); res = -EIO; goto end_listxattr; } @@ -541,7 +540,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size) if (hfsplus_uni2asc(inode->i_sb, (const struct hfsplus_unistr *)&fd.key->attr.key_name, strbuf, &xattr_name_len)) { - printk(KERN_ERR "hfs: unicode conversion failed\n"); + pr_err("unicode conversion failed\n"); res = -EIO; goto end_listxattr; } @@ -598,13 +597,13 @@ int hfsplus_removexattr(struct dentry *dentry, const char *name) err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd); if (err) { - printk(KERN_ERR "hfs: can't init xattr find struct\n"); + pr_err("can't init xattr find struct\n"); return err; } err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd); if (err) { - printk(KERN_ERR "hfs: catalog searching failed\n"); + pr_err("catalog searching failed\n"); goto end_removexattr; } @@ -643,7 +642,7 @@ int hfsplus_removexattr(struct dentry *dentry, const char *name) flags); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY); } else { - printk(KERN_ERR "hfs: invalid catalog entry type\n"); + pr_err("invalid catalog entry type\n"); err = -EIO; goto end_removexattr; } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6b49f14..cf02f55 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -175,6 +175,11 @@ static int nilfs_writepages(struct address_space *mapping, struct inode *inode = mapping->host; int err = 0; + if (inode->i_sb->s_flags & MS_RDONLY) { + nilfs_clear_dirty_pages(mapping, false); + return -EROFS; + } + if (wbc->sync_mode == WB_SYNC_ALL) err = nilfs_construct_dsync_segment(inode->i_sb, inode, wbc->range_start, @@ -187,6 +192,18 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode = page->mapping->host; int err; + if (inode->i_sb->s_flags & MS_RDONLY) { + /* + * It means that filesystem was remounted in read-only + * mode because of error or metadata corruption. But we + * have dirty pages that try to be flushed in background. + * So, here we simply discard this dirty page. + */ + nilfs_clear_dirty_page(page, false); + unlock_page(page); + return -EROFS; + } + redirty_page_for_writepage(wbc, page); unlock_page(page); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index f9897d0..c4dcd1d 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -375,14 +375,25 @@ int nilfs_mdt_fetch_dirty(struct inode *inode) static int nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc) { - struct inode *inode; + struct inode *inode = page->mapping->host; struct super_block *sb; int err = 0; + if (inode && (inode->i_sb->s_flags & MS_RDONLY)) { + /* + * It means that filesystem was remounted in read-only + * mode because of error or metadata corruption. But we + * have dirty pages that try to be flushed in background. + * So, here we simply discard this dirty page. + */ + nilfs_clear_dirty_page(page, false); + unlock_page(page); + return -EROFS; + } + redirty_page_for_writepage(wbc, page); unlock_page(page); - inode = page->mapping->host; if (!inode) return 0; @@ -561,10 +572,10 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode) if (mi->mi_palloc_cache) nilfs_palloc_clear_cache(inode); - nilfs_clear_dirty_pages(inode->i_mapping); + nilfs_clear_dirty_pages(inode->i_mapping, true); nilfs_copy_back_pages(inode->i_mapping, &shadow->frozen_data); - nilfs_clear_dirty_pages(&ii->i_btnode_cache); + nilfs_clear_dirty_pages(&ii->i_btnode_cache, true); nilfs_copy_back_pages(&ii->i_btnode_cache, &shadow->frozen_btnodes); nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 07f76db..0ba6798 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -370,7 +370,12 @@ repeat: goto repeat; } -void nilfs_clear_dirty_pages(struct address_space *mapping) +/** + * nilfs_clear_dirty_pages - discard dirty pages in address space + * @mapping: address space with dirty pages for discarding + * @silent: suppress [true] or print [false] warning messages + */ +void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) { struct pagevec pvec; unsigned int i; @@ -382,25 +387,9 @@ void nilfs_clear_dirty_pages(struct address_space *mapping) PAGEVEC_SIZE)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; - struct buffer_head *bh, *head; lock_page(page); - ClearPageUptodate(page); - ClearPageMappedToDisk(page); - bh = head = page_buffers(page); - do { - lock_buffer(bh); - clear_buffer_dirty(bh); - clear_buffer_nilfs_volatile(bh); - clear_buffer_nilfs_checked(bh); - clear_buffer_nilfs_redirected(bh); - clear_buffer_uptodate(bh); - clear_buffer_mapped(bh); - unlock_buffer(bh); - bh = bh->b_this_page; - } while (bh != head); - - __nilfs_clear_page_dirty(page); + nilfs_clear_dirty_page(page, silent); unlock_page(page); } pagevec_release(&pvec); @@ -408,6 +397,51 @@ void nilfs_clear_dirty_pages(struct address_space *mapping) } } +/** + * nilfs_clear_dirty_page - discard dirty page + * @page: dirty page that will be discarded + * @silent: suppress [true] or print [false] warning messages + */ +void nilfs_clear_dirty_page(struct page *page, bool silent) +{ + struct inode *inode = page->mapping->host; + struct super_block *sb = inode->i_sb; + + BUG_ON(!PageLocked(page)); + + if (!silent) { + nilfs_warning(sb, __func__, + "discard page: offset %lld, ino %lu", + page_offset(page), inode->i_ino); + } + + ClearPageUptodate(page); + ClearPageMappedToDisk(page); + + if (page_has_buffers(page)) { + struct buffer_head *bh, *head; + + bh = head = page_buffers(page); + do { + lock_buffer(bh); + if (!silent) { + nilfs_warning(sb, __func__, + "discard block %llu, size %zu", + (u64)bh->b_blocknr, bh->b_size); + } + clear_buffer_dirty(bh); + clear_buffer_nilfs_volatile(bh); + clear_buffer_nilfs_checked(bh); + clear_buffer_nilfs_redirected(bh); + clear_buffer_uptodate(bh); + clear_buffer_mapped(bh); + unlock_buffer(bh); + } while (bh = bh->b_this_page, bh != head); + } + + __nilfs_clear_page_dirty(page); +} + unsigned nilfs_page_count_clean_buffers(struct page *page, unsigned from, unsigned to) { diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index fb7de71..ef30c5c 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -55,7 +55,8 @@ void nilfs_page_bug(struct page *); int nilfs_copy_dirty_pages(struct address_space *, struct address_space *); void nilfs_copy_back_pages(struct address_space *, struct address_space *); -void nilfs_clear_dirty_pages(struct address_space *); +void nilfs_clear_dirty_page(struct page *, bool); +void nilfs_clear_dirty_pages(struct address_space *, bool); void nilfs_mapping_init(struct address_space *mapping, struct inode *inode, struct backing_dev_info *bdi); unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 8562bd3..c616a70 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -570,7 +570,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, int add = (arg & IN_MASK_ADD); int ret; - /* don't allow invalid bits: we don't want flags set */ mask = inotify_arg_to_mask(arg); fsn_mark = fsnotify_find_inode_mark(group, inode); @@ -621,7 +620,6 @@ static int inotify_new_watch(struct fsnotify_group *group, struct idr *idr = &group->inotify_data.idr; spinlock_t *idr_lock = &group->inotify_data.idr_lock; - /* don't allow invalid bits: we don't want flags set */ mask = inotify_arg_to_mask(arg); tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL); @@ -747,6 +745,10 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, int ret; unsigned flags = 0; + /* don't allow invalid bits: we don't want flags set */ + if (unlikely(!(mask & ALL_INOTIFY_BITS))) + return -EINVAL; + f = fdget(fd); if (unlikely(!f.file)) return -EBADF; diff --git a/fs/proc/base.c b/fs/proc/base.c index a193086..3861bce 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1348,11 +1348,10 @@ static ssize_t comm_write(struct file *file, const char __user *buf, struct inode *inode = file_inode(file); struct task_struct *p; char buffer[TASK_COMM_LEN]; + const size_t maxlen = sizeof(buffer) - 1; memset(buffer, 0, sizeof(buffer)); - if (count > sizeof(buffer) - 1) - count = sizeof(buffer) - 1; - if (copy_from_user(buffer, buf, count)) + if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count)) return -EFAULT; p = get_proc_task(inode); diff --git a/include/Kbuild b/include/Kbuild index 1dfd33e..bab1145 100644 --- a/include/Kbuild +++ b/include/Kbuild @@ -1,5 +1,2 @@ # Top-level Makefile calls into asm-$(ARCH) # List only non-arch directories below - -header-y += video/ -header-y += scsi/ diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index 42e55de..4ce9056 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -33,7 +33,7 @@ struct cleancache_ops { void (*invalidate_fs)(int); }; -extern struct cleancache_ops +extern struct cleancache_ops * cleancache_register_ops(struct cleancache_ops *ops); extern void __cleancache_init_fs(struct super_block *); extern void __cleancache_init_shared_fs(char *, struct super_block *); @@ -42,9 +42,9 @@ extern void __cleancache_put_page(struct page *); extern void __cleancache_invalidate_page(struct address_space *, struct page *); extern void __cleancache_invalidate_inode(struct address_space *); extern void __cleancache_invalidate_fs(struct super_block *); -extern int cleancache_enabled; #ifdef CONFIG_CLEANCACHE +#define cleancache_enabled (1) static inline bool cleancache_fs_enabled(struct page *page) { return page->mapping->host->i_sb->cleancache_poolid >= 0; diff --git a/include/linux/dmi.h b/include/linux/dmi.h index f156cca..b6eb7a0 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -99,6 +99,7 @@ extern const char * dmi_get_system_info(int field); extern const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from); extern void dmi_scan_machine(void); +extern void dmi_set_dump_stack_arch_desc(void); extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp); extern int dmi_name_in_vendors(const char *str); extern int dmi_name_in_serial(const char *str); @@ -114,6 +115,7 @@ static inline const char * dmi_get_system_info(int field) { return NULL; } static inline const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from) { return NULL; } static inline void dmi_scan_machine(void) { return; } +static inline void dmi_set_dump_stack_arch_desc(void) { } static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp) { if (yearp) diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 3044254..8293262 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -14,7 +14,7 @@ struct frontswap_ops { }; extern bool frontswap_enabled; -extern struct frontswap_ops +extern struct frontswap_ops * frontswap_register_ops(struct frontswap_ops *ops); extern void frontswap_shrink(unsigned long); extern unsigned long frontswap_curr_pages(void); @@ -22,33 +22,19 @@ extern void frontswap_writethrough(bool); #define FRONTSWAP_HAS_EXCLUSIVE_GETS extern void frontswap_tmem_exclusive_gets(bool); -extern void __frontswap_init(unsigned type); +extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); +extern void __frontswap_init(unsigned type, unsigned long *map); extern int __frontswap_store(struct page *page); extern int __frontswap_load(struct page *page); extern void __frontswap_invalidate_page(unsigned, pgoff_t); extern void __frontswap_invalidate_area(unsigned); #ifdef CONFIG_FRONTSWAP +#define frontswap_enabled (1) static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) { - bool ret = false; - - if (frontswap_enabled && sis->frontswap_map) - ret = test_bit(offset, sis->frontswap_map); - return ret; -} - -static inline void frontswap_set(struct swap_info_struct *sis, pgoff_t offset) -{ - if (frontswap_enabled && sis->frontswap_map) - set_bit(offset, sis->frontswap_map); -} - -static inline void frontswap_clear(struct swap_info_struct *sis, pgoff_t offset) -{ - if (frontswap_enabled && sis->frontswap_map) - clear_bit(offset, sis->frontswap_map); + return __frontswap_test(sis, offset); } static inline void frontswap_map_set(struct swap_info_struct *p, @@ -71,14 +57,6 @@ static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) return false; } -static inline void frontswap_set(struct swap_info_struct *sis, pgoff_t offset) -{ -} - -static inline void frontswap_clear(struct swap_info_struct *sis, pgoff_t offset) -{ -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { @@ -120,10 +98,10 @@ static inline void frontswap_invalidate_area(unsigned type) __frontswap_invalidate_area(type); } -static inline void frontswap_init(unsigned type) +static inline void frontswap_init(unsigned type, unsigned long *map) { if (frontswap_enabled) - __frontswap_init(type); + __frontswap_init(type, map); } #endif /* _LINUX_FRONTSWAP_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c28271..17d8b15 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -675,9 +675,11 @@ static inline loff_t i_size_read(const struct inode *inode) static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) + preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); + preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) preempt_disable(); inode->i_size = i_size; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2dac79c..6d1844f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -798,6 +798,4 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD #endif -extern int do_sysinfo(struct sysinfo *info); - #endif diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 5398d58..0555cc6 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -67,16 +67,15 @@ struct subprocess_info { }; extern int -call_usermodehelper_fns(char *path, char **argv, char **envp, int wait, - int (*init)(struct subprocess_info *info, struct cred *new), - void (*cleanup)(struct subprocess_info *), void *data); +call_usermodehelper(char *path, char **argv, char **envp, int wait); -static inline int -call_usermodehelper(char *path, char **argv, char **envp, int wait) -{ - return call_usermodehelper_fns(path, argv, envp, wait, - NULL, NULL, NULL); -} +extern struct subprocess_info * +call_usermodehelper_setup(char *path, char **argv, char **envp, gfp_t gfp_mask, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *), void *data); + +extern int +call_usermodehelper_exec(struct subprocess_info *info, int wait); extern struct ctl_table usermodehelper_table[]; diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 8d81664..7dcef33 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -43,6 +43,7 @@ bool kthread_should_stop(void); bool kthread_should_park(void); bool kthread_freezable_should_stop(bool *was_frozen); void *kthread_data(struct task_struct *k); +void *probe_kthread_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); diff --git a/include/linux/memory.h b/include/linux/memory.h index 