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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 From a940cb34fed73b2d4809a4575f2981d5927e2c21 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 9 Dec 2014 12:22:01 +0000 Subject: thermal: Fix cdev registration with THERMAL_NO_LIMIT on 64bit The size of unsigned long varies between 32 and 64 bit systems while the size of phandle arguments is always 32 bits per parameter. On 64-bit systems, cooling devices registered via of-thermal apis fail to bind when the min/max cooling state is specified as THERMAL_NO_LIMIT (-1UL) as there is a mis-match between the value read from the device tree (32bit) and the pre-processor define (64bit). As we're unlikely to need cooling states larger than 32 bits, and for consistency with the size of phandle arguments, explicitly limit THERMAL_NO_LIMIT to 32 bits. Reported-by: Hyungwoo Yang Acked-by: Zhang Rui Signed-off-by: Punit Agrawal Signed-off-by: Eduardo Valentin --- include/dt-bindings/thermal/thermal.h | 2 +- include/linux/thermal.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/dt-bindings/thermal/thermal.h b/include/dt-bindings/thermal/thermal.h index 59822a995858..b5e6b0069ac7 100644 --- a/include/dt-bindings/thermal/thermal.h +++ b/include/dt-bindings/thermal/thermal.h @@ -11,7 +11,7 @@ #define _DT_BINDINGS_THERMAL_THERMAL_H /* On cooling devices upper and lower limits */ -#define THERMAL_NO_LIMIT (-1UL) +#define THERMAL_NO_LIMIT (~0) #endif diff --git a/include/linux/thermal.h b/include/linux/thermal.h index ef90838b36a0..005586fdf82d 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -38,7 +38,7 @@ #define THERMAL_CSTATE_INVALID -1UL /* No upper/lower limit requirement */ -#define THERMAL_NO_LIMIT THERMAL_CSTATE_INVALID +#define THERMAL_NO_LIMIT ((u32)~0) /* Unit conversion macros */ #define KELVIN_TO_CELSIUS(t) (long)(((long)t-2732 >= 0) ? \ -- cgit v1.2.3-71-gd317 From 80e1dd82be59d247e899d8ce29389f84ed828994 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 3 Nov 2014 16:48:47 -0800 Subject: mfd: stmpe: add pull up/down register offsets for STMPE This adds the register offsets for pull up/down for the STMPE 1601, 1801 and 24xx expanders. This is used to bias GPIO lines and keypad lines. Signed-off-by: Linus Walleij Acked-by: Lee Jones Signed-off-by: Dmitry Torokhov --- drivers/mfd/stmpe.c | 4 ++++ drivers/mfd/stmpe.h | 3 +++ include/linux/mfd/stmpe.h | 2 ++ 3 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c index 02a17c388e87..2d29d17518c4 100644 --- a/drivers/mfd/stmpe.c +++ b/drivers/mfd/stmpe.c @@ -519,6 +519,7 @@ static const u8 stmpe1601_regs[] = { [STMPE_IDX_GPDR_LSB] = STMPE1601_REG_GPIO_SET_DIR_LSB, [STMPE_IDX_GPRER_LSB] = STMPE1601_REG_GPIO_RE_LSB, [STMPE_IDX_GPFER_LSB] = STMPE1601_REG_GPIO_FE_LSB, + [STMPE_IDX_GPPUR_LSB] = STMPE1601_REG_GPIO_PU_LSB, [STMPE_IDX_GPAFR_U_MSB] = STMPE1601_REG_GPIO_AF_U_MSB, [STMPE_IDX_IEGPIOR_LSB] = STMPE1601_REG_INT_EN_GPIO_MASK_LSB, [STMPE_IDX_ISGPIOR_MSB] = STMPE1601_REG_INT_STA_GPIO_MSB, @@ -667,6 +668,7 @@ static const u8 stmpe1801_regs[] = { [STMPE_IDX_GPDR_LSB] = STMPE1801_REG_GPIO_SET_DIR_LOW, [STMPE_IDX_GPRER_LSB] = STMPE1801_REG_GPIO_RE_LOW, [STMPE_IDX_GPFER_LSB] = STMPE1801_REG_GPIO_FE_LOW, + [STMPE_IDX_GPPUR_LSB] = STMPE1801_REG_GPIO_PULL_UP_LOW, [STMPE_IDX_IEGPIOR_LSB] = STMPE1801_REG_INT_EN_GPIO_MASK_LOW, [STMPE_IDX_ISGPIOR_LSB] = STMPE1801_REG_INT_STA_GPIO_LOW, }; @@ -750,6 +752,8 @@ static const u8 stmpe24xx_regs[] = { [STMPE_IDX_GPDR_LSB] = STMPE24XX_REG_GPDR_LSB, [STMPE_IDX_GPRER_LSB] = STMPE24XX_REG_GPRER_LSB, [STMPE_IDX_GPFER_LSB] = STMPE24XX_REG_GPFER_LSB, + [STMPE_IDX_GPPUR_LSB] = STMPE24XX_REG_GPPUR_LSB, + [STMPE_IDX_GPPDR_LSB] = STMPE24XX_REG_GPPDR_LSB, [STMPE_IDX_GPAFR_U_MSB] = STMPE24XX_REG_GPAFR_U_MSB, [STMPE_IDX_IEGPIOR_LSB] = STMPE24XX_REG_IEGPIOR_LSB, [STMPE_IDX_ISGPIOR_MSB] = STMPE24XX_REG_ISGPIOR_MSB, diff --git a/drivers/mfd/stmpe.h b/drivers/mfd/stmpe.h index 2d045f26f193..e00710b63932 100644 --- a/drivers/mfd/stmpe.h +++ b/drivers/mfd/stmpe.h @@ -188,6 +188,7 @@ int stmpe_remove(struct stmpe *stmpe); #define STMPE1601_REG_GPIO_ED_MSB 0x8A #define STMPE1601_REG_GPIO_RE_LSB 0x8D #define STMPE1601_REG_GPIO_FE_LSB 0x8F +#define STMPE1601_REG_GPIO_PU_LSB 0x91 #define STMPE1601_REG_GPIO_AF_U_MSB 0x92 #define STMPE1601_SYS_CTRL_ENABLE_GPIO (1 << 3) @@ -276,6 +277,8 @@ int stmpe_remove(struct stmpe *stmpe); #define STMPE24XX_REG_GPEDR_MSB 0x8C #define STMPE24XX_REG_GPRER_LSB 0x91 #define STMPE24XX_REG_GPFER_LSB 0x94 +#define STMPE24XX_REG_GPPUR_LSB 0x97 +#define STMPE24XX_REG_GPPDR_LSB 0x9a #define STMPE24XX_REG_GPAFR_U_MSB 0x9B #define STMPE24XX_SYS_CTRL_ENABLE_GPIO (1 << 3) diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index 575a86c7fcbd..cc0deb72e46b 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -50,6 +50,8 @@ enum { STMPE_IDX_GPEDR_MSB, STMPE_IDX_GPRER_LSB, STMPE_IDX_GPFER_LSB, + STMPE_IDX_GPPUR_LSB, + STMPE_IDX_GPPDR_LSB, STMPE_IDX_GPAFR_U_MSB, STMPE_IDX_IEGPIOR_LSB, STMPE_IDX_ISGPIOR_LSB, -- cgit v1.2.3-71-gd317 From a4164863e150c4991d2ac965e3fc52f9d8df3d7e Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 3 Nov 2014 16:51:26 -0800 Subject: Input: stmpe - enforce device tree only mode The STMPE keypad controller is only used with device tree configured systems, so force the configuration to come from device tree only, and now actually get the rows and cols from the device tree too. Signed-off-by: Linus Walleij Acked-by: Lee Jones Signed-off-by: Dmitry Torokhov --- .../devicetree/bindings/input/stmpe-keypad.txt | 2 + drivers/input/keyboard/Kconfig | 1 + drivers/input/keyboard/stmpe-keypad.c | 104 +++++++++------------ include/linux/mfd/stmpe.h | 20 ---- 4 files changed, 48 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/input/stmpe-keypad.txt b/Documentation/devicetree/bindings/input/stmpe-keypad.txt index 1b97222e8a0b..12bb771d66d4 100644 --- a/Documentation/devicetree/bindings/input/stmpe-keypad.txt +++ b/Documentation/devicetree/bindings/input/stmpe-keypad.txt @@ -8,6 +8,8 @@ Optional properties: - debounce-interval : Debouncing interval time in milliseconds - st,scan-count : Scanning cycles elapsed before key data is updated - st,no-autorepeat : If specified device will not autorepeat + - keypad,num-rows : See ./matrix-keymap.txt + - keypad,num-columns : See ./matrix-keymap.txt Example: diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 96ee26c555e0..a5d9b3f3c871 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -559,6 +559,7 @@ config KEYBOARD_SH_KEYSC config KEYBOARD_STMPE tristate "STMPE keypad support" depends on MFD_STMPE + depends on OF select INPUT_MATRIXKMAP help Say Y here if you want to use the keypad controller on STMPE I/O diff --git a/drivers/input/keyboard/stmpe-keypad.c b/drivers/input/keyboard/stmpe-keypad.c index c6727dda68f2..8d1e7af3c5b1 100644 --- a/drivers/input/keyboard/stmpe-keypad.c +++ b/drivers/input/keyboard/stmpe-keypad.c @@ -45,7 +45,7 @@ #define STMPE_KEYPAD_MAX_ROWS 8 #define STMPE_KEYPAD_MAX_COLS 8 #define STMPE_KEYPAD_ROW_SHIFT 3 -#define STMPE_KEYPAD_KEYMAP_SIZE \ +#define STMPE_KEYPAD_KEYMAP_MAX_SIZE \ (STMPE_KEYPAD_MAX_ROWS * STMPE_KEYPAD_MAX_COLS) /** @@ -99,16 +99,30 @@ static const struct stmpe_keypad_variant stmpe_keypad_variants[] = { }, }; +/** + * struct stmpe_keypad - STMPE keypad state container + * @stmpe: pointer to parent STMPE device + * @input: spawned input device + * @variant: STMPE variant + * @debounce_ms: debounce interval, in ms. Maximum is + * %STMPE_KEYPAD_MAX_DEBOUNCE. + * @scan_count: number of key scanning cycles to confirm key data. + * Maximum is %STMPE_KEYPAD_MAX_SCAN_COUNT. + * @no_autorepeat: disable key autorepeat + * @rows: bitmask for the rows + * @cols: bitmask for the columns + * @keymap: the keymap + */ struct stmpe_keypad { struct stmpe *stmpe; struct input_dev *input; const struct stmpe_keypad_variant *variant; - const struct stmpe_keypad_platform_data *plat; - + unsigned int debounce_ms; + unsigned int scan_count; + bool no_autorepeat; unsigned int rows; unsigned int cols; - - unsigned short keymap[STMPE_KEYPAD_KEYMAP_SIZE]; + unsigned short keymap[STMPE_KEYPAD_KEYMAP_MAX_SIZE]; }; static int stmpe_keypad_read_data(struct stmpe_keypad *keypad, u8 *data) @@ -208,15 +222,14 @@ static int stmpe_keypad_altfunc_init(struct stmpe_keypad *keypad) static int stmpe_keypad_chip_init(struct stmpe_keypad *keypad) { - const struct stmpe_keypad_platform_data *plat = keypad->plat; const struct stmpe_keypad_variant *variant = keypad->variant; struct stmpe *stmpe = keypad->stmpe; int ret; - if (plat->debounce_ms > STMPE_KEYPAD_MAX_DEBOUNCE) + if (keypad->debounce_ms > STMPE_KEYPAD_MAX_DEBOUNCE) return -EINVAL; - if (plat->scan_count > STMPE_KEYPAD_MAX_SCAN_COUNT) + if (keypad->scan_count > STMPE_KEYPAD_MAX_SCAN_COUNT) return -EINVAL; ret = stmpe_enable(stmpe, STMPE_BLOCK_KEYPAD); @@ -245,7 +258,7 @@ static int stmpe_keypad_chip_init(struct stmpe_keypad *keypad) ret = stmpe_set_bits(stmpe, STMPE_KPC_CTRL_MSB, STMPE_KPC_CTRL_MSB_SCAN_COUNT, - plat->scan_count << 4); + keypad->scan_count << 4); if (ret < 0) return ret; @@ -253,17 +266,18 @@ static int stmpe_keypad_chip_init(struct stmpe_keypad *keypad) STMPE_KPC_CTRL_LSB_SCAN | STMPE_KPC_CTRL_LSB_DEBOUNCE, STMPE_KPC_CTRL_LSB_SCAN | - (plat->debounce_ms << 1)); + (keypad->debounce_ms << 1)); } -static void stmpe_keypad_fill_used_pins(struct stmpe_keypad *keypad) +static void stmpe_keypad_fill_used_pins(struct stmpe_keypad *keypad, + u32 used_rows, u32 used_cols) { int row, col; - for (row = 0; row < STMPE_KEYPAD_MAX_ROWS; row++) { - for (col = 0; col < STMPE_KEYPAD_MAX_COLS; col++) { + for (row = 0; row < used_rows; row++) { + for (col = 0; col < used_cols; col++) { int code = MATRIX_SCAN_CODE(row, col, - STMPE_KEYPAD_ROW_SHIFT); + STMPE_KEYPAD_ROW_SHIFT); if (keypad->keymap[code] != KEY_RESERVED) { keypad->rows |= 1 << row; keypad->cols |= 1 << col; @@ -272,51 +286,17 @@ static void stmpe_keypad_fill_used_pins(struct stmpe_keypad *keypad) } } -#ifdef CONFIG_OF -static const struct stmpe_keypad_platform_data * -stmpe_keypad_of_probe(struct device *dev) -{ - struct device_node *np = dev->of_node; - struct stmpe_keypad_platform_data *plat; - - if (!np) - return ERR_PTR(-ENODEV); - - plat = devm_kzalloc(dev, sizeof(*plat), GFP_KERNEL); - if (!plat) - return ERR_PTR(-ENOMEM); - - of_property_read_u32(np, "debounce-interval", &plat->debounce_ms); - of_property_read_u32(np, "st,scan-count", &plat->scan_count); - - plat->no_autorepeat = of_property_read_bool(np, "st,no-autorepeat"); - - return plat; -} -#else -static inline const struct stmpe_keypad_platform_data * -stmpe_keypad_of_probe(struct device *dev) -{ - return ERR_PTR(-EINVAL); -} -#endif - static int stmpe_keypad_probe(struct platform_device *pdev) { struct stmpe *stmpe = dev_get_drvdata(pdev->dev.parent); - const struct stmpe_keypad_platform_data *plat; + struct device_node *np = pdev->dev.of_node; struct stmpe_keypad *keypad; struct input_dev *input; + u32 rows; + u32 cols; int error; int irq; - plat = stmpe->pdata->keypad; - if (!plat) { - plat = stmpe_keypad_of_probe(&pdev->dev); - if (IS_ERR(plat)) - return PTR_ERR(plat); - } - irq = platform_get_irq(pdev, 0); if (irq < 0) return irq; @@ -326,6 +306,13 @@ static int stmpe_keypad_probe(struct platform_device *pdev) if (!keypad) return -ENOMEM; + keypad->stmpe = stmpe; + keypad->variant = &stmpe_keypad_variants[stmpe->partnum]; + + of_property_read_u32(np, "debounce-interval", &keypad->debounce_ms); + of_property_read_u32(np, "st,scan-count", &keypad->scan_count); + keypad->no_autorepeat = of_property_read_bool(np, "st,no-autorepeat"); + input = devm_input_allocate_device(&pdev->dev); if (!input) return -ENOMEM; @@ -334,23 +321,22 @@ static int stmpe_keypad_probe(struct platform_device *pdev) input->id.bustype = BUS_I2C; input->dev.parent = &pdev->dev; - error = matrix_keypad_build_keymap(plat->keymap_data, NULL, - STMPE_KEYPAD_MAX_ROWS, - STMPE_KEYPAD_MAX_COLS, + error = matrix_keypad_parse_of_params(&pdev->dev, &rows, &cols); + if (error) + return error; + + error = matrix_keypad_build_keymap(NULL, NULL, rows, cols, keypad->keymap, input); if (error) return error; input_set_capability(input, EV_MSC, MSC_SCAN); - if (!plat->no_autorepeat) + if (!keypad->no_autorepeat) __set_bit(EV_REP, input->evbit); - stmpe_keypad_fill_used_pins(keypad); + stmpe_keypad_fill_used_pins(keypad, rows, cols); - keypad->stmpe = stmpe; - keypad->plat = plat; keypad->input = input; - keypad->variant = &stmpe_keypad_variants[stmpe->partnum]; error = stmpe_keypad_chip_init(keypad); if (error < 0) diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index cc0deb72e46b..f742b6717d52 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -115,24 +115,6 @@ extern int stmpe_set_altfunc(struct stmpe *stmpe, u32 pins, extern int stmpe_enable(struct stmpe *stmpe, unsigned int blocks); extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks); -struct matrix_keymap_data; - -/** - * struct stmpe_keypad_platform_data - STMPE keypad platform data - * @keymap_data: key map table and size - * @debounce_ms: debounce interval, in ms. Maximum is - * %STMPE_KEYPAD_MAX_DEBOUNCE. - * @scan_count: number of key scanning cycles to confirm key data. - * Maximum is %STMPE_KEYPAD_MAX_SCAN_COUNT. - * @no_autorepeat: disable key autorepeat - */ -struct stmpe_keypad_platform_data { - const struct matrix_keymap_data *keymap_data; - unsigned int debounce_ms; - unsigned int scan_count; - bool no_autorepeat; -}; - #define STMPE_GPIO_NOREQ_811_TOUCH (0xf0) /** @@ -201,7 +183,6 @@ struct stmpe_ts_platform_data { * @irq_gpio: gpio number over which irq will be requested (significant only if * irq_over_gpio is true) * @gpio: GPIO-specific platform data - * @keypad: keypad-specific platform data * @ts: touchscreen-specific platform data */ struct stmpe_platform_data { @@ -214,7 +195,6 @@ struct stmpe_platform_data { int autosleep_timeout; struct stmpe_gpio_platform_data *gpio; - struct stmpe_keypad_platform_data *keypad; struct stmpe_ts_platform_data *ts; }; -- cgit v1.2.3-71-gd317 From 62c4cf97e82cf79446642e599d155884f600cf17 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Tue, 16 Dec 2014 01:52:08 -0500 Subject: cpuidle / ACPI: remove unused CPUIDLE_FLAG_TIME_INVALID CPUIDLE_FLAG_TIME_INVALID is no longer checked by menu or ladder cpuidle governors, so don't bother setting or defining it. It was originally invented to account for the fact that acpi_safe_halt() enables interrupts to invoke HLT. That would allow interrupt service routines to be included in the last_idle duration measurements made in cpuidle_enter_state(), potentially returning a duration much larger than reality. But menu and ladder can gracefully handle erroneously large duration intervals without checking for CPUIDLE_FLAG_TIME_INVALID. Further, if they don't check CPUIDLE_FLAG_TIME_INVALID, they can also benefit from the instances when the duration interval is not erroneously large. Signed-off-by: Len Brown Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/acpi/processor_idle.c | 2 -- include/linux/cpuidle.h | 3 --- 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 380b4b43f361..7afba40e350e 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -985,8 +985,6 @@ static int acpi_processor_setup_cpuidle_states(struct acpi_processor *pr) state->flags = 0; switch (cx->type) { case ACPI_STATE_C1: - if (cx->entry_method != ACPI_CSTATE_FFH) - state->flags |= CPUIDLE_FLAG_TIME_INVALID; state->enter = acpi_idle_enter_c1; state->enter_dead = acpi_idle_play_dead; diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index a07e087f54b2..ab70f3bc44ad 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -53,7 +53,6 @@ struct cpuidle_state { }; /* Idle State Flags */ -#define CPUIDLE_FLAG_TIME_INVALID (0x01) /* is residency time measurable? */ #define CPUIDLE_FLAG_COUPLED (0x02) /* state applies to multiple cpus */ #define CPUIDLE_FLAG_TIMER_STOP (0x04) /* timer is stopped on this state */ @@ -89,8 +88,6 @@ DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev); /** * cpuidle_get_last_residency - retrieves the last state's residency time * @dev: the target CPU - * - * NOTE: this value is invalid if CPUIDLE_FLAG_TIME_INVALID is set */ static inline int cpuidle_get_last_residency(struct cpuidle_device *dev) { -- cgit v1.2.3-71-gd317 From 7496fcbe8a643097efc061160e1c3b65ee2fa350 Mon Sep 17 00:00:00 2001 From: Amit Daniel Kachhap Date: Mon, 15 Dec 2014 09:08:59 +0530 Subject: PM / Domains: Export of_genpd_get_from_provider function This function looks up a PM domain form the provider. This will be useful to add parent/child domain relationship from the SoC specific code. The caller of the function must make sure that PM domain provider is already registered. Reviewed-by: Ulf Hansson Signed-off-by: Amit Daniel Kachhap Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 3 ++- include/linux/pm_domain.h | 8 ++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 5d7b7548873a..1bd119efaac1 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2108,7 +2108,7 @@ EXPORT_SYMBOL_GPL(of_genpd_del_provider); * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR() * on failure. */ -static struct generic_pm_domain *of_genpd_get_from_provider( +struct