From 15a42a9bc9ffcff4315a7154313db08c6bf9ef11 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 6 Nov 2014 14:36:41 +0000 Subject: kdb: Rename kdb_repeat_t to kdb_cmdflags_t, cmd_repeat to cmd_flags We're about to add more options for command behaviour, so let's expand the meaning of kdb_repeat_t. So far we just do various renames, there should be no functional changes. Signed-off-by: Anton Vorontsov Signed-off-by: John Stultz Signed-off-by: Daniel Thompson Cc: Jason Wessel Signed-off-by: Jason Wessel --- include/linux/kdb.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 290db1269c4c..e650f79aa414 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -17,7 +17,7 @@ typedef enum { KDB_REPEAT_NONE = 0, /* Do not repeat this command */ KDB_REPEAT_NO_ARGS, /* Repeat the command without arguments */ KDB_REPEAT_WITH_ARGS, /* Repeat the command including its arguments */ -} kdb_repeat_t; +} kdb_cmdflags_t; typedef int (*kdb_func_t)(int, const char **); @@ -147,7 +147,7 @@ static inline const char *kdb_walk_kallsyms(loff_t *pos) /* Dynamic kdb shell command registration */ extern int kdb_register(char *, kdb_func_t, char *, char *, short); extern int kdb_register_repeat(char *, kdb_func_t, char *, char *, - short, kdb_repeat_t); + short, kdb_cmdflags_t); extern int kdb_unregister(char *); #else /* ! CONFIG_KGDB_KDB */ static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } @@ -156,7 +156,7 @@ static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, char *help, short minlen) { return 0; } static inline int kdb_register_repeat(char *cmd, kdb_func_t func, char *usage, char *help, short minlen, - kdb_repeat_t repeat) { return 0; } + kdb_cmdflags_t flags) { return 0; } static inline int kdb_unregister(char *cmd) { return 0; } #endif /* CONFIG_KGDB_KDB */ enum { -- cgit v1.2.3 From 42c884c10b775ce04f8aabe488820134625c893e Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 6 Nov 2014 14:36:42 +0000 Subject: kdb: Rename kdb_register_repeat() to kdb_register_flags() We're about to add more options for commands behaviour, so let's give a more generic name to the low-level kdb command registration function. There are just various renames, no functional changes. Signed-off-by: Anton Vorontsov Signed-off-by: John Stultz Signed-off-by: Daniel Thompson Cc: Jason Wessel Signed-off-by: Jason Wessel --- include/linux/kdb.h | 10 +++--- kernel/debug/kdb/kdb_bp.c | 14 ++++---- kernel/debug/kdb/kdb_main.c | 86 ++++++++++++++++++++++----------------------- kernel/trace/trace_kdb.c | 2 +- 4 files changed, 56 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index e650f79aa414..32d2f407981d 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -146,17 +146,17 @@ static inline const char *kdb_walk_kallsyms(loff_t *pos) /* Dynamic kdb shell command registration */ extern int kdb_register(char *, kdb_func_t, char *, char *, short); -extern int kdb_register_repeat(char *, kdb_func_t, char *, char *, - short, kdb_cmdflags_t); +extern int kdb_register_flags(char *, kdb_func_t, char *, char *, + short, kdb_cmdflags_t); extern int kdb_unregister(char *); #else /* ! CONFIG_KGDB_KDB */ static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } static inline void kdb_init(int level) {} static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, char *help, short minlen) { return 0; } -static inline int kdb_register_repeat(char *cmd, kdb_func_t func, char *usage, - char *help, short minlen, - kdb_cmdflags_t flags) { return 0; } +static inline int kdb_register_flags(char *cmd, kdb_func_t func, char *usage, + char *help, short minlen, + kdb_cmdflags_t flags) { return 0; } static inline int kdb_unregister(char *cmd) { return 0; } #endif /* CONFIG_KGDB_KDB */ enum { diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index b20d544f20c2..59536661c7b9 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -531,21 +531,21 @@ void __init kdb_initbptab(void) for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) bp->bp_free = 1; - kdb_register_repeat("bp", kdb_bp, "[]", + kdb_register_flags("bp", kdb_bp, "[]", "Set/Display breakpoints", 0, KDB_REPEAT_NO_ARGS); - kdb_register_repeat("bl", kdb_bp, "[]", + kdb_register_flags("bl", kdb_bp, "[]", "Display breakpoints", 0, KDB_REPEAT_NO_ARGS); if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT) - kdb_register_repeat("bph", kdb_bp, "[]", + kdb_register_flags("bph", kdb_bp, "[]", "[datar [length]|dataw [length]] Set hw brk", 0, KDB_REPEAT_NO_ARGS); - kdb_register_repeat("bc", kdb_bc, "", + kdb_register_flags("bc", kdb_bc, "", "Clear Breakpoint", 0, KDB_REPEAT_NONE); - kdb_register_repeat("be", kdb_bc, "", + kdb_register_flags("be", kdb_bc, "", "Enable Breakpoint", 0, KDB_REPEAT_NONE); - kdb_register_repeat("bd", kdb_bc, "", + kdb_register_flags("bd", kdb_bc, "", "Disable Breakpoint", 0, KDB_REPEAT_NONE); - kdb_register_repeat("ss", kdb_ss, "", + kdb_register_flags("ss", kdb_ss, "", "Single Step", 1, KDB_REPEAT_NO_ARGS); /* * Architecture dependent initialization. diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 41966b5f86b7..070f1ff358d2 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2629,7 +2629,7 @@ static int kdb_grep_help(int argc, const char **argv) } /* - * kdb_register_repeat - This function is used to register a kernel + * kdb_register_flags - This function is used to register a kernel * debugger command. * Inputs: * cmd Command name @@ -2641,12 +2641,12 @@ static int kdb_grep_help(int argc, const char **argv) * zero for success, one if a duplicate command. */ #define kdb_command_extend 50 /* arbitrary */ -int kdb_register_repeat(char *cmd, - kdb_func_t func, - char *usage, - char *help, - short minlen, - kdb_cmdflags_t flags) +int kdb_register_flags(char *cmd, + kdb_func_t func, + char *usage, + char *help, + short minlen, + kdb_cmdflags_t flags) { int i; kdbtab_t *kp; @@ -2699,13 +2699,13 @@ int kdb_register_repeat(char *cmd, return 0; } -EXPORT_SYMBOL_GPL(kdb_register_repeat); +EXPORT_SYMBOL_GPL(kdb_register_flags); /* * kdb_register - Compatibility register function for commands that do * not need to specify a repeat state. Equivalent to - * kdb_register_repeat with KDB_REPEAT_NONE. + * kdb_register_flags with KDB_REPEAT_NONE. * Inputs: * cmd Command name * func Function to execute the command @@ -2720,8 +2720,8 @@ int kdb_register(char *cmd, char *help, short minlen) { - return kdb_register_repeat(cmd, func, usage, help, minlen, - KDB_REPEAT_NONE); + return kdb_register_flags(cmd, func, usage, help, minlen, + KDB_REPEAT_NONE); } EXPORT_SYMBOL_GPL(kdb_register); @@ -2763,79 +2763,79 @@ static void __init kdb_inittab(void) for_each_kdbcmd(kp, i) kp->cmd_name = NULL; - kdb_register_repeat("md", kdb_md, "", + kdb_register_flags("md", kdb_md, "", "Display Memory Contents, also mdWcN, e.g. md8c1", 1, KDB_REPEAT_NO_ARGS); - kdb_register_repeat("mdr", kdb_md, " ", + kdb_register_flags("mdr", kdb_md, " ", "Display Raw Memory", 0, KDB_REPEAT_NO_ARGS); - kdb_register_repeat("mdp", kdb_md, " ", + kdb_register_flags("mdp", kdb_md, " ", "Display Physical Memory", 0, KDB_REPEAT_NO_ARGS); - kdb_register_repeat("mds", kdb_md, "", + kdb_register_flags("mds", kdb_md, "", "Display Memory Symbolically", 0, KDB_REPEAT_NO_ARGS); - kdb_register_repeat("mm", kdb_mm, " ", + kdb_register_flags("mm", kdb_mm, " ", "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS); - kdb_register_repeat("go", kdb_go, "[]", + kdb_register_flags("go", kdb_go, "[]", "Continue Execution", 1, KDB_REPEAT_NONE); - kdb_register_repeat("rd", kdb_rd, "", + kdb_register_flags("rd", kdb_rd, "", "Display Registers", 0, KDB_REPEAT_NONE); - kdb_register_repeat("rm", kdb_rm, " ", + kdb_register_flags("rm", kdb_rm, " ", "Modify Registers", 0, KDB_REPEAT_NONE); - kdb_register_repeat("ef", kdb_ef, "", + kdb_register_flags("ef", kdb_ef, "", "Display exception frame", 0, KDB_REPEAT_NONE); - kdb_register_repeat("bt", kdb_bt, "[]", + kdb_register_flags("bt", kdb_bt, "[]", "Stack