73817af..85c31a8 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -137,7 +137,7 @@ enum mem_add_context { BOOT, HOTPLUG }; #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) #else -#define hotplug_memory_notifier(fn, pri) (0) +#define hotplug_memory_notifier(fn, pri) ({ 0; }) /* These aren't inline functions due to a GCC bug. */ #define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) #define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 215e5e3..8ac3283 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -13,7 +13,9 @@ struct pidmap { void *page; }; -#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) +#define BITS_PER_PAGE (PAGE_SIZE * 8) +#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1) +#define PIDMAP_ENTRIES ((PID_MAX_LIMIT+BITS_PER_PAGE-1)/BITS_PER_PAGE) struct bsd_acct_struct; diff --git a/include/linux/printk.h b/include/linux/printk.h index 4890fe6..6af944a 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -145,6 +145,9 @@ extern void wake_up_klogd(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); +void dump_stack_set_arch_desc(const char *fmt, ...); +void dump_stack_print_info(const char *log_lvl); +void show_regs_print_info(const char *log_lvl); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -182,6 +185,18 @@ static inline void log_buf_kexec_setup(void) static inline void setup_log_buf(int early) { } + +static inline void dump_stack_set_arch_desc(const char *fmt, ...) +{ +} + +static inline void dump_stack_print_info(const char *log_lvl) +{ +} + +static inline void show_regs_print_info(const char *log_lvl) +{ +} #endif extern void dump_stack(void) __cold; diff --git a/include/linux/relay.h b/include/linux/relay.h index 91cacc3..d7c8359 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -20,9 +20,6 @@ #include <linux/poll.h> #include <linux/kref.h> -/* Needs a _much_ better name... */ -#define FIX_SIZE(x) ((((x) - 1) & PAGE_MASK) + PAGE_SIZE) - /* * Tracks changes to rchan/rchan_buf structs */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 54ddcb8..6f95004 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -626,6 +626,7 @@ struct signal_struct { #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ +#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ @@ -2248,27 +2249,18 @@ static inline void threadgroup_change_end(struct task_struct *tsk) * * Lock the threadgroup @tsk belongs to. No new task is allowed to enter * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or - * perform exec. This is useful for cases where the threadgroup needs to - * stay stable across blockable operations. + * change ->group_leader/pid. This is useful for cases where the threadgroup + * needs to stay stable across blockable operations. * * fork and exit paths explicitly call threadgroup_change_{begin|end}() for * synchronization. While held, no new task will be added to threadgroup * and no existing live task will have its PF_EXITING set. * - * During exec, a task goes and puts its thread group through unusual - * changes. After de-threading, exclusive access is assumed to resources - * which are usually shared by tasks in the same group - e.g. sighand may - * be replaced with a new one. Also, the exec'ing task takes over group - * leader role including its pid. Exclude these changes while locked by - * grabbing cred_guard_mutex which is used to synchronize exec path. + * de_thread() does threadgroup_change_{begin|end}() when a non-leader + * sub-thread becomes a new leader. */ static inline void threadgroup_lock(struct task_struct *tsk) { - /* - * exec uses exit for de-threading nesting group_rwsem inside - * cred_guard_mutex. Grab cred_guard_mutex first. - */ - mutex_lock(&tsk->signal->cred_guard_mutex); down_write(&tsk->signal->group_rwsem); } @@ -2281,7 +2273,6 @@ static inline void threadgroup_lock(struct task_struct *tsk) static inline void threadgroup_unlock(struct task_struct *tsk) { up_write(&tsk->signal->group_rwsem); - mutex_unlock(&tsk->signal->cred_guard_mutex); } #else static inline void threadgroup_change_begin(struct task_struct *tsk) {} diff --git a/include/linux/smp.h b/include/linux/smp.h index 3e07a7d..e6564c1 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -20,7 +20,6 @@ struct call_single_data { smp_call_func_t func; void *info; u16 flags; - u16 priv; }; /* total number of cpus in this system (may exceed NR_CPUS) */ diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index a3eb2f6..3eeee96 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -13,4 +13,62 @@ enum string_size_units { int string_get_size(u64 size, enum string_size_units units, char *buf, int len); +#define UNESCAPE_SPACE 0x01 +#define UNESCAPE_OCTAL 0x02 +#define UNESCAPE_HEX 0x04 +#define UNESCAPE_SPECIAL 0x08 +#define UNESCAPE_ANY \ + (UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL) + +/** + * string_unescape - unquote characters in the given string + * @src: source buffer (escaped) + * @dst: destination buffer (unescaped) + * @size: size of the destination buffer (0 to unlimit) + * @flags: combination of the flags (bitwise OR): + * %UNESCAPE_SPACE: + * '\f' - form feed + * '\n' - new line + * '\r' - carriage return + * '\t' - horizontal tab + * '\v' - vertical tab + * %UNESCAPE_OCTAL: + * '\NNN' - byte with octal value NNN (1 to 3 digits) + * %UNESCAPE_HEX: + * '\xHH' - byte with hexadecimal value HH (1 to 2 digits) + * %UNESCAPE_SPECIAL: + * '\"' - double quote + * '\\' - backslash + * '\a' - alert (BEL) + * '\e' - escape + * %UNESCAPE_ANY: + * all previous together + * + * Returns amount of characters processed to the destination buffer excluding + * trailing '\0'. + * + * Because the size of the output will be the same as or less than the size of + * the input, the transformation may be performed in place. + * + * Caller must provide valid source and destination pointers. Be aware that + * destination buffer will always be NULL-terminated. Source string must be + * NULL-terminated as well. + */ +int string_unescape(char *src, char *dst, size_t size, unsigned int flags); + +static inline int string_unescape_inplace(char *buf, unsigned int flags) +{ + return string_unescape(buf, buf, 0, flags); +} + +static inline int string_unescape_any(char *src, char *dst, size_t size) +{ + return string_unescape(src, dst, size, UNESCAPE_ANY); +} + +static inline int string_unescape_any_inplace(char *buf) +{ + return string_unescape_any(buf, buf, 0); +} + #endif diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7179756..623488f 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -92,6 +92,9 @@ enum { /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, + + /* maximum string length for set_worker_desc() */ + WORKER_DESC_LEN = 24, }; struct work_struct { @@ -447,6 +450,8 @@ extern void workqueue_set_max_active(struct workqueue_struct *wq, extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); +extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); +extern void print_worker_info(const char *log_lvl, struct task_struct *task); /** * queue_work - queue work on a workqueue diff --git a/include/scsi/Kbuild b/include/scsi/Kbuild deleted file mode 100644 index 562ff9d..0000000 --- a/include/scsi/Kbuild +++ /dev/null @@ -1 +0,0 @@ -header-y += fc/ diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index 022ab18..52ebcc8 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -5,6 +5,7 @@ /* has the defines to get at the registers. */ +#include <linux/types.h> #define PTRACE_TRACEME 0 #define PTRACE_PEEKTEXT 1 @@ -52,6 +53,17 @@ #define PTRACE_INTERRUPT 0x4207 #define PTRACE_LISTEN 0x4208 +#define PTRACE_PEEKSIGINFO 0x4209 + +struct ptrace_peeksiginfo_args { + __u64 off; /* from which siginfo to start */ + __u32 flags; + __s32 nr; /* how may siginfos to take */ +}; + +/* Read signals from a shared (process wide) queue */ +#define PTRACE_PEEKSIGINFO_SHARED (1 << 0) + /* Wait extended result codes for the above trace options. */ #define PTRACE_EVENT_FORK 1 #define PTRACE_EVENT_VFORK 2 diff --git a/include/xen/tmem.h b/include/xen/tmem.h index 591550a..3930a90 100644 --- a/include/xen/tmem.h +++ b/include/xen/tmem.h @@ -3,7 +3,15 @@ #include <linux/types.h> +#ifdef CONFIG_XEN_TMEM_MODULE +#define tmem_enabled true +#else /* defined in drivers/xen/tmem.c */ extern bool tmem_enabled; +#endif + +#ifdef CONFIG_XEN_SELFBALLOONING +extern int xen_selfballoon_init(bool, bool); +#endif #endif /* _XEN_TMEM_H */ diff --git a/init/Kconfig b/init/Kconfig index 4367e13..a76d131 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1221,6 +1221,35 @@ config SYSCTL config ANON_INODES bool +config HAVE_UID16 + bool + +config SYSCTL_EXCEPTION_TRACE + bool + help + Enable support for /proc/sys/debug/exception-trace. + +config SYSCTL_ARCH_UNALIGN_NO_WARN + bool + help + Enable support for /proc/sys/kernel/ignore-unaligned-usertrap + Allows arch to define/use @no_unaligned_warning to possibly warn + about unaligned access emulation going on under the hood. + +config SYSCTL_ARCH_UNALIGN_ALLOW + bool + help + Enable support for /proc/sys/kernel/unaligned-trap + Allows arches to define/use @unaligned_enabled to runtime toggle + the unaligned access emulation. + see arch/parisc/kernel/unaligned.c for reference + +config HOTPLUG + def_bool y + +config HAVE_PCSPKR_PLATFORM + bool + menuconfig EXPERT bool "Configure standard kernel features (expert users)" # Unhide debug options, to make the on-by-default options visible @@ -1231,9 +1260,6 @@ menuconfig EXPERT environments which can tolerate a "non-standard" kernel. Only use this if you really know what you are doing. -config HAVE_UID16 - bool - config UID16 bool "Enable 16-bit UID system calls" if EXPERT depends on HAVE_UID16 @@ -1258,26 +1284,6 @@ config SYSCTL_SYSCALL If unsure say N here. -config SYSCTL_EXCEPTION_TRACE - bool - help - Enable support for /proc/sys/debug/exception-trace. - -config SYSCTL_ARCH_UNALIGN_NO_WARN - bool - help - Enable support for /proc/sys/kernel/ignore-unaligned-usertrap - Allows arch to define/use @no_unaligned_warning to possibly warn - about unaligned access emulation going on under the hood. - -config SYSCTL_ARCH_UNALIGN_ALLOW - bool - help - Enable support for /proc/sys/kernel/unaligned-trap - Allows arches to define/use @unaligned_enabled to runtime toggle - the unaligned access emulation. - see arch/parisc/kernel/unaligned.c for reference - config KALLSYMS bool "Load all symbols for debugging/ksymoops" if EXPERT default y @@ -1303,9 +1309,6 @@ config KALLSYMS_ALL Say N unless you really need all symbols. -config HOTPLUG - def_bool y - config PRINTK default y bool "Enable support for printk" if EXPERT @@ -1344,9 +1347,6 @@ config PCSPKR_PLATFORM This option allows to disable the internal PC-Speaker support, saving some memory. -config HAVE_PCSPKR_PLATFORM - bool - config BASE_FULL default y bool "Enable full-sized data structures for core" if EXPERT @@ -1418,8 +1418,17 @@ config AIO default y help This option enables POSIX asynchronous I/O which may by used - by some high performance threaded applications. Disabling - this option saves about 7k. + by some high performance threaded applications. Disabling + this option saves about 7k. + +config PCI_QUIRKS + default y + bool "Enable PCI quirk workarounds" if EXPERT + depends on PCI + help + This enables workarounds for various PCI chipset + bugs/quirks. Disable this only if your target machine is + unaffected by PCI quirks. config EMBEDDED bool "Embedded system" @@ -1494,15 +1503,6 @@ config VM_EVENT_COUNTERS on EXPERT systems. /proc/vmstat will only show page counts if VM event counters are disabled. -config PCI_QUIRKS - default y - bool "Enable PCI quirk workarounds" if EXPERT - depends on PCI - help - This enables workarounds for various PCI chipset - bugs/quirks. Disable this only if your target machine is - unaffected by PCI quirks. - config SLUB_DEBUG default y bool "Enable SLUB debugging support" if EXPERT diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index a32ec1c..3e0878e 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -50,6 +50,7 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new) static void __init handle_initrd(void) { + struct subprocess_info *info; static char *argv[] = { "linuxrc", NULL, }; extern char *envp_init[]; int error; @@ -70,8 +71,11 @@ static void __init handle_initrd(void) */ current->flags |= PF_FREEZER_SKIP; - call_usermodehelper_fns("/linuxrc", argv, envp_init, UMH_WAIT_PROC, - init_linuxrc, NULL, NULL); + info = call_usermodehelper_setup("/linuxrc", argv, envp_init, + GFP_KERNEL, init_linuxrc, NULL, NULL); + if (!info) + return; + call_usermodehelper_exec(info, UMH_WAIT_PROC); current->flags &= ~PF_FREEZER_SKIP; diff --git a/kernel/compat.c b/kernel/compat.c index 19971d8..1e8f145 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -1138,71 +1138,6 @@ asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, } #endif -struct compat_sysinfo { - s32 uptime; - u32 loads[3]; - u32 totalram; - u32 freeram; - u32 sharedram; - u32 bufferram; - u32 totalswap; - u32 freeswap; - u16 procs; - u16 pad; - u32 totalhigh; - u32 freehigh; - u32 mem_unit; - char _f[20-2*sizeof(u32)-sizeof(int)]; -}; - -asmlinkage long -compat_sys_sysinfo(struct compat_sysinfo __user *info) -{ - struct sysinfo s; - - do_sysinfo(&s); - - /* Check to see if any memory value is too large for 32-bit and scale - * down if needed - */ - if ((s.totalram >> 32) || (s.totalswap >> 32)) { - int bitcount = 0; - - while (s.mem_unit < PAGE_SIZE) { - s.mem_unit <<= 1; - bitcount++; - } - - s.totalram >>= bitcount; - s.freeram >>= bitcount; - s.sharedram >>= bitcount; - s.bufferram >>= bitcount; - s.totalswap >>= bitcount; - s.freeswap >>= bitcount; - s.totalhigh >>= bitcount; - s.freehigh >>= bitcount; - } - - if (!access_ok(VERIFY_WRITE, info, sizeof(struct compat_sysinfo)) || - __put_user (s.uptime, &info->uptime) || - __put_user (s.loads[0], &info->loads[0]) || - __put_user (s.loads[1], &info->loads[1]) || - __put_user (s.loads[2], &info->loads[2]) || - __put_user (s.totalram, &info->totalram) || - __put_user (s.freeram, &info->freeram) || - __put_user (s.sharedram, &info->sharedram) || - __put_user (s.bufferram, &info->bufferram) || - __put_user (s.totalswap, &info->totalswap) || - __put_user (s.freeswap, &info->freeswap) || - __put_user (s.procs, &info->procs) || - __put_user (s.totalhigh, &info->totalhigh) || - __put_user (s.freehigh, &info->freehigh) || - __put_user (s.mem_unit, &info->mem_unit)) - return -EFAULT; - - return 