generic_pm_domain *of_genpd_get_from_provider( struct of_phandle_args *genpdspec) { struct generic_pm_domain *genpd = ERR_PTR(-ENOENT); @@ -2128,6 +2128,7 @@ static struct generic_pm_domain *of_genpd_get_from_provider( return genpd; } +EXPORT_SYMBOL_GPL(of_genpd_get_from_provider); /** * genpd_dev_pm_detach - Detach a device from its PM domain. diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 1dd6c7f64166..ba7ca5468a7b 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -275,6 +275,8 @@ typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args, int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate, void *data); void of_genpd_del_provider(struct device_node *np); +struct generic_pm_domain *of_genpd_get_from_provider( + struct of_phandle_args *genpdspec); struct generic_pm_domain *__of_genpd_xlate_simple( struct of_phandle_args *genpdspec, @@ -292,6 +294,12 @@ static inline int __of_genpd_add_provider(struct device_node *np, } static inline void of_genpd_del_provider(struct device_node *np) {} +static inline struct generic_pm_domain *of_genpd_get_from_provider( + struct of_phandle_args *genpdspec) +{ + return NULL; +} + #define __of_genpd_xlate_simple NULL #define __of_genpd_xlate_onecell NULL -- cgit v1.2.3-71-gd317 From 503ccc3fec4a56cdcfedc507cd1ea0d85e1fbfa2 Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Wed, 17 Dec 2014 11:11:24 +0000 Subject: thermal: cpu_cooling: return ERR_PTR() for !CPU_THERMAL or !THERMAL_OF The documentation of of_cpufreq_cooling_register() and cpufreq_cooling_register() say that they return ERR_PTR() on error. Accordingly, callers only check for IS_ERR(). Therefore, make them return ERR_PTR(-ENOSYS) as is customary in the kernel when config options are missing. Cc: Zhang Rui Cc: Eduardo Valentin Signed-off-by: Javi Merino Signed-off-by: Eduardo Valentin --- include/linux/cpu_cooling.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index c303d383def1..bd955270d5aa 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -50,7 +50,7 @@ static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, const struct cpumask *clip_cpus) { - return NULL; + return ERR_PTR(-ENOSYS); } #endif @@ -65,13 +65,13 @@ unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq); static inline struct thermal_cooling_device * cpufreq_cooling_register(const struct cpumask *clip_cpus) { - return NULL; + return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, const struct cpumask *clip_cpus) { - return NULL; + return ERR_PTR(-ENOSYS); } static inline void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) -- cgit v1.2.3-71-gd317 From b4c6a028774bcf3f20ed1e66c27a05aa51a8cf55 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 19 Dec 2014 17:54:14 -0700 Subject: blk-mq: Export freeze/unfreeze functions Let drivers prevent entering a queue that isn't available. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- block/blk-mq.c | 6 ++++-- include/linux/blk-mq.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index bfe0f1f9cfa0..97ebb84b5633 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -107,7 +107,7 @@ static void blk_mq_usage_counter_release(struct percpu_ref *ref) wake_up_all(&q->mq_freeze_wq); } -static void blk_mq_freeze_queue_start(struct request_queue *q) +void blk_mq_freeze_queue_start(struct request_queue *q) { bool freeze; @@ -120,6 +120,7 @@ static void blk_mq_freeze_queue_start(struct request_queue *q) blk_mq_run_queues(q, false); } } +EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start); static void blk_mq_freeze_queue_wait(struct request_queue *q) { @@ -136,7 +137,7 @@ void blk_mq_freeze_queue(struct request_queue *q) blk_mq_freeze_queue_wait(q); } -static void blk_mq_unfreeze_queue(struct request_queue *q) +void blk_mq_unfreeze_queue(struct request_queue *q) { bool wake; @@ -149,6 +150,7 @@ static void blk_mq_unfreeze_queue(struct request_queue *q) wake_up_all(&q->mq_freeze_wq); } } +EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8aded9ab2e4e..3b43f509432c 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -212,6 +212,8 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn, void *priv); +void blk_mq_unfreeze_queue(struct request_queue *q); +void blk_mq_freeze_queue_start(struct request_queue *q); /* * Driver command data is immediately after the request. So subtract request -- cgit v1.2.3-71-gd317 From 0bc09f9cdc589e0b54724096138996a00b19babb Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Tue, 16 Dec 2014 14:52:50 +0530 Subject: phy: phy-ti-pipe3: fix inconsistent enumeration of PCIe gen2 cards Prior to DRA74x silicon rev 1.1, pcie_pcs register bits 8-15 and bits 16-23 were used to configure RC delay count for phy1 and phy2 respectively. phyid was used as index to distinguish the phys and to configure the delay values appropriately. As of DRA74x silicon rev 1.1, pcie_pcs register definition has changed. Bits 16-23 are used to configure delay values for *both* phy1 and phy2. Hence phyid is no longer required. So, drop id field from ti_pipe3 structure and its subsequent references for configuring pcie_pcs register. Also, pcie_pcs register now needs to be configured with delay value of 0x96 at bit positions 16-23. See register description of CTRL_CORE_PCIE_PCS in ARM572x TRM, SPRUHZ6, October 2014, section 18.5.2.2, table 18-1804. This is needed to ensure Gen2 cards are enumerated consistently. DRA72x silicon behaves same way as DRA74x rev 1.1 as far as this functionality is considered. Test results on DRA74x and DRA72x EVMs: Before patch ------------ DRA74x ES 1.0: Gen1 cards work, Gen2 cards do not work (expected result due to silicon errata) DRA74x ES 1.1: Gen1 cards work, Gen2 cards do not work sometimes due to incorrect programming of register DRA72x: Gen1 cards work, Gen2 cards do not work sometimes due to incorrect programming of register After patch ----------- DRA74x ES 1.0: Gen1 cards work, Gen2 cards do not work (expected result due to silicon errata) DRA74x ES 1.1: Gen1 cards work, Gen2 cards work consistently. DRA72x: Gen1 and Gen2 cards enumerate consistently. Signed-off-by: Vignesh R Signed-off-by: Kishon Vijay Abraham I --- drivers/phy/phy-omap-control.c | 7 +++---- drivers/phy/phy-ti-pipe3.c | 10 ++++++---- include/linux/phy/omap_control_phy.h | 6 +++--- 3 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/phy/phy-omap-control.c b/drivers/phy/phy-omap-control.c index c96e8183a8ff..efe724f97e02 100644 --- a/drivers/phy/phy-omap-control.c +++ b/drivers/phy/phy-omap-control.c @@ -29,10 +29,9 @@ /** * omap_control_pcie_pcs - set the PCS delay count * @dev: the control module device - * @id: index of the pcie PHY (should be 1 or 2) * @delay: 8 bit delay value */ -void omap_control_pcie_pcs(struct device *dev, u8 id, u8 delay) +void omap_control_pcie_pcs(struct device *dev, u8 delay) { u32 val; struct omap_control_phy *control_phy; @@ -55,8 +54,8 @@ void omap_control_pcie_pcs(struct device *dev, u8 id, u8 delay) val = readl(control_phy->pcie_pcs); val &= ~(OMAP_CTRL_PCIE_PCS_MASK << - (id * OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT)); - val |= delay << (id * OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT); + OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT); + val |= (delay << OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT); writel(val, control_phy->pcie_pcs); } EXPORT_SYMBOL_GPL(omap_control_pcie_pcs); diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c index 1387b4d4afe3..465de2c800f2 100644 --- a/drivers/phy/phy-ti-pipe3.c +++ b/drivers/phy/phy-ti-pipe3.c @@ -82,7 +82,6 @@ struct ti_pipe3 { struct clk *refclk; struct clk *div_clk; struct pipe3_dpll_map *dpll_map; - u8 id; }; static struct pipe3_dpll_map dpll_map_usb[] = { @@ -217,8 +216,13 @@ static int ti_pipe3_init(struct phy *x) u32 val; int ret = 0; + /* + * Set pcie_pcs register to 0x96 for proper functioning of phy + * as recommended in AM572x TRM SPRUHZ6, section 18.5.2.2, table + * 18-1804. + */ if (of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-pcie")) { - omap_control_pcie_pcs(phy->control_dev, phy->id, 0xF1); + omap_control_pcie_pcs(phy->control_dev, 0x96); return 0; } @@ -347,8 +351,6 @@ static int ti_pipe3_probe(struct platform_device *pdev) } if (of_device_is_compatible(node, "ti,phy-pipe3-pcie")) { - if (of_property_read_u8(node, "id", &phy->id) < 0) - phy->id = 1; clk = devm_clk_get(phy->dev, "dpll_ref"); if (IS_ERR(clk)) { diff --git a/include/linux/phy/omap_control_phy.h b/include/linux/phy/omap_control_phy.h index e9e6cfbfbb58..eb7d4a135a9e 100644 --- a/include/linux/phy/omap_control_phy.h +++ b/include/linux/phy/omap_control_phy.h @@ -66,7 +66,7 @@ enum omap_control_usb_mode { #define OMAP_CTRL_PIPE3_PHY_TX_RX_POWEROFF 0x0 #define OMAP_CTRL_PCIE_PCS_MASK 0xff -#define OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT 0x8 +#define OMAP_CTRL_PCIE_PCS_DELAY_COUNT_SHIFT 16 #define OMAP_CTRL_USB2_PHY_PD BIT(28) @@ -79,7 +79,7 @@ enum omap_control_usb_mode { void omap_control_phy_power(struct device *dev, int on); void omap_control_usb_set_mode(struct device *dev, enum omap_control_usb_mode mode); -void omap_control_pcie_pcs(struct device *dev, u8 id, u8 delay); +void omap_control_pcie_pcs(struct device *dev, u8 delay); #else static inline void omap_control_phy_power(struct device *dev, int on) @@ -91,7 +91,7 @@ static inline void omap_control_usb_set_mode(struct device *dev, { } -static inline void omap_control_pcie_pcs(struct device *dev, u8 id, u8 delay) +static inline void omap_control_pcie_pcs(struct device *dev, u8 delay) { } #endif -- cgit v1.2.3-71-gd317 From 5f35227ea34bb616c436d9da47fc325866c428f3 Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Tue, 23 Dec 2014 22:37:26 -0800 Subject: net: Generalize ndo_gso_check to ndo_features_check GSO isn't the only offload feature with restrictions that potentially can't be expressed with the current features mechanism. Checksum is another although it's a general issue that could in theory apply to anything. Even if it may be possible to implement these restrictions in other ways, it can result in duplicate code or inefficient per-packet behavior. This generalizes ndo_gso_check so that drivers can remove any features that don't make sense for a given packet, similar to netif_skb_features(). It also converts existing driver restrictions to the new format, completing the work that was done to support tunnel protocols since the issues apply to checksums as well. By actually removing features from the set that are used to do offloading, it solves another problem with the existing interface. In these cases, GSO would run with the original set of features and not do anything because it appears that segmentation is not required. CC: Tom Herbert CC: Joe Stringer CC: Eric Dumazet CC: Hayes Wang Signed-off-by: Jesse Gross Acked-by: Tom Herbert Fixes: 04ffcb255f22 ("net: Add ndo_gso_check") Tested-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 8 ++++--- drivers/net/ethernet/emulex/benet/be_main.c | 8 ++++--- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 10 +++++---- drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 8 ++++--- include/linux/netdevice.h | 20 +++++++++-------- include/net/vxlan.h | 28 ++++++++++++++++++++---- net/core/dev.c | 23 +++++++++++-------- 7 files changed, 70 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 9f5e38769a29..72eef9fc883e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12553,9 +12553,11 @@ static int bnx2x_get_phys_port_id(struct net_device *netdev, return 0; } -static bool bnx2x_gso_check(struct sk_buff *skb, struct net_device *dev) +static netdev_features_t bnx2x_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) { - return vxlan_gso_check(skb); + return vxlan_features_check(skb, features); } static const struct net_device_ops bnx2x_netdev_ops = { @@ -12589,7 +12591,7 @@ static const struct net_device_ops bnx2x_netdev_ops = { #endif .ndo_get_phys_port_id = bnx2x_get_phys_port_id, .ndo_set_vf_link_state = bnx2x_set_vf_link_state, - .ndo_gso_check = bnx2x_gso_check, + .ndo_features_check = bnx2x_features_check, }; static int bnx2x_set_coherency_mask(struct bnx2x *bp) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 196073110e32..41a0a5498da7 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4459,9 +4459,11 @@ done: adapter->vxlan_port_count--; } -static bool be_gso_check(struct sk_buff *skb, struct net_device *dev) +static netdev_features_t be_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) { - return vxlan_gso_check(skb); + return vxlan_features_check(skb, features); } #endif @@ -4492,7 +4494,7 @@ static const struct net_device_ops be_netdev_ops = { #ifdef CONFIG_BE2NET_VXLAN .ndo_add_vxlan_port = be_add_vxlan_port, .ndo_del_vxlan_port = be_del_vxlan_port, - .ndo_gso_check = be_gso_check, + .ndo_features_check = be_features_check, #endif }; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 190cbd931f6b..d0d6dc1b8e46 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2365,9 +2365,11 @@ static void mlx4_en_del_vxlan_port(struct net_device *dev, queue_work(priv->mdev->workqueue, &priv->vxlan_del_task); } -static bool mlx4_en_gso_check(struct sk_buff *skb, struct net_device *dev) +static netdev_features_t mlx4_en_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) { - return vxlan_gso_check(skb); + return vxlan_features_check(skb, features); } #endif @@ -2400,7 +2402,7 @@ static const struct net_device_ops mlx4_netdev_ops = { #ifdef CONFIG_MLX4_EN_VXLAN .ndo_add_vxlan_port = mlx4_en_add_vxlan_port, .ndo_del_vxlan_port = mlx4_en_del_vxlan_port, - .ndo_gso_check = mlx4_en_gso_check, + .ndo_features_check = mlx4_en_features_check, #endif }; @@ -2434,7 +2436,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { #ifdef CONFIG_MLX4_EN_VXLAN .ndo_add_vxlan_port = mlx4_en_add_vxlan_port, .ndo_del_vxlan_port = mlx4_en_del_vxlan_port, - .ndo_gso_check = mlx4_en_gso_check, + .ndo_features_check = mlx4_en_features_check, #endif }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 1aa25b13ace1..9929b97cfb36 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -505,9 +505,11 @@ static void qlcnic_del_vxlan_port(struct net_device *netdev, adapter->flags |= QLCNIC_DEL_VXLAN_PORT; } -static bool qlcnic_gso_check(struct sk_buff *skb, struct net_device *dev) +static netdev_features_t qlcnic_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) { - return vxlan_gso_check(skb); + return vxlan_features_check(skb, features); } #endif @@ -532,7 +534,7 @@ static const struct net_device_ops qlcnic_netdev_ops = { #ifdef CONFIG_QLCNIC_VXLAN .ndo_add_vxlan_port = qlcnic_add_vxlan_port, .ndo_del_vxlan_port = qlcnic_del_vxlan_port, - .ndo_gso_check = qlcnic_gso_check, + .ndo_features_check = qlcnic_features_check, #endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = qlcnic_poll_controller, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c31f74d76ebd..679e6e90aa4c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1012,12 +1012,15 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * Callback to use for xmit over the accelerated station. This * is used in place of ndo_start_xmit on accelerated net * devices. - * bool (*ndo_gso_check) (struct sk_buff *skb, - * struct net_device *dev); + * netdev_features_t (*ndo_features_check) (struct sk_buff *skb, + * struct net_device *dev + * netdev_features_t features); * Called by core transmit path to determine if device is capable of - * performing GSO on a packet. The device returns true if it is - * able to GSO the packet, false otherwise. If the return value is - * false the stack will do software GSO. + * performing offload operations on a given packet. This is to give + * the device an opportunity to implement any restrictions that cannot + * be otherwise expressed by feature flags. The check is called with + * the set of features that the stack has calculated and it returns + * those the driver believes to be appropriate. * * int (*ndo_switch_parent_id_get)(struct net_device *dev, * struct netdev_phys_item_id *psid); @@ -1178,8 +1181,9 @@ struct net_device_ops { struct net_device *dev, void *priv); int (*ndo_get_lock_subclass)(struct net_device *dev); - bool (*ndo_gso_check) (struct sk_buff *skb, - struct net_device *dev); + netdev_features_t (*ndo_features_check) (struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features); #ifdef CONFIG_NET_SWITCHDEV int (*ndo_switch_parent_id_get)(struct net_device *dev, struct netdev_phys_item_id *psid); @@ -3611,8 +3615,6 @@ static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb, netdev_features_t features) { return skb_is_gso(skb) && (!skb_gso_ok(skb, features) || - (dev->netdev_ops->ndo_gso_check && - !dev->netdev_ops->ndo_gso_check(skb, dev)) || unlikely((skb->ip_summed != CHECKSUM_PARTIAL) && (skb->ip_summed != CHECKSUM_UNNECESSARY))); } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 57cccd0052e5..903461aa5644 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -1,6 +1,9 @@ #ifndef __NET_VXLAN_H #define __NET_VXLAN_H 1 +#include +#include +#include #include #include #include @@ -51,16 +54,33 @@ int vxlan_xmit_skb(struct vxlan_sock *vs, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, __be32 vni, bool xnet); -static inline bool