traceback", 1, KDB_REPEAT_NONE); - kdb_register_repeat("btp", kdb_bt, "", + kdb_register_flags("btp", kdb_bt, "", "Display stack for process ", 0, KDB_REPEAT_NONE); - kdb_register_repeat("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]", + kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]", "Backtrace all processes matching state flag", 0, KDB_REPEAT_NONE); - kdb_register_repeat("btc", kdb_bt, "", + kdb_register_flags("btc", kdb_bt, "", "Backtrace current process on each cpu", 0, KDB_REPEAT_NONE); - kdb_register_repeat("btt", kdb_bt, "", + kdb_register_flags("btt", kdb_bt, "", "Backtrace process given its struct task address", 0, KDB_REPEAT_NONE); - kdb_register_repeat("env", kdb_env, "", + kdb_register_flags("env", kdb_env, "", "Show environment variables", 0, KDB_REPEAT_NONE); - kdb_register_repeat("set", kdb_set, "", + kdb_register_flags("set", kdb_set, "", "Set environment variables", 0, KDB_REPEAT_NONE); - kdb_register_repeat("help", kdb_help, "", + kdb_register_flags("help", kdb_help, "", "Display Help Message", 1, KDB_REPEAT_NONE); - kdb_register_repeat("?", kdb_help, "", + kdb_register_flags("?", kdb_help, "", "Display Help Message", 0, KDB_REPEAT_NONE); - kdb_register_repeat("cpu", kdb_cpu, "", + kdb_register_flags("cpu", kdb_cpu, "", "Switch to new cpu", 0, KDB_REPEAT_NONE); - kdb_register_repeat("kgdb", kdb_kgdb, "", + kdb_register_flags("kgdb", kdb_kgdb, "", "Enter kgdb mode", 0, KDB_REPEAT_NONE); - kdb_register_repeat("ps", kdb_ps, "[|A]", + kdb_register_flags("ps", kdb_ps, "[|A]", "Display active task list", 0, KDB_REPEAT_NONE); - kdb_register_repeat("pid", kdb_pid, "", + kdb_register_flags("pid", kdb_pid, "", "Switch to another task", 0, KDB_REPEAT_NONE); - kdb_register_repeat("reboot", kdb_reboot, "", + kdb_register_flags("reboot", kdb_reboot, "", "Reboot the machine immediately", 0, KDB_REPEAT_NONE); #if defined(CONFIG_MODULES) - kdb_register_repeat("lsmod", kdb_lsmod, "", + kdb_register_flags("lsmod", kdb_lsmod, "", "List loaded kernel modules", 0, KDB_REPEAT_NONE); #endif #if defined(CONFIG_MAGIC_SYSRQ) - kdb_register_repeat("sr", kdb_sr, "", + kdb_register_flags("sr", kdb_sr, "", "Magic SysRq key", 0, KDB_REPEAT_NONE); #endif #if defined(CONFIG_PRINTK) - kdb_register_repeat("dmesg", kdb_dmesg, "[lines]", + kdb_register_flags("dmesg", kdb_dmesg, "[lines]", "Display syslog buffer", 0, KDB_REPEAT_NONE); #endif if (arch_kgdb_ops.enable_nmi) { - kdb_register_repeat("disable_nmi", kdb_disable_nmi, "", + kdb_register_flags("disable_nmi", kdb_disable_nmi, "", "Disable NMI entry to KDB", 0, KDB_REPEAT_NONE); } - kdb_register_repeat("defcmd", kdb_defcmd, "name \"usage\" \"help\"", + kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"", "Define a set of commands, down to endefcmd", 0, KDB_REPEAT_NONE); - kdb_register_repeat("kill", kdb_kill, "<-signal> ", + kdb_register_flags("kill", kdb_kill, "<-signal> ", "Send a signal to a process", 0, KDB_REPEAT_NONE); - kdb_register_repeat("summary", kdb_summary, "", + kdb_register_flags("summary", kdb_summary, "", "Summarize the system", 4, KDB_REPEAT_NONE); - kdb_register_repeat("per_cpu", kdb_per_cpu, " [] []", + kdb_register_flags("per_cpu", kdb_per_cpu, " [] []", "Display per_cpu variables", 3, KDB_REPEAT_NONE); - kdb_register_repeat("grephelp", kdb_grep_help, "", + kdb_register_flags("grephelp", kdb_grep_help, "", "Display help on | grep", 0, KDB_REPEAT_NONE); } diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index bd90e1b06088..1e3b36c75048 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -127,7 +127,7 @@ static int kdb_ftdump(int argc, const char **argv) static __init int kdb_ftrace_register(void) { - kdb_register_repeat("ftdump", kdb_ftdump, "[skip_#lines] [cpu]", + kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]", "Dump ftrace log", 0, KDB_REPEAT_NONE); return 0; } -- cgit v1.2.3 From 04bb171e7aa99dee0c92e772e4f66f8d5c1b4081 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 6 Nov 2014 14:36:43 +0000 Subject: kdb: Use KDB_REPEAT_* values as flags The actual values of KDB_REPEAT_* enum values and overall logic stayed the same, but we now treat the values as flags. This makes it possible to add other flags and combine them, plus makes the code a lot simpler and shorter. But functionality-wise, there should be no changes. Signed-off-by: Anton Vorontsov Signed-off-by: John Stultz Signed-off-by: Daniel Thompson Cc: Jason Wessel Signed-off-by: Jason Wessel --- include/linux/kdb.h | 4 ++-- kernel/debug/kdb/kdb_main.c | 21 +++++++-------------- 2 files changed, 9 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 32d2f407981d..90aed7c31f0d 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -15,8 +15,8 @@ typedef enum { KDB_REPEAT_NONE = 0, /* Do not repeat this command */ - KDB_REPEAT_NO_ARGS, /* Repeat the command without arguments */ - KDB_REPEAT_WITH_ARGS, /* Repeat the command including its arguments */ + KDB_REPEAT_NO_ARGS = 0x1, /* Repeat the command w/o arguments */ + KDB_REPEAT_WITH_ARGS = 0x2, /* Repeat the command w/ its arguments */ } kdb_cmdflags_t; typedef int (*kdb_func_t)(int, const char **); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 070f1ff358d2..cbacae24a55a 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1008,20 +1008,13 @@ int kdb_parse(const char *cmdstr) if (result && ignore_errors && result > KDB_CMD_GO) result = 0; KDB_STATE_CLEAR(CMD); - switch (tp->cmd_flags) { - case KDB_REPEAT_NONE: - argc = 0; - if (argv[0]) - *(argv[0]) = '\0'; - break; - case KDB_REPEAT_NO_ARGS: - argc = 1; - if (argv[1]) - *(argv[1]) = '\0'; - break; - case KDB_REPEAT_WITH_ARGS: - break; - } + + if (tp->cmd_flags & KDB_REPEAT_WITH_ARGS) + return result; + + argc = tp->cmd_flags & KDB_REPEAT_NO_ARGS ? 1 : 0; + if (argv[argc]) + *(argv[argc]) = '\0'; return result; } -- cgit v1.2.3 From e8ab24d9b0173ada3eeed31d7d7f982228efc2c5 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 6 Nov 2014 14:36:44 +0000 Subject: kdb: Remove KDB_REPEAT_NONE flag Since we now treat KDB_REPEAT_* as flags, there is no need to pass KDB_REPEAT_NONE. It's just the default behaviour when no flags are specified. Signed-off-by: Anton Vorontsov Signed-off-by: John Stultz Signed-off-by: Daniel Thompson Cc: Jason Wessel Signed-off-by: Jason Wessel --- include/linux/kdb.h | 1 - kernel/debug/kdb/kdb_bp.c | 6 ++--- kernel/debug/kdb/kdb_main.c | 59 ++++++++++++++++++++++----------------------- kernel/trace/trace_kdb.c | 2 +- 4 files changed, 33 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 90aed7c31f0d..39b44b37c8dc 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -14,7 +14,6 @@ */ typedef enum { - KDB_REPEAT_NONE = 0, /* Do not repeat this command */ KDB_REPEAT_NO_ARGS = 0x1, /* Repeat the command w/o arguments */ KDB_REPEAT_WITH_ARGS = 0x2, /* Repeat the command w/ its arguments */ } kdb_cmdflags_t; diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index 59536661c7b9..f8844fb55311 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -539,11 +539,11 @@ void __init kdb_initbptab(void) kdb_register_flags("bph", kdb_bp, "[]", "[datar [length]|dataw [length]] Set hw brk", 0, KDB_REPEAT_NO_ARGS); kdb_register_flags("bc", kdb_bc, "", - "Clear Breakpoint", 0, KDB_REPEAT_NONE); + "Clear Breakpoint", 0, 0); kdb_register_flags("be", kdb_bc, "", - "Enable Breakpoint", 0, KDB_REPEAT_NONE); + "Enable Breakpoint", 0, 0); kdb_register_flags("bd", kdb_bc, "", - "Disable Breakpoint", 0, KDB_REPEAT_NONE); + "Disable Breakpoint", 0, 0); kdb_register_flags("ss", kdb_ss, "", "Single Step", 1, KDB_REPEAT_NO_ARGS); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index cbacae24a55a..538bf1dce26a 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2698,7 +2698,7 @@ EXPORT_SYMBOL_GPL(kdb_register_flags); /* * kdb_register - Compatibility register function for commands that do * not need to specify a repeat state. Equivalent to - * kdb_register_flags with KDB_REPEAT_NONE. + * kdb_register_flags