0; -} - COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, compat_pid_t, pid, struct compat_timespec __user *, interval) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index c26278f..0506d44 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -775,7 +775,7 @@ static void sysrq_handle_dbg(int key) static struct sysrq_key_op sysrq_dbg_op = { .handler = sysrq_handle_dbg, - .help_msg = "debug(G)", + .help_msg = "debug(g)", .action_msg = "DEBUG", }; #endif diff --git a/kernel/kexec.c b/kernel/kexec.c index b574920..59f7b55 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -786,7 +786,7 @@ static int kimage_load_normal_segment(struct kimage *image, struct kexec_segment *segment) { unsigned long maddr; - unsigned long ubytes, mbytes; + size_t ubytes, mbytes; int result; unsigned char __user *buf; @@ -819,13 +819,9 @@ static int kimage_load_normal_segment(struct kimage *image, /* Start with a clear page */ clear_page(ptr); ptr += maddr & ~PAGE_MASK; - mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK); - if (mchunk > mbytes) - mchunk = mbytes; - - uchunk = mchunk; - if (uchunk > ubytes) - uchunk = ubytes; + mchunk = min_t(size_t, mbytes, + PAGE_SIZE - (maddr & ~PAGE_MASK)); + uchunk = min(ubytes, mchunk); result = copy_from_user(ptr, buf, uchunk); kunmap(page); @@ -850,7 +846,7 @@ static int kimage_load_crash_segment(struct kimage *image, * We do things a page at a time for the sake of kmap. */ unsigned long maddr; - unsigned long ubytes, mbytes; + size_t ubytes, mbytes; int result; unsigned char __user *buf; @@ -871,13 +867,10 @@ static int kimage_load_crash_segment(struct kimage *image, } ptr = kmap(page); ptr += maddr & ~PAGE_MASK; - mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK); - if (mchunk > mbytes) - mchunk = mbytes; - - uchunk = mchunk; - if (uchunk > ubytes) { - uchunk = ubytes; + mchunk = min_t(size_t, mbytes, + PAGE_SIZE - (maddr & ~PAGE_MASK)); + uchunk = min(ubytes, mchunk); + if (mchunk > uchunk) { /* Zero the trailing part of the page */ memset(ptr + uchunk, 0, mchunk - uchunk); } @@ -1540,14 +1533,13 @@ void vmcoreinfo_append_str(const char *fmt, ...) { va_list args; char buf[0x50]; - int r; + size_t r; va_start(args, fmt); r = vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); - if (r + vmcoreinfo_size > vmcoreinfo_max_size) - r = vmcoreinfo_max_size - vmcoreinfo_size; + r = min(r, vmcoreinfo_max_size - vmcoreinfo_size); memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); diff --git a/kernel/kmod.c b/kernel/kmod.c index 56dd349..1296e72 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -77,6 +77,7 @@ static void free_modprobe_argv(struct subprocess_info *info) static int call_modprobe(char *module_name, int wait) { + struct subprocess_info *info; static char *envp[] = { "HOME=/", "TERM=linux", @@ -98,8 +99,15 @@ static int call_modprobe(char *module_name, int wait) argv[3] = module_name; /* check free_modprobe_argv() */ argv[4] = NULL; - return call_usermodehelper_fns(modprobe_path, argv, envp, - wait | UMH_KILLABLE, NULL, free_modprobe_argv, NULL); + info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL, + NULL, free_modprobe_argv, NULL); + if (!info) + goto free_module_name; + + return call_usermodehelper_exec(info, wait | UMH_KILLABLE); + +free_module_name: + kfree(module_name); free_argv: kfree(argv); out: @@ -502,14 +510,28 @@ static void helper_unlock(void) * @argv: arg vector for process * @envp: environment for process * @gfp_mask: gfp mask for memory allocation + * @cleanup: a cleanup function + * @init: an init function + * @data: arbitrary context sensitive data * * Returns either %NULL on allocation failure, or a subprocess_info * structure. This should be passed to call_usermodehelper_exec to * exec the process and free the structure. + * + * The init function is used to customize the helper process prior to + * exec. A non-zero return code causes the process to error out, exit, + * and return the failure to the calling process + * + * The cleanup function is just before ethe subprocess_info is about to + * be freed. This can be used for freeing the argv and envp. The + * Function must be runnable in either a process context or the + * context in which call_usermodehelper_exec is called. */ -static struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, - char **envp, gfp_t gfp_mask) + char **envp, gfp_t gfp_mask, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *info), + void *data) { struct subprocess_info *sub_info; sub_info = kzalloc(sizeof(struct subprocess_info), gfp_mask); @@ -520,50 +542,27 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, sub_info->path = path; sub_info->argv = argv; sub_info->envp = envp; + + sub_info->cleanup = cleanup; + sub_info->init = init; + sub_info->data = data; out: return sub_info; } - -/** - * call_usermodehelper_setfns - set a cleanup/init function - * @info: a subprocess_info returned by call_usermodehelper_setup - * @cleanup: a cleanup function - * @init: an init function - * @data: arbitrary context sensitive data - * - * The init function is used to customize the helper process prior to - * exec. A non-zero return code causes the process to error out, exit, - * and return the failure to the calling process - * - * The cleanup function is just before ethe subprocess_info is about to - * be freed. This can be used for freeing the argv and envp. The - * Function must be runnable in either a process context or the - * context in which call_usermodehelper_exec is called. - */ -static -void call_usermodehelper_setfns(struct subprocess_info *info, - int (*init)(struct subprocess_info *info, struct cred *new), - void (*cleanup)(struct subprocess_info *info), - void *data) -{ - info->cleanup = cleanup; - info->init = init; - info->data = data; -} +EXPORT_SYMBOL(call_usermodehelper_setup); /** * call_usermodehelper_exec - start a usermode application * @sub_info: information about the subprocessa * @wait: wait for the application to finish and return status. - * when -1 don't wait at all, but you get no useful error back when - * the program couldn't be exec'ed. This makes it safe to call + * when UMH_NO_WAIT don't wait at all, but you get no useful error back + * when the program couldn't be exec'ed. This makes it safe to call * from interrupt context. * * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of keventd. * (ie. it runs with full root capabilities). */ -static int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { DECLARE_COMPLETION_ONSTACK(done); @@ -615,31 +614,34 @@ unlock: helper_unlock(); return retval; } +EXPORT_SYMBOL(call_usermodehelper_exec); -/* - * call_usermodehelper_fns() will not run the caller-provided cleanup function - * if a memory allocation failure is experienced. So the caller might need to - * check the call_usermodehelper_fns() return value: if it is -ENOMEM, perform - * the necessaary cleanup within the caller. +/** + * call_usermodehelper() - prepare and start a usermode application + * @path: path to usermode executable + * @argv: arg vector for process + * @envp: environment for process + * @wait: wait for the application to finish and return status. + * when UMH_NO_WAIT don't wait at all, but you get no useful error back + * when the program couldn't be exec'ed. This makes it safe to call + * from interrupt context. + * + * This function is the equivalent to use call_usermodehelper_setup() and + * call_usermodehelper_exec(). */ -int call_usermodehelper_fns( - char *path, char **argv, char **envp, int wait, - int (*init)(struct subprocess_info *info, struct cred *new), - void (*cleanup)(struct subprocess_info *), void *data) +int call_usermodehelper(char *path, char **argv, char **envp, int wait) { struct subprocess_info *info; gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; - info = call_usermodehelper_setup(path, argv, envp, gfp_mask); - + info = call_usermodehelper_setup(path, argv, envp, gfp_mask, + NULL, NULL, NULL); if (info == NULL) return -ENOMEM; - call_usermodehelper_setfns(info, init, cleanup, data); - return call_usermodehelper_exec(info, wait); } -EXPORT_SYMBOL(call_usermodehelper_fns); +EXPORT_SYMBOL(call_usermodehelper); static int proc_cap_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) diff --git a/kernel/kthread.c b/kernel/kthread.c index 16d8ddd..760e86d 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/freezer.h> #include <linux/ptrace.h> +#include <linux/uaccess.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); @@ -135,6 +136,24 @@ void *kthread_data(struct task_struct *task) return to_kthread(task)->data; } +/** + * probe_kthread_data - speculative version of kthread_data() + * @task: possible kthread task in question + * + * @task could be a kthread task. Return the data value specified when it + * was created if accessible. If @task isn't a kthread task or its data is + * inaccessible for any reason, %NULL is returned. This function requires + * that @task itself is safe to dereference. + */ +void *probe_kthread_data(struct task_struct *task) +{ + struct kthread *kthread = to_kthread(task); + void *data = NULL; + + probe_kernel_read(&data, &kthread->data, sizeof(data)); + return data; +} + static void __kthread_parkme(struct kthread *self) { __set_current_state(TASK_PARKED); diff --git a/kernel/panic.c b/kernel/panic.c index 7c57cc9..167ec097 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -22,7 +22,6 @@ #include <linux/sysrq.h> #include <linux/init.h> #include <linux/nmi.h> -#include <linux/dmi.h> #define PANIC_TIMER_STEP 100 #define PANIC_BLINK_SPD 18 @@ -400,13 +399,8 @@ struct slowpath_args { static void warn_slowpath_common(const char *file, int line, void *caller, unsigned taint, struct slowpath_args *args) { - const char *board; - printk(KERN_WARNING "------------[ cut here ]------------\n"); printk(KERN_WARNING "WARNING: at %s:%d %pS()\n", file, line, caller); - board = dmi_get_system_info(DMI_PRODUCT_NAME); - if (board) - printk(KERN_WARNING "Hardware name: %s\n", board); if (args) vprintk(args->fmt, args->args); diff --git a/kernel/pid.c b/kernel/pid.c index 047dc62..6283d64 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -51,9 +51,6 @@ int pid_max = PID_MAX_DEFAULT; int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; -#define BITS_PER_PAGE (PAGE_SIZE*8) -#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1) - static inline int mk_pid(struct pid_namespace *pid_ns, struct pidmap *map, int off) { @@ -183,15 +180,19 @@ static int alloc_pidmap(struct pid_namespace *pid_ns) break; } if (likely(atomic_read(&map->nr_free))) { - do { + for ( ; ; ) { if (!test_and_set_bit(offset, map->page)) { atomic_dec(&map->nr_free); set_last_pid(pid_ns, last, pid); return pid; } offset = find_next_offset(map, offset); + if (offset >= BITS_PER_PAGE) + break; pid = mk_pid(pid_ns, map, offset); - } while (offset < BITS_PER_PAGE && pid < pid_max); + if (pid >= pid_max) + break; + } } if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) { ++map; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index bea15bd..69473c4 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -19,8 +19,6 @@ #include <linux/reboot.h> #include <linux/export.h> -#define BITS_PER_PAGE (PAGE_SIZE*8) - struct pid_cache { int nr_ids; char name[16]; diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c index 68197a4..7ef6866 100644 --- a/kernel/power/poweroff.c +++ b/kernel/power/poweroff.c @@ -32,7 +32,7 @@ static void handle_poweroff(int key) static struct sysrq_key_op sysrq_poweroff_op = { .handler = handle_poweroff, - .help_msg = "powerOff", + .help_msg = "poweroff(o)", .action_msg = "Power Off", .enable_mask = SYSRQ_ENABLE_BOOT, }; diff --git a/kernel/printk.c b/kernel/printk.c index 376914e..96dcfcd 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -43,6 +43,7 @@ #include <linux/rculist.h> #include <linux/poll.h> #include <linux/irq_work.h> +#include <linux/utsname.h> #include <asm/uaccess.h> @@ -2849,4 +2850,65 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper) raw_spin_unlock_irqrestore(&logbuf_lock, flags); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); + +static char dump_stack_arch_desc_str[128]; + +/** + * dump_stack_set_arch_desc - set arch-specific str to show with task dumps + * @fmt: printf-style format string + * @...: arguments for the format string + * + * The configured string will be printed right after utsname during task + * dumps. Usually used to add arch-specific system identifiers. If an + * arch wants to make use of such an ID string, it should initialize this + * as soon as possible during boot. + */ +void __init dump_stack_set_arch_desc(const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsnprintf(dump_stack_arch_desc_str, sizeof(dump_stack_arch_desc_str), + fmt, args); + va_end(args); +} + +/** + * dump_stack_print_info - print generic debug info for dump_stack() + * @log_lvl: log level + * + * Arch-specific dump_stack() implementations can use this function to + * print out the same debug information as the generic dump_stack(). + */ +void dump_stack_print_info(const char *log_lvl) +{ + printk("%sCPU: %d PID: %d Comm: %.20s %s %s %.