vxlan_gso_check(struct sk_buff *skb) +static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, + netdev_features_t features) { - if ((skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) && + u8 l4_hdr = 0; + + if (!skb->encapsulation) + return features; + + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IP): + l4_hdr = ip_hdr(skb)->protocol; + break; + case htons(ETH_P_IPV6): + l4_hdr = ipv6_hdr(skb)->nexthdr; + break; + default: + return features;; + } + + if ((l4_hdr == IPPROTO_UDP) && (skb->inner_protocol_type != ENCAP_TYPE_ETHER || skb->inner_protocol != htons(ETH_P_TEB) || (skb_inner_mac_header(skb) - skb_transport_header(skb) != sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) - return false; + return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); - return true; + return features; } /* IP header + UDP + VXLAN + Ethernet header */ diff --git a/net/core/dev.c b/net/core/dev.c index 0094562b732a..683d493aa1bf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2563,7 +2563,7 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, netdev_features_t netif_skb_features(struct sk_buff *skb) { - const struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev; netdev_features_t features = dev->features; u16 gso_segs = skb_shinfo(skb)->gso_segs; __be16 protocol = skb->protocol; @@ -2571,13 +2571,20 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs) features &= ~NETIF_F_GSO_MASK; + /* If encapsulation offload request, verify we are testing + * hardware encapsulation features instead of standard + * features for the netdev + */ + if (skb->encapsulation) + features &= dev->hw_enc_features; + if (!vlan_tx_tag_present(skb)) { if (unlikely(protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else { - return harmonize_features(skb, features); + goto finalize; } } @@ -2595,6 +2602,11 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); +finalize: + if (dev->netdev_ops->ndo_features_check) + features &= dev->netdev_ops->ndo_features_check(skb, dev, + features); + return harmonize_features(skb, features); } EXPORT_SYMBOL(netif_skb_features); @@ -2665,13 +2677,6 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device if (unlikely(!skb)) goto out_null; - /* If encapsulation offload request, verify we are testing - * hardware encapsulation features instead of standard - * features for the netdev - */ - if (skb->encapsulation) - features &= dev->hw_enc_features; - if (netif_needs_gso(dev, skb, features)) { struct sk_buff *segs; -- cgit v1.2.3-71-gd317 From 023e2cfa36c31b0ad28c159a1bb0d61ff57334c8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 23 Dec 2014 21:00:06 +0100 Subject: netlink/genetlink: pass network namespace to bind/unbind Netlink families can exist in multiple namespaces, and for the most part multicast subscriptions are per network namespace. Thus it only makes sense to have bind/unbind notifications per network namespace. To achieve this, pass the network namespace of a given client socket to the bind/unbind functions. Also do this in generic netlink, and there also make sure that any bind for multicast groups that only exist in init_net is rejected. This isn't really a problem if it is accepted since a client in a different namespace will never receive any notifications from such a group, but it can confuse the family if not rejected (it's also possible to silently (without telling the family) accept it, but it would also have to be ignored on unbind so families that take any kind of action on bind/unbind won't do unnecessary work for invalid clients like that. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/netlink.h | 4 ++-- include/net/genetlink.h | 4 ++-- kernel/audit.c | 2 +- net/netfilter/nfnetlink.c | 2 +- net/netlink/af_netlink.c | 21 +++++++++++---------- net/netlink/af_netlink.h | 8 ++++---- net/netlink/genetlink.c | 12 +++++++----- 7 files changed, 28 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 9e572daa15d5..02fc86d2348e 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -46,8 +46,8 @@ struct netlink_kernel_cfg { unsigned int flags; void (*input)(struct sk_buff *skb); struct mutex *cb_mutex; - int (*bind)(int group); - void (*unbind)(int group); + int (*bind)(struct net *net, int group); + void (*unbind)(struct net *net, int group); bool (*compare)(struct net *net, struct sock *sk); }; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 3ed31e5a445b..84125088c309 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -56,8 +56,8 @@ struct genl_family { void (*post_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); - int (*mcast_bind)(int group); - void (*mcast_unbind)(int group); + int (*mcast_bind)(struct net *net, int group); + void (*mcast_unbind)(struct net *net, int group); struct nlattr ** attrbuf; /* private */ const struct genl_ops * ops; /* private */ const struct genl_multicast_group *mcgrps; /* private */ diff --git a/kernel/audit.c b/kernel/audit.c index f8f203e8018c..aba9d9fadf0c 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1100,7 +1100,7 @@ static void audit_receive(struct sk_buff *skb) } /* Run custom bind function on netlink socket group connect or bind requests. */ -static int audit_bind(int group) +static int audit_bind(struct net *net, int group) { if (!capable(CAP_AUDIT_READ)) return -EPERM; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 13c2e17bbe27..cde4a6702fa3 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -463,7 +463,7 @@ static void nfnetlink_rcv(struct sk_buff *skb) } #ifdef CONFIG_MODULES -static int nfnetlink_bind(int group) +static int nfnetlink_bind(struct net *net, int group) { const struct nfnetlink_subsystem *ss; int type; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f29b63fad932..84ea76ca3f1f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1141,8 +1141,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, struct module *module = NULL; struct mutex *cb_mutex; struct netlink_sock *nlk; - int (*bind)(int group); - void (*unbind)(int group); + int (*bind)(struct net *net, int group); + void (*unbind)(struct net *net, int group); int err = 0; sock->state = SS_UNCONNECTED; @@ -1251,7 +1251,7 @@ static int netlink_release(struct socket *sock) for (i = 0; i < nlk->ngroups; i++) if (test_bit(i, nlk->groups)) - nlk->netlink_unbind(i + 1); + nlk->netlink_unbind(sock_net(sk), i + 1); } kfree(nlk->groups); nlk->groups = NULL; @@ -1418,8 +1418,9 @@ static int netlink_realloc_groups(struct sock *sk) } static void netlink_undo_bind(int group, long unsigned int groups, - struct netlink_sock *nlk) + struct sock *sk) { + struct netlink_sock *nlk = nlk_sk(sk); int undo; if (!nlk->netlink_unbind) @@ -1427,7 +1428,7 @@ static void netlink_undo_bind(int group, long unsigned int groups, for (undo = 0; undo < group; undo++) if (test_bit(undo, &groups)) - nlk->netlink_unbind(undo); + nlk->netlink_unbind(sock_net(sk), undo); } static int netlink_bind(struct socket *sock, struct sockaddr *addr, @@ -1465,10 +1466,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, for (group = 0; group < nlk->ngroups; group++) { if (!test_bit(group, &groups)) continue; - err = nlk->netlink_bind(group); + err = nlk->netlink_bind(net, group); if (!err) continue; - netlink_undo_bind(group, groups, nlk); + netlink_undo_bind(group, groups, sk); return err; } } @@ -1478,7 +1479,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, net, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_undo_bind(nlk->ngroups, groups, nlk); + netlink_undo_bind(nlk->ngroups, groups, sk); return err; } } @@ -2129,7 +2130,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, if (!val || val - 1 >= nlk->ngroups) return -EINVAL; if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) { - err = nlk->netlink_bind(val); + err = nlk->netlink_bind(sock_net(sk), val); if (err) return err; } @@ -2138,7 +2139,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) - nlk->netlink_unbind(val); + nlk->netlink_unbind(sock_net(sk), val); err = 0; break; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index b20a1731759b..f123a88496f8 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -39,8 +39,8 @@ struct netlink_sock { struct mutex *cb_mutex; struct mutex cb_def_mutex; void (*netlink_rcv)(struct sk_buff *skb); - int (*netlink_bind)(int group); - void (*netlink_unbind)(int group); + int (*netlink_bind)(struct net *net, int group); + void (*netlink_unbind)(struct net *net, int group); struct module *module; #ifdef CONFIG_NETLINK_MMAP struct mutex pg_vec_lock; @@ -65,8 +65,8 @@ struct netlink_table { unsigned int groups; struct mutex *cb_mutex; struct module *module; - int (*bind)(int group); - void (*unbind)(int group); + int (*bind)(struct net *net, int group); + void (*unbind)(struct net *net, int group); bool (*compare)(struct net *net, struct sock *sock); int registered; }; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 05bf40bbd189..91566ed36c43 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -983,7 +983,7 @@ static struct genl_multicast_group genl_ctrl_groups[] = { { .name = "notify", }, }; -static int genl_bind(int group) +static int genl_bind(struct net *net, int group) { int i, err; bool found = false; @@ -997,8 +997,10 @@ static int genl_bind(int group) group < f->mcgrp_offset + f->n_mcgrps) { int fam_grp = group - f->mcgrp_offset; - if (f->mcast_bind) - err = f->mcast_bind(fam_grp); + if (!f->netnsok && net != &init_net) + err = -ENOENT; + else if (f->mcast_bind) + err = f->mcast_bind(net, fam_grp); else err = 0; found = true; @@ -1014,7 +1016,7 @@ static int genl_bind(int group) return err; } -static void genl_unbind(int group) +static void genl_unbind(struct net *net, int group) { int i; bool found = false; @@ -1029,7 +1031,7 @@ static void genl_unbind(int group) int fam_grp = group - f->mcgrp_offset; if (f->mcast_unbind) - f->mcast_unbind(fam_grp); + f->mcast_unbind(net, fam_grp); found = true; break; } -- cgit v1.2.3-71-gd317 From 45f87de57f8fad59302fd263dd81ffa4843b5b24 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 29 Dec 2014 20:30:35 +0100 Subject: mm: get rid of radix tree gfp mask for pagecache_get_page Commit 2457aec63745 ("mm: non-atomically mark page accessed during page cache allocation where possible") has added a separate parameter for specifying gfp mask for radix tree allocations. Not only this is less than optimal from the API point of view because it is error prone, it is also buggy currently because grab_cache_page_write_begin is using GFP_KERNEL for radix tree and if fgp_flags doesn't contain FGP_NOFS (mostly controlled by fs by AOP_FLAG_NOFS flag) but the mapping_gfp_mask has __GFP_FS cleared then the radix tree allocation wouldn't obey the restriction and might recurse into filesystem and cause deadlocks. This is the case for most filesystems unfortunately because only ext4 and gfs2 are using AOP_FLAG_NOFS. Let's simply remove radix_gfp_mask parameter because the allocation context is same for both page cache and for the radix tree. Just make sure that the radix tree gets only the sane subset of the mask (e.g. do not pass __GFP_WRITE). Long term it is more preferable to convert remaining users of AOP_FLAG_NOFS to use mapping_gfp_mask instead and simplify this interface even further. Reported-by: Dave Chinner Signed-off-by: Michal Hocko Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 13 ++++++------- mm/filemap.c | 29 ++++++++++++----------------- 2 files changed, 18 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7ea069cd3257..4b3736f7065c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -251,7 +251,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping, #define FGP_NOWAIT 0x00000020 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, - int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask); + int fgp_flags, gfp_t cache_gfp_mask); /** * find_get_page - find and get a page reference @@ -266,13 +266,13 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, static inline struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { - return pagecache_get_page(mapping, offset, 0, 0, 0); + return pagecache_get_page(mapping, offset, 0, 0); } static inline struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset, int fgp_flags) { - return pagecache_get_page(mapping, offset, fgp_flags, 0, 0); + return pagecache_get_page(mapping, offset, fgp_flags, 0); } /** @@ -292,7 +292,7 @@ static inline struct page *find_get_page_flags(struct address_space *mapping, static inline struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) { - return pagecache_get_page(mapping, offset, FGP_LOCK, 0, 0); + return pagecache_get_page(mapping, offset, FGP_LOCK, 0); } /** @@ -319,7 +319,7 @@ static inline struct page *find_or_create_page(struct address_space *mapping, { return pagecache_get_page(mapping, offset, FGP_LOCK|FGP_ACCESSED|FGP_CREAT, - gfp_mask, gfp_mask & GFP_RECLAIM_MASK); + gfp_mask); } /** @@ -340,8 +340,7 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, - mapping_gfp_mask(mapping), - GFP_NOFS); + mapping_gfp_mask(mapping)); } struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); diff --git a/mm/filemap.c b/mm/filemap.c index bd8543c6508f..673e4581a2e5 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1046,8 +1046,7 @@ EXPORT_SYMBOL(find_lock_entry); * @mapping: the address_space to search * @offset: the page index * @fgp_flags: PCG flags - * @cache_gfp_mask: gfp mask to use for the page cache data page allocation - * @radix_gfp_mask: gfp mask to use for radix tree node allocation + * @gfp_mask: gfp mask to use for the page cache data page allocation * * Looks up the page cache slot at @mapping & @offset. * @@ -1056,11 +1055,9 @@ EXPORT_SYMBOL(find_lock_entry); * FGP_ACCESSED: the page will be marked accessed * FGP_LOCK: Page is return locked * FGP_CREAT: If page is not present then a new page is allocated using - * @cache_gfp_mask and added to the page cache and the VM's LRU - * list. If radix tree nodes are allocated during page cache - * insertion then @radix_gfp_mask is used. The page is returned - * locked and with an increased refcount. Otherwise, %NULL is - * returned. + * @gfp_mask and added to the page cache and the VM's LRU + * list. The page is returned locked and with an increased + * refcount. Otherwise, %NULL is returned. * * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even * if the GFP flags specified for FGP_CREAT are atomic. @@ -1068,7 +1065,7 @@ EXPORT_SYMBOL(find_lock_entry); * If there is a page cache page, it is returned with an increased refcount. */ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, - int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask) + int fgp_flags, gfp_t gfp_mask) { struct page *page; @@ -1105,13 +1102,11 @@ no_page: if (!page && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) - cache_gfp_mask |= __GFP_WRITE; - if (fgp_flags & FGP_NOFS) { - cache_gfp_mask &= ~__GFP_FS; - radix_gfp_mask &= ~__GFP_FS; - } + gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) + gfp_mask &= ~__GFP_FS; - page = __page_cache_alloc(cache_gfp_mask); + page = __page_cache_alloc(gfp_mask); if (!page) return NULL; @@ -1122,7 +1117,8 @@ no_page: if (fgp_flags & FGP_ACCESSED) __SetPageReferenced(page); - err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask); + err = add_to_page_cache_lru(page, mapping, offset, + gfp_mask & GFP_RECLAIM_MASK); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -2443,8 +2439,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping, fgp_flags |= FGP_NOFS; page = pagecache_get_page(mapping, index, fgp_flags, - mapping_gfp_mask(mapping), - GFP_KERNEL); + mapping_gfp_mask(mapping)); if (page) wait_for_stable_page(page); -- cgit v1.2.3-71-gd317 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 v1.2.3-71-gd317 From ceb3a16c070c403f5f9ca46b46cf2bb79ea11750 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 3 Jan 2015 15:16:04 -0500 Subject: NFSv4: Cache the NFSv4/v4.1 client owner_id in the struct nfs_client Ensure that we cache the NFSv4/v4.1 client owner_id so that we can verify it when we're doing trunking detection. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4client.c | 1 + fs/nfs/nfs4proc.c | 19 +++++++++++++++---- include/linux/nfs_fs_sb.h | 3 +++ 3 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index d949d0f378ec..6ee9bf69a7a6 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -228,6 +228,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) kfree(clp->cl_serverowner); kfree(clp->cl_serverscope); kfree(clp->cl_implid); + kfree(clp->cl_owner_id); } void nfs4_free_client(struct nfs_client *clp) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e7f8d5ff2581..1fab51682042 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4917,11 +4917,14 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp, } static unsigned int -nfs4_init_nonuniform_client_string(const struct nfs_client *clp, +nfs4_init_nonuniform_client_string(struct nfs_client *clp, char *buf, size_t len) { unsigned int result; + if (clp->cl_owner_id != NULL) + return strlcpy(buf, clp->cl_owner_id, len); + rcu_read_lock(); result = scnprintf(buf, len, "Linux NFSv4.0 %s/%s %s", clp->cl_ipaddr, @@ -4930,24 +4933,32 @@ nfs4_init_nonuniform_client_string(const struct nfs_client *clp, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_PROTO)); rcu_read_unlock(); + clp->cl_owner_id = kstrdup(buf, GFP_KERNEL); return result; } static unsigned int -nfs4_init_uniform_client_string(const struct nfs_client *clp, +nfs4_init_uniform_client_string(struct nfs_client *clp, char *buf, size_t len) { const char *nodename = clp->cl_rpcclient->cl_nodename; + unsigned int result; + + if (clp->cl_owner_id != NULL) + return strlcpy(buf, clp->cl_owner_id, len); if (nfs4_client_id_uniquifier[0] != '\0') - return scnprintf(buf, len, "Linux NFSv%u.