with flags set to 0. * Inputs: * cmd Command name * func Function to execute the command @@ -2713,8 +2713,7 @@ int kdb_register(char *cmd, char *help, short minlen) { - return kdb_register_flags(cmd, func, usage, help, minlen, - KDB_REPEAT_NONE); + return kdb_register_flags(cmd, func, usage, help, minlen, 0); } EXPORT_SYMBOL_GPL(kdb_register); @@ -2768,68 +2767,68 @@ static void __init kdb_inittab(void) kdb_register_flags("mm", kdb_mm, " ", "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS); kdb_register_flags("go", kdb_go, "[]", - "Continue Execution", 1, KDB_REPEAT_NONE); + "Continue Execution", 1, 0); kdb_register_flags("rd", kdb_rd, "", - "Display Registers", 0, KDB_REPEAT_NONE); + "Display Registers", 0, 0); kdb_register_flags("rm", kdb_rm, " ", - "Modify Registers", 0, KDB_REPEAT_NONE); + "Modify Registers", 0, 0); kdb_register_flags("ef", kdb_ef, "", - "Display exception frame", 0, KDB_REPEAT_NONE); + "Display exception frame", 0, 0); kdb_register_flags("bt", kdb_bt, "[]", - "Stack traceback", 1, KDB_REPEAT_NONE); + "Stack traceback", 1, 0); kdb_register_flags("btp", kdb_bt, "", - "Display stack for process ", 0, KDB_REPEAT_NONE); + "Display stack for process ", 0, 0); kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]", - "Backtrace all processes matching state flag", 0, KDB_REPEAT_NONE); + "Backtrace all processes matching state flag", 0, 0); kdb_register_flags("btc", kdb_bt, "", - "Backtrace current process on each cpu", 0, KDB_REPEAT_NONE); + "Backtrace current process on each cpu", 0, 0); kdb_register_flags("btt", kdb_bt, "", "Backtrace process given its struct task address", 0, - KDB_REPEAT_NONE); + 0); kdb_register_flags("env", kdb_env, "", - "Show environment variables", 0, KDB_REPEAT_NONE); + "Show environment variables", 0, 0); kdb_register_flags("set", kdb_set, "", - "Set environment variables", 0, KDB_REPEAT_NONE); + "Set environment variables", 0, 0); kdb_register_flags("help", kdb_help, "", - "Display Help Message", 1, KDB_REPEAT_NONE); + "Display Help Message", 1, 0); kdb_register_flags("?", kdb_help, "", - "Display Help Message", 0, KDB_REPEAT_NONE); + "Display Help Message", 0, 0); kdb_register_flags("cpu", kdb_cpu, "", - "Switch to new cpu", 0, KDB_REPEAT_NONE); + "Switch to new cpu", 0, 0); kdb_register_flags("kgdb", kdb_kgdb, "", - "Enter kgdb mode", 0, KDB_REPEAT_NONE); + "Enter kgdb mode", 0, 0); kdb_register_flags("ps", kdb_ps, "[|A]", - "Display active task list", 0, KDB_REPEAT_NONE); + "Display active task list", 0, 0); kdb_register_flags("pid", kdb_pid, "", - "Switch to another task", 0, KDB_REPEAT_NONE); + "Switch to another task", 0, 0); kdb_register_flags("reboot", kdb_reboot, "", - "Reboot the machine immediately", 0, KDB_REPEAT_NONE); + "Reboot the machine immediately", 0, 0); #if defined(CONFIG_MODULES) kdb_register_flags("lsmod", kdb_lsmod, "", - "List loaded kernel modules", 0, KDB_REPEAT_NONE); + "List loaded kernel modules", 0, 0); #endif #if defined(CONFIG_MAGIC_SYSRQ) kdb_register_flags("sr", kdb_sr, "", - "Magic SysRq key", 0, KDB_REPEAT_NONE); + "Magic SysRq key", 0, 0); #endif #if defined(CONFIG_PRINTK) kdb_register_flags("dmesg", kdb_dmesg, "[lines]", - "Display syslog buffer", 0, KDB_REPEAT_NONE); + "Display syslog buffer", 0, 0); #endif if (arch_kgdb_ops.enable_nmi) { kdb_register_flags("disable_nmi", kdb_disable_nmi, "", - "Disable NMI entry to KDB", 0, KDB_REPEAT_NONE); + "Disable NMI entry to KDB", 0, 0); } kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"", - "Define a set of commands, down to endefcmd", 0, KDB_REPEAT_NONE); + "Define a set of commands, down to endefcmd", 0, 0); kdb_register_flags("kill", kdb_kill, "<-signal> ", - "Send a signal to a process", 0, KDB_REPEAT_NONE); + "Send a signal to a process", 0, 0); kdb_register_flags("summary", kdb_summary, "", - "Summarize the system", 4, KDB_REPEAT_NONE); + "Summarize the system", 4, 0); kdb_register_flags("per_cpu", kdb_per_cpu, " [] []", - "Display per_cpu variables", 3, KDB_REPEAT_NONE); + "Display per_cpu variables", 3, 0); kdb_register_flags("grephelp", kdb_grep_help, "", - "Display help on | grep", 0, KDB_REPEAT_NONE); + "Display help on | grep", 0, 0); } /* Execute any commands defined in kdb_cmds. */ diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 1e3b36c75048..3da7e3043596 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -128,7 +128,7 @@ static int kdb_ftdump(int argc, const char **argv) static __init int kdb_ftrace_register(void) { kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]", - "Dump ftrace log", 0, KDB_REPEAT_NONE); + "Dump ftrace log", 0, 0); return 0; } -- cgit v1.2.3 From 9452e977ac17caf9f98a91b33d5e3c3357258c64 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Thu, 6 Nov 2014 14:36:45 +0000 Subject: kdb: Categorize kdb commands (similar to SysRq categorization) This patch introduces several new flags to collect kdb commands into groups (later allowing them to be optionally disabled). This follows similar prior art to enable/disable magic sysrq commands. The commands have been categorized as follows: Always on: go (w/o args), env, set, help, ?, cpu (w/o args), sr, dmesg, disable_nmi, defcmd, summary, grephelp Mem read: md, mdr, mdp, mds, ef, bt (with args), per_cpu Mem write: mm Reg read: rd Reg write: go (with args), rm Inspect: bt (w/o args), btp, bta, btc, btt, ps, pid, lsmod Flow ctrl: bp, bl, bph, bc, be, bd, ss Signal: kill Reboot: reboot All: cpu, kgdb, (and all of the above), nmi_console Signed-off-by: Daniel Thompson Cc: Jason Wessel Signed-off-by: Jason Wessel --- include/linux/kdb.h | 48 +++++++++++++++++- kernel/debug/kdb/kdb_bp.c | 21 +++++--- kernel/debug/kdb/kdb_main.c | 120 ++++++++++++++++++++++++++++++++------------ kernel/trace/trace_kdb.c | 2 +- 4 files changed, 148 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 39b44b37c8dc..f1fe36185c17 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -13,9 +13,53 @@ * Copyright (C) 2009 Jason Wessel */ +/* Shifted versions of the command enable bits are be used if the command + * has no arguments (see kdb_check_flags). This allows commands, such as + * go, to have different permissions depending upon whether it is called + * with an argument. + */ +#define KDB_ENABLE_NO_ARGS_SHIFT 10 + typedef enum { - KDB_REPEAT_NO_ARGS = 0x1, /* Repeat the command w/o arguments */ - KDB_REPEAT_WITH_ARGS = 0x2, /* Repeat the command w/ its arguments */ + KDB_ENABLE_ALL = (1 << 0), /* Enable everything */ + KDB_ENABLE_MEM_READ = (1 << 1), + KDB_ENABLE_MEM_WRITE = (1 << 2), + KDB_ENABLE_REG_READ = (1 << 3), + KDB_ENABLE_REG_WRITE = (1 << 4), + KDB_ENABLE_INSPECT = (1 << 5), + KDB_ENABLE_FLOW_CTRL = (1 << 6), + KDB_ENABLE_SIGNAL = (1 << 7), + KDB_ENABLE_REBOOT = (1 << 8), + /* User exposed values stop here, all remaining flags are + * exclusively used to describe a commands behaviour. + */ + + KDB_ENABLE_ALWAYS_SAFE = (1 << 9), + KDB_ENABLE_MASK = (1 << KDB_ENABLE_NO_ARGS_SHIFT) - 1, + + KDB_ENABLE_ALL_NO_ARGS = KDB_ENABLE_ALL << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_MEM_READ_NO_ARGS = KDB_ENABLE_MEM_READ + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_MEM_WRITE_NO_ARGS = KDB_ENABLE_MEM_WRITE + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_REG_READ_NO_ARGS = KDB_ENABLE_REG_READ + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_REG_WRITE_NO_ARGS = KDB_ENABLE_REG_WRITE + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_INSPECT_NO_ARGS = KDB_ENABLE_INSPECT + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_FLOW_CTRL_NO_ARGS = KDB_ENABLE_FLOW_CTRL + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_SIGNAL_NO_ARGS = KDB_ENABLE_SIGNAL + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_REBOOT_NO_ARGS = KDB_ENABLE_REBOOT + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_ALWAYS_SAFE_NO_ARGS = KDB_ENABLE_ALWAYS_SAFE + << KDB_ENABLE_NO_ARGS_SHIFT, + KDB_ENABLE_MASK_NO_ARGS = KDB_ENABLE_MASK << KDB_ENABLE_NO_ARGS_SHIFT, + + KDB_REPEAT_NO_ARGS = 0x40000000, /* Repeat the command w/o arguments */ + KDB_REPEAT_WITH_ARGS = 0x80000000, /* Repeat the command with args */ } kdb_cmdflags_t; typedef int (*kdb_func_t)(int, const char **); diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index f8844fb55311..e1dbf4a2c69e 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -532,21 +532,28 @@ void __init kdb_initbptab(void) bp->bp_free = 1; kdb_register_flags("bp", kdb_bp, "[]", - "Set/Display breakpoints", 0, KDB_REPEAT_NO_ARGS); + "Set/Display breakpoints", 0, + KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS); kdb_register_flags("bl", kdb_bp, "[]", - "Display breakpoints", 0, KDB_REPEAT_NO_ARGS); + "Display breakpoints", 0, + KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS); if (arch_kgdb_ops.flags & KGDB_HW_BREAKPOINT) kdb_register_flags("bph", kdb_bp, "[]", - "[datar [length]|dataw [length]] Set hw brk", 0, KDB_REPEAT_NO_ARGS); + "[datar [length]|dataw [length]] Set hw brk", 0, + KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS); kdb_register_flags("bc", kdb_bc, "", - "Clear Breakpoint", 0, 0); + "Clear Breakpoint", 0, + KDB_ENABLE_FLOW_CTRL); kdb_register_flags("be", kdb_bc, "", - "Enable Breakpoint", 0, 0); + "Enable Breakpoint", 0, + KDB_ENABLE_FLOW_CTRL); kdb_register_flags("bd", kdb_bc, "", - "Disable Breakpoint", 0, 0); + "Disable Breakpoint", 0, + KDB_ENABLE_FLOW_CTRL); kdb_register_flags("ss", kdb_ss, "", - "Single Step", 1, KDB_REPEAT_NO_ARGS); + "Single Step", 1, + KDB_ENABLE_FLOW_CTRL | KDB_REPEAT_NO_ARGS); /* * Architecture dependent initialization. */ diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 538bf1dce26a..fae1fc3962f8 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -187,6 +187,26 @@ struct task_struct *kdb_curr_task(int cpu) return p; } +/* + * Check whether the flags of the current command and the permissions + * of the kdb console has allow a command to be run. + */ +static inline bool kdb_check_flags(kdb_cmdflags_t flags, int permissions, + bool no_args) +{ + /* permissions comes from userspace so needs massaging slightly */ + permissions &= KDB_ENABLE_MASK; + permissions |= KDB_ENABLE_ALWAYS_SAFE; + + /* some commands change group when launched with no arguments */ + if (no_args) + permissions |= permissions << KDB_ENABLE_NO_ARGS_SHIFT; + + flags |= KDB_ENABLE_ALL; + + return permissions & flags; +} + /* * kdbgetenv - This function will return the character string value of * an environment variable. @@ -641,8 +661,13 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0) if (!s->count) s->usable = 0; if (s->usable) - kdb_register(s->name, kdb_exec_defcmd, - s->usage, s->help, 0); + /* macros are always safe because when executed each + * internal command re-enters kdb_parse() and is + * safety checked individually. + */ + kdb_register_flags(s->name, kdb_exec_defcmd, s->usage, + s->help, 0, + KDB_ENABLE_ALWAYS_SAFE); return 0; } if (!s->usable) @@ -2757,78 +2782,107 @@ static void __init kdb_inittab(void) kdb_register_flags("md", kdb_md, "", "Display Memory Contents, also mdWcN, e.g. md8c1", 1, - KDB_REPEAT_NO_ARGS); + KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS); kdb_register_flags("mdr", kdb_md, " ", - "Display Raw Memory", 0, KDB_REPEAT_NO_ARGS); + "Display Raw Memory", 0, + KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS); kdb_register_flags("mdp", kdb_md, " ", - "Display Physical Memory", 0, KDB_REPEAT_NO_ARGS); + "Display Physical Memory", 0, + KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS); kdb_register_flags("mds", kdb_md, "", - "Display Memory Symbolically", 0, KDB_REPEAT_NO_ARGS); + "Display Memory Symbolically", 0, + KDB_ENABLE_MEM_READ | KDB_REPEAT_NO_ARGS); kdb_register_flags("mm", kdb_mm, " ", - "Modify Memory Contents", 0, KDB_REPEAT_NO_ARGS); + "Modify Memory Contents", 0, + KDB_ENABLE_MEM_WRITE | KDB_REPEAT_NO_ARGS); kdb_register_flags("go", kdb_go, "[]", - "Continue Execution", 1, 0); + "Continue Execution", 1, + KDB_ENABLE_REG_WRITE | KDB_ENABLE_ALWAYS_SAFE_NO_ARGS); kdb_register_flags("rd", kdb_rd, "", - "Display Registers", 0, 0); + "Display Registers", 0, + KDB_ENABLE_REG_READ); kdb_register_flags("rm", kdb_rm, " ", - "Modify Registers", 0, 0); + "Modify Registers", 0, + KDB_ENABLE_REG_WRITE); kdb_register_flags("ef", kdb_ef, "", - "Display exception frame", 0, 0); + "Display exception frame", 0, + KDB_ENABLE_MEM_READ); kdb_register_flags("bt", kdb_bt, "[]", - "Stack traceback", 1, 0); + "Stack traceback", 1, + KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS); kdb_register_flags("btp", kdb_bt, "", - "Display stack for process ", 0, 0); + "Display stack for process ", 0, + KDB_ENABLE_INSPECT); kdb_register_flags("bta", kdb_bt, "[D|R|S|T|C|Z|E|U|I|M|A]", - "Backtrace all processes matching state flag", 0, 0); + "Backtrace all processes matching state flag", 0, + KDB_ENABLE_INSPECT); kdb_register_flags("btc", kdb_bt, "", - "Backtrace current process on each cpu", 0, 0); + "Backtrace current process on each cpu", 0, + KDB_ENABLE_INSPECT); kdb_register_flags("btt", kdb_bt, "", "Backtrace process given its struct task address", 0, - 0); + KDB_ENABLE_MEM_READ | KDB_ENABLE_INSPECT_NO_ARGS); kdb_register_flags("env", kdb_env, "", - "Show environment variables", 0, 0); + "Show environment variables", 0, + KDB_ENABLE_ALWAYS_SAFE); kdb_register_flags("set", kdb_set, "", - "Set environment variables", 0, 0); + "Set environment variables", 0, + KDB_ENABLE_ALWAYS_SAFE); kdb_register_flags("help", kdb_help, "", - "Display Help Message", 1, 0); + "Display Help Message", 1, + KDB_ENABLE_ALWAYS_SAFE); kdb_register_flags("?", kdb_help, "", - "Display Help Message", 0, 0); + "Display Help Message", 0, + KDB_ENABLE_ALWAYS_SAFE); kdb_register_flags("cpu", kdb_cpu, "", - "Switch to new cpu", 0, 0); + "Switch to new cpu", 0, + KDB_ENABLE_ALWAYS_SAFE_NO_ARGS); kdb_register_flags("kgdb", kdb_kgdb, "", "Enter kgdb mode", 0, 0); kdb_register_flags("ps", kdb_ps, "[|A]", - "Display active task list", 0, 0); + "Display active task list", 0, + KDB_ENABLE_INSPECT); kdb_register_flags("pid", kdb_pid, "", - "Switch to another task", 0, 0); + "Switch to another task", 0, + KDB_ENABLE_INSPECT); kdb_register_flags("reboot", kdb_reboot, "", - "Reboot the machine immediately", 0, 0); + "Reboot the machine immediately", 0, + KDB_ENABLE_REBOOT); #if defined(CONFIG_MODULES) kdb_register_flags("lsmod", kdb_lsmod, "", - "List loaded kernel modules", 0, 0); + "List loaded kernel modules", 0, + KDB_ENABLE_INSPECT); #endif #if defined(CONFIG_MAGIC_SYSRQ) kdb_register_flags("sr", kdb_sr, "", - "Magic SysRq key", 0, 0); + "Magic SysRq key", 0, + KDB_ENABLE_ALWAYS_SAFE); #endif #if defined(CONFIG_PRINTK) kdb_register_flags("dmesg", kdb_dmesg, "[lines]", - "Display syslog buffer", 0, 0); + "Display syslog buffer", 0, + KDB_ENABLE_ALWAYS_SAFE); #endif if (arch_kgdb_ops.enable_nmi) { kdb_register_flags("disable_nmi", kdb_disable_nmi, "", - "Disable NMI entry to KDB", 0, 0); + "Disable NMI entry to KDB", 0, + KDB_ENABLE_ALWAYS_SAFE); } kdb_register_flags("defcmd", kdb_defcmd, "name \"usage\" \"help\"", - "Define a set of commands, down to endefcmd", 0, 0); + "Define a set of commands, down to endefcmd", 0, + KDB_ENABLE_ALWAYS_SAFE); kdb_register_flags("kill", kdb_kill, "<-signal> ", - "Send a signal to a process", 0, 0); + "Send a signal to a process", 0, + KDB_ENABLE_SIGNAL); kdb_register_flags("summary", kdb_summary, "", - "Summarize the system", 4, 0); + "Summarize the system", 4, + KDB_ENABLE_ALWAYS_SAFE); kdb_register_flags("per_cpu", kdb_per_cpu, " [] []", - "Display per_cpu variables", 3, 0); + "Display per_cpu variables", 3, + KDB_ENABLE_MEM_READ); kdb_register_flags("grephelp", kdb_grep_help, "", - "Display help on | grep", 0, 0); + "Display help on | grep", 0, + KDB_ENABLE_ALWAYS_SAFE); } /* Execute any commands defined in kdb_cmds. */ diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 