*s\n", + log_lvl, raw_smp_processor_id(), current->pid, current->comm, + print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + + if (dump_stack_arch_desc_str[0] != '\0') + printk("%sHardware name: %s\n", + log_lvl, dump_stack_arch_desc_str); + + print_worker_info(log_lvl, current); +} + +/** + * show_regs_print_info - print generic debug info for show_regs() + * @log_lvl: log level + * + * show_regs() implementations can use this function to print out generic + * debug information. + */ +void show_regs_print_info(const char *log_lvl) +{ + dump_stack_print_info(log_lvl); + + printk("%stask: %p ti: %p task.ti: %p\n", + log_lvl, current, current_thread_info(), + task_thread_info(current)); +} + #endif diff --git a/kernel/ptrace.c b/kernel/ptrace.c index acbd284..17ae54d 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -24,6 +24,7 @@ #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> +#include <linux/compat.h> static int ptrace_trapping_sleep_fn(void *flags) @@ -618,6 +619,81 @@ static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info) return error; } +static int ptrace_peek_siginfo(struct task_struct *child, + unsigned long addr, + unsigned long data) +{ + struct ptrace_peeksiginfo_args arg; + struct sigpending *pending; + struct sigqueue *q; + int ret, i; + + ret = copy_from_user(&arg, (void __user *) addr, + sizeof(struct ptrace_peeksiginfo_args)); + if (ret) + return -EFAULT; + + if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED) + return -EINVAL; /* unknown flags */ + + if (arg.nr < 0) + return -EINVAL; + + if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) + pending = &child->signal->shared_pending; + else + pending = &child->pending; + + for (i = 0; i < arg.nr; ) { + siginfo_t info; + s32 off = arg.off + i; + + spin_lock_irq(&child->sighand->siglock); + list_for_each_entry(q, &pending->list, list) { + if (!off--) { + copy_siginfo(&info, &q->info); + break; + } + } + spin_unlock_irq(&child->sighand->siglock); + + if (off >= 0) /* beyond the end of the list */ + break; + +#ifdef CONFIG_COMPAT + if (unlikely(is_compat_task())) { + compat_siginfo_t __user *uinfo = compat_ptr(data); + + ret = copy_siginfo_to_user32(uinfo, &info); + ret |= __put_user(info.si_code, &uinfo->si_code); + } else +#endif + { + siginfo_t __user *uinfo = (siginfo_t __user *) data; + + ret = copy_siginfo_to_user(uinfo, &info); + ret |= __put_user(info.si_code, &uinfo->si_code); + } + + if (ret) { + ret = -EFAULT; + break; + } + + data += sizeof(siginfo_t); + i++; + + if (signal_pending(current)) + break; + + cond_resched(); + } + + if (i > 0) + return i; + + return ret; +} #ifdef PTRACE_SINGLESTEP #define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) @@ -748,6 +824,10 @@ int ptrace_request(struct task_struct *child, long request, ret = put_user(child->ptrace_message, datalp); break; + case PTRACE_PEEKSIGINFO: + ret = ptrace_peek_siginfo(child, addr, data); + break; + case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) diff --git a/kernel/range.c b/kernel/range.c index 9b8ae2d..071b0ab 100644 --- a/kernel/range.c +++ b/kernel/range.c @@ -97,7 +97,8 @@ void subtract_range(struct range *range, int az, u64 start, u64 end) range[i].end = range[j].end; range[i].start = end; } else { - printk(KERN_ERR "run of slot in ranges\n"); + pr_err("%s: run out of slot in ranges\n", + __func__); } range[j].end = start; continue; diff --git a/kernel/relay.c b/kernel/relay.c index 01ab081..eef0d11 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -588,7 +588,7 @@ struct rchan *relay_open(const char *base_filename, chan->version = RELAYFS_CHANNEL_VERSION; chan->n_subbufs = n_subbufs; chan->subbuf_size = subbuf_size; - chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs); + chan->alloc_size = PAGE_ALIGN(subbuf_size * n_subbufs); chan->parent = parent; chan->private_data = private_data; if (base_filename) { @@ -1099,8 +1099,7 @@ static size_t relay_file_read_end_pos(struct rchan_buf *buf, static int subbuf_read_actor(size_t read_start, struct rchan_buf *buf, size_t avail, - read_descriptor_t *desc, - read_actor_t actor) + read_descriptor_t *desc) { void *from; int ret = 0; @@ -1121,15 +1120,13 @@ static int subbuf_read_actor(size_t read_start, typedef int (*subbuf_actor_t) (size_t read_start, struct rchan_buf *buf, size_t avail, - read_descriptor_t *desc, - read_actor_t actor); + read_descriptor_t *desc); /* * relay_file_read_subbufs - read count bytes, bridging subbuf boundaries */ static ssize_t relay_file_read_subbufs(struct file *filp, loff_t *ppos, subbuf_actor_t subbuf_actor, - read_actor_t actor, read_descriptor_t *desc) { struct rchan_buf *buf = filp->private_data; @@ -1150,7 +1147,7 @@ static ssize_t relay_file_read_subbufs(struct file *filp, loff_t *ppos, break; avail = min(desc->count, avail); - ret = subbuf_actor(read_start, buf, avail, desc, actor); + ret = subbuf_actor(read_start, buf, avail, desc); if (desc->error < 0) break; @@ -1174,8 +1171,7 @@ static ssize_t relay_file_read(struct file *filp, desc.count = count; desc.arg.buf = buffer; desc.error = 0; - return relay_file_read_subbufs(filp, ppos, subbuf_read_actor, - NULL, &desc); + return relay_file_read_subbufs(filp, ppos, subbuf_read_actor, &desc); } static void relay_consume_bytes(struct rchan_buf *rbuf, int bytes_consumed) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c70a881..5662f58 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4586,6 +4586,7 @@ void sched_show_task(struct task_struct *p) task_pid_nr(p), ppid, (unsigned long)task_thread_info(p)->flags); + print_worker_info(KERN_INFO, p); show_stack(p, NULL); } diff --git a/kernel/semaphore.c b/kernel/semaphore.c index 4567fc0..6815171 100644 --- a/kernel/semaphore.c +++ b/kernel/semaphore.c @@ -193,7 +193,7 @@ EXPORT_SYMBOL(up); struct semaphore_waiter { struct list_head list; struct task_struct *task; - int up; + bool up; }; /* @@ -209,12 +209,12 @@ static inline int __sched __down_common(struct semaphore *sem, long state, list_add_tail(&waiter.list, &sem->wait_list); waiter.task = task; - waiter.up = 0; + waiter.up = false; for (;;) { if (signal_pending_state(state, task)) goto interrupted; - if (timeout <= 0) + if (unlikely(timeout <= 0)) goto timed_out; __set_task_state(task, state); raw_spin_unlock_irq(&sem->lock); @@ -258,6 +258,6 @@ static noinline void __sched __up(struct semaphore *sem) struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list, struct semaphore_waiter, list); list_del(&waiter->list); - waiter->up = 1; + waiter->up = true; wake_up_process(waiter->task); } diff --git a/kernel/signal.c b/kernel/signal.c index 598dc06..cede589 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -854,12 +854,14 @@ static void ptrace_trap_notify(struct task_struct *t) * Returns true if the signal should be actually delivered, otherwise * it should be dropped. */ -static int prepare_signal(int sig, struct task_struct *p, bool force) +static bool prepare_signal(int sig, struct task_struct *p, bool force) { struct signal_struct *signal = p->signal; struct task_struct *t; - if (unlikely(signal->flags & SIGNAL_GROUP_EXIT)) { + if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) { + if (signal->flags & SIGNAL_GROUP_COREDUMP) + return sig == SIGKILL; /* * The process is in the middle of dying, nothing to do. */ @@ -1160,8 +1162,7 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, static void print_fatal_signal(int signr) { struct pt_regs *regs = signal_pt_regs(); - printk(KERN_INFO "%s/%d: potentially unexpected fatal signal %d.\n", - current->comm, task_pid_nr(current), signr); + printk(KERN_INFO "potentially unexpected fatal signal %d.\n", signr); #if defined(__i386__) && !defined(__arch_um__) printk(KERN_INFO "code at %08lx: ", regs->ip); diff --git a/kernel/smp.c b/kernel/smp.c index 8e451f3..4dba0f7 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -100,16 +100,16 @@ void __init call_function_init(void) * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ -static void csd_lock_wait(struct call_single_data *data) +static void csd_lock_wait(struct call_single_data *csd) { - while (data->flags & CSD_FLAG_LOCK) + while (csd->flags & CSD_FLAG_LOCK) cpu_relax(); } -static void csd_lock(struct call_single_data *data) +static void csd_lock(struct call_single_data *csd) { - csd_lock_wait(data); - data->flags = CSD_FLAG_LOCK; + csd_lock_wait(csd); + csd->flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment @@ -119,16 +119,16 @@ static void csd_lock(struct call_single_data *data) smp_mb(); } -static void csd_unlock(struct call_single_data *data) +static void csd_unlock(struct call_single_data *csd) { - WARN_ON(!(data->flags & CSD_FLAG_LOCK)); + WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_mb(); - data->flags &= ~CSD_FLAG_LOCK; + csd->flags &= ~CSD_FLAG_LOCK; } /* @@ -137,7 +137,7 @@ static void csd_unlock(struct call_single_data *data) * ->func, ->info, and ->flags set. */ static -void generic_exec_single(int cpu, struct call_single_data *data, int wait) +void generic_exec_single(int cpu, struct call_single_data *csd, int wait) { struct call_single_queue *dst = &per_cpu(call_single_queue, cpu); unsigned long flags; @@ -145,7 +145,7 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait) raw_spin_lock_irqsave(&dst->lock, flags); ipi = list_empty(&dst->list); - list_add_tail(&data->list, &dst->list); + list_add_tail(&csd->list, &dst->list); raw_spin_unlock_irqrestore(&dst->lock, flags); /* @@ -163,7 +163,7 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait) arch_send_call_function_single_ipi(cpu); if (wait) - csd_lock_wait(data); + csd_lock_wait(csd); } /* @@ -173,7 +173,6 @@ void generic_exec_single(int cpu, struct call_single_data *data, int wait) void generic_smp_call_function_single_interrupt(void) { struct call_single_queue *q = &__get_cpu_var(call_single_queue); - unsigned int data_flags; LIST_HEAD(list); /* @@ -186,25 +185,26 @@ void generic_smp_call_function_single_interrupt(void) raw_spin_unlock(&q->lock); while (!list_empty(&list)) { - struct call_single_data *data; + struct call_single_data *csd; + unsigned int csd_flags; - data = list_entry(list.next, struct call_single_data, list); - list_del(&data->list); + csd = list_entry(list.next, struct call_single_data, list); + list_del(&csd->list); /* - * 'data' can be invalid after this call if flags == 0 + * 'csd' can be invalid after this call if flags == 0 * (when called through generic_exec_single()), * so save them away before making the call: */ - data_flags = data->flags; + csd_flags = csd->flags; - data->func(data->info); + csd->func(csd->info); /* * Unlocked CSDs are valid through generic_exec_single(): */ - if (data_flags & CSD_FLAG_LOCK) - csd_unlock(data); + if (csd_flags & CSD_FLAG_LOCK) + csd_unlock(csd); } } @@ -249,16 +249,16 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, local_irq_restore(flags); } else { if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) { - struct call_single_data *data = &d; + struct call_single_data *csd = &d; if (!wait) - data = &__get_cpu_var(csd_data); + csd = &__get_cpu_var(csd_data); - csd_lock(data); + csd_lock(csd); - data->func = func; - data->info = info; - generic_exec_single(cpu, data, wait); + csd->func = func; + csd->info = info; + generic_exec_single(cpu, csd, wait); } else { err = -ENXIO; /* CPU not online */ } @@ -325,7 +325,7 @@ EXPORT_SYMBOL_GPL(smp_call_function_any); * pre-allocated data structure. Useful for embedding @data inside * other structures, for instance. */ -void __smp_call_function_single(int cpu, struct call_single_data *data, +void __smp_call_function_single(int cpu, struct call_single_data *csd, int wait) { unsigned int this_cpu; @@ -343,11 +343,11 @@ void __smp_call_function_single(int cpu, struct call_single_data *data, if (cpu == this_cpu) { local_irq_save(flags); - data->func(data->info); + csd->func(csd->info); local_irq_restore(flags); } else { - csd_lock(data); - generic_exec_single(cpu, data, wait); + csd_lock(csd); + generic_exec_single(cpu, csd, wait); } put_cpu(); } @@ -369,7 +369,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *data, void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { - struct call_function_data *data; + struct call_function_data *cfd; int cpu, next_cpu, this_cpu = smp_processor_id(); /* @@ -401,24 +401,24 @@ void smp_call_function_many(const struct cpumask *mask, return; } - data = &__get_cpu_var(cfd_data); + cfd = &__get_cpu_var(cfd_data); - cpumask_and(data->cpumask, mask, cpu_online_mask); - cpumask_clear_cpu(this_cpu, data->cpumask); + cpumask_and(cfd->cpumask, mask, cpu_online_mask); + cpumask_clear_cpu(this_cpu, cfd->cpumask); /* Some callers race with other cpus changing the passed mask */ - if (unlikely(!cpumask_weight(data->cpumask))) + if (unlikely(!cpumask_weight(cfd->cpumask))) return; /* - * After we put an entry into the list, data->cpumask - * may be cleared again when another CPU sends another IPI for - * a SMP function call, so data->cpumask will be zero. + * After we put an entry into the list, cfd->cpumask may be cleared + * again when another CPU sends another IPI for a SMP function call, so + * cfd->cpumask will be zero. */ - cpumask_copy(data->cpumask_ipi, data->cpumask); + cpumask_copy(cfd->cpumask_ipi, cfd->cpumask); - for_each_cpu(cpu, data->cpumask) { - struct call_single_data *csd = per_cpu_ptr(data->csd, cpu); + for_each_cpu(cpu, cfd->cpumask) { + struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu); struct call_single_queue *dst = &per_cpu(call_single_queue, cpu); unsigned long flags; @@ -433,12 +433,13 @@ void smp_call_function_many(const struct cpumask *mask, } /* Send a message to all CPUs in the map */ - arch_send_call_function_ipi_mask(data->cpumask_ipi); + arch_send_call_function_ipi_mask(cfd->cpumask_ipi); if (wait) { - for_each_cpu(cpu, data->cpumask) { - struct call_single_data *csd = - per_cpu_ptr(data->csd, cpu); + for_each_cpu(cpu, cfd->cpumask) { + struct call_single_data *csd; + + csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } diff --git a/kernel/softirq.c b/kernel/softirq.c index 14d7758..aa82723 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -620,8 +620,7 @@ static void remote_softirq_receive(void *data) unsigned long flags; int softirq; - softirq = cp->priv; - + softirq = *(int *)cp->info; local_irq_save(flags); __local_trigger(cp, softirq); local_irq_restore(flags); @@ -631,9 +630,8 @@ static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softir { if (cpu_online(cpu)) { cp->func = remote_softirq_receive; - cp->info = cp; + cp->info = &softirq; cp->flags = 0; - cp->priv = softirq; __smp_call_function_single(cpu, cp, 0); return 0; diff --git a/kernel/sys.c b/kernel/sys.c index 0da73cf..afd0f7e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -49,6 +49,11 @@ #include <linux/user_namespace.h> #include <linux/binfmts.h> +#include <linux/sched.h> +#include <linux/rcupdate.h> +#include <linux/uidgid.h> +#include <linux/cred.h> + #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> @@ -1044,6 +1049,67 @@ change_okay: return old_fsgid; } +/** + * sys_getpid - return the thread group id of the current process + * + * Note, despite the name, this returns the tgid not the pid. The tgid and + * the pid are identical unless CLONE_THREAD was specified on clone() in + * which case the tgid is the same in all threads of the same group. + * + * This is SMP safe as current->tgid does not change. + */ +SYSCALL_DEFINE0(getpid) +{ + return task_tgid_vnr(current); +} + +/* Thread ID - the internal kernel "pid" */ +SYSCALL_DEFINE0(gettid) +{ + return task_pid_vnr(current); +} + +/* + * Accessing ->real_parent is not SMP-safe, it could + * change from under us. However, we can use a stale + * value of ->real_parent under rcu_read_lock(), see + * release_task()->call_rcu(delayed_put_task_struct). + */ +SYSCALL_DEFINE0(getppid) +{ + int pid; + + rcu_read_lock(); + pid = task_tgid_vnr(rcu_dereference(current->real_parent)); + rcu_read_unlock(); + + return