%u %s/%s", + result = scnprintf(buf, len, "Linux NFSv%u.%u %s/%s", clp->rpc_ops->version, clp->cl_minorversion, nfs4_client_id_uniquifier, nodename); - return scnprintf(buf, len, "Linux NFSv%u.%u %s", + else + result = scnprintf(buf, len, "Linux NFSv%u.%u %s", clp->rpc_ops->version, clp->cl_minorversion, nodename); + clp->cl_owner_id = kstrdup(buf, GFP_KERNEL); + return result; } /* diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 1e37fbb78f7a..ddea982355f3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -74,6 +74,9 @@ struct nfs_client { /* idmapper */ struct idmap * cl_idmap; + /* Client owner identifier */ + const char * cl_owner_id; + /* Our own IP address, as a null-terminated string. * This is used to generate the mv0 callback address. */ -- cgit v1.2.3-71-gd317 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 v1.2.3-71-gd317 From 17ded320706c6316376059cfbe9dccab32c62b42 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 7 Jan 2015 10:44:04 -0700 Subject: blk-mq: get rid of ->cmd_size in the hardware queue We store it in the tag set, we don't need it in the hardware queue. While removing cmd_size, place ->queue_num further down to avoid a hole on 64-bit archs. It's not used in any fast paths, so we can safely move it. Signed-off-by: Jens Axboe --- block/blk-mq.c | 1 - include/linux/blk-mq.h | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 1a41d7aefbd5..cbd2a55d69b8 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1615,7 +1615,6 @@ static int blk_mq_init_hctx(struct request_queue *q, hctx->queue = q; hctx->queue_num = hctx_idx; hctx->flags = set->flags; - hctx->cmd_size = set->cmd_size; blk_mq_init_cpu_notifier(&hctx->cpu_notifier, blk_mq_hctx_notify, hctx); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 3b43f509432c..d0de259e92b2 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -34,7 +34,6 @@ struct blk_mq_hw_ctx { unsigned long flags; /* BLK_MQ_F_* flags */ struct request_queue *queue; - unsigned int queue_num; struct blk_flush_queue *fq; void *driver_data; @@ -54,7 +53,7 @@ struct blk_mq_hw_ctx { unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; unsigned int numa_node; - unsigned int cmd_size; /* per-request extra data */ + unsigned int queue_num; atomic_t nr_active; -- cgit v1.2.3-71-gd317 From 973c01919bce7e3559b62a856b29211ec5ac325c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 7 Jan 2015 18:55:43 -0700 Subject: blk-mq: Export if requests were started Drivers can iterate over all allocated request tags, but their callback needs a way to know if the driver started the request in the first place. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- block/blk-mq.c | 6 ++++++ include/linux/blk-mq.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index aefed96369dd..ce4811667d36 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -404,6 +404,12 @@ void blk_mq_complete_request(struct request *rq) } EXPORT_SYMBOL(blk_mq_complete_request); +int blk_mq_request_started(struct request *rq) +{ + return test_bit(REQ_ATOM_STARTED, &rq->atomic_flags); +} +EXPORT_SYMBOL_GPL(blk_mq_request_started); + void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d0de259e92b2..addf8a19d806 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -194,6 +194,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index); struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int); +int blk_mq_request_started(struct request *rq); void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, int error); void __blk_mq_end_request(struct request *rq, int error); -- cgit v1.2.3-71-gd317 From c68ed59f534c318716c6189050af3c5ea03b8071 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 7 Jan 2015 18:55:44 -0700 Subject: blk-mq: Let drivers cancel requeue_work Kicking requeued requests will start h/w queues in a work_queue, which may alter the driver's requested state to temporarily stop them. This patch exports a method to cancel the q->requeue_work so a driver can be assured stopped h/w queues won't be started up before it is ready. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- block/blk-mq.c | 6 ++++++ include/linux/blk-mq.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index ce4811667d36..e73a5dd89fc4 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -527,6 +527,12 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head) } EXPORT_SYMBOL(blk_mq_add_to_requeue_list); +void blk_mq_cancel_requeue_work(struct request_queue *q) +{ + cancel_work_sync(&q->requeue_work); +} +EXPORT_SYMBOL_GPL(blk_mq_cancel_requeue_work); + void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_schedule_work(&q->requeue_work); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index addf8a19d806..18684e0bdb8a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -201,6 +201,7 @@ void __blk_mq_end_request(struct request *rq, int error); void blk_mq_requeue_request(struct request *rq); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); +void blk_mq_cancel_requeue_work(struct request_queue *q); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_complete_request(struct request *rq); -- cgit v1.2.3-71-gd317 From 1885b24d23716e09b9c952822b05fd7f68099cdb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 7 Jan 2015 18:55:45 -0700 Subject: blk-mq: Add helper to abort requeued requests Adds a helper function a driver can use to abort requeued requests in case any are pending when h/w queues are being removed. Signed-off-by: Jens Axboe --- block/blk-mq.c | 20 ++++++++++++++++++++ include/linux/blk-mq.h | 1 + 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index e73a5dd89fc4..261ccd89e15d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -539,6 +539,26 @@ void blk_mq_kick_requeue_list(struct request_queue *q) } EXPORT_SYMBOL(blk_mq_kick_requeue_list); +void blk_mq_abort_requeue_list(struct request_queue *q) +{ + unsigned long flags; + LIST_HEAD(rq_list); + + spin_lock_irqsave(&q->requeue_lock, flags); + list_splice_init(&q->requeue_list, &rq_list); + spin_unlock_irqrestore(&q->requeue_lock, flags); + + while (!list_empty(&rq_list)) { + struct request *rq; + + rq = list_first_entry(&rq_list, struct request, queuelist); + list_del_init(&rq->queuelist); + rq->errors = -EIO; + blk_mq_end_request(rq, rq->errors); + } +} +EXPORT_SYMBOL(blk_mq_abort_requeue_list); + static inline bool is_flush_request(struct request *rq, struct blk_flush_queue *fq, unsigned int tag) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 18684e0bdb8a..5735e7130d63 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -203,6 +203,7 @@ void blk_mq_requeue_request(struct request *rq); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head); void blk_mq_cancel_requeue_work(struct request_queue *q); void blk_mq_kick_requeue_list(struct request_queue *q); +void blk_mq_abort_requeue_list(struct request_queue *q); void blk_mq_complete_request(struct request *rq); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); -- cgit v1.2.3-71-gd317 From 5b3f25fc343690cafd3e27431a69a7bdaf9df001 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 7 Jan 2015 18:55:46 -0700 Subject: blk-mq: Allow requests to never expire Some types of requests may be started that are not gauranteed to ever complete. This adds a request flag that a driver can use so mark the request as such. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- block/blk-mq.c | 4 +++- block/blk-timeout.c | 3 +++ include/linux/blk_types.h | 2 ++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 261ccd89e15d..78324a2f0e10 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -619,7 +619,7 @@ void blk_mq_rq_timed_out(struct request *req, bool reserved) break; } } - + static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { @@ -627,6 +627,8 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) return; + if (rq->cmd_flags & REQ_NO_TIMEOUT) + return; if (time_after_eq(jiffies, rq->deadline)) { if (!blk_mark_rq_complete(rq)) diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 56c025894cdf..246dfb16c3d9 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -190,6 +190,9 @@ void blk_add_timer(struct request *req) struct request_queue *q = req->q; unsigned long expiry; + if (req->cmd_flags & REQ_NO_TIMEOUT) + return; + /* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */ if (!q->mq_ops && !q->rq_timed_out_fn) return; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 445d59231bc4..c294e3e25e37 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -190,6 +190,7 @@ enum rq_flag_bits { __REQ_PM, /* runtime pm request */ __REQ_HASHED, /* on IO scheduler merge hash */ __REQ_MQ_INFLIGHT, /* track inflight for MQ */ + __REQ_NO_TIMEOUT, /* requests may never expire */ __REQ_NR_BITS, /* stops here */ }; @@ -243,5 +244,6 @@ enum rq_flag_bits { #define REQ_PM (1ULL << __REQ_PM) #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) +#define REQ_NO_TIMEOUT (1ULL << __REQ_NO_TIMEOUT) #endif /* __LINUX_BLK_TYPES_H */ -- cgit v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 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 v1.2.3-71-gd317 From b5540ce1512eede3bed68ab1e9949df9ad556091 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 5 Dec 2014 19:25:31 +0200 Subject: mmc: sdhci: Disable re-tuning for HS400 Re-tuning for HS400 mode must be done in HS200 mode. Currently there is no support for that. That needs to be reflected in the code. Specifically, if tuning is executed in HS400 mode then return an error, and do not start the tuning timer if HS200 tuning is being done prior to switching to HS400. Note that periodic re-tuning is not expected to be needed for HS400 but re-tuning is still needed after the host controller has lost power. In the case of suspend/resume that is not necessary because the card is fully re-initialised. That just leaves runtime suspend/resume with no support for HS400 re-tuning. Signed-off-by: Adrian Hunter Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci.c | 29 +++++++++++++++++++++++++++++ include/linux/mmc/sdhci.h | 1 + 2 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 5c28c19622e6..398e9e496736 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1878,6 +1878,18 @@ static int sdhci_card_busy(struct mmc_host *mmc) return !(present_state & SDHCI_DATA_LVL_MASK); } +static int sdhci_prepare_hs400_tuning(struct mmc_host *mmc, struct mmc_ios *ios) +{ + struct sdhci_host *host = mmc_priv(mmc); + unsigned long flags; + + spin_lock_irqsave(&host->lock, flags); + host->flags |= SDHCI_HS400_TUNING; + spin_unlock_irqrestore(&host->lock, flags); + + return 0; +} + static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct sdhci_host *host = mmc_priv(mmc); @@ -1886,10 +1898,14 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode) int err = 0; unsigned long flags; unsigned int tuning_count = 0; + bool hs400_tuning; sdhci_runtime_pm_get(host); spin_lock_irqsave(&host->lock, flags); + hs400_tuning = host->flags & SDHCI_HS400_TUNING; + host->flags &= ~SDHCI_HS400_TUNING; + if (host->tuning_mode == SDHCI_TUNING_MODE_1) tuning_count = host->tuning_count; @@ -1901,8 +1917,20 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode) * tuning function has to be executed. */ switch (host->timing) { + /* HS400 tuning is done in HS200 mode */ case MMC_TIMING_MMC_HS400: + err = -EINVAL; + goto out_unlock; + case MMC_TIMING_MMC_HS200: + /* + * Periodic re-tuning for HS400 is not expected to be needed, so + * disable it here. + */ + if (hs400_tuning) + tuning_count = 0; + break; + case MMC_TIMING_UHS_SDR104: break; @@ -2130,6 +2158,7 @@ static const struct mmc_host_ops sdhci_ops = { .hw_reset = sdhci_hw_reset, .enable_sdio_irq = sdhci_enable_sdio_irq, .start_signal_voltage_switch = sdhci_start_signal_voltage_switch, + .prepare_hs400_tuning = sdhci_prepare_hs400_tuning, .execute_tuning = sdhci_execute_tuning, .card_event = sdhci_card_event, .card_busy = sdhci_card_busy, diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 375af80bde7d..f767a0de611f 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -137,6 +137,7 @@ struct sdhci_host { #define SDHCI_SDR104_NEEDS_TUNING (1<<10) /* SDR104/HS200 needs tuning */ #define SDHCI_USING_RETUNING_TIMER (1<<11) /* Host is using a retuning timer for the card */ #define SDHCI_USE_64_BIT_DMA (1<<12) /* Use 64-bit DMA */ +#define SDHCI_HS400_TUNING (1<<13) /* Tuning for HS400 */ unsigned int version; /* SDHCI spec. version */ -- cgit v1.2.3-71-gd317 From 5d632cb70f454ac11158de40d563b08b0cd6e084 Mon Sep 17 00:00:00 2001 From: B Viswanath Date: Mon, 12 Jan 2015 14:46:25 +0530 Subject: net: Corrected the comment describing the ndo operations to reflect the actual prototype for couple of operations Corrected the comment describing the ndo operations to reflect the actual prototype for couple of operations Signed-off-by: B Viswanath Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 679e6e90aa4c..7f794db8e486 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -852,11 +852,11 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * - * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16t vid); + * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device support VLAN filtering this function is called when a * VLAN id is registered. * - * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); + * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device support VLAN filtering this function is called when a * VLAN id is unregistered. * -- cgit v1.2.3-71-gd317 From 43239cbe79fc369f5d2160bd7f69e28b5c50a58c Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 13 Jan 2015 10:46:42 +0100 Subject: kernel: Change ASSIGN_ONCE(val, x) to WRITE_ONCE(x, val) Feedback has shown that WRITE_ONCE(x, val) is easier to use than ASSIGN_ONCE(val,x). There are no in-tree users yet, so lets change it for 3.19. Signed-off-by: Christian Borntraeger Acked-by: Peter Zijlstra Acked-by: Davidlohr Bueso Acked-by: Paul E. McKenney --- include/linux/compiler.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index a1c81f80978e..33063f872ee3 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -215,7 +215,7 @@ static __always_inline void __read_once_size(volatile void *p, void *res, int si } } -static __always_inline void __assign_once_size(volatile void *p, void *res, int size) +static __always_inline void __write_once_size(volatile void *p, void *res, int size) { switch (size) { case 1: *(volatile __u8 *)p = *(__u8 *)res; break; @@ -235,15 +235,15 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of - * READ_ONCE, ASSIGN_ONCE and ACCESS_ONCE (see below), but only when the + * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the * compiler is aware of some particular ordering. One way to make the * compiler aware of ordering is to put the two invocations of READ_ONCE, - * ASSIGN_ONCE or ACCESS_ONCE() in different C statements. + * WRITE_ONCE or ACCESS_ONCE() in different C statements. * * In contrast to ACCESS_ONCE these two macros will also work on aggregate * data types like structs or unions. If the size of the accessed data * type exceeds the word size of the machine (e.g., 32 bits or 64 bits) - * READ_ONCE() and ASSIGN_ONCE() will fall back to memcpy and print a + * READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a * compile-time warning. * * Their two major use cases are: (1) Mediating communication between @@ -257,8 +257,8 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int #define READ_ONCE(x) \ ({ typeof(x) __val; __read_once_size(&x, &__val, sizeof(__val)); __val; }) -#define ASSIGN_ONCE(val, x) \ - ({ typeof(x) __val; __val = val; __assign_once_size(&x, &__val, sizeof(__val)); __val; }) +#define WRITE_ONCE(x, val) \ + ({ typeof(x) __val; __val = val; __write_once_size(&x, &__val, sizeof(__val)); __val; }) #endif /* __KERNEL__ */ -- cgit v1.2.3-71-gd317 From 4ccce02eb31b847dd6bf8486f037ba1db39403c5 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Wed, 14 Jan 2015 16:52:35 +0900 Subject: netdevice: Add missing parentheses in macro For example, one could conceivably call for_each_netdev_in_bond_rcu(condition ? bond1 : bond2, slave) and get an unexpected result. Signed-off-by: Benjamin Poirier Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f794db8e486..52fd8e8694cf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2085,7 +2085,7 @@ extern rwlock_t dev_base_lock; /* Device list lock */ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ for_each_netdev_rcu(&init_net, slave) \ - if (netdev_master_upper_dev_get_rcu(slave) == bond) + if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) static inline struct net_device *next_net_device(struct net_device *dev) -- cgit v1.2.3-71-gd317