3da7e3043596..1058f6bd8399 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -128,7 +128,7 @@ static int kdb_ftdump(int argc, const char **argv) static __init int kdb_ftrace_register(void) { kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]", - "Dump ftrace log", 0, 0); + "Dump ftrace log", 0, KDB_ENABLE_ALWAYS_SAFE); return 0; } -- cgit v1.2.3 From 420c2b1b0df84f5956036b5185cc1e11d247817d Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 6 Nov 2014 14:36:46 +0000 Subject: kdb: Add enable mask for groups of commands Currently all kdb commands are enabled whenever kdb is deployed. This makes it difficult to deploy kdb to help debug certain types of systems. Android phones provide one example; the FIQ debugger found on some Android devices has a deliberately weak set of commands to allow the debugger to enabled very late in the production cycle. Certain kiosk environments offer another interesting case where an engineer might wish to probe the system state using passive inspection commands without providing sufficient power for a passer by to root it. Without any restrictions, obtaining the root rights via KDB is a matter of a few commands, and works everywhere. For example, log in as a normal user: cbou:~$ id uid=1001(cbou) gid=1001(cbou) groups=1001(cbou) Now enter KDB (for example via sysrq): Entering kdb (current=0xffff8800065bc740, pid 920) due to Keyboard Entry kdb> ps 23 sleeping system daemon (state M) processes suppressed, use 'ps A' to see all. Task Addr Pid Parent [*] cpu State Thread Command 0xffff8800065bc740 920 919 1 0 R 0xffff8800065bca20 *bash 0xffff880007078000 1 0 0 0 S 0xffff8800070782e0 init [...snip...] 0xffff8800065be3c0 918 1 0 0 S 0xffff8800065be6a0 getty 0xffff8800065b9c80 919 1 0 0 S 0xffff8800065b9f60 login 0xffff8800065bc740 920 919 1 0 R 0xffff8800065bca20 *bash All we need is the offset of cred pointers. We can look up the offset in the distro's kernel source, but it is unnecessary. We can just start dumping init's task_struct, until we see the process name: kdb> md 0xffff880007078000 0xffff880007078000 0000000000000001 ffff88000703c000 ................ 0xffff880007078010 0040210000000002 0000000000000000 .....!@......... [...snip...] 0xffff8800070782b0 ffff8800073e0580 ffff8800073e0580 ..>.......>..... 0xffff8800070782c0 0000000074696e69 0000000000000000 init............ ^ Here, 'init'. Creds are just above it, so the offset is 0x02b0. Now we set up init's creds for our non-privileged shell: kdb> mm 0xffff8800065bc740+0x02b0 0xffff8800073e0580 0xffff8800065bc9f0 = 0xffff8800073e0580 kdb> mm 0xffff8800065bc740+0x02b8 0xffff8800073e0580 0xffff8800065bc9f8 = 0xffff8800073e0580 And thus gaining the root: kdb> go cbou:~$ id uid=0(root) gid=0(root) groups=0(root) cbou:~$ bash root:~# p.s. No distro enables kdb by default (although, with a nice KDB-over-KMS feature availability, I would expect at least some would enable it), so it's not actually some kind of a major issue. Signed-off-by: Anton Vorontsov Signed-off-by: John Stultz Signed-off-by: Daniel Thompson Cc: Jason Wessel Signed-off-by: Jason Wessel --- include/linux/kdb.h | 1 + kernel/debug/kdb/kdb_main.c | 30 +++++++++++++++++++++++++++++- 2 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index f1fe36185c17..75ae2e2631fc 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -105,6 +105,7 @@ extern atomic_t kdb_event; #define KDB_BADLENGTH (-19) #define KDB_NOBP (-20) #define KDB_BADADDR (-21) +#define KDB_NOPERM (-22) /* * kdb_diemsg diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index fae1fc3962f8..fe1ac56b62e9 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -12,6 +12,7 @@ */ #include +#include #include #include #include @@ -23,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -42,6 +44,12 @@ #include #include "kdb_private.h" +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "kdb." + +static int kdb_cmd_enabled; +module_param_named(cmd_enable, kdb_cmd_enabled, int, 0600); + #define GREP_LEN 256 char kdb_grep_string[GREP_LEN]; int kdb_grepping_flag; @@ -121,6 +129,7 @@ static kdbmsg_t kdbmsgs[] = { KDBMSG(BADLENGTH, "Invalid length field"), KDBMSG(NOBP, "No Breakpoint exists"), KDBMSG(BADADDR, "Invalid address"), + KDBMSG(NOPERM, "Permission denied"), }; #undef KDBMSG @@ -495,6 +504,15 @@ int kdbgetaddrarg(int argc, const char **argv, int *nextarg, char *cp; kdb_symtab_t symtab; + /* + * If the enable flags prohibit both arbitrary memory access + * and flow control then there are no reasonable grounds to + * provide symbol lookup. + */ + if (!kdb_check_flags(KDB_ENABLE_MEM_READ | KDB_ENABLE_FLOW_CTRL, + kdb_cmd_enabled, false)) + return KDB_NOPERM; + /* * Process arguments which follow the following syntax: * @@ -1028,6 +1046,10 @@ int kdb_parse(const char *cmdstr) if (i < kdb_max_commands) { int result; + + if (!kdb_check_flags(tp->cmd_flags, kdb_cmd_enabled, argc <= 1)) + return KDB_NOPERM; + KDB_STATE_SET(CMD); result = (*tp->cmd_func)(argc-1, (const char **)argv); if (result && ignore_errors && result > KDB_CMD_GO) @@ -1939,10 +1961,14 @@ static int kdb_rm(int argc, const char **argv) */ static int kdb_sr(int argc, const char **argv) { + bool check_mask = + !kdb_check_flags(KDB_ENABLE_ALL, kdb_cmd_enabled, false); + if (argc != 1) return KDB_ARGCOUNT; + kdb_trap_printk++; - __handle_sysrq(*argv[1], false); + __handle_sysrq(*argv[1], check_mask); kdb_trap_printk--; return 0; @@ -2393,6 +2419,8 @@ static int kdb_help(int argc, const char **argv) return 0; if (!kt->cmd_name) continue; + if (!kdb_check_flags(kt->cmd_flags, kdb_cmd_enabled, true)) + continue; if (strlen(kt->cmd_usage) > 20) space = "\n "; kdb_printf("%-15.15s %-20s%s%s\n", kt->cmd_name, -- cgit v1.2.3 From d02dc27db0dc74683efc4a2b36f55f5594451f38 Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Sun, 4 Jan 2015 18:55:03 +0800 Subject: ACPI / processor: Rename acpi_(un)map_lsapic() to acpi_(un)map_cpu() acpi_map_lsapic() will allocate a logical CPU number and map it to physical CPU id (such as APIC id) for the hot-added CPU, it will also do some mapping for NUMA node id and etc, acpi_unmap_lsapic() will do the reverse. We can see that the name of the function is a little bit confusing and arch (IA64) dependent so rename them as acpi_(un)map_cpu() to make arch agnostic and explicit. Signed-off-by: Hanjun Guo Signed-off-by: Rafael J. Wysocki --- arch/ia64/kernel/acpi.c | 9 ++++----- arch/x86/kernel/acpi/boot.c | 9 ++++----- drivers/acpi/acpi_processor.c | 6 +++--- include/linux/acpi.h | 4 ++-- 4 files changed, 13 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 615ef81def49..e795cb848154 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -893,13 +893,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) +int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu) { return _acpi_map_lsapic(handle, physid, pcpu); } -EXPORT_SYMBOL(acpi_map_lsapic); +EXPORT_SYMBOL(acpi_map_cpu); -int acpi_unmap_lsapic(int cpu) +int acpi_unmap_cpu(int cpu) { ia64_cpu_to_sapicid[cpu] = -1; set_cpu_present(cpu, false); @@ -910,8 +910,7 @@ int acpi_unmap_lsapic(int cpu) return (0); } - -EXPORT_SYMBOL(acpi_unmap_lsapic); +EXPORT_SYMBOL(acpi_unmap_cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ #ifdef CONFIG_ACPI_NUMA diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4433a4be8171..d1626364a28a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -750,13 +750,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) +int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu) { return _acpi_map_lsapic(handle, physid, pcpu); } -EXPORT_SYMBOL(acpi_map_lsapic); +EXPORT_SYMBOL(acpi_map_cpu); -int acpi_unmap_lsapic(int cpu) +int acpi_unmap_cpu(int cpu) { #ifdef CONFIG_ACPI_NUMA set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); @@ -768,8 +768,7 @@ int acpi_unmap_lsapic(int cpu) return (0); } - -EXPORT_SYMBOL(acpi_unmap_lsapic); +EXPORT_SYMBOL(acpi_unmap_cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index