pid; +} + +SYSCALL_DEFINE0(getuid) +{ + /* Only we change this so SMP safe */ + return from_kuid_munged(current_user_ns(), current_uid()); +} + +SYSCALL_DEFINE0(geteuid) +{ + /* Only we change this so SMP safe */ + return from_kuid_munged(current_user_ns(), current_euid()); +} + +SYSCALL_DEFINE0(getgid) +{ + /* Only we change this so SMP safe */ + return from_kgid_munged(current_user_ns(), current_gid()); +} + +SYSCALL_DEFINE0(getegid) +{ + /* Only we change this so SMP safe */ + return from_kgid_munged(current_user_ns(), current_egid()); +} + void do_sys_times(struct tms *tms) { cputime_t tgutime, tgstime, cutime, cstime; @@ -1791,7 +1857,6 @@ SYSCALL_DEFINE1(umask, int, mask) return mask; } -#ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { struct fd exe; @@ -1985,17 +2050,12 @@ out: return error; } +#ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) { return put_user(me->clear_child_tid, tid_addr); } - -#else /* CONFIG_CHECKPOINT_RESTORE */ -static int prctl_set_mm(int opt, unsigned long addr, - unsigned long arg4, unsigned long arg5) -{ - return -EINVAL; -} +#else static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) { return -EINVAL; @@ -2245,3 +2305,148 @@ int orderly_poweroff(bool force) return 0; } EXPORT_SYMBOL_GPL(orderly_poweroff); + +/** + * do_sysinfo - fill in sysinfo struct + * @info: pointer to buffer to fill + */ +static int do_sysinfo(struct sysinfo *info) +{ + unsigned long mem_total, sav_total; + unsigned int mem_unit, bitcount; + struct timespec tp; + + memset(info, 0, sizeof(struct sysinfo)); + + ktime_get_ts(&tp); + monotonic_to_bootbased(&tp); + info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); + + get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); + + info->procs = nr_threads; + + si_meminfo(info); + si_swapinfo(info); + + /* + * If the sum of all the available memory (i.e. ram + swap) + * is less than can be stored in a 32 bit unsigned long then + * we can be binary compatible with 2.2.x kernels. If not, + * well, in that case 2.2.x was broken anyways... + * + * -Erik Andersen <andersee@debian.org> + */ + + mem_total = info->totalram + info->totalswap; + if (mem_total < info->totalram || mem_total < info->totalswap) + goto out; + bitcount = 0; + mem_unit = info->mem_unit; + while (mem_unit > 1) { + bitcount++; + mem_unit >>= 1; + sav_total = mem_total; + mem_total <<= 1; + if (mem_total < sav_total) + goto out; + } + + /* + * If mem_total did not overflow, multiply all memory values by + * info->mem_unit and set it to 1. This leaves things compatible + * with 2.2.x, and also retains compatibility with earlier 2.4.x + * kernels... + */ + + info->mem_unit = 1; + info->totalram <<= bitcount; + info->freeram <<= bitcount; + info->sharedram <<= bitcount; + info->bufferram <<= bitcount; + info->totalswap <<= bitcount; + info->freeswap <<= bitcount; + info->totalhigh <<= bitcount; + info->freehigh <<= bitcount; + +out: + return 0; +} + +SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) +{ + struct sysinfo val; + + do_sysinfo(&val); + + if (copy_to_user(info, &val, sizeof(struct sysinfo))) + return -EFAULT; + + return 0; +} + +#ifdef CONFIG_COMPAT +struct compat_sysinfo { + s32 uptime; + u32 loads[3]; + u32 totalram; + u32 freeram; + u32 sharedram; + u32 bufferram; + u32 totalswap; + u32 freeswap; + u16 procs; + u16 pad; + u32 totalhigh; + u32 freehigh; + u32 mem_unit; + char _f[20-2*sizeof(u32)-sizeof(int)]; +}; + +COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) +{ + struct sysinfo s; + + do_sysinfo(&s); + + /* Check to see if any memory value is too large for 32-bit and scale + * down if needed + */ + if ((s.totalram >> 32) || (s.totalswap >> 32)) { + int bitcount = 0; + + while (s.mem_unit < PAGE_SIZE) { + s.mem_unit <<= 1; + bitcount++; + } + + s.totalram >>= bitcount; + s.freeram >>= bitcount; + s.sharedram >>= bitcount; + s.bufferram >>= bitcount; + s.totalswap >>= bitcount; + s.freeswap >>= bitcount; + s.totalhigh >>= bitcount; + s.freehigh >>= bitcount; + } + + if (!access_ok(VERIFY_WRITE, info, sizeof(struct compat_sysinfo)) || + __put_user(s.uptime, &info->uptime) || + __put_user(s.loads[0], &info->loads[0]) || + __put_user(s.loads[1], &info->loads[1]) || + __put_user(s.loads[2], &info->loads[2]) || + __put_user(s.totalram, &info->totalram) || + __put_user(s.freeram, &info->freeram) || + __put_user(s.sharedram, &info->sharedram) || + __put_user(s.bufferram, &info->bufferram) || + __put_user(s.totalswap, &info->totalswap) || + __put_user(s.freeswap, &info->freeswap) || + __put_user(s.procs, &info->procs) || + __put_user(s.totalhigh, &info->totalhigh) || + __put_user(s.freehigh, &info->freehigh) || + __put_user(s.mem_unit, &info->mem_unit)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_COMPAT */ diff --git a/kernel/timer.c b/kernel/timer.c index dbf7a78..09bca8c 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1,7 +1,7 @@ /* * linux/kernel/timer.c * - * Kernel internal timers, basic process system calls + * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * @@ -41,6 +41,7 @@ #include <linux/sched.h> #include <linux/sched/sysctl.h> #include <linux/slab.h> +#include <linux/compat.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -1395,61 +1396,6 @@ SYSCALL_DEFINE1(alarm, unsigned int, seconds) #endif -/** - * sys_getpid - return the thread group id of the current process - * - * Note, despite the name, this returns the tgid not the pid. The tgid and - * the pid are identical unless CLONE_THREAD was specified on clone() in - * which case the tgid is the same in all threads of the same group. - * - * This is SMP safe as current->tgid does not change. - */ -SYSCALL_DEFINE0(getpid) -{ - return task_tgid_vnr(current); -} - -/* - * Accessing ->real_parent is not SMP-safe, it could - * change from under us. However, we can use a stale - * value of ->real_parent under rcu_read_lock(), see - * release_task()->call_rcu(delayed_put_task_struct). - */ -SYSCALL_DEFINE0(getppid) -{ - int pid; - - rcu_read_lock(); - pid = task_tgid_vnr(rcu_dereference(current->real_parent)); - rcu_read_unlock(); - - return pid; -} - -SYSCALL_DEFINE0(getuid) -{ - /* Only we change this so SMP safe */ - return from_kuid_munged(current_user_ns(), current_uid()); -} - -SYSCALL_DEFINE0(geteuid) -{ - /* Only we change this so SMP safe */ - return from_kuid_munged(current_user_ns(), current_euid()); -} - -SYSCALL_DEFINE0(getgid) -{ - /* Only we change this so SMP safe */ - return from_kgid_munged(current_user_ns(), current_gid()); -} - -SYSCALL_DEFINE0(getegid) -{ - /* Only we change this so SMP safe */ - return from_kgid_munged(current_user_ns(), current_egid()); -} - static void process_timeout(unsigned long __data) { wake_up_process((struct task_struct *)__data); @@ -1557,91 +1503,6 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout) } EXPORT_SYMBOL(schedule_timeout_uninterruptible); -/* Thread ID - the internal kernel "pid" */ -SYSCALL_DEFINE0(gettid) -{ - return task_pid_vnr(current); -} - -/** - * do_sysinfo - fill in sysinfo struct - * @info: pointer to buffer to fill - */ -int do_sysinfo(struct sysinfo *info) -{ - unsigned long mem_total, sav_total; - unsigned int mem_unit, bitcount; - struct timespec tp; - - memset(info, 0, sizeof(struct sysinfo)); - - ktime_get_ts(&tp); - monotonic_to_bootbased(&tp); - info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); - - get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); - - info->procs = nr_threads; - - si_meminfo(info); - si_swapinfo(info); - - /* - * If the sum of all the available memory (i.e. ram + swap) - * is less than can be stored in a 32 bit unsigned long then - * we can be binary compatible with 2.2.x kernels. If not, - * well, in that case 2.2.x was broken anyways... - * - * -Erik Andersen <andersee@debian.org> - */ - - mem_total = info->totalram + info->totalswap; - if (mem_total < info->totalram || mem_total < info->totalswap) - goto out; - bitcount = 0; - mem_unit = info->mem_unit; - while (mem_unit > 1) { - bitcount++; - mem_unit >>= 1; - sav_total = mem_total; - mem_total <<= 1; - if (mem_total < sav_total) - goto out; - } - - /* - * If mem_total did not overflow, multiply all memory values by - * info->mem_unit and set it to 1. This leaves things compatible - * with 2.2.x, and also retains compatibility with earlier 2.4.x - * kernels... - */ - - info->mem_unit = 1; - info->totalram <<= bitcount; - info->freeram <<= bitcount; - info->sharedram <<= bitcount; - info->bufferram <<= bitcount; - info->totalswap <<= bitcount; - info->freeswap <<= bitcount; - info->totalhigh <<= bitcount; - info->freehigh <<= bitcount; - -out: - return 0; -} - -SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) -{ - struct sysinfo val; - - do_sysinfo(&val); - - if (copy_to_user(info, &val, sizeof(struct sysinfo))) - return -EFAULT; - - return 0; -} - static int __cpuinit init_timers_cpu(int cpu) { int j; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 154aa12..4aa9f5b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -46,6 +46,7 @@ #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> +#include <linux/uaccess.h> #include "workqueue_internal.h" @@ -2197,6 +2198,7 @@ __acquires(&pool->lock) worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; + worker->desc_valid = false; pwq_dec_nr_in_flight(pwq, work_color); } @@ -4365,6 +4367,83 @@ unsigned int work_busy(struct work_struct *work) } EXPORT_SYMBOL_GPL(work_busy); +/** + * set_worker_desc - set description for the current work item + * @fmt: printf-style format string + * @...: arguments for the format string + * + * This function can be called by a running work function to describe what + * the work item is about. If the worker task gets dumped, this + * information will be printed out together to help debugging. The + * description can be at most WORKER_DESC_LEN including the trailing '\0'. + */ +void set_worker_desc(const char *fmt, ...) +{ + struct worker *worker = current_wq_worker(); + va_list args; + + if (worker) { + va_start(args, fmt); + vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); + va_end(args); + worker->desc_valid = true; + } +} + +/** + * print_worker_info - print out worker information and description + * @log_lvl: the log level to use when printing + * @task: target task + * + * If @task is a worker and currently executing a work item, print out the + * name of the workqueue being serviced and worker description set with + * set_worker_desc() by the currently executing work item. + * + * This function can be safely called on any task as long as the + * task_struct itself is accessible. While safe, this function isn't + * synchronized and may print out mixups or garbages of limited length. + */ +void print_worker_info(const char *log_lvl, struct task_struct *task) +{ + work_func_t *fn = NULL; + char name[WQ_NAME_LEN] = { }; + char desc[WORKER_DESC_LEN] = { }; + struct pool_workqueue *pwq = NULL; + struct workqueue_struct *wq = NULL; + bool desc_valid = false; + struct worker *worker; + + if (!(task->flags & PF_WQ_WORKER)) + return; + + /* + * This function is called without any synchronization and @task + * could be in any state. Be careful with dereferences. + */ + worker = probe_kthread_data(task); + + /* + * Carefully copy the associated workqueue's workfn and name. Keep + * the original last '\0' in case the original contains garbage. + */ + probe_kernel_read(&fn, &worker->current_func, sizeof(fn)); + probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq)); + probe_kernel_read(&wq, &pwq->wq, sizeof(wq)); + probe_kernel_read(name, wq->name, sizeof(name) - 1); + + /* copy worker description */ + probe_kernel_read(&desc_valid, &worker->desc_valid, sizeof(desc_valid)); + if (desc_valid) + probe_kernel_read(desc, worker->desc, sizeof(desc) - 1); + + if (fn || name[0] || desc[0]) { + printk("%sWorkqueue: %s %pf", log_lvl, name, fn); + if (desc[0]) + pr_cont(" (%s)", desc); + pr_cont("\n"); + } +} + /* * CPU hotplug. * diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 84ab6e1..ad83c96 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -29,15 +29,25 @@ struct worker { struct work_struct *current_work; /* L: work being processed */ work_func_t current_func; /* L: current_work's fn */ struct pool_workqueue *current_pwq; /* L: current_work's pwq */ + bool desc_valid; /* ->desc is valid */ struct list_head scheduled; /* L: scheduled works */ + + /* 64 bytes boundary on 64bit, 32 on 32bit */ + struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* I: the associated pool */ /* L: for rescuers */ - /* 64 bytes boundary on 64bit, 32 on 32bit */ + unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ + /* + * Opaque string set with work_set_desc(). Printed out with task + * dump for debugging - WARN, BUG, panic or sysrq. + */ + char desc[WORKER_DESC_LEN]; + /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 28be08c..566cf2b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1192,7 +1192,7 @@ config MEMORY_NOTIFIER_ERROR_INJECT bash: echo: write error: Cannot allocate memory To compile this code as a module, choose M here: the module will - be called pSeries-reconfig-notifier-error-inject. + be called memory-notifier-error-inject. If unsure, say N. @@ -1209,7 +1209,7 @@ config OF_RECONFIG_NOTIFIER_ERROR_INJECT notified, write the error code to "actions/<notifier event>/error". To compile this code as a module, choose M here: the module will - be called memory-notifier-error-inject. + be called of-reconfig-notifier-error-inject. If unsure, say N. @@ -1292,6 +1292,24 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. +config ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + bool + +config DEBUG_STRICT_USER_COPY_CHECKS + bool "Strict user copy size checks" + depends on ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING + help + Enabling this option turns a certain set of sanity checks for user + copy operations into compile time failures. + + The copy_from_user() etc checks are there to help test if there + are sufficient security checks on the length argument of + the copy operation, by having gcc prove that the argument is + within bounds. + + If unsure, say N. + source mm/Kconfig.debug source kernel/trace/Kconfig @@ -1463,5 +1481,8 @@ source "lib/Kconfig.kgdb" source "lib/Kconfig.kmemcheck" +config TEST_STRING_HELPERS + tristate "Test functions located in the string_helpers module at runtime" + config TEST_KSTRTOX tristate "Test kstrto*() family of functions at runtime" diff --git a/lib/Makefile b/lib/Makefile index 6e2cc56..e9c52e1b 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -15,6 +15,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o +obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o @@ -22,8 +23,10 @@ lib-y += kobject.o klist.