f02b29eb0fda..1020b1b53a17 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -180,13 +180,13 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr) cpu_maps_update_begin(); cpu_hotplug_begin(); - ret = acpi_map_lsapic(pr->handle, pr->phys_id, &pr->id); + ret = acpi_map_cpu(pr->handle, pr->phys_id, &pr->id); if (ret) goto out; ret = arch_register_cpu(pr->id); if (ret) { - acpi_unmap_lsapic(pr->id); + acpi_unmap_cpu(pr->id); goto out; } @@ -461,7 +461,7 @@ static void acpi_processor_remove(struct acpi_device *device) /* Remove the CPU. */ arch_unregister_cpu(pr->id); - acpi_unmap_lsapic(pr->id); + acpi_unmap_cpu(pr->id); cpu_hotplug_done(); cpu_maps_update_done(); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 856d381b1d5b..d459cd17b477 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -147,8 +147,8 @@ void acpi_numa_arch_fixup(void); #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ -int acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu); -int acpi_unmap_lsapic(int cpu); +int acpi_map_cpu(acpi_handle handle, int physid, int *pcpu); +int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); -- cgit v1.2.3 From fee7e49d45149fba60156f5b59014f764d3e3728 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 6 Jan 2015 13:00:05 -0800 Subject: mm: propagate error from stack expansion even for guard page Jay Foad reports that the address sanitizer test (asan) sometimes gets confused by a stack pointer that ends up being outside the stack vma that is reported by /proc/maps. This happens due to an interaction between RLIMIT_STACK and the guard page: when we do the guard page check, we ignore the potential error from the stack expansion, which effectively results in a missing guard page, since the expected stack expansion won't have been done. And since /proc/maps explicitly ignores the guard page (commit d7824370e263: "mm: fix up some user-visible effects of the stack guard page"), the stack pointer ends up being outside the reported stack area. This is the minimal patch: it just propagates the error. It also effectively makes the guard page part of the stack limit, which in turn measn that the actual real stack is one page less than the stack limit. Let's see if anybody notices. We could teach acct_stack_growth() to allow an extra page for a grow-up/grow-down stack in the rlimit test, but I don't want to add more complexity if it isn't needed. Reported-and-tested-by: Jay Foad Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- mm/memory.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f80d0194c9bc..80fc92a49649 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1952,7 +1952,7 @@ extern int expand_downwards(struct vm_area_struct *vma, #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else - #define expand_upwards(vma, address) do { } while (0) + #define expand_upwards(vma, address) (0) #endif /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ diff --git a/mm/memory.c b/mm/memory.c index ca920d1fd314..d7e497e98f46 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2593,7 +2593,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (prev && prev->vm_end == address) return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - expand_downwards(vma, address - PAGE_SIZE); + return expand_downwards(vma, address - PAGE_SIZE); } if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { struct vm_area_struct *next = vma->vm_next; @@ -2602,7 +2602,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (next && next->vm_start == address + PAGE_SIZE) return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; - expand_upwards(vma, address + PAGE_SIZE); + return expand_upwards(vma, address + PAGE_SIZE); } return 0; } -- cgit v1.2.3 From d7d5a007b1c64c617ce3ee30c973ed0bb93443d9 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 19 Dec 2014 14:00:41 +0300 Subject: libceph: fix sparse endianness warnings The only real issue is the one in auth_x.c and it came with 3.19-rc1 merge. Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 4 ++-- net/ceph/auth_x.c | 2 +- net/ceph/mon_client.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 5d86416d35f2..61b19c46bdb3 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -87,8 +87,8 @@ struct ceph_osd_req_op { struct ceph_osd_data osd_data; } extent; struct { - __le32 name_len; - __le32 value_len; + u32 name_len; + u32 value_len; __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ struct ceph_osd_data osd_data; diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 15845814a0f2..ba6eb17226da 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -676,7 +676,7 @@ static int calcu_signature(struct ceph_x_authorizer *au, int ret; char tmp_enc[40]; __le32 tmp[5] = { - 16u, msg->hdr.crc, msg->footer.front_crc, + cpu_to_le32(16), msg->hdr.crc, msg->footer.front_crc, msg->footer.middle_crc, msg->footer.data_crc, }; ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp), diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index a83062ceeec9..f2148e22b148 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -717,7 +717,7 @@ static int get_poolop_reply_buf(const char *src, size_t src_len, if (src_len != sizeof(u32) + dst_len) return -EINVAL; - buf_len = le32_to_cpu(*(u32 *)src); + buf_len = le32_to_cpu(*(__le32 *)src); if (buf_len != dst_len) return -EINVAL; -- cgit v1.2.3 From 7a3ef208e662f4b63d43a23f61a64a129c525bbc Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 8 Jan 2015 14:32:15 -0800 Subject: mm: prevent endless growth of anon_vma hierarchy Constantly forking task causes unlimited grow of anon_vma chain. Each next child allocates new level of anon_vmas and links vma to all previous levels because pages might be inherited from any level. This patch adds heuristic which decides to reuse existing anon_vma instead of forking new one. It adds counter anon_vma->degree which counts linked vmas and directly descending anon_vmas and reuses anon_vma if counter is lower than two. As a result each anon_vma has either vma or at least two descending anon_vmas. In such trees half of nodes are leafs with alive vmas, thus count of anon_vmas is no more than two times bigger than count of vmas. This heuristic reuses anon_vmas as few as possible because each reuse adds false aliasing among vmas and rmap walker ought to scan more ptes when it searches where page is might be mapped. Link: http://lkml.kernel.org/r/20120816024610.GA5350@evergreen.ssec.wisc.edu Fixes: 5beb49305251 ("mm: change anon_vma linking to fix multi-process server scalability issue") [akpm@linux-foundation.org: fix typo, per Rik] Signed-off-by: Konstantin Khlebnikov Reported-by: Daniel Forrest Tested-by: Michal Hocko Tested-by: Jerome Marchand Reviewed-by: Michal Hocko Reviewed-by: Rik van Riel Cc: [2.6.34+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 10 ++++++++++ mm/rmap.c | 42 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 51 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c0c2bce6b0b7..d9d7e7e56352 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -36,6 +36,16 @@ struct anon_vma { */ atomic_t refcount; + /* + * Count of child anon_vmas and VMAs which points to this anon_vma. + * + * This counter is used for making decision about reusing anon_vma + * instead of forking new one. See comments in function anon_vma_clone. + */ + unsigned degree; + + struct anon_vma *parent; /* Parent of this anon_vma */ + /* * NOTE: the LSB of the rb_root.rb_node is set by * mm_take_all_locks() _after_ taking the above lock. So the diff --git a/mm/rmap.c b/mm/rmap.c index c5bc241127b2..71cd5bd0c17d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -72,6 +72,8 @@ static inline struct anon_vma *anon_vma_alloc(void) anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); + anon_vma->degree = 1; /* Reference for first vma */ + anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. @@ -188,6 +190,8 @@ int