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ - string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o \ + gcd.o lcm.o list_sort.o uuid.o flex_array.o \ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o +obj-y += string_helpers.o +obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o obj-y += kstrtox.o obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o diff --git a/lib/decompress.c b/lib/decompress.c index 31a8042..f8fdeda 100644 --- a/lib/decompress.c +++ b/lib/decompress.c @@ -38,7 +38,7 @@ struct compress_format { decompress_fn decompressor; }; -static const struct compress_format compressed_formats[] __initdata = { +static const struct compress_format compressed_formats[] __initconst = { { {037, 0213}, "gzip", gunzip }, { {037, 0236}, "gzip", gunzip }, { {0x42, 0x5a}, "bzip2", bunzip2 }, diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 42f4f55..53bad09 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -5,11 +5,16 @@ #include <linux/kernel.h> #include <linux/export.h> +#include <linux/sched.h> +/** + * dump_stack - dump the current task information and its stack trace + * + * Architectures can override this implementation by implementing its own. + */ void dump_stack(void) { - printk(KERN_NOTICE - "This architecture does not implement dump_stack()\n"); + dump_stack_print_info(KERN_DEFAULT); + show_stack(NULL, NULL); } - EXPORT_SYMBOL(dump_stack); diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 4603245..99fec3a 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -24,6 +24,7 @@ #include <linux/sysctl.h> #include <linux/ctype.h> #include <linux/string.h> +#include <linux/string_helpers.h> #include <linux/uaccess.h> #include <linux/dynamic_debug.h> #include <linux/debugfs.h> @@ -276,47 +277,6 @@ static inline int parse_lineno(const char *str, unsigned int *val) return 0; } -/* - * Undo octal escaping in a string, inplace. This is useful to - * allow the user to express a query which matches a format - * containing embedded spaces. - */ -static char *unescape(char *str) -{ - char *in = str; - char *out = str; - - while (*in) { - if (*in == '\\') { - if (in[1] == '\\') { - *out++ = '\\'; - in += 2; - continue; - } else if (in[1] == 't') { - *out++ = '\t'; - in += 2; - continue; - } else if (in[1] == 'n') { - *out++ = '\n'; - in += 2; - continue; - } else if (isodigit(in[1]) && - isodigit(in[2]) && - isodigit(in[3])) { - *out++ = (((in[1] - '0') << 6) | - ((in[2] - '0') << 3) | - (in[3] - '0')); - in += 4; - continue; - } - } - *out++ = *in++; - } - *out = '\0'; - - return str; -} - static int check_set(const char **dest, char *src, char *name) { int rc = 0; @@ -370,8 +330,10 @@ static int ddebug_parse_query(char *words[], int nwords, } else if (!strcmp(words[i], "module")) { rc = check_set(&query->module, words[i+1], "module"); } else if (!strcmp(words[i], "format")) { - rc = check_set(&query->format, unescape(words[i+1]), - "format"); + string_unescape_inplace(words[i+1], UNESCAPE_SPACE | + UNESCAPE_OCTAL | + UNESCAPE_SPECIAL); + rc = check_set(&query->format, words[i+1], "format"); } else if (!strcmp(words[i], "line")) { char *first = words[i+1]; char *last = strchr(first, '-'); diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c index af38aed..122f02f 100644 --- a/lib/rbtree_test.c +++ b/lib/rbtree_test.c @@ -117,8 +117,7 @@ static int black_path_count(struct rb_node *rb) static void check(int nr_nodes) { struct rb_node *rb; - int count = 0; - int blacks = 0; + int count = 0, blacks = 0; u32 prev_key = 0; for (rb = rb_first(&root); rb; rb = rb_next(rb)) { @@ -134,7 +133,9 @@ static void check(int nr_nodes) prev_key = node->key; count++; } + WARN_ON_ONCE(count != nr_nodes); + WARN_ON_ONCE(count < (1 << black_path_count(rb_last(&root))) - 1); } static void check_augmented(int nr_nodes) @@ -148,7 +149,7 @@ static void check_augmented(int nr_nodes) } } -static int rbtree_test_init(void) +static int __init rbtree_test_init(void) { int i, j; cycles_t time1, time2, time; @@ -221,7 +222,7 @@ static int rbtree_test_init(void) return -EAGAIN; /* Fail will directly unload the module */ } -static void rbtree_test_exit(void) +static void __exit rbtree_test_exit(void) { printk(KERN_ALERT "test exit\n"); } diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 1cffc22..ed5c145 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -2,10 +2,12 @@ * Helpers for formatting and printing strings * * Copyright 31 August 2008 James Bottomley + * Copyright (C) 2013, Intel Corporation */ #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> +#include <linux/ctype.h> #include <linux/string_helpers.h> /** @@ -66,3 +68,134 @@ int string_get_size(u64 size, const enum string_size_units units, return 0; } EXPORT_SYMBOL(string_get_size); + +static bool unescape_space(char **src, char **dst) +{ + char *p = *dst, *q = *src; + + switch (*q) { + case 'n': + *p = '\n'; + break; + case 'r': + *p = '\r'; + break; + case 't': + *p = '\t'; + break; + case 'v': + *p = '\v'; + break; + case 'f': + *p = '\f'; + break; + default: + return false; + } + *dst += 1; + *src += 1; + return true; +} + +static bool unescape_octal(char **src, char **dst) +{ + char *p = *dst, *q = *src; + u8 num; + + if (isodigit(*q) == 0) + return false; + + num = (*q++) & 7; + while (num < 32 && isodigit(*q) && (q - *src < 3)) { + num <<= 3; + num += (*q++) & 7; + } + *p = num; + *dst += 1; + *src = q; + return true; +} + +static bool unescape_hex(char **src, char **dst) +{ + char *p = *dst, *q = *src; + int digit; + u8 num; + + if (*q++ != 'x') + return false; + + num = digit = hex_to_bin(*q++); + if (digit < 0) + return false; + + digit = hex_to_bin(*q); + if (digit >= 0) { + q++; + num = (num << 4) | digit; + } + *p = num; + *dst += 1; + *src = q; + return true; +} + +static bool unescape_special(char **src, char **dst) +{ + char *p = *dst, *q = *src; + + switch (*q) { + case '\"': + *p = '\"'; + break; + case '\\': + *p = '\\'; + break; + case 'a': + *p = '\a'; + break; + case 'e': + *p = '\e'; + break; + default: + return false; + } + *dst += 1; + *src += 1; + return true; +} + +int string_unescape(char *src, char *dst, size_t size, unsigned int flags) +{ + char *out = dst; + + while (*src && --size) { + if (src[0] == '\\' && src[1] != '\0' && size > 1) { + src++; + size--; + + if (flags & UNESCAPE_SPACE && + unescape_space(&src, &out)) + continue; + + if (flags & UNESCAPE_OCTAL && + unescape_octal(&src, &out)) + continue; + + if (flags & UNESCAPE_HEX && + unescape_hex(&src, &out)) + continue; + + if (flags & UNESCAPE_SPECIAL && + unescape_special(&src, &out)) + continue; + + *out++ = '\\'; + } + *out++ = *src++; + } + *out = '\0'; + + return out - dst; +} +EXPORT_SYMBOL(string_unescape); diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c new file mode 100644 index 0000000..6ac48de --- /dev/null +++ b/lib/test-string_helpers.c @@ -0,0 +1,103 @@ +/* + * Test cases for lib/string_helpers.c module. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/string.h> +#include <linux/string_helpers.h> + +struct test_string { + const char *in; + const char *out; + unsigned int flags; +}; + +static const struct test_string strings[] __initconst = { + { + .in = "\\f\\ \\n\\r\\t\\v", + .out = "\f\\ \n\r\t\v", + .flags = UNESCAPE_SPACE, + }, + { + .in = "\\40\\1\\387\\0064\\05\\040\\8a\\110\\777", + .out = " \001\00387\0064\005 \\8aH?7", + .flags = UNESCAPE_OCTAL, + }, + { + .in = "\\xv\\xa\\x2c\\xD\\x6f2", + .out = "\\xv\n,\ro2", + .flags = UNESCAPE_HEX, + }, + { + .in = "\\h\\\\\\\"\\a\\e\\", + .out = "\\h\\\"\a\e\\", + .flags = UNESCAPE_SPECIAL, + }, +}; + +static void __init test_string_unescape(unsigned int flags, bool inplace) +{ + char in[256]; + char out_test[256]; + char out_real[256]; + int i, p = 0, q_test = 0, q_real = sizeof(out_real); + + for (i = 0; i < ARRAY_SIZE(strings); i++) { + const char *s = strings[i].in; + int len = strlen(strings[i].in); + + /* Copy string to in buffer */ + memcpy(&in[p], s, len); + p += len; + + /* Copy expected result for given flags */ + if (flags & strings[i].flags) { + s = strings[i].out; + len = strlen(strings[i].out); + } + memcpy(&out_test[q_test], s, len); + q_test += len; + } + in[p++] = '\0'; + + /* Call string_unescape and compare result */ + if (inplace) { + memcpy(out_real, in, p); + if (flags == UNESCAPE_ANY) + q_real = string_unescape_any_inplace(out_real); + else + q_real = string_unescape_inplace(out_real, flags); + } else if (flags == UNESCAPE_ANY) { + q_real = string_unescape_any(in, out_real, q_real); + } else { + q_real = string_unescape(in, out_real, q_real, flags); + } + + if (q_real != q_test || memcmp(out_test, out_real, q_test)) { + pr_warn("Test failed: flags = %u\n", flags); + print_hex_dump(KERN_WARNING, "Input: ", + DUMP_PREFIX_NONE, 16, 1, in, p - 1, true); + print_hex_dump(KERN_WARNING, "Expected: ", + DUMP_PREFIX_NONE, 16, 1, out_test, q_test, true); + print_hex_dump(KERN_WARNING, "Got: ", + DUMP_PREFIX_NONE, 16, 1, out_real, q_real, true); + } +} + +static int __init test_string_helpers_init(void) +{ + unsigned int i; + + pr_info("Running tests...\n"); + for (i = 0; i < UNESCAPE_ANY + 1; i++) + test_string_unescape(i, false); + test_string_unescape(get_random_int() % (UNESCAPE_ANY + 1), true); + + return -EINVAL; +} +module_init(test_string_helpers_init); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/arch/s390/lib/usercopy.c b/lib/usercopy.c index 14b363f..4f5b1dd 100644 --- a/arch/s390/lib/usercopy.c +++ b/lib/usercopy.c @@ -1,5 +1,6 @@ -#include <linux/module.h> +#include <linux/export.h> #include <linux/bug.h> +#include <linux/uaccess.h> void copy_from_user_overflow(void) { diff --git a/mm/cleancache.c b/mm/cleancache.c index d76ba74..5875f48 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -19,20 +19,10 @@ #include <linux/cleancache.h> /* - * This global enablement flag may be read thousands of times per second - * by cleancache_get/put/invalidate even on systems where cleancache_ops - * is not claimed (e.g. cleancache is config'ed on but remains - * disabled), so is preferred to the slower alternative: a function - * call that checks a non-global. - */ -int cleancache_enabled __read_mostly; -EXPORT_SYMBOL(cleancache_enabled); - -/* * cleancache_ops is set by cleancache_ops_register to contain the pointers * to the cleancache "backend" implementation functions. */ -static struct cleancache_ops cleancache_ops __read_mostly; +static struct cleancache_ops *cleancache_ops __read_mostly; /* * Counters available via /sys/kernel/debug/frontswap (if debugfs is @@ -45,15 +35,101 @@ static u64 cleancache_puts; static u64 cleancache_invalidates; /* - * register operations for cleancache, returning previous thus allowing - * detection of multiple backends and possible nesting + * When no backend is registered all calls to init_fs and init_shared_fs + * are registered and fake poolids (FAKE_FS_POOLID_OFFSET or + * FAKE_SHARED_FS_POOLID_OFFSET, plus offset in the respective array + * [shared_|]fs_poolid_map) are given to the respective super block + * (sb->cleancache_poolid) and no tmem_pools are created. When a backend + * registers with cleancache the previous calls to init_fs and init_shared_fs + * are executed to create tmem_pools and set the respective poolids. While no + * backend is registered all "puts", "gets" and "flushes" are ignored or failed. + */ +#define MAX_INITIALIZABLE_FS 32 +#define FAKE_FS_POOLID_OFFSET 1000 +#define FAKE_SHARED_FS_POOLID_OFFSET 2000 + +#define FS_NO_BACKEND (-1) +#define FS_UNKNOWN (-2) +static int fs_poolid_map[MAX_INITIALIZABLE_FS]; +static int shared_fs_poolid_map[MAX_INITIALIZABLE_FS]; +static char *uuids[MAX_INITIALIZABLE_FS]; +/* + * Mutex for the [shared_|]fs_poolid_map to guard against multiple threads + * invoking umount (and ending in __cleancache_invalidate_fs) and also multiple + * threads calling mount (and ending up in __cleancache_init_[shared|]fs). + */ +static DEFINE_MUTEX(poolid_mutex); +/* + * When set to false (default) all calls to the cleancache functions, except + * the __cleancache_invalidate_fs and __cleancache_init_[shared|]fs are guarded + * by the if (!cleancache_ops) return. This means multiple threads (from + * different filesystems) will be checking cleancache_ops. The usage of a + * bool instead of a atomic_t or a bool guarded by a spinlock is OK - we are + * OK if the time between the backend's have been initialized (and + * cleancache_ops has been set to not NULL) and when the filesystems start + * actually calling the backends. The inverse (when unloading) is obviously + * not good - but this shim does not do that (yet). + */ + +/* + * The backends and filesystems work all asynchronously. This is b/c the + * backends can be built as modules. + * The usual sequence of events is: + * a) mount / -> __cleancache_init_fs is called. We set the + * [shared_|]fs_poolid_map and uuids for. + * + * b). user does I/Os -> we call the rest of __cleancache_* functions + * which return immediately as cleancache_ops is false. + * + * c). modprobe zcache -> cleancache_register_ops. We init the backend + * and set cleancache_ops to true, and for any fs_poolid_map + * (which is set by __cleancache_init_fs) we initialize the poolid. + * + * d). user does I/Os -> now that cleancache_ops is true all the + * __cleancache_* functions can call the backend. They all check + * that fs_poolid_map is valid and if so invoke the backend. + * + * e). umount / -> __cleancache_invalidate_fs, the fs_poolid_map is + * reset (which is the second check in the __cleancache_* ops + * to call the backend). + * + * The sequence of event could also be c), followed by a), and d). and e). The + * c) would not happen anymore. There is also the chance of c), and one thread + * doing a) + d), and another doing e). For that case we depend on the + * filesystem calling __cleancache_invalidate_fs in the proper sequence (so + * that it handles all I/Os before it invalidates the fs (which is last part + * of unmounting process). + * + * Note: The acute reader will notice that there is no "rmmod zcache" case. + * This is b/c the functionality for that is not yet implemented and when + * done, will require some extra locking not yet devised. + */ + +/* + * Register