anon_vma_prepare(struct vm_area_struct *vma) if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); + /* vma reference or self-parent link for new root */ + anon_vma->degree++; allocated = NULL; avc = NULL; } @@ -236,6 +240,14 @@ static inline void unlock_anon_vma_root(struct anon_vma *root) /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. + * + * If dst->anon_vma is NULL this function tries to find and reuse existing + * anon_vma which has no vmas and only one child anon_vma. This prevents + * degradation of anon_vma hierarchy to endless linear chain in case of + * constantly forking task. On the other hand, an anon_vma with more than one + * child isn't reused even if there was no alive vma, thus rmap walker has a + * good chance of avoiding scanning the whole hierarchy when it searches where + * page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { @@ -256,7 +268,21 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); + + /* + * Reuse existing anon_vma if its degree lower than two, + * that means it has no vma and only one anon_vma child. + * + * Do not chose parent anon_vma, otherwise first child + * will always reuse it. Root anon_vma is never reused: + * it has self-parent reference and at least one child. + */ + if (!dst->anon_vma && anon_vma != src->anon_vma && + anon_vma->degree < 2) + dst->anon_vma = anon_vma; } + if (dst->anon_vma) + dst->anon_vma->degree++; unlock_anon_vma_root(root); return 0; @@ -280,6 +306,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) if (!pvma->anon_vma) return 0; + /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ + vma->anon_vma = NULL; + /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. @@ -288,6 +317,10 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) if (error) return error; + /* An existing anon_vma has been reused, all done then. */ + if (vma->anon_vma) + return 0; + /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) @@ -301,6 +334,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; + anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until @@ -311,6 +345,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); + anon_vma->parent->degree++; anon_vma_unlock_write(anon_vma); return 0; @@ -341,12 +376,16 @@ void unlink_anon_vmas(struct vm_area_struct *vma) * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ - if (RB_EMPTY_ROOT(&anon_vma->rb_root)) + if (RB_EMPTY_ROOT(&anon_vma->rb_root)) { + anon_vma->parent->degree--; continue; + } list_del(&avc->same_vma); anon_vma_chain_free(avc); } + if (vma->anon_vma) + vma->anon_vma->degree--; unlock_anon_vma_root(root); /* @@ -357,6 +396,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; + BUG_ON(anon_vma->degree); put_anon_vma(anon_vma); list_del(&avc->same_vma); -- cgit v1.2.3 From 2d6d7f98284648c5ed113fe22a132148950b140f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 8 Jan 2015 14:32:18 -0800 Subject: mm: protect set_page_dirty() from ongoing truncation Tejun, while reviewing the code, spotted the following race condition between the dirtying and truncation of a page: __set_page_dirty_nobuffers() __delete_from_page_cache() if (TestSetPageDirty(page)) page->mapping = NULL if (PageDirty()) dec_zone_page_state(page, NR_FILE_DIRTY); dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); if (page->mapping) account_page_dirtied(page) __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); which results in an imbalance of NR_FILE_DIRTY and BDI_RECLAIMABLE. Dirtiers usually lock out truncation, either by holding the page lock directly, or in case of zap_pte_range(), by pinning the mapcount with the page table lock held. The notable exception to this rule, though, is do_wp_page(), for which this race exists. However, do_wp_page() already waits for a locked page to unlock before setting the dirty bit, in order to prevent a race where clear_page_dirty() misses the page bit in the presence of dirty ptes. Upgrade that wait to a fully locked set_page_dirty() to also cover the situation explained above. Afterwards, the code in set_page_dirty() dealing with a truncation race is no longer needed. Remove it. Reported-by: Tejun Heo Signed-off-by: Johannes Weiner Acked-by: Kirill A. Shutemov Reviewed-by: Jan Kara Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 1 - mm/memory.c | 27 +++++++++++++++++---------- mm/page-writeback.c | 43 ++++++++++++------------------------------- 3 files changed, 29 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a219be961c0a..00048339c23e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -177,7 +177,6 @@ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); -void set_page_dirty_balance(struct page *page); void writeback_set_ratelimit(void); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); diff --git a/mm/memory.c b/mm/memory.c index d7e497e98f46..c6565f00fb38 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2137,17 +2137,24 @@ reuse: if (!dirty_page) return ret; - /* - * Yes, Virginia, this is actually required to prevent a race - * with clear_page_dirty_for_io() from clearing the page dirty - * bit after it clear all dirty ptes, but before a racing - * do_wp_page installs a dirty pte. - * - * do_shared_fault is protected similarly. - */ if (!page_mkwrite) { - wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page); + struct address_space *mapping; + int dirtied; + + lock_page(dirty_page); + dirtied = set_page_dirty(dirty_page); + VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page); + mapping = dirty_page->mapping; + unlock_page(dirty_page); + + if (dirtied && mapping) { + /* + * Some device drivers do not set page.mapping + * but still dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + /* file_update_time outside page_lock */ if (vma->vm_file) file_update_time(vma->vm_file); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d5d81f5384d1..6f4335238e33 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1541,16 +1541,6 @@ pause: bdi_start_background_writeback(bdi); } -void set_page_dirty_balance(struct page *page) -{ - if (set_page_dirty(page)) { - struct address_space *mapping = page_mapping(page); - - if (mapping) - balance_dirty_pages_ratelimited(mapping); - } -} - static DEFINE_PER_CPU(int, bdp_ratelimits); /* @@ -2123,32 +2113,25 @@ EXPORT_SYMBOL(account_page_dirtied); * page dirty in that case, but not all the buffers. This is a "bottom-up" * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. * - * Most callers have locked the page, which pins the address_space in memory. - * But zap_pte_range() does not lock the page, however in that case the - * mapping is pinned by the vma's ->vm_file reference. - * - * We take care to handle the case where the page was truncated from the - * mapping by re-checking page_mapping() inside tree_lock. + * The caller must ensure this doesn't race with truncation. Most will simply + * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and + * the pte lock held, which also locks out truncation. */ int __set_page_dirty_nobuffers(struct page *page) { if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); - struct address_space *mapping2; unsigned long flags; if (!mapping) return 1; spin_lock_irqsave(&mapping->tree_lock, flags); - mapping2 = page_mapping(page); - if (mapping2) { /* Race with truncate? */ - BUG_ON(mapping2 != mapping); - WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); - account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - } + BUG_ON(page_mapping(page) != mapping); + WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); + account_page_dirtied(page, mapping); + radix_tree_tag_set(&mapping->page_tree, page_index(page), + PAGECACHE_TAG_DIRTY); spin_unlock_irqrestore(&mapping->tree_lock, flags); if (mapping->host) { /* !PageAnon && !swapper_space */ @@ -2305,12 +2288,10 @@ int clear_page_dirty_for_io(struct page *page) /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the page dirty - * at this point. We do this by having them hold the - * page lock at some point after installing their - * pte, but before marking the page dirty. - * Pages are always locked coming in here, so we get - * the desired exclusion. See mm/memory.c:do_wp_page() - * for more comments. + * at this point. We do this by having them hold the + * page lock while dirtying the page, and pages are + * always locked coming in here, so we get the desired + * exclusion. */ if (TestClearPageDirty(page)) { dec_zone_page_state(page, NR_FILE_DIRTY); -- cgit v1.2.3 From 75069f2b5bfb5164beafaf3da597279c25b5535a Mon Sep 17 00:00:00 2001 From: David Drysdale Date: Thu, 8 Jan 2015 14:32:29 -0800 Subject: vfs: renumber FMODE_NONOTIFY and add to uniqueness check Fix clashing values for O_PATH and FMODE_NONOTIFY on sparc. The clashing O_PATH value was added in commit 5229645bdc35 ("vfs: add nonconflicting values for O_PATH") but this can't be changed as it is user-visible. FMODE_NONOTIFY is only used internally in the kernel, but it is in the same numbering space as the other O_* flags, as indicated by the comment at the top of include/uapi/asm-generic/fcntl.h (and its use in fs/notify/fanotify/fanotify_user.c). So renumber it to avoid the clash. All of this has happened before (commit 12ed2e36c98a: "fanotify: FMODE_NONOTIFY and __O_SYNC in sparc conflict"), and all of this will happen again -- so update the uniqueness check in fcntl_init() to include __FMODE_NONOTIFY. Signed-off-by: David Drysdale Acked-by: David S. Miller Acked-by: Jan Kara Cc: Heinrich Schuchardt Cc: Alexander Viro Cc: Arnd Bergmann Cc: Stephen Rothwell Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fcntl.c | 5 +++-- include/linux/fs.h | 2 +- include/uapi/asm-generic/fcntl.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/fcntl.c b/fs/fcntl.c index 99d440a4a6ba..ee85cd4e136a 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -740,14 +740,15 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( + BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | O_APPEND | /* O_NONBLOCK | */ __O_SYNC | O_DSYNC | FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | O_NOATIME | O_CLOEXEC | - __FMODE_EXEC | O_PATH | __O_TMPFILE + __FMODE_EXEC | O_PATH | __O_TMPFILE | + __FMODE_NONOTIFY )); fasync_cache = kmem_cache_create("fasync_cache", diff --git a/include/linux/fs.h b/include/linux/fs.h index f90c0282c114..42efe13077b6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -135,7 +135,7 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x1000000) +#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 7543b3e51331..e063effe0cc1 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -5,7 +5,7 @@ /* * FMODE_EXEC is 0x20 - * FMODE_NONOTIFY is 0x1000000 + * FMODE_NONOTIFY is 0x4000000 * These cannot be used by userspace O_* until internal and external open * flags are split. * -Eric Paris -- cgit v1.2.3 From 88a7c26af8dab2f2d69f5a6067eb670694ec38c0 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sun, 4 Jan 2015 10:36:19 -0800 Subject: perf: Move task_pt_regs sampling into arch code On x86_64, at least, task_pt_regs may be only partially initialized in many contexts, so x86_64 should not use it without extra care from interrupt context, let alone NMI context. This will allow x86_64 to override the logic and will supply some scratch space to use to make a cleaner copy of user regs. Tested-by: Jiri Olsa Signed-off-by: Andy Lutomirski Signed-off-by: Peter Zijlstra (Intel) Cc: Stephane Eranian Cc: chenggang.qcg@taobao.com Cc: Wu Fengguang Cc: Namhyung Kim Cc: Mike Galbraith Cc: Arjan van de Ven Cc: David Ahern Cc: Arnaldo Carvalho de Melo Cc: Catalin Marinas Cc: Jean Pihet Cc: Linus Torvalds Cc: Mark Salter Cc: Russell King Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/e431cd4c18c2e1c44c774f10758527fb2d1025c4.1420396372.git.luto@amacapital.net Signed-off-by: Ingo Molnar --- arch/arm/kernel/perf_regs.c | 8 ++++++++ arch/arm64/kernel/perf_regs.c | 8 ++++++++ arch/x86/kernel/perf_regs.c | 16 ++++++++++++++++ include/linux/perf_event.h | 12 +++++++----- include/linux/perf_regs.h | 16 ++++++++++++++++ kernel/events/core.c | 19 ++++++++----------- 6 files changed, 63 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c index 6e4379c67cbc..592dda3f21ff 100644 --- a/arch/arm/kernel/perf_regs.c +++ b/arch/arm/kernel/perf_regs.c @@ -28,3 +28,11 @@ u64 perf_reg_abi(struct task_struct *task) { return PERF_SAMPLE_REGS_ABI_32; } + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 6762ad705587..3f62b35fb6f1 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -50,3 +50,11 @@ u64 perf_reg_abi(struct task_struct *task) else return PERF_SAMPLE_REGS_ABI_64; } + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index e309cc5c276e..3bbbb1a4fb52 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task) { return PERF_SAMPLE_REGS_ABI_32; } + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} #else /* CONFIG_X86_64 */ #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ (1ULL << PERF_REG_X86_ES) | \ @@ -102,4 +110,12 @@ u64 perf_reg_abi(struct task_struct *task) else return PERF_SAMPLE_REGS_ABI_64; } + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} #endif /* CONFIG_X86_32 */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 486e84ccb1f9..4f7a61ca4b39 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -79,11 +79,6 @@ struct perf_branch_stack { struct perf_branch_entry entries[0]; }; -struct perf_regs { - __u64 abi; - struct pt_regs *regs; -}; - struct task_struct; /* @@ -610,7 +605,14 @@ struct perf_sample_data { u32 reserved; } cpu_entry; struct perf_callchain_entry *callchain; + + /* + * regs_user may point to task_pt_regs or to regs_user_copy, depending + * on arch details. + */ struct perf_regs regs_user; + struct pt_regs regs_user_copy; + struct perf_regs regs_intr; u64 stack_user_size; } ____cacheline_aligned; diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h index 3c73d5fe18be..a5f98d53d732 100644 --- a/include/linux/perf_regs.h +++ b/include/linux/perf_regs.h @@ -1,11 +1,19 @@ #ifndef _LINUX_PERF_REGS_H #define _LINUX_PERF_REGS_H +struct perf_regs { + __u64 abi; + struct pt_regs *regs; +}; + #ifdef CONFIG_HAVE_PERF_REGS #include u64 perf_reg_value(struct pt_regs *regs, int idx); int perf_reg_validate(u64 mask); u64 perf_reg_abi(struct task_struct *task); +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy); #else static inline u64 perf_reg_value(struct pt_regs *regs, int idx) { @@ -21,5 +29,13 @@ static inline u64 perf_reg_abi(struct task_struct *task) { return PERF_SAMPLE_REGS_ABI_NONE; } + +static inline void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs, + struct pt_regs *regs_user_copy) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} #endif /* CONFIG_HAVE_PERF_REGS */ #endif /* _LINUX_PERF_REGS_H */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 4c1ee7f2bebc..882f835a0d85 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4461,18 +4461,14 @@ perf_output_sample_regs(struct perf_output_handle *handle, } static void perf_sample_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs) + struct pt_regs *regs, + struct pt_regs *regs_user_copy) { - if (!user_mode(regs)) { - if (current->mm) - regs = task_pt_regs(current); - else - regs = NULL; - } - - if (regs) { - regs_user->abi = perf_reg_abi(current); + if (user_mode(regs)) { + regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; + } else if (current->mm) { + perf_get_regs_user(regs_user, regs, regs_user_copy); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; regs_user->regs = NULL; @@ -4951,7 +4947,8 @@ void perf_prepare_sample(struct perf_event_header *header, } if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER)) - perf_sample_regs_user(&data->regs_user, regs); + perf_sample_regs_user(&data->regs_user, regs, + &data->regs_user_copy); if (sample_type & PERF_SAMPLE_REGS_USER) { /* regs dump ABI info */ -- cgit v1.2.3