operations for cleancache, returning previous thus allowing + * detection of multiple backends and possible nesting. */ -struct cleancache_ops cleancache_register_ops(struct cleancache_ops *ops) +struct cleancache_ops *cleancache_register_ops(struct cleancache_ops *ops) { - struct cleancache_ops old = cleancache_ops; + struct cleancache_ops *old = cleancache_ops; + int i; - cleancache_ops = *ops; - cleancache_enabled = 1; + mutex_lock(&poolid_mutex); + for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { + if (fs_poolid_map[i] == FS_NO_BACKEND) + fs_poolid_map[i] = ops->init_fs(PAGE_SIZE); + if (shared_fs_poolid_map[i] == FS_NO_BACKEND) + shared_fs_poolid_map[i] = ops->init_shared_fs + (uuids[i], PAGE_SIZE); + } + /* + * We MUST set cleancache_ops _after_ we have called the backends + * init_fs or init_shared_fs functions. Otherwise the compiler might + * re-order where cleancache_ops is set in this function. + */ + barrier(); + cleancache_ops = ops; + mutex_unlock(&poolid_mutex); return old; } EXPORT_SYMBOL(cleancache_register_ops); @@ -61,15 +137,42 @@ EXPORT_SYMBOL(cleancache_register_ops); /* Called by a cleancache-enabled filesystem at time of mount */ void __cleancache_init_fs(struct super_block *sb) { - sb->cleancache_poolid = (*cleancache_ops.init_fs)(PAGE_SIZE); + int i; + + mutex_lock(&poolid_mutex); + for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { + if (fs_poolid_map[i] == FS_UNKNOWN) { + sb->cleancache_poolid = i + FAKE_FS_POOLID_OFFSET; + if (cleancache_ops) + fs_poolid_map[i] = cleancache_ops->init_fs(PAGE_SIZE); + else + fs_poolid_map[i] = FS_NO_BACKEND; + break; + } + } + mutex_unlock(&poolid_mutex); } EXPORT_SYMBOL(__cleancache_init_fs); /* Called by a cleancache-enabled clustered filesystem at time of mount */ void __cleancache_init_shared_fs(char *uuid, struct super_block *sb) { - sb->cleancache_poolid = - (*cleancache_ops.init_shared_fs)(uuid, PAGE_SIZE); + int i; + + mutex_lock(&poolid_mutex); + for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { + if (shared_fs_poolid_map[i] == FS_UNKNOWN) { + sb->cleancache_poolid = i + FAKE_SHARED_FS_POOLID_OFFSET; + uuids[i] = uuid; + if (cleancache_ops) + shared_fs_poolid_map[i] = cleancache_ops->init_shared_fs + (uuid, PAGE_SIZE); + else + shared_fs_poolid_map[i] = FS_NO_BACKEND; + break; + } + } + mutex_unlock(&poolid_mutex); } EXPORT_SYMBOL(__cleancache_init_shared_fs); @@ -99,27 +202,53 @@ static int cleancache_get_key(struct inode *inode, } /* + * Returns a pool_id that is associated with a given fake poolid. + */ +static int get_poolid_from_fake(int fake_pool_id) +{ + if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) + return shared_fs_poolid_map[fake_pool_id - + FAKE_SHARED_FS_POOLID_OFFSET]; + else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) + return fs_poolid_map[fake_pool_id - FAKE_FS_POOLID_OFFSET]; + return FS_NO_BACKEND; +} + +/* * "Get" data from cleancache associated with the poolid/inode/index * that were specified when the data was put to cleanache and, if * successful, use it to fill the specified page with data and return 0. * The pageframe is unchanged and returns -1 if the get fails. * Page must be locked by caller. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. */ int __cleancache_get_page(struct page *page) { int ret = -1; int pool_id; + int fake_pool_id; struct cleancache_filekey key = { .u.key = { 0 } }; + if (!cleancache_ops) { + cleancache_failed_gets++; + goto out; + } + VM_BUG_ON(!PageLocked(page)); - pool_id = page->mapping->host->i_sb->cleancache_poolid; - if (pool_id < 0) + fake_pool_id = page->mapping->host->i_sb->cleancache_poolid; + if (fake_pool_id < 0) goto out; + pool_id = get_poolid_from_fake(fake_pool_id); if (cleancache_get_key(page->mapping->host, &key) < 0) goto out; - ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page); + if (pool_id >= 0) + ret = cleancache_ops->get_page(pool_id, + key, page->index, page); if (ret == 0) cleancache_succ_gets++; else @@ -134,17 +263,32 @@ EXPORT_SYMBOL(__cleancache_get_page); * (previously-obtained per-filesystem) poolid and the page's, * inode and page index. Page must be locked. Note that a put_page * always "succeeds", though a subsequent get_page may succeed or fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. */ void __cleancache_put_page(struct page *page) { int pool_id; + int fake_pool_id; struct cleancache_filekey key = { .u.key = { 0 } }; + if (!cleancache_ops) { + cleancache_puts++; + return; + } + VM_BUG_ON(!PageLocked(page)); - pool_id = page->mapping->host->i_sb->cleancache_poolid; + fake_pool_id = page->mapping->host->i_sb->cleancache_poolid; + if (fake_pool_id < 0) + return; + + pool_id = get_poolid_from_fake(fake_pool_id); + if (pool_id >= 0 && - cleancache_get_key(page->mapping->host, &key) >= 0) { - (*cleancache_ops.put_page)(pool_id, key, page->index, page); + cleancache_get_key(page->mapping->host, &key) >= 0) { + cleancache_ops->put_page(pool_id, key, page->index, page); cleancache_puts++; } } @@ -153,19 +297,31 @@ EXPORT_SYMBOL(__cleancache_put_page); /* * Invalidate any data from cleancache associated with the poolid and the * page's inode and page index so that a subsequent "get" will fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. */ void __cleancache_invalidate_page(struct address_space *mapping, struct page *page) { /* careful... page->mapping is NULL sometimes when this is called */ - int pool_id = mapping->host->i_sb->cleancache_poolid; + int pool_id; + int fake_pool_id = mapping->host->i_sb->cleancache_poolid; struct cleancache_filekey key = { .u.key = { 0 } }; - if (pool_id >= 0) { + if (!cleancache_ops) + return; + + if (fake_pool_id >= 0) { + pool_id = get_poolid_from_fake(fake_pool_id); + if (pool_id < 0) + return; + VM_BUG_ON(!PageLocked(page)); if (cleancache_get_key(mapping->host, &key) >= 0) { - (*cleancache_ops.invalidate_page)(pool_id, - key, page->index); + cleancache_ops->invalidate_page(pool_id, + key, page->index); cleancache_invalidates++; } } @@ -176,34 +332,63 @@ EXPORT_SYMBOL(__cleancache_invalidate_page); * Invalidate all data from cleancache associated with the poolid and the * mappings's inode so that all subsequent gets to this poolid/inode * will fail. + * + * The function has two checks before any action is taken - whether + * a backend is registered and whether the sb->cleancache_poolid + * is correct. */ void __cleancache_invalidate_inode(struct address_space *mapping) { - int pool_id = mapping->host->i_sb->cleancache_poolid; + int pool_id; + int fake_pool_id = mapping->host->i_sb->cleancache_poolid; struct cleancache_filekey key = { .u.key = { 0 } }; + if (!cleancache_ops) + return; + + if (fake_pool_id < 0) + return; + + pool_id = get_poolid_from_fake(fake_pool_id); + if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0) - (*cleancache_ops.invalidate_inode)(pool_id, key); + cleancache_ops->invalidate_inode(pool_id, key); } EXPORT_SYMBOL(__cleancache_invalidate_inode); /* * Called by any cleancache-enabled filesystem at time of unmount; - * note that pool_id is surrendered and may be reutrned by a subsequent - * cleancache_init_fs or cleancache_init_shared_fs + * note that pool_id is surrendered and may be returned by a subsequent + * cleancache_init_fs or cleancache_init_shared_fs. */ void __cleancache_invalidate_fs(struct super_block *sb) { - if (sb->cleancache_poolid >= 0) { - int old_poolid = sb->cleancache_poolid; - sb->cleancache_poolid = -1; - (*cleancache_ops.invalidate_fs)(old_poolid); + int index; + int fake_pool_id = sb->cleancache_poolid; + int old_poolid = fake_pool_id; + + mutex_lock(&poolid_mutex); + if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) { + index = fake_pool_id - FAKE_SHARED_FS_POOLID_OFFSET; + old_poolid = shared_fs_poolid_map[index]; + shared_fs_poolid_map[index] = FS_UNKNOWN; + uuids[index] = NULL; + } else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) { + index = fake_pool_id - FAKE_FS_POOLID_OFFSET; + old_poolid = fs_poolid_map[index]; + fs_poolid_map[index] = FS_UNKNOWN; } + sb->cleancache_poolid = -1; + if (cleancache_ops) + cleancache_ops->invalidate_fs(old_poolid); + mutex_unlock(&poolid_mutex); } EXPORT_SYMBOL(__cleancache_invalidate_fs); static int __init init_cleancache(void) { + int i; + #ifdef CONFIG_DEBUG_FS struct dentry *root = debugfs_create_dir("cleancache", NULL); if (root == NULL) @@ -215,6 +400,10 @@ static int __init init_cleancache(void) debugfs_create_u64("invalidates", S_IRUGO, root, &cleancache_invalidates); #endif + for (i = 0; i < MAX_INITIALIZABLE_FS; i++) { + fs_poolid_map[i] = FS_UNKNOWN; + shared_fs_poolid_map[i] = FS_UNKNOWN; + } return 0; } module_init(init_cleancache) diff --git a/mm/frontswap.c b/mm/frontswap.c index 2890e67d..538367e 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -24,15 +24,7 @@ * frontswap_ops is set by frontswap_register_ops to contain the pointers * to the frontswap "backend" implementation functions. */ -static struct frontswap_ops frontswap_ops __read_mostly; - -/* - * This global enablement flag reduces overhead on systems where frontswap_ops - * has not been registered, so is preferred to the slower alternative: a - * function call that checks a non-global. - */ -bool frontswap_enabled __read_mostly; -EXPORT_SYMBOL(frontswap_enabled); +static struct frontswap_ops *frontswap_ops __read_mostly; /* * If enabled, frontswap_store will return failure even on success. As @@ -80,16 +72,70 @@ static inline void inc_frontswap_succ_stores(void) { } static inline void inc_frontswap_failed_stores(void) { } static inline void inc_frontswap_invalidates(void) { } #endif + +/* + * Due to the asynchronous nature of the backends loading potentially + * _after_ the swap system has been activated, we have chokepoints + * on all frontswap functions to not call the backend until the backend + * has registered. + * + * Specifically when no backend is registered (nobody called + * frontswap_register_ops) all calls to frontswap_init (which is done via + * swapon -> enable_swap_info -> frontswap_init) are registered and remembered + * (via the setting of need_init bitmap) but fail to create tmem_pools. When a + * backend registers with frontswap at some later point the previous + * calls to frontswap_init are executed (by iterating over the need_init + * bitmap) to create tmem_pools and set the respective poolids. All of that is + * guarded by us using atomic bit operations on the 'need_init' bitmap. + * + * This would not guards us against the user deciding to call swapoff right as + * we are calling the backend to initialize (so swapon is in action). + * Fortunatly for us, the swapon_mutex has been taked by the callee so we are + * OK. The other scenario where calls to frontswap_store (called via + * swap_writepage) is racing with frontswap_invalidate_area (called via + * swapoff) is again guarded by the swap subsystem. + * + * While no backend is registered all calls to frontswap_[store|load| + * invalidate_area|invalidate_page] are ignored or fail. + * + * The time between the backend being registered and the swap file system + * calling the backend (via the frontswap_* functions) is indeterminate as + * frontswap_ops is not atomic_t (or a value guarded by a spinlock). + * That is OK as we are comfortable missing some of these calls to the newly + * registered backend. + * + * Obviously the opposite (unloading the backend) must be done after all + * the frontswap_[store|load|invalidate_area|invalidate_page] start + * ignorning or failing the requests - at which point frontswap_ops + * would have to be made in some fashion atomic. + */ +static DECLARE_BITMAP(need_init, MAX_SWAPFILES); + /* * Register operations for frontswap, returning previous thus allowing * detection of multiple backends and possible nesting. */ -struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops) +struct frontswap_ops *frontswap_register_ops(struct frontswap_ops *ops) { - struct frontswap_ops old = frontswap_ops; - - frontswap_ops = *ops; - frontswap_enabled = true; + struct frontswap_ops *old = frontswap_ops; + int i; + + for (i = 0; i < MAX_SWAPFILES; i++) { + if (test_and_clear_bit(i, need_init)) { + struct swap_info_struct *sis = swap_info[i]; + /* __frontswap_init _should_ have set it! */ + if (!sis->frontswap_map) + return ERR_PTR(-EINVAL); + ops->init(i); + } + } + /* + * We MUST have frontswap_ops set _after_ the frontswap_init's + * have been called. Otherwise __frontswap_store might fail. Hence + * the barrier to make sure compiler does not re-order us. + */ + barrier(); + frontswap_ops = ops; return old; } EXPORT_SYMBOL(frontswap_register_ops); @@ -115,20 +161,48 @@ EXPORT_SYMBOL(frontswap_tmem_exclusive_gets); /* * Called when a swap device is swapon'd. */ -void __frontswap_init(unsigned type) +void __frontswap_init(unsigned type, unsigned long *map) { struct swap_info_struct *sis = swap_info[type]; BUG_ON(sis == NULL); - if (sis->frontswap_map == NULL) + + /* + * p->frontswap is a bitmap that we MUST have to figure out which page + * has gone in frontswap. Without it there is no point of continuing. + */ + if (WARN_ON(!map)) return; - frontswap_ops.init(type); + /* + * Irregardless of whether the frontswap backend has been loaded + * before this function or it will be later, we _MUST_ have the + * p->frontswap set to something valid to work properly. + */ + frontswap_map_set(sis, map); + if (frontswap_ops) + frontswap_ops->init(type); + else { + BUG_ON(type > MAX_SWAPFILES); + set_bit(type, need_init); + } } EXPORT_SYMBOL(__frontswap_init); -static inline void __frontswap_clear(struct swap_info_struct *sis, pgoff_t offset) +bool __frontswap_test(struct swap_info_struct *sis, + pgoff_t offset) +{ + bool ret = false; + + if (frontswap_ops && sis->frontswap_map) + ret = test_bit(offset, sis->frontswap_map); + return ret; +} +EXPORT_SYMBOL(__frontswap_test); + +static inline void __frontswap_clear(struct swap_info_struct *sis, + pgoff_t offset) { - frontswap_clear(sis, offset); + clear_bit(offset, sis->frontswap_map); atomic_dec(&sis->frontswap_pages); } @@ -147,13 +221,20 @@ int __frontswap_store(struct page *page) struct swap_info_struct *sis = swap_info[type]; pgoff_t offset = swp_offset(entry); + /* + * Return if no backend registed. + * Don't need to inc frontswap_failed_stores here. + */ + if (!frontswap_ops) + return ret; + BUG_ON(!PageLocked(page)); BUG_ON(sis == NULL); - if (frontswap_test(sis, offset)) + if (__frontswap_test(sis, offset)) dup = 1; - ret = frontswap_ops.store(type, offset, page); + ret = frontswap_ops->store(type, offset, page); if (ret == 0) { - frontswap_set(sis, offset); + set_bit(offset, sis->frontswap_map); inc_frontswap_succ_stores(); if (!dup) atomic_inc(&sis->frontswap_pages); @@ -188,13 +269,16 @@ int __frontswap_load(struct page *page) BUG_ON(!PageLocked(page)); BUG_ON(sis == NULL); - if (frontswap_test(sis, offset)) - ret = frontswap_ops.load(type, offset, page); + /* + * __frontswap_test() will check whether there is backend registered + */ + if (__frontswap_test(sis, offset)) + ret = frontswap_ops->load(type, offset, page); if (ret == 0) { inc_frontswap_loads(); if (frontswap_tmem_exclusive_gets_enabled) { SetPageDirty(page); - frontswap_clear(sis, offset); + __frontswap_clear(sis, offset); } } return ret; @@ -210,8 +294,11 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset) struct swap_info_struct *sis = swap_info[type]; BUG_ON(sis == NULL); - if (frontswap_test(sis, offset)) { - frontswap_ops.invalidate_page(type, offset); + /* + * __frontswap_test() will check whether there is backend registered + */ + if (__frontswap_test(sis, offset)) { + frontswap_ops->invalidate_page(type, offset); __frontswap_clear(sis, offset); inc_frontswap_invalidates(); } @@ -226,12 +313,15 @@ void __frontswap_invalidate_area(unsigned type) { struct swap_info_struct *sis = swap_info[type]; - BUG_ON(sis == NULL); - if (sis->frontswap_map == NULL) - return; - frontswap_ops.invalidate_area(type); - atomic_set(&sis->frontswap_pages, 0); - memset(sis->frontswap_map, 0, sis->max / sizeof(long)); + if (frontswap_ops) { + BUG_ON(sis == NULL); + if (sis->frontswap_map == NULL) + return; + frontswap_ops->invalidate_area(type); + atomic_set(&sis->frontswap_pages, 0); + memset(sis->frontswap_map, 0, sis->max / sizeof(long)); + } + clear_bit(type, need_init); } EXPORT_SYMBOL(__frontswap_invalidate_area); diff --git a/mm/swapfile.c b/mm/swapfile.c index d417efd..6c340d9 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1509,8 +1509,7 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) } static void _enable_swap_info(struct swap_info_struct *p, int prio, - unsigned char *swap_map, - unsigned long *frontswap_map) + unsigned char *swap_map) { int i, prev; @@ -1519,7 +1518,6 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, else p->prio = --least_priority; p->swap_map = swap_map; - frontswap_map_set(p, frontswap_map); p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; @@ -1542,10 +1540,10 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, unsigned long *frontswap_map) { + frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, prio, swap_map, frontswap_map); - frontswap_init(p->type); + _enable_swap_info(p, prio, swap_map); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -1554,7 +1552,7 @@ static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); - _enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p)); + _enable_swap_info(p, p->prio, p->swap_map); spin_unlock(&p->lock); spin_unlock(&swap_lock); } @@ -1563,6 +1561,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; + unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; @@ -1662,12 +1661,14 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) swap_map = p->swap_map; p->swap_map = NULL; p->flags = 0; - frontswap_invalidate_area(type); + frontswap_map = frontswap_map_get(p); + frontswap_map_set(p, NULL); spin_unlock(&p->lock); spin_unlock(&swap_lock); + frontswap_invalidate_area(type); mutex_unlock(&swapon_mutex); vfree(swap_map); - vfree(frontswap_map_get(p)); + vfree(frontswap_map); /* Destroy swap account informatin */ swap_cgroup_swapoff(type); diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index f3bffa3..826da66 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -515,13 +515,6 @@ static void get_prompt_str(struct gstr *r, struct property *prop, struct jump_key *jump; str_printf(r, _("Prompt: %s\n"), _(prop->text)); - str_printf(r, _(" Defined at %s:%d\n"), prop->menu->file->name, - prop->menu->lineno); - if (!expr_is_yes(prop->visible.expr)) { - str_append(r, _(" Depends on: ")); - expr_gstr_print(prop->visible.expr, r); - str_append(r, "\n"); - } menu = prop->menu->parent; for (i = 0; menu != &rootmenu && i < 8; menu = menu->parent) { bool accessible = menu_is_visible(menu); @@ -572,6 +565,18 @@ static void get_prompt_str(struct gstr *r, struct property *prop, } /* + * get peoperty of type P_SYMBOL + */ +static struct property *get_symbol_prop(struct symbol *sym) +{ + struct property *prop = NULL; + + for_all_properties(sym, prop, P_SYMBOL) + break; + return prop; +} + +/* * head is optional and may be NULL */ void get_symbol_str(struct gstr *r, struct symbol *sym, @@ -595,6 +600,14 @@ void get_symbol_str(struct gstr *r, struct symbol *sym, } for_all_prompts(sym, prop) get_prompt_str(r, prop, head); + prop = get_symbol_prop(sym); + str_printf(r, _(" Defined at %s:%d\n"), prop->menu->file->name, + prop->menu->lineno); + if (!expr_is_yes(prop->visible.expr)) { + str_append(r, _(" Depends on: ")); + expr_gstr_print(prop->visible.expr, r); + str_append(r, "\n"); + } hit = false; for_all_properties(sym, prop, P_SELECT) { if (!hit) { diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 4bd6bdb7..c411f9b 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -93,9 +93,16 @@ static void umh_keys_cleanup(struct subprocess_info *info) static int call_usermodehelper_keys(char *path, char **argv, char **envp, struct key *session_keyring, int wait) { - return call_usermodehelper_fns(path, argv, envp, wait, - umh_keys_init, umh_keys_cleanup, - key_get(session_keyring)); + struct subprocess_info *info; + + info = call_usermodehelper_setup(path, argv, envp, GFP_KERNEL, + umh_keys_init, umh_keys_cleanup, + session_keyring); + if (!info) + return -ENOMEM; + + key_get(session_keyring); + return call_usermodehelper_exec(info, wait); } /* diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 3cc0ad7..fa6ea69 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,10 +1,12 @@ TARGETS = breakpoints +TARGETS += cpu-hotplug +TARGETS += efivarfs TARGETS += kcmp +TARGETS += memory-hotplug TARGETS += mqueue +TARGETS += ptrace +TARGETS += soft-dirty TARGETS += vm -TARGETS += cpu-hotplug -TARGETS += memory-hotplug -TARGETS += efivarfs all: for TARGET in $(TARGETS); do \ diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile new file mode 100644 index 0000000..47ae2d3 --- /dev/null +++ b/tools/testing/selftests/ptrace/Makefile @@ -0,0 +1,10 @@ +CFLAGS += -iquote../../../../include/uapi -Wall +peeksiginfo: peeksiginfo.c + +all: peeksiginfo + +clean: + rm -f peeksiginfo + +run_tests: all + @./peeksiginfo || echo "peeksiginfo selftests: [FAIL]" diff --git a/tools/testing/selftests/ptrace/peeksiginfo.c b/tools/testing/selftests/ptrace/peeksiginfo.c new file mode 100644 index 0000000..d46558b --- /dev/null +++ b/tools/testing/selftests/ptrace/peeksiginfo.c @@ -0,0 +1,214 @@ +#define _GNU_SOURCE +#include <stdio.h> +#include <signal.h> +#include <unistd.h> +#include <errno.h> +#include <linux/types.h> +#include <sys/wait.h> +#include <sys/syscall.h> +#include <sys/user.h> +#include <sys/mman.h> + +#include "linux/ptrace.h" + +static int sys_rt_sigqueueinfo(pid_t tgid, int sig, siginfo_t *uinfo) +{ + return syscall(SYS_rt_sigqueueinfo, tgid, sig, uinfo); +} + +static int sys_rt_tgsigqueueinfo(pid_t tgid, pid_t tid, + int sig, siginfo_t *uinfo) +{ + return syscall(SYS_rt_tgsigqueueinfo, tgid, tid, sig, uinfo); +} + +static int sys_ptrace(int request, pid_t pid, void *addr, void *data) +{ + return syscall(SYS_ptrace, request, pid, addr, data); +} + +#define SIGNR 10 +#define TEST_SICODE_PRIV -1 +#define TEST_SICODE_SHARE -2 + +#define err(fmt, ...) \ + fprintf(stderr, \ + "Error (%s:%d): " fmt, \ + __FILE__, __LINE__, ##__VA_ARGS__) + +static int check_error_paths(pid_t child) +{ + struct ptrace_peeksiginfo_args arg; + int ret, exit_code = -1; + void *addr_rw, *addr_ro; + + /* + * Allocate two contiguous pages. The first one is for read-write, + * another is for read-only. + */ + addr_rw = mmap(NULL, 2 * PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (addr_rw == MAP_FAILED) { + err("mmap() failed: %m\n"); + return 1; + } + + addr_ro = mmap(addr_rw + PAGE_SIZE, PAGE_SIZE, PROT_READ, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0); + if (addr_ro == MAP_FAILED) { + err("mmap() failed: %m\n"); + goto out; + } + + arg.nr = SIGNR; + arg.off = 0; + + /* Unsupported flags */ + arg.flags = ~0; + ret = sys_ptrace(PTRACE_PEEKSIGINFO, child, &arg, addr_rw); + if (ret != -1 || errno != EINVAL) { + err("sys_ptrace() returns %d (expected -1)," + " errno %d (expected %d): %m\n", + ret, errno, EINVAL); + goto out; + } + arg.flags = 0; + + /* A part of the buffer is read-only */ + ret = sys_ptrace(PTRACE_PEEKSIGINFO, child, &arg, + addr_ro - sizeof(siginfo_t) * 2); + if (ret != 2) { + err("sys_ptrace() returns %d (expected 2): %m\n", ret); + goto out; + } + + /* Read-only buffer */ + ret = sys_ptrace(PTRACE_PEEKSIGINFO, child, &arg, addr_ro); + if (ret != -1 && errno != EFAULT) { + err("sys_ptrace() returns %d (expected -1)," + " errno %d (expected %d): %m\n", + ret, errno, EFAULT); + goto out; + } + + exit_code = 0; +out: + munmap(addr_rw, 2 * PAGE_SIZE); + return exit_code; +} + +int check_direct_path(pid_t child, int shared, int nr) +{ + struct ptrace_peeksiginfo_args arg = {.flags = 0, .nr = nr, .off = 0}; + int i, j, ret, exit_code = -1; + siginfo_t siginfo[SIGNR]; + int si_code; + + if (shared == 1) { + arg.flags = PTRACE_PEEKSIGINFO_SHARED; + si_code = TEST_SICODE_SHARE; + } else { + arg.flags = 0; + si_code = TEST_SICODE_PRIV; + } + + for (i = 0; i < SIGNR; ) { + arg.off = i; + ret = sys_ptrace(PTRACE_PEEKSIGINFO, child, &arg, siginfo); + if (ret == -1) { + err("ptrace() failed: %m\n"); + goto out; + } + + if (ret == 0) + break; + + for (j = 0; j < ret; j++, i++) { + if (siginfo[j].si_code == si_code && + siginfo[j].si_int == i) + continue; + + err("%d: Wrong siginfo i=%d si_code=%d si_int=%d\n", + shared, i, siginfo[j].si_code, siginfo[j].si_int); + goto out; + } + } + + if (i != SIGNR) { + err("Only %d signals were read\n", i); + goto out; + } + + exit_code = 0; +out: + return exit_code; +} + +int main(int argc, char *argv[]) +{ + siginfo_t siginfo[SIGNR]; + int i, exit_code = 1; + sigset_t blockmask; + pid_t child; + + sigemptyset(&blockmask); + sigaddset(&blockmask, SIGRTMIN); + sigprocmask(SIG_BLOCK, &blockmask, NULL); + + child = fork(); + if (child == -1) { + err("fork() failed: %m"); + return 1; + } else if (child == 0) { + pid_t ppid = getppid(); + while (1) { + if (ppid != getppid()) + break; + sleep(1); + } + return 1; + } + + /* Send signals in process-wide and per-thread queues */ + for (i = 0; i < SIGNR; i++) { + siginfo->si_code = TEST_SICODE_SHARE; + siginfo->si_int = i; + sys_rt_sigqueueinfo(child, SIGRTMIN, siginfo); + + siginfo->si_code = TEST_SICODE_PRIV; + siginfo->si_int = i; + sys_rt_tgsigqueueinfo(child, child, SIGRTMIN, siginfo); + } + + if (sys_ptrace(PTRACE_ATTACH, child, NULL, NULL) == -1) + return 1; + + waitpid(child, NULL, 0); + + /* Dump signals one by one*/ + if (check_direct_path(child, 0, 1)) + goto out; + /* Dump all signals for one call */ + if (check_direct_path(child, 0, SIGNR)) + goto out; + + /* + * Dump signal from the process-wide queue. + * The number of signals is not multible to the buffer size + */ + if (check_direct_path(child, 1, 3)) + goto out; + + if (check_error_paths(child)) + goto out; + + printf("PASS\n"); + exit_code = 0; +out: + if (sys_ptrace(PTRACE_KILL, child, NULL, NULL) == -1) + return 1; + + waitpid(child, NULL, 0); + + return exit_code; +} diff --git a/tools/testing/selftests/soft-dirty/Makefile b/tools/testing/selftests/soft-dirty/Makefile new file mode 100644 index 0000000..a9cdc82 --- /dev/null +++ b/tools/testing/selftests/soft-dirty/Makefile @@ -0,0 +1,10 @@ +CFLAGS += -iquote../../../../include/uapi -Wall +soft-dirty: soft-dirty.c + +all: soft-dirty + +clean: + rm -f soft-dirty + +run_tests: all + @./soft-dirty || echo "soft-dirty selftests: [FAIL]" diff --git a/tools/testing/selftests/soft-dirty/soft-dirty.c b/tools/testing/selftests/soft-dirty/soft-dirty.c new file mode 100644 index 0000000..aba4f87 --- /dev/null +++ b/tools/testing/selftests/soft-dirty/soft-dirty.c @@ -0,0 +1,114 @@ +#include <stdlib.h> +#include <stdio.h> +#include <sys/mman.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/types.h> + +typedef unsigned long long u64; + +#define PME_PRESENT (1ULL << 63) +#define PME_SOFT_DIRTY (1Ull << 55) + +#define PAGES_TO_TEST 3 +#ifndef PAGE_SIZE +#define PAGE_SIZE 4096 +#endif + +static void get_pagemap2(char *mem, u64 *map) +{ + int fd; + + fd = open("/proc/self/pagemap2", O_RDONLY); + if (fd < 0) { + perror("Can't open pagemap2"); + exit(1); + } + + lseek(fd, (unsigned long)mem / PAGE_SIZE * sizeof(u64), SEEK_SET); + read(fd, map, sizeof(u64) * PAGES_TO_TEST); + close(fd); +} + +static inline char map_p(u64 map) +{ + return map & PME_PRESENT ? 'p' : '-'; +} + +static inline char map_sd(u64 map) +{ + return map & PME_SOFT_DIRTY ? 'd' : '-'; +} + +static int check_pte(int step, int page, u64 *map, u64 want) +{ + if ((map[page] & want) != want) { + printf("Step %d Page %d has %c%c, want %c%c\n", + step, page, + map_p(map[page]), map_sd(map[page]), + map_p(want), map_sd(want)); + return 1; + } + + return 0; +} + +static void clear_refs(void) +{ + int fd; + char *v = "4"; + + fd = open("/proc/self/clear_refs", O_WRONLY); + if (write(fd, v, 3) < 3) { + perror("Can't clear soft-dirty bit"); + exit(1); + } + close(fd); +} + +int main(void) +{ + char *mem, x; + u64 map[PAGES_TO_TEST]; + + mem = mmap(NULL, PAGES_TO_TEST * PAGE_SIZE, + PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, 0, 0); + + x = mem[0]; + mem[2 * PAGE_SIZE] = 'c'; + get_pagemap2(mem, map); + + if (check_pte(1, 0, map, PME_PRESENT)) + return 1; + if (check_pte(1, 1, map, 0)) + return 1; + if (check_pte(1, 2, map, PME_PRESENT | PME_SOFT_DIRTY)) + return 1; + + clear_refs(); + get_pagemap2(mem, map); + + if (check_pte(2, 0, map, PME_PRESENT)) + return 1; + if (check_pte(2, 1, map, 0)) + return 1; + if (check_pte(2, 2, map, PME_PRESENT)) + return 1; + + mem[0] = 'a'; + mem[PAGE_SIZE] = 'b'; + x = mem[2 * PAGE_SIZE]; + get_pagemap2(mem, map); + + if (check_pte(3, 0, map, PME_PRESENT | PME_SOFT_DIRTY)) + return 1; + if (check_pte(3, 1, map, PME_PRESENT | PME_SOFT_DIRTY)) + return 1; + if (check_pte(3, 2, map, PME_PRESENT)) + return 1; + + (void)x; /* gcc warn */ + + printf("PASS\n"); + return 0; +} |
